System

Abstract

To provide a system for efficiently performing the management of stockpiles and the demand prediction of supplies, and for quickly executing fund raising or the order of supplies.SOLUTION: The system includes a means for acquiring stock data from a stockpile data base and updating the latest stock information to the data base, a means for analyzing population statistics data, human flow data, and past disaster data by using an AI model to predict a material demand, a means for generating a necessary material list on the basis of the predicted material demand, a means for analyzing an emergency request received from a disaster area and specifying a kind and an amount of a necessary material, a means for preparing an optimum distribution plan on the basis of geographical information of the disaster area and demand data at the site, and determining a delivery route and means, a means for receiving and collecting fund-raising data through a cashless settlement service, a means for ordering necessary materials through online shopping, and a means for arranging the ordered materials to be quickly delivered to the disaster area through a designated delivery company and tracking a delivery situation in real time.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Traditionally, the distribution of relief supplies during disasters has relied heavily on manual work, posing numerous challenges in terms of speed, fairness of distribution, and efficiency. Furthermore, there have been frequent issues with necessary supplies not reaching victims at the right time and in the right place. In particular, manual stockpile management is prone to errors, leading to shortages and excess inventory. Furthermore, it is difficult to quickly collect donations and order supplies, which can lead to delays in the delivery of supplies to disaster-stricken areas. To solve these issues, an efficient and rapid system combining AI technology, cashless payments, and online shopping is needed. [Means for solving the problem]

[0005] The present invention solves these problems by providing a system that includes: means for acquiring inventory data from a stockpile database and updating the database with the latest inventory information; means for analyzing demographic data, people flow data, and past disaster data using an AI model to predict demand for supplies; means for generating a list of needed supplies based on the predicted demand for supplies; means for receiving emergency requests from disaster-stricken areas, analyzing the contents of the requests, and identifying the types and quantities of supplies needed; means for formulating an optimal distribution plan and determining delivery routes and means based on geographic information of the disaster-stricken areas and local demand data; means for receiving and aggregating donation data through a cashless payment service; means for ordering needed supplies through online shopping and confirming the contents of the order; and means for arranging for the ordered supplies to be delivered promptly to the disaster-stricken areas via a designated delivery company and tracking the delivery status in real time.

[0006] This allows for efficient management of stockpiles and forecasting of demand for supplies, and allows for quick donations and ordering of supplies. Furthermore, by checking delivery status in real time and responding immediately in the event of an abnormality, it is possible to distribute supplies more quickly and fairly.

[0007] The "stockpiled goods database" is a database for managing inventory information of supplies stored in preparation for disasters.

[0008] "Inventory data" is information that indicates how much of a particular item or resource is currently in stock.

[0009] An "AI model" is a collection of algorithms and technologies that mimic human intelligence to analyze data and make decisions.

[0010] "Demographic data" refers to statistical data that includes information on the age structure, birth and death rates, and migration and mobility of a particular region.

[0011] "People flow data" refers to data that indicates people's movement patterns and locations of stay, and includes information on evacuation behavior and evacuation destinations, particularly in the event of a disaster.

[0012] "Past disaster data" refers to information on the type, scale, extent of impact, and recovery status of disasters that have occurred in the past.

[0013] "Demand for supplies" is information that indicates how much of a supply is needed in a particular area or situation.

[0014] A "supply list" is a list that clearly indicates the types and quantities of supplies needed.

[0015] An "emergency request" is a request or notification sent from a disaster-stricken area requesting immediate assistance or supplies.

[0016] "Geographic information" refers to map information such as the location, topography, and traffic conditions of a specific location.

[0017] "Allocation planning" refers to the development of a plan for optimally distributing limited resources and supplies.

[0018] A "delivery route" is the optimal route for delivering goods and materials to their destination.

[0019] "Cashless payment service" refers to a service that conducts transactions electronically without using cash.

[0020] "Donation Data" is a collection of information about donation amounts and donations received from donors.

[0021] "Online shopping" is a form of electronic commerce that allows users to search for products and complete purchase procedures via the Internet.

[0022] A "delivery company" is a company or organization whose job is to receive goods or supplies from a requesting party and transport them to a designated location.

[0023] "Real-time tracking" means constantly monitoring the current situation and obtaining that information instantly. [Brief explanation of the drawings]

[0024] [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

[0025] 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.

[0026] First, the terms used in the following description will be explained.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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."

[0032] [First embodiment]

[0033] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0034] 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.

[0035] 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).

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0041] 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.

[0042] 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.

[0043] 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.

[0044] 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."

[0045] MODE FOR CARRYING OUT THE INVENTION

[0046] This invention relates to a system for optimizing the distribution of relief supplies in the event of a disaster. This system utilizes AI technology to optimize stockpile management, people flow data analysis, donation collection, and supply ordering and delivery, with the aim of minimizing shortages and surpluses of supplies in disaster-stricken areas.

[0047] Management of emergency supplies database

[0048] server

[0049] The server automatically obtains inventory data from storage facilities set up for each region. This data is updated periodically, and the latest inventory information can be reflected in the database. As a specific example, the server obtains inventory data for water transported from the storage facility in "City A" and updates the database.

[0050] Demographic data and supply demand forecasts

[0051] server

[0052] The server uses AI models to analyze demographic data, people flow data, and past disaster data to predict demand for supplies. This prediction is intended to assess how much supplies will be needed at a specific point in the future. For example, the server analyzes demographic data, people flow data, and past disaster data for "City B" and predicts that "10,000 liters of water will be needed in the next week."

[0053] Analysis of emergency requests and optimal allocation planning

[0054] server

[0055] The server receives emergency requests from disaster-stricken areas and analyzes their contents to determine the type and quantity of supplies needed. Based on this information, an AI model is used to create an optimal distribution plan. For example, if an emergency request is received from "City C" stating "5,000 liters of water is needed," the AI ​​model calculates the most efficient delivery route.

[0056] Collecting donations and ordering supplies

[0057] User

[0058] Users can make donations through a cashless payment service. These donations are aggregated in real time, and the progress is displayed to the user. For example, User D donates 1,000 yen using a cashless payment service and can check the total amount donated in real time.

[0059] server

[0060] The server generates a list of needed supplies based on the collected donation data and orders them through online shopping. For example, the server aggregates donations of 5 million yen and orders water, emergency food, blankets, etc. online based on that amount.

[0061] Delivery of supplies

[0062] server

[0063] The server arranges for the ordered supplies to be delivered promptly to the disaster area via the designated delivery company. The delivery status is tracked in real time, and any abnormalities are dealt with immediately. For example, the server arranges for "3,000 liters of water" and "5,000 emergency rations" to be delivered by the delivery company, and monitors in real time the status of the truck heading to its destination.

[0064] This will enable efficient stockpile management and optimal distribution of relief supplies using AI. Specific system components and their linkages will enable rapid and fair distribution of relief supplies.

[0065] The processing flow will be explained below.

[0066] Specific processing flow of the program

[0067] Collecting and updating stockpile data

[0068] Step 1: The server periodically obtains inventory data from storage facilities set up for each region (e.g., once a day).

[0069] Step 2: The server automatically updates the database with the acquired inventory data to reflect the latest inventory status.

[0070] Step 3: The server lists the shortages and excess supplies at this stage.

[0071] Demographic data and supply demand forecasts

[0072] Step 4: The server inputs demographic data, people flow data, and past disaster data into the AI ​​model.

[0073] Step 5: An AI model analyzes this data and predicts future demand for supplies.

[0074] Step 6: The server generates a list of required supplies based on the prediction results.

[0075] Analysis of emergency requests and optimal allocation planning

[0076] Step 7: The server receives an emergency request from the disaster area.

[0077] Step 8: The server analyzes the emergency request and identifies the type and amount of supplies needed.

[0078] Step 9: The server inputs the geographical information of the affected area and local demand data into the AI ​​model to develop an optimal distribution plan.

[0079] Step 10: The server calculates the delivery route and means and determines the optimal delivery method.

[0080] Collecting donations and ordering supplies

[0081] Step 11: The user makes a donation through a cashless payment service.

[0082] Step 12: The terminal notifies the user that the donation process is complete and displays the progress of the donation in real time.

[0083] Step 13: The server receives and aggregates donation data from the cashless payment service.

[0084] Step 14: The server generates a list of supplies needed based on the aggregated donation data.

[0085] Step 15: The server orders the necessary supplies using online shopping and confirms the order.

[0086] Delivery of supplies

[0087] Step 16: The server arranges for the ordered supplies to be delivered promptly to the disaster area by the designated delivery company.

[0088] Step 17: The server tracks the delivery status in real time and responds immediately if any abnormalities occur.

[0089] Step 18: Once delivery is complete, the server updates the database with the results and reports them to the relevant parties.

[0090] The above processing steps enable efficient stockpile management and optimal distribution of relief supplies using AI.

[0091] Example 1

[0092] 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."

[0093] The distribution of relief supplies during disasters is extremely important for protecting the lives and livelihoods of many people. However, the current system is prone to shortages and surpluses of supplies, making efficient and rapid distribution difficult. There are also many issues with analyzing emergency requests from disaster-stricken areas, collecting donations, and managing the ordering and delivery of supplies. This can lead to delays in the supply of supplies to disaster-stricken areas and insufficient support. These issues need to be resolved.

[0094] 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.

[0095] In this invention, the server includes means for retrieving inventory data from a stockpile database and updating the database with the latest inventory information, means for analyzing demographic data, people flow data, and past disaster data using a generative AI model to predict demand for supplies, means for generating a list of needed supplies based on the predicted demand, means for receiving emergency requests from disaster-stricken areas, analyzing the requests, and identifying the types and quantities of supplies needed, means for formulating an optimal distribution plan and determining delivery routes and means based on geographic information and local demand data for the disaster-stricken areas, means for receiving and aggregating donation data via a cashless payment service, means for ordering needed supplies through online ordering and confirming the order details, and means for arranging for the ordered supplies to be delivered promptly to the disaster-stricken areas via a designated delivery company and tracking the delivery status in real time. This minimizes supply shortages and surpluses, which have been a problem in the past, and enables efficient and rapid distribution of relief supplies.

[0096] The "stockpiled goods database" is a database for managing and storing information such as the type, quantity, and storage condition of supplies stockpiled in the event of a disaster.

[0097] "Inventory data" refers to information about the current quantity and status of each stockpile item stored in the stockpile database.

[0098] A "generative AI model" is an artificial intelligence model that analyzes demographic data, people flow data, and past disaster data to predict demand for supplies.

[0099] "Demographic data" is information about changes and distribution of a region's population.

[0100] "People flow data" is information about people's movement patterns in specific areas and time periods.

[0101] "Past disaster data" refers to information on the type, scale, and scope of impact of disasters that have occurred in the past.

[0102] "Demand for goods" refers to the types and quantities of goods needed at a particular time or in a particular area.

[0103] An "emergency request" is an urgent request from the disaster area regarding the type and quantity of supplies.

[0104] A "delivery route" is the optimal route for delivering goods.

[0105] "Cashless payment service" refers to a service that allows payments to be made electronically without using cash.

[0106] "Donation data" is information regarding donations collected from users.

[0107] "Online ordering" is the process of ordering supplies over the Internet.

[0108] A "delivery company" is a company that provides services to deliver ordered goods to a specified location.

[0109] "Real-time tracking" means checking and monitoring the current situation instantly.

[0110] An "anomaly" is an event or problem that deviates from the normal or expected state.

[0111] This invention is a system for optimizing the distribution of relief supplies in the event of a disaster. This system mainly involves a server, terminals, and users, each of which plays a specific role.

[0112] The server manages the emergency supplies database and automatically obtains inventory data from the emergency supplies facilities set up for each region. This data is updated periodically, and the latest inventory information is reflected in the database. For example, the server obtains inventory data for water transported from the emergency supplies facility in "Region A" and updates the database.

[0113] Next, the server uses the generative AI model to analyze demographic data, people flow data, and past disaster data to predict demand for supplies. This prediction is intended to assess how much supplies will be needed at a specific point in the future. As a specific example, the server analyzes demographic data, people flow data, and past disaster data for "Area B" and predicts that "10,000 liters of water will be needed in the next week."

[0114] Furthermore, the server receives emergency requests from disaster-stricken areas and analyzes their contents to identify the type and quantity of supplies needed. Based on this information, the generative AI model formulates an optimal distribution plan. For example, if the server receives an emergency request from "Area C" saying "5,000 liters of water is needed," the AI ​​model calculates the most efficient delivery route.

[0115] Users make donations through a cashless payment service. These donations are aggregated in real time, and the progress is displayed to the user. For example, a user donates 1,000 yen using a cashless payment service and can check the total amount donated in real time.

[0116] The server generates a list of needed supplies based on the collected donation data and orders them through online ordering. For example, the server aggregates donations of 5 million yen and orders water, emergency food, blankets, etc. online based on that amount.

[0117] The server arranges for the ordered supplies to be delivered promptly to the disaster area via the designated delivery company. The delivery status is tracked in real time, and any abnormalities are dealt with immediately. For example, the server arranges for "3,000 liters of water" and "5,000 emergency rations" to be delivered by the delivery company, and monitors in real time the status of the truck heading to its destination.

[0118] As a concrete example, the prompt text for analyzing demographic data to predict demand for goods is as follows:

[0119] "Using demographic data, people flow data, and past disaster data for Region B, please predict the demand for supplies for the next week."

[0120] In this way, this invention is a system that utilizes AI technology to achieve efficient stockpile management and optimal distribution of relief supplies. The system's components and their coordination enable rapid and fair distribution of relief supplies.

[0121] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0122] The flow of this system's program processing

[0123] Step 1: Obtaining emergency supplies data

[0124] The server automatically retrieves inventory data from each regional stockpile facility. This process is performed using API requests and is updated periodically. The input is the stockpile facility's API endpoint, and the output is the inventory data in JSON format. This data is stored in a database to reflect the latest inventory information. As a concrete example, the server retrieves water inventory data from the stockpile facility API for "Region A" and updates the database with it.

[0125] Step 2: Analyze demographic data and forecast demand

[0126] The server uses a generative AI model to analyze demographic data, people flow data, and past disaster data to predict future demand for supplies. The inputs are demographic data, people flow data, and past disaster data for each region. The AI ​​model analyzes these data and generates a demand forecast for supplies as output. Specifically, it analyzes data for "Region B" and predicts that 10,000 liters of water will be needed in the next week. For example, the prompt statement might look like this:

[0127] "Using demographic data, people flow data, and past disaster data for Region B, please predict the demand for supplies for the next week."

[0128] Step 3: Analyze emergency requests and develop optimal allocation plans

[0129] The server receives emergency requests from disaster-stricken areas and analyzes their contents using an AI model. The input is the emergency request data (XML format), and the output is the type and quantity of supplies needed. After analysis, this information is used to formulate an optimal distribution plan and calculate the optimal delivery route. For example, a request from "Area C" for "5,000 liters of water" is analyzed, and the most efficient delivery route is identified.

[0130] Step 4: Collect donations

[0131] Users make donations using a cashless payment service. The input is data on the amount donated by the user using a payment app. The server aggregates this data in real time and updates the total amount donated as output. For example, if a user donates 1,000 yen, the server updates the total amount donated to 10,000 yen.

[0132] Step 5: Order supplies

[0133] The server generates a list of needed supplies based on the collected donation data and orders the supplies online. The input is the donation data and the list of supplies, and the output is order confirmation data. As a concrete example, the server aggregates donations of 5 million yen and orders 2,000 liters of water, 5,000 emergency rations, and 200 blankets.

[0134] Step 6: Manage material delivery

[0135] The server arranges for the ordered supplies to reach the disaster area as quickly as possible. The input is order confirmation data and delivery company information, and the output is delivery status tracking data. The server monitors the delivery status in real time and responds immediately if a problem occurs. For example, it arranges for "3,000 liters of water" and "5,000 emergency rations" to be delivered by a delivery company, and monitors the delivery status in real time.

[0136] This will enable efficient and rapid distribution of relief supplies in the event of a disaster.

[0137] (Application example 1)

[0138] 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."

[0139] In recent years, as demand for food delivery services has rapidly increased, efficient inventory management, demand forecasting, and delivery route optimization have become important challenges. There is also a need for efficient management of the process of users making donations as gifts, ordering meals based on the donation amounts, and delivering them. These challenges are particularly pronounced during large-scale disasters, when a rapid and accurate response is required. The purpose of this invention is to solve these challenges and improve the efficiency of food delivery services.

[0140] 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.

[0141] In this invention, the server includes: means for acquiring inventory data from a stockpile database and updating the database with the latest inventory information; means for analyzing demographic data, people flow data, and past disaster data using an AI model to predict demand for supplies; means for generating a list of required supplies based on the predicted demand for supplies; means for receiving emergency requests from disaster-stricken areas, analyzing the contents of the requests, and identifying the types and quantities of supplies needed; means for formulating an optimal distribution plan and determining delivery routes and means based on geographic information of the disaster-stricken areas and local demand data; means for receiving and aggregating donation data through a cashless payment service; means for ordering required supplies through online shopping and confirming the order contents; means for arranging for the ordered supplies to be delivered promptly to the disaster-stricken areas via designated delivery companies and tracking the delivery status in real time; means for analyzing past order data and trend data using an AI model to predict demand for food delivery services; means for calculating optimal food delivery routes based on geographic information and operation data, and providing the routes to drivers; and means for users to make donations as gifts, order meals based on the donation amount, and arrange for delivery. This will enable food delivery services to efficiently manage inventory, forecast demand, optimize delivery routes, and provide meals through donations.

[0142] The "stockpile database" is a database for managing inventory information of ingredients and supplies for food delivery services.

[0143] "Inventory data" means data that indicates the quantity and status of ingredients and supplies in a food delivery service at a specific point in time.

[0144] "Latest inventory information" refers to regularly updated information showing the current quantity and status of ingredients and supplies in food delivery services.

[0145] An "AI model" is an artificial intelligence model used to analyze data and make predictions.

[0146] "Demographic data" refers to statistical information such as the age structure, gender, and increase or decrease of the population in a particular area.

[0147] "People flow data" refers to data on people's movement patterns and traffic flows.

[0148] "Past disaster data" refers to data on the type, scale, impact, etc. of disasters that have occurred in the past.

[0149] "Demand for goods" refers to the amount and type of goods needed at a particular time and place.

[0150] "Forecasting means" refers to methods or devices that use AI models to estimate future demand and supply requirements.

[0151] A "list of required supplies" is a list showing the types and quantities of supplies needed based on predicted demand.

[0152] An "emergency request" is a notice or request issued from a disaster-stricken area for immediate assistance.

[0153] "Geographic information" refers to information such as topography, location, and routes related to a specific area.

[0154] "Local demand data" means data relating to the specific wants and needs for goods and services at a site or region.

[0155] An "optimal allocation plan" is a plan for distributing goods and services efficiently and fairly.

[0156] A "delivery route" is the route or route for delivering goods or services.

[0157] A "cashless payment service" is a service that allows you to make payments using digital means without using cash.

[0158] "Donation data" refers to data relating to the amount of donations collected from users and the progress of the donations.

[0159] "Online shopping" is a method for purchasing goods and services over the Internet.

[0160] "Delivery status" is information that indicates the current stage and status of goods or services.

[0161] "Real-time tracking means" refers to methods and technologies for instantly checking and tracking delivery status.

[0162] "Donation as a gift" refers to a donation made by a user as a kind gesture, and the donation is used for a specific purpose.

[0163] "Operation data" refers to data related to the food delivery driver's driving route, speed, and delivery time.

[0164] An "optimal food delivery route" is a route that allows food delivery to be completed efficiently and quickly.

[0165] The present invention relates to a system for improving the efficiency of food delivery services. This system realizes fast and accurate food delivery through management of a stockpile database, demand forecasting, calculation of optimal delivery routes, and management of a donation function.

[0166] The system is implemented using hardware such as smartphones, servers, and GPS tracking devices, and software such as Python, Django, PostgreSQL, and Google Maps API.

[0167] The server first retrieves inventory data from the emergency supplies database and updates it periodically. As a specific example, it automatically retrieves food inventory data from each food delivery location and updates the database. In this process, Python is used to retrieve and update inventory data.

[0168] Next, the server uses an AI model to analyze past order data, people flow data, and past disaster data to predict demand for food delivery services. This allows it to evaluate how much food and supplies will be needed at what point in time. An example of a specific prompt is, "Please predict this month's demand based on the order data from the past six months." This AI model is built using Python and machine learning libraries (e.g., TensorFlow and scikit-learn).

[0169] The server calculates the optimal food delivery route based on geographical information and operational data, and provides it to the driver. This is achieved using the Google Maps API. An example of a specific prompt is "Please calculate the optimal delivery route to the following three order locations." This makes it possible to calculate an efficient route and provide it to the driver.

[0170] Users can make donations through a cashless payment service, and can order meals and arrange for delivery according to the amount donated. This donation data is aggregated by the server, and progress is displayed to users in real time. For example, if a user donates 1,000 yen, the system displays in real time that the total amount donated has reached 10,000 yen. This is achieved using a real-time update function using Django.

[0171] Furthermore, the system will ensure that ordered goods are delivered promptly via the designated delivery company and track the delivery status in real time using GPS tracking devices and Google Maps APIs. For example, the system will monitor the current location of delivery vehicles in real time and respond immediately if any abnormalities occur.

[0172] This system will enable food delivery services to efficiently manage inventory, forecast demand, optimize delivery routes, and provide meals through donations.

[0173] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0174] Step 1:

[0175] The server retrieves inventory data from the emergency supplies database. This inventory data includes the current quantities of food and supplies at each location. The data is periodically updated and reflected in the database. As input, the latest information from the emergency supplies database is required. As output, the latest inventory information is stored in the database.

[0176] Step 2:

[0177] The server uses an AI model to analyze past order data, people flow data, and past disaster data to predict demand for food delivery services. These datasets are required as input, and the output generates predicted demand for a specific future point in time. Specifically, the server uses Python and machine learning libraries (e.g., TensorFlow and scikit-learn) to build an AI model and perform analysis.

[0178] Step 3:

[0179] The server generates a list of required supplies based on the forecasted demand. As input, it takes the forecasted demand data obtained in step 2, and as output, it lists the types and quantities of required supplies. This list provides the specific ordering information needed for the next step.

[0180] Step 4:

[0181] The server receives emergency requests from disaster-stricken areas and users and analyzes their contents. The input required is the content of the emergency request (type and quantity of supplies), and the output extracts the specific identification and quantity of supplies. Natural language processing technology is used for the analysis to efficiently extract the necessary information.

[0182] Step 5:

[0183] The server formulates an optimal distribution plan based on geographic information and local demand data, and determines delivery routes and means. The inputs required are geographic information, local demand data, and a list of required supplies, and the output generates an optimal distribution plan and delivery route. Specifically, the server uses the Google Maps API to calculate routes and create delivery plans.

[0184] Step 6:

[0185] Users make donations through a cashless payment service. The amount donated by the user is required as input, and donation data is sent to the server as output. Users can use the payment service to check the progress of their donations in real time.

[0186] Step 7:

[0187] The server orders the necessary supplies through online shopping based on the collected donation data. The inputs are the donation data and the list of supplies from step 3, and the output is the confirmed order details. The order details are sent to the connected online shopping platform.

[0188] Step 8:

[0189] The server arranges for the ordered goods to be delivered promptly via the designated delivery company and tracks the delivery status in real time. The inputs are the order details and delivery company information, and the output is the tracking and real-time monitoring of the delivery status. Specifically, it uses a GPS tracking device to obtain the location information of the delivery vehicle and immediately notifies the user if any abnormalities occur.

[0190] The above processing steps enable efficient inventory management, demand forecasting, delivery route optimization, and donation-based meal provision for food delivery services.

[0191] 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.

[0192] MODE FOR CARRYING OUT THE INVENTION

[0193] This invention relates to a system for optimizing the distribution of relief supplies in the event of a disaster. This system utilizes AI technology and an emotion engine to optimize stockpile management, people flow data analysis, donation collection, and supply ordering and delivery, with the aim of minimizing shortages and surpluses of supplies in disaster-stricken areas.

[0194] Management of emergency supplies database

[0195] server

[0196] The server automatically retrieves inventory data from stockpiles set up for each region and periodically updates the database, ensuring that inventory information is always up to date and instantly listing shortages and surplus supplies.

[0197] (Example)

[0198] The server retrieves inventory data for water and medical supplies from the storage facility in "City A" and updates the database. At this time, it lists shortages (e.g., 500 liters of water, 2,000 masks) and excess inventory (e.g., 1,000 cans of food).

[0199] Demographic data and supply demand forecasts

[0200] server

[0201] The server inputs demographic data, human flow data, and data from past disasters into an AI model to predict demand for supplies, which then evaluates the amount of supplies that will be needed at a specific point in time in the future.

[0202] (Example)

[0203] The server analyzes demographic data, people flow data, and past disaster data for "City B" and predicts that "10,000 liters of water and 5,000 emergency meals will be needed over the next week."

[0204] Analysis of emergency requests and optimal allocation planning

[0205] server

[0206] The server receives emergency requests from disaster-stricken areas and analyzes their contents to determine the type and quantity of supplies needed. Based on this, an AI model is used to create an optimal distribution plan, determining delivery routes and methods.

[0207] (Example)

[0208] An emergency request for 5,000 liters of water is received from City C, and the AI ​​model calculates the most efficient delivery route, taking into account evacuation routes and traffic conditions.

[0209] Aggregating donations and ordering supplies using an emotion engine

[0210] User

[0211] Before a user makes a donation through the cashless payment service, the emotion engine recognizes the user's emotions, and appropriate donation campaigns and suggestions are displayed based on the recognition results.

[0212] (Example)

[0213] When User D uses the cashless payment service, the emotion engine recognizes User D's emotions, such as "empathy" and "sense of crisis," and suggests "disaster relief donations." User D donates 1,000 yen and checks the total amount and progress in real time.

[0214] server

[0215] The server generates a list of needed supplies based on the collected donation data and orders the supplies through online shopping.

[0216] (Example)

[0217] The server tallies the 5 million yen in donations and orders water, emergency food, blankets, etc. online based on that amount. The order details are confirmed and dispatched to a delivery company.

[0218] Delivery of supplies

[0219] server

[0220] The server then arranges for the ordered supplies to be delivered to the disaster area as quickly as possible. Delivery status is tracked in real time, and any abnormalities are dealt with immediately.

[0221] (Example)

[0222] The server arranges for 3,000 liters of water and 5,000 emergency rations to be delivered to a designated delivery company, and monitors the truck's progress in real time as it heads to its destination. If the truck gets stuck in traffic, the server notifies the delivery company of an alternative route.

[0223] This will enable efficient stockpile management and optimal distribution of relief supplies by combining AI technology and an emotion engine. Specific system components and their linkages will enable rapid and fair distribution of relief supplies.

[0224] The processing flow will be explained below.

[0225] Specific processing flow of the program

[0226] Collecting and updating stockpile data

[0227] Step 1: The server periodically obtains inventory data from storage facilities set up for each region (e.g., once a day).

[0228] Step 2: The server automatically updates the database with the acquired inventory data to reflect the latest inventory status.

[0229] Step 3: The server lists the shortages and excess supplies at this stage.

[0230] Demographic data and supply demand forecasts

[0231] Step 4: The server inputs demographic data, people flow data, and past disaster data into the AI ​​model.

[0232] Step 5: An AI model analyzes this data and predicts future demand for supplies.

[0233] Step 6: The server generates a list of required supplies based on the prediction results.

[0234] Analysis of emergency requests and optimal allocation planning

[0235] Step 7: The server receives an emergency request from the disaster area.

[0236] Step 8: The server analyzes the emergency request and identifies the type and amount of supplies needed.

[0237] Step 9: The server inputs the geographical information of the affected area and local demand data into the AI ​​model to develop an optimal distribution plan.

[0238] Step 10: The server calculates the delivery route and means and determines the optimal delivery method.

[0239] Aggregating donations and ordering supplies using an emotion engine

[0240] Step 11: Before the user makes a donation using the cashless payment service, the terminal recognizes the user's emotions using the emotion engine.

[0241] Step 12: The terminal displays appropriate fundraising campaigns and proposals to the user based on the emotions (e.g., "empathy," "sense of crisis," etc.) recognized by the emotion engine.

[0242] Step 13: The user makes a donation based on the proposed fundraising campaign.

[0243] Step 14: The terminal notifies the user that the donation process is complete and displays the progress of the donation in real time.

[0244] Step 15: The server receives and aggregates donation data from the cashless payment service.

[0245] Step 16: The server generates a list of supplies needed based on the aggregated donation data.

[0246] Step 17: The server orders the necessary supplies using online shopping and confirms the order.

[0247] Delivery of supplies

[0248] Step 18: The server arranges for the ordered supplies to be delivered promptly to the disaster area by the designated delivery company.

[0249] Step 19: The server tracks the delivery status in real time and responds immediately if any abnormalities occur.

[0250] Step 20: Once delivery is complete, the server updates the database with the results and reports them to the relevant parties.

[0251] Example 2

[0252] 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."

[0253] In times of disaster, it is necessary to prevent shortages or excesses of relief supplies and distribute necessary supplies to disaster-stricken areas quickly and efficiently. However, in conventional systems, inventory data is often managed manually, and the latest information may not be reflected. Furthermore, adequate forecasting of supply demand using demographic data and past disaster data is not performed, making it difficult to formulate appropriate supply distribution plans. Furthermore, functions for user emotion recognition during fundraising activities, real-time tracking during supply delivery, and abnormality response are also insufficient. To solve these problems, the present invention proposes a new system.

[0254] 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.

[0255] In this invention, the server includes means for retrieving inventory data from a stockpile database and updating the database with the latest inventory information, means for inputting demographic data, people flow data, and past disaster data into a generative AI model as prompt sentences to predict demand for supplies, means for generating a list of needed supplies based on the predicted demand for supplies, means for receiving emergency requests from disaster-stricken areas, analyzing the requests, and identifying the types and quantities of needed supplies, means for formulating an optimal distribution plan and determining delivery routes and means based on geographic information of the disaster-stricken area and local demand data, means for recognizing user emotions using an emotion engine, receiving and aggregating donation data through a cashless payment service, means for ordering needed supplies through online shopping and confirming the order details, and means for arranging for the ordered supplies to be delivered promptly to the disaster-stricken area via a designated delivery company and tracking the delivery status in real time. This makes it possible to minimize shortages and excesses of relief supplies during disasters and quickly and efficiently distribute needed supplies to disaster-stricken areas.

[0256] The "stockpile database" is a data storage system that manages inventory information for relief supplies needed in the event of a disaster and stores data collected from stockpile facilities in each region.

[0257] "Inventory data" is information on the types and quantities of relief supplies stored at each stockpile facility.

[0258] A "generative AI model" is an artificial intelligence algorithm that analyzes input data and makes predictions and optimizations according to specific objectives.

[0259] A "prompt" is text in the form of a question or command that gives instructions to a generative AI model.

[0260] "Supply demand forecasting" is the process of predicting the quantity and type of relief supplies needed for a specific period in the future.

[0261] An "urgent request" is an urgent request or communication requesting assistance for relief supplies to be sent from a disaster area.

[0262] An "allocation plan" is a plan that determines how relief supplies will be distributed and through which routes they will be delivered most efficiently.

[0263] An "emotion engine" is a software engine that recognizes the user's emotions and responds appropriately or makes suggestions based on those emotions.

[0264] A "cashless payment service" is a service that allows payments to be made electronically without using cash.

[0265] "Fundraising Data" means information relating to the amount of money raised through a fundraising activity and the progress of that fundraising.

[0266] "Online shopping" is a system for ordering and purchasing products via the Internet.

[0267] A "delivery company" is a company or organization that provides logistics services to deliver ordered goods to a specified location.

[0268] "Real-time tracking" is the process of monitoring the delivery status of goods in real time and instantly understanding their current location and progress.

[0269] "Anomaly response" is a method of quickly taking measures to resolve problems when any issues or failures occur during delivery.

[0270] MODE FOR CARRYING OUT THE INVENTION

[0271] This invention is a system that optimizes the distribution of relief supplies during disasters. It aims to minimize shortages and surpluses of supplies in disaster-stricken areas by utilizing AI technology and an emotion engine to optimize stockpile management, analysis of people flow data, collection of donations, and supply ordering and delivery.

[0272] System Configuration

[0273] Hardware and Software

[0274] Server: Plays a central role in collecting, analyzing, storing data, and formulating delivery plans. Uses cloud or on-premise servers as needed.

[0275] Device: A PC or smartphone operated by the user, used to check the status of donations and deliveries.

[0276] AI Model: Perform data analysis and demand forecasting using generative AI models.

[0277] Emotion Engine: Recognizes user emotions and makes appropriate donation suggestions.

[0278] Cashless payment service: Used to collect donations.

[0279] Online shopping system: Used to order necessary supplies.

[0280] Carrier system: Used to arrange and track deliveries.

[0281] Management of emergency supplies database

[0282] The server automatically retrieves inventory data from stockpiles set up for each region and periodically updates the database, thus maintaining up-to-date inventory information and listing shortages and excess supplies.

[0283] (Example)

[0284] The server retrieves inventory data for water and medical supplies from the storage facility in "City A" using an API and updates the database. It lists shortages (e.g., 500 liters of water, 2,000 masks) and excess inventory (e.g., 1,000 cans of food).

[0285] Demographic data and supply demand forecasts

[0286] The server collects demographic data, human flow data, and past disaster data for each region, and inputs this data into a generative AI model as prompts to predict supply demand. This process evaluates the amount of supplies that will be needed at a specific point in the future.

[0287] (Example)

[0288] The server inputs demographic data, human flow data, and past disaster data for "City B" into the generative AI model and makes a prediction using a prompt such as "Please predict City B's demand for supplies over the next week." The resulting prediction is "10,000 liters of water and 5,000 emergency rations will be needed over the next week."

[0289] Analysis of emergency requests and optimal allocation planning

[0290] The server receives emergency requests from disaster-stricken areas, analyzes their contents, and identifies the types and quantities of supplies needed. Based on this, a generative AI model formulates an optimal distribution plan and determines delivery routes and methods.

[0291] (Example)

[0292] An emergency request for 5,000 liters of water is received from "City C," and the AI ​​model calculates the optimal delivery route. The server then formulates the most efficient delivery plan, taking into account evacuation routes and traffic conditions.

[0293] Aggregating donations and ordering supplies using an emotion engine

[0294] Before a user makes a donation through a cashless payment service, an emotion engine recognizes the user's emotions and displays appropriate donation campaigns and suggestions.

[0295] (Example)

[0296] When User D uses the cashless payment service, the emotion engine recognizes User D's emotions, such as "empathy" and "sense of crisis," and suggests "disaster relief donations." User D donates 1,000 yen and checks the total amount and progress in real time.

[0297] The server generates a list of needed supplies based on the collected donation data and orders them through an online shopping system.

[0298] (Example)

[0299] The server tallies the 5 million yen in donations and orders water, emergency food, blankets, etc. online based on that amount. The order details are confirmed and dispatched to a delivery company.

[0300] Delivery of supplies

[0301] The server will then arrange for the ordered supplies to be delivered to the affected areas as quickly as possible. Delivery status will be tracked in real time, and any irregularities will be dealt with immediately.

[0302] (Example)

[0303] The server arranges for 3,000 liters of water and 5,000 emergency rations to be delivered to a designated delivery company, and monitors the truck's progress in real time as it heads to its destination. If the truck gets stuck in traffic, the server notifies the delivery company of an alternative route.

[0304] In this way, the present invention combines AI technology and an emotion engine to achieve efficient and fair distribution of relief supplies. Specific system components and their cooperation enable rapid and reliable response.

[0305] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0306] The flow of this system's program processing

[0307] Step 1: Acquire and manage emergency supply data

[0308] Input: Inventory data from each regional stockpile facility

[0309] Output: A database containing the latest inventory information

[0310] The server automatically retrieves inventory data from local stockpiles by accessing the stockpiles' APIs. The server then updates the database with the latest inventory information and lists shortages and surplus supplies.

[0311] Specific operation:

[0312] 1. The server accesses the storage facility's API and obtains inventory data for water, medical supplies, emergency food, etc.

[0313] 2. The server stores the acquired data in a database and compares it with past data to list shortages and surplus items.

[0314] 3. The list generated by the server is displayed on the management screen so that the person in charge can keep track of the latest inventory status.

[0315] Step 2: Demographic data and supply demand forecasts

[0316] Input: Demographic data, human flow data, past disaster data

[0317] Output: A list of predicted material demands

[0318] The server collects demographic data, human flow data, and past disaster data for each region, and inputs this data as prompts into the generative AI model, which then analyzes the data and predicts demand for supplies.

[0319] Specific operation:

[0320] 1. The server collects the necessary data from demographic and population flow databases.

[0321] 2. The server generates a prompt such as "Please predict the supply demand for city B over the next week."

[0322] 3. The server inputs the prompt and collected data into the generative AI model.

[0323] 4. The AI ​​model analyzes the data and outputs the predicted amount of supplies needed.

[0324] 5. The server saves the prediction results in a database and displays them on the management screen.

[0325] Step 3: Analysis of emergency requests and optimal allocation plan

[0326] Input: Emergency request data from the affected area, geographic information of the affected area, local demand data

[0327] Output: Optimal material allocation plan and delivery route

[0328] The server receives emergency requests from disaster-stricken areas, analyzes their contents, and identifies the types and quantities of supplies needed. It then uses a generative AI model to create an optimal distribution plan and determine delivery routes and methods.

[0329] Specific operation:

[0330] 1. The server receives an emergency request from the disaster area.

[0331] 2. The server analyzes the emergency request and identifies the type and quantity of supplies needed.

[0332] 3. The server generates a prompt such as "Please suggest the optimal route and means to deliver this item."

[0333] 4. The server inputs the prompt text, emergency request data, geographic information, and local demand data into the generative AI model.

[0334] 5. The AI ​​model analyzes and outputs the optimal allocation plan.

[0335] 6. The server saves the allocation plan in the database and displays it on the management screen.

[0336] Step 4: Using the Emotion Engine to Raise Funds and Order Supplies

[0337] Input: User payment information, sentiment data, donation data

[0338] Output: Received donation data, order list for needed supplies

[0339] Before a user makes a donation through a cashless payment service, an emotion engine recognizes the user's emotions and displays appropriate donation campaigns and suggestions.

[0340] Specific operation:

[0341] 1. A user accesses the donation page using a cashless payment service.

[0342] 2. The emotion engine recognizes the user's face and detects "empathy" or "sense of crisis."

[0343] 3. The emotion engine suggests fundraising campaigns based on the user's emotions.

[0344] 4. The user enters the donation amount and completes the cashless payment.

[0345] The server generates a list of needed supplies based on the collected donation data and orders them through online shopping.

[0346] Specific operation:

[0347] 1. The server stores the donation data in a database.

[0348] 2. The server generates a prompt such as "Please create a list of items to be purchased with the 5 million yen donation."

[0349] 3. The server inputs the prompt and donation data into the generative AI model.

[0350] 4. The AI ​​model analyzes and outputs a list of necessary supplies.

[0351] 5. The server orders the necessary supplies through the online shopping system and confirms the order.

[0352] 6. The server notifies the delivery company of the order details so that the order can be processed.

[0353] Step 5: Delivering supplies

[0354] Input: Order data, delivery company information, delivery route information

[0355] Output: Real-time monitoring data on delivery status, response information in case of abnormalities

[0356] The server arranges for the ordered supplies to be delivered promptly to the disaster area, tracks the delivery status in real time, and responds immediately if any abnormalities occur.

[0357] Specific operation:

[0358] 1. The server communicates with the delivery company and confirms the delivery arrangements for the goods.

[0359] 2. The server monitors the delivery truck's GPS data and tracks its progress in real time.

[0360] 3. If the server detects an abnormality, it notifies the delivery company of an alternative route and reroutes the truck.

[0361] 4. The server displays delivery status and progress on the management screen, allowing the person in charge to check it in real time.

[0362] Following this procedure, the system effectively manages and optimizes the distribution of relief supplies.

[0363] (Application example 2)

[0364] 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."

[0365] Conventional systems for distributing relief supplies during disasters have had difficulty in forecasting demand and responding to emergency requests, and efficiently and fairly distributing supplies. In particular, the lack of appropriate proposals that take into account fluctuations in traffic conditions and user emotions often makes it difficult to deliver supplies quickly and manage donation campaigns effectively.

[0366] 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 acquiring inventory data from a stockpile database and updating the database with the latest inventory information; means for analyzing demographic data, people flow data, and past disaster data using an AI model to predict demand for supplies; means for generating a list of needed supplies based on the predicted demand for supplies; means for receiving emergency requests from disaster-stricken areas, analyzing the contents of the requests, and identifying the types and quantities of needed supplies; means for formulating an optimal distribution plan and determining delivery routes and means based on geographic information of the disaster-stricken areas and local demand data; means for receiving and aggregating donation data through a cashless payment service; means for ordering needed supplies through online shopping and confirming the order contents; means for arranging for the ordered supplies to be delivered promptly to the disaster-stricken areas via a designated delivery company and tracking the delivery status in real time; means for acquiring real-time traffic conditions and notifying of dynamic route changes; and means for analyzing a user's emotions using an emotion recognition engine and making appropriate suggestions. This will enable efficient and fair distribution of relief supplies through rapid delivery that adapts to changes in traffic conditions and effective donation suggestions based on user emotions.

[0367] The "stockpile database" is a database that records and manages inventory information for supplies needed in the event of a disaster.

[0368] "Inventory data" refers to information regarding the types and quantities of supplies recorded in the stockpile database.

[0369] An "AI model" is an algorithm that uses artificial intelligence technology to analyze data and make predictions.

[0370] "Demographic data" refers to data on population changes and composition by region.

[0371] "People flow data" refers to data about the movement of people within and outside a specific area.

[0372] "Demand for goods" refers to the quantity and type of goods required within a specific period of time.

[0373] An "emergency request" is a request for relief supplies from an affected area during a disaster.

[0374] "Geographic information" refers to data about the geographic characteristics and traffic conditions of a particular area.

[0375] An "allocation plan" is a plan that determines the optimal delivery route and distribution method for supplies.

[0376] "Cashless payment service" refers to a means of transferring funds electronically without using cash.

[0377] "Fundraising Data" means information about funds raised through fundraising activities.

[0378] "Online shopping" refers to the process of purchasing goods over the Internet.

[0379] "Delivery company" means a company that transports goods to a specified location.

[0380] "Real-time" refers to processing data and providing information on the same time axis as the current time.

[0381] "Traffic conditions" refers to data on vehicle flow and congestion in specific areas and routes.

[0382] "Dynamic routing" refers to instantly adjusting and changing delivery routes based on real-time traffic information.

[0383] An "emotion recognition engine" is a technology that analyzes a user's emotions and makes appropriate suggestions based on the results.

[0384] This invention provides a system for optimizing the distribution of relief supplies during disasters. The system utilizes AI technology and an emotion recognition engine to optimize stockpile management, people flow data analysis, donation collection, and supply ordering and delivery. This will also minimize shortages and surpluses of supplies in disaster-stricken areas.

[0385] Hardware and software used

[0386] Hardware

[0387] Server: High-performance processor, SSD storage, and sufficient RAM

[0388] Devices: Smartphones, devices with GPS

[0389] software

[0390] Programming language: Python

[0391] Web framework: Django

[0392] Machine learning library: Scikit-learn (Sklearn)

[0393] Data processing and calculation flow

[0394] Management of emergency supplies database

[0395] The server automatically retrieves inventory data from stockpiles set up for each region and periodically updates the database, ensuring that inventory information is always up to date and instantly listing shortages and surplus supplies.

[0396] Demographic data and supply demand forecasts

[0397] The server inputs demographic data, human flow data, and data from past disasters into an AI model to predict demand for supplies, which then evaluates the amount of supplies that will be needed at a specific point in time in the future.

[0398] Analysis of emergency requests and optimal allocation planning

[0399] The server receives emergency requests from disaster-stricken areas and analyzes their contents to determine the type and quantity of supplies needed. Based on this, an AI model is used to create an optimal distribution plan, determining delivery routes and means. It also adds a function to obtain real-time traffic conditions and notify of dynamic route changes.

[0400] Aggregating donations and ordering supplies using an emotion recognition engine

[0401] Before a user makes a donation through the cashless payment service, an emotion recognition engine recognizes the user's emotions. Based on the recognition results, appropriate donation campaigns and donation suggestions are displayed. The server also generates a list of needed supplies based on the collected donation data and orders the supplies through online shopping.

[0402] Delivery of supplies

[0403] The server then arranges for the ordered supplies to be delivered to the disaster area as quickly as possible. Delivery status is tracked in real time, and any abnormalities are dealt with immediately.

[0404] Examples and prompts

[0405] Example 1

[0406] During a disaster, when water supplies are tight in a certain area, the server uses stockpile information and past data to predict demand for the next week and generate a list of necessary supplies.

[0407] Example 2

[0408] When a user uses the cashless payment service, an emotion recognition engine recognizes the user's "empathy" or "sense of crisis" and suggests "disaster relief donations." The user can donate and check the total amount and progress in real time.

[0409] Prompt Sentence Examples

[0410] "The emotion recognition engine should suggest the most appropriate menu based on the user's emotional state."

[0411] "Please provide the best way to notify dynamic route changes according to traffic conditions in the affected area."

[0412] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0413] Step 1:

[0414] The server retrieves inventory data from each regional stockpile facility and periodically updates this data in a database. The input data is the type and amount of inventory at each stockpile facility, and the output is a database containing the latest inventory information. At this time, shortages and excess inventory are listed.

[0415] Step 2:

[0416] The server acquires demographic data, human flow data, and past disaster data, and inputs this into an AI model to predict demand for supplies. The input data is data on regional population changes and past disasters, and based on this, a forecast of supply demand is output. This forecast includes the amount and type of supplies that will be needed at a specific point in the future.

[0417] Step 3:

[0418] The server generates a list of required supplies based on predicted demand. It uses the output of the demand forecast from the AI ​​model to list the specific supplies and quantities needed. The input is predicted demand data, and the output is a list of required supplies.

[0419] Step 4:

[0420] The server receives emergency requests from disaster-stricken areas, analyzes their contents, and identifies the types and quantities of supplies needed. The input data is the content of the emergency request, and the output is the identified types and quantities of supplies needed. The server then formulates an optimal distribution plan based on this information.

[0421] Step 5:

[0422] The server formulates an optimal distribution plan based on geographic information of the affected area and local demand data, and determines delivery routes and means. The input data is geographic information and demand data, and the output is an optimal distribution plan and delivery route. Routes are dynamically changed, taking into account real-time traffic conditions.

[0423] Step 6:

[0424] The server receives and aggregates donation data through a cashless payment service. The input data is donation information from users, and the output is aggregated donation data. Based on this data, a list of necessary supplies is generated and the supplies are ordered through online shopping.

[0425] Step 7:

[0426] When a user makes a cashless payment, the emotion recognition engine recognizes the user's emotions and then proposes appropriate donation campaigns and suggestions based on the results. The input data is the user's emotion data, and the output is appropriate donation campaigns and suggestions.

[0427] Step 8:

[0428] The server arranges for the ordered supplies to be delivered to the disaster area promptly and tracks the delivery status in real time. The input data is the order information and delivery status of the supplies, and the output is the real-time delivery status. If an abnormality occurs, it responds immediately.

[0429] Specific examples

[0430] Example prompt sentence:

[0431] Let the emotion recognition engine suggest the most appropriate menu based on the user's emotional state.

[0432] 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.

[0433] 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.

[0434] 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.

[0435] [Second embodiment]

[0436] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0437] 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.

[0438] 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).

[0439] 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.

[0440] 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.

[0441] 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).

[0442] 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.

[0443] 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.

[0444] 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.

[0445] 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.

[0446] 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.

[0447] 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."

[0448] MODE FOR CARRYING OUT THE INVENTION

[0449] This invention relates to a system for optimizing the distribution of relief supplies in the event of a disaster. This system utilizes AI technology to optimize stockpile management, people flow data analysis, donation collection, and supply ordering and delivery, with the aim of minimizing shortages and surpluses of supplies in disaster-stricken areas.

[0450] Management of emergency supplies database

[0451] server

[0452] The server automatically obtains inventory data from storage facilities set up for each region. This data is updated periodically, and the latest inventory information can be reflected in the database. As a specific example, the server obtains inventory data for water transported from the storage facility in "City A" and updates the database.

[0453] Demographic data and supply demand forecasts

[0454] server

[0455] The server uses AI models to analyze demographic data, people flow data, and past disaster data to predict demand for supplies. This prediction is intended to assess how much supplies will be needed at a specific point in the future. For example, the server analyzes demographic data, people flow data, and past disaster data for "City B" and predicts that "10,000 liters of water will be needed in the next week."

[0456] Analysis of emergency requests and optimal allocation planning

[0457] server

[0458] The server receives emergency requests from disaster-stricken areas and analyzes their contents to determine the type and quantity of supplies needed. Based on this information, an AI model is used to create an optimal distribution plan. For example, if an emergency request is received from "City C" stating "5,000 liters of water is needed," the AI ​​model calculates the most efficient delivery route.

[0459] Collecting donations and ordering supplies

[0460] User

[0461] Users can make donations through a cashless payment service. These donations are aggregated in real time, and the progress is displayed to the user. For example, User D donates 1,000 yen using a cashless payment service and can check the total amount donated in real time.

[0462] server

[0463] The server generates a list of needed supplies based on the collected donation data and orders them through online shopping. For example, the server aggregates donations of 5 million yen and orders water, emergency food, blankets, etc. online based on that amount.

[0464] Delivery of supplies

[0465] server

[0466] The server arranges for the ordered supplies to be delivered promptly to the disaster area via the designated delivery company. The delivery status is tracked in real time, and any abnormalities are dealt with immediately. For example, the server arranges for "3,000 liters of water" and "5,000 emergency rations" to be delivered by the delivery company, and monitors in real time the status of the truck heading to its destination.

[0467] This will enable efficient stockpile management and optimal distribution of relief supplies using AI. Specific system components and their linkages will enable rapid and fair distribution of relief supplies.

[0468] The processing flow will be explained below.

[0469] Specific processing flow of the program

[0470] Collecting and updating stockpile data

[0471] Step 1: The server periodically obtains inventory data from storage facilities set up for each region (e.g., once a day).

[0472] Step 2: The server automatically updates the database with the acquired inventory data to reflect the latest inventory status.

[0473] Step 3: The server lists the shortages and excess supplies at this stage.

[0474] Demographic data and supply demand forecasts

[0475] Step 4: The server inputs demographic data, people flow data, and past disaster data into the AI ​​model.

[0476] Step 5: An AI model analyzes this data and predicts future demand for supplies.

[0477] Step 6: The server generates a list of required supplies based on the prediction results.

[0478] Analysis of emergency requests and optimal allocation planning

[0479] Step 7: The server receives an emergency request from the disaster area.

[0480] Step 8: The server analyzes the emergency request and identifies the type and amount of supplies needed.

[0481] Step 9: The server inputs the geographical information of the affected area and local demand data into the AI ​​model to develop an optimal distribution plan.

[0482] Step 10: The server calculates the delivery route and means and determines the optimal delivery method.

[0483] Collecting donations and ordering supplies

[0484] Step 11: The user makes a donation through a cashless payment service.

[0485] Step 12: The terminal notifies the user that the donation process is complete and displays the progress of the donation in real time.

[0486] Step 13: The server receives and aggregates donation data from the cashless payment service.

[0487] Step 14: The server generates a list of supplies needed based on the aggregated donation data.

[0488] Step 15: The server orders the necessary supplies using online shopping and confirms the order.

[0489] Delivery of supplies

[0490] Step 16: The server arranges for the ordered supplies to be delivered promptly to the disaster area by the designated delivery company.

[0491] Step 17: The server tracks the delivery status in real time and responds immediately if any abnormalities occur.

[0492] Step 18: Once delivery is complete, the server updates the database with the results and reports them to the relevant parties.

[0493] The above processing steps enable efficient stockpile management and optimal distribution of relief supplies using AI.

[0494] Example 1

[0495] 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."

[0496] The distribution of relief supplies during disasters is extremely important for protecting the lives and livelihoods of many people. However, the current system is prone to shortages and surpluses of supplies, making efficient and rapid distribution difficult. There are also many issues with analyzing emergency requests from disaster-stricken areas, collecting donations, and managing the ordering and delivery of supplies. This can lead to delays in the supply of supplies to disaster-stricken areas and insufficient support. These issues need to be resolved.

[0497] 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.

[0498] In this invention, the server includes means for retrieving inventory data from a stockpile database and updating the database with the latest inventory information, means for analyzing demographic data, people flow data, and past disaster data using a generative AI model to predict demand for supplies, means for generating a list of needed supplies based on the predicted demand, means for receiving emergency requests from disaster-stricken areas, analyzing the requests, and identifying the types and quantities of supplies needed, means for formulating an optimal distribution plan and determining delivery routes and means based on geographic information and local demand data for the disaster-stricken areas, means for receiving and aggregating donation data via a cashless payment service, means for ordering needed supplies through online ordering and confirming the order details, and means for arranging for the ordered supplies to be delivered promptly to the disaster-stricken areas via a designated delivery company and tracking the delivery status in real time. This minimizes supply shortages and surpluses, which have been a problem in the past, and enables efficient and rapid distribution of relief supplies.

[0499] The "stockpiled goods database" is a database for managing and storing information such as the type, quantity, and storage condition of supplies stockpiled in the event of a disaster.

[0500] "Inventory data" refers to information about the current quantity and status of each stockpile item stored in the stockpile database.

[0501] A "generative AI model" is an artificial intelligence model that analyzes demographic data, people flow data, and past disaster data to predict demand for supplies.

[0502] "Demographic data" is information about changes and distribution of a region's population.

[0503] "People flow data" is information about people's movement patterns in specific areas and time periods.

[0504] "Past disaster data" refers to information on the type, scale, and scope of impact of disasters that have occurred in the past.

[0505] "Demand for goods" refers to the types and quantities of goods needed at a particular time or in a particular area.

[0506] An "emergency request" is an urgent request from the disaster area regarding the type and quantity of supplies.

[0507] A "delivery route" is the optimal route for delivering goods.

[0508] "Cashless payment service" refers to a service that allows payments to be made electronically without using cash.

[0509] "Donation data" is information regarding donations collected from users.

[0510] "Online ordering" is the process of ordering supplies over the Internet.

[0511] A "delivery company" is a company that provides services to deliver ordered goods to a specified location.

[0512] "Real-time tracking" means checking and monitoring the current situation instantly.

[0513] An "anomaly" is an event or problem that deviates from the normal or expected state.

[0514] This invention is a system for optimizing the distribution of relief supplies in the event of a disaster. This system mainly involves a server, terminals, and users, each of which plays a specific role.

[0515] The server manages the emergency supplies database and automatically obtains inventory data from the emergency supplies facilities set up for each region. This data is updated periodically, and the latest inventory information is reflected in the database. For example, the server obtains inventory data for water transported from the emergency supplies facility in "Region A" and updates the database.

[0516] Next, the server uses the generative AI model to analyze demographic data, people flow data, and past disaster data to predict demand for supplies. This prediction is intended to assess how much supplies will be needed at a specific point in the future. As a specific example, the server analyzes demographic data, people flow data, and past disaster data for "Area B" and predicts that "10,000 liters of water will be needed in the next week."

[0517] Furthermore, the server receives emergency requests from disaster-stricken areas and analyzes their contents to identify the type and quantity of supplies needed. Based on this information, the generative AI model formulates an optimal distribution plan. For example, if the server receives an emergency request from "Area C" saying "5,000 liters of water is needed," the AI ​​model calculates the most efficient delivery route.

[0518] Users make donations through a cashless payment service. These donations are aggregated in real time, and the progress is displayed to the user. For example, a user donates 1,000 yen using a cashless payment service and can check the total amount donated in real time.

[0519] The server generates a list of needed supplies based on the collected donation data and orders them through online ordering. For example, the server aggregates donations of 5 million yen and orders water, emergency food, blankets, etc. online based on that amount.

[0520] The server arranges for the ordered supplies to be delivered promptly to the disaster area via the designated delivery company. The delivery status is tracked in real time, and any abnormalities are dealt with immediately. For example, the server arranges for "3,000 liters of water" and "5,000 emergency rations" to be delivered by the delivery company, and monitors in real time the status of the truck heading to its destination.

[0521] As a concrete example, the prompt text for analyzing demographic data to predict demand for goods is as follows:

[0522] "Using demographic data, people flow data, and past disaster data for Region B, please predict the demand for supplies for the next week."

[0523] In this way, this invention is a system that utilizes AI technology to achieve efficient stockpile management and optimal distribution of relief supplies. The system's components and their coordination enable rapid and fair distribution of relief supplies.

[0524] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0525] The flow of this system's program processing

[0526] Step 1: Obtaining emergency supplies data

[0527] The server automatically retrieves inventory data from each regional stockpile facility. This process is performed using API requests and is updated periodically. The input is the stockpile facility's API endpoint, and the output is the inventory data in JSON format. This data is stored in a database to reflect the latest inventory information. As a concrete example, the server retrieves water inventory data from the stockpile facility API for "Region A" and updates the database with it.

[0528] Step 2: Analyze demographic data and forecast demand

[0529] The server uses a generative AI model to analyze demographic data, people flow data, and past disaster data to predict future demand for supplies. The inputs are demographic data, people flow data, and past disaster data for each region. The AI ​​model analyzes these data and generates a demand forecast for supplies as output. Specifically, it analyzes data for "Region B" and predicts that 10,000 liters of water will be needed in the next week. For example, the prompt statement might look like this:

[0530] "Using demographic data, people flow data, and past disaster data for Region B, please predict the demand for supplies for the next week."

[0531] Step 3: Analyze emergency requests and develop optimal allocation plans

[0532] The server receives emergency requests from disaster-stricken areas and analyzes their contents using an AI model. The input is the emergency request data (XML format), and the output is the type and quantity of supplies needed. After analysis, this information is used to formulate an optimal distribution plan and calculate the optimal delivery route. For example, a request from "Area C" for "5,000 liters of water" is analyzed, and the most efficient delivery route is identified.

[0533] Step 4: Collect donations

[0534] Users make donations using a cashless payment service. The input is data on the amount donated by the user using a payment app. The server aggregates this data in real time and updates the total amount donated as output. For example, if a user donates 1,000 yen, the server updates the total amount donated to 10,000 yen.

[0535] Step 5: Order supplies

[0536] The server generates a list of needed supplies based on the collected donation data and orders the supplies online. The input is the donation data and the list of supplies, and the output is order confirmation data. As a concrete example, the server aggregates donations of 5 million yen and orders 2,000 liters of water, 5,000 emergency rations, and 200 blankets.

[0537] Step 6: Manage material delivery

[0538] The server arranges for the ordered supplies to reach the disaster area as quickly as possible. The input is order confirmation data and delivery company information, and the output is delivery status tracking data. The server monitors the delivery status in real time and responds immediately if a problem occurs. For example, it arranges for "3,000 liters of water" and "5,000 emergency rations" to be delivered by a delivery company, and monitors the delivery status in real time.

[0539] This will enable efficient and rapid distribution of relief supplies in the event of a disaster.

[0540] (Application example 1)

[0541] 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."

[0542] In recent years, as demand for food delivery services has rapidly increased, efficient inventory management, demand forecasting, and delivery route optimization have become important challenges. There is also a need for efficient management of the process of users making donations as gifts, ordering meals based on the donation amounts, and delivering them. These challenges are particularly pronounced during large-scale disasters, when a rapid and accurate response is required. The purpose of this invention is to solve these challenges and improve the efficiency of food delivery services.

[0543] 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.

[0544] In this invention, the server includes: means for acquiring inventory data from a stockpile database and updating the database with the latest inventory information; means for analyzing demographic data, people flow data, and past disaster data using an AI model to predict demand for supplies; means for generating a list of required supplies based on the predicted demand for supplies; means for receiving emergency requests from disaster-stricken areas, analyzing the contents of the requests, and identifying the types and quantities of supplies needed; means for formulating an optimal distribution plan and determining delivery routes and means based on geographic information of the disaster-stricken areas and local demand data; means for receiving and aggregating donation data through a cashless payment service; means for ordering required supplies through online shopping and confirming the order contents; means for arranging for the ordered supplies to be delivered promptly to the disaster-stricken areas via designated delivery companies and tracking the delivery status in real time; means for analyzing past order data and trend data using an AI model to predict demand for food delivery services; means for calculating optimal food delivery routes based on geographic information and operation data, and providing the routes to drivers; and means for users to make donations as gifts, order meals based on the donation amount, and arrange for delivery. This will enable food delivery services to efficiently manage inventory, forecast demand, optimize delivery routes, and provide meals through donations.

[0545] The "stockpile database" is a database for managing inventory information of ingredients and supplies for food delivery services.

[0546] "Inventory data" means data that indicates the quantity and status of ingredients and supplies in a food delivery service at a specific point in time.

[0547] "Latest inventory information" refers to regularly updated information showing the current quantity and status of ingredients and supplies in food delivery services.

[0548] An "AI model" is an artificial intelligence model used to analyze data and make predictions.

[0549] "Demographic data" refers to statistical information such as the age structure, gender, and increase or decrease of the population in a particular area.

[0550] "People flow data" refers to data on people's movement patterns and traffic flows.

[0551] "Past disaster data" refers to data on the type, scale, impact, etc. of disasters that have occurred in the past.

[0552] "Demand for goods" refers to the amount and type of goods needed at a particular time and place.

[0553] "Forecasting means" refers to methods or devices that use AI models to estimate future demand and supply requirements.

[0554] A "list of required supplies" is a list showing the types and quantities of supplies needed based on predicted demand.

[0555] An "emergency request" is a notice or request issued from a disaster-stricken area for immediate assistance.

[0556] "Geographic information" refers to information such as topography, location, and routes related to a specific area.

[0557] "Local demand data" means data relating to the specific wants and needs for goods and services at a site or region.

[0558] An "optimal allocation plan" is a plan for distributing goods and services efficiently and fairly.

[0559] A "delivery route" is the route or route for delivering goods or services.

[0560] A "cashless payment service" is a service that allows you to make payments using digital means without using cash.

[0561] "Donation data" refers to data relating to the amount of donations collected from users and the progress of the donations.

[0562] "Online shopping" is a method for purchasing goods and services over the Internet.

[0563] "Delivery status" is information that indicates the current stage and status of goods or services.

[0564] "Real-time tracking means" refers to methods and technologies for instantly checking and tracking delivery status.

[0565] "Donation as a gift" refers to a donation made by a user as a kind gesture, and the donation is used for a specific purpose.

[0566] "Operation data" refers to data related to the food delivery driver's driving route, speed, and delivery time.

[0567] An "optimal food delivery route" is a route that allows food delivery to be completed efficiently and quickly.

[0568] The present invention relates to a system for improving the efficiency of food delivery services. This system realizes fast and accurate food delivery through management of a stockpile database, demand forecasting, calculation of optimal delivery routes, and management of a donation function.

[0569] The system is implemented using hardware such as smartphones, servers, and GPS tracking devices, and software such as Python, Django, PostgreSQL, and Google Maps API.

[0570] The server first retrieves inventory data from the emergency supplies database and updates it periodically. As a specific example, it automatically retrieves food inventory data from each food delivery location and updates the database. In this process, Python is used to retrieve and update inventory data.

[0571] Next, the server uses an AI model to analyze past order data, people flow data, and past disaster data to predict demand for food delivery services. This allows it to evaluate how much food and supplies will be needed at what point in time. An example of a specific prompt is, "Please predict this month's demand based on the order data from the past six months." This AI model is built using Python and machine learning libraries (e.g., TensorFlow and scikit-learn).

[0572] The server calculates the optimal food delivery route based on geographical information and operational data, and provides it to the driver. This is achieved using the Google Maps API. An example of a specific prompt is "Please calculate the optimal delivery route to the following three order locations." This makes it possible to calculate an efficient route and provide it to the driver.

[0573] Users can make donations through a cashless payment service, and can order meals and arrange for delivery according to the amount donated. This donation data is aggregated by the server, and progress is displayed to users in real time. For example, if a user donates 1,000 yen, the system displays in real time that the total amount donated has reached 10,000 yen. This is achieved using a real-time update function using Django.

[0574] Furthermore, the system will ensure that ordered goods are delivered promptly via the designated delivery company and track the delivery status in real time using GPS tracking devices and Google Maps APIs. For example, the system will monitor the current location of delivery vehicles in real time and respond immediately if any abnormalities occur.

[0575] This system will enable food delivery services to efficiently manage inventory, forecast demand, optimize delivery routes, and provide meals through donations.

[0576] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0577] Step 1:

[0578] The server retrieves inventory data from the emergency supplies database. This inventory data includes the current quantities of food and supplies at each location. The data is periodically updated and reflected in the database. As input, the latest information from the emergency supplies database is required. As output, the latest inventory information is stored in the database.

[0579] Step 2:

[0580] The server uses an AI model to analyze past order data, people flow data, and past disaster data to predict demand for food delivery services. These datasets are required as input, and the output generates predicted demand for a specific future point in time. Specifically, the server uses Python and machine learning libraries (e.g., TensorFlow and scikit-learn) to build an AI model and perform analysis.

[0581] Step 3:

[0582] The server generates a list of required supplies based on the forecasted demand. As input, it takes the forecasted demand data obtained in step 2, and as output, it lists the types and quantities of required supplies. This list provides the specific ordering information needed for the next step.

[0583] Step 4:

[0584] The server receives emergency requests from disaster-stricken areas and users and analyzes their contents. The input required is the content of the emergency request (type and quantity of supplies), and the output extracts the specific identification and quantity of supplies. Natural language processing technology is used for the analysis to efficiently extract the necessary information.

[0585] Step 5:

[0586] The server formulates an optimal distribution plan based on geographic information and local demand data, and determines delivery routes and means. The inputs required are geographic information, local demand data, and a list of required supplies, and the output generates an optimal distribution plan and delivery route. Specifically, the server uses the Google Maps API to calculate routes and create delivery plans.

[0587] Step 6:

[0588] Users make donations through a cashless payment service. The amount donated by the user is required as input, and donation data is sent to the server as output. Users can use the payment service to check the progress of their donations in real time.

[0589] Step 7:

[0590] The server orders the necessary supplies through online shopping based on the collected donation data. The inputs are the donation data and the list of supplies from step 3, and the output is the confirmed order details. The order details are sent to the connected online shopping platform.

[0591] Step 8:

[0592] The server arranges for the ordered goods to be delivered promptly via the designated delivery company and tracks the delivery status in real time. The inputs are the order details and delivery company information, and the output is the tracking and real-time monitoring of the delivery status. Specifically, it uses a GPS tracking device to obtain the location information of the delivery vehicle and immediately notifies the user if any abnormalities occur.

[0593] The above processing steps enable efficient inventory management, demand forecasting, delivery route optimization, and donation-based meal provision for food delivery services.

[0594] 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.

[0595] MODE FOR CARRYING OUT THE INVENTION

[0596] This invention relates to a system for optimizing the distribution of relief supplies in the event of a disaster. This system utilizes AI technology and an emotion engine to optimize stockpile management, people flow data analysis, donation collection, and supply ordering and delivery, with the aim of minimizing shortages and surpluses of supplies in disaster-stricken areas.

[0597] Management of emergency supplies database

[0598] server

[0599] The server automatically retrieves inventory data from stockpiles set up for each region and periodically updates the database, ensuring that inventory information is always up to date and instantly listing shortages and surplus supplies.

[0600] (Example)

[0601] The server retrieves inventory data for water and medical supplies from the storage facility in "City A" and updates the database. At this time, it lists shortages (e.g., 500 liters of water, 2,000 masks) and excess inventory (e.g., 1,000 cans of food).

[0602] Demographic data and supply demand forecasts

[0603] server

[0604] The server inputs demographic data, human flow data, and data from past disasters into an AI model to predict demand for supplies, which then evaluates the amount of supplies that will be needed at a specific point in time in the future.

[0605] (Example)

[0606] The server analyzes demographic data, people flow data, and past disaster data for "City B" and predicts that "10,000 liters of water and 5,000 emergency meals will be needed over the next week."

[0607] Analysis of emergency requests and optimal allocation planning

[0608] server

[0609] The server receives emergency requests from disaster-stricken areas and analyzes their contents to determine the type and quantity of supplies needed. Based on this, an AI model is used to create an optimal distribution plan, determining delivery routes and methods.

[0610] (Example)

[0611] An emergency request for 5,000 liters of water is received from City C, and the AI ​​model calculates the most efficient delivery route, taking into account evacuation routes and traffic conditions.

[0612] Aggregating donations and ordering supplies using an emotion engine

[0613] User

[0614] Before a user makes a donation through the cashless payment service, the emotion engine recognizes the user's emotions, and appropriate donation campaigns and suggestions are displayed based on the recognition results.

[0615] (Example)

[0616] When User D uses the cashless payment service, the emotion engine recognizes User D's emotions, such as "empathy" and "sense of crisis," and suggests "disaster relief donations." User D donates 1,000 yen and checks the total amount and progress in real time.

[0617] server

[0618] The server generates a list of needed supplies based on the collected donation data and orders the supplies through online shopping.

[0619] (Example)

[0620] The server tallies the 5 million yen in donations and orders water, emergency food, blankets, etc. online based on that amount. The order details are confirmed and dispatched to a delivery company.

[0621] Delivery of supplies

[0622] server

[0623] The server then arranges for the ordered supplies to be delivered to the disaster area as quickly as possible. Delivery status is tracked in real time, and any abnormalities are dealt with immediately.

[0624] (Example)

[0625] The server arranges for 3,000 liters of water and 5,000 emergency rations to be delivered to a designated delivery company, and monitors the truck's progress in real time as it heads to its destination. If the truck gets stuck in traffic, the server notifies the delivery company of an alternative route.

[0626] This will enable efficient stockpile management and optimal distribution of relief supplies by combining AI technology and an emotion engine. Specific system components and their linkages will enable rapid and fair distribution of relief supplies.

[0627] The processing flow will be explained below.

[0628] Specific processing flow of the program

[0629] Collecting and updating stockpile data

[0630] Step 1: The server periodically obtains inventory data from storage facilities set up for each region (e.g., once a day).

[0631] Step 2: The server automatically updates the database with the acquired inventory data to reflect the latest inventory status.

[0632] Step 3: The server lists the shortages and excess supplies at this stage.

[0633] Demographic data and supply demand forecasts

[0634] Step 4: The server inputs demographic data, people flow data, and past disaster data into the AI ​​model.

[0635] Step 5: An AI model analyzes this data and predicts future demand for supplies.

[0636] Step 6: The server generates a list of required supplies based on the prediction results.

[0637] Analysis of emergency requests and optimal allocation planning

[0638] Step 7: The server receives an emergency request from the disaster area.

[0639] Step 8: The server analyzes the emergency request and identifies the type and amount of supplies needed.

[0640] Step 9: The server inputs the geographical information of the affected area and local demand data into the AI ​​model to develop an optimal distribution plan.

[0641] Step 10: The server calculates the delivery route and means and determines the optimal delivery method.

[0642] Aggregating donations and ordering supplies using an emotion engine

[0643] Step 11: Before the user makes a donation using the cashless payment service, the terminal recognizes the user's emotions using the emotion engine.

[0644] Step 12: The terminal displays appropriate fundraising campaigns and proposals to the user based on the emotions (e.g., "empathy," "sense of crisis," etc.) recognized by the emotion engine.

[0645] Step 13: The user makes a donation based on the proposed fundraising campaign.

[0646] Step 14: The terminal notifies the user that the donation process is complete and displays the progress of the donation in real time.

[0647] Step 15: The server receives and aggregates donation data from the cashless payment service.

[0648] Step 16: The server generates a list of supplies needed based on the aggregated donation data.

[0649] Step 17: The server orders the necessary supplies using online shopping and confirms the order.

[0650] Delivery of supplies

[0651] Step 18: The server arranges for the ordered supplies to be delivered promptly to the disaster area by the designated delivery company.

[0652] Step 19: The server tracks the delivery status in real time and responds immediately if any abnormalities occur.

[0653] Step 20: Once delivery is complete, the server updates the database with the results and reports them to the relevant parties.

[0654] Example 2

[0655] 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."

[0656] In times of disaster, it is necessary to prevent shortages or excesses of relief supplies and distribute necessary supplies to disaster-stricken areas quickly and efficiently. However, in conventional systems, inventory data is often managed manually, and the latest information may not be reflected. Furthermore, adequate forecasting of supply demand using demographic data and past disaster data is not performed, making it difficult to formulate appropriate supply distribution plans. Furthermore, functions for user emotion recognition during fundraising activities, real-time tracking during supply delivery, and abnormality response are also insufficient. To solve these problems, the present invention proposes a new system.

[0657] 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.

[0658] In this invention, the server includes means for retrieving inventory data from a stockpile database and updating the database with the latest inventory information, means for inputting demographic data, people flow data, and past disaster data into a generative AI model as prompt sentences to predict demand for supplies, means for generating a list of needed supplies based on the predicted demand for supplies, means for receiving emergency requests from disaster-stricken areas, analyzing the requests, and identifying the types and quantities of needed supplies, means for formulating an optimal distribution plan and determining delivery routes and means based on geographic information of the disaster-stricken area and local demand data, means for recognizing user emotions using an emotion engine, receiving and aggregating donation data through a cashless payment service, means for ordering needed supplies through online shopping and confirming the order details, and means for arranging for the ordered supplies to be delivered promptly to the disaster-stricken area via a designated delivery company and tracking the delivery status in real time. This makes it possible to minimize shortages and excesses of relief supplies during disasters and quickly and efficiently distribute needed supplies to disaster-stricken areas.

[0659] The "stockpile database" is a data storage system that manages inventory information for relief supplies needed in the event of a disaster and stores data collected from stockpile facilities in each region.

[0660] "Inventory data" is information on the types and quantities of relief supplies stored at each stockpile facility.

[0661] A "generative AI model" is an artificial intelligence algorithm that analyzes input data and makes predictions and optimizations according to specific objectives.

[0662] A "prompt" is text in the form of a question or command that gives instructions to a generative AI model.

[0663] "Supply demand forecasting" is the process of predicting the quantity and type of relief supplies needed for a specific period in the future.

[0664] An "urgent request" is an urgent request or communication requesting assistance for relief supplies to be sent from a disaster area.

[0665] An "allocation plan" is a plan that determines how relief supplies will be distributed and through which routes they will be delivered most efficiently.

[0666] An "emotion engine" is a software engine that recognizes the user's emotions and responds appropriately or makes suggestions based on those emotions.

[0667] A "cashless payment service" is a service that allows payments to be made electronically without using cash.

[0668] "Fundraising Data" means information relating to the amount of money raised through a fundraising activity and the progress of that fundraising.

[0669] "Online shopping" is a system for ordering and purchasing products via the Internet.

[0670] A "delivery company" is a company or organization that provides logistics services to deliver ordered goods to a specified location.

[0671] "Real-time tracking" is the process of monitoring the delivery status of goods in real time and instantly understanding their current location and progress.

[0672] "Anomaly response" is a method of quickly taking measures to resolve problems when any issues or failures occur during delivery.

[0673] MODE FOR CARRYING OUT THE INVENTION

[0674] This invention is a system that optimizes the distribution of relief supplies during disasters. It aims to minimize shortages and surpluses of supplies in disaster-stricken areas by utilizing AI technology and an emotion engine to optimize stockpile management, analysis of people flow data, collection of donations, and supply ordering and delivery.

[0675] System Configuration

[0676] Hardware and Software

[0677] Server: Plays a central role in collecting, analyzing, storing data, and formulating delivery plans. Uses cloud or on-premise servers as needed.

[0678] Device: A PC or smartphone operated by the user, used to check the status of donations and deliveries.

[0679] AI Model: Perform data analysis and demand forecasting using generative AI models.

[0680] Emotion Engine: Recognizes user emotions and makes appropriate donation suggestions.

[0681] Cashless payment service: Used to collect donations.

[0682] Online shopping system: Used to order necessary supplies.

[0683] Carrier system: Used to arrange and track deliveries.

[0684] Management of emergency supplies database

[0685] The server automatically retrieves inventory data from stockpiles set up for each region and periodically updates the database, thus maintaining up-to-date inventory information and listing shortages and excess supplies.

[0686] (Example)

[0687] The server retrieves inventory data for water and medical supplies from the storage facility in "City A" using an API and updates the database. It lists shortages (e.g., 500 liters of water, 2,000 masks) and excess inventory (e.g., 1,000 cans of food).

[0688] Demographic data and supply demand forecasts

[0689] The server collects demographic data, human flow data, and past disaster data for each region, and inputs this data into a generative AI model as prompts to predict supply demand. This process evaluates the amount of supplies that will be needed at a specific point in the future.

[0690] (Example)

[0691] The server inputs demographic data, human flow data, and past disaster data for "City B" into the generative AI model and makes a prediction using a prompt such as "Please predict City B's demand for supplies over the next week." The resulting prediction is "10,000 liters of water and 5,000 emergency rations will be needed over the next week."

[0692] Analysis of emergency requests and optimal allocation planning

[0693] The server receives emergency requests from disaster-stricken areas, analyzes their contents, and identifies the types and quantities of supplies needed. Based on this, a generative AI model formulates an optimal distribution plan and determines delivery routes and methods.

[0694] (Example)

[0695] An emergency request for 5,000 liters of water is received from "City C," and the AI ​​model calculates the optimal delivery route. The server then formulates the most efficient delivery plan, taking into account evacuation routes and traffic conditions.

[0696] Aggregating donations and ordering supplies using an emotion engine

[0697] Before a user makes a donation through a cashless payment service, an emotion engine recognizes the user's emotions and displays appropriate donation campaigns and suggestions.

[0698] (Example)

[0699] When User D uses the cashless payment service, the emotion engine recognizes User D's emotions, such as "empathy" and "sense of crisis," and suggests "disaster relief donations." User D donates 1,000 yen and checks the total amount and progress in real time.

[0700] The server generates a list of needed supplies based on the collected donation data and orders them through an online shopping system.

[0701] (Example)

[0702] The server tallies the 5 million yen in donations and orders water, emergency food, blankets, etc. online based on that amount. The order details are confirmed and dispatched to a delivery company.

[0703] Delivery of supplies

[0704] The server will then arrange for the ordered supplies to be delivered to the affected areas as quickly as possible. Delivery status will be tracked in real time, and any irregularities will be dealt with immediately.

[0705] (Example)

[0706] The server arranges for 3,000 liters of water and 5,000 emergency rations to be delivered to a designated delivery company, and monitors the truck's progress in real time as it heads to its destination. If the truck gets stuck in traffic, the server notifies the delivery company of an alternative route.

[0707] In this way, the present invention combines AI technology and an emotion engine to achieve efficient and fair distribution of relief supplies. Specific system components and their cooperation enable rapid and reliable response.

[0708] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0709] The flow of this system's program processing

[0710] Step 1: Acquire and manage emergency supply data

[0711] Input: Inventory data from each regional stockpile facility

[0712] Output: A database containing the latest inventory information

[0713] The server automatically retrieves inventory data from local stockpiles by accessing the stockpiles' APIs. The server then updates the database with the latest inventory information and lists shortages and surplus supplies.

[0714] Specific operation:

[0715] 1. The server accesses the storage facility's API and obtains inventory data for water, medical supplies, emergency food, etc.

[0716] 2. The server stores the acquired data in a database and compares it with past data to list shortages and surplus items.

[0717] 3. The list generated by the server is displayed on the management screen so that the person in charge can keep track of the latest inventory status.

[0718] Step 2: Demographic data and supply demand forecasts

[0719] Input: Demographic data, human flow data, past disaster data

[0720] Output: A list of predicted material demands

[0721] The server collects demographic data, human flow data, and past disaster data for each region, and inputs this data as prompts into the generative AI model, which then analyzes the data and predicts demand for supplies.

[0722] Specific operation:

[0723] 1. The server collects the necessary data from demographic and population flow databases.

[0724] 2. The server generates a prompt such as "Please predict the supply demand for city B over the next week."

[0725] 3. The server inputs the prompt and collected data into the generative AI model.

[0726] 4. The AI ​​model analyzes the data and outputs the predicted amount of supplies needed.

[0727] 5. The server saves the prediction results in a database and displays them on the management screen.

[0728] Step 3: Analysis of emergency requests and optimal allocation plan

[0729] Input: Emergency request data from the affected area, geographic information of the affected area, local demand data

[0730] Output: Optimal material allocation plan and delivery route

[0731] The server receives emergency requests from disaster-stricken areas, analyzes their contents, and identifies the types and quantities of supplies needed. It then uses a generative AI model to create an optimal distribution plan and determine delivery routes and methods.

[0732] Specific operation:

[0733] 1. The server receives an emergency request from the disaster area.

[0734] 2. The server analyzes the emergency request and identifies the type and quantity of supplies needed.

[0735] 3. The server generates a prompt such as "Please suggest the optimal route and means to deliver this item."

[0736] 4. The server inputs the prompt text, emergency request data, geographic information, and local demand data into the generative AI model.

[0737] 5. The AI ​​model analyzes and outputs the optimal allocation plan.

[0738] 6. The server saves the allocation plan in the database and displays it on the management screen.

[0739] Step 4: Using the Emotion Engine to Raise Funds and Order Supplies

[0740] Input: User payment information, sentiment data, donation data

[0741] Output: Received donation data, order list for needed supplies

[0742] Before a user makes a donation through a cashless payment service, an emotion engine recognizes the user's emotions and displays appropriate donation campaigns and suggestions.

[0743] Specific operation:

[0744] 1. A user accesses the donation page using a cashless payment service.

[0745] 2. The emotion engine recognizes the user's face and detects "empathy" or "sense of crisis."

[0746] 3. The emotion engine suggests fundraising campaigns based on the user's emotions.

[0747] 4. The user enters the donation amount and completes the cashless payment.

[0748] The server generates a list of needed supplies based on the collected donation data and orders them through online shopping.

[0749] Specific operation:

[0750] 1. The server stores the donation data in a database.

[0751] 2. The server generates a prompt such as "Please create a list of items to be purchased with the 5 million yen donation."

[0752] 3. The server inputs the prompt and donation data into the generative AI model.

[0753] 4. The AI ​​model analyzes and outputs a list of necessary supplies.

[0754] 5. The server orders the necessary supplies through the online shopping system and confirms the order.

[0755] 6. The server notifies the delivery company of the order details so that the order can be processed.

[0756] Step 5: Delivering supplies

[0757] Input: Order data, delivery company information, delivery route information

[0758] Output: Real-time monitoring data on delivery status, response information in case of abnormalities

[0759] The server arranges for the ordered supplies to be delivered promptly to the disaster area, tracks the delivery status in real time, and responds immediately if any abnormalities occur.

[0760] Specific operation:

[0761] 1. The server communicates with the delivery company and confirms the delivery arrangements for the goods.

[0762] 2. The server monitors the delivery truck's GPS data and tracks its progress in real time.

[0763] 3. If the server detects an abnormality, it notifies the delivery company of an alternative route and reroutes the truck.

[0764] 4. The server displays delivery status and progress on the management screen, allowing the person in charge to check it in real time.

[0765] Following this procedure, the system effectively manages and optimizes the distribution of relief supplies.

[0766] (Application example 2)

[0767] 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."

[0768] Conventional systems for distributing relief supplies during disasters have had difficulty in forecasting demand and responding to emergency requests, and efficiently and fairly distributing supplies. In particular, the lack of appropriate proposals that take into account fluctuations in traffic conditions and user emotions often makes it difficult to deliver supplies quickly and manage donation campaigns effectively.

[0769] 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 acquiring inventory data from a stockpile database and updating the database with the latest inventory information; means for analyzing demographic data, people flow data, and past disaster data using an AI model to predict demand for supplies; means for generating a list of needed supplies based on the predicted demand for supplies; means for receiving emergency requests from disaster-stricken areas, analyzing the contents of the requests, and identifying the types and quantities of needed supplies; means for formulating an optimal distribution plan and determining delivery routes and means based on geographic information of the disaster-stricken areas and local demand data; means for receiving and aggregating donation data through a cashless payment service; means for ordering needed supplies through online shopping and confirming the order contents; means for arranging for the ordered supplies to be delivered promptly to the disaster-stricken areas via a designated delivery company and tracking the delivery status in real time; means for acquiring real-time traffic conditions and notifying of dynamic route changes; and means for analyzing a user's emotions using an emotion recognition engine and making appropriate suggestions. This will enable efficient and fair distribution of relief supplies through rapid delivery that adapts to changes in traffic conditions and effective donation suggestions based on user emotions.

[0770] The "stockpile database" is a database that records and manages inventory information for supplies needed in the event of a disaster.

[0771] "Inventory data" refers to information regarding the types and quantities of supplies recorded in the stockpile database.

[0772] An "AI model" is an algorithm that uses artificial intelligence technology to analyze data and make predictions.

[0773] "Demographic data" refers to data on population changes and composition by region.

[0774] "People flow data" refers to data about the movement of people within and outside a specific area.

[0775] "Demand for goods" refers to the quantity and type of goods required within a specific period of time.

[0776] An "emergency request" is a request for relief supplies from an affected area during a disaster.

[0777] "Geographic information" refers to data about the geographic characteristics and traffic conditions of a particular area.

[0778] An "allocation plan" is a plan that determines the optimal delivery route and distribution method for supplies.

[0779] "Cashless payment service" refers to a means of transferring funds electronically without using cash.

[0780] "Fundraising Data" means information about funds raised through fundraising activities.

[0781] "Online shopping" refers to the process of purchasing goods over the Internet.

[0782] "Delivery company" means a company that transports goods to a specified location.

[0783] "Real-time" refers to processing data and providing information on the same time axis as the current time.

[0784] "Traffic conditions" refers to data on vehicle flow and congestion in specific areas and routes.

[0785] "Dynamic routing" refers to instantly adjusting and changing delivery routes based on real-time traffic information.

[0786] An "emotion recognition engine" is a technology that analyzes a user's emotions and makes appropriate suggestions based on the results.

[0787] This invention provides a system for optimizing the distribution of relief supplies during disasters. The system utilizes AI technology and an emotion recognition engine to optimize stockpile management, people flow data analysis, donation collection, and supply ordering and delivery. This will also minimize shortages and surpluses of supplies in disaster-stricken areas.

[0788] Hardware and software used

[0789] Hardware

[0790] Server: High-performance processor, SSD storage, and sufficient RAM

[0791] Devices: Smartphones, devices with GPS

[0792] software

[0793] Programming language: Python

[0794] Web framework: Django

[0795] Machine learning library: Scikit-learn (Sklearn)

[0796] Data processing and calculation flow

[0797] Management of emergency supplies database

[0798] The server automatically retrieves inventory data from stockpiles set up for each region and periodically updates the database, ensuring that inventory information is always up to date and instantly listing shortages and surplus supplies.

[0799] Demographic data and supply demand forecasts

[0800] The server inputs demographic data, human flow data, and data from past disasters into an AI model to predict demand for supplies, which then evaluates the amount of supplies that will be needed at a specific point in time in the future.

[0801] Analysis of emergency requests and optimal allocation planning

[0802] The server receives emergency requests from disaster-stricken areas and analyzes their contents to determine the type and quantity of supplies needed. Based on this, an AI model is used to create an optimal distribution plan, determining delivery routes and means. It also adds a function to obtain real-time traffic conditions and notify of dynamic route changes.

[0803] Aggregating donations and ordering supplies using an emotion recognition engine

[0804] Before a user makes a donation through the cashless payment service, an emotion recognition engine recognizes the user's emotions. Based on the recognition results, appropriate donation campaigns and donation suggestions are displayed. The server also generates a list of needed supplies based on the collected donation data and orders the supplies through online shopping.

[0805] Delivery of supplies

[0806] The server then arranges for the ordered supplies to be delivered to the disaster area as quickly as possible. Delivery status is tracked in real time, and any abnormalities are dealt with immediately.

[0807] Examples and prompts

[0808] Example 1

[0809] During a disaster, when water supplies are tight in a certain area, the server uses stockpile information and past data to predict demand for the next week and generate a list of necessary supplies.

[0810] Example 2

[0811] When a user uses the cashless payment service, an emotion recognition engine recognizes the user's "empathy" or "sense of crisis" and suggests "disaster relief donations." The user can donate and check the total amount and progress in real time.

[0812] Prompt Sentence Examples

[0813] "The emotion recognition engine should suggest the most appropriate menu based on the user's emotional state."

[0814] "Please provide the best way to notify dynamic route changes according to traffic conditions in the affected area."

[0815] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0816] Step 1:

[0817] The server retrieves inventory data from each regional stockpile facility and periodically updates this data in a database. The input data is the type and amount of inventory at each stockpile facility, and the output is a database containing the latest inventory information. At this time, shortages and excess inventory are listed.

[0818] Step 2:

[0819] The server acquires demographic data, human flow data, and past disaster data, and inputs this into an AI model to predict demand for supplies. The input data is data on regional population changes and past disasters, and based on this, a forecast of supply demand is output. This forecast includes the amount and type of supplies that will be needed at a specific point in the future.

[0820] Step 3:

[0821] The server generates a list of required supplies based on predicted demand. It uses the output of the demand forecast from the AI ​​model to list the specific supplies and quantities needed. The input is predicted demand data, and the output is a list of required supplies.

[0822] Step 4:

[0823] The server receives emergency requests from disaster-stricken areas, analyzes their contents, and identifies the types and quantities of supplies needed. The input data is the content of the emergency request, and the output is the identified types and quantities of supplies needed. The server then formulates an optimal distribution plan based on this information.

[0824] Step 5:

[0825] The server formulates an optimal distribution plan based on geographic information of the affected area and local demand data, and determines delivery routes and means. The input data is geographic information and demand data, and the output is an optimal distribution plan and delivery route. Routes are dynamically changed, taking into account real-time traffic conditions.

[0826] Step 6:

[0827] The server receives and aggregates donation data through a cashless payment service. The input data is donation information from users, and the output is aggregated donation data. Based on this data, a list of necessary supplies is generated and the supplies are ordered through online shopping.

[0828] Step 7:

[0829] When a user makes a cashless payment, the emotion recognition engine recognizes the user's emotions and then proposes appropriate donation campaigns and suggestions based on the results. The input data is the user's emotion data, and the output is appropriate donation campaigns and suggestions.

[0830] Step 8:

[0831] The server arranges for the ordered supplies to be delivered to the disaster area promptly and tracks the delivery status in real time. The input data is the order information and delivery status of the supplies, and the output is the real-time delivery status. If an abnormality occurs, it responds immediately.

[0832] Specific examples

[0833] Example prompt sentence:

[0834] Let the emotion recognition engine suggest the most appropriate menu based on the user's emotional state.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] [Third embodiment]

[0839] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0840] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0841] 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).

[0842] 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.

[0843] 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.

[0844] 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).

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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."

[0851] MODE FOR CARRYING OUT THE INVENTION

[0852] This invention relates to a system for optimizing the distribution of relief supplies in the event of a disaster. This system utilizes AI technology to optimize stockpile management, people flow data analysis, donation collection, and supply ordering and delivery, with the aim of minimizing shortages and surpluses of supplies in disaster-stricken areas.

[0853] Management of emergency supplies database

[0854] server

[0855] The server automatically obtains inventory data from storage facilities set up for each region. This data is updated periodically, and the latest inventory information can be reflected in the database. As a specific example, the server obtains inventory data for water transported from the storage facility in "City A" and updates the database.

[0856] Demographic data and supply demand forecasts

[0857] server

[0858] The server uses AI models to analyze demographic data, people flow data, and past disaster data to predict demand for supplies. This prediction is intended to assess how much supplies will be needed at a specific point in the future. For example, the server analyzes demographic data, people flow data, and past disaster data for "City B" and predicts that "10,000 liters of water will be needed in the next week."

[0859] Analysis of emergency requests and optimal allocation planning

[0860] server

[0861] The server receives emergency requests from disaster-stricken areas and analyzes their contents to determine the type and quantity of supplies needed. Based on this information, an AI model is used to create an optimal distribution plan. For example, if an emergency request is received from "City C" stating "5,000 liters of water is needed," the AI ​​model calculates the most efficient delivery route.

[0862] Collecting donations and ordering supplies

[0863] User

[0864] Users can make donations through a cashless payment service. These donations are aggregated in real time, and the progress is displayed to the user. For example, User D donates 1,000 yen using a cashless payment service and can check the total amount donated in real time.

[0865] server

[0866] The server generates a list of needed supplies based on the collected donation data and orders them through online shopping. For example, the server aggregates donations of 5 million yen and orders water, emergency food, blankets, etc. online based on that amount.

[0867] Delivery of supplies

[0868] server

[0869] The server arranges for the ordered supplies to be delivered promptly to the disaster area via the designated delivery company. The delivery status is tracked in real time, and any abnormalities are dealt with immediately. For example, the server arranges for "3,000 liters of water" and "5,000 emergency rations" to be delivered by the delivery company, and monitors in real time the status of the truck heading to its destination.

[0870] This will enable efficient stockpile management and optimal distribution of relief supplies using AI. Specific system components and their linkages will enable rapid and fair distribution of relief supplies.

[0871] The processing flow will be explained below.

[0872] Specific processing flow of the program

[0873] Collecting and updating stockpile data

[0874] Step 1: The server periodically obtains inventory data from storage facilities set up for each region (e.g., once a day).

[0875] Step 2: The server automatically updates the database with the acquired inventory data to reflect the latest inventory status.

[0876] Step 3: The server lists the shortages and excess supplies at this stage.

[0877] Demographic data and supply demand forecasts

[0878] Step 4: The server inputs demographic data, people flow data, and past disaster data into the AI ​​model.

[0879] Step 5: An AI model analyzes this data and predicts future demand for supplies.

[0880] Step 6: The server generates a list of required supplies based on the prediction results.

[0881] Analysis of emergency requests and optimal allocation planning

[0882] Step 7: The server receives an emergency request from the disaster area.

[0883] Step 8: The server analyzes the emergency request and identifies the type and amount of supplies needed.

[0884] Step 9: The server inputs the geographical information of the affected area and local demand data into the AI ​​model to develop an optimal distribution plan.

[0885] Step 10: The server calculates the delivery route and means and determines the optimal delivery method.

[0886] Collecting donations and ordering supplies

[0887] Step 11: The user makes a donation through a cashless payment service.

[0888] Step 12: The terminal notifies the user that the donation process is complete and displays the progress of the donation in real time.

[0889] Step 13: The server receives and aggregates donation data from the cashless payment service.

[0890] Step 14: The server generates a list of supplies needed based on the aggregated donation data.

[0891] Step 15: The server orders the necessary supplies using online shopping and confirms the order.

[0892] Delivery of supplies

[0893] Step 16: The server arranges for the ordered supplies to be delivered promptly to the disaster area by the designated delivery company.

[0894] Step 17: The server tracks the delivery status in real time and responds immediately if any abnormalities occur.

[0895] Step 18: Once delivery is complete, the server updates the database with the results and reports them to the relevant parties.

[0896] The above processing steps enable efficient stockpile management and optimal distribution of relief supplies using AI.

[0897] Example 1

[0898] 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."

[0899] The distribution of relief supplies during disasters is extremely important for protecting the lives and livelihoods of many people. However, the current system is prone to shortages and surpluses of supplies, making efficient and rapid distribution difficult. There are also many issues with analyzing emergency requests from disaster-stricken areas, collecting donations, and managing the ordering and delivery of supplies. This can lead to delays in the supply of supplies to disaster-stricken areas and insufficient support. These issues need to be resolved.

[0900] 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.

[0901] In this invention, the server includes means for retrieving inventory data from a stockpile database and updating the database with the latest inventory information, means for analyzing demographic data, people flow data, and past disaster data using a generative AI model to predict demand for supplies, means for generating a list of needed supplies based on the predicted demand, means for receiving emergency requests from disaster-stricken areas, analyzing the requests, and identifying the types and quantities of supplies needed, means for formulating an optimal distribution plan and determining delivery routes and means based on geographic information and local demand data for the disaster-stricken areas, means for receiving and aggregating donation data via a cashless payment service, means for ordering needed supplies through online ordering and confirming the order details, and means for arranging for the ordered supplies to be delivered promptly to the disaster-stricken areas via a designated delivery company and tracking the delivery status in real time. This minimizes supply shortages and surpluses, which have been a problem in the past, and enables efficient and rapid distribution of relief supplies.

[0902] The "stockpiled goods database" is a database for managing and storing information such as the type, quantity, and storage condition of supplies stockpiled in the event of a disaster.

[0903] "Inventory data" refers to information about the current quantity and status of each stockpile item stored in the stockpile database.

[0904] A "generative AI model" is an artificial intelligence model that analyzes demographic data, people flow data, and past disaster data to predict demand for supplies.

[0905] "Demographic data" is information about changes and distribution of a region's population.

[0906] "People flow data" is information about people's movement patterns in specific areas and time periods.

[0907] "Past disaster data" refers to information on the type, scale, and scope of impact of disasters that have occurred in the past.

[0908] "Demand for goods" refers to the types and quantities of goods needed at a particular time or in a particular area.

[0909] An "emergency request" is an urgent request from the disaster area regarding the type and quantity of supplies.

[0910] A "delivery route" is the optimal route for delivering goods.

[0911] "Cashless payment service" refers to a service that allows payments to be made electronically without using cash.

[0912] "Donation data" is information regarding donations collected from users.

[0913] "Online ordering" is the process of ordering supplies over the Internet.

[0914] A "delivery company" is a company that provides services to deliver ordered goods to a specified location.

[0915] "Real-time tracking" means checking and monitoring the current situation instantly.

[0916] An "anomaly" is an event or problem that deviates from the normal or expected state.

[0917] This invention is a system for optimizing the distribution of relief supplies in the event of a disaster. This system mainly involves a server, terminals, and users, each of which plays a specific role.

[0918] The server manages the emergency supplies database and automatically obtains inventory data from the emergency supplies facilities set up for each region. This data is updated periodically, and the latest inventory information is reflected in the database. For example, the server obtains inventory data for water transported from the emergency supplies facility in "Region A" and updates the database.

[0919] Next, the server uses the generative AI model to analyze demographic data, people flow data, and past disaster data to predict demand for supplies. This prediction is intended to assess how much supplies will be needed at a specific point in the future. As a specific example, the server analyzes demographic data, people flow data, and past disaster data for "Area B" and predicts that "10,000 liters of water will be needed in the next week."

[0920] Furthermore, the server receives emergency requests from disaster-stricken areas and analyzes their contents to identify the type and quantity of supplies needed. Based on this information, the generative AI model formulates an optimal distribution plan. For example, if the server receives an emergency request from "Area C" saying "5,000 liters of water is needed," the AI ​​model calculates the most efficient delivery route.

[0921] Users make donations through a cashless payment service. These donations are aggregated in real time, and the progress is displayed to the user. For example, a user donates 1,000 yen using a cashless payment service and can check the total amount donated in real time.

[0922] The server generates a list of needed supplies based on the collected donation data and orders them through online ordering. For example, the server aggregates donations of 5 million yen and orders water, emergency food, blankets, etc. online based on that amount.

[0923] The server arranges for the ordered supplies to be delivered promptly to the disaster area via the designated delivery company. The delivery status is tracked in real time, and any abnormalities are dealt with immediately. For example, the server arranges for "3,000 liters of water" and "5,000 emergency rations" to be delivered by the delivery company, and monitors in real time the status of the truck heading to its destination.

[0924] As a concrete example, the prompt text for analyzing demographic data to predict demand for goods is as follows:

[0925] "Using demographic data, people flow data, and past disaster data for Region B, please predict the demand for supplies for the next week."

[0926] In this way, this invention is a system that utilizes AI technology to achieve efficient stockpile management and optimal distribution of relief supplies. The system's components and their coordination enable rapid and fair distribution of relief supplies.

[0927] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0928] The flow of this system's program processing

[0929] Step 1: Obtaining emergency supplies data

[0930] The server automatically retrieves inventory data from each regional stockpile facility. This process is performed using API requests and is updated periodically. The input is the stockpile facility's API endpoint, and the output is the inventory data in JSON format. This data is stored in a database to reflect the latest inventory information. As a concrete example, the server retrieves water inventory data from the stockpile facility API for "Region A" and updates the database with it.

[0931] Step 2: Analyze demographic data and forecast demand

[0932] The server uses a generative AI model to analyze demographic data, people flow data, and past disaster data to predict future demand for supplies. The inputs are demographic data, people flow data, and past disaster data for each region. The AI ​​model analyzes these data and generates a demand forecast for supplies as output. Specifically, it analyzes data for "Region B" and predicts that 10,000 liters of water will be needed in the next week. For example, the prompt statement might look like this:

[0933] "Using demographic data, people flow data, and past disaster data for Region B, please predict the demand for supplies for the next week."

[0934] Step 3: Analyze emergency requests and develop optimal allocation plans

[0935] The server receives emergency requests from disaster-stricken areas and analyzes their contents using an AI model. The input is the emergency request data (XML format), and the output is the type and quantity of supplies needed. After analysis, this information is used to formulate an optimal distribution plan and calculate the optimal delivery route. For example, a request from "Area C" for "5,000 liters of water" is analyzed, and the most efficient delivery route is identified.

[0936] Step 4: Collect donations

[0937] Users make donations using a cashless payment service. The input is data on the amount donated by the user using a payment app. The server aggregates this data in real time and updates the total amount donated as output. For example, if a user donates 1,000 yen, the server updates the total amount donated to 10,000 yen.

[0938] Step 5: Order supplies

[0939] The server generates a list of needed supplies based on the collected donation data and orders the supplies online. The input is the donation data and the list of supplies, and the output is order confirmation data. As a concrete example, the server aggregates donations of 5 million yen and orders 2,000 liters of water, 5,000 emergency rations, and 200 blankets.

[0940] Step 6: Manage material delivery

[0941] The server arranges for the ordered supplies to reach the disaster area as quickly as possible. The input is order confirmation data and delivery company information, and the output is delivery status tracking data. The server monitors the delivery status in real time and responds immediately if a problem occurs. For example, it arranges for "3,000 liters of water" and "5,000 emergency rations" to be delivered by a delivery company, and monitors the delivery status in real time.

[0942] This will enable efficient and rapid distribution of relief supplies in the event of a disaster.

[0943] (Application example 1)

[0944] 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."

[0945] In recent years, as demand for food delivery services has rapidly increased, efficient inventory management, demand forecasting, and delivery route optimization have become important challenges. There is also a need for efficient management of the process of users making donations as gifts, ordering meals based on the donation amounts, and delivering them. These challenges are particularly pronounced during large-scale disasters, when a rapid and accurate response is required. The purpose of this invention is to solve these challenges and improve the efficiency of food delivery services.

[0946] 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.

[0947] In this invention, the server includes: means for acquiring inventory data from a stockpile database and updating the database with the latest inventory information; means for analyzing demographic data, people flow data, and past disaster data using an AI model to predict demand for supplies; means for generating a list of required supplies based on the predicted demand for supplies; means for receiving emergency requests from disaster-stricken areas, analyzing the contents of the requests, and identifying the types and quantities of supplies needed; means for formulating an optimal distribution plan and determining delivery routes and means based on geographic information of the disaster-stricken areas and local demand data; means for receiving and aggregating donation data through a cashless payment service; means for ordering required supplies through online shopping and confirming the order contents; means for arranging for the ordered supplies to be delivered promptly to the disaster-stricken areas via designated delivery companies and tracking the delivery status in real time; means for analyzing past order data and trend data using an AI model to predict demand for food delivery services; means for calculating optimal food delivery routes based on geographic information and operation data, and providing the routes to drivers; and means for users to make donations as gifts, order meals based on the donation amount, and arrange for delivery. This will enable food delivery services to efficiently manage inventory, forecast demand, optimize delivery routes, and provide meals through donations.

[0948] The "stockpile database" is a database for managing inventory information of ingredients and supplies for food delivery services.

[0949] "Inventory data" means data that indicates the quantity and status of ingredients and supplies in a food delivery service at a specific point in time.

[0950] "Latest inventory information" refers to regularly updated information showing the current quantity and status of ingredients and supplies in food delivery services.

[0951] An "AI model" is an artificial intelligence model used to analyze data and make predictions.

[0952] "Demographic data" refers to statistical information such as the age structure, gender, and increase or decrease of the population in a particular area.

[0953] "People flow data" refers to data on people's movement patterns and traffic flows.

[0954] "Past disaster data" refers to data on the type, scale, impact, etc. of disasters that have occurred in the past.

[0955] "Demand for goods" refers to the amount and type of goods needed at a particular time and place.

[0956] "Forecasting means" refers to methods or devices that use AI models to estimate future demand and supply requirements.

[0957] A "list of required supplies" is a list showing the types and quantities of supplies needed based on predicted demand.

[0958] An "emergency request" is a notice or request issued from a disaster-stricken area for immediate assistance.

[0959] "Geographic information" refers to information such as topography, location, and routes related to a specific area.

[0960] "Local demand data" means data relating to the specific wants and needs for goods and services at a site or region.

[0961] An "optimal allocation plan" is a plan for distributing goods and services efficiently and fairly.

[0962] A "delivery route" is the route or route for delivering goods or services.

[0963] A "cashless payment service" is a service that allows you to make payments using digital means without using cash.

[0964] "Donation data" refers to data relating to the amount of donations collected from users and the progress of the donations.

[0965] "Online shopping" is a method for purchasing goods and services over the Internet.

[0966] "Delivery status" is information that indicates the current stage and status of goods or services.

[0967] "Real-time tracking means" refers to methods and technologies for instantly checking and tracking delivery status.

[0968] "Donation as a gift" refers to a donation made by a user as a kind gesture, and the donation is used for a specific purpose.

[0969] "Operation data" refers to data related to the food delivery driver's driving route, speed, and delivery time.

[0970] An "optimal food delivery route" is a route that allows food delivery to be completed efficiently and quickly.

[0971] The present invention relates to a system for improving the efficiency of food delivery services. This system realizes fast and accurate food delivery through management of a stockpile database, demand forecasting, calculation of optimal delivery routes, and management of a donation function.

[0972] The system is implemented using hardware such as smartphones, servers, and GPS tracking devices, and software such as Python, Django, PostgreSQL, and Google Maps API.

[0973] The server first retrieves inventory data from the emergency supplies database and updates it periodically. As a specific example, it automatically retrieves food inventory data from each food delivery location and updates the database. In this process, Python is used to retrieve and update inventory data.

[0974] Next, the server uses an AI model to analyze past order data, people flow data, and past disaster data to predict demand for food delivery services. This allows it to evaluate how much food and supplies will be needed at what point in time. An example of a specific prompt is, "Please predict this month's demand based on the order data from the past six months." This AI model is built using Python and machine learning libraries (e.g., TensorFlow and scikit-learn).

[0975] The server calculates the optimal food delivery route based on geographical information and operational data, and provides it to the driver. This is achieved using the Google Maps API. An example of a specific prompt is "Please calculate the optimal delivery route to the following three order locations." This makes it possible to calculate an efficient route and provide it to the driver.

[0976] Users can make donations through a cashless payment service, and can order meals and arrange for delivery according to the amount donated. This donation data is aggregated by the server, and progress is displayed to users in real time. For example, if a user donates 1,000 yen, the system displays in real time that the total amount donated has reached 10,000 yen. This is achieved using a real-time update function using Django.

[0977] Furthermore, the system will ensure that ordered goods are delivered promptly via the designated delivery company and track the delivery status in real time using GPS tracking devices and Google Maps APIs. For example, the system will monitor the current location of delivery vehicles in real time and respond immediately if any abnormalities occur.

[0978] This system will enable food delivery services to efficiently manage inventory, forecast demand, optimize delivery routes, and provide meals through donations.

[0979] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0980] Step 1:

[0981] The server retrieves inventory data from the emergency supplies database. This inventory data includes the current quantities of food and supplies at each location. The data is periodically updated and reflected in the database. As input, the latest information from the emergency supplies database is required. As output, the latest inventory information is stored in the database.

[0982] Step 2:

[0983] The server uses an AI model to analyze past order data, people flow data, and past disaster data to predict demand for food delivery services. These datasets are required as input, and the output generates predicted demand for a specific future point in time. Specifically, the server uses Python and machine learning libraries (e.g., TensorFlow and scikit-learn) to build an AI model and perform analysis.

[0984] Step 3:

[0985] The server generates a list of required supplies based on the forecasted demand. As input, it takes the forecasted demand data obtained in step 2, and as output, it lists the types and quantities of required supplies. This list provides the specific ordering information needed for the next step.

[0986] Step 4:

[0987] The server receives emergency requests from disaster-stricken areas and users and analyzes their contents. The input required is the content of the emergency request (type and quantity of supplies), and the output extracts the specific identification and quantity of supplies. Natural language processing technology is used for the analysis to efficiently extract the necessary information.

[0988] Step 5:

[0989] The server formulates an optimal distribution plan based on geographic information and local demand data, and determines delivery routes and means. The inputs required are geographic information, local demand data, and a list of required supplies, and the output generates an optimal distribution plan and delivery route. Specifically, the server uses the Google Maps API to calculate routes and create delivery plans.

[0990] Step 6:

[0991] Users make donations through a cashless payment service. The amount donated by the user is required as input, and donation data is sent to the server as output. Users can use the payment service to check the progress of their donations in real time.

[0992] Step 7:

[0993] The server orders the necessary supplies through online shopping based on the collected donation data. The inputs are the donation data and the list of supplies from step 3, and the output is the confirmed order details. The order details are sent to the connected online shopping platform.

[0994] Step 8:

[0995] The server arranges for the ordered goods to be delivered promptly via the designated delivery company and tracks the delivery status in real time. The inputs are the order details and delivery company information, and the output is the tracking and real-time monitoring of the delivery status. Specifically, it uses a GPS tracking device to obtain the location information of the delivery vehicle and immediately notifies the user if any abnormalities occur.

[0996] The above processing steps enable efficient inventory management, demand forecasting, delivery route optimization, and donation-based meal provision for food delivery services.

[0997] 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.

[0998] MODE FOR CARRYING OUT THE INVENTION

[0999] This invention relates to a system for optimizing the distribution of relief supplies in the event of a disaster. This system utilizes AI technology and an emotion engine to optimize stockpile management, people flow data analysis, donation collection, and supply ordering and delivery, with the aim of minimizing shortages and surpluses of supplies in disaster-stricken areas.

[1000] Management of emergency supplies database

[1001] server

[1002] The server automatically retrieves inventory data from stockpiles set up for each region and periodically updates the database, ensuring that inventory information is always up to date and instantly listing shortages and surplus supplies.

[1003] (Example)

[1004] The server retrieves inventory data for water and medical supplies from the storage facility in "City A" and updates the database. At this time, it lists shortages (e.g., 500 liters of water, 2,000 masks) and excess inventory (e.g., 1,000 cans of food).

[1005] Demographic data and supply demand forecasts

[1006] server

[1007] The server inputs demographic data, human flow data, and data from past disasters into an AI model to predict demand for supplies, which then evaluates the amount of supplies that will be needed at a specific point in time in the future.

[1008] (Example)

[1009] The server analyzes demographic data, people flow data, and past disaster data for "City B" and predicts that "10,000 liters of water and 5,000 emergency meals will be needed over the next week."

[1010] Analysis of emergency requests and optimal allocation planning

[1011] server

[1012] The server receives emergency requests from disaster-stricken areas and analyzes their contents to determine the type and quantity of supplies needed. Based on this, an AI model is used to create an optimal distribution plan, determining delivery routes and methods.

[1013] (Example)

[1014] An emergency request for 5,000 liters of water is received from City C, and the AI ​​model calculates the most efficient delivery route, taking into account evacuation routes and traffic conditions.

[1015] Aggregating donations and ordering supplies using an emotion engine

[1016] User

[1017] Before a user makes a donation through the cashless payment service, the emotion engine recognizes the user's emotions, and appropriate donation campaigns and suggestions are displayed based on the recognition results.

[1018] (Example)

[1019] When User D uses the cashless payment service, the emotion engine recognizes User D's emotions, such as "empathy" and "sense of crisis," and suggests "disaster relief donations." User D donates 1,000 yen and checks the total amount and progress in real time.

[1020] server

[1021] The server generates a list of needed supplies based on the collected donation data and orders the supplies through online shopping.

[1022] (Example)

[1023] The server tallies the 5 million yen in donations and orders water, emergency food, blankets, etc. online based on that amount. The order details are confirmed and dispatched to a delivery company.

[1024] Delivery of supplies

[1025] server

[1026] The server then arranges for the ordered supplies to be delivered to the disaster area as quickly as possible. Delivery status is tracked in real time, and any abnormalities are dealt with immediately.

[1027] (Example)

[1028] The server arranges for 3,000 liters of water and 5,000 emergency rations to be delivered to a designated delivery company, and monitors the truck's progress in real time as it heads to its destination. If the truck gets stuck in traffic, the server notifies the delivery company of an alternative route.

[1029] This will enable efficient stockpile management and optimal distribution of relief supplies by combining AI technology and an emotion engine. Specific system components and their linkages will enable rapid and fair distribution of relief supplies.

[1030] The processing flow will be explained below.

[1031] Specific processing flow of the program

[1032] Collecting and updating stockpile data

[1033] Step 1: The server periodically obtains inventory data from storage facilities set up for each region (e.g., once a day).

[1034] Step 2: The server automatically updates the database with the acquired inventory data to reflect the latest inventory status.

[1035] Step 3: The server lists the shortages and excess supplies at this stage.

[1036] Demographic data and supply demand forecasts

[1037] Step 4: The server inputs demographic data, people flow data, and past disaster data into the AI ​​model.

[1038] Step 5: An AI model analyzes this data and predicts future demand for supplies.

[1039] Step 6: The server generates a list of required supplies based on the prediction results.

[1040] Analysis of emergency requests and optimal allocation planning

[1041] Step 7: The server receives an emergency request from the disaster area.

[1042] Step 8: The server analyzes the emergency request and identifies the type and amount of supplies needed.

[1043] Step 9: The server inputs the geographical information of the affected area and local demand data into the AI ​​model to develop an optimal distribution plan.

[1044] Step 10: The server calculates the delivery route and means and determines the optimal delivery method.

[1045] Aggregating donations and ordering supplies using an emotion engine

[1046] Step 11: Before the user makes a donation using the cashless payment service, the terminal recognizes the user's emotions using the emotion engine.

[1047] Step 12: The terminal displays appropriate fundraising campaigns and proposals to the user based on the emotions (e.g., "empathy," "sense of crisis," etc.) recognized by the emotion engine.

[1048] Step 13: The user makes a donation based on the proposed fundraising campaign.

[1049] Step 14: The terminal notifies the user that the donation process is complete and displays the progress of the donation in real time.

[1050] Step 15: The server receives and aggregates donation data from the cashless payment service.

[1051] Step 16: The server generates a list of supplies needed based on the aggregated donation data.

[1052] Step 17: The server orders the necessary supplies using online shopping and confirms the order.

[1053] Delivery of supplies

[1054] Step 18: The server arranges for the ordered supplies to be delivered promptly to the disaster area by the designated delivery company.

[1055] Step 19: The server tracks the delivery status in real time and responds immediately if any abnormalities occur.

[1056] Step 20: Once delivery is complete, the server updates the database with the results and reports them to the relevant parties.

[1057] Example 2

[1058] 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."

[1059] In times of disaster, it is necessary to prevent shortages or excesses of relief supplies and distribute necessary supplies to disaster-stricken areas quickly and efficiently. However, in conventional systems, inventory data is often managed manually, and the latest information may not be reflected. Furthermore, adequate forecasting of supply demand using demographic data and past disaster data is not performed, making it difficult to formulate appropriate supply distribution plans. Furthermore, functions for user emotion recognition during fundraising activities, real-time tracking during supply delivery, and abnormality response are also insufficient. To solve these problems, the present invention proposes a new system.

[1060] 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.

[1061] In this invention, the server includes means for retrieving inventory data from a stockpile database and updating the database with the latest inventory information, means for inputting demographic data, people flow data, and past disaster data into a generative AI model as prompt sentences to predict demand for supplies, means for generating a list of needed supplies based on the predicted demand for supplies, means for receiving emergency requests from disaster-stricken areas, analyzing the requests, and identifying the types and quantities of needed supplies, means for formulating an optimal distribution plan and determining delivery routes and means based on geographic information of the disaster-stricken area and local demand data, means for recognizing user emotions using an emotion engine, receiving and aggregating donation data through a cashless payment service, means for ordering needed supplies through online shopping and confirming the order details, and means for arranging for the ordered supplies to be delivered promptly to the disaster-stricken area via a designated delivery company and tracking the delivery status in real time. This makes it possible to minimize shortages and excesses of relief supplies during disasters and quickly and efficiently distribute needed supplies to disaster-stricken areas.

[1062] The "stockpile database" is a data storage system that manages inventory information for relief supplies needed in the event of a disaster and stores data collected from stockpile facilities in each region.

[1063] "Inventory data" is information on the types and quantities of relief supplies stored at each stockpile facility.

[1064] A "generative AI model" is an artificial intelligence algorithm that analyzes input data and makes predictions and optimizations according to specific objectives.

[1065] A "prompt" is text in the form of a question or command that gives instructions to a generative AI model.

[1066] "Supply demand forecasting" is the process of predicting the quantity and type of relief supplies needed for a specific period in the future.

[1067] An "urgent request" is an urgent request or communication requesting assistance for relief supplies to be sent from a disaster area.

[1068] An "allocation plan" is a plan that determines how relief supplies will be distributed and through which routes they will be delivered most efficiently.

[1069] An "emotion engine" is a software engine that recognizes the user's emotions and responds appropriately or makes suggestions based on those emotions.

[1070] A "cashless payment service" is a service that allows payments to be made electronically without using cash.

[1071] "Fundraising Data" means information relating to the amount of money raised through a fundraising activity and the progress of that fundraising.

[1072] "Online shopping" is a system for ordering and purchasing products via the Internet.

[1073] A "delivery company" is a company or organization that provides logistics services to deliver ordered goods to a specified location.

[1074] "Real-time tracking" is the process of monitoring the delivery status of goods in real time and instantly understanding their current location and progress.

[1075] "Anomaly response" is a method of quickly taking measures to resolve problems when any issues or failures occur during delivery.

[1076] MODE FOR CARRYING OUT THE INVENTION

[1077] This invention is a system that optimizes the distribution of relief supplies during disasters. It aims to minimize shortages and surpluses of supplies in disaster-stricken areas by utilizing AI technology and an emotion engine to optimize stockpile management, analysis of people flow data, collection of donations, and supply ordering and delivery.

[1078] System Configuration

[1079] Hardware and Software

[1080] Server: Plays a central role in collecting, analyzing, storing data, and formulating delivery plans. Uses cloud or on-premise servers as needed.

[1081] Device: A PC or smartphone operated by the user, used to check the status of donations and deliveries.

[1082] AI Model: Perform data analysis and demand forecasting using generative AI models.

[1083] Emotion Engine: Recognizes user emotions and makes appropriate donation suggestions.

[1084] Cashless payment service: Used to collect donations.

[1085] Online shopping system: Used to order necessary supplies.

[1086] Carrier system: Used to arrange and track deliveries.

[1087] Management of emergency supplies database

[1088] The server automatically retrieves inventory data from stockpiles set up for each region and periodically updates the database, thus maintaining up-to-date inventory information and listing shortages and excess supplies.

[1089] (Example)

[1090] The server retrieves inventory data for water and medical supplies from the storage facility in "City A" using an API and updates the database. It lists shortages (e.g., 500 liters of water, 2,000 masks) and excess inventory (e.g., 1,000 cans of food).

[1091] Demographic data and supply demand forecasts

[1092] The server collects demographic data, human flow data, and past disaster data for each region, and inputs this data into a generative AI model as prompts to predict supply demand. This process evaluates the amount of supplies that will be needed at a specific point in the future.

[1093] (Example)

[1094] The server inputs demographic data, human flow data, and past disaster data for "City B" into the generative AI model and makes a prediction using a prompt such as "Please predict City B's demand for supplies over the next week." The resulting prediction is "10,000 liters of water and 5,000 emergency rations will be needed over the next week."

[1095] Analysis of emergency requests and optimal allocation planning

[1096] The server receives emergency requests from disaster-stricken areas, analyzes their contents, and identifies the types and quantities of supplies needed. Based on this, a generative AI model formulates an optimal distribution plan and determines delivery routes and methods.

[1097] (Example)

[1098] An emergency request for 5,000 liters of water is received from "City C," and the AI ​​model calculates the optimal delivery route. The server then formulates the most efficient delivery plan, taking into account evacuation routes and traffic conditions.

[1099] Aggregating donations and ordering supplies using an emotion engine

[1100] Before a user makes a donation through a cashless payment service, an emotion engine recognizes the user's emotions and displays appropriate donation campaigns and suggestions.

[1101] (Example)

[1102] When User D uses the cashless payment service, the emotion engine recognizes User D's emotions, such as "empathy" and "sense of crisis," and suggests "disaster relief donations." User D donates 1,000 yen and checks the total amount and progress in real time.

[1103] The server generates a list of needed supplies based on the collected donation data and orders them through an online shopping system.

[1104] (Example)

[1105] The server tallies the 5 million yen in donations and orders water, emergency food, blankets, etc. online based on that amount. The order details are confirmed and dispatched to a delivery company.

[1106] Delivery of supplies

[1107] The server will then arrange for the ordered supplies to be delivered to the affected areas as quickly as possible. Delivery status will be tracked in real time, and any irregularities will be dealt with immediately.

[1108] (Example)

[1109] The server arranges for 3,000 liters of water and 5,000 emergency rations to be delivered to a designated delivery company, and monitors the truck's progress in real time as it heads to its destination. If the truck gets stuck in traffic, the server notifies the delivery company of an alternative route.

[1110] In this way, the present invention combines AI technology and an emotion engine to achieve efficient and fair distribution of relief supplies. Specific system components and their cooperation enable rapid and reliable response.

[1111] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1112] The flow of this system's program processing

[1113] Step 1: Acquire and manage emergency supply data

[1114] Input: Inventory data from each regional stockpile facility

[1115] Output: A database containing the latest inventory information

[1116] The server automatically retrieves inventory data from local stockpiles by accessing the stockpiles' APIs. The server then updates the database with the latest inventory information and lists shortages and surplus supplies.

[1117] Specific operation:

[1118] 1. The server accesses the storage facility's API and obtains inventory data for water, medical supplies, emergency food, etc.

[1119] 2. The server stores the acquired data in a database and compares it with past data to list shortages and surplus items.

[1120] 3. The list generated by the server is displayed on the management screen so that the person in charge can keep track of the latest inventory status.

[1121] Step 2: Demographic data and supply demand forecasts

[1122] Input: Demographic data, human flow data, past disaster data

[1123] Output: A list of predicted material demands

[1124] The server collects demographic data, human flow data, and past disaster data for each region, and inputs this data as prompts into the generative AI model, which then analyzes the data and predicts demand for supplies.

[1125] Specific operation:

[1126] 1. The server collects the necessary data from demographic and population flow databases.

[1127] 2. The server generates a prompt such as "Please predict the supply demand for city B over the next week."

[1128] 3. The server inputs the prompt and collected data into the generative AI model.

[1129] 4. The AI ​​model analyzes the data and outputs the predicted amount of supplies needed.

[1130] 5. The server saves the prediction results in a database and displays them on the management screen.

[1131] Step 3: Analysis of emergency requests and optimal allocation plan

[1132] Input: Emergency request data from the affected area, geographic information of the affected area, local demand data

[1133] Output: Optimal material allocation plan and delivery route

[1134] The server receives emergency requests from disaster-stricken areas, analyzes their contents, and identifies the types and quantities of supplies needed. It then uses a generative AI model to create an optimal distribution plan and determine delivery routes and methods.

[1135] Specific operation:

[1136] 1. The server receives an emergency request from the disaster area.

[1137] 2. The server analyzes the emergency request and identifies the type and quantity of supplies needed.

[1138] 3. The server generates a prompt such as "Please suggest the optimal route and means to deliver this item."

[1139] 4. The server inputs the prompt text, emergency request data, geographic information, and local demand data into the generative AI model.

[1140] 5. The AI ​​model analyzes and outputs the optimal allocation plan.

[1141] 6. The server saves the allocation plan in the database and displays it on the management screen.

[1142] Step 4: Using the Emotion Engine to Raise Funds and Order Supplies

[1143] Input: User payment information, sentiment data, donation data

[1144] Output: Received donation data, order list for needed supplies

[1145] Before a user makes a donation through a cashless payment service, an emotion engine recognizes the user's emotions and displays appropriate donation campaigns and suggestions.

[1146] Specific operation:

[1147] 1. A user accesses the donation page using a cashless payment service.

[1148] 2. The emotion engine recognizes the user's face and detects "empathy" or "sense of crisis."

[1149] 3. The emotion engine suggests fundraising campaigns based on the user's emotions.

[1150] 4. The user enters the donation amount and completes the cashless payment.

[1151] The server generates a list of needed supplies based on the collected donation data and orders them through online shopping.

[1152] Specific operation:

[1153] 1. The server stores the donation data in a database.

[1154] 2. The server generates a prompt such as "Please create a list of items to be purchased with the 5 million yen donation."

[1155] 3. The server inputs the prompt and donation data into the generative AI model.

[1156] 4. The AI ​​model analyzes and outputs a list of necessary supplies.

[1157] 5. The server orders the necessary supplies through the online shopping system and confirms the order.

[1158] 6. The server notifies the delivery company of the order details so that the order can be processed.

[1159] Step 5: Delivering supplies

[1160] Input: Order data, delivery company information, delivery route information

[1161] Output: Real-time monitoring data on delivery status, response information in case of abnormalities

[1162] The server arranges for the ordered supplies to be delivered promptly to the disaster area, tracks the delivery status in real time, and responds immediately if any abnormalities occur.

[1163] Specific operation:

[1164] 1. The server communicates with the delivery company and confirms the delivery arrangements for the goods.

[1165] 2. The server monitors the delivery truck's GPS data and tracks its progress in real time.

[1166] 3. If the server detects an abnormality, it notifies the delivery company of an alternative route and reroutes the truck.

[1167] 4. The server displays delivery status and progress on the management screen, allowing the person in charge to check it in real time.

[1168] Following this procedure, the system effectively manages and optimizes the distribution of relief supplies.

[1169] (Application example 2)

[1170] 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."

[1171] Conventional systems for distributing relief supplies during disasters have had difficulty in forecasting demand and responding to emergency requests, and efficiently and fairly distributing supplies. In particular, the lack of appropriate proposals that take into account fluctuations in traffic conditions and user emotions often makes it difficult to deliver supplies quickly and manage donation campaigns effectively.

[1172] 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 acquiring inventory data from a stockpile database and updating the database with the latest inventory information; means for analyzing demographic data, people flow data, and past disaster data using an AI model to predict demand for supplies; means for generating a list of needed supplies based on the predicted demand for supplies; means for receiving emergency requests from disaster-stricken areas, analyzing the contents of the requests, and identifying the types and quantities of needed supplies; means for formulating an optimal distribution plan and determining delivery routes and means based on geographic information of the disaster-stricken areas and local demand data; means for receiving and aggregating donation data through a cashless payment service; means for ordering needed supplies through online shopping and confirming the order contents; means for arranging for the ordered supplies to be delivered promptly to the disaster-stricken areas via a designated delivery company and tracking the delivery status in real time; means for acquiring real-time traffic conditions and notifying of dynamic route changes; and means for analyzing a user's emotions using an emotion recognition engine and making appropriate suggestions. This will enable efficient and fair distribution of relief supplies through rapid delivery that adapts to changes in traffic conditions and effective donation suggestions based on user emotions.

[1173] The "stockpile database" is a database that records and manages inventory information for supplies needed in the event of a disaster.

[1174] "Inventory data" refers to information regarding the types and quantities of supplies recorded in the stockpile database.

[1175] An "AI model" is an algorithm that uses artificial intelligence technology to analyze data and make predictions.

[1176] "Demographic data" refers to data on population changes and composition by region.

[1177] "People flow data" refers to data about the movement of people within and outside a specific area.

[1178] "Demand for goods" refers to the quantity and type of goods required within a specific period of time.

[1179] An "emergency request" is a request for relief supplies from an affected area during a disaster.

[1180] "Geographic information" refers to data about the geographic characteristics and traffic conditions of a particular area.

[1181] An "allocation plan" is a plan that determines the optimal delivery route and distribution method for supplies.

[1182] "Cashless payment service" refers to a means of transferring funds electronically without using cash.

[1183] "Fundraising Data" means information about funds raised through fundraising activities.

[1184] "Online shopping" refers to the process of purchasing goods over the Internet.

[1185] "Delivery company" means a company that transports goods to a specified location.

[1186] "Real-time" refers to processing data and providing information on the same time axis as the current time.

[1187] "Traffic conditions" refers to data on vehicle flow and congestion in specific areas and routes.

[1188] "Dynamic routing" refers to instantly adjusting and changing delivery routes based on real-time traffic information.

[1189] An "emotion recognition engine" is a technology that analyzes a user's emotions and makes appropriate suggestions based on the results.

[1190] This invention provides a system for optimizing the distribution of relief supplies during disasters. The system utilizes AI technology and an emotion recognition engine to optimize stockpile management, people flow data analysis, donation collection, and supply ordering and delivery. This will also minimize shortages and surpluses of supplies in disaster-stricken areas.

[1191] Hardware and software used

[1192] Hardware

[1193] Server: High-performance processor, SSD storage, and sufficient RAM

[1194] Devices: Smartphones, devices with GPS

[1195] software

[1196] Programming language: Python

[1197] Web framework: Django

[1198] Machine learning library: Scikit-learn (Sklearn)

[1199] Data processing and calculation flow

[1200] Management of emergency supplies database

[1201] The server automatically retrieves inventory data from stockpiles set up for each region and periodically updates the database, ensuring that inventory information is always up to date and instantly listing shortages and surplus supplies.

[1202] Demographic data and supply demand forecasts

[1203] The server inputs demographic data, human flow data, and data from past disasters into an AI model to predict demand for supplies, which then evaluates the amount of supplies that will be needed at a specific point in time in the future.

[1204] Analysis of emergency requests and optimal allocation planning

[1205] The server receives emergency requests from disaster-stricken areas and analyzes their contents to determine the type and quantity of supplies needed. Based on this, an AI model is used to create an optimal distribution plan, determining delivery routes and means. It also adds a function to obtain real-time traffic conditions and notify of dynamic route changes.

[1206] Aggregating donations and ordering supplies using an emotion recognition engine

[1207] Before a user makes a donation through the cashless payment service, an emotion recognition engine recognizes the user's emotions. Based on the recognition results, appropriate donation campaigns and donation suggestions are displayed. The server also generates a list of needed supplies based on the collected donation data and orders the supplies through online shopping.

[1208] Delivery of supplies

[1209] The server then arranges for the ordered supplies to be delivered to the disaster area as quickly as possible. Delivery status is tracked in real time, and any abnormalities are dealt with immediately.

[1210] Examples and prompts

[1211] Example 1

[1212] During a disaster, when water supplies are tight in a certain area, the server uses stockpile information and past data to predict demand for the next week and generate a list of necessary supplies.

[1213] Example 2

[1214] When a user uses the cashless payment service, an emotion recognition engine recognizes the user's "empathy" or "sense of crisis" and suggests "disaster relief donations." The user can donate and check the total amount and progress in real time.

[1215] Prompt Sentence Examples

[1216] "The emotion recognition engine should suggest the most appropriate menu based on the user's emotional state."

[1217] "Please provide the best way to notify dynamic route changes according to traffic conditions in the affected area."

[1218] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1219] Step 1:

[1220] The server retrieves inventory data from each regional stockpile facility and periodically updates this data in a database. The input data is the type and amount of inventory at each stockpile facility, and the output is a database containing the latest inventory information. At this time, shortages and excess inventory are listed.

[1221] Step 2:

[1222] The server acquires demographic data, human flow data, and past disaster data, and inputs this into an AI model to predict demand for supplies. The input data is data on regional population changes and past disasters, and based on this, a forecast of supply demand is output. This forecast includes the amount and type of supplies that will be needed at a specific point in the future.

[1223] Step 3:

[1224] The server generates a list of required supplies based on predicted demand. It uses the output of the demand forecast from the AI ​​model to list the specific supplies and quantities needed. The input is predicted demand data, and the output is a list of required supplies.

[1225] Step 4:

[1226] The server receives emergency requests from disaster-stricken areas, analyzes their contents, and identifies the types and quantities of supplies needed. The input data is the content of the emergency request, and the output is the identified types and quantities of supplies needed. The server then formulates an optimal distribution plan based on this information.

[1227] Step 5:

[1228] The server formulates an optimal distribution plan based on geographic information of the affected area and local demand data, and determines delivery routes and means. The input data is geographic information and demand data, and the output is an optimal distribution plan and delivery route. Routes are dynamically changed, taking into account real-time traffic conditions.

[1229] Step 6:

[1230] The server receives and aggregates donation data through a cashless payment service. The input data is donation information from users, and the output is aggregated donation data. Based on this data, a list of necessary supplies is generated and the supplies are ordered through online shopping.

[1231] Step 7:

[1232] When a user makes a cashless payment, the emotion recognition engine recognizes the user's emotions and then proposes appropriate donation campaigns and suggestions based on the results. The input data is the user's emotion data, and the output is appropriate donation campaigns and suggestions.

[1233] Step 8:

[1234] The server arranges for the ordered supplies to be delivered to the disaster area promptly and tracks the delivery status in real time. The input data is the order information and delivery status of the supplies, and the output is the real-time delivery status. If an abnormality occurs, it responds immediately.

[1235] Specific examples

[1236] Example prompt sentence:

[1237] Let the emotion recognition engine suggest the most appropriate menu based on the user's emotional state.

[1238] 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.

[1239] 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.

[1240] 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.

[1241] [Fourth embodiment]

[1242] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1243] 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.

[1244] 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).

[1245] 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.

[1246] 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.

[1247] 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).

[1248] 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.

[1249] 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.

[1250] 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.

[1251] 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.

[1252] 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.

[1253] 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.

[1254] 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."

[1255] MODE FOR CARRYING OUT THE INVENTION

[1256] This invention relates to a system for optimizing the distribution of relief supplies in the event of a disaster. This system utilizes AI technology to optimize stockpile management, people flow data analysis, donation collection, and supply ordering and delivery, with the aim of minimizing shortages and surpluses of supplies in disaster-stricken areas.

[1257] Management of emergency supplies database

[1258] server

[1259] The server automatically obtains inventory data from storage facilities set up for each region. This data is updated periodically, and the latest inventory information can be reflected in the database. As a specific example, the server obtains inventory data for water transported from the storage facility in "City A" and updates the database.

[1260] Demographic data and supply demand forecasts

[1261] server

[1262] The server uses AI models to analyze demographic data, people flow data, and past disaster data to predict demand for supplies. This prediction is intended to assess how much supplies will be needed at a specific point in the future. For example, the server analyzes demographic data, people flow data, and past disaster data for "City B" and predicts that "10,000 liters of water will be needed in the next week."

[1263] Analysis of emergency requests and optimal allocation planning

[1264] server

[1265] The server receives emergency requests from disaster-stricken areas and analyzes their contents to determine the type and quantity of supplies needed. Based on this information, an AI model is used to create an optimal distribution plan. For example, if an emergency request is received from "City C" stating "5,000 liters of water is needed," the AI ​​model calculates the most efficient delivery route.

[1266] Collecting donations and ordering supplies

[1267] User

[1268] Users can make donations through a cashless payment service. These donations are aggregated in real time, and the progress is displayed to the user. For example, User D donates 1,000 yen using a cashless payment service and can check the total amount donated in real time.

[1269] server

[1270] The server generates a list of needed supplies based on the collected donation data and orders them through online shopping. For example, the server aggregates donations of 5 million yen and orders water, emergency food, blankets, etc. online based on that amount.

[1271] Delivery of supplies

[1272] server

[1273] The server arranges for the ordered supplies to be delivered promptly to the disaster area via the designated delivery company. The delivery status is tracked in real time, and any abnormalities are dealt with immediately. For example, the server arranges for "3,000 liters of water" and "5,000 emergency rations" to be delivered by the delivery company, and monitors in real time the status of the truck heading to its destination.

[1274] This will enable efficient stockpile management and optimal distribution of relief supplies using AI. Specific system components and their linkages will enable rapid and fair distribution of relief supplies.

[1275] The processing flow will be explained below.

[1276] Specific processing flow of the program

[1277] Collecting and updating stockpile data

[1278] Step 1: The server periodically obtains inventory data from storage facilities set up for each region (e.g., once a day).

[1279] Step 2: The server automatically updates the database with the acquired inventory data to reflect the latest inventory status.

[1280] Step 3: The server lists the shortages and excess supplies at this stage.

[1281] Demographic data and supply demand forecasts

[1282] Step 4: The server inputs demographic data, people flow data, and past disaster data into the AI ​​model.

[1283] Step 5: An AI model analyzes this data and predicts future demand for supplies.

[1284] Step 6: The server generates a list of required supplies based on the prediction results.

[1285] Analysis of emergency requests and optimal allocation planning

[1286] Step 7: The server receives an emergency request from the disaster area.

[1287] Step 8: The server analyzes the emergency request and identifies the type and amount of supplies needed.

[1288] Step 9: The server inputs the geographical information of the affected area and local demand data into the AI ​​model to develop an optimal distribution plan.

[1289] Step 10: The server calculates the delivery route and means and determines the optimal delivery method.

[1290] Collecting donations and ordering supplies

[1291] Step 11: The user makes a donation through a cashless payment service.

[1292] Step 12: The terminal notifies the user that the donation process is complete and displays the progress of the donation in real time.

[1293] Step 13: The server receives and aggregates donation data from the cashless payment service.

[1294] Step 14: The server generates a list of supplies needed based on the aggregated donation data.

[1295] Step 15: The server orders the necessary supplies using online shopping and confirms the order.

[1296] Delivery of supplies

[1297] Step 16: The server arranges for the ordered supplies to be delivered promptly to the disaster area by the designated delivery company.

[1298] Step 17: The server tracks the delivery status in real time and responds immediately if any abnormalities occur.

[1299] Step 18: Once delivery is complete, the server updates the database with the results and reports them to the relevant parties.

[1300] The above processing steps enable efficient stockpile management and optimal distribution of relief supplies using AI.

[1301] Example 1

[1302] 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."

[1303] The distribution of relief supplies during disasters is extremely important for protecting the lives and livelihoods of many people. However, the current system is prone to shortages and surpluses of supplies, making efficient and rapid distribution difficult. There are also many issues with analyzing emergency requests from disaster-stricken areas, collecting donations, and managing the ordering and delivery of supplies. This can lead to delays in the supply of supplies to disaster-stricken areas and insufficient support. These issues need to be resolved.

[1304] 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.

[1305] In this invention, the server includes means for retrieving inventory data from a stockpile database and updating the database with the latest inventory information, means for analyzing demographic data, people flow data, and past disaster data using a generative AI model to predict demand for supplies, means for generating a list of needed supplies based on the predicted demand, means for receiving emergency requests from disaster-stricken areas, analyzing the requests, and identifying the types and quantities of supplies needed, means for formulating an optimal distribution plan and determining delivery routes and means based on geographic information and local demand data for the disaster-stricken areas, means for receiving and aggregating donation data via a cashless payment service, means for ordering needed supplies through online ordering and confirming the order details, and means for arranging for the ordered supplies to be delivered promptly to the disaster-stricken areas via a designated delivery company and tracking the delivery status in real time. This minimizes supply shortages and surpluses, which have been a problem in the past, and enables efficient and rapid distribution of relief supplies.

[1306] The "stockpiled goods database" is a database for managing and storing information such as the type, quantity, and storage condition of supplies stockpiled in the event of a disaster.

[1307] "Inventory data" refers to information about the current quantity and status of each stockpile item stored in the stockpile database.

[1308] A "generative AI model" is an artificial intelligence model that analyzes demographic data, people flow data, and past disaster data to predict demand for supplies.

[1309] "Demographic data" is information about changes and distribution of a region's population.

[1310] "People flow data" is information about people's movement patterns in specific areas and time periods.

[1311] "Past disaster data" refers to information on the type, scale, and scope of impact of disasters that have occurred in the past.

[1312] "Demand for goods" refers to the types and quantities of goods needed at a particular time or in a particular area.

[1313] An "emergency request" is an urgent request from the disaster area regarding the type and quantity of supplies.

[1314] A "delivery route" is the optimal route for delivering goods.

[1315] "Cashless payment service" refers to a service that allows payments to be made electronically without using cash.

[1316] "Donation data" is information regarding donations collected from users.

[1317] "Online ordering" is the process of ordering supplies over the Internet.

[1318] A "delivery company" is a company that provides services to deliver ordered goods to a specified location.

[1319] "Real-time tracking" means checking and monitoring the current situation instantly.

[1320] An "anomaly" is an event or problem that deviates from the normal or expected state.

[1321] This invention is a system for optimizing the distribution of relief supplies in the event of a disaster. This system mainly involves a server, terminals, and users, each of which plays a specific role.

[1322] The server manages the emergency supplies database and automatically obtains inventory data from the emergency supplies facilities set up for each region. This data is updated periodically, and the latest inventory information is reflected in the database. For example, the server obtains inventory data for water transported from the emergency supplies facility in "Region A" and updates the database.

[1323] Next, the server uses the generative AI model to analyze demographic data, people flow data, and past disaster data to predict demand for supplies. This prediction is intended to assess how much supplies will be needed at a specific point in the future. As a specific example, the server analyzes demographic data, people flow data, and past disaster data for "Area B" and predicts that "10,000 liters of water will be needed in the next week."

[1324] Furthermore, the server receives emergency requests from disaster-stricken areas and analyzes their contents to identify the type and quantity of supplies needed. Based on this information, the generative AI model formulates an optimal distribution plan. For example, if the server receives an emergency request from "Area C" saying "5,000 liters of water is needed," the AI ​​model calculates the most efficient delivery route.

[1325] Users make donations through a cashless payment service. These donations are aggregated in real time, and the progress is displayed to the user. For example, a user donates 1,000 yen using a cashless payment service and can check the total amount donated in real time.

[1326] The server generates a list of needed supplies based on the collected donation data and orders them through online ordering. For example, the server aggregates donations of 5 million yen and orders water, emergency food, blankets, etc. online based on that amount.

[1327] The server arranges for the ordered supplies to be delivered promptly to the disaster area via the designated delivery company. The delivery status is tracked in real time, and any abnormalities are dealt with immediately. For example, the server arranges for "3,000 liters of water" and "5,000 emergency rations" to be delivered by the delivery company, and monitors in real time the status of the truck heading to its destination.

[1328] As a concrete example, the prompt text for analyzing demographic data to predict demand for goods is as follows:

[1329] "Using demographic data, people flow data, and past disaster data for Region B, please predict the demand for supplies for the next week."

[1330] In this way, this invention is a system that utilizes AI technology to achieve efficient stockpile management and optimal distribution of relief supplies. The system's components and their coordination enable rapid and fair distribution of relief supplies.

[1331] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1332] The flow of this system's program processing

[1333] Step 1: Obtaining emergency supplies data

[1334] The server automatically retrieves inventory data from each regional stockpile facility. This process is performed using API requests and is updated periodically. The input is the stockpile facility's API endpoint, and the output is the inventory data in JSON format. This data is stored in a database to reflect the latest inventory information. As a concrete example, the server retrieves water inventory data from the stockpile facility API for "Region A" and updates the database with it.

[1335] Step 2: Analyze demographic data and forecast demand

[1336] The server uses a generative AI model to analyze demographic data, people flow data, and past disaster data to predict future demand for supplies. The inputs are demographic data, people flow data, and past disaster data for each region. The AI ​​model analyzes these data and generates a demand forecast for supplies as output. Specifically, it analyzes data for "Region B" and predicts that 10,000 liters of water will be needed in the next week. For example, the prompt statement might look like this:

[1337] "Using demographic data, people flow data, and past disaster data for Region B, please predict the demand for supplies for the next week."

[1338] Step 3: Analyze emergency requests and develop optimal allocation plans

[1339] The server receives emergency requests from disaster-stricken areas and analyzes their contents using an AI model. The input is the emergency request data (XML format), and the output is the type and quantity of supplies needed. After analysis, this information is used to formulate an optimal distribution plan and calculate the optimal delivery route. For example, a request from "Area C" for "5,000 liters of water" is analyzed, and the most efficient delivery route is identified.

[1340] Step 4: Collect donations

[1341] Users make donations using a cashless payment service. The input is data on the amount donated by the user using a payment app. The server aggregates this data in real time and updates the total amount donated as output. For example, if a user donates 1,000 yen, the server updates the total amount donated to 10,000 yen.

[1342] Step 5: Order supplies

[1343] The server generates a list of needed supplies based on the collected donation data and orders the supplies online. The input is the donation data and the list of supplies, and the output is order confirmation data. As a concrete example, the server aggregates donations of 5 million yen and orders 2,000 liters of water, 5,000 emergency rations, and 200 blankets.

[1344] Step 6: Manage material delivery

[1345] The server arranges for the ordered supplies to reach the disaster area as quickly as possible. The input is order confirmation data and delivery company information, and the output is delivery status tracking data. The server monitors the delivery status in real time and responds immediately if a problem occurs. For example, it arranges for "3,000 liters of water" and "5,000 emergency rations" to be delivered by a delivery company, and monitors the delivery status in real time.

[1346] This will enable efficient and rapid distribution of relief supplies in the event of a disaster.

[1347] (Application example 1)

[1348] 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."

[1349] In recent years, as demand for food delivery services has rapidly increased, efficient inventory management, demand forecasting, and delivery route optimization have become important challenges. There is also a need for efficient management of the process of users making donations as gifts, ordering meals based on the donation amounts, and delivering them. These challenges are particularly pronounced during large-scale disasters, when a rapid and accurate response is required. The purpose of this invention is to solve these challenges and improve the efficiency of food delivery services.

[1350] 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.

[1351] In this invention, the server includes: means for acquiring inventory data from a stockpile database and updating the database with the latest inventory information; means for analyzing demographic data, people flow data, and past disaster data using an AI model to predict demand for supplies; means for generating a list of required supplies based on the predicted demand for supplies; means for receiving emergency requests from disaster-stricken areas, analyzing the contents of the requests, and identifying the types and quantities of supplies needed; means for formulating an optimal distribution plan and determining delivery routes and means based on geographic information of the disaster-stricken areas and local demand data; means for receiving and aggregating donation data through a cashless payment service; means for ordering required supplies through online shopping and confirming the order contents; means for arranging for the ordered supplies to be delivered promptly to the disaster-stricken areas via designated delivery companies and tracking the delivery status in real time; means for analyzing past order data and trend data using an AI model to predict demand for food delivery services; means for calculating optimal food delivery routes based on geographic information and operation data, and providing the routes to drivers; and means for users to make donations as gifts, order meals based on the donation amount, and arrange for delivery. This will enable food delivery services to efficiently manage inventory, forecast demand, optimize delivery routes, and provide meals through donations.

[1352] The "stockpile database" is a database for managing inventory information of ingredients and supplies for food delivery services.

[1353] "Inventory data" means data that indicates the quantity and status of ingredients and supplies in a food delivery service at a specific point in time.

[1354] "Latest inventory information" refers to regularly updated information showing the current quantity and status of ingredients and supplies in food delivery services.

[1355] An "AI model" is an artificial intelligence model used to analyze data and make predictions.

[1356] "Demographic data" refers to statistical information such as the age structure, gender, and increase or decrease of the population in a particular area.

[1357] "People flow data" refers to data on people's movement patterns and traffic flows.

[1358] "Past disaster data" refers to data on the type, scale, impact, etc. of disasters that have occurred in the past.

[1359] "Demand for goods" refers to the amount and type of goods needed at a particular time and place.

[1360] "Forecasting means" refers to methods or devices that use AI models to estimate future demand and supply requirements.

[1361] A "list of required supplies" is a list showing the types and quantities of supplies needed based on predicted demand.

[1362] An "emergency request" is a notice or request issued from a disaster-stricken area for immediate assistance.

[1363] "Geographic information" refers to information such as topography, location, and routes related to a specific area.

[1364] "Local demand data" means data relating to the specific wants and needs for goods and services at a site or region.

[1365] An "optimal allocation plan" is a plan for distributing goods and services efficiently and fairly.

[1366] A "delivery route" is the route or route for delivering goods or services.

[1367] A "cashless payment service" is a service that allows you to make payments using digital means without using cash.

[1368] "Donation data" refers to data relating to the amount of donations collected from users and the progress of the donations.

[1369] "Online shopping" is a method for purchasing goods and services over the Internet.

[1370] "Delivery status" is information that indicates the current stage and status of goods or services.

[1371] "Real-time tracking means" refers to methods and technologies for instantly checking and tracking delivery status.

[1372] "Donation as a gift" refers to a donation made by a user as a kind gesture, and the donation is used for a specific purpose.

[1373] "Operation data" refers to data related to the food delivery driver's driving route, speed, and delivery time.

[1374] An "optimal food delivery route" is a route that allows food delivery to be completed efficiently and quickly.

[1375] The present invention relates to a system for improving the efficiency of food delivery services. This system realizes fast and accurate food delivery through management of a stockpile database, demand forecasting, calculation of optimal delivery routes, and management of a donation function.

[1376] The system is implemented using hardware such as smartphones, servers, and GPS tracking devices, and software such as Python, Django, PostgreSQL, and Google Maps API.

[1377] The server first retrieves inventory data from the emergency supplies database and updates it periodically. As a specific example, it automatically retrieves food inventory data from each food delivery location and updates the database. In this process, Python is used to retrieve and update inventory data.

[1378] Next, the server uses an AI model to analyze past order data, people flow data, and past disaster data to predict demand for food delivery services. This allows it to evaluate how much food and supplies will be needed at what point in time. An example of a specific prompt is, "Please predict this month's demand based on the order data from the past six months." This AI model is built using Python and machine learning libraries (e.g., TensorFlow and scikit-learn).

[1379] The server calculates the optimal food delivery route based on geographical information and operational data, and provides it to the driver. This is achieved using the Google Maps API. An example of a specific prompt is "Please calculate the optimal delivery route to the following three order locations." This makes it possible to calculate an efficient route and provide it to the driver.

[1380] Users can make donations through a cashless payment service, and can order meals and arrange for delivery according to the amount donated. This donation data is aggregated by the server, and progress is displayed to users in real time. For example, if a user donates 1,000 yen, the system displays in real time that the total amount donated has reached 10,000 yen. This is achieved using a real-time update function using Django.

[1381] Furthermore, the system will ensure that ordered goods are delivered promptly via the designated delivery company and track the delivery status in real time using GPS tracking devices and Google Maps APIs. For example, the system will monitor the current location of delivery vehicles in real time and respond immediately if any abnormalities occur.

[1382] This system will enable food delivery services to efficiently manage inventory, forecast demand, optimize delivery routes, and provide meals through donations.

[1383] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1384] Step 1:

[1385] The server retrieves inventory data from the emergency supplies database. This inventory data includes the current quantities of food and supplies at each location. The data is periodically updated and reflected in the database. As input, the latest information from the emergency supplies database is required. As output, the latest inventory information is stored in the database.

[1386] Step 2:

[1387] The server uses an AI model to analyze past order data, people flow data, and past disaster data to predict demand for food delivery services. These datasets are required as input, and the output generates predicted demand for a specific future point in time. Specifically, the server uses Python and machine learning libraries (e.g., TensorFlow and scikit-learn) to build an AI model and perform analysis.

[1388] Step 3:

[1389] The server generates a list of required supplies based on the forecasted demand. As input, it takes the forecasted demand data obtained in step 2, and as output, it lists the types and quantities of required supplies. This list provides the specific ordering information needed for the next step.

[1390] Step 4:

[1391] The server receives emergency requests from disaster-stricken areas and users and analyzes their contents. The input required is the content of the emergency request (type and quantity of supplies), and the output extracts the specific identification and quantity of supplies. Natural language processing technology is used for the analysis to efficiently extract the necessary information.

[1392] Step 5:

[1393] The server formulates an optimal distribution plan based on geographic information and local demand data, and determines delivery routes and means. The inputs required are geographic information, local demand data, and a list of required supplies, and the output generates an optimal distribution plan and delivery route. Specifically, the server uses the Google Maps API to calculate routes and create delivery plans.

[1394] Step 6:

[1395] Users make donations through a cashless payment service. The amount donated by the user is required as input, and donation data is sent to the server as output. Users can use the payment service to check the progress of their donations in real time.

[1396] Step 7:

[1397] The server orders the necessary supplies through online shopping based on the collected donation data. The inputs are the donation data and the list of supplies from step 3, and the output is the confirmed order details. The order details are sent to the connected online shopping platform.

[1398] Step 8:

[1399] The server arranges for the ordered goods to be delivered promptly via the designated delivery company and tracks the delivery status in real time. The inputs are the order details and delivery company information, and the output is the tracking and real-time monitoring of the delivery status. Specifically, it uses a GPS tracking device to obtain the location information of the delivery vehicle and immediately notifies the user if any abnormalities occur.

[1400] The above processing steps enable efficient inventory management, demand forecasting, delivery route optimization, and donation-based meal provision for food delivery services.

[1401] 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.

[1402] MODE FOR CARRYING OUT THE INVENTION

[1403] This invention relates to a system for optimizing the distribution of relief supplies in the event of a disaster. This system utilizes AI technology and an emotion engine to optimize stockpile management, people flow data analysis, donation collection, and supply ordering and delivery, with the aim of minimizing shortages and surpluses of supplies in disaster-stricken areas.

[1404] Management of emergency supplies database

[1405] server

[1406] The server automatically retrieves inventory data from stockpiles set up for each region and periodically updates the database, ensuring that inventory information is always up to date and instantly listing shortages and surplus supplies.

[1407] (Example)

[1408] The server retrieves inventory data for water and medical supplies from the storage facility in "City A" and updates the database. At this time, it lists shortages (e.g., 500 liters of water, 2,000 masks) and excess inventory (e.g., 1,000 cans of food).

[1409] Demographic data and supply demand forecasts

[1410] server

[1411] The server inputs demographic data, human flow data, and data from past disasters into an AI model to predict demand for supplies, which then evaluates the amount of supplies that will be needed at a specific point in time in the future.

[1412] (Example)

[1413] The server analyzes demographic data, people flow data, and past disaster data for "City B" and predicts that "10,000 liters of water and 5,000 emergency meals will be needed over the next week."

[1414] Analysis of emergency requests and optimal allocation planning

[1415] server

[1416] The server receives emergency requests from disaster-stricken areas and analyzes their contents to determine the type and quantity of supplies needed. Based on this, an AI model is used to create an optimal distribution plan, determining delivery routes and methods.

[1417] (Example)

[1418] An emergency request for 5,000 liters of water is received from City C, and the AI ​​model calculates the most efficient delivery route, taking into account evacuation routes and traffic conditions.

[1419] Aggregating donations and ordering supplies using an emotion engine

[1420] User

[1421] Before a user makes a donation through the cashless payment service, the emotion engine recognizes the user's emotions, and appropriate donation campaigns and suggestions are displayed based on the recognition results.

[1422] (Example)

[1423] When User D uses the cashless payment service, the emotion engine recognizes User D's emotions, such as "empathy" and "sense of crisis," and suggests "disaster relief donations." User D donates 1,000 yen and checks the total amount and progress in real time.

[1424] server

[1425] The server generates a list of needed supplies based on the collected donation data and orders the supplies through online shopping.

[1426] (Example)

[1427] The server tallies the 5 million yen in donations and orders water, emergency food, blankets, etc. online based on that amount. The order details are confirmed and dispatched to a delivery company.

[1428] Delivery of supplies

[1429] server

[1430] The server then arranges for the ordered supplies to be delivered to the disaster area as quickly as possible. Delivery status is tracked in real time, and any abnormalities are dealt with immediately.

[1431] (Example)

[1432] The server arranges for 3,000 liters of water and 5,000 emergency rations to be delivered to a designated delivery company, and monitors the truck's progress in real time as it heads to its destination. If the truck gets stuck in traffic, the server notifies the delivery company of an alternative route.

[1433] This will enable efficient stockpile management and optimal distribution of relief supplies by combining AI technology and an emotion engine. Specific system components and their linkages will enable rapid and fair distribution of relief supplies.

[1434] The processing flow will be explained below.

[1435] Specific processing flow of the program

[1436] Collecting and updating stockpile data

[1437] Step 1: The server periodically obtains inventory data from storage facilities set up for each region (e.g., once a day).

[1438] Step 2: The server automatically updates the database with the acquired inventory data to reflect the latest inventory status.

[1439] Step 3: The server lists the shortages and excess supplies at this stage.

[1440] Demographic data and supply demand forecasts

[1441] Step 4: The server inputs demographic data, people flow data, and past disaster data into the AI ​​model.

[1442] Step 5: An AI model analyzes this data and predicts future demand for supplies.

[1443] Step 6: The server generates a list of required supplies based on the prediction results.

[1444] Analysis of emergency requests and optimal allocation planning

[1445] Step 7: The server receives an emergency request from the disaster area.

[1446] Step 8: The server analyzes the emergency request and identifies the type and amount of supplies needed.

[1447] Step 9: The server inputs the geographical information of the affected area and local demand data into the AI ​​model to develop an optimal distribution plan.

[1448] Step 10: The server calculates the delivery route and means and determines the optimal delivery method.

[1449] Aggregating donations and ordering supplies using an emotion engine

[1450] Step 11: Before the user makes a donation using the cashless payment service, the terminal recognizes the user's emotions using the emotion engine.

[1451] Step 12: The terminal displays appropriate fundraising campaigns and proposals to the user based on the emotions (e.g., "empathy," "sense of crisis," etc.) recognized by the emotion engine.

[1452] Step 13: The user makes a donation based on the proposed fundraising campaign.

[1453] Step 14: The terminal notifies the user that the donation process is complete and displays the progress of the donation in real time.

[1454] Step 15: The server receives and aggregates donation data from the cashless payment service.

[1455] Step 16: The server generates a list of supplies needed based on the aggregated donation data.

[1456] Step 17: The server orders the necessary supplies using online shopping and confirms the order.

[1457] Delivery of supplies

[1458] Step 18: The server arranges for the ordered supplies to be delivered promptly to the disaster area by the designated delivery company.

[1459] Step 19: The server tracks the delivery status in real time and responds immediately if any abnormalities occur.

[1460] Step 20: Once delivery is complete, the server updates the database with the results and reports them to the relevant parties.

[1461] Example 2

[1462] 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."

[1463] In times of disaster, it is necessary to prevent shortages or excesses of relief supplies and distribute necessary supplies to disaster-stricken areas quickly and efficiently. However, in conventional systems, inventory data is often managed manually, and the latest information may not be reflected. Furthermore, adequate forecasting of supply demand using demographic data and past disaster data is not performed, making it difficult to formulate appropriate supply distribution plans. Furthermore, functions for user emotion recognition during fundraising activities, real-time tracking during supply delivery, and abnormality response are also insufficient. To solve these problems, the present invention proposes a new system.

[1464] 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.

[1465] In this invention, the server includes means for retrieving inventory data from a stockpile database and updating the database with the latest inventory information, means for inputting demographic data, people flow data, and past disaster data into a generative AI model as prompt sentences to predict demand for supplies, means for generating a list of needed supplies based on the predicted demand for supplies, means for receiving emergency requests from disaster-stricken areas, analyzing the requests, and identifying the types and quantities of needed supplies, means for formulating an optimal distribution plan and determining delivery routes and means based on geographic information of the disaster-stricken area and local demand data, means for recognizing user emotions using an emotion engine, receiving and aggregating donation data through a cashless payment service, means for ordering needed supplies through online shopping and confirming the order details, and means for arranging for the ordered supplies to be delivered promptly to the disaster-stricken area via a designated delivery company and tracking the delivery status in real time. This makes it possible to minimize shortages and excesses of relief supplies during disasters and quickly and efficiently distribute needed supplies to disaster-stricken areas.

[1466] The "stockpile database" is a data storage system that manages inventory information for relief supplies needed in the event of a disaster and stores data collected from stockpile facilities in each region.

[1467] "Inventory data" is information on the types and quantities of relief supplies stored at each stockpile facility.

[1468] A "generative AI model" is an artificial intelligence algorithm that analyzes input data and makes predictions and optimizations according to specific objectives.

[1469] A "prompt" is text in the form of a question or command that gives instructions to a generative AI model.

[1470] "Supply demand forecasting" is the process of predicting the quantity and type of relief supplies needed for a specific period in the future.

[1471] An "urgent request" is an urgent request or communication requesting assistance for relief supplies to be sent from a disaster area.

[1472] An "allocation plan" is a plan that determines how relief supplies will be distributed and through which routes they will be delivered most efficiently.

[1473] An "emotion engine" is a software engine that recognizes the user's emotions and responds appropriately or makes suggestions based on those emotions.

[1474] A "cashless payment service" is a service that allows payments to be made electronically without using cash.

[1475] "Fundraising Data" means information relating to the amount of money raised through a fundraising activity and the progress of that fundraising.

[1476] "Online shopping" is a system for ordering and purchasing products via the Internet.

[1477] A "delivery company" is a company or organization that provides logistics services to deliver ordered goods to a specified location.

[1478] "Real-time tracking" is the process of monitoring the delivery status of goods in real time and instantly understanding their current location and progress.

[1479] "Anomaly response" is a method of quickly taking measures to resolve problems when any issues or failures occur during delivery.

[1480] MODE FOR CARRYING OUT THE INVENTION

[1481] This invention is a system that optimizes the distribution of relief supplies during disasters. It aims to minimize shortages and surpluses of supplies in disaster-stricken areas by utilizing AI technology and an emotion engine to optimize stockpile management, analysis of people flow data, collection of donations, and supply ordering and delivery.

[1482] System Configuration

[1483] Hardware and Software

[1484] Server: Plays a central role in collecting, analyzing, storing data, and formulating delivery plans. Uses cloud or on-premise servers as needed.

[1485] Device: A PC or smartphone operated by the user, used to check the status of donations and deliveries.

[1486] AI Model: Perform data analysis and demand forecasting using generative AI models.

[1487] Emotion Engine: Recognizes user emotions and makes appropriate donation suggestions.

[1488] Cashless payment service: Used to collect donations.

[1489] Online shopping system: Used to order necessary supplies.

[1490] Carrier system: Used to arrange and track deliveries.

[1491] Management of emergency supplies database

[1492] The server automatically retrieves inventory data from stockpiles set up for each region and periodically updates the database, thus maintaining up-to-date inventory information and listing shortages and excess supplies.

[1493] (Example)

[1494] The server retrieves inventory data for water and medical supplies from the storage facility in "City A" using an API and updates the database. It lists shortages (e.g., 500 liters of water, 2,000 masks) and excess inventory (e.g., 1,000 cans of food).

[1495] Demographic data and supply demand forecasts

[1496] The server collects demographic data, human flow data, and past disaster data for each region, and inputs this data into a generative AI model as prompts to predict supply demand. This process evaluates the amount of supplies that will be needed at a specific point in the future.

[1497] (Example)

[1498] The server inputs demographic data, human flow data, and past disaster data for "City B" into the generative AI model and makes a prediction using a prompt such as "Please predict City B's demand for supplies over the next week." The resulting prediction is "10,000 liters of water and 5,000 emergency rations will be needed over the next week."

[1499] Analysis of emergency requests and optimal allocation planning

[1500] The server receives emergency requests from disaster-stricken areas, analyzes their contents, and identifies the types and quantities of supplies needed. Based on this, a generative AI model formulates an optimal distribution plan and determines delivery routes and methods.

[1501] (Example)

[1502] An emergency request for 5,000 liters of water is received from "City C," and the AI ​​model calculates the optimal delivery route. The server then formulates the most efficient delivery plan, taking into account evacuation routes and traffic conditions.

[1503] Aggregating donations and ordering supplies using an emotion engine

[1504] Before a user makes a donation through a cashless payment service, an emotion engine recognizes the user's emotions and displays appropriate donation campaigns and suggestions.

[1505] (Example)

[1506] When User D uses the cashless payment service, the emotion engine recognizes User D's emotions, such as "empathy" and "sense of crisis," and suggests "disaster relief donations." User D donates 1,000 yen and checks the total amount and progress in real time.

[1507] The server generates a list of needed supplies based on the collected donation data and orders them through an online shopping system.

[1508] (Example)

[1509] The server tallies the 5 million yen in donations and orders water, emergency food, blankets, etc. online based on that amount. The order details are confirmed and dispatched to a delivery company.

[1510] Delivery of supplies

[1511] The server will then arrange for the ordered supplies to be delivered to the affected areas as quickly as possible. Delivery status will be tracked in real time, and any irregularities will be dealt with immediately.

[1512] (Example)

[1513] The server arranges for 3,000 liters of water and 5,000 emergency rations to be delivered to a designated delivery company, and monitors the truck's progress in real time as it heads to its destination. If the truck gets stuck in traffic, the server notifies the delivery company of an alternative route.

[1514] In this way, the present invention combines AI technology and an emotion engine to achieve efficient and fair distribution of relief supplies. Specific system components and their cooperation enable rapid and reliable response.

[1515] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1516] The flow of this system's program processing

[1517] Step 1: Acquire and manage emergency supply data

[1518] Input: Inventory data from each regional stockpile facility

[1519] Output: A database containing the latest inventory information

[1520] The server automatically retrieves inventory data from local stockpiles by accessing the stockpiles' APIs. The server then updates the database with the latest inventory information and lists shortages and surplus supplies.

[1521] Specific operation:

[1522] 1. The server accesses the storage facility's API and obtains inventory data for water, medical supplies, emergency food, etc.

[1523] 2. The server stores the acquired data in a database and compares it with past data to list shortages and surplus items.

[1524] 3. The list generated by the server is displayed on the management screen so that the person in charge can keep track of the latest inventory status.

[1525] Step 2: Demographic data and supply demand forecasts

[1526] Input: Demographic data, human flow data, past disaster data

[1527] Output: A list of predicted material demands

[1528] The server collects demographic data, human flow data, and past disaster data for each region, and inputs this data as prompts into the generative AI model, which then analyzes the data and predicts demand for supplies.

[1529] Specific operation:

[1530] 1. The server collects the necessary data from demographic and population flow databases.

[1531] 2. The server generates a prompt such as "Please predict the supply demand for city B over the next week."

[1532] 3. The server inputs the prompt and collected data into the generative AI model.

[1533] 4. The AI ​​model analyzes the data and outputs the predicted amount of supplies needed.

[1534] 5. The server saves the prediction results in a database and displays them on the management screen.

[1535] Step 3: Analysis of emergency requests and optimal allocation plan

[1536] Input: Emergency request data from the affected area, geographic information of the affected area, local demand data

[1537] Output: Optimal material allocation plan and delivery route

[1538] The server receives emergency requests from disaster-stricken areas, analyzes their contents, and identifies the types and quantities of supplies needed. It then uses a generative AI model to create an optimal distribution plan and determine delivery routes and methods.

[1539] Specific operation:

[1540] 1. The server receives an emergency request from the disaster area.

[1541] 2. The server analyzes the emergency request and identifies the type and quantity of supplies needed.

[1542] 3. The server generates a prompt such as "Please suggest the optimal route and means to deliver this item."

[1543] 4. The server inputs the prompt text, emergency request data, geographic information, and local demand data into the generative AI model.

[1544] 5. The AI ​​model analyzes and outputs the optimal allocation plan.

[1545] 6. The server saves the allocation plan in the database and displays it on the management screen.

[1546] Step 4: Using the Emotion Engine to Raise Funds and Order Supplies

[1547] Input: User payment information, sentiment data, donation data

[1548] Output: Received donation data, order list for needed supplies

[1549] Before a user makes a donation through a cashless payment service, an emotion engine recognizes the user's emotions and displays appropriate donation campaigns and suggestions.

[1550] Specific operation:

[1551] 1. A user accesses the donation page using a cashless payment service.

[1552] 2. The emotion engine recognizes the user's face and detects "empathy" or "sense of crisis."

[1553] 3. The emotion engine suggests fundraising campaigns based on the user's emotions.

[1554] 4. The user enters the donation amount and completes the cashless payment.

[1555] The server generates a list of needed supplies based on the collected donation data and orders them through online shopping.

[1556] Specific operation:

[1557] 1. The server stores the donation data in a database.

[1558] 2. The server generates a prompt such as "Please create a list of items to be purchased with the 5 million yen donation."

[1559] 3. The server inputs the prompt and donation data into the generative AI model.

[1560] 4. The AI ​​model analyzes and outputs a list of necessary supplies.

[1561] 5. The server orders the necessary supplies through the online shopping system and confirms the order.

[1562] 6. The server notifies the delivery company of the order details so that the order can be processed.

[1563] Step 5: Delivering supplies

[1564] Input: Order data, delivery company information, delivery route information

[1565] Output: Real-time monitoring data on delivery status, response information in case of abnormalities

[1566] The server arranges for the ordered supplies to be delivered promptly to the disaster area, tracks the delivery status in real time, and responds immediately if any abnormalities occur.

[1567] Specific operation:

[1568] 1. The server communicates with the delivery company and confirms the delivery arrangements for the goods.

[1569] 2. The server monitors the delivery truck's GPS data and tracks its progress in real time.

[1570] 3. If the server detects an abnormality, it notifies the delivery company of an alternative route and reroutes the truck.

[1571] 4. The server displays delivery status and progress on the management screen, allowing the person in charge to check it in real time.

[1572] Following this procedure, the system effectively manages and optimizes the distribution of relief supplies.

[1573] (Application example 2)

[1574] 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."

[1575] Conventional systems for distributing relief supplies during disasters have had difficulty in forecasting demand and responding to emergency requests, and efficiently and fairly distributing supplies. In particular, the lack of appropriate proposals that take into account fluctuations in traffic conditions and user emotions often makes it difficult to deliver supplies quickly and manage donation campaigns effectively.

[1576] 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 acquiring inventory data from a stockpile database and updating the database with the latest inventory information; means for analyzing demographic data, people flow data, and past disaster data using an AI model to predict demand for supplies; means for generating a list of needed supplies based on the predicted demand for supplies; means for receiving emergency requests from disaster-stricken areas, analyzing the contents of the requests, and identifying the types and quantities of needed supplies; means for formulating an optimal distribution plan and determining delivery routes and means based on geographic information of the disaster-stricken areas and local demand data; means for receiving and aggregating donation data through a cashless payment service; means for ordering needed supplies through online shopping and confirming the order contents; means for arranging for the ordered supplies to be delivered promptly to the disaster-stricken areas via a designated delivery company and tracking the delivery status in real time; means for acquiring real-time traffic conditions and notifying of dynamic route changes; and means for analyzing a user's emotions using an emotion recognition engine and making appropriate suggestions. This will enable efficient and fair distribution of relief supplies through rapid delivery that adapts to changes in traffic conditions and effective donation suggestions based on user emotions.

[1577] The "stockpile database" is a database that records and manages inventory information for supplies needed in the event of a disaster.

[1578] "Inventory data" refers to information regarding the types and quantities of supplies recorded in the stockpile database.

[1579] An "AI model" is an algorithm that uses artificial intelligence technology to analyze data and make predictions.

[1580] "Demographic data" refers to data on population changes and composition by region.

[1581] "People flow data" refers to data about the movement of people within and outside a specific area.

[1582] "Demand for goods" refers to the quantity and type of goods required within a specific period of time.

[1583] An "emergency request" is a request for relief supplies from an affected area during a disaster.

[1584] "Geographic information" refers to data about the geographic characteristics and traffic conditions of a particular area.

[1585] An "allocation plan" is a plan that determines the optimal delivery route and distribution method for supplies.

[1586] "Cashless payment service" refers to a means of transferring funds electronically without using cash.

[1587] "Fundraising Data" means information about funds raised through fundraising activities.

[1588] "Online shopping" refers to the process of purchasing goods over the Internet.

[1589] "Delivery company" means a company that transports goods to a specified location.

[1590] "Real-time" refers to processing data and providing information on the same time axis as the current time.

[1591] "Traffic conditions" refers to data on vehicle flow and congestion in specific areas and routes.

[1592] "Dynamic routing" refers to instantly adjusting and changing delivery routes based on real-time traffic information.

[1593] An "emotion recognition engine" is a technology that analyzes a user's emotions and makes appropriate suggestions based on the results.

[1594] This invention provides a system for optimizing the distribution of relief supplies during disasters. The system utilizes AI technology and an emotion recognition engine to optimize stockpile management, people flow data analysis, donation collection, and supply ordering and delivery. This will also minimize shortages and surpluses of supplies in disaster-stricken areas.

[1595] Hardware and software used

[1596] Hardware

[1597] Server: High-performance processor, SSD storage, and sufficient RAM

[1598] Devices: Smartphones, devices with GPS

[1599] software

[1600] Programming language: Python

[1601] Web framework: Django

[1602] Machine learning library: Scikit-learn (Sklearn)

[1603] Data processing and calculation flow

[1604] Management of emergency supplies database

[1605] The server automatically retrieves inventory data from stockpiles set up for each region and periodically updates the database, ensuring that inventory information is always up to date and instantly listing shortages and surplus supplies.

[1606] Demographic data and supply demand forecasts

[1607] The server inputs demographic data, human flow data, and data from past disasters into an AI model to predict demand for supplies, which then evaluates the amount of supplies that will be needed at a specific point in time in the future.

[1608] Analysis of emergency requests and optimal allocation planning

[1609] The server receives emergency requests from disaster-stricken areas and analyzes their contents to determine the type and quantity of supplies needed. Based on this, an AI model is used to create an optimal distribution plan, determining delivery routes and means. It also adds a function to obtain real-time traffic conditions and notify of dynamic route changes.

[1610] Aggregating donations and ordering supplies using an emotion recognition engine

[1611] Before a user makes a donation through the cashless payment service, an emotion recognition engine recognizes the user's emotions. Based on the recognition results, appropriate donation campaigns and donation suggestions are displayed. The server also generates a list of needed supplies based on the collected donation data and orders the supplies through online shopping.

[1612] Delivery of supplies

[1613] The server then arranges for the ordered supplies to be delivered to the disaster area as quickly as possible. Delivery status is tracked in real time, and any abnormalities are dealt with immediately.

[1614] Examples and prompts

[1615] Example 1

[1616] During a disaster, when water supplies are tight in a certain area, the server uses stockpile information and past data to predict demand for the next week and generate a list of necessary supplies.

[1617] Example 2

[1618] When a user uses the cashless payment service, an emotion recognition engine recognizes the user's "empathy" or "sense of crisis" and suggests "disaster relief donations." The user can donate and check the total amount and progress in real time.

[1619] Prompt Sentence Examples

[1620] "The emotion recognition engine should suggest the most appropriate menu based on the user's emotional state."

[1621] "Please provide the best way to notify dynamic route changes according to traffic conditions in the affected area."

[1622] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1623] Step 1:

[1624] The server retrieves inventory data from each regional stockpile facility and periodically updates this data in a database. The input data is the type and amount of inventory at each stockpile facility, and the output is a database containing the latest inventory information. At this time, shortages and excess inventory are listed.

[1625] Step 2:

[1626] The server acquires demographic data, human flow data, and past disaster data, and inputs this into an AI model to predict demand for supplies. The input data is data on regional population changes and past disasters, and based on this, a forecast of supply demand is output. This forecast includes the amount and type of supplies that will be needed at a specific point in the future.

[1627] Step 3:

[1628] The server generates a list of required supplies based on predicted demand. It uses the output of the demand forecast from the AI ​​model to list the specific supplies and quantities needed. The input is predicted demand data, and the output is a list of required supplies.

[1629] Step 4:

[1630] The server receives emergency requests from disaster-stricken areas, analyzes their contents, and identifies the types and quantities of supplies needed. The input data is the content of the emergency request, and the output is the identified types and quantities of supplies needed. The server then formulates an optimal distribution plan based on this information.

[1631] Step 5:

[1632] The server formulates an optimal distribution plan based on geographic information of the affected area and local demand data, and determines delivery routes and means. The input data is geographic information and demand data, and the output is an optimal distribution plan and delivery route. Routes are dynamically changed, taking into account real-time traffic conditions.

[1633] Step 6:

[1634] The server receives and aggregates donation data through a cashless payment service. The input data is donation information from users, and the output is aggregated donation data. Based on this data, a list of necessary supplies is generated and the supplies are ordered through online shopping.

[1635] Step 7:

[1636] When a user makes a cashless payment, the emotion recognition engine recognizes the user's emotions and then proposes appropriate donation campaigns and suggestions based on the results. The input data is the user's emotion data, and the output is appropriate donation campaigns and suggestions.

[1637] Step 8:

[1638] The server arranges for the ordered supplies to be delivered to the disaster area promptly and tracks the delivery status in real time. The input data is the order information and delivery status of the supplies, and the output is the real-time delivery status. If an abnormality occurs, it responds immediately.

[1639] Specific examples

[1640] Example prompt sentence:

[1641] Let the emotion recognition engine suggest the most appropriate menu based on the user's emotional state.

[1642] 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.

[1643] 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.

[1644] 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.

[1645] 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.

[1646] 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.

[1647] 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.

[1648] 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).

[1649] 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.

[1650] 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."

[1651] 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.

[1652] 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).

[1653] 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.

[1654] 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.

[1655] 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.

[1656] 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.

[1657] 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.

[1658] 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.

[1659] 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.

[1660] 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.

[1661] 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.

[1662] 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.

[1663] The following is further disclosed regarding the above embodiment.

[1664] (Claim 1)

[1665] A means for obtaining inventory data from the stockpile database and updating the database with the latest inventory information;

[1666] A method for predicting demand for supplies by analyzing demographic data, people flow data, and past disaster data using AI models;

[1667] means for generating a required supplies list based on the predicted supplies demand;

[1668] A means to receive emergency requests from disaster-stricken areas, analyze the contents of those requests, and identify the types and quantities of supplies needed;

[1669] A method for formulating optimal distribution plans and determining delivery routes and means based on geographic information of the affected areas and local demand data;

[1670] A means of receiving and aggregating donation data through cashless payment services;

[1671] A way to order necessary supplies through online shopping and check the order details;

[1672] Arrange for ordered supplies to be delivered promptly to affected areas via designated delivery companies, and track delivery status in real time.

[1673] A system including:

[1674] (Claim 2)

[1675] 10. The system of claim 1, further comprising means for allowing a user to check the progress of a donation in real time.

[1676] (Claim 3)

[1677] 10. The system of claim 1, further comprising means for immediately responding if an abnormality occurs during the delivery of goods.

[1678] "Example 1"

[1679] (Claim 1)

[1680] A means for obtaining inventory data from the stockpile database and updating the database with the latest inventory information;

[1681] A means of using generative AI models to analyze demographic data, people flow data, and past disaster data to predict demand for supplies;

[1682] means for generating a required supplies list based on the predicted supplies demand;

[1683] A means to receive emergency requests from disaster-stricken areas, analyze the contents of those requests, and identify the types and quantities of supplies needed;

[1684] A method for formulating optimal distribution plans and determining delivery routes and means based on geographic information of the affected areas and local demand data;

[1685] A means of receiving and aggregating donation data through cashless payment services;

[1686] A way to order and track supplies through online ordering;

[1687] A means to arrange for ordered supplies to be delivered promptly to disaster areas via designated delivery companies and track delivery status in real time.

[1688] A system including:

[1689] (Claim 2)

[1690] 10. The system of claim 1, further comprising means for allowing a user to check the progress of a donation in real time.

[1691] (Claim 3)

[1692] 10. The system of claim 1, further comprising means for immediately responding if an abnormality occurs during the delivery of goods.

[1693] "Application Example 1"

[1694] (Claim 1)

[1695] A means for obtaining inventory data from the stockpile database and updating the database with the latest inventory information;

[1696] A method for predicting demand for supplies by analyzing demographic data, people flow data, and past disaster data using AI models;

[1697] means for generating a required supplies list based on the predicted supplies demand;

[1698] A means to receive emergency requests from disaster-stricken areas, analyze the contents of those requests, and identify the types and quantities of supplies needed;

[1699] A method for formulating optimal distribution plans and determining delivery routes and means based on geographic information of the affected areas and local demand data;

[1700] A means of receiving and aggregating donation data through cashless pa...

Claims

1. A means for obtaining inventory data from the stockpile database and updating the database with the latest inventory information; A method for predicting demand for supplies by analyzing demographic data, people flow data, and past disaster data using AI models; means for generating a required supplies list based on the predicted supplies demand; A means to receive emergency requests from disaster-stricken areas, analyze the contents of those requests, and identify the types and quantities of supplies needed; A method for formulating optimal distribution plans and determining delivery routes and means based on geographic information of the affected areas and local demand data; A means of receiving and aggregating donation data through cashless payment services; A way to order necessary supplies through online shopping and check the order details; Arrange for ordered supplies to be delivered promptly to affected areas via designated delivery companies, and track delivery status in real time. A system including:

2. The system of claim 1 further comprising means for allowing a user to check the progress of a donation in real time.

3. 2. The system according to claim 1, further comprising means for immediately responding when an abnormality occurs during the delivery of goods.

Images