system

Abstract

Provide a system. [Solution] A means for receiving stock information and donation amounts sent from evacuation centers and support organizations; a means for storing the received data in a database; The received data will be analyzed using an AI model to predict the shortage of supplies and the amount of donations required. The analysis results will be published on a web page or mobile app, allowing users to check the situation in real time. A system including:

Description

[Technical Field]

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

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

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

[0004] When natural disasters occur, the problem is that supplies and donations are not properly managed, leading to imbalances in distribution. As a result, not enough supplies and funds reach the areas and evacuation centers that need assistance, which can have a significant impact on the lives and safety of disaster victims. Currently, it is difficult for donors to see how much supplies are needed where, or how donations are being used, so there is a need to improve the efficiency and transparency of aid activities. [Means for solving the problem]

[0005] This invention proposes a system that receives supply inventory information and donation amounts sent from evacuation centers and relief organizations and stores this data in a database. This system analyzes the received data using an AI model to predict supply shortages and necessary donation amounts. The analysis results are then published on a web page or mobile app, allowing users to check the situation in real time, thereby improving the efficiency and transparency of relief activities. Furthermore, the system includes a means for centrally managing data sent from evacuation centers and relief organizations via a server, allowing users to identify areas and evacuation centers in need of assistance, and providing instructions for appropriate relief activities. This ensures prompt and appropriate assistance and protects the lives and safety of disaster victims.

[0006] An "evacuation shelter" is a facility or place where people gather temporarily to ensure their safety during natural disasters or other emergencies.

[0007] A "support group" is an organization or group that works to provide assistance to victims of natural disasters.

[0008] "Supplies" is a general term for items and goods necessary for life in evacuation shelters, such as food, water, clothing, and medicine.

[0009] "Inventory information" is data that indicates how much of a particular item is on hand at an evacuation center or aid organization.

[0010] "Amount raised" is the total amount of money raised to carry out relief activities.

[0011] "Receiving" is the act of taking data or information from outside into the system.

[0012] A "database" is a collection of data that is collected, managed, and stored in an organized manner, and is a system that allows access to the data and retrieval of information.

[0013] An "AI model" is a set of algorithms and programs based on artificial intelligence that analyze data and make predictions.

[0014] "Analysis" is the process of using collected data to calculate and understand its content and trends.

[0015] "Forecasting" is the act of estimating future conditions or needs based on current and past data.

[0016] A "web page" is a page of documents or data that can be viewed over the Internet.

[0017] A "mobile app" is a software program that runs on a mobile device, such as a smartphone or tablet.

[0018] "Users" are people or organizations that use this system to obtain information and carry out support activities.

[0019] "Real-time" refers to the processing and display of specific events or data almost simultaneously at the moment they occur.

[0020] "Centralized management" refers to integrating and managing multiple pieces of information and data in one system or location.

[0021] "Support activities" refers to the act of providing necessary supplies and donations to disaster-stricken areas and evacuation centers.

[0022] "Instructions" are guidelines or instructions that clearly show the user what to do next. [Brief explanation of the drawings]

[0023] [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

[0024] 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.

[0025] First, the terms used in the following description will be explained.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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."

[0031] [First embodiment]

[0032] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0033] 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.

[0034] 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).

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] 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."

[0044] This invention is a system for improving the efficiency of managing supplies and donations and providing support when natural disasters occur. Specifically, it receives data from evacuation centers and support organizations, analyzes and predicts using an AI model, and provides the results to users.

[0045] The server first receives stock information and donation amounts sent by evacuation centers and aid organizations. The received data is stored in a database. The server then analyzes the stored data using an AI model to predict which supplies are in short supply in which areas and how much donations are needed.

[0046] The analysis results are made public via a web page or mobile app, allowing users to check the situation in real time and obtain reference information for providing appropriate assistance. For example, if shelter A reports a food shortage, that information is saved in a database in real time and compared and analyzed with data from other shelters and the region. As a result, if a food shortage is predicted not only at shelter A but also at nearby shelter B, that information will be displayed on the web page or app.

[0047] Based on this information, users can decide how much supplies and donations to send to which areas. For example, after checking the food shortage information for shelter A, users can complete the process of sending relief supplies online.

[0048] Consider the following scenario as a concrete example: A major earthquake occurs in a certain area, and several evacuation centers are set up. Evacuation center A sends information that "water stocks are low," and the server receives this data and stores it in a database. By analyzing this data together with other data using an AI model, a "water shortage" is predicted for evacuation center B as well. The results are displayed on a web page or app, and users can view them and make a decision to send relief supplies, including water, to evacuation centers A and B.

[0049] This system makes it possible to accurately grasp where and how much supplies and donations are needed, enabling prompt and appropriate assistance to be provided. As a result, the efficiency and transparency of assistance activities are improved, helping disaster victims.

[0050] The processing flow will be explained below.

[0051] Step 1: Receiving Data

[0052] The server receives information about the inventory of supplies and donation amounts sent by evacuation centers and relief organizations. This information is often received via HTTP POST requests, and may be in JSON format. The server temporarily stores this data in memory.

[0053] Step 2: Save your data

[0054] The server stores the received inventory information and donation amount in a database, including the type of item, the amount in stock, and information about the evacuation center or aid organization that sent it. The information is saved by executing an INSERT query to the database.

[0055] Step 3: Feature extraction

[0056] The server retrieves the stored information from the database and extracts the features necessary for analysis and prediction by the AI ​​model. This includes data such as stock fluctuations of specific supplies and regional aid needs. The server extracts the data using SQL SELECT queries.

[0057] Step 4: Analysis by AI model

[0058] The server trains an AI model (e.g., a linear regression model) based on the extracted features. After training, it analyzes the current data to predict which supplies are in short supply and to what extent, and which areas need assistance. The AI ​​model generates its analysis results.

[0059] Step 5: Formatting the analysis results

[0060] The server then formats the analysis results obtained from the AI ​​model in a user-friendly format, often in JSON or HTML format. The formatted data is then output as a list of supply shortages by region, donation amounts, and so on.

[0061] Step 6: Disclosure

[0062] The server then publishes the formatted analysis results on a web page or mobile app. Using a web framework such as Flask, the analysis results are displayed in real time when the endpoint is accessed. Users can access this information through their browser or app.

[0063] Step 7: Verify the user

[0064] Users can access information and analysis results from evacuation shelters and relief organizations through publicly available web pages and apps. Based on data updated in real time, they can determine where to send aid. After checking the situation at a specific evacuation shelter or area, they can decide on specific actions to take to provide relief.

[0065] Step 8: Implementing the support

[0066] Based on the information they have confirmed, users can send the necessary supplies and donations to the appropriate locations. They can use the online platform to order relief supplies and make donations, and their relief efforts are carried out quickly in a way that meets the needs of the disaster-stricken areas.

[0067] These steps allow the server to receive, store, and analyze data, and then make the information public, allowing users to make decisions in real time to provide appropriate assistance, thereby streamlining assistance activities.

[0068] Example 1

[0069] 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."

[0070] In order to improve the efficiency of managing supplies and donations and providing support when natural disasters occur, it is necessary to grasp the shortage of supplies and the amount of donations needed in real time and carry out appropriate support activities. However, collecting and analyzing data from evacuation centers and support organizations takes time, making it difficult to respond quickly. Furthermore, there are concerns that centralized data management and information provision to users are not being carried out efficiently, which could lead to delays and imbalances in support activities.

[0071] 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.

[0072] In this invention, the server includes means for receiving supply inventory information and donation amounts sent from evacuation shelters and support organizations, means for storing the received data in a relational database, and means for analyzing the received data using a generative model to predict supply shortages and required donation amounts. This makes it possible to quickly and accurately analyze the received data and publish necessary support information in real time. As a result, users can carry out appropriate support activities in a timely manner, improving the efficiency and transparency of support activities.

[0073] "Supply inventory information" is data on the types and quantities of supplies held by evacuation centers and support organizations.

[0074] "Amount raised" is data on the total amount of donations collected by evacuation centers and support organizations.

[0075] "Means of receiving" refers to the technical means for electronically receiving data sent from evacuation centers and support organizations.

[0076] A "relational database" is a data storage system that stores received data and manages it so that it can be later analyzed or referenced.

[0077] A "generative model" is a mathematical model that uses artificial intelligence (AI) to analyze data and predict future shortages and fundraising needs.

[0078] "Means of analysis" are technical means for analyzing data and extracting specific patterns or trends.

[0079] An "internet page" is an online platform viewable through a web browser.

[0080] "Mobile device software" refers to applications that run on mobile devices such as smartphones and tablets.

[0081] "Means for checking the status in real time" refers to technological means that allow users to instantly check the current status of supplies and donations.

[0082] "Means of centralized management" refers to the technical means for aggregating information from multiple data sources and managing it in a single system.

[0083] The "means for providing instructions for carrying out support activities" refers to a technical means for providing a specific action plan or guidance for the user to provide appropriate support.

[0084] The present invention is a system for improving the efficiency of managing supplies and donations and providing support when a natural disaster occurs. Specifically, the system receives data from evacuation centers and support organizations, analyzes and predicts using a generative AI model, and provides the results to users. A specific embodiment of this system is described below.

[0085] The server receives data on supply inventory and donation amounts sent by evacuation centers and aid organizations. The received data is stored in a relational database (e.g., MySQL®). The server then uses generative AI models such as Python's TENSORFLOW® or PyTorch to analyze the stored data and predict which areas are short of which supplies and how much donations are needed. This analysis process also uses data science libraries such as NumPy and Pandas.

[0086] The analysis results are published through a web page with a Node.js-based backend and a React.js-based frontend, or a mobile app using Flutter®, allowing users to check the situation in real time and obtain reference information for providing appropriate support.

[0087] Consider the following scenario as a concrete example: A major earthquake occurs in a certain area, and multiple evacuation centers are set up. Evacuation center A sends information that "water stocks are low," and the server receives this data and stores it in a database. The server analyzes this data together with other data using TensorFlow, and predicts that a similar "water shortage" will occur at evacuation center B. The results are displayed on a web page using React.js or a mobile app developed with Flutter, and users can view them and make decisions about sending relief supplies, including water, to evacuation centers A and B.

[0088] Examples of prompts to input to a generative AI model include:

[0089] "A major earthquake has occurred in the area and water shortages have been reported at shelter A and shelter B. What are the next steps?"

[0090] This system makes it possible to accurately grasp where and how much supplies and donations are needed, enabling prompt and appropriate assistance to be provided. As a result, the efficiency and transparency of assistance activities are improved, helping disaster victims.

[0091] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0092] Step 1:

[0093] The server receives information on stock of supplies and donation amounts sent by evacuation centers and support organizations.

[0094] Input: JSON formatted data sent via HTTP POST request from shelters and aid organizations.

[0095] Specific operation: The server receives data through the API endpoint and extracts JSON data from the body of the HTTP request.

[0096] Data processing and calculation: Parse the received JSON data and extract the necessary fields.

[0097] Output: The extracted data.

[0098] Step 2:

[0099] The server stores the received data in a relational database.

[0100] Input: The data extracted in step 1.

[0101] Specific behavior: The server connects to the database (e.g., MySQL) and generates the appropriate INSERT statements to save the data.

[0102] Data processing and calculation: Convert the received data into SQL format and insert it into the database.

[0103] Output: The records stored in the database.

[0104] Step 3:

[0105] The server uses a generative AI model to analyze the stored data and predict supply shortages and the amount of donations needed.

[0106] Input: Historical and current data stored in a database.

[0107] How it works: The server retrieves data from the database, converts it into a data frame using Pandas, and then inputs the data into a TensorFlow or PyTorch model for analysis.

[0108] Data processing and calculation: The generative model makes predictions based on the data frame.

[0109] Output: Analysis results (e.g., which areas are short of which supplies, and the need for donations).

[0110] Step 4:

[0111] The server publishes the analysis results on an internet page or via software for mobile devices.

[0112] Input: Analysis results obtained in step 3.

[0113] Specific operation: The server provides the analysis results as an API on a Node.js-based backend and sends the data to a frontend using React.js or Flutter.

[0114] Data processing and calculation: The analysis results are converted into JSON format and published at the API endpoint.

[0115] Output: The analytics results displayed on a user-visible web page or mobile app.

[0116] Step 5:

[0117] Users can check the situation in real time via an internet page or software on their mobile device and provide appropriate support.

[0118] Input: Interface based on analysis results.

[0119] What happens: A user browses a webpage or app to find information about a need for assistance, then fills out an online form to arrange for the delivery of supplies.

[0120] Data processing and calculation: The data entered in the form is sent to the server, where it is processed to send relief supplies.

[0121] Output: A confirmation message that the outreach activity was completed.

[0122] (Application example 1)

[0123] 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."

[0124] When a natural disaster occurs, it is difficult to quickly grasp the shortage of supplies at evacuation centers and relief organizations and efficiently manage and provide the necessary relief supplies and donations. While real-time information provision is important for users to carry out relief activities appropriately, conventional systems do not adequately meet this requirement. In particular, there is a lack of means to quickly provide food delivery services, which can lead to delays in food supplies during emergencies.

[0125] 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.

[0126] In this invention, the server includes means for receiving stock information and donation amounts sent from evacuation shelters and support organizations, means for saving the received data in a database, means for analyzing the received data using an AI model to predict the shortage status of supplies and the amount of donations required, means for publishing the analysis results on a web page or mobile app so that users can check the situation in real time, means for users to process relief supplies and donations online, and means for notifying users of shortage information in the event of an emergency. This makes it possible to quickly and accurately grasp the shortage status of supplies at evacuation shelters and support organizations and to efficiently carry out support activities, including food delivery services.

[0127] An "evacuation shelter" is a facility set up during a disaster to temporarily gather victims and ensure their safety.

[0128] "Support groups" are non-profit organizations and groups that provide supplies and donations to support disaster victims and evacuees during disasters and emergencies.

[0129] "Supply inventory information" refers to information about the quantity and types of supplies that evacuation centers and support organizations have on hand.

[0130] "Amount raised" is information indicating the total amount of money raised for support.

[0131] "Means of receiving" refers to the systems and technologies used to receive information sent from evacuation centers and support organizations.

[0132] "Means for storing data in a database" refers to a system for storing received data in an appropriate format so that it can be retrieved as needed.

[0133] "Means of analysis using AI models" refers to means of analyzing received data using artificial intelligence technology and making predictions and decisions.

[0134] "Supply shortage status" is information that indicates the extent to which specific supplies are in short supply during a disaster.

[0135] "Raising Needs" is the monetary amount needed to carry out a particular relief effort.

[0136] "Means of publishing on web pages or mobile apps" refers to the means of providing analysis results and information to users via the Internet.

[0137] "Means that users can use to process online" refers to a system that allows users to process donations and relief supplies via the Internet.

[0138] "Means for notifying shortage information in an emergency" refers to means for quickly conveying information to users when a shortage of supplies occurs during a disaster.

[0139] This invention is a system that improves the efficiency of managing supplies and donations and providing support in the event of a natural disaster. In particular, by applying this system to food delivery services, it can quickly provide food in emergencies.

[0140] 1. System Components

[0141] The system includes the following major components:

[0142] server

[0143] Database

[0144] Mobile Applications

[0145] AI model

[0146] Notification System

[0147] 2. Hardware and Software

[0148] The hardware used in this system includes cloud servers (e.g., AWS (registered trademark), GCP) and smartphones. The following software is used:

[0149] TensorFlow (for AI model analysis)

[0150] REST API (for receiving data)

[0151] Flask / Django (server-side framework)

[0152] Firebase Cloud Messaging (notification system)

[0153] 3. Receipt and storage of data

[0154] The server receives stock information and donation amounts sent from evacuation centers and support organizations via a REST API. The received data is stored in a database, allowing for centralized data management.

[0155] 4. Analysis using AI models

[0156] The stored data is analyzed using an AI model, which uses the TensorFlow library to predict the supply shortage and the amount of donations needed. The analysis results are then stored back in the database.

[0157] 5. Data Disclosure and Notification

[0158] The analysis results are made available to users via a web page and mobile application, and a notification system is activated to send real-time notifications to users in the event of a serious shortage of supplies or an emergency.

[0159] 6. Online Procedures

[0160] Users can donate supplies and funds online through the mobile app, enabling fast and efficient relief efforts.

[0161] 7. Specific Examples

[0162] For example, if a major earthquake occurs in a certain area and shelter A sends information that "water stocks are low," the server receives that data and stores it in a database. Analysis using an AI model predicts a similar "water shortage" at shelter B. The results are displayed on the mobile app, and users can review them and make a decision to send relief supplies, including water, to shelters A and B. In addition, push notifications are sent to users in the event of an emergency.

[0163] 8. Examples of prompts

[0164] An example of a prompt sentence to input to the generative AI model is as follows:

[0165] "Shelter A is running low on food supplies. Please estimate what supplies will be needed and propose specific support."

[0166] Such a system will enable prompt and appropriate support in the event of a disaster, and will enable effective assistance to be provided to victims.

[0167] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0168] Step 1:

[0169] The server receives stock information and donation amounts sent from evacuation centers and support organizations via a REST API. The input data includes the type and quantity of supplies currently held by the evacuation center or support organization, as well as the donation amount. The received data is sent to the server in JSON format or other formats. The received data is temporarily stored in memory.

[0170] Step 2:

[0171] The server stores the received data in a database, typically a relational database such as MySQL or PostgreSQL. Input data includes the shelter ID, type of supplies, quantity, and donation amount. This data is inserted into the appropriate tables and persisted as output data for later analysis.

[0172] Step 3:

[0173] The server inputs the data stored in the database into an AI model for analysis. The AI ​​model, built using the TensorFlow library, predicts the shortage of supplies and the amount of donations needed. The input data indicates the current situation at the evacuation shelter, and the AI ​​model analyzes past data and patterns to generate a prediction. The output data is a prediction of the level of shortage of supplies and the amount of donations needed. The prediction results are then stored back in the database.

[0174] Step 4:

[0175] The server retrieves the analysis results from the database and publishes them on a web page or mobile application. The analysis results are retrieved from the database as input data. These data are converted into an appropriate format (HTML, JSON, etc.) and displayed on the user interface of the web page or mobile application, allowing users to check the situation in real time.

[0176] Step 5:

[0177] The mobile application allows users to process donations and donations online. Users input donation details through the mobile app. The input data includes the type of goods, quantity, recipient, and donation amount. This data is sent to the server and processed appropriately. The server verifies the donation details received and stores the data in a database.

[0178] Step 6:

[0179] The server notifies users of missing information in an emergency using a notification system such as Firebase Cloud Messaging (FCM). The input data includes analysis results and missing information. Based on this, the server creates push notifications in real time and sends them to the target user's device. Users who receive the notifications can immediately understand the emergency situation and take prompt action.

[0180] In this way, servers, databases, AI models, mobile apps, and notification systems work together to streamline the management and support of emergency supplies and donations.

[0181] 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.

[0182] This invention is a system for managing supplies and donations in the event of a natural disaster, and for improving the efficiency of support. By combining it with an emotion engine that recognizes the user's emotions, it is possible to more accurately determine the priority and urgency of support activities. The specific processing flow and operation example of the system are shown below.

[0183] The server receives stock information and donation amount data sent by evacuation centers and aid organizations. The received data is stored in a database. The server then analyzes the stored data using an AI model to predict which supplies are in short supply in which areas and how much donations are needed.

[0184] The analysis results are published on a webpage and through a mobile app, allowing users to check the situation in real time and obtain reference information for providing appropriate assistance. The system also incorporates an emotion engine that recognizes the emotions of users when they offer assistance and can prioritize assistance activities based on those emotions.

[0185] Specifically, the server performs the following actions:

[0186] 1. Data Receipt and Storage:

[0187] The system receives information on stock of supplies and donation amounts sent by evacuation centers and relief organizations and stores it in a database, allowing the latest relief situation to be constantly monitored.

[0188] 2. Analysis by AI model:

[0189] The received data is used to train an AI model to predict supplies shortages and donation amounts needed, allowing for accurate identification of aid needs based on past data and current trends.

[0190] 3. Emotion Recognition with Emotion Engine:

[0191] When a user offers help, the emotion engine recognizes their emotion. For example, if a user is enthusiastic about offering help, the engine takes that information into account when prioritizing the help.

[0192] 4. Information Disclosure and User Acknowledgment:

[0193] The analysis results and the output of the emotion engine are published on a web page or mobile app, allowing users to view them in real time and decide how much aid should be provided to which areas.

[0194] For example, suppose a major earthquake occurs in a certain area and shelters A, B, and C are set up. Information about a "food shortage" is sent from shelter A, and the server receives and stores the data. Analysis using an AI model predicts that there will be a "food shortage" not only at shelter A but also at nearby shelter B. When a user offers to help, the emotion engine analyzes the user's emotions, and if the user is highly motivated, it takes this into account and gives the help a higher priority.

[0195] This system accurately predicts the shortage of supplies and the amount of donations needed, and also takes into account the emotions of users when carrying out relief activities. As a result, relief activities can be provided quickly and appropriately in line with the needs of disaster victims, improving the efficiency and transparency of relief activities.

[0196] The processing flow will be explained below.

[0197] Step 1: Receiving Data

[0198] The server receives information about the inventory of supplies and donation amounts sent by evacuation centers and relief organizations. This information is often received via HTTP POST requests, and may be in JSON format. The server temporarily stores this data in memory.

[0199] Step 2: Save your data

[0200] The server stores the received inventory information and donation amount in a database, including the type of item, the amount in stock, and information about the evacuation center or aid organization that sent it. The information is saved by executing an INSERT query to the database.

[0201] Step 3: Feature extraction

[0202] The server retrieves the stored information from the database and extracts the features necessary for analysis and prediction by the AI ​​model. This includes data such as stock fluctuations of specific supplies and regional aid needs. The server extracts the data using SQL SELECT queries.

[0203] Step 4: Analysis by AI model

[0204] The server trains an AI model (e.g., a linear regression model) based on the extracted features. After training, it analyzes the current data to predict which supplies are in short supply and to what extent, and which areas need assistance. The AI ​​model generates its analysis results.

[0205] Step 5: Emotion Recognition with the Emotion Engine

[0206] When a user offers assistance, the server uses an emotion engine to recognize the user's emotions. For example, it determines emotions from text input, voice input, facial expressions, etc. If the user's emotions are strong, it reflects that information in the analysis results.

[0207] Step 6: Formatting the analysis results

[0208] The server then formats the analysis results obtained from the AI ​​model and emotion engine into a user-friendly format, often converted into JSON or HTML. The formatted data is then output as a list of supply shortages by region, donation amounts, and so on.

[0209] Step 7: Disclosure

[0210] The server then publishes the formatted analysis results on a web page or mobile app. Using a web framework such as Flask, the analysis results are displayed in real time when the endpoint is accessed. Users can access this information through their browser or app.

[0211] Step 8: Verify the user

[0212] Users can access information and analysis results from evacuation shelters and relief organizations through publicly available web pages and apps. Based on data updated in real time, they can determine where to send aid. After checking the situation at a specific evacuation shelter or area, they can decide on specific actions to take to provide relief.

[0213] Step 9: Implementing the support

[0214] Based on the information they have confirmed, users can send the necessary supplies and donations to the appropriate locations. They can use the online platform to order relief supplies and make donations, and their relief efforts are carried out quickly in a way that meets the needs of the disaster-stricken areas.

[0215] Example 2

[0216] 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."

[0217] In emergencies such as natural disasters, there is a need for a means to efficiently manage and analyze supply inventory information and donation amounts sent from evacuation centers and relief organizations, and accurately predict shortages and required donation amounts in real time. However, conventional systems have difficulty centrally managing and analyzing this information, making it difficult to accurately prioritize relief efforts. Furthermore, they are unable to prioritize relief efforts taking user emotions into account, preventing rapid and appropriate relief efforts.

[0218] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0219] In this invention, the server includes means for receiving supply inventory information and donation amounts sent from evacuation shelters and support organizations, means for storing the received data in a database, means for analyzing the received data using a machine learning model to predict supply shortages and required donation amounts, means for recognizing emotions and setting priorities for support when users offer support, and means for publishing the analysis results and emotion recognition results via the Internet so that users can check the information in real time. This enables quick and effective support activities that accurately predict supply shortages and required donation amounts and take user emotions into consideration.

[0220] "Supply inventory information" refers to data sent from evacuation centers and support organizations regarding the current remaining amount and stock status of supplies.

[0221] "Amount raised" refers to the amount of donations and support received by evacuation centers and support organizations.

[0222] "Means of receiving" refers to the hardware or software mechanisms used to obtain data sent by evacuation centers and aid organizations.

[0223] "Means for storing data in a database" refers to a database system for systematically managing and storing received data.

[0224] A "machine learning model" is an algorithm or mathematical model that learns patterns and knowledge from large amounts of data and makes predictions and classifications.

[0225] "Means of analysis" refers to a system that uses a certain algorithm to analyze the received data and derive insights and predictive information.

[0226] A "shortage of supplies" is a situation in which the amount of supplies currently available is less than the amount needed.

[0227] The "required amount of donations" refers to the amount of donations that evacuation centers and relief organizations need to carry out effective relief activities.

[0228] The "means for recognizing the user's emotions" refers to a mechanism for analyzing and understanding the user's emotional state when the user offers assistance.

[0229] The "means for setting support priorities" refers to a mechanism for determining the importance and urgency of support activities based on the analysis results and the user's emotions.

[0230] "Means of publishing via the Internet" refers to a mechanism for providing analysis results and emotion recognition results to users via web pages or mobile apps on the Internet.

[0231] "Means for checking information in real time" refers to a system that allows users to check ongoing status and the latest data in a timely manner.

[0232] This invention is a system for managing supplies and donations and for streamlining support in the event of a natural disaster. By combining this system with an emotion engine that recognizes the user's emotions, it can more accurately determine the priority and urgency of support activities.

[0233] First, the server receives data on stock of supplies and donation amounts from evacuation centers and relief organizations. This is done using the HTTPS protocol, and the data is received in JSON format. The received data is then stored in a MySQL database. Storing the data makes it possible to always keep track of the latest relief situation.

[0234] The server then uses the stored data to train a machine learning model. This process uses TensorFlow. The server analyzes past data and current trends to predict shortages of supplies and the amount of donations needed. For example, based on the stored past data, the server can predict that a local evacuation center will be short of 50 food items within the next week.

[0235] Furthermore, the server uses an emotion engine (e.g., a general emotion analysis API) to recognize the emotion of the user when offering help. The server captures the help offer entered by the user through the form as text data and sends the text data to the emotion analysis API. Based on the returned emotion analysis results, the server sets the priority of the user's help. For example, if the user shows strong motivation and enthusiasm, the help offer will have a high priority.

[0236] Finally, the server publishes the analysis results and emotion recognition results over the Internet. To do this, the analysis data is formatted in JSON and published through a RESTful API. Users can check the information in real time using a web page or mobile app. For example, when a user checks the aid situation in an area affected by a major earthquake, the information displayed will say, "Shelter A is short of 50 food items."

[0237] As a specific example of how it works, consider a scenario in which a major earthquake occurs and shelters A, B, and C are set up. Information about a "food shortage" is sent from shelter A, and the server receives and stores the data. The server analyzes the data using TensorFlow and determines that a "food shortage" is predicted not only at shelter A, but also at the nearby shelter B. When a user offers help, the emotion engine analyzes the data and, if the user is enthusiastic, prioritizes the offer of help.

[0238] An example prompt is:

[0239] "Based on the latest inventory data for shelters A and B, please predict the shortages of supplies over the next week. Also, please use user sentiment data to prioritize support."

[0240] This system accurately predicts the shortage of supplies and the amount of donations needed, and enables relief activities to be carried out while taking into account the emotions of users. As a result, relief activities can be provided quickly and appropriately in line with the needs of disaster victims, improving the efficiency and transparency of relief activities.

[0241] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0242] Step 1:

[0243] The server receives data on stock information and donation amounts sent by evacuation centers and aid organizations. This data is sent using the HTTPS protocol and received in JSON format. The received data includes information such as "100 units of food stock at evacuation center A." The server then parses the received JSON data and extracts it as key-value pairs.

[0244] Input: JSON formatted supply inventory information and donation amount data sent from evacuation centers and support organizations

[0245] Output: Parsed data as key-value pairs

[0246] Step 2:

[0247] The server stores the data received in step 1 in a MySQL database. Specifically, it uses the INSERT statement to insert the parsed data into the corresponding table. This table contains fields such as "shelter," "supply name," "stock amount," and "donation amount."

[0248] Input: Parsed data as key-value pairs

[0249] Output: Data stored in a MySQL database

[0250] Step 3:

[0251] The server uses the stored data to train a machine learning model. This process uses TensorFlow. First, the server loads historical data and current trends to create a dataset. Then, it trains a model based on this dataset. Once the model is fully trained, it can predict supply shortages and donation needs based on new data.

[0252] Input: Historical and current trend data stored in a MySQL database

[0253] Output: Trained machine learning model and prediction results

[0254] Step 4:

[0255] When a user offers to help, the server uses an emotion engine to recognize their emotion. The server takes the offer of help entered by the user through a form as text data and sends this text data to an emotion analysis API. The server receives the emotion analysis results returned by the API and sets the priority of the offer based on the results. For example, if a user comments, "I want to help with all my might," the server identifies their enthusiasm and sets a high priority.

[0256] Input: The offer of help entered by the user through the form

[0257] Output: Sentiment analysis results and support priorities

[0258] Step 5:

[0259] The server publishes the analysis results and emotion recognition results via the internet on a web page or mobile app. First, the analysis data is formatted into JSON and provided to the front end via a RESTful API. Users can check this using a React-based interface. For example, when a user checks the aid situation at shelter A, information such as "Shelter A is short of 50 food items" is displayed in real time.

[0260] Input: Analysis results from machine learning models and emotion recognition results

[0261] Output: User-viewable information on web pages and mobile apps

[0262] (Application example 2)

[0263] 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."

[0264] When a natural disaster occurs, there is a need to accurately grasp the shortage of supplies and the need for donations, and to carry out relief activities quickly and efficiently. However, conventional systems often fail to properly manage supplies or prioritize donations, resulting in ineffective relief activities. Furthermore, there is no way to consider the emotions and urgency of users and staff involved in relief activities, which reduces the efficiency and appropriateness of relief efforts. In particular, optimal task allocation that takes into account staff stress and urgency is required for inventory management and shortage prediction at logistics centers.

[0265] The specific processing by the specific 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 receiving supply inventory information and donation amounts transmitted from evacuation shelters and support organizations; means for saving the received data in a database; means for analyzing the received data using an AI model and predicting the supply shortage status and the required donation amount; means for recognizing the emotions of users performing support activities using an emotion engine and prioritizing the support activities based on the emotions; and means for managing supply inventory at the logistics center and recommending optimal tasks to staff based on the shortage prediction and the results of the emotion engine. This makes it possible to accurately grasp the supply shortage status and the required donation amount, and to carry out support activities that take into account the emotions and urgency of users and staff.

[0266] An "evacuation shelter" is a facility set up to provide temporary safety for victims of natural disasters or other emergencies.

[0267] A "support group" is an organization or group that provides supplies, donations, and human support in disaster-stricken areas.

[0268] "Supplies" are supplies such as food, water, clothing, and medicines needed during natural disasters.

[0269] "Inventory information" is data on the amount of goods held at a particular point in time and their breakdown.

[0270] "Amount raised" is the total amount of money raised for a particular purpose.

[0271] A database is a system that organizes and stores various types of information so that it can be retrieved as needed.

[0272] An "AI model" is an algorithm that uses machine learning and artificial intelligence technology to analyze data and make predictions and judgments.

[0273] An "emotion engine" is a technology that analyzes a user's emotions and suggests appropriate responses based on those emotions.

[0274] A "web page" is a unit of information that is made public on the Internet and is created in a description format such as HTML.

[0275] A "mobile app" is a software application that runs on a mobile device such as a smartphone or tablet.

[0276] A "logistics center" is a facility that receives, stores, sorts, and ships goods.

[0277] The present invention is a system that improves the efficiency of managing supplies and donations in the event of a natural disaster, and further combines it with an emotion engine that recognizes the user's emotions to accurately determine the priority and urgency of relief activities. Specific embodiments for implementing this system are described below.

[0278] First, the server receives stock information and donation amounts sent by evacuation centers and support organizations via API. This data is received in JSON format and stored in a database. The database used here could be a relational database such as MySQL or PostgreSQL. The database has redundancy and is regularly backed up to ensure data accuracy.

[0279] The server then analyzes the received data using an AI model. The AI ​​model is trained using machine learning techniques and predicts supply shortages and donation amounts needed based on past data and current trends. Specific AI models can use regression analysis or neural networks. The results predicted by the AI ​​model are used as basic data to quickly grasp the current situation at evacuation centers and aid organizations.

[0280] The emotion engine implemented on the server also analyzes the emotions expressed by users when they offer support activities. The emotion engine uses natural language processing technology to extract emotions from the user's text input. For example, if the text input is "I am very worried about this situation," the emotion engine detects the emotion "worry" and reflects it in the priority of support activities.

[0281] The server then publishes the analysis results and the output of the emotion engine through a web page and a mobile app, allowing users to check the situation in real time and understand which areas need assistance and to what extent. The web page is designed using HTML and CSS, and the mobile app is developed to run on either the ANDROID (registered trademark) or iOS platform.

[0282] Additionally, this system can also be applied in logistics centers, where the center manages inventory and recommends optimal tasks to staff based on shortage predictions and the results of the emotion engine. For example, a logistics center manager can receive instructions such as, "This item is in short supply and needs to be replenished as a priority." This significantly improves the efficiency and speed of support.

[0283] Also, the following format is used as an example prompt:

[0284] "We received information from shelter A about a food shortage. Please use the AI ​​model to predict the shortage of supplies and use the emotion engine to analyze the emotions of staff."

[0285] In this way, the present invention provides a system that supports rapid and efficient relief efforts in the event of a natural disaster.

[0286] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0287] Step 1:

[0288] The server receives information on stock of supplies and donation amounts from evacuation centers and support organizations.

[0289] As input, it receives JSON format data sent via API and stores it in a database. Specifically, the server processes an HTTP request, parses the received JSON data, and stores it in a relational database.

[0290] As an output, the latest inventory information and donation amounts are stored in a database.

[0291] Step 2:

[0292] The server analyzes the stored data using an AI model.

[0293] As input, the system takes stock information and donation amount data stored in a database. Data processing involves preprocessing this data and converting it into a format suitable for the AI ​​model. Specific operations include cleaning the data, filling in missing values, and normalizing it.

[0294] The output is a forecast of supply shortages and the amount of donations needed.

[0295] Step 3:

[0296] The server analyzes the user's emotions using an emotion engine.

[0297] The input is text input from the user (e.g., a comment accompanying an offer of assistance). Data processing involves analyzing the text using natural language processing technology and extracting emotions. Specific operations include tokenizing the text and mapping it to emotion categories.

[0298] As an output, the user's emotion data is obtained.

[0299] Step 4:

[0300] The server publishes the analysis results via a web page or mobile app.

[0301] The input data used is a compilation of the AI ​​model's predictions of shortages, the amount of donations needed, and the output of the emotion engine. The data is then processed to convert these analysis results into a visually easy-to-understand format. Specific operations include generating dashboards, creating graphs, and updating the data in real time.

[0302] The output is a real-time display of the assistance status that can be viewed by the user on a web page or mobile app.

[0303] Step 5:

[0304] Manage inventory of materials at the logistics center.

[0305] The inputs are the supply shortage prediction results generated by the server and user emotion data. The data is then processed by an algorithm that assigns optimal tasks to staff based on this data. Specific operations include updating inventory lists, recommending high-priority tasks, and scheduling staff.

[0306] As an output, instructions are sent to staff, streamlining inventory management at the logistics center.

[0307] 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.

[0308] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0309] 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.

[0310] [Second embodiment]

[0311] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0312] 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.

[0313] 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).

[0314] 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.

[0315] 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.

[0316] 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).

[0317] 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.

[0318] 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.

[0319] 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.

[0320] 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.

[0321] 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.

[0322] 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."

[0323] This invention is a system for improving the efficiency of managing supplies and donations and providing support when natural disasters occur. Specifically, it receives data from evacuation centers and support organizations, analyzes and predicts using an AI model, and provides the results to users.

[0324] The server first receives stock information and donation amounts sent by evacuation centers and aid organizations. The received data is stored in a database. The server then analyzes the stored data using an AI model to predict which supplies are in short supply in which areas and how much donations are needed.

[0325] The analysis results are made public via a web page or mobile app, allowing users to check the situation in real time and obtain reference information for providing appropriate assistance. For example, if shelter A reports a food shortage, that information is saved in a database in real time and compared and analyzed with data from other shelters and the region. As a result, if a food shortage is predicted not only at shelter A but also at nearby shelter B, that information will be displayed on the web page or app.

[0326] Based on this information, users can decide how much supplies and donations to send to which areas. For example, after checking the food shortage information for shelter A, users can complete the process of sending relief supplies online.

[0327] Consider the following scenario as a concrete example: A major earthquake occurs in a certain area, and several evacuation centers are set up. Evacuation center A sends information that "water stocks are low," and the server receives this data and stores it in a database. By analyzing this data together with other data using an AI model, a "water shortage" is predicted for evacuation center B as well. The results are displayed on a web page or app, and users can view them and make a decision to send relief supplies, including water, to evacuation centers A and B.

[0328] This system makes it possible to accurately grasp where and how much supplies and donations are needed, enabling prompt and appropriate assistance to be provided. As a result, the efficiency and transparency of assistance activities are improved, helping disaster victims.

[0329] The processing flow will be explained below.

[0330] Step 1: Receiving Data

[0331] The server receives information about the inventory of supplies and donation amounts sent by evacuation centers and relief organizations. This information is often received via HTTP POST requests, and may be in JSON format. The server temporarily stores this data in memory.

[0332] Step 2: Save your data

[0333] The server stores the received inventory information and donation amount in a database, including the type of item, the amount in stock, and information about the evacuation center or aid organization that sent it. The information is saved by executing an INSERT query to the database.

[0334] Step 3: Feature extraction

[0335] The server retrieves the stored information from the database and extracts the features necessary for analysis and prediction by the AI ​​model. This includes data such as stock fluctuations of specific supplies and regional aid needs. The server extracts the data using SQL SELECT queries.

[0336] Step 4: Analysis by AI model

[0337] The server trains an AI model (e.g., a linear regression model) based on the extracted features. After training, it analyzes the current data to predict which supplies are in short supply and to what extent, and which areas need assistance. The AI ​​model generates its analysis results.

[0338] Step 5: Formatting the analysis results

[0339] The server then formats the analysis results obtained from the AI ​​model in a user-friendly format, often in JSON or HTML format. The formatted data is then output as a list of supply shortages by region, donation amounts, and so on.

[0340] Step 6: Disclosure

[0341] The server then publishes the formatted analysis results on a web page or mobile app. Using a web framework such as Flask, the analysis results are displayed in real time when the endpoint is accessed. Users can access this information through their browser or app.

[0342] Step 7: Verify the user

[0343] Users can access information and analysis results from evacuation shelters and relief organizations through publicly available web pages and apps. Based on data updated in real time, they can determine where to send aid. After checking the situation at a specific evacuation shelter or area, they can decide on specific actions to take to provide relief.

[0344] Step 8: Implementing the support

[0345] Based on the information they have confirmed, users can send the necessary supplies and donations to the appropriate locations. They can use the online platform to order relief supplies and make donations, and their relief efforts are carried out quickly in a way that meets the needs of the disaster-stricken areas.

[0346] These steps allow the server to receive, store, and analyze data, and then make the information public, allowing users to make decisions in real time to provide appropriate assistance, thereby streamlining assistance activities.

[0347] Example 1

[0348] 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."

[0349] In order to improve the efficiency of managing supplies and donations and providing support when natural disasters occur, it is necessary to grasp the shortage of supplies and the amount of donations needed in real time and carry out appropriate support activities. However, collecting and analyzing data from evacuation centers and support organizations takes time, making it difficult to respond quickly. Furthermore, there are concerns that centralized data management and information provision to users are not being carried out efficiently, which could lead to delays and imbalances in support activities.

[0350] 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.

[0351] In this invention, the server includes means for receiving supply inventory information and donation amounts sent from evacuation shelters and support organizations, means for storing the received data in a relational database, and means for analyzing the received data using a generative model to predict supply shortages and required donation amounts. This makes it possible to quickly and accurately analyze the received data and publish necessary support information in real time. As a result, users can carry out appropriate support activities in a timely manner, improving the efficiency and transparency of support activities.

[0352] "Supply inventory information" is data on the types and quantities of supplies held by evacuation centers and support organizations.

[0353] "Amount raised" is data on the total amount of donations collected by evacuation centers and support organizations.

[0354] "Means of receiving" refers to the technical means for electronically receiving data sent from evacuation centers and support organizations.

[0355] A "relational database" is a data storage system that stores received data and manages it so that it can be later analyzed or referenced.

[0356] A "generative model" is a mathematical model that uses artificial intelligence (AI) to analyze data and predict future shortages and fundraising needs.

[0357] "Means of analysis" are technical means for analyzing data and extracting specific patterns or trends.

[0358] An "internet page" is an online platform viewable through a web browser.

[0359] "Mobile device software" refers to applications that run on mobile devices such as smartphones and tablets.

[0360] "Means for checking the status in real time" refers to technological means that allow users to instantly check the current status of supplies and donations.

[0361] "Means of centralized management" refers to the technical means for aggregating information from multiple data sources and managing it in a single system.

[0362] The "means for providing instructions for carrying out support activities" refers to a technical means for providing a specific action plan or guidance for the user to provide appropriate support.

[0363] The present invention is a system for improving the efficiency of managing supplies and donations and providing support when a natural disaster occurs. Specifically, the system receives data from evacuation centers and support organizations, analyzes and predicts using a generative AI model, and provides the results to users. A specific embodiment of this system is described below.

[0364] The server receives data on supply inventory and donation amounts sent by evacuation centers and aid organizations. The received data is stored in a relational database (e.g., MySQL). The server then analyzes the stored data using generative AI models such as Python's TensorFlow or PyTorch to predict which areas are short of which supplies and how much donations are needed. This analysis process also uses data science libraries such as NumPy and Pandas.

[0365] The analysis results are published through a web page with a Node.js-based backend and a React.js-based frontend, or a mobile app using Flutter, allowing users to check the situation in real time and obtain reference information for providing appropriate assistance.

[0366] Consider the following scenario as a concrete example: A major earthquake occurs in a certain area, and multiple evacuation centers are set up. Evacuation center A sends information that "water stocks are low," and the server receives this data and stores it in a database. The server analyzes this data together with other data using TensorFlow, and predicts that a similar "water shortage" will occur at evacuation center B. The results are displayed on a web page using React.js or a mobile app developed with Flutter, and users can view them and make decisions about sending relief supplies, including water, to evacuation centers A and B.

[0367] Examples of prompts to input to a generative AI model include:

[0368] "A major earthquake has occurred in the area and water shortages have been reported at shelter A and shelter B. What are the next steps?"

[0369] This system makes it possible to accurately grasp where and how much supplies and donations are needed, enabling prompt and appropriate assistance to be provided. As a result, the efficiency and transparency of assistance activities are improved, helping disaster victims.

[0370] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0371] Step 1:

[0372] The server receives information on stock of supplies and donation amounts sent by evacuation centers and support organizations.

[0373] Input: JSON formatted data sent via HTTP POST request from shelters and aid organizations.

[0374] Specific operation: The server receives data through the API endpoint and extracts JSON data from the body of the HTTP request.

[0375] Data processing and calculation: Parse the received JSON data and extract the necessary fields.

[0376] Output: The extracted data.

[0377] Step 2:

[0378] The server stores the received data in a relational database.

[0379] Input: The data extracted in step 1.

[0380] Specific behavior: The server connects to the database (e.g., MySQL) and generates the appropriate INSERT statements to save the data.

[0381] Data processing and calculation: Convert the received data into SQL format and insert it into the database.

[0382] Output: The records stored in the database.

[0383] Step 3:

[0384] The server uses a generative AI model to analyze the stored data and predict supply shortages and the amount of donations needed.

[0385] Input: Historical and current data stored in a database.

[0386] How it works: The server retrieves data from the database, converts it into a data frame using Pandas, and then inputs the data into a TensorFlow or PyTorch model for analysis.

[0387] Data processing and calculation: The generative model makes predictions based on the data frame.

[0388] Output: Analysis results (e.g., which areas are short of which supplies, and the need for donations).

[0389] Step 4:

[0390] The server publishes the analysis results on an internet page or via software for mobile devices.

[0391] Input: Analysis results obtained in step 3.

[0392] Specific operation: The server provides the analysis results as an API on a Node.js-based backend and sends the data to a frontend using React.js or Flutter.

[0393] Data processing and calculation: The analysis results are converted into JSON format and published at the API endpoint.

[0394] Output: The analytics results displayed on a user-visible web page or mobile app.

[0395] Step 5:

[0396] Users can check the situation in real time via an internet page or software on their mobile device and provide appropriate support.

[0397] Input: Interface based on analysis results.

[0398] What happens: A user browses a webpage or app to find information about a need for assistance, then fills out an online form to arrange for the delivery of supplies.

[0399] Data processing and calculation: The data entered in the form is sent to the server, where it is processed to send relief supplies.

[0400] Output: A confirmation message that the outreach activity was completed.

[0401] (Application example 1)

[0402] 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."

[0403] When a natural disaster occurs, it is difficult to quickly grasp the shortage of supplies at evacuation centers and relief organizations and efficiently manage and provide the necessary relief supplies and donations. While real-time information provision is important for users to carry out relief activities appropriately, conventional systems do not adequately meet this requirement. In particular, there is a lack of means to quickly provide food delivery services, which can lead to delays in food supplies during emergencies.

[0404] 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.

[0405] In this invention, the server includes means for receiving stock information and donation amounts sent from evacuation shelters and support organizations, means for saving the received data in a database, means for analyzing the received data using an AI model to predict the shortage status of supplies and the amount of donations required, means for publishing the analysis results on a web page or mobile app so that users can check the situation in real time, means for users to process relief supplies and donations online, and means for notifying users of shortage information in the event of an emergency. This makes it possible to quickly and accurately grasp the shortage status of supplies at evacuation shelters and support organizations and to efficiently carry out support activities, including food delivery services.

[0406] An "evacuation shelter" is a facility set up during a disaster to temporarily gather victims and ensure their safety.

[0407] "Support groups" are non-profit organizations and groups that provide supplies and donations to support disaster victims and evacuees during disasters and emergencies.

[0408] "Supply inventory information" refers to information about the quantity and types of supplies that evacuation centers and support organizations have on hand.

[0409] "Amount raised" is information indicating the total amount of money raised for support.

[0410] "Means of receiving" refers to the systems and technologies used to receive information sent from evacuation centers and support organizations.

[0411] "Means for storing data in a database" refers to a system for storing received data in an appropriate format so that it can be retrieved as needed.

[0412] "Means of analysis using AI models" refers to means of analyzing received data using artificial intelligence technology and making predictions and decisions.

[0413] "Supply shortage status" is information that indicates the extent to which specific supplies are in short supply during a disaster.

[0414] "Raising Needs" is the monetary amount needed to carry out a particular relief effort.

[0415] "Means of publishing on web pages or mobile apps" refers to the means of providing analysis results and information to users via the Internet.

[0416] "Means that users can use to process online" refers to a system that allows users to process donations and relief supplies via the Internet.

[0417] "Means for notifying shortage information in an emergency" refers to means for quickly conveying information to users when a shortage of supplies occurs during a disaster.

[0418] This invention is a system that improves the efficiency of managing supplies and donations and providing support in the event of a natural disaster. In particular, by applying this system to food delivery services, it can quickly provide food in emergencies.

[0419] 1. System Components

[0420] The system includes the following major components:

[0421] server

[0422] Database

[0423] Mobile Applications

[0424] AI model

[0425] Notification System

[0426] 2. Hardware and Software

[0427] The hardware used in this system includes cloud servers (e.g., AWS, GCP) and smartphones. The following software is used:

[0428] TensorFlow (for AI model analysis)

[0429] REST API (for receiving data)

[0430] Flask / Django (server-side framework)

[0431] Firebase Cloud Messaging (notification system)

[0432] 3. Receipt and storage of data

[0433] The server receives stock information and donation amounts sent from evacuation centers and support organizations via a REST API. The received data is stored in a database, allowing for centralized data management.

[0434] 4. Analysis using AI models

[0435] The stored data is analyzed using an AI model, which uses the TensorFlow library to predict the supply shortage and the amount of donations needed. The analysis results are then stored back in the database.

[0436] 5. Data Disclosure and Notification

[0437] The analysis results are made available to users via a web page and mobile application, and a notification system is activated to send real-time notifications to users in the event of a serious shortage of supplies or an emergency.

[0438] 6. Online Procedures

[0439] Users can donate supplies and funds online through the mobile app, enabling fast and efficient relief efforts.

[0440] 7. Specific Examples

[0441] For example, if a major earthquake occurs in a certain area and shelter A sends information that "water stocks are low," the server receives that data and stores it in a database. Analysis using an AI model predicts a similar "water shortage" at shelter B. The results are displayed on the mobile app, and users can review them and make a decision to send relief supplies, including water, to shelters A and B. In addition, push notifications are sent to users in the event of an emergency.

[0442] 8. Examples of prompts

[0443] An example of a prompt sentence to input to the generative AI model is as follows:

[0444] "Shelter A is running low on food supplies. Please estimate what supplies will be needed and propose specific support."

[0445] Such a system will enable prompt and appropriate support in the event of a disaster, and will enable effective assistance to be provided to victims.

[0446] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0447] Step 1:

[0448] The server receives stock information and donation amounts sent from evacuation centers and support organizations via a REST API. The input data includes the type and quantity of supplies currently held by the evacuation center or support organization, as well as the donation amount. The received data is sent to the server in JSON format or other formats. The received data is temporarily stored in memory.

[0449] Step 2:

[0450] The server stores the received data in a database, typically a relational database such as MySQL or PostgreSQL. Input data includes the shelter ID, type of supplies, quantity, and donation amount. This data is inserted into the appropriate tables and persisted as output data for later analysis.

[0451] Step 3:

[0452] The server inputs the data stored in the database into an AI model for analysis. The AI ​​model, built using the TensorFlow library, predicts the shortage of supplies and the amount of donations needed. The input data indicates the current situation at the evacuation shelter, and the AI ​​model analyzes past data and patterns to generate a prediction. The output data is a prediction of the level of shortage of supplies and the amount of donations needed. The prediction results are then stored back in the database.

[0453] Step 4:

[0454] The server retrieves the analysis results from the database and publishes them on a web page or mobile application. The analysis results are retrieved from the database as input data. These data are converted into an appropriate format (HTML, JSON, etc.) and displayed on the user interface of the web page or mobile application, allowing users to check the situation in real time.

[0455] Step 5:

[0456] The mobile application allows users to process donations and donations online. Users input donation details through the mobile app. The input data includes the type of goods, quantity, recipient, and donation amount. This data is sent to the server and processed appropriately. The server verifies the donation details received and stores the data in a database.

[0457] Step 6:

[0458] The server notifies users of missing information in an emergency using a notification system such as Firebase Cloud Messaging (FCM). The input data includes analysis results and missing information. Based on this, the server creates push notifications in real time and sends them to the target user's device. Users who receive the notifications can immediately understand the emergency situation and take prompt action.

[0459] In this way, servers, databases, AI models, mobile apps, and notification systems work together to streamline the management and support of emergency supplies and donations.

[0460] 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.

[0461] This invention is a system for managing supplies and donations in the event of a natural disaster, and for improving the efficiency of support. By combining it with an emotion engine that recognizes the user's emotions, it is possible to more accurately determine the priority and urgency of support activities. The specific processing flow and operation example of the system are shown below.

[0462] The server receives stock information and donation amount data sent by evacuation centers and aid organizations. The received data is stored in a database. The server then analyzes the stored data using an AI model to predict which supplies are in short supply in which areas and how much donations are needed.

[0463] The analysis results are published on a webpage and through a mobile app, allowing users to check the situation in real time and obtain reference information for providing appropriate assistance. The system also incorporates an emotion engine that recognizes the emotions of users when they offer assistance and can prioritize assistance activities based on those emotions.

[0464] Specifically, the server performs the following actions:

[0465] 1. Data Receipt and Storage:

[0466] The system receives information on stock of supplies and donation amounts sent by evacuation centers and relief organizations and stores it in a database, allowing the latest relief situation to be constantly monitored.

[0467] 2. Analysis by AI model:

[0468] The received data is used to train an AI model to predict supplies shortages and donation amounts needed, allowing for accurate identification of aid needs based on past data and current trends.

[0469] 3. Emotion Recognition with Emotion Engine:

[0470] When a user offers help, the emotion engine recognizes their emotion. For example, if a user is enthusiastic about offering help, the engine takes that information into account when prioritizing the help.

[0471] 4. Information Disclosure and User Acknowledgment:

[0472] The analysis results and the output of the emotion engine are published on a web page or mobile app, allowing users to view them in real time and decide how much aid should be provided to which areas.

[0473] For example, suppose a major earthquake occurs in a certain area and shelters A, B, and C are set up. Information about a "food shortage" is sent from shelter A, and the server receives and stores the data. Analysis using an AI model predicts that there will be a "food shortage" not only at shelter A but also at nearby shelter B. When a user offers to help, the emotion engine analyzes the user's emotions, and if the user is highly motivated, it takes this into account and gives the help a higher priority.

[0474] This system accurately predicts the shortage of supplies and the amount of donations needed, and also takes into account the emotions of users when carrying out relief activities. As a result, relief activities can be provided quickly and appropriately in line with the needs of disaster victims, improving the efficiency and transparency of relief activities.

[0475] The processing flow will be explained below.

[0476] Step 1: Receiving Data

[0477] The server receives information about the inventory of supplies and donation amounts sent by evacuation centers and relief organizations. This information is often received via HTTP POST requests, and may be in JSON format. The server temporarily stores this data in memory.

[0478] Step 2: Save your data

[0479] The server stores the received inventory information and donation amount in a database, including the type of item, the amount in stock, and information about the evacuation center or aid organization that sent it. The information is saved by executing an INSERT query to the database.

[0480] Step 3: Feature extraction

[0481] The server retrieves the stored information from the database and extracts the features necessary for analysis and prediction by the AI ​​model. This includes data such as stock fluctuations of specific supplies and regional aid needs. The server extracts the data using SQL SELECT queries.

[0482] Step 4: Analysis by AI model

[0483] The server trains an AI model (e.g., a linear regression model) based on the extracted features. After training, it analyzes the current data to predict which supplies are in short supply and to what extent, and which areas need assistance. The AI ​​model generates its analysis results.

[0484] Step 5: Emotion Recognition with the Emotion Engine

[0485] When a user offers assistance, the server uses an emotion engine to recognize the user's emotions. For example, it determines emotions from text input, voice input, facial expressions, etc. If the user's emotions are strong, it reflects that information in the analysis results.

[0486] Step 6: Formatting the analysis results

[0487] The server then formats the analysis results obtained from the AI ​​model and emotion engine into a user-friendly format, often converted into JSON or HTML. The formatted data is then output as a list of supply shortages by region, donation amounts, and so on.

[0488] Step 7: Disclosure

[0489] The server then publishes the formatted analysis results on a web page or mobile app. Using a web framework such as Flask, the analysis results are displayed in real time when the endpoint is accessed. Users can access this information through their browser or app.

[0490] Step 8: Verify the user

[0491] Users can access information and analysis results from evacuation shelters and relief organizations through publicly available web pages and apps. Based on data updated in real time, they can determine where to send aid. After checking the situation at a specific evacuation shelter or area, they can decide on specific actions to take to provide relief.

[0492] Step 9: Implementing the support

[0493] Based on the information they have confirmed, users can send the necessary supplies and donations to the appropriate locations. They can use the online platform to order relief supplies and make donations, and their relief efforts are carried out quickly in a way that meets the needs of the disaster-stricken areas.

[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 glasses 214 will be referred to as a "terminal."

[0496] In emergencies such as natural disasters, there is a need for a means to efficiently manage and analyze supply inventory information and donation amounts sent from evacuation centers and relief organizations, and accurately predict shortages and required donation amounts in real time. However, conventional systems have difficulty centrally managing and analyzing this information, making it difficult to accurately prioritize relief efforts. Furthermore, they are unable to prioritize relief efforts taking user emotions into account, preventing rapid and appropriate relief efforts.

[0497] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0498] In this invention, the server includes means for receiving supply inventory information and donation amounts sent from evacuation shelters and support organizations, means for storing the received data in a database, means for analyzing the received data using a machine learning model to predict supply shortages and required donation amounts, means for recognizing emotions and setting priorities for support when users offer support, and means for publishing the analysis results and emotion recognition results via the Internet so that users can check the information in real time. This enables quick and effective support activities that accurately predict supply shortages and required donation amounts and take user emotions into consideration.

[0499] "Supply inventory information" refers to data sent from evacuation centers and support organizations regarding the current remaining amount and stock status of supplies.

[0500] "Amount raised" refers to the amount of donations and support received by evacuation centers and support organizations.

[0501] "Means of receiving" refers to the hardware or software mechanisms used to obtain data sent by evacuation centers and aid organizations.

[0502] "Means for storing data in a database" refers to a database system for systematically managing and storing received data.

[0503] A "machine learning model" is an algorithm or mathematical model that learns patterns and knowledge from large amounts of data and makes predictions and classifications.

[0504] "Means of analysis" refers to a system that uses a certain algorithm to analyze the received data and derive insights and predictive information.

[0505] A "shortage of supplies" is a situation in which the amount of supplies currently available is less than the amount needed.

[0506] The "required amount of donations" refers to the amount of donations that evacuation centers and relief organizations need to carry out effective relief activities.

[0507] The "means for recognizing the user's emotions" refers to a mechanism for analyzing and understanding the user's emotional state when the user offers assistance.

[0508] The "means for setting support priorities" refers to a mechanism for determining the importance and urgency of support activities based on the analysis results and the user's emotions.

[0509] "Means of publishing via the Internet" refers to a mechanism for providing analysis results and emotion recognition results to users via web pages or mobile apps on the Internet.

[0510] "Means for checking information in real time" refers to a system that allows users to check ongoing status and the latest data in a timely manner.

[0511] This invention is a system for managing supplies and donations and for streamlining support in the event of a natural disaster. By combining this system with an emotion engine that recognizes the user's emotions, it can more accurately determine the priority and urgency of support activities.

[0512] First, the server receives data on stock of supplies and donation amounts from evacuation centers and relief organizations. This is done using the HTTPS protocol, and the data is received in JSON format. The received data is then stored in a MySQL database. Storing the data makes it possible to always keep track of the latest relief situation.

[0513] The server then uses the stored data to train a machine learning model. This process uses TensorFlow. The server analyzes past data and current trends to predict shortages of supplies and the amount of donations needed. For example, based on the stored past data, the server can predict that a local evacuation center will be short of 50 food items within the next week.

[0514] Furthermore, the server uses an emotion engine (e.g., a general emotion analysis API) to recognize the emotion of the user when offering help. The server captures the help offer entered by the user through the form as text data and sends the text data to the emotion analysis API. Based on the returned emotion analysis results, the server sets the priority of the user's help. For example, if the user shows strong motivation and enthusiasm, the help offer will have a high priority.

[0515] Finally, the server publishes the analysis results and emotion recognition results over the Internet. To do this, the analysis data is formatted in JSON and published through a RESTful API. Users can check the information in real time using a web page or mobile app. For example, when a user checks the aid situation in an area affected by a major earthquake, the information displayed will say, "Shelter A is short of 50 food items."

[0516] As a specific example of how it works, consider a scenario in which a major earthquake occurs and shelters A, B, and C are set up. Information about a "food shortage" is sent from shelter A, and the server receives and stores the data. The server analyzes the data using TensorFlow and determines that a "food shortage" is predicted not only at shelter A, but also at the nearby shelter B. When a user offers help, the emotion engine analyzes the data and, if the user is enthusiastic, prioritizes the offer of help.

[0517] An example prompt is:

[0518] "Based on the latest inventory data for shelters A and B, please predict the shortages of supplies over the next week. Also, please use user sentiment data to prioritize support."

[0519] This system accurately predicts the shortage of supplies and the amount of donations needed, and enables relief activities to be carried out while taking into account the emotions of users. As a result, relief activities can be provided quickly and appropriately in line with the needs of disaster victims, improving the efficiency and transparency of relief activities.

[0520] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0521] Step 1:

[0522] The server receives data on stock information and donation amounts sent by evacuation centers and aid organizations. This data is sent using the HTTPS protocol and received in JSON format. The received data includes information such as "100 units of food stock at evacuation center A." The server then parses the received JSON data and extracts it as key-value pairs.

[0523] Input: JSON formatted supply inventory information and donation amount data sent from evacuation centers and support organizations

[0524] Output: Parsed data as key-value pairs

[0525] Step 2:

[0526] The server stores the data received in step 1 in a MySQL database. Specifically, it uses the INSERT statement to insert the parsed data into the corresponding table. This table contains fields such as "shelter," "supply name," "stock amount," and "donation amount."

[0527] Input: Parsed data as key-value pairs

[0528] Output: Data stored in a MySQL database

[0529] Step 3:

[0530] The server uses the stored data to train a machine learning model. This process uses TensorFlow. First, the server loads historical data and current trends to create a dataset. Then, it trains a model based on this dataset. Once the model is fully trained, it can predict supply shortages and donation needs based on new data.

[0531] Input: Historical and current trend data stored in a MySQL database

[0532] Output: Trained machine learning model and prediction results

[0533] Step 4:

[0534] When a user offers to help, the server uses an emotion engine to recognize their emotion. The server takes the offer of help entered by the user through a form as text data and sends this text data to an emotion analysis API. The server receives the emotion analysis results returned by the API and sets the priority of the offer based on the results. For example, if a user comments, "I want to help with all my might," the server identifies their enthusiasm and sets a high priority.

[0535] Input: The offer of help entered by the user through the form

[0536] Output: Sentiment analysis results and support priorities

[0537] Step 5:

[0538] The server publishes the analysis results and emotion recognition results via the internet on a web page or mobile app. First, the analysis data is formatted into JSON and provided to the front end via a RESTful API. Users can check this using a React-based interface. For example, when a user checks the aid situation at shelter A, information such as "Shelter A is short of 50 food items" is displayed in real time.

[0539] Input: Analysis results from machine learning models and emotion recognition results

[0540] Output: User-viewable information on web pages and mobile apps

[0541] (Application example 2)

[0542] 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."

[0543] When a natural disaster occurs, there is a need to accurately grasp the shortage of supplies and the need for donations, and to carry out relief activities quickly and efficiently. However, conventional systems often fail to properly manage supplies or prioritize donations, resulting in ineffective relief activities. Furthermore, there is no way to consider the emotions and urgency of users and staff involved in relief activities, which reduces the efficiency and appropriateness of relief efforts. In particular, optimal task allocation that takes into account staff stress and urgency is required for inventory management and shortage prediction at logistics centers.

[0544] The specific processing by the specific 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 receiving supply inventory information and donation amounts transmitted from evacuation shelters and support organizations; means for saving the received data in a database; means for analyzing the received data using an AI model and predicting the supply shortage status and the required donation amount; means for recognizing the emotions of users performing support activities using an emotion engine and prioritizing the support activities based on the emotions; and means for managing supply inventory at the logistics center and recommending optimal tasks to staff based on the shortage prediction and the results of the emotion engine. This makes it possible to accurately grasp the supply shortage status and the required donation amount, and to carry out support activities that take into account the emotions and urgency of users and staff.

[0545] An "evacuation shelter" is a facility set up to provide temporary safety for victims of natural disasters or other emergencies.

[0546] A "support group" is an organization or group that provides supplies, donations, and human support in disaster-stricken areas.

[0547] "Supplies" are supplies such as food, water, clothing, and medicines needed during natural disasters.

[0548] "Inventory information" is data on the amount of goods held at a particular point in time and their breakdown.

[0549] "Amount raised" is the total amount of money raised for a particular purpose.

[0550] A database is a system that organizes and stores various types of information so that it can be retrieved as needed.

[0551] An "AI model" is an algorithm that uses machine learning and artificial intelligence technology to analyze data and make predictions and judgments.

[0552] An "emotion engine" is a technology that analyzes a user's emotions and suggests appropriate responses based on those emotions.

[0553] A "web page" is a unit of information that is made public on the Internet and is created in a description format such as HTML.

[0554] A "mobile app" is a software application that runs on a mobile device such as a smartphone or tablet.

[0555] A "logistics center" is a facility that receives, stores, sorts, and ships goods.

[0556] The present invention is a system that improves the efficiency of managing supplies and donations in the event of a natural disaster, and further combines it with an emotion engine that recognizes the user's emotions to accurately determine the priority and urgency of relief activities. Specific embodiments for implementing this system are described below.

[0557] First, the server receives stock information and donation amounts sent by evacuation centers and support organizations via API. This data is received in JSON format and stored in a database. The database used here could be a relational database such as MySQL or PostgreSQL. The database has redundancy and is regularly backed up to ensure data accuracy.

[0558] The server then analyzes the received data using an AI model. The AI ​​model is trained using machine learning techniques and predicts supply shortages and donation amounts needed based on past data and current trends. Specific AI models can use regression analysis or neural networks. The results predicted by the AI ​​model are used as basic data to quickly grasp the current situation at evacuation centers and aid organizations.

[0559] The emotion engine implemented on the server also analyzes the emotions expressed by users when they offer support activities. The emotion engine uses natural language processing technology to extract emotions from the user's text input. For example, if the text input is "I am very worried about this situation," the emotion engine detects the emotion "worry" and reflects it in the priority of support activities.

[0560] The server then publishes the analysis results and the output of the emotion engine through a web page and a mobile app, allowing users to check the situation in real time and understand which areas need assistance and to what extent. The web page is designed using HTML and CSS, and the mobile app is developed to run on either the Android or iOS platform.

[0561] Additionally, this system can also be applied in logistics centers, where the center manages inventory and recommends optimal tasks to staff based on shortage predictions and the results of the emotion engine. For example, a logistics center manager can receive instructions such as, "This item is in short supply and needs to be replenished as a priority." This significantly improves the efficiency and speed of support.

[0562] Also, the following format is used as an example prompt:

[0563] "We received information from shelter A about a food shortage. Please use the AI ​​model to predict the shortage of supplies and use the emotion engine to analyze the emotions of staff."

[0564] In this way, the present invention provides a system that supports rapid and efficient relief efforts in the event of a natural disaster.

[0565] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0566] Step 1:

[0567] The server receives information on stock of supplies and donation amounts from evacuation centers and support organizations.

[0568] As input, it receives JSON format data sent via API and stores it in a database. Specifically, the server processes an HTTP request, parses the received JSON data, and stores it in a relational database.

[0569] As an output, the latest inventory information and donation amounts are stored in a database.

[0570] Step 2:

[0571] The server analyzes the stored data using an AI model.

[0572] As input, the system takes stock information and donation amount data stored in a database. Data processing involves preprocessing this data and converting it into a format suitable for the AI ​​model. Specific operations include cleaning the data, filling in missing values, and normalizing it.

[0573] The output is a forecast of supply shortages and the amount of donations needed.

[0574] Step 3:

[0575] The server analyzes the user's emotions using an emotion engine.

[0576] The input is text input from the user (e.g., a comment accompanying an offer of assistance). Data processing involves analyzing the text using natural language processing technology and extracting emotions. Specific operations include tokenizing the text and mapping it to emotion categories.

[0577] As an output, the user's emotion data is obtained.

[0578] Step 4:

[0579] The server publishes the analysis results via a web page or mobile app.

[0580] The input data used is a compilation of the AI ​​model's predictions of shortages, the amount of donations needed, and the output of the emotion engine. The data is then processed to convert these analysis results into a visually easy-to-understand format. Specific operations include generating dashboards, creating graphs, and updating the data in real time.

[0581] The output is a real-time display of the assistance status that can be viewed by the user on a web page or mobile app.

[0582] Step 5:

[0583] Manage inventory of materials at the logistics center.

[0584] The inputs are the supply shortage prediction results generated by the server and user emotion data. The data is then processed by an algorithm that assigns optimal tasks to staff based on this data. Specific operations include updating inventory lists, recommending high-priority tasks, and scheduling staff.

[0585] As an output, instructions are sent to staff, streamlining inventory management at the logistics center.

[0586] 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.

[0587] 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.

[0588] 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.

[0589] [Third embodiment]

[0590] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0591] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0592] 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).

[0593] 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.

[0594] 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.

[0595] 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).

[0596] 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.

[0597] 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.

[0598] 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.

[0599] 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.

[0600] 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.

[0601] 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."

[0602] This invention is a system for improving the efficiency of managing supplies and donations and providing support when natural disasters occur. Specifically, it receives data from evacuation centers and support organizations, analyzes and predicts using an AI model, and provides the results to users.

[0603] The server first receives stock information and donation amounts sent by evacuation centers and aid organizations. The received data is stored in a database. The server then analyzes the stored data using an AI model to predict which supplies are in short supply in which areas and how much donations are needed.

[0604] The analysis results are made public via a web page or mobile app, allowing users to check the situation in real time and obtain reference information for providing appropriate assistance. For example, if shelter A reports a food shortage, that information is saved in a database in real time and compared and analyzed with data from other shelters and the region. As a result, if a food shortage is predicted not only at shelter A but also at nearby shelter B, that information will be displayed on the web page or app.

[0605] Based on this information, users can decide how much supplies and donations to send to which areas. For example, after checking the food shortage information for shelter A, users can complete the process of sending relief supplies online.

[0606] Consider the following scenario as a concrete example: A major earthquake occurs in a certain area, and several evacuation centers are set up. Evacuation center A sends information that "water stocks are low," and the server receives this data and stores it in a database. By analyzing this data together with other data using an AI model, a "water shortage" is predicted for evacuation center B as well. The results are displayed on a web page or app, and users can view them and make a decision to send relief supplies, including water, to evacuation centers A and B.

[0607] This system makes it possible to accurately grasp where and how much supplies and donations are needed, enabling prompt and appropriate assistance to be provided. As a result, the efficiency and transparency of assistance activities are improved, helping disaster victims.

[0608] The processing flow will be explained below.

[0609] Step 1: Receiving Data

[0610] The server receives information about the inventory of supplies and donation amounts sent by evacuation centers and relief organizations. This information is often received via HTTP POST requests, and may be in JSON format. The server temporarily stores this data in memory.

[0611] Step 2: Save your data

[0612] The server stores the received inventory information and donation amount in a database, including the type of item, the amount in stock, and information about the evacuation center or aid organization that sent it. The information is saved by executing an INSERT query to the database.

[0613] Step 3: Feature extraction

[0614] The server retrieves the stored information from the database and extracts the features necessary for analysis and prediction by the AI ​​model. This includes data such as stock fluctuations of specific supplies and regional aid needs. The server extracts the data using SQL SELECT queries.

[0615] Step 4: Analysis by AI model

[0616] The server trains an AI model (e.g., a linear regression model) based on the extracted features. After training, it analyzes the current data to predict which supplies are in short supply and to what extent, and which areas need assistance. The AI ​​model generates its analysis results.

[0617] Step 5: Formatting the analysis results

[0618] The server then formats the analysis results obtained from the AI ​​model in a user-friendly format, often in JSON or HTML format. The formatted data is then output as a list of supply shortages by region, donation amounts, and so on.

[0619] Step 6: Disclosure

[0620] The server then publishes the formatted analysis results on a web page or mobile app. Using a web framework such as Flask, the analysis results are displayed in real time when the endpoint is accessed. Users can access this information through their browser or app.

[0621] Step 7: Verify the user

[0622] Users can access information and analysis results from evacuation shelters and relief organizations through publicly available web pages and apps. Based on data updated in real time, they can determine where to send aid. After checking the situation at a specific evacuation shelter or area, they can decide on specific actions to take to provide relief.

[0623] Step 8: Implementing the support

[0624] Based on the information they have confirmed, users can send the necessary supplies and donations to the appropriate locations. They can use the online platform to order relief supplies and make donations, and their relief efforts are carried out quickly in a way that meets the needs of the disaster-stricken areas.

[0625] These steps allow the server to receive, store, and analyze data, and then make the information public, allowing users to make decisions in real time to provide appropriate assistance, thereby streamlining assistance activities.

[0626] Example 1

[0627] 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."

[0628] In order to improve the efficiency of managing supplies and donations and providing support when natural disasters occur, it is necessary to grasp the shortage of supplies and the amount of donations needed in real time and carry out appropriate support activities. However, collecting and analyzing data from evacuation centers and support organizations takes time, making it difficult to respond quickly. Furthermore, there are concerns that centralized data management and information provision to users are not being carried out efficiently, which could lead to delays and imbalances in support activities.

[0629] 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.

[0630] In this invention, the server includes means for receiving supply inventory information and donation amounts sent from evacuation shelters and support organizations, means for storing the received data in a relational database, and means for analyzing the received data using a generative model to predict supply shortages and required donation amounts. This makes it possible to quickly and accurately analyze the received data and publish necessary support information in real time. As a result, users can carry out appropriate support activities in a timely manner, improving the efficiency and transparency of support activities.

[0631] "Supply inventory information" is data on the types and quantities of supplies held by evacuation centers and support organizations.

[0632] "Amount raised" is data on the total amount of donations collected by evacuation centers and support organizations.

[0633] "Means of receiving" refers to the technical means for electronically receiving data sent from evacuation centers and support organizations.

[0634] A "relational database" is a data storage system that stores received data and manages it so that it can be later analyzed or referenced.

[0635] A "generative model" is a mathematical model that uses artificial intelligence (AI) to analyze data and predict future shortages and fundraising needs.

[0636] "Means of analysis" are technical means for analyzing data and extracting specific patterns or trends.

[0637] An "internet page" is an online platform viewable through a web browser.

[0638] "Mobile device software" refers to applications that run on mobile devices such as smartphones and tablets.

[0639] "Means for checking the status in real time" refers to technological means that allow users to instantly check the current status of supplies and donations.

[0640] "Means of centralized management" refers to the technical means for aggregating information from multiple data sources and managing it in a single system.

[0641] The "means for providing instructions for carrying out support activities" refers to a technical means for providing a specific action plan or guidance for the user to provide appropriate support.

[0642] The present invention is a system for improving the efficiency of managing supplies and donations and providing support when a natural disaster occurs. Specifically, the system receives data from evacuation centers and support organizations, analyzes and predicts using a generative AI model, and provides the results to users. A specific embodiment of this system is described below.

[0643] The server receives data on supply inventory and donation amounts sent by evacuation centers and aid organizations. The received data is stored in a relational database (e.g., MySQL). The server then analyzes the stored data using generative AI models such as Python's TensorFlow or PyTorch to predict which areas are short of which supplies and how much donations are needed. This analysis process also uses data science libraries such as NumPy and Pandas.

[0644] The analysis results are published through a web page with a Node.js-based backend and a React.js-based frontend, or a mobile app using Flutter, allowing users to check the situation in real time and obtain reference information for providing appropriate assistance.

[0645] Consider the following scenario as a concrete example: A major earthquake occurs in a certain area, and multiple evacuation centers are set up. Evacuation center A sends information that "water stocks are low," and the server receives this data and stores it in a database. The server analyzes this data together with other data using TensorFlow, and predicts that a similar "water shortage" will occur at evacuation center B. The results are displayed on a web page using React.js or a mobile app developed with Flutter, and users can view them and make decisions about sending relief supplies, including water, to evacuation centers A and B.

[0646] Examples of prompts to input to a generative AI model include:

[0647] "A major earthquake has occurred in the area and water shortages have been reported at shelter A and shelter B. What are the next steps?"

[0648] This system makes it possible to accurately grasp where and how much supplies and donations are needed, enabling prompt and appropriate assistance to be provided. As a result, the efficiency and transparency of assistance activities are improved, helping disaster victims.

[0649] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0650] Step 1:

[0651] The server receives information on stock of supplies and donation amounts sent by evacuation centers and support organizations.

[0652] Input: JSON formatted data sent via HTTP POST request from shelters and aid organizations.

[0653] Specific operation: The server receives data through the API endpoint and extracts JSON data from the body of the HTTP request.

[0654] Data processing and calculation: Parse the received JSON data and extract the necessary fields.

[0655] Output: The extracted data.

[0656] Step 2:

[0657] The server stores the received data in a relational database.

[0658] Input: The data extracted in step 1.

[0659] Specific behavior: The server connects to the database (e.g., MySQL) and generates the appropriate INSERT statements to save the data.

[0660] Data processing and calculation: Convert the received data into SQL format and insert it into the database.

[0661] Output: The records stored in the database.

[0662] Step 3:

[0663] The server uses a generative AI model to analyze the stored data and predict supply shortages and the amount of donations needed.

[0664] Input: Historical and current data stored in a database.

[0665] How it works: The server retrieves data from the database, converts it into a data frame using Pandas, and then inputs the data into a TensorFlow or PyTorch model for analysis.

[0666] Data processing and calculation: The generative model makes predictions based on the data frame.

[0667] Output: Analysis results (e.g., which areas are short of which supplies, and the need for donations).

[0668] Step 4:

[0669] The server publishes the analysis results on an internet page or via software for mobile devices.

[0670] Input: Analysis results obtained in step 3.

[0671] Specific operation: The server provides the analysis results as an API on a Node.js-based backend and sends the data to a frontend using React.js or Flutter.

[0672] Data processing and calculation: The analysis results are converted into JSON format and published at the API endpoint.

[0673] Output: The analytics results displayed on a user-visible web page or mobile app.

[0674] Step 5:

[0675] Users can check the situation in real time via an internet page or software on their mobile device and provide appropriate support.

[0676] Input: Interface based on analysis results.

[0677] What happens: A user browses a webpage or app to find information about a need for assistance, then fills out an online form to arrange for the delivery of supplies.

[0678] Data processing and calculation: The data entered in the form is sent to the server, where it is processed to send relief supplies.

[0679] Output: A confirmation message that the outreach activity was completed.

[0680] (Application example 1)

[0681] 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."

[0682] When a natural disaster occurs, it is difficult to quickly grasp the shortage of supplies at evacuation centers and relief organizations and efficiently manage and provide the necessary relief supplies and donations. While real-time information provision is important for users to carry out relief activities appropriately, conventional systems do not adequately meet this requirement. In particular, there is a lack of means to quickly provide food delivery services, which can lead to delays in food supplies during emergencies.

[0683] 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.

[0684] In this invention, the server includes means for receiving stock information and donation amounts sent from evacuation shelters and support organizations, means for saving the received data in a database, means for analyzing the received data using an AI model to predict the shortage status of supplies and the amount of donations required, means for publishing the analysis results on a web page or mobile app so that users can check the situation in real time, means for users to process relief supplies and donations online, and means for notifying users of shortage information in the event of an emergency. This makes it possible to quickly and accurately grasp the shortage status of supplies at evacuation shelters and support organizations and to efficiently carry out support activities, including food delivery services.

[0685] An "evacuation shelter" is a facility set up during a disaster to temporarily gather victims and ensure their safety.

[0686] "Support groups" are non-profit organizations and groups that provide supplies and donations to support disaster victims and evacuees during disasters and emergencies.

[0687] "Supply inventory information" refers to information about the quantity and types of supplies that evacuation centers and support organizations have on hand.

[0688] "Amount raised" is information indicating the total amount of money raised for support.

[0689] "Means of receiving" refers to the systems and technologies used to receive information sent from evacuation centers and support organizations.

[0690] "Means for storing data in a database" refers to a system for storing received data in an appropriate format so that it can be retrieved as needed.

[0691] "Means of analysis using AI models" refers to means of analyzing received data using artificial intelligence technology and making predictions and decisions.

[0692] "Supply shortage status" is information that indicates the extent to which specific supplies are in short supply during a disaster.

[0693] "Raising Needs" is the monetary amount needed to carry out a particular relief effort.

[0694] "Means of publishing on web pages or mobile apps" refers to the means of providing analysis results and information to users via the Internet.

[0695] "Means that users can use to process online" refers to a system that allows users to process donations and relief supplies via the Internet.

[0696] "Means for notifying shortage information in an emergency" refers to means for quickly conveying information to users when a shortage of supplies occurs during a disaster.

[0697] This invention is a system that improves the efficiency of managing supplies and donations and providing support in the event of a natural disaster. In particular, by applying this system to food delivery services, it can quickly provide food in emergencies.

[0698] 1. System Components

[0699] The system includes the following major components:

[0700] server

[0701] Database

[0702] Mobile Applications

[0703] AI model

[0704] Notification System

[0705] 2. Hardware and Software

[0706] The hardware used in this system includes cloud servers (e.g., AWS, GCP) and smartphones. The following software is used:

[0707] TensorFlow (for AI model analysis)

[0708] REST API (for receiving data)

[0709] Flask / Django (server-side framework)

[0710] Firebase Cloud Messaging (notification system)

[0711] 3. Receipt and storage of data

[0712] The server receives stock information and donation amounts sent from evacuation centers and support organizations via a REST API. The received data is stored in a database, allowing for centralized data management.

[0713] 4. Analysis using AI models

[0714] The stored data is analyzed using an AI model, which uses the TensorFlow library to predict the supply shortage and the amount of donations needed. The analysis results are then stored back in the database.

[0715] 5. Data Disclosure and Notification

[0716] The analysis results are made available to users via a web page and mobile application, and a notification system is activated to send real-time notifications to users in the event of a serious shortage of supplies or an emergency.

[0717] 6. Online Procedures

[0718] Users can donate supplies and funds online through the mobile app, enabling fast and efficient relief efforts.

[0719] 7. Specific Examples

[0720] For example, if a major earthquake occurs in a certain area and shelter A sends information that "water stocks are low," the server receives that data and stores it in a database. Analysis using an AI model predicts a similar "water shortage" at shelter B. The results are displayed on the mobile app, and users can review them and make a decision to send relief supplies, including water, to shelters A and B. In addition, push notifications are sent to users in the event of an emergency.

[0721] 8. Examples of prompts

[0722] An example of a prompt sentence to input to the generative AI model is as follows:

[0723] "Shelter A is running low on food supplies. Please estimate what supplies will be needed and propose specific support."

[0724] Such a system will enable prompt and appropriate support in the event of a disaster, and will enable effective assistance to be provided to victims.

[0725] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0726] Step 1:

[0727] The server receives stock information and donation amounts sent from evacuation centers and support organizations via a REST API. The input data includes the type and quantity of supplies currently held by the evacuation center or support organization, as well as the donation amount. The received data is sent to the server in JSON format or other formats. The received data is temporarily stored in memory.

[0728] Step 2:

[0729] The server stores the received data in a database, typically a relational database such as MySQL or PostgreSQL. Input data includes the shelter ID, type of supplies, quantity, and donation amount. This data is inserted into the appropriate tables and persisted as output data for later analysis.

[0730] Step 3:

[0731] The server inputs the data stored in the database into an AI model for analysis. The AI ​​model, built using the TensorFlow library, predicts the shortage of supplies and the amount of donations needed. The input data indicates the current situation at the evacuation shelter, and the AI ​​model analyzes past data and patterns to generate a prediction. The output data is a prediction of the level of shortage of supplies and the amount of donations needed. The prediction results are then stored back in the database.

[0732] Step 4:

[0733] The server retrieves the analysis results from the database and publishes them on a web page or mobile application. The analysis results are retrieved from the database as input data. These data are converted into an appropriate format (HTML, JSON, etc.) and displayed on the user interface of the web page or mobile application, allowing users to check the situation in real time.

[0734] Step 5:

[0735] The mobile application allows users to process donations and donations online. Users input donation details through the mobile app. The input data includes the type of goods, quantity, recipient, and donation amount. This data is sent to the server and processed appropriately. The server verifies the donation details received and stores the data in a database.

[0736] Step 6:

[0737] The server notifies users of missing information in an emergency using a notification system such as Firebase Cloud Messaging (FCM). The input data includes analysis results and missing information. Based on this, the server creates push notifications in real time and sends them to the target user's device. Users who receive the notifications can immediately understand the emergency situation and take prompt action.

[0738] In this way, servers, databases, AI models, mobile apps, and notification systems work together to streamline the management and support of emergency supplies and donations.

[0739] 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.

[0740] This invention is a system for managing supplies and donations in the event of a natural disaster, and for improving the efficiency of support. By combining it with an emotion engine that recognizes the user's emotions, it is possible to more accurately determine the priority and urgency of support activities. The specific processing flow and operation example of the system are shown below.

[0741] The server receives stock information and donation amount data sent by evacuation centers and aid organizations. The received data is stored in a database. The server then analyzes the stored data using an AI model to predict which supplies are in short supply in which areas and how much donations are needed.

[0742] The analysis results are published on a webpage and through a mobile app, allowing users to check the situation in real time and obtain reference information for providing appropriate assistance. The system also incorporates an emotion engine that recognizes the emotions of users when they offer assistance and can prioritize assistance activities based on those emotions.

[0743] Specifically, the server performs the following actions:

[0744] 1. Data Receipt and Storage:

[0745] The system receives information on stock of supplies and donation amounts sent by evacuation centers and relief organizations and stores it in a database, allowing the latest relief situation to be constantly monitored.

[0746] 2. Analysis by AI model:

[0747] The received data is used to train an AI model to predict supplies shortages and donation amounts needed, allowing for accurate identification of aid needs based on past data and current trends.

[0748] 3. Emotion Recognition with Emotion Engine:

[0749] When a user offers help, the emotion engine recognizes their emotion. For example, if a user is enthusiastic about offering help, the engine takes that information into account when prioritizing the help.

[0750] 4. Information Disclosure and User Acknowledgment:

[0751] The analysis results and the output of the emotion engine are published on a web page or mobile app, allowing users to view them in real time and decide how much aid should be provided to which areas.

[0752] For example, suppose a major earthquake occurs in a certain area and shelters A, B, and C are set up. Information about a "food shortage" is sent from shelter A, and the server receives and stores the data. Analysis using an AI model predicts that there will be a "food shortage" not only at shelter A but also at nearby shelter B. When a user offers to help, the emotion engine analyzes the user's emotions, and if the user is highly motivated, it takes this into account and gives the help a higher priority.

[0753] This system accurately predicts the shortage of supplies and the amount of donations needed, and also takes into account the emotions of users when carrying out relief activities. As a result, relief activities can be provided quickly and appropriately in line with the needs of disaster victims, improving the efficiency and transparency of relief activities.

[0754] The processing flow will be explained below.

[0755] Step 1: Receiving Data

[0756] The server receives information about the inventory of supplies and donation amounts sent by evacuation centers and relief organizations. This information is often received via HTTP POST requests, and may be in JSON format. The server temporarily stores this data in memory.

[0757] Step 2: Save your data

[0758] The server stores the received inventory information and donation amount in a database, including the type of item, the amount in stock, and information about the evacuation center or aid organization that sent it. The information is saved by executing an INSERT query to the database.

[0759] Step 3: Feature extraction

[0760] The server retrieves the stored information from the database and extracts the features necessary for analysis and prediction by the AI ​​model. This includes data such as stock fluctuations of specific supplies and regional aid needs. The server extracts the data using SQL SELECT queries.

[0761] Step 4: Analysis by AI model

[0762] The server trains an AI model (e.g., a linear regression model) based on the extracted features. After training, it analyzes the current data to predict which supplies are in short supply and to what extent, and which areas need assistance. The AI ​​model generates its analysis results.

[0763] Step 5: Emotion Recognition with the Emotion Engine

[0764] When a user offers assistance, the server uses an emotion engine to recognize the user's emotions. For example, it determines emotions from text input, voice input, facial expressions, etc. If the user's emotions are strong, it reflects that information in the analysis results.

[0765] Step 6: Formatting the analysis results

[0766] The server then formats the analysis results obtained from the AI ​​model and emotion engine into a user-friendly format, often converted into JSON or HTML. The formatted data is then output as a list of supply shortages by region, donation amounts, and so on.

[0767] Step 7: Disclosure

[0768] The server then publishes the formatted analysis results on a web page or mobile app. Using a web framework such as Flask, the analysis results are displayed in real time when the endpoint is accessed. Users can access this information through their browser or app.

[0769] Step 8: Verify the user

[0770] Users can access information and analysis results from evacuation shelters and relief organizations through publicly available web pages and apps. Based on data updated in real time, they can determine where to send aid. After checking the situation at a specific evacuation shelter or area, they can decide on specific actions to take to provide relief.

[0771] Step 9: Implementing the support

[0772] Based on the information they have confirmed, users can send the necessary supplies and donations to the appropriate locations. They can use the online platform to order relief supplies and make donations, and their relief efforts are carried out quickly in a way that meets the needs of the disaster-stricken areas.

[0773] Example 2

[0774] 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."

[0775] In emergencies such as natural disasters, there is a need for a means to efficiently manage and analyze supply inventory information and donation amounts sent from evacuation centers and relief organizations, and accurately predict shortages and required donation amounts in real time. However, conventional systems have difficulty centrally managing and analyzing this information, making it difficult to accurately prioritize relief efforts. Furthermore, they are unable to prioritize relief efforts taking user emotions into account, preventing rapid and appropriate relief efforts.

[0776] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0777] In this invention, the server includes means for receiving supply inventory information and donation amounts sent from evacuation shelters and support organizations, means for storing the received data in a database, means for analyzing the received data using a machine learning model to predict supply shortages and required donation amounts, means for recognizing emotions and setting priorities for support when users offer support, and means for publishing the analysis results and emotion recognition results via the Internet so that users can check the information in real time. This enables quick and effective support activities that accurately predict supply shortages and required donation amounts and take user emotions into consideration.

[0778] "Supply inventory information" refers to data sent from evacuation centers and support organizations regarding the current remaining amount and stock status of supplies.

[0779] "Amount raised" refers to the amount of donations and support received by evacuation centers and support organizations.

[0780] "Means of receiving" refers to the hardware or software mechanisms used to obtain data sent by evacuation centers and aid organizations.

[0781] "Means for storing data in a database" refers to a database system for systematically managing and storing received data.

[0782] A "machine learning model" is an algorithm or mathematical model that learns patterns and knowledge from large amounts of data and makes predictions and classifications.

[0783] "Means of analysis" refers to a system that uses a certain algorithm to analyze the received data and derive insights and predictive information.

[0784] A "shortage of supplies" is a situation in which the amount of supplies currently available is less than the amount needed.

[0785] The "required amount of donations" refers to the amount of donations that evacuation centers and relief organizations need to carry out effective relief activities.

[0786] The "means for recognizing the user's emotions" refers to a mechanism for analyzing and understanding the user's emotional state when the user offers assistance.

[0787] The "means for setting support priorities" refers to a mechanism for determining the importance and urgency of support activities based on the analysis results and the user's emotions.

[0788] "Means of publishing via the Internet" refers to a mechanism for providing analysis results and emotion recognition results to users via web pages or mobile apps on the Internet.

[0789] "Means for checking information in real time" refers to a system that allows users to check ongoing status and the latest data in a timely manner.

[0790] This invention is a system for managing supplies and donations and for streamlining support in the event of a natural disaster. By combining this system with an emotion engine that recognizes the user's emotions, it can more accurately determine the priority and urgency of support activities.

[0791] First, the server receives data on stock of supplies and donation amounts from evacuation centers and relief organizations. This is done using the HTTPS protocol, and the data is received in JSON format. The received data is then stored in a MySQL database. Storing the data makes it possible to always keep track of the latest relief situation.

[0792] The server then uses the stored data to train a machine learning model. This process uses TensorFlow. The server analyzes past data and current trends to predict shortages of supplies and the amount of donations needed. For example, based on the stored past data, the server can predict that a local evacuation center will be short of 50 food items within the next week.

[0793] Furthermore, the server uses an emotion engine (e.g., a general emotion analysis API) to recognize the emotion of the user when offering help. The server captures the help offer entered by the user through the form as text data and sends the text data to the emotion analysis API. Based on the returned emotion analysis results, the server sets the priority of the user's help. For example, if the user shows strong motivation and enthusiasm, the help offer will have a high priority.

[0794] Finally, the server publishes the analysis results and emotion recognition results over the Internet. To do this, the analysis data is formatted in JSON and published through a RESTful API. Users can check the information in real time using a web page or mobile app. For example, when a user checks the aid situation in an area affected by a major earthquake, the information displayed will say, "Shelter A is short of 50 food items."

[0795] As a specific example of how it works, consider a scenario in which a major earthquake occurs and shelters A, B, and C are set up. Information about a "food shortage" is sent from shelter A, and the server receives and stores the data. The server analyzes the data using TensorFlow and determines that a "food shortage" is predicted not only at shelter A, but also at the nearby shelter B. When a user offers help, the emotion engine analyzes the data and, if the user is enthusiastic, prioritizes the offer of help.

[0796] An example prompt is:

[0797] "Based on the latest inventory data for shelters A and B, please predict the shortages of supplies over the next week. Also, please use user sentiment data to prioritize support."

[0798] This system accurately predicts the shortage of supplies and the amount of donations needed, and enables relief activities to be carried out while taking into account the emotions of users. As a result, relief activities can be provided quickly and appropriately in line with the needs of disaster victims, improving the efficiency and transparency of relief activities.

[0799] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0800] Step 1:

[0801] The server receives data on stock information and donation amounts sent by evacuation centers and aid organizations. This data is sent using the HTTPS protocol and received in JSON format. The received data includes information such as "100 units of food stock at evacuation center A." The server then parses the received JSON data and extracts it as key-value pairs.

[0802] Input: JSON formatted supply inventory information and donation amount data sent from evacuation centers and support organizations

[0803] Output: Parsed data as key-value pairs

[0804] Step 2:

[0805] The server stores the data received in step 1 in a MySQL database. Specifically, it uses the INSERT statement to insert the parsed data into the corresponding table. This table contains fields such as "shelter," "supply name," "stock amount," and "donation amount."

[0806] Input: Parsed data as key-value pairs

[0807] Output: Data stored in a MySQL database

[0808] Step 3:

[0809] The server uses the stored data to train a machine learning model. This process uses TensorFlow. First, the server loads historical data and current trends to create a dataset. Then, it trains a model based on this dataset. Once the model is fully trained, it can predict supply shortages and donation needs based on new data.

[0810] Input: Historical and current trend data stored in a MySQL database

[0811] Output: Trained machine learning model and prediction results

[0812] Step 4:

[0813] When a user offers to help, the server uses an emotion engine to recognize their emotion. The server takes the offer of help entered by the user through a form as text data and sends this text data to an emotion analysis API. The server receives the emotion analysis results returned by the API and sets the priority of the offer based on the results. For example, if a user comments, "I want to help with all my might," the server identifies their enthusiasm and sets a high priority.

[0814] Input: The offer of help entered by the user through the form

[0815] Output: Sentiment analysis results and support priorities

[0816] Step 5:

[0817] The server publishes the analysis results and emotion recognition results via the internet on a web page or mobile app. First, the analysis data is formatted into JSON and provided to the front end via a RESTful API. Users can check this using a React-based interface. For example, when a user checks the aid situation at shelter A, information such as "Shelter A is short of 50 food items" is displayed in real time.

[0818] Input: Analysis results from machine learning models and emotion recognition results

[0819] Output: User-viewable information on web pages and mobile apps

[0820] (Application example 2)

[0821] 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."

[0822] When a natural disaster occurs, there is a need to accurately grasp the shortage of supplies and the need for donations, and to carry out relief activities quickly and efficiently. However, conventional systems often fail to properly manage supplies or prioritize donations, resulting in ineffective relief activities. Furthermore, there is no way to consider the emotions and urgency of users and staff involved in relief activities, which reduces the efficiency and appropriateness of relief efforts. In particular, optimal task allocation that takes into account staff stress and urgency is required for inventory management and shortage prediction at logistics centers.

[0823] The specific processing by the specific 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 receiving supply inventory information and donation amounts transmitted from evacuation shelters and support organizations; means for saving the received data in a database; means for analyzing the received data using an AI model and predicting the supply shortage status and the required donation amount; means for recognizing the emotions of users performing support activities using an emotion engine and prioritizing the support activities based on the emotions; and means for managing supply inventory at the logistics center and recommending optimal tasks to staff based on the shortage prediction and the results of the emotion engine. This makes it possible to accurately grasp the supply shortage status and the required donation amount, and to carry out support activities that take into account the emotions and urgency of users and staff.

[0824] An "evacuation shelter" is a facility set up to provide temporary safety for victims of natural disasters or other emergencies.

[0825] A "support group" is an organization or group that provides supplies, donations, and human support in disaster-stricken areas.

[0826] "Supplies" are supplies such as food, water, clothing, and medicines needed during natural disasters.

[0827] "Inventory information" is data on the amount of goods held at a particular point in time and their breakdown.

[0828] "Amount raised" is the total amount of money raised for a particular purpose.

[0829] A database is a system that organizes and stores various types of information so that it can be retrieved as needed.

[0830] An "AI model" is an algorithm that uses machine learning and artificial intelligence technology to analyze data and make predictions and judgments.

[0831] An "emotion engine" is a technology that analyzes a user's emotions and suggests appropriate responses based on those emotions.

[0832] A "web page" is a unit of information that is made public on the Internet and is created in a description format such as HTML.

[0833] A "mobile app" is a software application that runs on a mobile device such as a smartphone or tablet.

[0834] A "logistics center" is a facility that receives, stores, sorts, and ships goods.

[0835] The present invention is a system that improves the efficiency of managing supplies and donations in the event of a natural disaster, and further combines it with an emotion engine that recognizes the user's emotions to accurately determine the priority and urgency of relief activities. Specific embodiments for implementing this system are described below.

[0836] First, the server receives stock information and donation amounts sent by evacuation centers and support organizations via API. This data is received in JSON format and stored in a database. The database used here could be a relational database such as MySQL or PostgreSQL. The database has redundancy and is regularly backed up to ensure data accuracy.

[0837] The server then analyzes the received data using an AI model. The AI ​​model is trained using machine learning techniques and predicts supply shortages and donation amounts needed based on past data and current trends. Specific AI models can use regression analysis or neural networks. The results predicted by the AI ​​model are used as basic data to quickly grasp the current situation at evacuation centers and aid organizations.

[0838] The emotion engine implemented on the server also analyzes the emotions expressed by users when they offer support activities. The emotion engine uses natural language processing technology to extract emotions from the user's text input. For example, if the text input is "I am very worried about this situation," the emotion engine detects the emotion "worry" and reflects it in the priority of support activities.

[0839] The server then publishes the analysis results and the output of the emotion engine through a web page and a mobile app, allowing users to check the situation in real time and understand which areas need assistance and to what extent. The web page is designed using HTML and CSS, and the mobile app is developed to run on either the Android or iOS platform.

[0840] Additionally, this system can also be applied in logistics centers, where the center manages inventory and recommends optimal tasks to staff based on shortage predictions and the results of the emotion engine. For example, a logistics center manager can receive instructions such as, "This item is in short supply and needs to be replenished as a priority." This significantly improves the efficiency and speed of support.

[0841] Also, the following format is used as an example prompt:

[0842] "We received information from shelter A about a food shortage. Please use the AI ​​model to predict the shortage of supplies and use the emotion engine to analyze the emotions of staff."

[0843] In this way, the present invention provides a system that supports rapid and efficient relief efforts in the event of a natural disaster.

[0844] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0845] Step 1:

[0846] The server receives information on stock of supplies and donation amounts from evacuation centers and support organizations.

[0847] As input, it receives JSON format data sent via API and stores it in a database. Specifically, the server processes an HTTP request, parses the received JSON data, and stores it in a relational database.

[0848] As an output, the latest inventory information and donation amounts are stored in a database.

[0849] Step 2:

[0850] The server analyzes the stored data using an AI model.

[0851] As input, the system takes stock information and donation amount data stored in a database. Data processing involves preprocessing this data and converting it into a format suitable for the AI ​​model. Specific operations include cleaning the data, filling in missing values, and normalizing it.

[0852] The output is a forecast of supply shortages and the amount of donations needed.

[0853] Step 3:

[0854] The server analyzes the user's emotions using an emotion engine.

[0855] The input is text input from the user (e.g., a comment accompanying an offer of assistance). Data processing involves analyzing the text using natural language processing technology and extracting emotions. Specific operations include tokenizing the text and mapping it to emotion categories.

[0856] As an output, the user's emotion data is obtained.

[0857] Step 4:

[0858] The server publishes the analysis results via a web page or mobile app.

[0859] The input data used is a compilation of the AI ​​model's predictions of shortages, the amount of donations needed, and the output of the emotion engine. The data is then processed to convert these analysis results into a visually easy-to-understand format. Specific operations include generating dashboards, creating graphs, and updating the data in real time.

[0860] The output is a real-time display of the assistance status that can be viewed by the user on a web page or mobile app.

[0861] Step 5:

[0862] Manage inventory of materials at the logistics center.

[0863] The inputs are the supply shortage prediction results generated by the server and user emotion data. The data is then processed by an algorithm that assigns optimal tasks to staff based on this data. Specific operations include updating inventory lists, recommending high-priority tasks, and scheduling staff.

[0864] As an output, instructions are sent to staff, streamlining inventory management at the logistics center.

[0865] 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.

[0866] 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.

[0867] 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.

[0868] [Fourth embodiment]

[0869] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0870] 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.

[0871] 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).

[0872] 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.

[0873] 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.

[0874] 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).

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] 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."

[0882] This invention is a system for improving the efficiency of managing supplies and donations and providing support when natural disasters occur. Specifically, it receives data from evacuation centers and support organizations, analyzes and predicts using an AI model, and provides the results to users.

[0883] The server first receives stock information and donation amounts sent by evacuation centers and aid organizations. The received data is stored in a database. The server then analyzes the stored data using an AI model to predict which supplies are in short supply in which areas and how much donations are needed.

[0884] The analysis results are made public via a web page or mobile app, allowing users to check the situation in real time and obtain reference information for providing appropriate assistance. For example, if shelter A reports a food shortage, that information is saved in a database in real time and compared and analyzed with data from other shelters and the region. As a result, if a food shortage is predicted not only at shelter A but also at nearby shelter B, that information will be displayed on the web page or app.

[0885] Based on this information, users can decide how much supplies and donations to send to which areas. For example, after checking the food shortage information for shelter A, users can complete the process of sending relief supplies online.

[0886] Consider the following scenario as a concrete example: A major earthquake occurs in a certain area, and several evacuation centers are set up. Evacuation center A sends information that "water stocks are low," and the server receives this data and stores it in a database. By analyzing this data together with other data using an AI model, a "water shortage" is predicted for evacuation center B as well. The results are displayed on a web page or app, and users can view them and make a decision to send relief supplies, including water, to evacuation centers A and B.

[0887] This system makes it possible to accurately grasp where and how much supplies and donations are needed, enabling prompt and appropriate assistance to be provided. As a result, the efficiency and transparency of assistance activities are improved, helping disaster victims.

[0888] The processing flow will be explained below.

[0889] Step 1: Receiving Data

[0890] The server receives information about the inventory of supplies and donation amounts sent by evacuation centers and relief organizations. This information is often received via HTTP POST requests, and may be in JSON format. The server temporarily stores this data in memory.

[0891] Step 2: Save your data

[0892] The server stores the received inventory information and donation amount in a database, including the type of item, the amount in stock, and information about the evacuation center or aid organization that sent it. The information is saved by executing an INSERT query to the database.

[0893] Step 3: Feature extraction

[0894] The server retrieves the stored information from the database and extracts the features necessary for analysis and prediction by the AI ​​model. This includes data such as stock fluctuations of specific supplies and regional aid needs. The server extracts the data using SQL SELECT queries.

[0895] Step 4: Analysis by AI model

[0896] The server trains an AI model (e.g., a linear regression model) based on the extracted features. After training, it analyzes the current data to predict which supplies are in short supply and to what extent, and which areas need assistance. The AI ​​model generates its analysis results.

[0897] Step 5: Formatting the analysis results

[0898] The server then formats the analysis results obtained from the AI ​​model in a user-friendly format, often in JSON or HTML format. The formatted data is then output as a list of supply shortages by region, donation amounts, and so on.

[0899] Step 6: Disclosure

[0900] The server then publishes the formatted analysis results on a web page or mobile app. Using a web framework such as Flask, the analysis results are displayed in real time when the endpoint is accessed. Users can access this information through their browser or app.

[0901] Step 7: Verify the user

[0902] Users can access information and analysis results from evacuation shelters and relief organizations through publicly available web pages and apps. Based on data updated in real time, they can determine where to send aid. After checking the situation at a specific evacuation shelter or area, they can decide on specific actions to take to provide relief.

[0903] Step 8: Implementing the support

[0904] Based on the information they have confirmed, users can send the necessary supplies and donations to the appropriate locations. They can use the online platform to order relief supplies and make donations, and their relief efforts are carried out quickly in a way that meets the needs of the disaster-stricken areas.

[0905] These steps allow the server to receive, store, and analyze data, and then make the information public, allowing users to make decisions in real time to provide appropriate assistance, thereby streamlining assistance activities.

[0906] Example 1

[0907] 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."

[0908] In order to improve the efficiency of managing supplies and donations and providing support when natural disasters occur, it is necessary to grasp the shortage of supplies and the amount of donations needed in real time and carry out appropriate support activities. However, collecting and analyzing data from evacuation centers and support organizations takes time, making it difficult to respond quickly. Furthermore, there are concerns that centralized data management and information provision to users are not being carried out efficiently, which could lead to delays and imbalances in support activities.

[0909] 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.

[0910] In this invention, the server includes means for receiving supply inventory information and donation amounts sent from evacuation shelters and support organizations, means for storing the received data in a relational database, and means for analyzing the received data using a generative model to predict supply shortages and required donation amounts. This makes it possible to quickly and accurately analyze the received data and publish necessary support information in real time. As a result, users can carry out appropriate support activities in a timely manner, improving the efficiency and transparency of support activities.

[0911] "Supply inventory information" is data on the types and quantities of supplies held by evacuation centers and support organizations.

[0912] "Amount raised" is data on the total amount of donations collected by evacuation centers and support organizations.

[0913] "Means of receiving" refers to the technical means for electronically receiving data sent from evacuation centers and support organizations.

[0914] A "relational database" is a data storage system that stores received data and manages it so that it can be later analyzed or referenced.

[0915] A "generative model" is a mathematical model that uses artificial intelligence (AI) to analyze data and predict future shortages and fundraising needs.

[0916] "Means of analysis" are technical means for analyzing data and extracting specific patterns or trends.

[0917] An "internet page" is an online platform viewable through a web browser.

[0918] "Mobile device software" refers to applications that run on mobile devices such as smartphones and tablets.

[0919] "Means for checking the status in real time" refers to technological means that allow users to instantly check the current status of supplies and donations.

[0920] "Means of centralized management" refers to the technical means for aggregating information from multiple data sources and managing it in a single system.

[0921] The "means for providing instructions for carrying out support activities" refers to a technical means for providing a specific action plan or guidance for the user to provide appropriate support.

[0922] The present invention is a system for improving the efficiency of managing supplies and donations and providing support when a natural disaster occurs. Specifically, the system receives data from evacuation centers and support organizations, analyzes and predicts using a generative AI model, and provides the results to users. A specific embodiment of this system is described below.

[0923] The server receives data on supply inventory and donation amounts sent by evacuation centers and aid organizations. The received data is stored in a relational database (e.g., MySQL). The server then analyzes the stored data using generative AI models such as Python's TensorFlow or PyTorch to predict which areas are short of which supplies and how much donations are needed. This analysis process also uses data science libraries such as NumPy and Pandas.

[0924] The analysis results are published through a web page with a Node.js-based backend and a React.js-based frontend, or a mobile app using Flutter, allowing users to check the situation in real time and obtain reference information for providing appropriate assistance.

[0925] Consider the following scenario as a concrete example: A major earthquake occurs in a certain area, and multiple evacuation centers are set up. Evacuation center A sends information that "water stocks are low," and the server receives this data and stores it in a database. The server analyzes this data together with other data using TensorFlow, and predicts that a similar "water shortage" will occur at evacuation center B. The results are displayed on a web page using React.js or a mobile app developed with Flutter, and users can view them and make decisions about sending relief supplies, including water, to evacuation centers A and B.

[0926] Examples of prompts to input to a generative AI model include:

[0927] "A major earthquake has occurred in the area and water shortages have been reported at shelter A and shelter B. What are the next steps?"

[0928] This system makes it possible to accurately grasp where and how much supplies and donations are needed, enabling prompt and appropriate assistance to be provided. As a result, the efficiency and transparency of assistance activities are improved, helping disaster victims.

[0929] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0930] Step 1:

[0931] The server receives information on stock of supplies and donation amounts sent by evacuation centers and support organizations.

[0932] Input: JSON formatted data sent via HTTP POST request from shelters and aid organizations.

[0933] Specific operation: The server receives data through the API endpoint and extracts JSON data from the body of the HTTP request.

[0934] Data processing and calculation: Parse the received JSON data and extract the necessary fields.

[0935] Output: The extracted data.

[0936] Step 2:

[0937] The server stores the received data in a relational database.

[0938] Input: The data extracted in step 1.

[0939] Specific behavior: The server connects to the database (e.g., MySQL) and generates the appropriate INSERT statements to save the data.

[0940] Data processing and calculation: Convert the received data into SQL format and insert it into the database.

[0941] Output: The records stored in the database.

[0942] Step 3:

[0943] The server uses a generative AI model to analyze the stored data and predict supply shortages and the amount of donations needed.

[0944] Input: Historical and current data stored in a database.

[0945] How it works: The server retrieves data from the database, converts it into a data frame using Pandas, and then inputs the data into a TensorFlow or PyTorch model for analysis.

[0946] Data processing and calculation: The generative model makes predictions based on the data frame.

[0947] Output: Analysis results (e.g., which areas are short of which supplies, and the need for donations).

[0948] Step 4:

[0949] The server publishes the analysis results on an internet page or via software for mobile devices.

[0950] Input: Analysis results obtained in step 3.

[0951] Specific operation: The server provides the analysis results as an API on a Node.js-based backend and sends the data to a frontend using React.js or Flutter.

[0952] Data processing and calculation: The analysis results are converted into JSON format and published at the API endpoint.

[0953] Output: The analytics results displayed on a user-visible web page or mobile app.

[0954] Step 5:

[0955] Users can check the situation in real time via an internet page or software on their mobile device and provide appropriate support.

[0956] Input: Interface based on analysis results.

[0957] What happens: A user browses a webpage or app to find information about a need for assistance, then fills out an online form to arrange for the delivery of supplies.

[0958] Data processing and calculation: The data entered in the form is sent to the server, where it is processed to send relief supplies.

[0959] Output: A confirmation message that the outreach activity was completed.

[0960] (Application example 1)

[0961] 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."

[0962] When a natural disaster occurs, it is difficult to quickly grasp the shortage of supplies at evacuation centers and relief organizations and efficiently manage and provide the necessary relief supplies and donations. While real-time information provision is important for users to carry out relief activities appropriately, conventional systems do not adequately meet this requirement. In particular, there is a lack of means to quickly provide food delivery services, which can lead to delays in food supplies during emergencies.

[0963] 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.

[0964] In this invention, the server includes means for receiving stock information and donation amounts sent from evacuation shelters and support organizations, means for saving the received data in a database, means for analyzing the received data using an AI model to predict the shortage status of supplies and the amount of donations required, means for publishing the analysis results on a web page or mobile app so that users can check the situation in real time, means for users to process relief supplies and donations online, and means for notifying users of shortage information in the event of an emergency. This makes it possible to quickly and accurately grasp the shortage status of supplies at evacuation shelters and support organizations and to efficiently carry out support activities, including food delivery services.

[0965] An "evacuation shelter" is a facility set up during a disaster to temporarily gather victims and ensure their safety.

[0966] "Support groups" are non-profit organizations and groups that provide supplies and donations to support disaster victims and evacuees during disasters and emergencies.

[0967] "Supply inventory information" refers to information about the quantity and types of supplies that evacuation centers and support organizations have on hand.

[0968] "Amount raised" is information indicating the total amount of money raised for support.

[0969] "Means of receiving" refers to the systems and technologies used to receive information sent from evacuation centers and support organizations.

[0970] "Means for storing data in a database" refers to a system for storing received data in an appropriate format so that it can be retrieved as needed.

[0971] "Means of analysis using AI models" refers to means of analyzing received data using artificial intelligence technology and making predictions and decisions.

[0972] "Supply shortage status" is information that indicates the extent to which specific supplies are in short supply during a disaster.

[0973] "Raising Needs" is the monetary amount needed to carry out a particular relief effort.

[0974] "Means of publishing on web pages or mobile apps" refers to the means of providing analysis results and information to users via the Internet.

[0975] "Means that users can use to process online" refers to a system that allows users to process donations and relief supplies via the Internet.

[0976] "Means for notifying shortage information in an emergency" refers to means for quickly conveying information to users when a shortage of supplies occurs during a disaster.

[0977] This invention is a system that improves the efficiency of managing supplies and donations and providing support in the event of a natural disaster. In particular, by applying this system to food delivery services, it can quickly provide food in emergencies.

[0978] 1. System Components

[0979] The system includes the following major components:

[0980] server

[0981] Database

[0982] Mobile Applications

[0983] AI model

[0984] Notification System

[0985] 2. Hardware and Software

[0986] The hardware used in this system includes cloud servers (e.g., AWS, GCP) and smartphones. The following software is used:

[0987] TensorFlow (for AI model analysis)

[0988] REST API (for receiving data)

[0989] Flask / Django (server-side framework)

[0990] Firebase Cloud Messaging (notification system)

[0991] 3. Receipt and storage of data

[0992] The server receives stock information and donation amounts sent from evacuation centers and support organizations via a REST API. The received data is stored in a database, allowing for centralized data management.

[0993] 4. Analysis using AI models

[0994] The stored data is analyzed using an AI model, which uses the TensorFlow library to predict the supply shortage and the amount of donations needed. The analysis results are then stored back in the database.

[0995] 5. Data Disclosure and Notification

[0996] The analysis results are made available to users via a web page and mobile application, and a notification system is activated to send real-time notifications to users in the event of a serious shortage of supplies or an emergency.

[0997] 6. Online Procedures

[0998] Users can donate supplies and funds online through the mobile app, enabling fast and efficient relief efforts.

[0999] 7. Specific Examples

[1000] For example, if a major earthquake occurs in a certain area and shelter A sends information that "water stocks are low," the server receives that data and stores it in a database. Analysis using an AI model predicts a similar "water shortage" at shelter B. The results are displayed on the mobile app, and users can review them and make a decision to send relief supplies, including water, to shelters A and B. In addition, push notifications are sent to users in the event of an emergency.

[1001] 8. Examples of prompts

[1002] An example of a prompt sentence to input to the generative AI model is as follows:

[1003] "Shelter A is running low on food supplies. Please estimate what supplies will be needed and propose specific support."

[1004] Such a system will enable prompt and appropriate support in the event of a disaster, and will enable effective assistance to be provided to victims.

[1005] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1006] Step 1:

[1007] The server receives stock information and donation amounts sent from evacuation centers and support organizations via a REST API. The input data includes the type and quantity of supplies currently held by the evacuation center or support organization, as well as the donation amount. The received data is sent to the server in JSON format or other formats. The received data is temporarily stored in memory.

[1008] Step 2:

[1009] The server stores the received data in a database, typically a relational database such as MySQL or PostgreSQL. Input data includes the shelter ID, type of supplies, quantity, and donation amount. This data is inserted into the appropriate tables and persisted as output data for later analysis.

[1010] Step 3:

[1011] The server inputs the data stored in the database into an AI model for analysis. The AI ​​model, built using the TensorFlow library, predicts the shortage of supplies and the amount of donations needed. The input data indicates the current situation at the evacuation shelter, and the AI ​​model analyzes past data and patterns to generate a prediction. The output data is a prediction of the level of shortage of supplies and the amount of donations needed. The prediction results are then stored back in the database.

[1012] Step 4:

[1013] The server retrieves the analysis results from the database and publishes them on a web page or mobile application. The analysis results are retrieved from the database as input data. These data are converted into an appropriate format (HTML, JSON, etc.) and displayed on the user interface of the web page or mobile application, allowing users to check the situation in real time.

[1014] Step 5:

[1015] The mobile application allows users to process donations and donations online. Users input donation details through the mobile app. The input data includes the type of goods, quantity, recipient, and donation amount. This data is sent to the server and processed appropriately. The server verifies the donation details received and stores the data in a database.

[1016] Step 6:

[1017] The server notifies users of missing information in an emergency using a notification system such as Firebase Cloud Messaging (FCM). The input data includes analysis results and missing information. Based on this, the server creates push notifications in real time and sends them to the target user's device. Users who receive the notifications can immediately understand the emergency situation and take prompt action.

[1018] In this way, servers, databases, AI models, mobile apps, and notification systems work together to streamline the management and support of emergency supplies and donations.

[1019] 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.

[1020] This invention is a system for managing supplies and donations in the event of a natural disaster, and for improving the efficiency of support. By combining it with an emotion engine that recognizes the user's emotions, it is possible to more accurately determine the priority and urgency of support activities. The specific processing flow and operation example of the system are shown below.

[1021] The server receives stock information and donation amount data sent by evacuation centers and aid organizations. The received data is stored in a database. The server then analyzes the stored data using an AI model to predict which supplies are in short supply in which areas and how much donations are needed.

[1022] The analysis results are published on a webpage and through a mobile app, allowing users to check the situation in real time and obtain reference information for providing appropriate assistance. The system also incorporates an emotion engine that recognizes the emotions of users when they offer assistance and can prioritize assistance activities based on those emotions.

[1023] Specifically, the server performs the following actions:

[1024] 1. Data Receipt and Storage:

[1025] The system receives information on stock of supplies and donation amounts sent by evacuation centers and relief organizations and stores it in a database, allowing the latest relief situation to be constantly monitored.

[1026] 2. Analysis by AI model:

[1027] The received data is used to train an AI model to predict supplies shortages and donation amounts needed, allowing for accurate identification of aid needs based on past data and current trends.

[1028] 3. Emotion Recognition with Emotion Engine:

[1029] When a user offers help, the emotion engine recognizes their emotion. For example, if a user is enthusiastic about offering help, the engine takes that information into account when prioritizing the help.

[1030] 4. Information Disclosure and User Acknowledgment:

[1031] The analysis results and the output of the emotion engine are published on a web page or mobile app, allowing users to view them in real time and decide how much aid should be provided to which areas.

[1032] For example, suppose a major earthquake occurs in a certain area and shelters A, B, and C are set up. Information about a "food shortage" is sent from shelter A, and the server receives and stores the data. Analysis using an AI model predicts that there will be a "food shortage" not only at shelter A but also at nearby shelter B. When a user offers to help, the emotion engine analyzes the user's emotions, and if the user is highly motivated, it takes this into account and gives the help a higher priority.

[1033] This system accurately predicts the shortage of supplies and the amount of donations needed, and also takes into account the emotions of users when carrying out relief activities. As a result, relief activities can be provided quickly and appropriately in line with the needs of disaster victims, improving the efficiency and transparency of relief activities.

[1034] The processing flow will be explained below.

[1035] Step 1: Receiving Data

[1036] The server receives information about the inventory of supplies and donation amounts sent by evacuation centers and relief organizations. This information is often received via HTTP POST requests, and may be in JSON format. The server temporarily stores this data in memory.

[1037] Step 2: Save your data

[1038] The server stores the received inventory information and donation amount in a database, including the type of item, the amount in stock, and information about the evacuation center or aid organization that sent it. The information is saved by executing an INSERT query to the database.

[1039] Step 3: Feature extraction

[1040] The server retrieves the stored information from the database and extracts the features necessary for analysis and prediction by the AI ​​model. This includes data such as stock fluctuations of specific supplies and regional aid needs. The server extracts the data using SQL SELECT queries.

[1041] Step 4: Analysis by AI model

[1042] The server trains an AI model (e.g., a linear regression model) based on the extracted features. After training, it analyzes the current data to predict which supplies are in short supply and to what extent, and which areas need assistance. The AI ​​model generates its analysis results.

[1043] Step 5: Emotion Recognition with the Emotion Engine

[1044] When a user offers assistance, the server uses an emotion engine to recognize the user's emotions. For example, it determines emotions from text input, voice input, facial expressions, etc. If the user's emotions are strong, it reflects that information in the analysis results.

[1045] Step 6: Formatting the analysis results

[1046] The server then formats the analysis results obtained from the AI ​​model and emotion engine into a user-friendly format, often converted into JSON or HTML. The formatted data is then output as a list of supply shortages by region, donation amounts, and so on.

[1047] Step 7: Disclosure

[1048] The server then publishes the formatted analysis results on a web page or mobile app. Using a web framework such as Flask, the analysis results are displayed in real time when the endpoint is accessed. Users can access this information through their browser or app.

[1049] Step 8: Verify the user

[1050] Users can access information and analysis results from evacuation shelters and relief organizations through publicly available web pages and apps. Based on data updated in real time, they can determine where to send aid. After checking the situation at a specific evacuation shelter or area, they can decide on specific actions to take to provide relief.

[1051] Step 9: Implementing the support

[1052] Based on the information they have confirmed, users can send the necessary supplies and donations to the appropriate locations. They can use the online platform to order relief supplies and make donations, and their relief efforts are carried out quickly in a way that meets the needs of the disaster-stricken areas.

[1053] Example 2

[1054] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1055] In emergencies such as natural disasters, there is a need for a means to efficiently manage and analyze supply inventory information and donation amounts sent from evacuation centers and relief organizations, and accurately predict shortages and required donation amounts in real time. However, conventional systems have difficulty centrally managing and analyzing this information, making it difficult to accurately prioritize relief efforts. Furthermore, they are unable to prioritize relief efforts taking user emotions into account, preventing rapid and appropriate relief efforts.

[1056] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1057] In this invention, the server includes means for receiving supply inventory information and donation amounts sent from evacuation shelters and support organizations, means for storing the received data in a database, means for analyzing the received data using a machine learning model to predict supply shortages and required donation amounts, means for recognizing emotions and setting priorities for support when users offer support, and means for publishing the analysis results and emotion recognition results via the Internet so that users can check the information in real time. This enables quick and effective support activities that accurately predict supply shortages and required donation amounts and take user emotions into consideration.

[1058] "Supply inventory information" refers to data sent from evacuation centers and support organizations regarding the current remaining amount and stock status of supplies.

[1059] "Amount raised" refers to the amount of donations and support received by evacuation centers and support organizations.

[1060] "Means of receiving" refers to the hardware or software mechanisms used to obtain data sent by evacuation centers and aid organizations.

[1061] "Means for storing data in a database" refers to a database system for systematically managing and storing received data.

[1062] A "machine learning model" is an algorithm or mathematical model that learns patterns and knowledge from large amounts of data and makes predictions and classifications.

[1063] "Means of analysis" refers to a system that uses a certain algorithm to analyze the received data and derive insights and predictive information.

[1064] A "shortage of supplies" is a situation in which the amount of supplies currently available is less than the amount needed.

[1065] The "required amount of donations" refers to the amount of donations that evacuation centers and relief organizations need to carry out effective relief activities.

[1066] The "means for recognizing the user's emotions" refers to a mechanism for analyzing and understanding the user's emotional state when the user offers assistance.

[1067] The "means for setting support priorities" refers to a mechanism for determining the importance and urgency of support activities based on the analysis results and the user's emotions.

[1068] "Means of publishing via the Internet" refers to a mechanism for providing analysis results and emotion recognition results to users via web pages or mobile apps on the Internet.

[1069] "Means for checking information in real time" refers to a system that allows users to check ongoing status and the latest data in a timely manner.

[1070] This invention is a system for managing supplies and donations and for streamlining support in the event of a natural disaster. By combining this system with an emotion engine that recognizes the user's emotions, it can more accurately determine the priority and urgency of support activities.

[1071] First, the server receives data on stock of supplies and donation amounts from evacuation centers and relief organizations. This is done using the HTTPS protocol, and the data is received in JSON format. The received data is then stored in a MySQL database. Storing the data makes it possible to always keep track of the latest relief situation.

[1072] The server then uses the stored data to train a machine learning model. This process uses TensorFlow. The server analyzes past data and current trends to predict shortages of supplies and the amount of donations needed. For example, based on the stored past data, the server can predict that a local evacuation center will be short of 50 food items within the next week.

[1073] Furthermore, the server uses an emotion engine (e.g., a general emotion analysis API) to recognize the emotion of the user when offering help. The server captures the help offer entered by the user through the form as text data and sends the text data to the emotion analysis API. Based on the returned emotion analysis results, the server sets the priority of the user's help. For example, if the user shows strong motivation and enthusiasm, the help offer will have a high priority.

[1074] Finally, the server publishes the analysis results and emotion recognition results over the Internet. To do this, the analysis data is formatted in JSON and published through a RESTful API. Users can check the information in real time using a web page or mobile app. For example, when a user checks the aid situation in an area affected by a major earthquake, the information displayed will say, "Shelter A is short of 50 food items."

[1075] As a specific example of how it works, consider a scenario in which a major earthquake occurs and shelters A, B, and C are set up. Information about a "food shortage" is sent from shelter A, and the server receives and stores the data. The server analyzes the data using TensorFlow and determines that a "food shortage" is predicted not only at shelter A, but also at the nearby shelter B. When a user offers help, the emotion engine analyzes the data and, if the user is enthusiastic, prioritizes the offer of help.

[1076] An example prompt is:

[1077] "Based on the latest inventory data for shelters A and B, please predict the shortages of supplies over the next week. Also, please use user sentiment data to prioritize support."

[1078] This system accurately predicts the shortage of supplies and the amount of donations needed, and enables relief activities to be carried out while taking into account the emotions of users. As a result, relief activities can be provided quickly and appropriately in line with the needs of disaster victims, improving the efficiency and transparency of relief activities.

[1079] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1080] Step 1:

[1081] The server receives data on stock information and donation amounts sent by evacuation centers and aid organizations. This data is sent using the HTTPS protocol and received in JSON format. The received data includes information such as "100 units of food stock at evacuation center A." The server then parses the received JSON data and extracts it as key-value pairs.

[1082] Input: JSON formatted supply inventory information and donation amount data sent from evacuation centers and support organizations

[1083] Output: Parsed data as key-value pairs

[1084] Step 2:

[1085] The server stores the data received in step 1 in a MySQL database. Specifically, it uses the INSERT statement to insert the parsed data into the corresponding table. This table contains fields such as "shelter," "supply name," "stock amount," and "donation amount."

[1086] Input: Parsed data as key-value pairs

[1087] Output: Data stored in a MySQL database

[1088] Step 3:

[1089] The server uses the stored data to train a machine learning model. This process uses TensorFlow. First, the server loads historical data and current trends to create a dataset. Then, it trains a model based on this dataset. Once the model is fully trained, it can predict supply shortages and donation needs based on new data.

[1090] Input: Historical and current trend data stored in a MySQL database

[1091] Output: Trained machine learning model and prediction results

[1092] Step 4:

[1093] When a user offers to help, the server uses an emotion engine to recognize their emotion. The server takes the offer of help entered by the user through a form as text data and sends this text data to an emotion analysis API. The server receives the emotion analysis results returned by the API and sets the priority of the offer based on the results. For example, if a user comments, "I want to help with all my might," the server identifies their enthusiasm and sets a high priority.

[1094] Input: The offer of help entered by the user through the form

[1095] Output: Sentiment analysis results and support priorities

[1096] Step 5:

[1097] The server publishes the analysis results and emotion recognition results via the internet on a web page or mobile app. First, the analysis data is formatted into JSON and provided to the front end via a RESTful API. Users can check this using a React-based interface. For example, when a user checks the aid situation at shelter A, information such as "Shelter A is short of 50 food items" is displayed in real time.

[1098] Input: Analysis results from machine learning models and emotion recognition results

[1099] Output: User-viewable information on web pages and mobile apps

[1100] (Application example 2)

[1101] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1102] When a natural disaster occurs, there is a need to accurately grasp the shortage of supplies and the need for donations, and to carry out relief activities quickly and efficiently. However, conventional systems often fail to properly manage supplies or prioritize donations, resulting in ineffective relief activities. Furthermore, there is no way to consider the emotions and urgency of users and staff involved in relief activities, which reduces the efficiency and appropriateness of relief efforts. In particular, optimal task allocation that takes into account staff stress and urgency is required for inventory management and shortage prediction at logistics centers.

[1103] The specific processing by the specific 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 receiving supply inventory information and donation amounts transmitted from evacuation shelters and support organizations; means for saving the received data in a database; means for analyzing the received data using an AI model and predicting the supply shortage status and the required donation amount; means for recognizing the emotions of users performing support activities using an emotion engine and prioritizing the support activities based on the emotions; and means for managing supply inventory at the logistics center and recommending optimal tasks to staff based on the shortage prediction and the results of the emotion engine. This makes it possible to accurately grasp the supply shortage status and the required donation amount, and to carry out support activities that take into account the emotions and urgency of users and staff.

[1104] An "evacuation shelter" is a facility set up to provide temporary safety for victims of natural disasters or other emergencies.

[1105] A "support group" is an organization or group that provides supplies, donations, and human support in disaster-stricken areas.

[1106] "Supplies" are supplies such as food, water, clothing, and medicines needed during natural disasters.

[1107] "Inventory information" is data on the amount of goods held at a particular point in time and their breakdown.

[1108] "Amount raised" is the total amount of money raised for a particular purpose.

[1109] A database is a system that organizes and stores various types of information so that it can be retrieved as needed.

[1110] An "AI model" is an algorithm that uses machine learning and artificial intelligence technology to analyze data and make predictions and judgments.

[1111] An "emotion engine" is a technology that analyzes a user's emotions and suggests appropriate responses based on those emotions.

[1112] A "web page" is a unit of information that is made public on the Internet and is created in a description format such as HTML.

[1113] A "mobile app" is a software application that runs on a mobile device such as a smartphone or tablet.

[1114] A "logistics center" is a facility that receives, stores, sorts, and ships goods.

[1115] The present invention is a system that improves the efficiency of managing supplies and donations in the event of a natural disaster, and further combines it with an emotion engine that recognizes the user's emotions to accurately determine the priority and urgency of relief activities. Specific embodiments for implementing this system are described below.

[1116] First, the server receives stock information and donation amounts sent by evacuation centers and support organizations via API. This data is received in JSON format and stored in a database. The database used here could be a relational database such as MySQL or PostgreSQL. The database has redundancy and is regularly backed up to ensure data accuracy.

[1117] The server then analyzes the received data using an AI model. The AI ​​model is trained using machine learning techniques and predicts supply shortages and donation amounts needed based on past data and current trends. Specific AI models can use regression analysis or neural networks. The results predicted by the AI ​​model are used as basic data to quickly grasp the current situation at evacuation centers and aid organizations.

[1118] The emotion engine implemented on the server also analyzes the emotions expressed by users when they offer support activities. The emotion engine uses natural language processing technology to extract emotions from the user's text input. For example, if the text input is "I am very worried about this situation," the emotion engine detects the emotion "worry" and reflects it in the priority of support activities.

[1119] The server then publishes the analysis results and the output of the emotion engine through a web page and a mobile app, allowing users to check the situation in real time and understand which areas need assistance and to what extent. The web page is designed using HTML and CSS, and the mobile app is developed to run on either the Android or iOS platform.

[1120] Additionally, this system can also be applied in logistics centers, where the center manages inventory and recommends optimal tasks to staff based on shortage predictions and the results of the emotion engine. For example, a logistics center manager can receive instructions such as, "This item is in short supply and needs to be replenished as a priority." This significantly improves the efficiency and speed of support.

[1121] Also, the following format is used as an example prompt:

[1122] "We received information from shelter A about a food shortage. Please use the AI ​​model to predict the shortage of supplies and use the emotion engine to analyze the emotions of staff."

[1123] In this way, the present invention provides a system that supports rapid and efficient relief efforts in the event of a natural disaster.

[1124] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1125] Step 1:

[1126] The server receives information on stock of supplies and donation amounts from evacuation centers and support organizations.

[1127] As input, it receives JSON format data sent via API and stores it in a database. Specifically, the server processes an HTTP request, parses the received JSON data, and stores it in a relational database.

[1128] As an output, the latest inventory information and donation amounts are stored in a database.

[1129] Step 2:

[1130] The server analyzes the stored data using an AI model.

[1131] As input, the system takes stock information and donation amount data stored in a database. Data processing involves preprocessing this data and converting it into a format suitable for the AI ​​model. Specific operations include cleaning the data, filling in missing values, and normalizing it.

[1132] The output is a forecast of supply shortages and the amount of donations needed.

[1133] Step 3:

[1134] The server analyzes the user's emotions using an emotion engine.

[1135] The input is text input from the user (e.g., a comment accompanying an offer of assistance). Data processing involves analyzing the text using natural language processing technology and extracting emotions. Specific operations include tokenizing the text and mapping it to emotion categories.

[1136] As an output, the user's emotion data is obtained.

[1137] Step 4:

[1138] The server publishes the analysis results via a web page or mobile app.

[1139] The input data used is a compilation of the AI ​​model's predictions of shortages, the amount of donations needed, and the output of the emotion engine. The data is then processed to convert these analysis results into a visually easy-to-understand format. Specific operations include generating dashboards, creating graphs, and updating the data in real time.

[1140] The output is a real-time display of the assistance status that can be viewed by the user on a web page or mobile app.

[1141] Step 5:

[1142] Manage inventory of materials at the logistics center.

[1143] The inputs are the supply shortage prediction results generated by the server and user emotion data. The data is then processed by an algorithm that assigns optimal tasks to staff based on this data. Specific operations include updating inventory lists, recommending high-priority tasks, and scheduling staff.

[1144] As an output, instructions are sent to staff, streamlining inventory management at the logistics center.

[1145] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1146] 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.

[1147] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1148] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1149] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1150] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1151] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1152] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1153] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1154] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1155] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1156] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1157] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1158] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1159] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1160] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1161] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1162] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1163] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1164] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1165] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1166] The following is further disclosed regarding the above embodiment.

[1167] (Claim 1)

[1168] A means to receive information on stock of supplies and donation amounts sent by evacuation centers and support organizations,

[1169] a means for storing the received data in a database;

[1170] The received data will be analyzed using an AI model to predict the shortage of supplies and the amount of donations required.

[1171] The analysis results will be published on a web page or mobile app, allowing users to check the situation in real time.

[1172] A system including:

[1173] (Claim 2)

[1174] 2. The system according to claim 1, further comprising means for centrally managing data transmitted from evacuation centers and support organizations by a server.

[1175] (Claim 3)

[1176] 10. The system of claim 1, further comprising means for a user to identify areas and evacuation shelters in need of assistance and provide instructions for appropriate assistance activities.

[1177] "Example 1"

[1178] (Claim 1)

[1179] A means to receive information on stock of supplies and donation amounts sent by evacuation centers and support organizations,

[1180] means for storing the received data in a relational database;

[1181] A means to analyze the received data using a generative model to predict the shortage of supplies and the amount of donations required;

[1182] The analysis results will be published on an internet page or via software for mobile devices, allowing users to check the situation in real time.

[1183] A system including:

[1184] (Claim 2)

[1185] 2. The system according to claim 1, further comprising a means for centrally managing data transmitted from evacuation centers and support organizations by a server.

[1186] (Claim 3)

[1187] 10. The system of claim 1, further comprising means for a user to identify areas and evacuation shelters in need of assistance and provide instructions for appropriate assistance activities.

[1188] "Application Example 1"

[1189] (Claim 1)

[1190] A means to receive information on stock of supplies and donation amounts sent by evacuation centers and support organizations,

[1191] a means for storing the received data in a database;

[1192] The received data will be analyzed using an AI model to predict the shortage of supplies and the amount of donations required.

[1193] The analysis results will be published on a web page or mobile app, allowing users to check the situation in real time.

[1194] A means for users to process donations and relief supplies online,

[1195] a means for notifying a user of missing information in an emergency;

[1196] A system including:

[1197] (Claim 2)

[1198] 2. The system according to claim 1, further comprising a means for centrally managing data transmitted from evacuation centers and support organizations by a server.

[1199] (Claim 3)

[1200] 10. The system of claim 1, further comprising means for a user to identify areas and evacuation shelters in need of assistance and provide instructions for appropriate assistance activities.

[1201] "Example 2: Combining Emotion Engines"

[1202] (Claim 1)

[1203] A means to receive information on stock of supplies and donation amounts sent by evacuation centers and support organizations,

[1204] a means for storing the received data in a database;

[1205] A method to analyze the received data using machine learning models to predict the shortage of supplies and the amount of donations required, and

[1206] means for recognizing emotions and prioritizing assistance when a user offers assistance;

[1207] The analysis results and emotion recognition results will be made public via the Internet, allowing users to check the information in real time.

[1208] A system including:

[1209] (Claim 2)

[1210] 2. The system according to claim 1, further comprising a means for centrally managing data transmitted from evacuation centers and support organizations by a server.

[1211] (Claim 3)

[1212] 10. The system of claim 1, further comprising means for a user to identify areas and evacuation shelters in need of assistance and provide instructions for appropriate assistance activities.

[1213] "Application example 2 when combining emotion engines"

[1214] (Claim 1)

[1215] A means to receive information on stock of supplies and donation amounts sent by evacuation centers and support organizations,

[1216] a means for storing the received data in a database;

[1217] The received data will be analyzed using an AI model to predict the shortage of supplies and the amount of donations required.

[1218] The analysis results will be published on a web page or mobile app, allowing users to check the situation in real time.

[1219] a means for recognizing emotions of a user performing a support activity using an emotion engine and prioritizing support activities based on the emotions;

[1220] It manages inventory at logistics centers and recommends optimal tasks to staff based on shortage predictions and the results of an emotion engine.

[1221] A system including:

[1222] (Claim 2)

[1223] 2. The system according to claim 1, further comprising a means for centrally managing data transmitted from evacuation centers and support organizations by a server.

[1224] (Claim 3)

[1225] 10. The system of claim 1, further comprising means for a user to identify areas and evacuation shelters in need of assistance and provide instructions for appropriate assistance activities. [Explanation of symbols]

[1226] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means to receive information on stock of supplies and donation amounts sent by evacuation centers and support organizations, a means for storing the received data in a database; The received data will be analyzed using an AI model to predict the shortage of supplies and the amount of donations required. The analysis results will be published on a web page or mobile app, allowing users to check the situation in real time. A system including:

2. 2. The system according to claim 1, further comprising a means for centrally managing data transmitted from evacuation centers and support organizations by a server.

3. 10. The system according to claim 1, further comprising means for a user to identify areas and evacuation shelters in need of assistance and to provide instructions for carrying out appropriate assistance activities.

Images