System

Abstract

A system is provided.SOLUTION: Means for collecting data on food shortages, food inventory data, infrastructure conditions, and logistics data, means for analyzing the collected data with a generative AI model to generate a list of food shortages and necessary supplies for each area, means for visualizing the generated analysis results on a visual dashboard and transmitting the visual dashboard to a user terminal, and means for inputting supplies and funds that the user can provide; The system includes a means for matching the support destination with the supplies based on the information, a means for analyzing a delivery route and a method of the recommended supplies to formulate an efficient physical distribution plan, and a means for issuing a credit for the support activity after completion of the support and providing feedback to the user.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] There are currently many people suffering from hunger in the world, with the number reaching 828 million. This problem, coupled with the fact that one-third of food production is wasted, calls for a solution. However, the complex intertwining of economic, social, and environmental factors makes it difficult to solve the problem efficiently using conventional methods. Furthermore, the distribution of supplies poses challenges, such as selecting appropriate recipients and optimizing logistics. In these circumstances, a new system is needed to effectively solve the hunger problem. [Means for solving the problem]

[0005] The present invention provides a system that utilizes a generative AI model to collect and analyze data on hunger levels, food inventory, infrastructure status, and logistics. Specifically, the system includes the following means:

[0006] 1. Means of collecting hunger status, food inventory data, infrastructure status, and logistics data.

[0007] 2. A means of analyzing collected data using a generative AI model to generate regional hunger situations and lists of needed supplies.

[0008] 3. A means of visualizing the generated analysis results on a visual dashboard and sending them to the user's device.

[0009] 4. A means for users to input the supplies and funds they can provide, and then match supplies with recipients based on that information.

[0010] 5. A means of analyzing the routes and methods of delivery of recommended supplies and developing an efficient logistics plan.

[0011] 6. A means of issuing credit for the assistance activity and providing feedback to the user after the assistance is completed.

[0012] This will enable the selection of appropriate recipients and the optimal distribution of supplies, which is expected to lead to an effective solution to the hunger problem. It will also improve the transparency and efficiency of aid activities, increasing the likelihood that more companies and individuals will participate in aid.

[0013] A "famine situation" refers to a situation in which food is difficult to obtain in a particular region or group, resulting in nutritional deficiencies and health problems.

[0014] "Food inventory data" refers to information regarding the quantity and quality of current food stocks in a particular area or facility.

[0015] "Infrastructure condition" refers to the condition and function of infrastructure such as roads, communications, electricity, and water supplies in a particular area.

[0016] "Logistics data" refers to information such as routes, times, costs, and means of transporting and delivering goods.

[0017] A "generative AI model" refers to an artificial intelligence system that uses machine learning and data analysis techniques to make predictions and perform analysis for specific purposes.

[0018] A "visual dashboard" refers to an interface that visually displays analysis results and data, allowing users to easily understand the information.

[0019] "Supplies" refers to items such as food, daily necessities, and medicines provided to alleviate hunger and support daily life.

[0020] "Users" refer to companies and individuals who use the system to participate in support activities.

[0021] "Aid recipients" refer to regions or groups experiencing hunger and where relief supplies and infrastructure development are needed.

[0022] "Credits" refer to points or rewards given for support activities, which indicate the degree of contribution of a user. [Brief explanation of the drawings]

[0023] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0024] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0026] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0027] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0028] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0029] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0030] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0031] [First embodiment]

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

[0033] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0034] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0035] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0036] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0037] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0038] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0040] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0041] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0042] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0043] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0044] This invention relates to a platform system that aims to effectively solve the problem of hunger using generative AI. Specific embodiments for implementing this system will be described below.

[0045] System Configuration

[0046] This system mainly consists of three main components: a server, a terminal, and a user.

[0047] Server: The central location for data collection, analysis, and results management. This is where the generative AI model runs, generating hunger statistics and supply lists for each region.

[0048] Terminal: A device where users access the system, enter data, and view results. Here, analytical results are displayed through a visual dashboard.

[0049] Users: Primarily companies and individuals who use the platform to participate in relief activities. Users provide supplies and funds, enter data, and obtain records and credits for their donations.

[0050] Program processing

[0051] Data collection and analysis

[0052] The server will first collect hunger status, food inventory data, infrastructure status, and logistics data from multiple public agencies and non-governmental organizations (NGOs), including access to APIs and data storage.

[0053] The collected data is fed into a generative AI model, which analyzes the data and generates a regional hunger situation and a list of needed supplies.

[0054] Data Visualization

[0055] The analysis results are displayed in the form of a visual dashboard. The server creates visualization components such as graphs and maps based on the generated data and sends them to the device.

[0056] The dashboard displayed on the device allows users to see at a glance the hunger situation in each region, the types of supplies needed, and aid priorities.

[0057] Supply and matching

[0058] Users input details of the supplies and funds they can provide through their terminals and submit the information, which is then stored on the server.

[0059] The server uses a generative AI model to calculate the optimal recipient of aid based on the supply information provided by users, thereby matching the needs of each region with the supplies provided by users.

[0060] Logistics management

[0061] The server calculates the optimal support route and method, and develops an efficient logistics plan. Specifically, it evaluates delivery options by air, sea, and land, and selects the most efficient delivery route.

[0062] Details of the logistics plan will be communicated to the relevant logistics partners.

[0063] Crediting and Feedback

[0064] Once the assistance activity is completed, the server receives a local acknowledgement of receipt and adds a "credit" to the user's account.

[0065] The server also provides feedback on the results of the support activities, providing reference information for the user when planning their next support.

[0066] Specific examples

[0067] For example, consider a company that can donate 5,000 kg of rice. A company representative logs into the platform using a device and enters the details of the donation (e.g., 5,000 kg of rice). The server then receives the data, and based on the collected hunger situation data, the generative AI model calculates the optimal recipient (e.g., a specific region in Africa). The results are displayed on a dashboard, where the company representative can check the progress of the donation and logistics plans.

[0068] Once the donation is complete, receipt confirmation data from the local area is sent to the server and credits are added to the company's account. At the same time, a feedback report is provided to help the company decide whether to donate next time. In this way, the entire system operates efficiently and aims to contribute to solving hunger.

[0069] The processing flow will be explained below.

[0070] Step 1:

[0071] The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public institutions and non-governmental organizations (NGOs) by sending requests to the United Nations Hunger Database API and the World Bank's data storage.

[0072] Step 2:

[0073] The server stores the collected data in an internal database, and when storing it, it formats and converts the data to ensure consistency.

[0074] Step 3:

[0075] The server inputs the data retrieved from the database into the generative AI model, which then begins analysis. The generative AI model identifies the hunger situation in each region, a list of necessary supplies, infrastructure shortages, and other information, and generates a report.

[0076] Step 4:

[0077] The server converts the analysis results into a visual dashboard, specifically by creating visualization components such as graphs and maps and designing a user-friendly interface.

[0078] Step 5:

[0079] The server then sends the generated visual dashboard to the device, where users can access the dashboard and check the hunger situation in each region, the types of supplies needed, and the priority of aid.

[0080] Step 6:

[0081] The user uses the terminal to input and submit details of the goods and funds available for donation, including the quantity, quality, and period of time available.

[0082] Step 7:

[0083] The server receives the material data obtained from the user, stores it in a database, and converts the stored data into an appropriate format for analysis.

[0084] Step 8:

[0085] The server uses a generative AI model to match the items provided by users with local needs, specifically by comparing the provided items with local hunger data and identifying the best recipients.

[0086] Step 9:

[0087] Based on the matching results, the server calculates the appropriate delivery route and method for the goods, analyzes multiple logistics options (air transport, sea transport, land transport) and formulates an efficient transportation plan.

[0088] Step 10:

[0089] The server notifies the relevant logistics partners of the details of the logistics plan and begins preparations for delivery, monitoring the delivery status in real time and making adjustments as necessary.

[0090] Step 11:

[0091] Once the relief activities are completed, the server receives receipt confirmation data from the site, and uses this data to confirm the completion of the relief activities.

[0092] Step 12:

[0093] The server will add "credits" to the user's account for the support, which will then be reflected in the user's profile.

[0094] Step 13:

[0095] The server provides the user with feedback on the results of the support activities, along with analytical data to help them improve their next support efforts. The feedback report is displayed on the user's dashboard.

[0096] The above are the specific program processing steps of the system for implementing the invention.

[0097] Example 1

[0098] 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."

[0099] This invention relates to a platform system for effectively solving the problem of hunger, which occurs frequently around the world. Currently, it is difficult to grasp the hunger situation, procure and supply necessary supplies, and efficiently manage the delivery of supplies and relief activities, which hinders the speed and effectiveness of relief activities. Other issues include low transparency and reliability of relief activities, and a lack of appropriate feedback to donors.

[0100] 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.

[0101] In this invention, the server includes: means for collecting hunger status, food inventory data, infrastructure status, and logistics data; means for analyzing the collected data using a generative AI model to generate a list of hunger status and needed supplies for each region; means for visualizing the generated analysis results on a visual dashboard and sending them to the user's device; means for users to input the supplies and funds they can provide and match supplies with recipients based on that information; means for analyzing the recommended delivery routes and methods for supplies using an advanced algorithm, formulating an efficient logistics plan, and notifying appropriate logistics partners; and means for issuing credits for relief activities using blockchain technology and providing feedback to users after the relief activities are completed. This enables effective and prompt resolution of hunger issues, improved transparency and reliability of relief activities, and appropriate feedback to donors.

[0102] "Hunger Situation" is data showing the degree of food shortages and malnutrition in each region.

[0103] "Food inventory data" refers to data that indicates information regarding the current amount and type of food in stock in a particular area or facility.

[0104] "Infrastructure status" refers to data that indicates the status of basic facilities and services such as roads, communications, power supply, and water supply.

[0105] "Logistics data" refers to data that indicates information related to the transportation and delivery of goods, including routes, means of transportation, and delivery schedules.

[0106] "Generative AI models" refer to artificial intelligence algorithms or programs used to analyze collected data and make predictions or optimizations.

[0107] A "visual dashboard" is an interface for visually displaying analysis results, and includes visual components such as graphs and maps.

[0108] "User terminal" refers to a device used by a user to access and operate the system, including a personal computer or smartphone.

[0109] "Resource matching" refers to the process by which aid providers optimally allocate available resources and funds to areas and facilities in need.

[0110] "Logistics planning" is a plan for the efficient transportation and delivery of goods, and refers to the process of determining the optimal routes and means.

[0111] "Logistics Partner" refers to a company or organization that partners with us to carry out the transportation or delivery of goods.

[0112] "Blockchain technology" is a distributed database technology used to ensure data transparency and prevention of tampering.

[0113] "Credits" refer to digital points or certificates that indicate recognition and reward for support activities.

[0114] "Feedback" refers to the process of providing evaluation information about the effectiveness and results of support activities.

[0115] This invention relates to a platform system that aims to effectively solve the problem of hunger using a generative AI model. This system consists of three entities: a server, a terminal, and a user. Specific embodiments for implementing this system are described below.

[0116] System Configuration

[0117] Server: The central location for data collection, analysis, and results management. This is where the generative AI model runs, generating hunger statistics and supply lists for each region.

[0118] Terminal: A device where users access the system, enter data, and view results. Here, analytical results are displayed through a visual dashboard.

[0119] Users: Primarily companies and individuals who use the platform to participate in relief activities. Users provide supplies and funds, enter data, and obtain records and credits for their donations.

[0120] Data collection and analysis

[0121] The server will collect hunger, food inventory, infrastructure, and logistics data from multiple public and non-governmental organizations, utilizing APIs and cloud storage.

[0122] For example, the server accesses a public institution's database via an API to obtain the latest hunger situation data, which is then stored in cloud storage such as AWS (registered trademark) S3.

[0123] The collected data is fed into a generative AI model (specifically, using TENSORFLOW®), which analyzes the data and generates a regional hunger situation and a list of supplies needed, using statistical models and machine learning algorithms.

[0124] Data Visualization

[0125] The server uses the D3.js library to convert the generated analysis results into visual components such as graphs and maps, and the generated visual data is sent to the device in JSON format.

[0126] The device displays a visual dashboard that allows users to interactively check the hunger situation map and supply status in real time on their browser.

[0127] Supply and matching

[0128] Users input detailed information about the supplies and funds they can provide through their devices. For example, specific information such as "donating 5,000 kg of rice." This data is sent to the server via API and stored in a database (e.g., MySQL®).

[0129] The server uses a generative AI model to match the material information provided by users with the most appropriate recipients. This matching process compares the needs of each region with the materials provided to make the best match.

[0130] Logistics management

[0131] The server uses Dijkstra's algorithm to calculate the optimal relief route and delivery method, which determines the most efficient delivery route and ensures that relief supplies reach their destination as quickly as possible.

[0132] The results of the optimal delivery route calculation are sent to logistics partners via API, allowing them to carry out efficient logistics planning.

[0133] Crediting and Feedback

[0134] Once the donation is completed, the server receives local confirmation data and adds "credits" to the user's account, a process that utilizes blockchain technology to ensure transparency and reliability.

[0135] The server also provides the user with feedback on the results of the support activities and information that can be used as reference for planning the next support. The feedback report is sent from the server to the terminal, and the user can refer to it when planning the next support.

[0136] Examples of prompt statements

[0137] "Generate the best recipients and necessary supplies list based on the following data: Hunger situation data (areas A, B, C), Food inventory data (areas A, B, C), Infrastructure situation (areas A, B, C), Logistics data (areas A, B, C)"

[0138] This will ensure that the entire system is run efficiently, and is expected to contribute to solving the problem of hunger.

[0139] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0140] Step 1:

[0141] Data collection

[0142] The server collects hunger, food inventory, infrastructure, and logistics data from multiple public and non-governmental organizations, using API endpoints to access each organization's database and retrieve the latest data.

[0143] Input: Data collected via API (hunger status, food stocks, infrastructure, logistics)

[0144] Output: Raw data stored in cloud storage (e.g. AWS S3)

[0145] Specific operation: The server periodically executes an API call and saves the acquired data to the specified cloud storage.

[0146] Step 2:

[0147] Data analysis

[0148] The server inputs the collected data into a generative AI model, specifically using TensorFlow to analyze it and generate a hunger situation and a list of supplies needed.

[0149] Input: Datasets of hunger, food inventory, infrastructure, and logistics retrieved from cloud storage.

[0150] Output: Hunger report and list of supplies needed for each analyzed region

[0151] Specific operation: The server feeds the collected data into the TensorFlow model, calculates the analysis results, and stores the generated report and list of required supplies in a database.

[0152] Step 3:

[0153] Data visualization

[0154] The server converts the generated analysis results into a visual dashboard, generating graphs, maps, and other data using the D3.js library, and sends them to the device in JSON format.

[0155] Input: Analysis results from the generative AI model (hunger situation report, list of needed supplies)

[0156] Output: Visual data in JSON format

[0157] Specific operation: The server uses the analysis results to generate heat maps and bar charts using D3.js, converts them to JSON format, saves them, and sends them to the terminal as appropriate.

[0158] Step 4:

[0159] Viewing the Dashboard

[0160] The terminal receives the JSON data sent from the server and displays it as a visual dashboard.

[0161] Input: Visual data in JSON format from the server

[0162] Output: A visual dashboard displayed in the user's browser

[0163] Specific operation: The terminal parses the received JSON and displays it as an interactive dashboard using the D3.js library.

[0164] Step 5:

[0165] Enter and submit supply information

[0166] The user uses a terminal to input detailed information about the supplies and funds that can be provided and sends this information to the server.

[0167] Input: Information about supplies and funds entered by the user (e.g., 5,000 kg of rice)

[0168] Output: Material information sent to the server

[0169] Specific operation: The user enters the necessary information into a form on the device, which is then sent to the server via the API and stored in a database.

[0170] Step 6:

[0171] Executing the matching algorithm

[0172] The server uses a generative AI model to calculate the optimal recipient of support based on the material information provided by the user.

[0173] Input: Provided supplies information, hunger situation data, list of required supplies

[0174] Output: List of optimal support recipients

[0175] Specific operation: The server inputs the supply information into the TensorFlow model, and calculates the optimal support destination as the analysis result. This information is stored in a database.

[0176] Step 7:

[0177] Delivery route calculation and notification

[0178] The server uses advanced algorithms to calculate efficient delivery routes and methods for supplies and notifies logistics partners.

[0179] Input: List of optimal support recipients and logistics data

[0180] Output: Delivery plan notification to logistics partners

[0181] Specific operation: The server calculates the optimal delivery route using Dijkstra's algorithm and notifies the logistics partner of this information via API.

[0182] Step 8:

[0183] Confirmation of support activities and issuance of credits

[0184] The user receives confirmation data from the site to confirm the completion of the relief activity and sends it to the server, which issues credits to the user's account based on the confirmation data and provides feedback.

[0185] Input: Receipt confirmation data from the site

[0186] Output: Credits to user accounts and feedback reports

[0187] Specific operation: The server records the receipt confirmation data using blockchain technology, adds credits to the user, and generates and sends a feedback report.

[0188] (Application example 1)

[0189] 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."

[0190] Hunger is a global issue, threatening the very foundations of life in many regions. To combat this, adequate supplies and efficient logistics planning are essential. However, managing aid activities and calculating optimal supply delivery routes is complex and consumes significant human resources. Furthermore, the lack of real-time inventory management and visibility into delivery routes increases the risk of aid delays. This makes it difficult to provide fast and effective aid to famine-stricken areas.

[0191] 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.

[0192] In this invention, the server includes a means for collecting data on the famine situation, food inventory data, infrastructure status, and logistics data, a means for analyzing the collected data with a generative AI model to generate a list of the famine situation and supplies needed by region, and a means for visualizing the generated analysis results on a visual dashboard and sending them to the user's device, thereby enabling more efficient and rapid response in relief activities.

[0193] The invention further includes a means for users to input the supplies and funds they can provide and match supplies with recipients based on that information, a means for analyzing the recommended delivery route and method for the supplies and formulating an efficient logistics plan, a means for issuing credits for the relief activities and providing feedback to the user after the relief is completed, a means using a smart device for displaying inventory status and delivery routes in real time, and a means for supporting the picking and delivery of relief supplies at the logistics center. This improves work efficiency within the logistics center and enables fast and effective relief to famine-stricken areas.

[0194] "Hunger situation" refers to the level of food shortages in a particular area and the situation of people suffering from malnutrition.

[0195] "Food inventory data" refers to data that includes inventory information for food, beverages, and other items provided as relief supplies.

[0196] "Infrastructure status" refers to the current condition and performance of infrastructure such as roads, transportation, and communication networks related to relief activities.

[0197] "Logistics data" refers to information relating to the transportation of goods, including information such as the point of departure, destination, transportation method, route, and time.

[0198] A "generative AI model" is an artificial intelligence model that analyzes collected data and generates specific outputs (for example, the hunger situation in each region and a list of needed supplies).

[0199] A "visual dashboard" refers to a visual user interface for displaying analyzed data in an easy-to-read format.

[0200] "Terminal" means a device (such as a smartphone, tablet, or computer) through which a user accesses the system, enters data, and views results.

[0201] "Matching" is the process of matching available supplies and funds with the needs of the recipient and finding the optimal combination.

[0202] A "logistics plan" is a plan to determine efficient routes and methods for delivering supplies and to ensure optimal relief activities.

[0203] "Credits" are evaluation points or rewards given to users who perform support activities.

[0204] "Feedback" is information provided to users reporting on the results of support activities and areas for improvement.

[0205] "Smart devices" are wearable electronic devices such as glasses and headsets that have internet connectivity and high-performance sensors.

[0206] "Picking" refers to the task of selecting specific items from inventory at a logistics center.

[0207] This invention relates to a platform system that aims to effectively solve the problem of hunger using a generative AI model. The system of the present invention is mainly composed of three entities: a server, a terminal, and a user.

[0208] System Configuration

[0209] Server: Collects data, analyzes, and manages the results. This server runs a generative AI model that generates hunger situations and lists of supplies for each region.

[0210] Terminal: A device where users access the system, enter data, and view results. Here, analytical results are displayed through a visual dashboard.

[0211] Users: Primarily companies and individuals who use the system to participate in relief activities. Users provide and input supplies and funds, and obtain records and credits for their support.

[0212] Program Overview

[0213] 1. Data Collection and Analysis

[0214] The server first collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public institutions and non-governmental organizations (NGOs). This data collection includes access to APIs and data storage. The collected data is then fed into a generative AI model, which analyzes the data and generates regional hunger status and a list of needed supplies.

[0215] 2. Data visualization

[0216] The analysis results are displayed in the form of a visual dashboard. The server creates visualization components such as graphs and maps based on the generated data and sends them to the device. The dashboard displayed on the device allows users to see at a glance the hunger situation in each region, the types of supplies needed, and aid priorities.

[0217] 3. Supply and matching

[0218] Users input detailed information about the supplies and funds they can provide through their devices and submit it. This information is stored on the server. The server then uses a generative AI model based on the supply information provided by the user to calculate the optimal recipient of support. This allows the system to match the needs of each region with the supplies provided by the user.

[0219] 4. Logistics management

[0220] The server calculates the optimal support route and method, and develops an efficient logistics plan. Specifically, it evaluates air, sea, and land delivery options and selects the most efficient delivery route. The details of the logistics plan are then communicated to the relevant logistics partners.

[0221] 5. Crediting and Feedback

[0222] Once the relief effort is completed, the server receives a local confirmation of receipt, credits the user's account, and provides feedback on the success of the relief effort, providing reference information for the user when planning their next relief effort.

[0223] Specific examples

[0224] For example, let's say a company can donate 5,000 kg of rice. The company's representative logs into the platform using a terminal and enters the details of the goods to be donated (e.g., 5,000 kg of rice). The server then receives this data, and the generative AI model calculates the optimal recipient of the donation based on the collected hunger situation data. The results are displayed on a dashboard, where company representatives can check the progress of the donation and logistics plans. Once the donation is completed, confirmation of receipt from the site is sent to the server, and credits are added to the company's account. At the same time, a feedback report is provided to help with the next donation. In this way, the entire system operates efficiently, aiming to contribute to resolving hunger.

[0225] Prompt Sentence Examples

[0226] "Please describe the overview and functionality of your hunger relief logistics management app. Include a specific example of a program that retrieves data from Firebase, analyzes it using a TensorFlow model, calculates optimal delivery routes using the Google® Maps API, and displays the data on smart glasses using OpenCV."

[0227] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0228] Step 1:

[0229] Data collection

[0230] Subject: Server

[0231] The server collects hunger status, food inventory data, infrastructure status, and logistics data from public institutions and non-governmental organizations (NGOs) through APIs and data storage. The collected data is stored as raw data. Specifically, the server sends requests to the APIs of each data provider and imports the returned data.

[0232] Input: Send API request

[0233] Output: Save various data

[0234] Step 2:

[0235] Data analysis

[0236] Subject: Server

[0237] The server inputs the collected data into a generative AI model, which analyzes the data and generates a regional hunger situation and a list of needed supplies. Specifically, the server runs the model using TensorFlow to obtain predictions.

[0238] Input: Collected data

[0239] Output: Analysis results (hungry situation by region and list of necessary supplies)

[0240] Step 3:

[0241] Data Visualization

[0242] Subject: Server

[0243] The server uses the generated analysis results to create a visual dashboard and sends it to the terminal. The data is visualized in the form of graphs, maps, etc. Specifically, the server generates the dashboard using libraries such as OpenCV and D3.js and sends it to the terminal via WebSocket.

[0244] Input: Analysis results

[0245] Output: Visual dashboard

[0246] Step 4:

[0247] Supply and matching

[0248] Subject: User and Server

[0249] Users enter information about the supplies and funds they can provide through their devices and send it to the server. The server receives this information and uses a generative AI model to calculate the optimal recipient of aid. Specifically, users enter information into a web form, and the server then analyzes it again using the AI ​​model.

[0250] Input: Material and financial information

[0251] Output: Best Support

[0252] Step 5:

[0253] Logistics planning

[0254] Subject: Server

[0255] The server calculates the optimal support route and method, and develops an efficient logistics plan. It evaluates delivery options by air, sea, and land, and selects the most efficient delivery route. Specifically, the server calculates the delivery route using the Google Maps API and notifies the logistics partner of the results.

[0256] Input: Information on the provided supplies and recipients

[0257] Output: Efficient logistics planning

[0258] Step 6:

[0259] Crediting and Feedback

[0260] Subject: Server

[0261] Once a relief effort is completed, local receipt confirmation data is sent to the server. The server uses this information to add credits to the user's account. It also provides feedback on the success of the relief effort, providing reference information for the user when planning their next relief effort. Specifically, the server analyzes the receipt confirmation data, updates the user's credits, and generates a report.

[0262] Input: Receipt confirmation data

[0263] Output: Credits added, feedback report

[0264] Step 7:

[0265] Real-time display on smart devices

[0266] Subject: Smart device (terminal)

[0267] The smart device displays real-time inventory status and delivery routes. To assist with the picking and delivery of relief supplies at the logistics center, the device incorporates OpenCV and Google Maps API. Specifically, the smart glasses overlay information on the user's field of vision based on data sent from the server.

[0268] Input: Shipping and inventory data from the server

[0269] Output: Real-time display on smart devices

[0270] 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.

[0271] This invention combines an emotion engine with a platform system that aims to effectively solve the problem of hunger using generative AI. Specific embodiments for implementing this system are described below.

[0272] System Configuration

[0273] This system is mainly composed of three entities: a server, a terminal, and a user. It also incorporates an emotion engine that recognizes the user's emotions.

[0274] Server: This is the central location for data collection, analysis, emotion recognition, and result management. This is where the generative AI model runs, generating regional hunger alerts and lists of supplies, and the emotion engine analyzes user feedback.

[0275] Terminal: A device where users access the system, input data, and view results. Here, analysis results are displayed through a visual dashboard, and users' emotional data is also entered.

[0276] Users: These are primarily companies and individuals who use the platform to participate in relief efforts. Users provide supplies and funds, enter emotional feedback, and receive records of their support and credits.

[0277] Program processing

[0278] Data collection and analysis

[0279] The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public agencies and non-governmental organizations (NGOs), including access to APIs and data storage.

[0280] The collected data is fed into a generative AI model, which analyzes the data and generates a regional hunger situation and a list of needed supplies.

[0281] Data Visualization

[0282] The analysis results are displayed in the form of a visual dashboard. The server creates visualization components such as graphs and maps based on the generated data and sends them to the device.

[0283] The dashboard displayed on the device allows users to see at a glance the hunger situation in each region, the types of supplies needed, and aid priorities.

[0284] Supply and matching

[0285] Users input details of the supplies and funds they can provide through their terminals and submit the information, which is then stored on the server.

[0286] The server uses a generative AI model to calculate the optimal recipient of aid based on the supply information provided by users, thereby matching the needs of each region with the supplies provided by users.

[0287] Logistics management

[0288] The server calculates the optimal support route and method, and develops an efficient logistics plan. Specifically, it evaluates delivery options by air, sea, and land, and selects the most efficient delivery route.

[0289] Details of the logistics plan will be communicated to the relevant logistics partners.

[0290] Crediting and Feedback

[0291] Once the relief effort is completed, the server receives local receipt confirmation data, which is used to confirm the relief effort has been completed and add a "credit" to the user's account.

[0292] The server also provides feedback on the results of the support activities, providing reference information for the user when planning their next support.

[0293] Emotion Recognition and Customized Feedback

[0294] The server uses an emotion engine to collect and analyze the user's emotional data when the user provides feedback, thereby identifying how the user feels about the support activity.

[0295] Based on the emotion data, the server provides customized feedback to the user, including encouragement and suggestions for improvement based on the user's emotions.

[0296] The analysis results of the emotion engine are used to optimize the next relief operation plan.

[0297] Specific examples

[0298] For example, consider a company that can donate 5,000 kg of rice. A company representative logs into the platform using a device and enters the details of the donation (e.g., 5,000 kg of rice). The server then receives the data, and based on the collected hunger situation data, the generative AI model calculates the optimal recipient (e.g., a specific region in Africa). The results are displayed on a dashboard, where the company representative can check the progress of the donation and logistics plans.

[0299] Once the donation is completed, receipt confirmation data from the site is sent to the server, and credits are added to the company's account. At the same time, the server uses an emotion engine to analyze the emotions of the person in charge. For example, if there are many positive emotions about the donation activity, the server will provide feedback emphasizing its success. Conversely, if there is a lot of feedback pointing out areas for improvement, the server will provide a report containing suggestions to help optimize the next donation activity. In this way, the entire system operates efficiently, aiming to increase user satisfaction while contributing to solving hunger.

[0300] The processing flow will be explained below.

[0301] Step 1:

[0302] The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public institutions and non-governmental organizations (NGOs) by sending requests to the United Nations Hunger Database API and the World Bank's data storage.

[0303] Step 2:

[0304] The server stores the collected data in an internal database. When storing the data, it formats and converts the data to maintain consistency. For example, it unifies data in different formats and extracts necessary indicators.

[0305] Step 3:

[0306] The server inputs the data retrieved from the database into the generative AI model, which then begins analysis. The generative AI model identifies the hunger situation in each region, a list of necessary supplies, infrastructure shortages, and other information, and generates a report.

[0307] Step 4:

[0308] The server converts the analysis results into a visual dashboard, specifically by creating visualization components such as graphs and maps and designing a user-friendly interface.

[0309] Step 5:

[0310] The server then sends the generated visual dashboard to the device, where users can access the dashboard and check the hunger situation in each region, the types of supplies needed, and the priority of aid.

[0311] Step 6:

[0312] The user uses the terminal to input and submit details of the goods and funds available for donation, including the quantity, quality, and period of time available.

[0313] Step 7:

[0314] The server receives the material data obtained from the user, stores it in a database, and converts the stored data into an appropriate format for analysis.

[0315] Step 8:

[0316] The server uses a generative AI model to match the items provided by users with local needs, specifically by comparing the provided items with local hunger data and identifying the best recipients.

[0317] Step 9:

[0318] Based on the matching results, the server calculates the appropriate delivery route and method for the goods, analyzes multiple logistics options (air transport, sea transport, land transport) and formulates an efficient transportation plan.

[0319] Step 10:

[0320] The server notifies the relevant logistics partners of the details of the logistics plan and begins preparations for delivery, monitoring the delivery status in real time and making adjustments as necessary.

[0321] Step 11:

[0322] Once the relief activities are completed, the server receives receipt confirmation data from the site, and uses this data to confirm the completion of the relief activities.

[0323] Step 12:

[0324] The server will add "credits" to the user's account for the support, which will then be reflected in the user's profile.

[0325] Step 13:

[0326] The server provides the user with feedback on the results of the support activities, along with analytical data to help them improve their next support efforts. The feedback report is displayed on the user's dashboard.

[0327] Step 14:

[0328] When a user inputs feedback, the server uses an emotion engine to collect the user's emotion data, for example, by analyzing the text of the feedback or voice input and classifying the emotion as positive, negative, etc.

[0329] Step 15:

[0330] The server analyzes the user's feedback in detail based on the emotion data analyzed by the emotion engine, thereby identifying how the user feels about the support activities.

[0331] Step 16:

[0332] The server then provides customized feedback to the user based on the emotional data, such as highlighting achievements when emotions are predominantly positive, or providing specific areas for improvement when emotions are predominantly negative.

[0333] Step 17:

[0334] The server uses the analysis results of the emotion engine to reflect user feedback in the next support activity plan, specifically identifying support methods to increase user motivation and issues that need improvement.

[0335] The above are the specific program processing steps of the system for implementing the invention.

[0336] Example 2

[0337] 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."

[0338] Hunger is becoming a serious problem around the world, and appropriate aid is urgently needed, especially in resource-limited areas. The current system involves a complex and cumbersome process, including the provision and delivery of aid supplies, on-site receipt confirmation, and feedback to donors, making it difficult to manage efficiently. Furthermore, emotional feedback on aid activities is not fully utilized, making it difficult to motivate donors. Therefore, a comprehensive system is needed that can provide effective aid against hunger and improve donor satisfaction.

[0339] 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.

[0340] In this invention, the server includes: means for collecting hunger status, food inventory data, infrastructure status, and logistics data; means for analyzing the collected data using a generative AI model to generate a list of hunger status and needed supplies for each region; means for visualizing the generated analysis results on a visual dashboard and sending them to a user's device; means for users to input the supplies and funds they can provide and match the supplies with recipients based on that information; means for analyzing the delivery route and method for the recommended supplies and formulating an efficient logistics plan; means for obtaining local receipt confirmation data after the completion of the support and issuing credits to the user's account; and means for collecting and analyzing emotional data when the user provides feedback and providing customized feedback. This makes it possible to provide effective support for hunger issues and further increase the satisfaction of supporters by analyzing users' emotions and customizing the feedback.

[0341] "Hunger Situation" is information that indicates the state and severity of food shortages in a particular area.

[0342] "Food inventory data" is information that indicates the current food supply and stockpiles in a particular region or organization.

[0343] "Infrastructure status" refers to information that indicates the status of the infrastructure needed to carry out relief activities, such as transportation and storage facilities, in a particular area.

[0344] "Logistics data" refers to information related to logistics activities, such as delivery routes, transportation methods, and delivery schedules for goods.

[0345] A "generative AI model" is an artificial intelligence model that performs analysis and predictions based on accumulated data, and is used to analyze hunger situations and select the most appropriate recipients of aid.

[0346] A "visual dashboard" is an interface for visually displaying analysis results, using graphs and maps to enable users to easily understand the data.

[0347] "Support recipient" refers to the target region or organization that receives supplies and funds.

[0348] "Matching" is the process of comparing the supplies and financial information of the aid provider with the needs of the recipient to determine the optimal combination.

[0349] "Logistics planning" is the activity of formulating schedules and procedures for delivering goods via the optimal routes and means.

[0350] "Credits" are evaluation points or rewards given to a user after completing a support activity, and serve as an incentive for the next support activity.

[0351] "Emotion data" is information that quantifies or classifies the emotional state or tendency shown by the user when providing feedback.

[0352] "Customized feedback" refers to feedback messages and advice that are individually tailored based on the user's emotional data, in order to optimize the next support activity.

[0353] This invention combines an emotion engine with a platform system that aims to effectively solve the hunger problem using a generative AI model. Specific embodiments for implementing this system are described below.

[0354] System Configuration

[0355] This system is mainly composed of three entities: a server, a terminal, and a user. It also incorporates an emotion engine that recognizes the user's emotions.

[0356] Server: This is the central location for data collection, analysis, emotion recognition, and result management. This is where the generative AI model runs to generate regional hunger alerts and lists of supplies, and the emotion engine analyzes user feedback. Software used includes Python, TensorFlow, Node.js, and Express.

[0357] Terminal: This is the device where users access the system, input data, and view results. Here, analysis results are displayed through a visual dashboard, and user sentiment data is also entered. Visualization is done using D3.js and Tableau.

[0358] Users: These are primarily companies and individuals who use the platform to participate in relief efforts. Users provide supplies and funds, enter emotional feedback, and receive records of their support and credits.

[0359] Program processing

[0360] Data collection and analysis

[0361] The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public institutions and NGOs. This collection is done using access to APIs and data storage. For example, it retrieves the latest hunger status data from the API of an international organization.

[0362] The collected data is fed into a generative AI model, which analyzes the data and generates a regional hunger situation and a list of needed supplies. Specifically, the model is built using Python and TensorFlow.

[0363] Data Visualization

[0364] The analysis results are displayed in the form of a visual dashboard. The server creates visualization components such as graphs and maps using D3.js or Tableau based on the generated data and sends them to the device.

[0365] The dashboard displayed on the device allows users to check the hunger situation in each region, the types of supplies needed, and aid priorities.

[0366] Supply and matching

[0367] Users input details of the supplies and funds they can provide through their terminals and submit them. For example, a company representative might input "5,000 kg of rice" into the platform.

[0368] The server uses a generative AI model to calculate the optimal recipient of aid based on the supply information provided by the user, effectively matching local needs with the supplies provided by the user.

[0369] Logistics management

[0370] The server calculates the optimal support route and method, develops an efficient logistics plan, and evaluates air, sea, and land delivery options to select the most efficient delivery route. Logistics partners are notified via a RESTful API.

[0371] Credit issuance and confirmation of support completion

[0372] Once the relief effort is complete, the server receives local receipt confirmation data, such as a receipt confirmation report sent from the site via API.

[0373] The server uses this data to add credits to the user's account, and also provides feedback on the results of the support activity, providing reference information for the user when planning their next support.

[0374] Emotion Recognition and Customized Feedback

[0375] The server uses an emotion engine to collect and analyze the user's emotional data when the user provides feedback, and provides customized feedback including encouragement and suggestions for improvement according to the user's emotions.

[0376] Data obtained from the emotion engine is used to optimize the next outreach plan.

[0377] Specific examples

[0378] For example, consider a company that can donate 5,000 kg of rice. The company's representative logs into the platform using a terminal and enters the details of the donation (e.g., 5,000 kg of rice). The server then receives the data, and based on the collected hunger situation data, the generative AI model calculates the optimal recipient (e.g., a specific region) of the donation. The results are displayed on a dashboard, where the company's representative can check the progress of the donation and the logistics plan. The log data contains the following prompt:

[0379] Example prompt sentence:

[0380] "We can provide 5,000 kg of rice. Please calculate the optimal recipient and propose a delivery plan."

[0381] Once the donation is completed, a receipt confirmation is sent from the site to the server, and a credit is added to the company's account. At the same time, the server uses an emotion engine to analyze the emotions of the person in charge. For example, if there are many positive emotions about the donation activity, the server will provide feedback that highlights the success. Conversely, if there is a lot of feedback pointing out areas for improvement, the server will provide a report with suggestions to help optimize the next donation activity.

[0382] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0383] Step 1: Data collection

[0384] The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public organizations and NGOs. Specifically, the server accesses API endpoints to retrieve this data. This input data includes real-time hunger status data and logistics data from international organizations. The collected data is stored in a database on the server. To collect data, the server uses a Python script to access the API using the requests library. As a result, the retrieved data is stored on the server in JSON format.

[0385] Step 2: Data analysis

[0386] The server inputs the collected data into a generative AI model. Specifically, the generative AI model built with TensorFlow inputs hunger situation data and food inventory data for analysis. The input data includes the hunger situation and inventory situation for each region. The server uses the generative AI model to calculate the hunger situation and list of needed supplies for each region. The output data is saved on the server as the analyzed hunger situation and supply list. This analysis is performed by running the analyze_data_with_AI() function, which supplies the data to the generative AI model.

[0387] Step 3: Visualize the data

[0388] The server displays the generated analysis results in the form of a visual dashboard. Specifically, the server generates graphs and maps using D3.js or Tableau and sends them to the terminal. The input data includes the JSON data of the analysis results. The server visualizes the data and converts it into a format that is easy for users to understand. The output data is sent to the terminal as visualized graphs and maps. For this process, the create_visuals_from_data() function is used to generate visualization components using D3.js.

[0389] Step 4: Enter your supply

[0390] The user inputs detailed information about the supplies and funds that can be provided through the terminal. Specifically, the type and amount of supplies are entered into the input form on the terminal and sent to the server. The input data includes the supplies that the user will provide (e.g., 5,000 kg of rice). The terminal sends this data to the server via the send button. The server stores the received data in a database. The user enters detailed information using the input form and sends the information to the server by clicking the "Send" button.

[0391] Step 5: Matching supplies with recipients

[0392] The server inputs the supply information provided by the user into the generative AI model and calculates the optimal recipients of support. Specifically, the server matches the supply data provided by the user with the collected hunger situation data. The input data includes the supply data provided by the user and the hunger situation data. The server uses the generative AI model to calculate the optimal recipients of support and generates a list of optimal recipients as output data. For this, it uses the match_supply_to_demand() function.

[0393] Step 6: Logistics Management

[0394] The server calculates the optimal support route and method and creates an efficient logistics plan. Specifically, it evaluates air, sea, and land options and selects the most efficient delivery route. Input data includes a list of optimal support destinations and logistics options. The server creates a delivery plan using a logistics optimization algorithm and generates optimal route information as output data. This information is notified to logistics partners via a RESTful API. The server optimizes the logistics route using the optimize_logistics_route() function.

[0395] Step 7: Credit issuance and confirmation of support completion

[0396] Once the relief activity is completed, the server obtains the local receipt confirmation data. Specifically, the receipt confirmation data sent from the local site is obtained using an API and processed on the server. The input data includes the local receipt confirmation report. The server adds credits to the user's account based on the receipt confirmation data. The output data is the updated user credit information. This process uses the verify_delivery() function to obtain the receipt confirmation data and add credits.

[0397] Step 8: Emotion Recognition and Customized Feedback

[0398] The server uses an emotion engine to collect and analyze emotion data when a user provides feedback. Specifically, it analyzes the feedback submitted by the user and extracts emotion data. The input data includes the user's feedback. The server generates a customized feedback message based on the analysis results. The output data is the customized feedback provided to the user. This process uses the analyze_feedback_emotions() function to perform emotion analysis.

[0399] (Application example 2)

[0400] 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."

[0401] To effectively solve hunger problems and efficiently manage relief supplies, it is necessary to quickly analyze collected data and develop distribution plans that meet local needs. It is also important to monitor the progress of relief activities in real time and provide appropriate feedback to relief workers. However, these processes in current systems are partial and fragmented, posing challenges to improving overall efficiency and user satisfaction.

[0402] 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 collecting hunger status, food inventory data, infrastructure status, and logistics data; means for analyzing the collected data using a generative AI model to generate a list of hunger status and needed supplies for each region; means for visualizing the generated analysis results on a visual dashboard and sending them to the user's terminal; means for users to input the supplies and funds they can provide and match supplies with recipients based on that information; means for calculating and executing the optimal logistics route by autonomous vehicles; means for issuing credits for the relief activities and providing feedback to the user after the relief activities are completed; and means for using an emotion engine to collect and analyze emotion data of the user's feedback and provide customized feedback based on that data. This enables more efficient relief activities and more effective distribution of supplies.

[0403] "Hunger Situation" is data showing the state of food shortages in a given area and their causes and effects.

[0404] "Food inventory data" is information about the amount and type of food currently available.

[0405] "Infrastructure status" is information that indicates the state of infrastructure related to transportation, such as logistics networks, roads, and bridges.

[0406] "Logistics data" refers to information related to the transportation of goods, including transportation routes, transportation means, transportation times, and the like.

[0407] A "generative AI model" is an artificial intelligence model used to analyze collected data and generate regional hunger situations and lists of needed supplies.

[0408] A "visual dashboard" is an interface for visually displaying analysis results, providing information in the form of graphs, maps, etc.

[0409] "User terminal" means a device used by a user to access and operate the system, including a smartphone or computer.

[0410] An "autonomous vehicle" is a vehicle that uses AI technology to operate autonomously and transport goods.

[0411] A "credit" is a unit of evaluation or reward given to a user who participates in a support activity.

[0412] An "emotion engine" is a software component that analyzes a user's feedback and identifies their emotional state.

[0413] "Customized feedback" refers to personalized feedback provided based on the user's emotional data.

[0414] This invention is a system that combines an emotion engine with a platform system that aims to effectively solve the hunger problem. This system has a wide range of functions as shown below.

[0415] System Configuration

[0416] This system is mainly composed of three entities: a server, a terminal, and a user. It also incorporates an emotion engine that recognizes the user's emotions.

[0417] Server: This is the central location for data collection, analysis, emotion recognition, and result management. This is where the generative AI model runs, generating regional hunger alerts and lists of supplies, and the emotion engine analyzes user feedback.

[0418] Software used: Generative AI model, emotion engine

[0419] Hardware used: High-performance server

[0420] Terminal: A device through which users access the system, input data, and view results. Analysis results are displayed through a visual dashboard, and users' emotional data is also entered.

[0421] Hardware used: smartphones, computers, smart glasses, etc.

[0422] Software used: Visual Dashboard

[0423] Users: These are primarily companies and individuals who use the platform to participate in relief efforts. Users provide supplies and funds, enter emotional feedback, and receive records of their support and credits.

[0424] Program processing explanation

[0425] 1. The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public institutions and non-governmental organizations (NGOs). The collected data is input into a generative AI model to generate hunger status and a list of needed supplies for each region.

[0426] 2. The analysis results are displayed in the form of a visual dashboard. The server creates visualization components such as graphs and maps based on the generated data and sends them to the device. The dashboard displayed on the device allows users to see at a glance the hunger situation in each region, the types of supplies needed, and aid priorities.

[0427] 3. The user inputs and submits detailed information about the supplies and funds they can provide via their device. This information is stored on the server. Based on the supply information provided by the user, the server uses a generative AI model to calculate the optimal recipient of support. This allows the system to match the needs of each region with the supplies provided by the user.

[0428] 4. Calculate optimal support routes and methods to develop efficient logistics plans, including evaluating air, sea, and land delivery options and selecting the most efficient delivery route, including autonomous vehicle delivery plans.

[0429] 5. Once the donation is completed, the server receives local receipt confirmation data. Based on this data, the server confirms the donation's completion and credits the user's account. The server also provides feedback on the success of the donation, providing reference information for the user when planning their next donation.

[0430] 6. The emotion engine is used to analyze the user's feedback and identify how the user feels about the support activity. Based on the emotion data, the server provides the user with customized feedback, including encouragement and suggestions for improvement based on the user's emotions.

[0431] Examples of concrete examples and prompts

[0432] For example, if a company can provide 5,000 kg of rice, the company's representative would enter the following:

[0433] Example prompt sentence:

[0434] We will provide 5000 kg of rice.

[0435] The server then receives the data, and the generative AI model calculates the optimal recipient of aid based on the collected hunger situation data. The results are displayed on a dashboard, allowing company personnel to check the progress of aid and logistics plans. Once aid is completed, receipt confirmation data from the site is sent to the server, and credits are added to the company's account. An emotion engine also analyzes the emotions of personnel and provides appropriate feedback.

[0436] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0437] Specific processing steps of the program

[0438] Step 1:

[0439] The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public institutions and non-governmental organizations (NGOs) via APIs. The input data is often provided in JSON format. The server centralizes and stores this data. Specifically, it periodically sends HTTP requests to each data source to retrieve the latest data. The output is a centralized database of hunger-related data.

[0440] Step 2:

[0441] The server inputs the collected data into a generative AI model and analyzes the data. The generative AI model uses a machine learning algorithm to generate the hunger situation and list of needed supplies for each region. The input is the data collected in step 1, and the output is the analyzed hunger situation and list of needed supplies. Specifically, data preprocessing (filling in missing values, standardizing data, etc.) is performed, and the data is then input into the model.

[0442] Step 3:

[0443] The server converts the generated analysis results into a data format for the visual dashboard. The converted data is sent to the terminal in a format that is easy to understand visually, such as a graph or map. The input is the analysis results, and the output is data for displaying the visual dashboard. Specifically, the data is converted into HTML and JavaScript (registered trademark) format and sent to the terminal via a Web API.

[0444] Step 4:

[0445] The user enters detailed information about the supplies and funds they can provide into the terminal. The entered information is sent to the server and stored. The input is the information about the supplies and funds provided by the user, and the output is the resource information stored on the server. In concrete terms, the user enters data into a dedicated input form, and that data is sent to the server via HTTP POST.

[0446] Step 5:

[0447] The server uses a generative AI model to calculate the optimal recipient of aid based on the material information provided by the user. The input is the user's material information obtained in step 4 and the hunger status data obtained in step 2, and the output is information on the optimal recipient of aid. Specifically, the matching algorithm analyzes the information provided by the user and determines the recipient of aid as recommended by the generative AI model.

[0448] Step 6:

[0449] The server evaluates and selects the recommended delivery route and method for the goods, and formulates an efficient logistics plan, which includes the use of autonomous vehicles. The input is optimal support destination information and logistics data, and the output is an optimal delivery plan. Specific operations include calculating delivery routes and selecting transportation methods, and notifying the results to logistics partners and autonomous vehicles.

[0450] Step 7:

[0451] Once the relief activity is completed, the local receipt confirmation data is sent to the server. The server uses this data to add credits to the user's account. The input is the local receipt confirmation data, and the output is the updated user's account information. Specifically, the receipt confirmation data is sent and the server-side database is updated.

[0452] Step 8:

[0453] The server uses an emotion engine to analyze the user's feedback. Emotion data is collected along with the content of the feedback, and customized feedback is provided based on the analysis results. The input is the user's feedback, and the output is the emotion analysis results and customized feedback. Specifically, the emotion engine performs text analysis to determine the user's emotions and generate appropriate feedback.

[0454] Prompt Sentence Examples

[0455] "We will provide 5,000 kg of rice."

[0456] 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.

[0457] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0458] 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.

[0459] [Second embodiment]

[0460] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0461] 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.

[0462] 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).

[0463] 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.

[0464] 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.

[0465] 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).

[0466] 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. 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.

[0467] 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.

[0468] 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.

[0469] 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.

[0470] In the smart glasses 214, 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.

[0471] 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."

[0472] This invention relates to a platform system that aims to effectively solve the problem of hunger using generative AI. Specific embodiments for implementing this system will be described below.

[0473] System Configuration

[0474] This system mainly consists of three main components: a server, a terminal, and a user.

[0475] Server: The central location for data collection, analysis, and results management. This is where the generative AI model runs, generating hunger statistics and supply lists for each region.

[0476] Terminal: A device where users access the system, enter data, and view results. Here, analytical results are displayed through a visual dashboard.

[0477] Users: Primarily companies and individuals who use the platform to participate in relief activities. Users provide supplies and funds, enter data, and obtain records and credits for their donations.

[0478] Program processing

[0479] Data collection and analysis

[0480] The server will first collect hunger status, food inventory data, infrastructure status, and logistics data from multiple public agencies and non-governmental organizations (NGOs), including access to APIs and data storage.

[0481] The collected data is fed into a generative AI model, which analyzes the data and generates a regional hunger situation and a list of needed supplies.

[0482] Data Visualization

[0483] The analysis results are displayed in the form of a visual dashboard. The server creates visualization components such as graphs and maps based on the generated data and sends them to the device.

[0484] The dashboard displayed on the device allows users to see at a glance the hunger situation in each region, the types of supplies needed, and aid priorities.

[0485] Supply and matching

[0486] Users input details of the supplies and funds they can provide through their terminals and submit the information, which is then stored on the server.

[0487] The server uses a generative AI model to calculate the optimal recipient of aid based on the supply information provided by users, thereby matching the needs of each region with the supplies provided by users.

[0488] Logistics management

[0489] The server calculates the optimal support route and method, and develops an efficient logistics plan. Specifically, it evaluates delivery options by air, sea, and land, and selects the most efficient delivery route.

[0490] Details of the logistics plan will be communicated to the relevant logistics partners.

[0491] Crediting and Feedback

[0492] Once the assistance activity is completed, the server receives a local acknowledgement of receipt and adds a "credit" to the user's account.

[0493] The server also provides feedback on the results of the support activities, providing reference information for the user when planning their next support.

[0494] Specific examples

[0495] For example, consider a company that can donate 5,000 kg of rice. A company representative logs into the platform using a device and enters the details of the donation (e.g., 5,000 kg of rice). The server then receives the data, and based on the collected hunger situation data, the generative AI model calculates the optimal recipient (e.g., a specific region in Africa). The results are displayed on a dashboard, where the company representative can check the progress of the donation and logistics plans.

[0496] Once the donation is complete, receipt confirmation data from the local area is sent to the server and credits are added to the company's account. At the same time, a feedback report is provided to help the company decide whether to donate next time. In this way, the entire system operates efficiently and aims to contribute to solving hunger.

[0497] The processing flow will be explained below.

[0498] Step 1:

[0499] The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public institutions and non-governmental organizations (NGOs) by sending requests to the United Nations Hunger Database API and the World Bank's data storage.

[0500] Step 2:

[0501] The server stores the collected data in an internal database, and when storing it, it formats and converts the data to ensure consistency.

[0502] Step 3:

[0503] The server inputs the data retrieved from the database into the generative AI model, which then begins analysis. The generative AI model identifies the hunger situation in each region, a list of necessary supplies, infrastructure shortages, and other information, and generates a report.

[0504] Step 4:

[0505] The server converts the analysis results into a visual dashboard, specifically by creating visualization components such as graphs and maps and designing a user-friendly interface.

[0506] Step 5:

[0507] The server then sends the generated visual dashboard to the device, where users can access the dashboard and check the hunger situation in each region, the types of supplies needed, and the priority of aid.

[0508] Step 6:

[0509] The user uses the terminal to input and submit details of the goods and funds available for donation, including the quantity, quality, and period of time available.

[0510] Step 7:

[0511] The server receives the material data obtained from the user, stores it in a database, and converts the stored data into an appropriate format for analysis.

[0512] Step 8:

[0513] The server uses a generative AI model to match the items provided by users with local needs, specifically by comparing the provided items with local hunger data and identifying the best recipients.

[0514] Step 9:

[0515] Based on the matching results, the server calculates the appropriate delivery route and method for the goods, analyzes multiple logistics options (air transport, sea transport, land transport) and formulates an efficient transportation plan.

[0516] Step 10:

[0517] The server notifies the relevant logistics partners of the details of the logistics plan and begins preparations for delivery, monitoring the delivery status in real time and making adjustments as necessary.

[0518] Step 11:

[0519] Once the relief activities are completed, the server receives receipt confirmation data from the site, and uses this data to confirm the completion of the relief activities.

[0520] Step 12:

[0521] The server will add "credits" to the user's account for the support, which will then be reflected in the user's profile.

[0522] Step 13:

[0523] The server provides the user with feedback on the results of the support activities, along with analytical data to help them improve their next support efforts. The feedback report is displayed on the user's dashboard.

[0524] The above are the specific program processing steps of the system for implementing the invention.

[0525] Example 1

[0526] 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."

[0527] This invention relates to a platform system for effectively solving the problem of hunger, which occurs frequently around the world. Currently, it is difficult to grasp the hunger situation, procure and supply necessary supplies, and efficiently manage the delivery of supplies and relief activities, which hinders the speed and effectiveness of relief activities. Other issues include low transparency and reliability of relief activities, and a lack of appropriate feedback to donors.

[0528] 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.

[0529] In this invention, the server includes: means for collecting hunger status, food inventory data, infrastructure status, and logistics data; means for analyzing the collected data using a generative AI model to generate a list of hunger status and needed supplies for each region; means for visualizing the generated analysis results on a visual dashboard and sending them to the user's device; means for users to input the supplies and funds they can provide and match supplies with recipients based on that information; means for analyzing the recommended delivery routes and methods for supplies using an advanced algorithm, formulating an efficient logistics plan, and notifying appropriate logistics partners; and means for issuing credits for relief activities using blockchain technology and providing feedback to users after the relief activities are completed. This enables effective and prompt resolution of hunger issues, improved transparency and reliability of relief activities, and appropriate feedback to donors.

[0530] "Hunger Situation" is data showing the degree of food shortages and malnutrition in each region.

[0531] "Food inventory data" refers to data that indicates information regarding the current amount and type of food in stock in a particular area or facility.

[0532] "Infrastructure status" refers to data that indicates the status of basic facilities and services such as roads, communications, power supply, and water supply.

[0533] "Logistics data" refers to data that indicates information related to the transportation and delivery of goods, including routes, means of transportation, and delivery schedules.

[0534] "Generative AI models" refer to artificial intelligence algorithms or programs used to analyze collected data and make predictions or optimizations.

[0535] A "visual dashboard" is an interface for visually displaying analysis results, and includes visual components such as graphs and maps.

[0536] "User terminal" refers to a device used by a user to access and operate the system, including a personal computer or smartphone.

[0537] "Resource matching" refers to the process by which aid providers optimally allocate available resources and funds to areas and facilities in need.

[0538] "Logistics planning" is a plan for the efficient transportation and delivery of goods, and refers to the process of determining the optimal routes and means.

[0539] "Logistics Partner" refers to a company or organization that partners with us to carry out the transportation or delivery of goods.

[0540] "Blockchain technology" is a distributed database technology used to ensure data transparency and prevention of tampering.

[0541] "Credits" refer to digital points or certificates that indicate recognition and reward for support activities.

[0542] "Feedback" refers to the process of providing evaluation information about the effectiveness and results of support activities.

[0543] This invention relates to a platform system that aims to effectively solve the problem of hunger using a generative AI model. This system consists of three entities: a server, a terminal, and a user. Specific embodiments for implementing this system are described below.

[0544] System Configuration

[0545] Server: The central location for data collection, analysis, and results management. This is where the generative AI model runs, generating hunger statistics and supply lists for each region.

[0546] Terminal: A device where users access the system, enter data, and view results. Here, analytical results are displayed through a visual dashboard.

[0547] Users: Primarily companies and individuals who use the platform to participate in relief activities. Users provide supplies and funds, enter data, and obtain records and credits for their donations.

[0548] Data collection and analysis

[0549] The server will collect hunger, food inventory, infrastructure, and logistics data from multiple public and non-governmental organizations, utilizing APIs and cloud storage.

[0550] For example, the server accesses a public institution's database via an API to obtain the latest hunger situation data, which is then stored in cloud storage such as AWS S3.

[0551] The collected data is fed into a generative AI model (specifically, using TensorFlow), which analyzes the data and generates a regional hunger alert and a list of supplies needed, using statistical models and machine learning algorithms.

[0552] Data Visualization

[0553] The server uses the D3.js library to convert the generated analysis results into visual components such as graphs and maps, and the generated visual data is sent to the device in JSON format.

[0554] The device displays a visual dashboard that allows users to interactively check the hunger situation map and supply status in real time on their browser.

[0555] Supply and matching

[0556] Users input details of the goods and funds they can provide through their devices, such as "donating 5,000 kg of rice." This data is sent to the server via API and stored in a database (e.g., MySQL).

[0557] The server uses a generative AI model to match the material information provided by users with the most appropriate recipients. This matching process compares the needs of each region with the materials provided to make the best match.

[0558] Logistics management

[0559] The server uses Dijkstra's algorithm to calculate the optimal relief route and delivery method, which determines the most efficient delivery route and ensures that relief supplies reach their destination as quickly as possible.

[0560] The results of the optimal delivery route calculation are sent to logistics partners via API, allowing them to carry out efficient logistics planning.

[0561] Crediting and Feedback

[0562] Once the donation is completed, the server receives local confirmation data and adds "credits" to the user's account, a process that utilizes blockchain technology to ensure transparency and reliability.

[0563] The server also provides the user with feedback on the results of the support activities and information that can be used as reference for planning the next support. The feedback report is sent from the server to the terminal, and the user can refer to it when planning the next support.

[0564] Examples of prompt statements

[0565] "Generate the best recipients and necessary supplies list based on the following data: Hunger situation data (areas A, B, C), Food inventory data (areas A, B, C), Infrastructure situation (areas A, B, C), Logistics data (areas A, B, C)"

[0566] This will ensure that the entire system is run efficiently, and is expected to contribute to solving the problem of hunger.

[0567] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0568] Step 1:

[0569] Data collection

[0570] The server collects hunger, food inventory, infrastructure, and logistics data from multiple public and non-governmental organizations, using API endpoints to access each organization's database and retrieve the latest data.

[0571] Input: Data collected via API (hunger status, food stocks, infrastructure, logistics)

[0572] Output: Raw data stored in cloud storage (e.g. AWS S3)

[0573] Specific operation: The server periodically executes an API call and saves the acquired data to the specified cloud storage.

[0574] Step 2:

[0575] Data analysis

[0576] The server inputs the collected data into a generative AI model, specifically using TensorFlow to analyze it and generate a hunger situation and a list of supplies needed.

[0577] Input: Datasets of hunger, food inventory, infrastructure, and logistics retrieved from cloud storage.

[0578] Output: Hunger report and list of supplies needed for each analyzed region

[0579] Specific operation: The server feeds the collected data into the TensorFlow model, calculates the analysis results, and stores the generated report and list of required supplies in a database.

[0580] Step 3:

[0581] Data visualization

[0582] The server converts the generated analysis results into a visual dashboard, generating graphs, maps, and other data using the D3.js library, and sends them to the device in JSON format.

[0583] Input: Analysis results from the generative AI model (hunger situation report, list of needed supplies)

[0584] Output: Visual data in JSON format

[0585] Specific operation: The server uses the analysis results to generate heat maps and bar charts using D3.js, converts them to JSON format, saves them, and sends them to the terminal as appropriate.

[0586] Step 4:

[0587] Viewing the Dashboard

[0588] The terminal receives the JSON data sent from the server and displays it as a visual dashboard.

[0589] Input: Visual data in JSON format from the server

[0590] Output: A visual dashboard displayed in the user's browser

[0591] Specific operation: The terminal parses the received JSON and displays it as an interactive dashboard using the D3.js library.

[0592] Step 5:

[0593] Enter and submit supply information

[0594] The user uses a terminal to input detailed information about the supplies and funds that can be provided and sends this information to the server.

[0595] Input: Information about supplies and funds entered by the user (e.g., 5,000 kg of rice)

[0596] Output: Material information sent to the server

[0597] Specific operation: The user enters the necessary information into a form on the device, which is then sent to the server via the API and stored in a database.

[0598] Step 6:

[0599] Executing the matching algorithm

[0600] The server uses a generative AI model to calculate the optimal recipient of support based on the material information provided by the user.

[0601] Input: Provided supplies information, hunger situation data, list of required supplies

[0602] Output: List of optimal support recipients

[0603] Specific operation: The server inputs the supply information into the TensorFlow model, and calculates the optimal support destination as the analysis result. This information is stored in a database.

[0604] Step 7:

[0605] Delivery route calculation and notification

[0606] The server uses advanced algorithms to calculate efficient delivery routes and methods for supplies and notifies logistics partners.

[0607] Input: List of optimal support recipients and logistics data

[0608] Output: Delivery plan notification to logistics partners

[0609] Specific operation: The server calculates the optimal delivery route using Dijkstra's algorithm and notifies the logistics partner of this information via API.

[0610] Step 8:

[0611] Confirmation of support activities and issuance of credits

[0612] The user receives confirmation data from the site to confirm the completion of the relief activity and sends it to the server, which issues credits to the user's account based on the confirmation data and provides feedback.

[0613] Input: Receipt confirmation data from the site

[0614] Output: Credits to user accounts and feedback reports

[0615] Specific operation: The server records the receipt confirmation data using blockchain technology, adds credits to the user, and generates and sends a feedback report.

[0616] (Application example 1)

[0617] 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."

[0618] Hunger is a global issue, threatening the very foundations of life in many regions. To combat this, adequate supplies and efficient logistics planning are essential. However, managing aid activities and calculating optimal supply delivery routes is complex and consumes significant human resources. Furthermore, the lack of real-time inventory management and visibility into delivery routes increases the risk of aid delays. This makes it difficult to provide fast and effective aid to famine-stricken areas.

[0619] 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.

[0620] In this invention, the server includes a means for collecting data on the famine situation, food inventory data, infrastructure status, and logistics data, a means for analyzing the collected data with a generative AI model to generate a list of the famine situation and supplies needed by region, and a means for visualizing the generated analysis results on a visual dashboard and sending them to the user's device, thereby enabling more efficient and rapid response in relief activities.

[0621] The invention further includes a means for users to input the supplies and funds they can provide and match supplies with recipients based on that information, a means for analyzing the recommended delivery route and method for the supplies and formulating an efficient logistics plan, a means for issuing credits for the relief activities and providing feedback to the user after the relief is completed, a means using a smart device for displaying inventory status and delivery routes in real time, and a means for supporting the picking and delivery of relief supplies at the logistics center. This improves work efficiency within the logistics center and enables fast and effective relief to famine-stricken areas.

[0622] "Hunger situation" refers to the level of food shortages in a particular area and the situation of people suffering from malnutrition.

[0623] "Food inventory data" refers to data that includes inventory information for food, beverages, and other items provided as relief supplies.

[0624] "Infrastructure status" refers to the current condition and performance of infrastructure such as roads, transportation, and communication networks related to relief activities.

[0625] "Logistics data" refers to information relating to the transportation of goods, including information such as the point of departure, destination, transportation method, route, and time.

[0626] A "generative AI model" is an artificial intelligence model that analyzes collected data and generates specific outputs (for example, the hunger situation in each region and a list of needed supplies).

[0627] A "visual dashboard" refers to a visual user interface for displaying analyzed data in an easy-to-read format.

[0628] "Terminal" means a device (such as a smartphone, tablet, or computer) through which a user accesses the system, enters data, and views results.

[0629] "Matching" is the process of matching available supplies and funds with the needs of the recipient and finding the optimal combination.

[0630] A "logistics plan" is a plan to determine efficient routes and methods for delivering supplies and to ensure optimal relief activities.

[0631] "Credits" are evaluation points or rewards given to users who perform support activities.

[0632] "Feedback" is information provided to users reporting on the results of support activities and areas for improvement.

[0633] "Smart devices" are wearable electronic devices such as glasses and headsets that have internet connectivity and high-performance sensors.

[0634] "Picking" refers to the task of selecting specific items from inventory at a logistics center.

[0635] This invention relates to a platform system that aims to effectively solve the problem of hunger using a generative AI model. The system of the present invention is mainly composed of three entities: a server, a terminal, and a user.

[0636] System Configuration

[0637] Server: Collects data, analyzes, and manages the results. This server runs a generative AI model that generates hunger situations and lists of supplies for each region.

[0638] Terminal: A device where users access the system, enter data, and view results. Here, analytical results are displayed through a visual dashboard.

[0639] Users: Primarily companies and individuals who use the system to participate in relief activities. Users provide and input supplies and funds, and obtain records and credits for their support.

[0640] Program Overview

[0641] 1. Data Collection and Analysis

[0642] The server first collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public institutions and non-governmental organizations (NGOs). This data collection includes access to APIs and data storage. The collected data is then fed into a generative AI model, which analyzes the data and generates regional hunger status and a list of needed supplies.

[0643] 2. Data visualization

[0644] The analysis results are displayed in the form of a visual dashboard. The server creates visualization components such as graphs and maps based on the generated data and sends them to the device. The dashboard displayed on the device allows users to see at a glance the hunger situation in each region, the types of supplies needed, and aid priorities.

[0645] 3. Supply and matching

[0646] Users input detailed information about the supplies and funds they can provide through their devices and submit it. This information is stored on the server. The server then uses a generative AI model based on the supply information provided by the user to calculate the optimal recipient of support. This allows the system to match the needs of each region with the supplies provided by the user.

[0647] 4. Logistics management

[0648] The server calculates the optimal support route and method, and develops an efficient logistics plan. Specifically, it evaluates air, sea, and land delivery options and selects the most efficient delivery route. The details of the logistics plan are then communicated to the relevant logistics partners.

[0649] 5. Crediting and Feedback

[0650] Once the relief effort is completed, the server receives a local confirmation of receipt, credits the user's account, and provides feedback on the success of the relief effort, providing reference information for the user when planning their next relief effort.

[0651] Specific examples

[0652] For example, let's say a company can donate 5,000 kg of rice. The company's representative logs into the platform using a terminal and enters the details of the goods to be donated (e.g., 5,000 kg of rice). The server then receives this data, and the generative AI model calculates the optimal recipient of the donation based on the collected hunger situation data. The results are displayed on a dashboard, where company representatives can check the progress of the donation and logistics plans. Once the donation is completed, confirmation of receipt from the site is sent to the server, and credits are added to the company's account. At the same time, a feedback report is provided to help with the next donation. In this way, the entire system operates efficiently, aiming to contribute to resolving hunger.

[0653] Prompt Sentence Examples

[0654] "Please describe the overview and functionality of the hunger relief logistics management app. Include a specific example of a program that retrieves data from Firebase, analyzes it using a TensorFlow model, calculates optimal delivery routes using the Google Maps API, and displays the data on smart glasses using OpenCV."

[0655] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0656] Step 1:

[0657] Data collection

[0658] Subject: Server

[0659] The server collects hunger status, food inventory data, infrastructure status, and logistics data from public institutions and non-governmental organizations (NGOs) through APIs and data storage. The collected data is stored as raw data. Specifically, the server sends requests to the APIs of each data provider and imports the returned data.

[0660] Input: Send API request

[0661] Output: Save various data

[0662] Step 2:

[0663] Data analysis

[0664] Subject: Server

[0665] The server inputs the collected data into a generative AI model, which analyzes the data and generates a regional hunger situation and a list of needed supplies. Specifically, the server runs the model using TensorFlow to obtain predictions.

[0666] Input: Collected data

[0667] Output: Analysis results (hungry situation by region and list of necessary supplies)

[0668] Step 3:

[0669] Data Visualization

[0670] Subject: Server

[0671] The server uses the generated analysis results to create a visual dashboard and sends it to the terminal. The data is visualized in the form of graphs, maps, etc. Specifically, the server generates the dashboard using libraries such as OpenCV and D3.js and sends it to the terminal via WebSocket.

[0672] Input: Analysis results

[0673] Output: Visual dashboard

[0674] Step 4:

[0675] Supply and matching

[0676] Subject: User and Server

[0677] Users enter information about the supplies and funds they can provide through their devices and send it to the server. The server receives this information and uses a generative AI model to calculate the optimal recipient of aid. Specifically, users enter information into a web form, and the server then analyzes it again using the AI ​​model.

[0678] Input: Material and financial information

[0679] Output: Best Support

[0680] Step 5:

[0681] Logistics planning

[0682] Subject: Server

[0683] The server calculates the optimal support route and method, and develops an efficient logistics plan. It evaluates delivery options by air, sea, and land, and selects the most efficient delivery route. Specifically, the server calculates the delivery route using the Google Maps API and notifies the logistics partner of the results.

[0684] Input: Information on the provided supplies and recipients

[0685] Output: Efficient logistics planning

[0686] Step 6:

[0687] Crediting and Feedback

[0688] Subject: Server

[0689] Once a relief effort is completed, local receipt confirmation data is sent to the server. The server uses this information to add credits to the user's account. It also provides feedback on the success of the relief effort, providing reference information for the user when planning their next relief effort. Specifically, the server analyzes the receipt confirmation data, updates the user's credits, and generates a report.

[0690] Input: Receipt confirmation data

[0691] Output: Credits added, feedback report

[0692] Step 7:

[0693] Real-time display on smart devices

[0694] Subject: Smart device (terminal)

[0695] The smart device displays real-time inventory status and delivery routes. To assist with the picking and delivery of relief supplies at the logistics center, the device incorporates OpenCV and Google Maps API. Specifically, the smart glasses overlay information on the user's field of vision based on data sent from the server.

[0696] Input: Shipping and inventory data from the server

[0697] Output: Real-time display on smart devices

[0698] 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.

[0699] This invention combines an emotion engine with a platform system that aims to effectively solve the problem of hunger using generative AI. Specific embodiments for implementing this system are described below.

[0700] System Configuration

[0701] This system is mainly composed of three entities: a server, a terminal, and a user. It also incorporates an emotion engine that recognizes the user's emotions.

[0702] Server: This is the central location for data collection, analysis, emotion recognition, and result management. This is where the generative AI model runs, generating regional hunger alerts and lists of supplies, and the emotion engine analyzes user feedback.

[0703] Terminal: A device where users access the system, input data, and view results. Here, analysis results are displayed through a visual dashboard, and users' emotional data is also entered.

[0704] Users: These are primarily companies and individuals who use the platform to participate in relief efforts. Users provide supplies and funds, enter emotional feedback, and receive records of their support and credits.

[0705] Program processing

[0706] Data collection and analysis

[0707] The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public agencies and non-governmental organizations (NGOs), including access to APIs and data storage.

[0708] The collected data is fed into a generative AI model, which analyzes the data and generates a regional hunger situation and a list of needed supplies.

[0709] Data Visualization

[0710] The analysis results are displayed in the form of a visual dashboard. The server creates visualization components such as graphs and maps based on the generated data and sends them to the device.

[0711] The dashboard displayed on the device allows users to see at a glance the hunger situation in each region, the types of supplies needed, and aid priorities.

[0712] Supply and matching

[0713] Users input details of the supplies and funds they can provide through their terminals and submit the information, which is then stored on the server.

[0714] The server uses a generative AI model to calculate the optimal recipient of aid based on the supply information provided by users, thereby matching the needs of each region with the supplies provided by users.

[0715] Logistics management

[0716] The server calculates the optimal support route and method, and develops an efficient logistics plan. Specifically, it evaluates delivery options by air, sea, and land, and selects the most efficient delivery route.

[0717] Details of the logistics plan will be communicated to the relevant logistics partners.

[0718] Crediting and Feedback

[0719] Once the relief effort is completed, the server receives local receipt confirmation data, which is used to confirm the relief effort has been completed and add a "credit" to the user's account.

[0720] The server also provides feedback on the results of the support activities, providing reference information for the user when planning their next support.

[0721] Emotion Recognition and Customized Feedback

[0722] The server uses an emotion engine to collect and analyze the user's emotional data when the user provides feedback, thereby identifying how the user feels about the support activity.

[0723] Based on the emotion data, the server provides customized feedback to the user, including encouragement and suggestions for improvement based on the user's emotions.

[0724] The analysis results of the emotion engine are used to optimize the next relief operation plan.

[0725] Specific examples

[0726] For example, consider a company that can donate 5,000 kg of rice. A company representative logs into the platform using a device and enters the details of the donation (e.g., 5,000 kg of rice). The server then receives the data, and based on the collected hunger situation data, the generative AI model calculates the optimal recipient (e.g., a specific region in Africa). The results are displayed on a dashboard, where the company representative can check the progress of the donation and logistics plans.

[0727] Once the donation is completed, receipt confirmation data from the site is sent to the server, and credits are added to the company's account. At the same time, the server uses an emotion engine to analyze the emotions of the person in charge. For example, if there are many positive emotions about the donation activity, the server will provide feedback emphasizing its success. Conversely, if there is a lot of feedback pointing out areas for improvement, the server will provide a report containing suggestions to help optimize the next donation activity. In this way, the entire system operates efficiently, aiming to increase user satisfaction while contributing to solving hunger.

[0728] The processing flow will be explained below.

[0729] Step 1:

[0730] The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public institutions and non-governmental organizations (NGOs) by sending requests to the United Nations Hunger Database API and the World Bank's data storage.

[0731] Step 2:

[0732] The server stores the collected data in an internal database. When storing the data, it formats and converts the data to maintain consistency. For example, it unifies data in different formats and extracts necessary indicators.

[0733] Step 3:

[0734] The server inputs the data retrieved from the database into the generative AI model, which then begins analysis. The generative AI model identifies the hunger situation in each region, a list of necessary supplies, infrastructure shortages, and other information, and generates a report.

[0735] Step 4:

[0736] The server converts the analysis results into a visual dashboard, specifically by creating visualization components such as graphs and maps and designing a user-friendly interface.

[0737] Step 5:

[0738] The server then sends the generated visual dashboard to the device, where users can access the dashboard and check the hunger situation in each region, the types of supplies needed, and the priority of aid.

[0739] Step 6:

[0740] The user uses the terminal to input and submit details of the goods and funds available for donation, including the quantity, quality, and period of time available.

[0741] Step 7:

[0742] The server receives the material data obtained from the user, stores it in a database, and converts the stored data into an appropriate format for analysis.

[0743] Step 8:

[0744] The server uses a generative AI model to match the items provided by users with local needs, specifically by comparing the provided items with local hunger data and identifying the best recipients.

[0745] Step 9:

[0746] Based on the matching results, the server calculates the appropriate delivery route and method for the goods, analyzes multiple logistics options (air transport, sea transport, land transport) and formulates an efficient transportation plan.

[0747] Step 10:

[0748] The server notifies the relevant logistics partners of the details of the logistics plan and begins preparations for delivery, monitoring the delivery status in real time and making adjustments as necessary.

[0749] Step 11:

[0750] Once the relief activities are completed, the server receives receipt confirmation data from the site, and uses this data to confirm the completion of the relief activities.

[0751] Step 12:

[0752] The server will add "credits" to the user's account for the support, which will then be reflected in the user's profile.

[0753] Step 13:

[0754] The server provides the user with feedback on the results of the support activities, along with analytical data to help them improve their next support efforts. The feedback report is displayed on the user's dashboard.

[0755] Step 14:

[0756] When a user inputs feedback, the server uses an emotion engine to collect the user's emotion data, for example, by analyzing the text of the feedback or voice input and classifying the emotion as positive, negative, etc.

[0757] Step 15:

[0758] The server analyzes the user's feedback in detail based on the emotion data analyzed by the emotion engine, thereby identifying how the user feels about the support activities.

[0759] Step 16:

[0760] The server then provides customized feedback to the user based on the emotional data, such as highlighting achievements when emotions are predominantly positive, or providing specific areas for improvement when emotions are predominantly negative.

[0761] Step 17:

[0762] The server uses the analysis results of the emotion engine to reflect user feedback in the next support activity plan, specifically identifying support methods to increase user motivation and issues that need improvement.

[0763] The above are the specific program processing steps of the system for implementing the invention.

[0764] Example 2

[0765] 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."

[0766] Hunger is becoming a serious problem around the world, and appropriate aid is urgently needed, especially in resource-limited areas. The current system involves a complex and cumbersome process, including the provision and delivery of aid supplies, on-site receipt confirmation, and feedback to donors, making it difficult to manage efficiently. Furthermore, emotional feedback on aid activities is not fully utilized, making it difficult to motivate donors. Therefore, a comprehensive system is needed that can provide effective aid against hunger and improve donor satisfaction.

[0767] 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.

[0768] In this invention, the server includes: means for collecting hunger status, food inventory data, infrastructure status, and logistics data; means for analyzing the collected data using a generative AI model to generate a list of hunger status and needed supplies for each region; means for visualizing the generated analysis results on a visual dashboard and sending them to a user's device; means for users to input the supplies and funds they can provide and match the supplies with recipients based on that information; means for analyzing the delivery route and method for the recommended supplies and formulating an efficient logistics plan; means for obtaining local receipt confirmation data after the completion of the support and issuing credits to the user's account; and means for collecting and analyzing emotional data when the user provides feedback and providing customized feedback. This makes it possible to provide effective support for hunger issues and further increase the satisfaction of supporters by analyzing users' emotions and customizing the feedback.

[0769] "Hunger Situation" is information that indicates the state and severity of food shortages in a particular area.

[0770] "Food inventory data" is information that indicates the current food supply and stockpiles in a particular region or organization.

[0771] "Infrastructure status" refers to information that indicates the status of the infrastructure needed to carry out relief activities, such as transportation and storage facilities, in a particular area.

[0772] "Logistics data" refers to information related to logistics activities, such as delivery routes, transportation methods, and delivery schedules for goods.

[0773] A "generative AI model" is an artificial intelligence model that performs analysis and predictions based on accumulated data, and is used to analyze hunger situations and select the most appropriate recipients of aid.

[0774] A "visual dashboard" is an interface for visually displaying analysis results, using graphs and maps to enable users to easily understand the data.

[0775] "Support recipient" refers to the target region or organization that receives supplies and funds.

[0776] "Matching" is the process of comparing the supplies and financial information of the aid provider with the needs of the recipient to determine the optimal combination.

[0777] "Logistics planning" is the activity of formulating schedules and procedures for delivering goods via the optimal routes and means.

[0778] "Credits" are evaluation points or rewards given to a user after completing a support activity, and serve as an incentive for the next support activity.

[0779] "Emotion data" is information that quantifies or classifies the emotional state or tendency shown by the user when providing feedback.

[0780] "Customized feedback" refers to feedback messages and advice that are individually tailored based on the user's emotional data, in order to optimize the next support activity.

[0781] This invention combines an emotion engine with a platform system that aims to effectively solve the hunger problem using a generative AI model. Specific embodiments for implementing this system are described below.

[0782] System Configuration

[0783] This system is mainly composed of three entities: a server, a terminal, and a user. It also incorporates an emotion engine that recognizes the user's emotions.

[0784] Server: This is the central location for data collection, analysis, emotion recognition, and result management. This is where the generative AI model runs to generate regional hunger alerts and lists of supplies, and the emotion engine analyzes user feedback. Software used includes Python, TensorFlow, Node.js, and Express.

[0785] Terminal: This is the device where users access the system, input data, and view results. Here, analysis results are displayed through a visual dashboard, and user sentiment data is also entered. Visualization is done using D3.js and Tableau.

[0786] Users: These are primarily companies and individuals who use the platform to participate in relief efforts. Users provide supplies and funds, enter emotional feedback, and receive records of their support and credits.

[0787] Program processing

[0788] Data collection and analysis

[0789] The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public institutions and NGOs. This collection is done using access to APIs and data storage. For example, it retrieves the latest hunger status data from the API of an international organization.

[0790] The collected data is fed into a generative AI model, which analyzes the data and generates a regional hunger situation and a list of needed supplies. Specifically, the model is built using Python and TensorFlow.

[0791] Data Visualization

[0792] The analysis results are displayed in the form of a visual dashboard. The server creates visualization components such as graphs and maps using D3.js or Tableau based on the generated data and sends them to the device.

[0793] The dashboard displayed on the device allows users to check the hunger situation in each region, the types of supplies needed, and aid priorities.

[0794] Supply and matching

[0795] Users input details of the supplies and funds they can provide through their terminals and submit them. For example, a company representative might input "5,000 kg of rice" into the platform.

[0796] The server uses a generative AI model to calculate the optimal recipient of aid based on the supply information provided by the user, effectively matching local needs with the supplies provided by the user.

[0797] Logistics management

[0798] The server calculates the optimal support route and method, develops an efficient logistics plan, and evaluates air, sea, and land delivery options to select the most efficient delivery route. Logistics partners are notified via a RESTful API.

[0799] Credit issuance and confirmation of support completion

[0800] Once the relief effort is complete, the server receives local receipt confirmation data, such as a receipt confirmation report sent from the site via API.

[0801] The server uses this data to add credits to the user's account, and also provides feedback on the results of the support activity, providing reference information for the user when planning their next support.

[0802] Emotion Recognition and Customized Feedback

[0803] The server uses an emotion engine to collect and analyze the user's emotional data when the user provides feedback, and provides customized feedback including encouragement and suggestions for improvement according to the user's emotions.

[0804] Data obtained from the emotion engine is used to optimize the next outreach plan.

[0805] Specific examples

[0806] For example, consider a company that can donate 5,000 kg of rice. The company's representative logs into the platform using a terminal and enters the details of the donation (e.g., 5,000 kg of rice). The server then receives the data, and based on the collected hunger situation data, the generative AI model calculates the optimal recipient (e.g., a specific region) of the donation. The results are displayed on a dashboard, where the company's representative can check the progress of the donation and the logistics plan. The log data contains the following prompt:

[0807] Example prompt sentence:

[0808] "We can provide 5,000 kg of rice. Please calculate the optimal recipient and propose a delivery plan."

[0809] Once the donation is completed, a receipt confirmation is sent from the site to the server, and a credit is added to the company's account. At the same time, the server uses an emotion engine to analyze the emotions of the person in charge. For example, if there are many positive emotions about the donation activity, the server will provide feedback that highlights the success. Conversely, if there is a lot of feedback pointing out areas for improvement, the server will provide a report with suggestions to help optimize the next donation activity.

[0810] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0811] Step 1: Data collection

[0812] The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public organizations and NGOs. Specifically, the server accesses API endpoints to retrieve this data. This input data includes real-time hunger status data and logistics data from international organizations. The collected data is stored in a database on the server. To collect data, the server uses a Python script to access the API using the requests library. As a result, the retrieved data is stored on the server in JSON format.

[0813] Step 2: Data analysis

[0814] The server inputs the collected data into a generative AI model. Specifically, the generative AI model built with TensorFlow inputs hunger situation data and food inventory data for analysis. The input data includes the hunger situation and inventory situation for each region. The server uses the generative AI model to calculate the hunger situation and list of needed supplies for each region. The output data is saved on the server as the analyzed hunger situation and supply list. This analysis is performed by running the analyze_data_with_AI() function, which supplies the data to the generative AI model.

[0815] Step 3: Visualize the data

[0816] The server displays the generated analysis results in the form of a visual dashboard. Specifically, the server generates graphs and maps using D3.js or Tableau and sends them to the terminal. The input data includes the JSON data of the analysis results. The server visualizes the data and converts it into a format that is easy for users to understand. The output data is sent to the terminal as visualized graphs and maps. For this process, the create_visuals_from_data() function is used to generate visualization components using D3.js.

[0817] Step 4: Enter your supply

[0818] The user inputs detailed information about the supplies and funds that can be provided through the terminal. Specifically, the type and amount of supplies are entered into the input form on the terminal and sent to the server. The input data includes the supplies that the user will provide (e.g., 5,000 kg of rice). The terminal sends this data to the server via the send button. The server stores the received data in a database. The user enters detailed information using the input form and sends the information to the server by clicking the "Send" button.

[0819] Step 5: Matching supplies with recipients

[0820] The server inputs the supply information provided by the user into the generative AI model and calculates the optimal recipients of support. Specifically, the server matches the supply data provided by the user with the collected hunger situation data. The input data includes the supply data provided by the user and the hunger situation data. The server uses the generative AI model to calculate the optimal recipients of support and generates a list of optimal recipients as output data. For this, it uses the match_supply_to_demand() function.

[0821] Step 6: Logistics Management

[0822] The server calculates the optimal support route and method and creates an efficient logistics plan. Specifically, it evaluates air, sea, and land options and selects the most efficient delivery route. Input data includes a list of optimal support destinations and logistics options. The server creates a delivery plan using a logistics optimization algorithm and generates optimal route information as output data. This information is notified to logistics partners via a RESTful API. The server optimizes the logistics route using the optimize_logistics_route() function.

[0823] Step 7: Credit issuance and confirmation of support completion

[0824] Once the relief activity is completed, the server obtains the local receipt confirmation data. Specifically, the receipt confirmation data sent from the local site is obtained using an API and processed on the server. The input data includes the local receipt confirmation report. The server adds credits to the user's account based on the receipt confirmation data. The output data is the updated user credit information. This process uses the verify_delivery() function to obtain the receipt confirmation data and add credits.

[0825] Step 8: Emotion Recognition and Customized Feedback

[0826] The server uses an emotion engine to collect and analyze emotion data when a user provides feedback. Specifically, it analyzes the feedback submitted by the user and extracts emotion data. The input data includes the user's feedback. The server generates a customized feedback message based on the analysis results. The output data is the customized feedback provided to the user. This process uses the analyze_feedback_emotions() function to perform emotion analysis.

[0827] (Application example 2)

[0828] 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."

[0829] To effectively solve hunger problems and efficiently manage relief supplies, it is necessary to quickly analyze collected data and develop distribution plans that meet local needs. It is also important to monitor the progress of relief activities in real time and provide appropriate feedback to relief workers. However, these processes in current systems are partial and fragmented, posing challenges to improving overall efficiency and user satisfaction.

[0830] 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 collecting hunger status, food inventory data, infrastructure status, and logistics data; means for analyzing the collected data using a generative AI model to generate a list of hunger status and needed supplies for each region; means for visualizing the generated analysis results on a visual dashboard and sending them to the user's terminal; means for users to input the supplies and funds they can provide and match supplies with recipients based on that information; means for calculating and executing the optimal logistics route by autonomous vehicles; means for issuing credits for the relief activities and providing feedback to the user after the relief activities are completed; and means for using an emotion engine to collect and analyze emotion data of the user's feedback and provide customized feedback based on that data. This enables more efficient relief activities and more effective distribution of supplies.

[0831] "Hunger Situation" is data showing the state of food shortages in a given area and their causes and effects.

[0832] "Food inventory data" is information about the amount and type of food currently available.

[0833] "Infrastructure status" is information that indicates the state of infrastructure related to transportation, such as logistics networks, roads, and bridges.

[0834] "Logistics data" refers to information related to the transportation of goods, including transportation routes, transportation means, transportation times, and the like.

[0835] A "generative AI model" is an artificial intelligence model used to analyze collected data and generate regional hunger situations and lists of needed supplies.

[0836] A "visual dashboard" is an interface for visually displaying analysis results, providing information in the form of graphs, maps, etc.

[0837] "User terminal" means a device used by a user to access and operate the system, including a smartphone or computer.

[0838] An "autonomous vehicle" is a vehicle that uses AI technology to operate autonomously and transport goods.

[0839] A "credit" is a unit of evaluation or reward given to a user who participates in a support activity.

[0840] An "emotion engine" is a software component that analyzes a user's feedback and identifies their emotional state.

[0841] "Customized feedback" refers to personalized feedback provided based on the user's emotional data.

[0842] This invention is a system that combines an emotion engine with a platform system that aims to effectively solve the hunger problem. This system has a wide range of functions as shown below.

[0843] System Configuration

[0844] This system is mainly composed of three entities: a server, a terminal, and a user. It also incorporates an emotion engine that recognizes the user's emotions.

[0845] Server: This is the central location for data collection, analysis, emotion recognition, and result management. This is where the generative AI model runs, generating regional hunger alerts and lists of supplies, and the emotion engine analyzes user feedback.

[0846] Software used: Generative AI model, emotion engine

[0847] Hardware used: High-performance server

[0848] Terminal: A device through which users access the system, input data, and view results. Analysis results are displayed through a visual dashboard, and users' emotional data is also entered.

[0849] Hardware used: smartphones, computers, smart glasses, etc.

[0850] Software used: Visual Dashboard

[0851] Users: These are primarily companies and individuals who use the platform to participate in relief efforts. Users provide supplies and funds, enter emotional feedback, and receive records of their support and credits.

[0852] Program processing explanation

[0853] 1. The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public institutions and non-governmental organizations (NGOs). The collected data is input into a generative AI model to generate hunger status and a list of needed supplies for each region.

[0854] 2. The analysis results are displayed in the form of a visual dashboard. The server creates visualization components such as graphs and maps based on the generated data and sends them to the device. The dashboard displayed on the device allows users to see at a glance the hunger situation in each region, the types of supplies needed, and aid priorities.

[0855] 3. The user inputs and submits detailed information about the supplies and funds they can provide via their device. This information is stored on the server. Based on the supply information provided by the user, the server uses a generative AI model to calculate the optimal recipient of support. This allows the system to match the needs of each region with the supplies provided by the user.

[0856] 4. Calculate optimal support routes and methods to develop efficient logistics plans, including evaluating air, sea, and land delivery options and selecting the most efficient delivery route, including autonomous vehicle delivery plans.

[0857] 5. Once the donation is completed, the server receives local receipt confirmation data. Based on this data, the server confirms the donation's completion and credits the user's account. The server also provides feedback on the success of the donation, providing reference information for the user when planning their next donation.

[0858] 6. The emotion engine is used to analyze the user's feedback and identify how the user feels about the support activity. Based on the emotion data, the server provides the user with customized feedback, including encouragement and suggestions for improvement based on the user's emotions.

[0859] Examples of concrete examples and prompts

[0860] For example, if a company can provide 5,000 kg of rice, the company's representative would enter the following:

[0861] Example prompt sentence:

[0862] We will provide 5000 kg of rice.

[0863] The server then receives the data, and the generative AI model calculates the optimal recipient of aid based on the collected hunger situation data. The results are displayed on a dashboard, allowing company personnel to check the progress of aid and logistics plans. Once aid is completed, receipt confirmation data from the site is sent to the server, and credits are added to the company's account. An emotion engine also analyzes the emotions of personnel and provides appropriate feedback.

[0864] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0865] Specific processing steps of the program

[0866] Step 1:

[0867] The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public institutions and non-governmental organizations (NGOs) via APIs. The input data is often provided in JSON format. The server centralizes and stores this data. Specifically, it periodically sends HTTP requests to each data source to retrieve the latest data. The output is a centralized database of hunger-related data.

[0868] Step 2:

[0869] The server inputs the collected data into a generative AI model and analyzes the data. The generative AI model uses a machine learning algorithm to generate the hunger situation and list of needed supplies for each region. The input is the data collected in step 1, and the output is the analyzed hunger situation and list of needed supplies. Specifically, data preprocessing (filling in missing values, standardizing data, etc.) is performed, and the data is then input into the model.

[0870] Step 3:

[0871] The server converts the generated analysis results into a data format for the visual dashboard. The converted data is sent to the terminal in a format that is easy to understand visually, such as a graph or map. The input is the analysis results, and the output is data for displaying the visual dashboard. Specifically, the data is converted into HTML and JavaScript format and sent to the terminal via a Web API.

[0872] Step 4:

[0873] The user enters detailed information about the supplies and funds they can provide into the terminal. The entered information is sent to the server and stored. The input is the information about the supplies and funds provided by the user, and the output is the resource information stored on the server. In concrete terms, the user enters data into a dedicated input form, and that data is sent to the server via HTTP POST.

[0874] Step 5:

[0875] The server uses a generative AI model to calculate the optimal recipient of aid based on the material information provided by the user. The input is the user's material information obtained in step 4 and the hunger status data obtained in step 2, and the output is information on the optimal recipient of aid. Specifically, the matching algorithm analyzes the information provided by the user and determines the recipient of aid as recommended by the generative AI model.

[0876] Step 6:

[0877] The server evaluates and selects the recommended delivery route and method for the goods, and formulates an efficient logistics plan, which includes the use of autonomous vehicles. The input is optimal support destination information and logistics data, and the output is an optimal delivery plan. Specific operations include calculating delivery routes and selecting transportation methods, and notifying the results to logistics partners and autonomous vehicles.

[0878] Step 7:

[0879] Once the relief activity is completed, the local receipt confirmation data is sent to the server. The server uses this data to add credits to the user's account. The input is the local receipt confirmation data, and the output is the updated user's account information. Specifically, the receipt confirmation data is sent and the server-side database is updated.

[0880] Step 8:

[0881] The server uses an emotion engine to analyze the user's feedback. Emotion data is collected along with the content of the feedback, and customized feedback is provided based on the analysis results. The input is the user's feedback, and the output is the emotion analysis results and customized feedback. Specifically, the emotion engine performs text analysis to determine the user's emotions and generate appropriate feedback.

[0882] Prompt Sentence Examples

[0883] "We will provide 5,000 kg of rice."

[0884] 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.

[0885] 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.

[0886] 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.

[0887] [Third embodiment]

[0888] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0889] 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.

[0890] 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).

[0891] 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.

[0892] 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.

[0893] 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).

[0894] 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. 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.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] 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.

[0899] 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."

[0900] This invention relates to a platform system that aims to effectively solve the problem of hunger using generative AI. Specific embodiments for implementing this system will be described below.

[0901] System Configuration

[0902] This system mainly consists of three main components: a server, a terminal, and a user.

[0903] Server: The central location for data collection, analysis, and results management. This is where the generative AI model runs, generating hunger statistics and supply lists for each region.

[0904] Terminal: A device where users access the system, enter data, and view results. Here, analytical results are displayed through a visual dashboard.

[0905] Users: Primarily companies and individuals who use the platform to participate in relief activities. Users provide supplies and funds, enter data, and obtain records and credits for their donations.

[0906] Program processing

[0907] Data collection and analysis

[0908] The server will first collect hunger status, food inventory data, infrastructure status, and logistics data from multiple public agencies and non-governmental organizations (NGOs), including access to APIs and data storage.

[0909] The collected data is fed into a generative AI model, which analyzes the data and generates a regional hunger situation and a list of needed supplies.

[0910] Data Visualization

[0911] The analysis results are displayed in the form of a visual dashboard. The server creates visualization components such as graphs and maps based on the generated data and sends them to the device.

[0912] The dashboard displayed on the device allows users to see at a glance the hunger situation in each region, the types of supplies needed, and aid priorities.

[0913] Supply and matching

[0914] Users input details of the supplies and funds they can provide through their terminals and submit the information, which is then stored on the server.

[0915] The server uses a generative AI model to calculate the optimal recipient of aid based on the supply information provided by users, thereby matching the needs of each region with the supplies provided by users.

[0916] Logistics management

[0917] The server calculates the optimal support route and method, and develops an efficient logistics plan. Specifically, it evaluates delivery options by air, sea, and land, and selects the most efficient delivery route.

[0918] Details of the logistics plan will be communicated to the relevant logistics partners.

[0919] Crediting and Feedback

[0920] Once the assistance activity is completed, the server receives a local acknowledgement of receipt and adds a "credit" to the user's account.

[0921] The server also provides feedback on the results of the support activities, providing reference information for the user when planning their next support.

[0922] Specific examples

[0923] For example, consider a company that can donate 5,000 kg of rice. A company representative logs into the platform using a device and enters the details of the donation (e.g., 5,000 kg of rice). The server then receives the data, and based on the collected hunger situation data, the generative AI model calculates the optimal recipient (e.g., a specific region in Africa). The results are displayed on a dashboard, where the company representative can check the progress of the donation and logistics plans.

[0924] Once the donation is complete, receipt confirmation data from the local area is sent to the server and credits are added to the company's account. At the same time, a feedback report is provided to help the company decide whether to donate next time. In this way, the entire system operates efficiently and aims to contribute to solving hunger.

[0925] The processing flow will be explained below.

[0926] Step 1:

[0927] The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public institutions and non-governmental organizations (NGOs) by sending requests to the United Nations Hunger Database API and the World Bank's data storage.

[0928] Step 2:

[0929] The server stores the collected data in an internal database, and when storing it, it formats and converts the data to ensure consistency.

[0930] Step 3:

[0931] The server inputs the data retrieved from the database into the generative AI model, which then begins analysis. The generative AI model identifies the hunger situation in each region, a list of necessary supplies, infrastructure shortages, and other information, and generates a report.

[0932] Step 4:

[0933] The server converts the analysis results into a visual dashboard, specifically by creating visualization components such as graphs and maps and designing a user-friendly interface.

[0934] Step 5:

[0935] The server then sends the generated visual dashboard to the device, where users can access the dashboard and check the hunger situation in each region, the types of supplies needed, and the priority of aid.

[0936] Step 6:

[0937] The user uses the terminal to input and submit details of the goods and funds available for donation, including the quantity, quality, and period of time available.

[0938] Step 7:

[0939] The server receives the material data obtained from the user, stores it in a database, and converts the stored data into an appropriate format for analysis.

[0940] Step 8:

[0941] The server uses a generative AI model to match the items provided by users with local needs, specifically by comparing the provided items with local hunger data and identifying the best recipients.

[0942] Step 9:

[0943] Based on the matching results, the server calculates the appropriate delivery route and method for the goods, analyzes multiple logistics options (air transport, sea transport, land transport) and formulates an efficient transportation plan.

[0944] Step 10:

[0945] The server notifies the relevant logistics partners of the details of the logistics plan and begins preparations for delivery, monitoring the delivery status in real time and making adjustments as necessary.

[0946] Step 11:

[0947] Once the relief activities are completed, the server receives receipt confirmation data from the site, and uses this data to confirm the completion of the relief activities.

[0948] Step 12:

[0949] The server will add "credits" to the user's account for the support, which will then be reflected in the user's profile.

[0950] Step 13:

[0951] The server provides the user with feedback on the results of the support activities, along with analytical data to help them improve their next support efforts. The feedback report is displayed on the user's dashboard.

[0952] The above are the specific program processing steps of the system for implementing the invention.

[0953] Example 1

[0954] 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."

[0955] This invention relates to a platform system for effectively solving the problem of hunger, which occurs frequently around the world. Currently, it is difficult to grasp the hunger situation, procure and supply necessary supplies, and efficiently manage the delivery of supplies and relief activities, which hinders the speed and effectiveness of relief activities. Other issues include low transparency and reliability of relief activities, and a lack of appropriate feedback to donors.

[0956] 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.

[0957] In this invention, the server includes: means for collecting hunger status, food inventory data, infrastructure status, and logistics data; means for analyzing the collected data using a generative AI model to generate a list of hunger status and needed supplies for each region; means for visualizing the generated analysis results on a visual dashboard and sending them to the user's device; means for users to input the supplies and funds they can provide and match supplies with recipients based on that information; means for analyzing the recommended delivery routes and methods for supplies using an advanced algorithm, formulating an efficient logistics plan, and notifying appropriate logistics partners; and means for issuing credits for relief activities using blockchain technology and providing feedback to users after the relief activities are completed. This enables effective and prompt resolution of hunger issues, improved transparency and reliability of relief activities, and appropriate feedback to donors.

[0958] "Hunger Situation" is data showing the degree of food shortages and malnutrition in each region.

[0959] "Food inventory data" refers to data that indicates information regarding the current amount and type of food in stock in a particular area or facility.

[0960] "Infrastructure status" refers to data that indicates the status of basic facilities and services such as roads, communications, power supply, and water supply.

[0961] "Logistics data" refers to data that indicates information related to the transportation and delivery of goods, including routes, means of transportation, and delivery schedules.

[0962] "Generative AI models" refer to artificial intelligence algorithms or programs used to analyze collected data and make predictions or optimizations.

[0963] A "visual dashboard" is an interface for visually displaying analysis results, and includes visual components such as graphs and maps.

[0964] "User terminal" refers to a device used by a user to access and operate the system, including a personal computer or smartphone.

[0965] "Resource matching" refers to the process by which aid providers optimally allocate available resources and funds to areas and facilities in need.

[0966] "Logistics planning" is a plan for the efficient transportation and delivery of goods, and refers to the process of determining the optimal routes and means.

[0967] "Logistics Partner" refers to a company or organization that partners with us to carry out the transportation or delivery of goods.

[0968] "Blockchain technology" is a distributed database technology used to ensure data transparency and prevention of tampering.

[0969] "Credits" refer to digital points or certificates that indicate recognition and reward for support activities.

[0970] "Feedback" refers to the process of providing evaluation information about the effectiveness and results of support activities.

[0971] This invention relates to a platform system that aims to effectively solve the problem of hunger using a generative AI model. This system consists of three entities: a server, a terminal, and a user. Specific embodiments for implementing this system are described below.

[0972] System Configuration

[0973] Server: The central location for data collection, analysis, and results management. This is where the generative AI model runs, generating hunger statistics and supply lists for each region.

[0974] Terminal: A device where users access the system, enter data, and view results. Here, analytical results are displayed through a visual dashboard.

[0975] Users: Primarily companies and individuals who use the platform to participate in relief activities. Users provide supplies and funds, enter data, and obtain records and credits for their donations.

[0976] Data collection and analysis

[0977] The server will collect hunger, food inventory, infrastructure, and logistics data from multiple public and non-governmental organizations, utilizing APIs and cloud storage.

[0978] For example, the server accesses a public institution's database via an API to obtain the latest hunger situation data, which is then stored in cloud storage such as AWS S3.

[0979] The collected data is fed into a generative AI model (specifically, using TensorFlow), which analyzes the data and generates a regional hunger alert and a list of supplies needed, using statistical models and machine learning algorithms.

[0980] Data Visualization

[0981] The server uses the D3.js library to convert the generated analysis results into visual components such as graphs and maps, and the generated visual data is sent to the device in JSON format.

[0982] The device displays a visual dashboard that allows users to interactively check the hunger situation map and supply status in real time on their browser.

[0983] Supply and matching

[0984] Users input details of the goods and funds they can provide through their devices, such as "donating 5,000 kg of rice." This data is sent to the server via API and stored in a database (e.g., MySQL).

[0985] The server uses a generative AI model to match the material information provided by users with the most appropriate recipients. This matching process compares the needs of each region with the materials provided to make the best match.

[0986] Logistics management

[0987] The server uses Dijkstra's algorithm to calculate the optimal relief route and delivery method, which determines the most efficient delivery route and ensures that relief supplies reach their destination as quickly as possible.

[0988] The results of the optimal delivery route calculation are sent to logistics partners via API, allowing them to carry out efficient logistics planning.

[0989] Crediting and Feedback

[0990] Once the donation is completed, the server receives local confirmation data and adds "credits" to the user's account, a process that utilizes blockchain technology to ensure transparency and reliability.

[0991] The server also provides the user with feedback on the results of the support activities and information that can be used as reference for planning the next support. The feedback report is sent from the server to the terminal, and the user can refer to it when planning the next support.

[0992] Examples of prompt statements

[0993] "Generate the best recipients and necessary supplies list based on the following data: Hunger situation data (areas A, B, C), Food inventory data (areas A, B, C), Infrastructure situation (areas A, B, C), Logistics data (areas A, B, C)"

[0994] This will ensure that the entire system is run efficiently, and is expected to contribute to solving the problem of hunger.

[0995] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0996] Step 1:

[0997] Data collection

[0998] The server collects hunger, food inventory, infrastructure, and logistics data from multiple public and non-governmental organizations, using API endpoints to access each organization's database and retrieve the latest data.

[0999] Input: Data collected via API (hunger status, food stocks, infrastructure, logistics)

[1000] Output: Raw data stored in cloud storage (e.g. AWS S3)

[1001] Specific operation: The server periodically executes an API call and saves the acquired data to the specified cloud storage.

[1002] Step 2:

[1003] Data analysis

[1004] The server inputs the collected data into a generative AI model, specifically using TensorFlow to analyze it and generate a hunger situation and a list of supplies needed.

[1005] Input: Datasets of hunger, food inventory, infrastructure, and logistics retrieved from cloud storage.

[1006] Output: Hunger report and list of supplies needed for each analyzed region

[1007] Specific operation: The server feeds the collected data into the TensorFlow model, calculates the analysis results, and stores the generated report and list of required supplies in a database.

[1008] Step 3:

[1009] Data visualization

[1010] The server converts the generated analysis results into a visual dashboard, generating graphs, maps, and other data using the D3.js library, and sends them to the device in JSON format.

[1011] Input: Analysis results from the generative AI model (hunger situation report, list of needed supplies)

[1012] Output: Visual data in JSON format

[1013] Specific operation: The server uses the analysis results to generate heat maps and bar charts using D3.js, converts them to JSON format, saves them, and sends them to the terminal as appropriate.

[1014] Step 4:

[1015] Viewing the Dashboard

[1016] The terminal receives the JSON data sent from the server and displays it as a visual dashboard.

[1017] Input: Visual data in JSON format from the server

[1018] Output: A visual dashboard displayed in the user's browser

[1019] Specific operation: The terminal parses the received JSON and displays it as an interactive dashboard using the D3.js library.

[1020] Step 5:

[1021] Enter and submit supply information

[1022] The user uses a terminal to input detailed information about the supplies and funds that can be provided and sends this information to the server.

[1023] Input: Information about supplies and funds entered by the user (e.g., 5,000 kg of rice)

[1024] Output: Material information sent to the server

[1025] Specific operation: The user enters the necessary information into a form on the device, which is then sent to the server via the API and stored in a database.

[1026] Step 6:

[1027] Executing the matching algorithm

[1028] The server uses a generative AI model to calculate the optimal recipient of support based on the material information provided by the user.

[1029] Input: Provided supplies information, hunger situation data, list of required supplies

[1030] Output: List of optimal support recipients

[1031] Specific operation: The server inputs the supply information into the TensorFlow model, and calculates the optimal support destination as the analysis result. This information is stored in a database.

[1032] Step 7:

[1033] Delivery route calculation and notification

[1034] The server uses advanced algorithms to calculate efficient delivery routes and methods for supplies and notifies logistics partners.

[1035] Input: List of optimal support recipients and logistics data

[1036] Output: Delivery plan notification to logistics partners

[1037] Specific operation: The server calculates the optimal delivery route using Dijkstra's algorithm and notifies the logistics partner of this information via API.

[1038] Step 8:

[1039] Confirmation of support activities and issuance of credits

[1040] The user receives confirmation data from the site to confirm the completion of the relief activity and sends it to the server, which issues credits to the user's account based on the confirmation data and provides feedback.

[1041] Input: Receipt confirmation data from the site

[1042] Output: Credits to user accounts and feedback reports

[1043] Specific operation: The server records the receipt confirmation data using blockchain technology, adds credits to the user, and generates and sends a feedback report.

[1044] (Application example 1)

[1045] 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."

[1046] Hunger is a global issue, threatening the very foundations of life in many regions. To combat this, adequate supplies and efficient logistics planning are essential. However, managing aid activities and calculating optimal supply delivery routes is complex and consumes significant human resources. Furthermore, the lack of real-time inventory management and visibility into delivery routes increases the risk of aid delays. This makes it difficult to provide fast and effective aid to famine-stricken areas.

[1047] 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.

[1048] In this invention, the server includes a means for collecting data on the famine situation, food inventory data, infrastructure status, and logistics data, a means for analyzing the collected data with a generative AI model to generate a list of the famine situation and supplies needed by region, and a means for visualizing the generated analysis results on a visual dashboard and sending them to the user's device, thereby enabling more efficient and rapid response in relief activities.

[1049] The invention further includes a means for users to input the supplies and funds they can provide and match supplies with recipients based on that information, a means for analyzing the recommended delivery route and method for the supplies and formulating an efficient logistics plan, a means for issuing credits for the relief activities and providing feedback to the user after the relief is completed, a means using a smart device for displaying inventory status and delivery routes in real time, and a means for supporting the picking and delivery of relief supplies at the logistics center. This improves work efficiency within the logistics center and enables fast and effective relief to famine-stricken areas.

[1050] "Hunger situation" refers to the level of food shortages in a particular area and the situation of people suffering from malnutrition.

[1051] "Food inventory data" refers to data that includes inventory information for food, beverages, and other items provided as relief supplies.

[1052] "Infrastructure status" refers to the current condition and performance of infrastructure such as roads, transportation, and communication networks related to relief activities.

[1053] "Logistics data" refers to information relating to the transportation of goods, including information such as the point of departure, destination, transportation method, route, and time.

[1054] A "generative AI model" is an artificial intelligence model that analyzes collected data and generates specific outputs (for example, the hunger situation in each region and a list of needed supplies).

[1055] A "visual dashboard" refers to a visual user interface for displaying analyzed data in an easy-to-read format.

[1056] "Terminal" means a device (such as a smartphone, tablet, or computer) through which a user accesses the system, enters data, and views results.

[1057] "Matching" is the process of matching available supplies and funds with the needs of the recipient and finding the optimal combination.

[1058] A "logistics plan" is a plan to determine efficient routes and methods for delivering supplies and to ensure optimal relief activities.

[1059] "Credits" are evaluation points or rewards given to users who perform support activities.

[1060] "Feedback" is information provided to users reporting on the results of support activities and areas for improvement.

[1061] "Smart devices" are wearable electronic devices such as glasses and headsets that have internet connectivity and high-performance sensors.

[1062] "Picking" refers to the task of selecting specific items from inventory at a logistics center.

[1063] This invention relates to a platform system that aims to effectively solve the problem of hunger using a generative AI model. The system of the present invention is mainly composed of three entities: a server, a terminal, and a user.

[1064] System Configuration

[1065] Server: Collects data, analyzes, and manages the results. This server runs a generative AI model that generates hunger situations and lists of supplies for each region.

[1066] Terminal: A device where users access the system, enter data, and view results. Here, analytical results are displayed through a visual dashboard.

[1067] Users: Primarily companies and individuals who use the system to participate in relief activities. Users provide and input supplies and funds, and obtain records and credits for their support.

[1068] Program Overview

[1069] 1. Data Collection and Analysis

[1070] The server first collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public institutions and non-governmental organizations (NGOs). This data collection includes access to APIs and data storage. The collected data is then fed into a generative AI model, which analyzes the data and generates regional hunger status and a list of needed supplies.

[1071] 2. Data visualization

[1072] The analysis results are displayed in the form of a visual dashboard. The server creates visualization components such as graphs and maps based on the generated data and sends them to the device. The dashboard displayed on the device allows users to see at a glance the hunger situation in each region, the types of supplies needed, and aid priorities.

[1073] 3. Supply and matching

[1074] Users input detailed information about the supplies and funds they can provide through their devices and submit it. This information is stored on the server. The server then uses a generative AI model based on the supply information provided by the user to calculate the optimal recipient of support. This allows the system to match the needs of each region with the supplies provided by the user.

[1075] 4. Logistics management

[1076] The server calculates the optimal support route and method, and develops an efficient logistics plan. Specifically, it evaluates air, sea, and land delivery options and selects the most efficient delivery route. The details of the logistics plan are then communicated to the relevant logistics partners.

[1077] 5. Crediting and Feedback

[1078] Once the relief effort is completed, the server receives a local confirmation of receipt, credits the user's account, and provides feedback on the success of the relief effort, providing reference information for the user when planning their next relief effort.

[1079] Specific examples

[1080] For example, let's say a company can donate 5,000 kg of rice. The company's representative logs into the platform using a terminal and enters the details of the goods to be donated (e.g., 5,000 kg of rice). The server then receives this data, and the generative AI model calculates the optimal recipient of the donation based on the collected hunger situation data. The results are displayed on a dashboard, where company representatives can check the progress of the donation and logistics plans. Once the donation is completed, confirmation of receipt from the site is sent to the server, and credits are added to the company's account. At the same time, a feedback report is provided to help with the next donation. In this way, the entire system operates efficiently, aiming to contribute to resolving hunger.

[1081] Prompt Sentence Examples

[1082] "Please describe the overview and functionality of the hunger relief logistics management app. Include a specific example of a program that retrieves data from Firebase, analyzes it using a TensorFlow model, calculates optimal delivery routes using the Google Maps API, and displays the data on smart glasses using OpenCV."

[1083] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1084] Step 1:

[1085] Data collection

[1086] Subject: Server

[1087] The server collects hunger status, food inventory data, infrastructure status, and logistics data from public institutions and non-governmental organizations (NGOs) through APIs and data storage. The collected data is stored as raw data. Specifically, the server sends requests to the APIs of each data provider and imports the returned data.

[1088] Input: Send API request

[1089] Output: Save various data

[1090] Step 2:

[1091] Data analysis

[1092] Subject: Server

[1093] The server inputs the collected data into a generative AI model, which analyzes the data and generates a regional hunger situation and a list of needed supplies. Specifically, the server runs the model using TensorFlow to obtain predictions.

[1094] Input: Collected data

[1095] Output: Analysis results (hungry situation by region and list of necessary supplies)

[1096] Step 3:

[1097] Data Visualization

[1098] Subject: Server

[1099] The server uses the generated analysis results to create a visual dashboard and sends it to the terminal. The data is visualized in the form of graphs, maps, etc. Specifically, the server generates the dashboard using libraries such as OpenCV and D3.js and sends it to the terminal via WebSocket.

[1100] Input: Analysis results

[1101] Output: Visual dashboard

[1102] Step 4:

[1103] Supply and matching

[1104] Subject: User and Server

[1105] Users enter information about the supplies and funds they can provide through their devices and send it to the server. The server receives this information and uses a generative AI model to calculate the optimal recipient of aid. Specifically, users enter information into a web form, and the server then analyzes it again using the AI ​​model.

[1106] Input: Material and financial information

[1107] Output: Best Support

[1108] Step 5:

[1109] Logistics planning

[1110] Subject: Server

[1111] The server calculates the optimal support route and method, and develops an efficient logistics plan. It evaluates delivery options by air, sea, and land, and selects the most efficient delivery route. Specifically, the server calculates the delivery route using the Google Maps API and notifies the logistics partner of the results.

[1112] Input: Information on the provided supplies and recipients

[1113] Output: Efficient logistics planning

[1114] Step 6:

[1115] Crediting and Feedback

[1116] Subject: Server

[1117] Once a relief effort is completed, local receipt confirmation data is sent to the server. The server uses this information to add credits to the user's account. It also provides feedback on the success of the relief effort, providing reference information for the user when planning their next relief effort. Specifically, the server analyzes the receipt confirmation data, updates the user's credits, and generates a report.

[1118] Input: Receipt confirmation data

[1119] Output: Credits added, feedback report

[1120] Step 7:

[1121] Real-time display on smart devices

[1122] Subject: Smart device (terminal)

[1123] The smart device displays real-time inventory status and delivery routes. To assist with the picking and delivery of relief supplies at the logistics center, the device incorporates OpenCV and Google Maps API. Specifically, the smart glasses overlay information on the user's field of vision based on data sent from the server.

[1124] Input: Shipping and inventory data from the server

[1125] Output: Real-time display on smart devices

[1126] 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.

[1127] This invention combines an emotion engine with a platform system that aims to effectively solve the problem of hunger using generative AI. Specific embodiments for implementing this system are described below.

[1128] System Configuration

[1129] This system is mainly composed of three entities: a server, a terminal, and a user. It also incorporates an emotion engine that recognizes the user's emotions.

[1130] Server: This is the central location for data collection, analysis, emotion recognition, and result management. This is where the generative AI model runs, generating regional hunger alerts and lists of supplies, and the emotion engine analyzes user feedback.

[1131] Terminal: A device where users access the system, input data, and view results. Here, analysis results are displayed through a visual dashboard, and users' emotional data is also entered.

[1132] Users: These are primarily companies and individuals who use the platform to participate in relief efforts. Users provide supplies and funds, enter emotional feedback, and receive records of their support and credits.

[1133] Program processing

[1134] Data collection and analysis

[1135] The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public agencies and non-governmental organizations (NGOs), including access to APIs and data storage.

[1136] The collected data is fed into a generative AI model, which analyzes the data and generates a regional hunger situation and a list of needed supplies.

[1137] Data Visualization

[1138] The analysis results are displayed in the form of a visual dashboard. The server creates visualization components such as graphs and maps based on the generated data and sends them to the device.

[1139] The dashboard displayed on the device allows users to see at a glance the hunger situation in each region, the types of supplies needed, and aid priorities.

[1140] Supply and matching

[1141] Users input details of the supplies and funds they can provide through their terminals and submit the information, which is then stored on the server.

[1142] The server uses a generative AI model to calculate the optimal recipient of aid based on the supply information provided by users, thereby matching the needs of each region with the supplies provided by users.

[1143] Logistics management

[1144] The server calculates the optimal support route and method, and develops an efficient logistics plan. Specifically, it evaluates delivery options by air, sea, and land, and selects the most efficient delivery route.

[1145] Details of the logistics plan will be communicated to the relevant logistics partners.

[1146] Crediting and Feedback

[1147] Once the relief effort is completed, the server receives local receipt confirmation data, which is used to confirm the relief effort has been completed and add a "credit" to the user's account.

[1148] The server also provides feedback on the results of the support activities, providing reference information for the user when planning their next support.

[1149] Emotion Recognition and Customized Feedback

[1150] The server uses an emotion engine to collect and analyze the user's emotional data when the user provides feedback, thereby identifying how the user feels about the support activity.

[1151] Based on the emotion data, the server provides customized feedback to the user, including encouragement and suggestions for improvement based on the user's emotions.

[1152] The analysis results of the emotion engine are used to optimize the next relief operation plan.

[1153] Specific examples

[1154] For example, consider a company that can donate 5,000 kg of rice. A company representative logs into the platform using a device and enters the details of the donation (e.g., 5,000 kg of rice). The server then receives the data, and based on the collected hunger situation data, the generative AI model calculates the optimal recipient (e.g., a specific region in Africa). The results are displayed on a dashboard, where the company representative can check the progress of the donation and logistics plans.

[1155] Once the donation is completed, receipt confirmation data from the site is sent to the server, and credits are added to the company's account. At the same time, the server uses an emotion engine to analyze the emotions of the person in charge. For example, if there are many positive emotions about the donation activity, the server will provide feedback emphasizing its success. Conversely, if there is a lot of feedback pointing out areas for improvement, the server will provide a report containing suggestions to help optimize the next donation activity. In this way, the entire system operates efficiently, aiming to increase user satisfaction while contributing to solving hunger.

[1156] The processing flow will be explained below.

[1157] Step 1:

[1158] The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public institutions and non-governmental organizations (NGOs) by sending requests to the United Nations Hunger Database API and the World Bank's data storage.

[1159] Step 2:

[1160] The server stores the collected data in an internal database. When storing the data, it formats and converts the data to maintain consistency. For example, it unifies data in different formats and extracts necessary indicators.

[1161] Step 3:

[1162] The server inputs the data retrieved from the database into the generative AI model, which then begins analysis. The generative AI model identifies the hunger situation in each region, a list of necessary supplies, infrastructure shortages, and other information, and generates a report.

[1163] Step 4:

[1164] The server converts the analysis results into a visual dashboard, specifically by creating visualization components such as graphs and maps and designing a user-friendly interface.

[1165] Step 5:

[1166] The server then sends the generated visual dashboard to the device, where users can access the dashboard and check the hunger situation in each region, the types of supplies needed, and the priority of aid.

[1167] Step 6:

[1168] The user uses the terminal to input and submit details of the goods and funds available for donation, including the quantity, quality, and period of time available.

[1169] Step 7:

[1170] The server receives the material data obtained from the user, stores it in a database, and converts the stored data into an appropriate format for analysis.

[1171] Step 8:

[1172] The server uses a generative AI model to match the items provided by users with local needs, specifically by comparing the provided items with local hunger data and identifying the best recipients.

[1173] Step 9:

[1174] Based on the matching results, the server calculates the appropriate delivery route and method for the goods, analyzes multiple logistics options (air transport, sea transport, land transport) and formulates an efficient transportation plan.

[1175] Step 10:

[1176] The server notifies the relevant logistics partners of the details of the logistics plan and begins preparations for delivery, monitoring the delivery status in real time and making adjustments as necessary.

[1177] Step 11:

[1178] Once the relief activities are completed, the server receives receipt confirmation data from the site, and uses this data to confirm the completion of the relief activities.

[1179] Step 12:

[1180] The server will add "credits" to the user's account for the support, which will then be reflected in the user's profile.

[1181] Step 13:

[1182] The server provides the user with feedback on the results of the support activities, along with analytical data to help them improve their next support efforts. The feedback report is displayed on the user's dashboard.

[1183] Step 14:

[1184] When a user inputs feedback, the server uses an emotion engine to collect the user's emotion data, for example, by analyzing the text of the feedback or voice input and classifying the emotion as positive, negative, etc.

[1185] Step 15:

[1186] The server analyzes the user's feedback in detail based on the emotion data analyzed by the emotion engine, thereby identifying how the user feels about the support activities.

[1187] Step 16:

[1188] The server then provides customized feedback to the user based on the emotional data, such as highlighting achievements when emotions are predominantly positive, or providing specific areas for improvement when emotions are predominantly negative.

[1189] Step 17:

[1190] The server uses the analysis results of the emotion engine to reflect user feedback in the next support activity plan, specifically identifying support methods to increase user motivation and issues that need improvement.

[1191] The above are the specific program processing steps of the system for implementing the invention.

[1192] Example 2

[1193] 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."

[1194] Hunger is becoming a serious problem around the world, and appropriate aid is urgently needed, especially in resource-limited areas. The current system involves a complex and cumbersome process, including the provision and delivery of aid supplies, on-site receipt confirmation, and feedback to donors, making it difficult to manage efficiently. Furthermore, emotional feedback on aid activities is not fully utilized, making it difficult to motivate donors. Therefore, a comprehensive system is needed that can provide effective aid against hunger and improve donor satisfaction.

[1195] 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.

[1196] In this invention, the server includes: means for collecting hunger status, food inventory data, infrastructure status, and logistics data; means for analyzing the collected data using a generative AI model to generate a list of hunger status and needed supplies for each region; means for visualizing the generated analysis results on a visual dashboard and sending them to a user's device; means for users to input the supplies and funds they can provide and match the supplies with recipients based on that information; means for analyzing the delivery route and method for the recommended supplies and formulating an efficient logistics plan; means for obtaining local receipt confirmation data after the completion of the support and issuing credits to the user's account; and means for collecting and analyzing emotional data when the user provides feedback and providing customized feedback. This makes it possible to provide effective support for hunger issues and further increase the satisfaction of supporters by analyzing users' emotions and customizing the feedback.

[1197] "Hunger Situation" is information that indicates the state and severity of food shortages in a particular area.

[1198] "Food inventory data" is information that indicates the current food supply and stockpiles in a particular region or organization.

[1199] "Infrastructure status" refers to information that indicates the status of the infrastructure needed to carry out relief activities, such as transportation and storage facilities, in a particular area.

[1200] "Logistics data" refers to information related to logistics activities, such as delivery routes, transportation methods, and delivery schedules for goods.

[1201] A "generative AI model" is an artificial intelligence model that performs analysis and predictions based on accumulated data, and is used to analyze hunger situations and select the most appropriate recipients of aid.

[1202] A "visual dashboard" is an interface for visually displaying analysis results, using graphs and maps to enable users to easily understand the data.

[1203] "Support recipient" refers to the target region or organization that receives supplies and funds.

[1204] "Matching" is the process of comparing the supplies and financial information of the aid provider with the needs of the recipient to determine the optimal combination.

[1205] "Logistics planning" is the activity of formulating schedules and procedures for delivering goods via the optimal routes and means.

[1206] "Credits" are evaluation points or rewards given to a user after completing a support activity, and serve as an incentive for the next support activity.

[1207] "Emotion data" is information that quantifies or classifies the emotional state or tendency shown by the user when providing feedback.

[1208] "Customized feedback" refers to feedback messages and advice that are individually tailored based on the user's emotional data, in order to optimize the next support activity.

[1209] This invention combines an emotion engine with a platform system that aims to effectively solve the hunger problem using a generative AI model. Specific embodiments for implementing this system are described below.

[1210] System Configuration

[1211] This system is mainly composed of three entities: a server, a terminal, and a user. It also incorporates an emotion engine that recognizes the user's emotions.

[1212] Server: This is the central location for data collection, analysis, emotion recognition, and result management. This is where the generative AI model runs to generate regional hunger alerts and lists of supplies, and the emotion engine analyzes user feedback. Software used includes Python, TensorFlow, Node.js, and Express.

[1213] Terminal: This is the device where users access the system, input data, and view results. Here, analysis results are displayed through a visual dashboard, and user sentiment data is also entered. Visualization is done using D3.js and Tableau.

[1214] Users: These are primarily companies and individuals who use the platform to participate in relief efforts. Users provide supplies and funds, enter emotional feedback, and receive records of their support and credits.

[1215] Program processing

[1216] Data collection and analysis

[1217] The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public institutions and NGOs. This collection is done using access to APIs and data storage. For example, it retrieves the latest hunger status data from the API of an international organization.

[1218] The collected data is fed into a generative AI model, which analyzes the data and generates a regional hunger situation and a list of needed supplies. Specifically, the model is built using Python and TensorFlow.

[1219] Data Visualization

[1220] The analysis results are displayed in the form of a visual dashboard. The server creates visualization components such as graphs and maps using D3.js or Tableau based on the generated data and sends them to the device.

[1221] The dashboard displayed on the device allows users to check the hunger situation in each region, the types of supplies needed, and aid priorities.

[1222] Supply and matching

[1223] Users input details of the supplies and funds they can provide through their terminals and submit them. For example, a company representative might input "5,000 kg of rice" into the platform.

[1224] The server uses a generative AI model to calculate the optimal recipient of aid based on the supply information provided by the user, effectively matching local needs with the supplies provided by the user.

[1225] Logistics management

[1226] The server calculates the optimal support route and method, develops an efficient logistics plan, and evaluates air, sea, and land delivery options to select the most efficient delivery route. Logistics partners are notified via a RESTful API.

[1227] Credit issuance and confirmation of support completion

[1228] Once the relief effort is complete, the server receives local receipt confirmation data, such as a receipt confirmation report sent from the site via API.

[1229] The server uses this data to add credits to the user's account, and also provides feedback on the results of the support activity, providing reference information for the user when planning their next support.

[1230] Emotion Recognition and Customized Feedback

[1231] The server uses an emotion engine to collect and analyze the user's emotional data when the user provides feedback, and provides customized feedback including encouragement and suggestions for improvement according to the user's emotions.

[1232] Data obtained from the emotion engine is used to optimize the next outreach plan.

[1233] Specific examples

[1234] For example, consider a company that can donate 5,000 kg of rice. The company's representative logs into the platform using a terminal and enters the details of the donation (e.g., 5,000 kg of rice). The server then receives the data, and based on the collected hunger situation data, the generative AI model calculates the optimal recipient (e.g., a specific region) of the donation. The results are displayed on a dashboard, where the company's representative can check the progress of the donation and the logistics plan. The log data contains the following prompt:

[1235] Example prompt sentence:

[1236] "We can provide 5,000 kg of rice. Please calculate the optimal recipient and propose a delivery plan."

[1237] Once the donation is completed, a receipt confirmation is sent from the site to the server, and a credit is added to the company's account. At the same time, the server uses an emotion engine to analyze the emotions of the person in charge. For example, if there are many positive emotions about the donation activity, the server will provide feedback that highlights the success. Conversely, if there is a lot of feedback pointing out areas for improvement, the server will provide a report with suggestions to help optimize the next donation activity.

[1238] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1239] Step 1: Data collection

[1240] The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public organizations and NGOs. Specifically, the server accesses API endpoints to retrieve this data. This input data includes real-time hunger status data and logistics data from international organizations. The collected data is stored in a database on the server. To collect data, the server uses a Python script to access the API using the requests library. As a result, the retrieved data is stored on the server in JSON format.

[1241] Step 2: Data analysis

[1242] The server inputs the collected data into a generative AI model. Specifically, the generative AI model built with TensorFlow inputs hunger situation data and food inventory data for analysis. The input data includes the hunger situation and inventory situation for each region. The server uses the generative AI model to calculate the hunger situation and list of needed supplies for each region. The output data is saved on the server as the analyzed hunger situation and supply list. This analysis is performed by running the analyze_data_with_AI() function, which supplies the data to the generative AI model.

[1243] Step 3: Visualize the data

[1244] The server displays the generated analysis results in the form of a visual dashboard. Specifically, the server generates graphs and maps using D3.js or Tableau and sends them to the terminal. The input data includes the JSON data of the analysis results. The server visualizes the data and converts it into a format that is easy for users to understand. The output data is sent to the terminal as visualized graphs and maps. For this process, the create_visuals_from_data() function is used to generate visualization components using D3.js.

[1245] Step 4: Enter your supply

[1246] The user inputs detailed information about the supplies and funds that can be provided through the terminal. Specifically, the type and amount of supplies are entered into the input form on the terminal and sent to the server. The input data includes the supplies that the user will provide (e.g., 5,000 kg of rice). The terminal sends this data to the server via the send button. The server stores the received data in a database. The user enters detailed information using the input form and sends the information to the server by clicking the "Send" button.

[1247] Step 5: Matching supplies with recipients

[1248] The server inputs the supply information provided by the user into the generative AI model and calculates the optimal recipients of support. Specifically, the server matches the supply data provided by the user with the collected hunger situation data. The input data includes the supply data provided by the user and the hunger situation data. The server uses the generative AI model to calculate the optimal recipients of support and generates a list of optimal recipients as output data. For this, it uses the match_supply_to_demand() function.

[1249] Step 6: Logistics Management

[1250] The server calculates the optimal support route and method and creates an efficient logistics plan. Specifically, it evaluates air, sea, and land options and selects the most efficient delivery route. Input data includes a list of optimal support destinations and logistics options. The server creates a delivery plan using a logistics optimization algorithm and generates optimal route information as output data. This information is notified to logistics partners via a RESTful API. The server optimizes the logistics route using the optimize_logistics_route() function.

[1251] Step 7: Credit issuance and confirmation of support completion

[1252] Once the relief activity is completed, the server obtains the local receipt confirmation data. Specifically, the receipt confirmation data sent from the local site is obtained using an API and processed on the server. The input data includes the local receipt confirmation report. The server adds credits to the user's account based on the receipt confirmation data. The output data is the updated user credit information. This process uses the verify_delivery() function to obtain the receipt confirmation data and add credits.

[1253] Step 8: Emotion Recognition and Customized Feedback

[1254] The server uses an emotion engine to collect and analyze emotion data when a user provides feedback. Specifically, it analyzes the feedback submitted by the user and extracts emotion data. The input data includes the user's feedback. The server generates a customized feedback message based on the analysis results. The output data is the customized feedback provided to the user. This process uses the analyze_feedback_emotions() function to perform emotion analysis.

[1255] (Application example 2)

[1256] 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."

[1257] To effectively solve hunger problems and efficiently manage relief supplies, it is necessary to quickly analyze collected data and develop distribution plans that meet local needs. It is also important to monitor the progress of relief activities in real time and provide appropriate feedback to relief workers. However, these processes in current systems are partial and fragmented, posing challenges to improving overall efficiency and user satisfaction.

[1258] 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 collecting hunger status, food inventory data, infrastructure status, and logistics data; means for analyzing the collected data using a generative AI model to generate a list of hunger status and needed supplies for each region; means for visualizing the generated analysis results on a visual dashboard and sending them to the user's terminal; means for users to input the supplies and funds they can provide and match supplies with recipients based on that information; means for calculating and executing the optimal logistics route by autonomous vehicles; means for issuing credits for the relief activities and providing feedback to the user after the relief activities are completed; and means for using an emotion engine to collect and analyze emotion data of the user's feedback and provide customized feedback based on that data. This enables more efficient relief activities and more effective distribution of supplies.

[1259] "Hunger Situation" is data showing the state of food shortages in a given area and their causes and effects.

[1260] "Food inventory data" is information about the amount and type of food currently available.

[1261] "Infrastructure status" is information that indicates the state of infrastructure related to transportation, such as logistics networks, roads, and bridges.

[1262] "Logistics data" refers to information related to the transportation of goods, including transportation routes, transportation means, transportation times, and the like.

[1263] A "generative AI model" is an artificial intelligence model used to analyze collected data and generate regional hunger situations and lists of needed supplies.

[1264] A "visual dashboard" is an interface for visually displaying analysis results, providing information in the form of graphs, maps, etc.

[1265] "User terminal" means a device used by a user to access and operate the system, including a smartphone or computer.

[1266] An "autonomous vehicle" is a vehicle that uses AI technology to operate autonomously and transport goods.

[1267] A "credit" is a unit of evaluation or reward given to a user who participates in a support activity.

[1268] An "emotion engine" is a software component that analyzes a user's feedback and identifies their emotional state.

[1269] "Customized feedback" refers to personalized feedback provided based on the user's emotional data.

[1270] This invention is a system that combines an emotion engine with a platform system that aims to effectively solve the hunger problem. This system has a wide range of functions as shown below.

[1271] System Configuration

[1272] This system is mainly composed of three entities: a server, a terminal, and a user. It also incorporates an emotion engine that recognizes the user's emotions.

[1273] Server: This is the central location for data collection, analysis, emotion recognition, and result management. This is where the generative AI model runs, generating regional hunger alerts and lists of supplies, and the emotion engine analyzes user feedback.

[1274] Software used: Generative AI model, emotion engine

[1275] Hardware used: High-performance server

[1276] Terminal: A device through which users access the system, input data, and view results. Analysis results are displayed through a visual dashboard, and users' emotional data is also entered.

[1277] Hardware used: smartphones, computers, smart glasses, etc.

[1278] Software used: Visual Dashboard

[1279] Users: These are primarily companies and individuals who use the platform to participate in relief efforts. Users provide supplies and funds, enter emotional feedback, and receive records of their support and credits.

[1280] Program processing explanation

[1281] 1. The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public institutions and non-governmental organizations (NGOs). The collected data is input into a generative AI model to generate hunger status and a list of needed supplies for each region.

[1282] 2. The analysis results are displayed in the form of a visual dashboard. The server creates visualization components such as graphs and maps based on the generated data and sends them to the device. The dashboard displayed on the device allows users to see at a glance the hunger situation in each region, the types of supplies needed, and aid priorities.

[1283] 3. The user inputs and submits detailed information about the supplies and funds they can provide via their device. This information is stored on the server. Based on the supply information provided by the user, the server uses a generative AI model to calculate the optimal recipient of support. This allows the system to match the needs of each region with the supplies provided by the user.

[1284] 4. Calculate optimal support routes and methods to develop efficient logistics plans, including evaluating air, sea, and land delivery options and selecting the most efficient delivery route, including autonomous vehicle delivery plans.

[1285] 5. Once the donation is completed, the server receives local receipt confirmation data. Based on this data, the server confirms the donation's completion and credits the user's account. The server also provides feedback on the success of the donation, providing reference information for the user when planning their next donation.

[1286] 6. The emotion engine is used to analyze the user's feedback and identify how the user feels about the support activity. Based on the emotion data, the server provides the user with customized feedback, including encouragement and suggestions for improvement based on the user's emotions.

[1287] Examples of concrete examples and prompts

[1288] For example, if a company can provide 5,000 kg of rice, the company's representative would enter the following:

[1289] Example prompt sentence:

[1290] We will provide 5000 kg of rice.

[1291] The server then receives the data, and the generative AI model calculates the optimal recipient of aid based on the collected hunger situation data. The results are displayed on a dashboard, allowing company personnel to check the progress of aid and logistics plans. Once aid is completed, receipt confirmation data from the site is sent to the server, and credits are added to the company's account. An emotion engine also analyzes the emotions of personnel and provides appropriate feedback.

[1292] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1293] Specific processing steps of the program

[1294] Step 1:

[1295] The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public institutions and non-governmental organizations (NGOs) via APIs. The input data is often provided in JSON format. The server centralizes and stores this data. Specifically, it periodically sends HTTP requests to each data source to retrieve the latest data. The output is a centralized database of hunger-related data.

[1296] Step 2:

[1297] The server inputs the collected data into a generative AI model and analyzes the data. The generative AI model uses a machine learning algorithm to generate the hunger situation and list of needed supplies for each region. The input is the data collected in step 1, and the output is the analyzed hunger situation and list of needed supplies. Specifically, data preprocessing (filling in missing values, standardizing data, etc.) is performed, and the data is then input into the model.

[1298] Step 3:

[1299] The server converts the generated analysis results into a data format for the visual dashboard. The converted data is sent to the terminal in a format that is easy to understand visually, such as a graph or map. The input is the analysis results, and the output is data for displaying the visual dashboard. Specifically, the data is converted into HTML and JavaScript format and sent to the terminal via a Web API.

[1300] Step 4:

[1301] The user enters detailed information about the supplies and funds they can provide into the terminal. The entered information is sent to the server and stored. The input is the information about the supplies and funds provided by the user, and the output is the resource information stored on the server. In concrete terms, the user enters data into a dedicated input form, and that data is sent to the server via HTTP POST.

[1302] Step 5:

[1303] The server uses a generative AI model to calculate the optimal recipient of aid based on the material information provided by the user. The input is the user's material information obtained in step 4 and the hunger status data obtained in step 2, and the output is information on the optimal recipient of aid. Specifically, the matching algorithm analyzes the information provided by the user and determines the recipient of aid as recommended by the generative AI model.

[1304] Step 6:

[1305] The server evaluates and selects the recommended delivery route and method for the goods, and formulates an efficient logistics plan, which includes the use of autonomous vehicles. The input is optimal support destination information and logistics data, and the output is an optimal delivery plan. Specific operations include calculating delivery routes and selecting transportation methods, and notifying the results to logistics partners and autonomous vehicles.

[1306] Step 7:

[1307] Once the relief activity is completed, the local receipt confirmation data is sent to the server. The server uses this data to add credits to the user's account. The input is the local receipt confirmation data, and the output is the updated user's account information. Specifically, the receipt confirmation data is sent and the server-side database is updated.

[1308] Step 8:

[1309] The server uses an emotion engine to analyze the user's feedback. Emotion data is collected along with the content of the feedback, and customized feedback is provided based on the analysis results. The input is the user's feedback, and the output is the emotion analysis results and customized feedback. Specifically, the emotion engine performs text analysis to determine the user's emotions and generate appropriate feedback.

[1310] Prompt Sentence Examples

[1311] "We will provide 5,000 kg of rice."

[1312] 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.

[1313] 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.

[1314] 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.

[1315] [Fourth embodiment]

[1316] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1317] 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.

[1318] 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).

[1319] 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.

[1320] 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.

[1321] 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).

[1322] 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. 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.

[1323] 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.

[1324] 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.

[1325] 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.

[1326] 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.

[1327] 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.

[1328] 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."

[1329] This invention relates to a platform system that aims to effectively solve the problem of hunger using generative AI. Specific embodiments for implementing this system will be described below.

[1330] System Configuration

[1331] This system mainly consists of three main components: a server, a terminal, and a user.

[1332] Server: The central location for data collection, analysis, and results management. This is where the generative AI model runs, generating hunger statistics and supply lists for each region.

[1333] Terminal: A device where users access the system, enter data, and view results. Here, analytical results are displayed through a visual dashboard.

[1334] Users: Primarily companies and individuals who use the platform to participate in relief activities. Users provide supplies and funds, enter data, and obtain records and credits for their donations.

[1335] Program processing

[1336] Data collection and analysis

[1337] The server will first collect hunger status, food inventory data, infrastructure status, and logistics data from multiple public agencies and non-governmental organizations (NGOs), including access to APIs and data storage.

[1338] The collected data is fed into a generative AI model, which analyzes the data and generates a regional hunger situation and a list of needed supplies.

[1339] Data Visualization

[1340] The analysis results are displayed in the form of a visual dashboard. The server creates visualization components such as graphs and maps based on the generated data and sends them to the device.

[1341] The dashboard displayed on the device allows users to see at a glance the hunger situation in each region, the types of supplies needed, and aid priorities.

[1342] Supply and matching

[1343] Users input details of the supplies and funds they can provide through their terminals and submit the information, which is then stored on the server.

[1344] The server uses a generative AI model to calculate the optimal recipient of aid based on the supply information provided by users, thereby matching the needs of each region with the supplies provided by users.

[1345] Logistics management

[1346] The server calculates the optimal support route and method, and develops an efficient logistics plan. Specifically, it evaluates delivery options by air, sea, and land, and selects the most efficient delivery route.

[1347] Details of the logistics plan will be communicated to the relevant logistics partners.

[1348] Crediting and Feedback

[1349] Once the assistance activity is completed, the server receives a local acknowledgement of receipt and adds a "credit" to the user's account.

[1350] The server also provides feedback on the results of the support activities, providing reference information for the user when planning their next support.

[1351] Specific examples

[1352] For example, consider a company that can donate 5,000 kg of rice. A company representative logs into the platform using a device and enters the details of the donation (e.g., 5,000 kg of rice). The server then receives the data, and based on the collected hunger situation data, the generative AI model calculates the optimal recipient (e.g., a specific region in Africa). The results are displayed on a dashboard, where the company representative can check the progress of the donation and logistics plans.

[1353] Once the donation is complete, receipt confirmation data from the local area is sent to the server and credits are added to the company's account. At the same time, a feedback report is provided to help the company decide whether to donate next time. In this way, the entire system operates efficiently and aims to contribute to solving hunger.

[1354] The processing flow will be explained below.

[1355] Step 1:

[1356] The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public institutions and non-governmental organizations (NGOs) by sending requests to the United Nations Hunger Database API and the World Bank's data storage.

[1357] Step 2:

[1358] The server stores the collected data in an internal database, and when storing it, it formats and converts the data to ensure consistency.

[1359] Step 3:

[1360] The server inputs the data retrieved from the database into the generative AI model, which then begins analysis. The generative AI model identifies the hunger situation in each region, a list of necessary supplies, infrastructure shortages, and other information, and generates a report.

[1361] Step 4:

[1362] The server converts the analysis results into a visual dashboard, specifically by creating visualization components such as graphs and maps and designing a user-friendly interface.

[1363] Step 5:

[1364] The server then sends the generated visual dashboard to the device, where users can access the dashboard and check the hunger situation in each region, the types of supplies needed, and the priority of aid.

[1365] Step 6:

[1366] The user uses the terminal to input and submit details of the goods and funds available for donation, including the quantity, quality, and period of time available.

[1367] Step 7:

[1368] The server receives the material data obtained from the user, stores it in a database, and converts the stored data into an appropriate format for analysis.

[1369] Step 8:

[1370] The server uses a generative AI model to match the items provided by users with local needs, specifically by comparing the provided items with local hunger data and identifying the best recipients.

[1371] Step 9:

[1372] Based on the matching results, the server calculates the appropriate delivery route and method for the goods, analyzes multiple logistics options (air transport, sea transport, land transport) and formulates an efficient transportation plan.

[1373] Step 10:

[1374] The server notifies the relevant logistics partners of the details of the logistics plan and begins preparations for delivery, monitoring the delivery status in real time and making adjustments as necessary.

[1375] Step 11:

[1376] Once the relief activities are completed, the server receives receipt confirmation data from the site, and uses this data to confirm the completion of the relief activities.

[1377] Step 12:

[1378] The server will add "credits" to the user's account for the support, which will then be reflected in the user's profile.

[1379] Step 13:

[1380] The server provides the user with feedback on the results of the support activities, along with analytical data to help them improve their next support efforts. The feedback report is displayed on the user's dashboard.

[1381] The above are the specific program processing steps of the system for implementing the invention.

[1382] Example 1

[1383] 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."

[1384] This invention relates to a platform system for effectively solving the problem of hunger, which occurs frequently around the world. Currently, it is difficult to grasp the hunger situation, procure and supply necessary supplies, and efficiently manage the delivery of supplies and relief activities, which hinders the speed and effectiveness of relief activities. Other issues include low transparency and reliability of relief activities, and a lack of appropriate feedback to donors.

[1385] 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.

[1386] In this invention, the server includes: means for collecting hunger status, food inventory data, infrastructure status, and logistics data; means for analyzing the collected data using a generative AI model to generate a list of hunger status and needed supplies for each region; means for visualizing the generated analysis results on a visual dashboard and sending them to the user's device; means for users to input the supplies and funds they can provide and match supplies with recipients based on that information; means for analyzing the recommended delivery routes and methods for supplies using an advanced algorithm, formulating an efficient logistics plan, and notifying appropriate logistics partners; and means for issuing credits for relief activities using blockchain technology and providing feedback to users after the relief activities are completed. This enables effective and prompt resolution of hunger issues, improved transparency and reliability of relief activities, and appropriate feedback to donors.

[1387] "Hunger Situation" is data showing the degree of food shortages and malnutrition in each region.

[1388] "Food inventory data" refers to data that indicates information regarding the current amount and type of food in stock in a particular area or facility.

[1389] "Infrastructure status" refers to data that indicates the status of basic facilities and services such as roads, communications, power supply, and water supply.

[1390] "Logistics data" refers to data that indicates information related to the transportation and delivery of goods, including routes, means of transportation, and delivery schedules.

[1391] "Generative AI models" refer to artificial intelligence algorithms or programs used to analyze collected data and make predictions or optimizations.

[1392] A "visual dashboard" is an interface for visually displaying analysis results, and includes visual components such as graphs and maps.

[1393] "User terminal" refers to a device used by a user to access and operate the system, including a personal computer or smartphone.

[1394] "Resource matching" refers to the process by which aid providers optimally allocate available resources and funds to areas and facilities in need.

[1395] "Logistics planning" is a plan for the efficient transportation and delivery of goods, and refers to the process of determining the optimal routes and means.

[1396] "Logistics Partner" refers to a company or organization that partners with us to carry out the transportation or delivery of goods.

[1397] "Blockchain technology" is a distributed database technology used to ensure data transparency and prevention of tampering.

[1398] "Credits" refer to digital points or certificates that indicate recognition and reward for support activities.

[1399] "Feedback" refers to the process of providing evaluation information about the effectiveness and results of support activities.

[1400] This invention relates to a platform system that aims to effectively solve the problem of hunger using a generative AI model. This system consists of three entities: a server, a terminal, and a user. Specific embodiments for implementing this system are described below.

[1401] System Configuration

[1402] Server: The central location for data collection, analysis, and results management. This is where the generative AI model runs, generating hunger statistics and supply lists for each region.

[1403] Terminal: A device where users access the system, enter data, and view results. Here, analytical results are displayed through a visual dashboard.

[1404] Users: Primarily companies and individuals who use the platform to participate in relief activities. Users provide supplies and funds, enter data, and obtain records and credits for their donations.

[1405] Data collection and analysis

[1406] The server will collect hunger, food inventory, infrastructure, and logistics data from multiple public and non-governmental organizations, utilizing APIs and cloud storage.

[1407] For example, the server accesses a public institution's database via an API to obtain the latest hunger situation data, which is then stored in cloud storage such as AWS S3.

[1408] The collected data is fed into a generative AI model (specifically, using TensorFlow), which analyzes the data and generates a regional hunger alert and a list of supplies needed, using statistical models and machine learning algorithms.

[1409] Data Visualization

[1410] The server uses the D3.js library to convert the generated analysis results into visual components such as graphs and maps, and the generated visual data is sent to the device in JSON format.

[1411] The device displays a visual dashboard that allows users to interactively check the hunger situation map and supply status in real time on their browser.

[1412] Supply and matching

[1413] Users input details of the goods and funds they can provide through their devices, such as "donating 5,000 kg of rice." This data is sent to the server via API and stored in a database (e.g., MySQL).

[1414] The server uses a generative AI model to match the material information provided by users with the most appropriate recipients. This matching process compares the needs of each region with the materials provided to make the best match.

[1415] Logistics management

[1416] The server uses Dijkstra's algorithm to calculate the optimal relief route and delivery method, which determines the most efficient delivery route and ensures that relief supplies reach their destination as quickly as possible.

[1417] The results of the optimal delivery route calculation are sent to logistics partners via API, allowing them to carry out efficient logistics planning.

[1418] Crediting and Feedback

[1419] Once the donation is completed, the server receives local confirmation data and adds "credits" to the user's account, a process that utilizes blockchain technology to ensure transparency and reliability.

[1420] The server also provides the user with feedback on the results of the support activities and information that can be used as reference for planning the next support. The feedback report is sent from the server to the terminal, and the user can refer to it when planning the next support.

[1421] Examples of prompt statements

[1422] "Generate the best recipients and necessary supplies list based on the following data: Hunger situation data (areas A, B, C), Food inventory data (areas A, B, C), Infrastructure situation (areas A, B, C), Logistics data (areas A, B, C)"

[1423] This will ensure that the entire system is run efficiently, and is expected to contribute to solving the problem of hunger.

[1424] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1425] Step 1:

[1426] Data collection

[1427] The server collects hunger, food inventory, infrastructure, and logistics data from multiple public and non-governmental organizations, using API endpoints to access each organization's database and retrieve the latest data.

[1428] Input: Data collected via API (hunger status, food stocks, infrastructure, logistics)

[1429] Output: Raw data stored in cloud storage (e.g. AWS S3)

[1430] Specific operation: The server periodically executes an API call and saves the acquired data to the specified cloud storage.

[1431] Step 2:

[1432] Data analysis

[1433] The server inputs the collected data into a generative AI model, specifically using TensorFlow to analyze it and generate a hunger situation and a list of supplies needed.

[1434] Input: Datasets of hunger, food inventory, infrastructure, and logistics retrieved from cloud storage.

[1435] Output: Hunger report and list of supplies needed for each analyzed region

[1436] Specific operation: The server feeds the collected data into the TensorFlow model, calculates the analysis results, and stores the generated report and list of required supplies in a database.

[1437] Step 3:

[1438] Data visualization

[1439] The server converts the generated analysis results into a visual dashboard, generating graphs, maps, and other data using the D3.js library, and sends them to the device in JSON format.

[1440] Input: Analysis results from the generative AI model (hunger situation report, list of needed supplies)

[1441] Output: Visual data in JSON format

[1442] Specific operation: The server uses the analysis results to generate heat maps and bar charts using D3.js, converts them to JSON format, saves them, and sends them to the terminal as appropriate.

[1443] Step 4:

[1444] Viewing the Dashboard

[1445] The terminal receives the JSON data sent from the server and displays it as a visual dashboard.

[1446] Input: Visual data in JSON format from the server

[1447] Output: A visual dashboard displayed in the user's browser

[1448] Specific operation: The terminal parses the received JSON and displays it as an interactive dashboard using the D3.js library.

[1449] Step 5:

[1450] Enter and submit supply information

[1451] The user uses a terminal to input detailed information about the supplies and funds that can be provided and sends this information to the server.

[1452] Input: Information about supplies and funds entered by the user (e.g., 5,000 kg of rice)

[1453] Output: Material information sent to the server

[1454] Specific operation: The user enters the necessary information into a form on the device, which is then sent to the server via the API and stored in a database.

[1455] Step 6:

[1456] Executing the matching algorithm

[1457] The server uses a generative AI model to calculate the optimal recipient of support based on the material information provided by the user.

[1458] Input: Provided supplies information, hunger situation data, list of required supplies

[1459] Output: List of optimal support recipients

[1460] Specific operation: The server inputs the supply information into the TensorFlow model, and calculates the optimal support destination as the analysis result. This information is stored in a database.

[1461] Step 7:

[1462] Delivery route calculation and notification

[1463] The server uses advanced algorithms to calculate efficient delivery routes and methods for supplies and notifies logistics partners.

[1464] Input: List of optimal support recipients and logistics data

[1465] Output: Delivery plan notification to logistics partners

[1466] Specific operation: The server calculates the optimal delivery route using Dijkstra's algorithm and notifies the logistics partner of this information via API.

[1467] Step 8:

[1468] Confirmation of support activities and issuance of credits

[1469] The user receives confirmation data from the site to confirm the completion of the relief activity and sends it to the server, which issues credits to the user's account based on the confirmation data and provides feedback.

[1470] Input: Receipt confirmation data from the site

[1471] Output: Credits to user accounts and feedback reports

[1472] Specific operation: The server records the receipt confirmation data using blockchain technology, adds credits to the user, and generates and sends a feedback report.

[1473] (Application example 1)

[1474] 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."

[1475] Hunger is a global issue, threatening the very foundations of life in many regions. To combat this, adequate supplies and efficient logistics planning are essential. However, managing aid activities and calculating optimal supply delivery routes is complex and consumes significant human resources. Furthermore, the lack of real-time inventory management and visibility into delivery routes increases the risk of aid delays. This makes it difficult to provide fast and effective aid to famine-stricken areas.

[1476] 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.

[1477] In this invention, the server includes a means for collecting data on the famine situation, food inventory data, infrastructure status, and logistics data, a means for analyzing the collected data with a generative AI model to generate a list of the famine situation and supplies needed by region, and a means for visualizing the generated analysis results on a visual dashboard and sending them to the user's device, thereby enabling more efficient and rapid response in relief activities.

[1478] The invention further includes a means for users to input the supplies and funds they can provide and match supplies with recipients based on that information, a means for analyzing the recommended delivery route and method for the supplies and formulating an efficient logistics plan, a means for issuing credits for the relief activities and providing feedback to the user after the relief is completed, a means using a smart device for displaying inventory status and delivery routes in real time, and a means for supporting the picking and delivery of relief supplies at the logistics center. This improves work efficiency within the logistics center and enables fast and effective relief to famine-stricken areas.

[1479] "Hunger situation" refers to the level of food shortages in a particular area and the situation of people suffering from malnutrition.

[1480] "Food inventory data" refers to data that includes inventory information for food, beverages, and other items provided as relief supplies.

[1481] "Infrastructure status" refers to the current condition and performance of infrastructure such as roads, transportation, and communication networks related to relief activities.

[1482] "Logistics data" refers to information relating to the transportation of goods, including information such as the point of departure, destination, transportation method, route, and time.

[1483] A "generative AI model" is an artificial intelligence model that analyzes collected data and generates specific outputs (for example, the hunger situation in each region and a list of needed supplies).

[1484] A "visual dashboard" refers to a visual user interface for displaying analyzed data in an easy-to-read format.

[1485] "Terminal" means a device (such as a smartphone, tablet, or computer) through which a user accesses the system, enters data, and views results.

[1486] "Matching" is the process of matching available supplies and funds with the needs of the recipient and finding the optimal combination.

[1487] A "logistics plan" is a plan to determine efficient routes and methods for delivering supplies and to ensure optimal relief activities.

[1488] "Credits" are evaluation points or rewards given to users who perform support activities.

[1489] "Feedback" is information provided to users reporting on the results of support activities and areas for improvement.

[1490] "Smart devices" are wearable electronic devices such as glasses and headsets that have internet connectivity and high-performance sensors.

[1491] "Picking" refers to the task of selecting specific items from inventory at a logistics center.

[1492] This invention relates to a platform system that aims to effectively solve the problem of hunger using a generative AI model. The system of the present invention is mainly composed of three entities: a server, a terminal, and a user.

[1493] System Configuration

[1494] Server: Collects data, analyzes, and manages the results. This server runs a generative AI model that generates hunger situations and lists of supplies for each region.

[1495] Terminal: A device where users access the system, enter data, and view results. Here, analytical results are displayed through a visual dashboard.

[1496] Users: Primarily companies and individuals who use the system to participate in relief activities. Users provide and input supplies and funds, and obtain records and credits for their support.

[1497] Program Overview

[1498] 1. Data Collection and Analysis

[1499] The server first collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public institutions and non-governmental organizations (NGOs). This data collection includes access to APIs and data storage. The collected data is then fed into a generative AI model, which analyzes the data and generates regional hunger status and a list of needed supplies.

[1500] 2. Data visualization

[1501] The analysis results are displayed in the form of a visual dashboard. The server creates visualization components such as graphs and maps based on the generated data and sends them to the device. The dashboard displayed on the device allows users to see at a glance the hunger situation in each region, the types of supplies needed, and aid priorities.

[1502] 3. Supply and matching

[1503] Users input detailed information about the supplies and funds they can provide through their devices and submit it. This information is stored on the server. The server then uses a generative AI model based on the supply information provided by the user to calculate the optimal recipient of support. This allows the system to match the needs of each region with the supplies provided by the user.

[1504] 4. Logistics management

[1505] The server calculates the optimal support route and method, and develops an efficient logistics plan. Specifically, it evaluates air, sea, and land delivery options and selects the most efficient delivery route. The details of the logistics plan are then communicated to the relevant logistics partners.

[1506] 5. Crediting and Feedback

[1507] Once the relief effort is completed, the server receives a local confirmation of receipt, credits the user's account, and provides feedback on the success of the relief effort, providing reference information for the user when planning their next relief effort.

[1508] Specific examples

[1509] For example, let's say a company can donate 5,000 kg of rice. The company's representative logs into the platform using a terminal and enters the details of the goods to be donated (e.g., 5,000 kg of rice). The server then receives this data, and the generative AI model calculates the optimal recipient of the donation based on the collected hunger situation data. The results are displayed on a dashboard, where company representatives can check the progress of the donation and logistics plans. Once the donation is completed, confirmation of receipt from the site is sent to the server, and credits are added to the company's account. At the same time, a feedback report is provided to help with the next donation. In this way, the entire system operates efficiently, aiming to contribute to resolving hunger.

[1510] Prompt Sentence Examples

[1511] "Please describe the overview and functionality of the hunger relief logistics management app. Include a specific example of a program that retrieves data from Firebase, analyzes it using a TensorFlow model, calculates optimal delivery routes using the Google Maps API, and displays the data on smart glasses using OpenCV."

[1512] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1513] Step 1:

[1514] Data collection

[1515] Subject: Server

[1516] The server collects hunger status, food inventory data, infrastructure status, and logistics data from public institutions and non-governmental organizations (NGOs) through APIs and data storage. The collected data is stored as raw data. Specifically, the server sends requests to the APIs of each data provider and imports the returned data.

[1517] Input: Send API request

[1518] Output: Save various data

[1519] Step 2:

[1520] Data analysis

[1521] Subject: Server

[1522] The server inputs the collected data into a generative AI model, which analyzes the data and generates a regional hunger situation and a list of needed supplies. Specifically, the server runs the model using TensorFlow to obtain predictions.

[1523] Input: Collected data

[1524] Output: Analysis results (hungry situation by region and list of necessary supplies)

[1525] Step 3:

[1526] Data Visualization

[1527] Subject: Server

[1528] The server uses the generated analysis results to create a visual dashboard and sends it to the terminal. The data is visualized in the form of graphs, maps, etc. Specifically, the server generates the dashboard using libraries such as OpenCV and D3.js and sends it to the terminal via WebSocket.

[1529] Input: Analysis results

[1530] Output: Visual dashboard

[1531] Step 4:

[1532] Supply and matching

[1533] Subject: User and Server

[1534] Users enter information about the supplies and funds they can provide through their devices and send it to the server. The server receives this information and uses a generative AI model to calculate the optimal recipient of aid. Specifically, users enter information into a web form, and the server then analyzes it again using the AI ​​model.

[1535] Input: Material and financial information

[1536] Output: Best Support

[1537] Step 5:

[1538] Logistics planning

[1539] Subject: Server

[1540] The server calculates the optimal support route and method, and develops an efficient logistics plan. It evaluates delivery options by air, sea, and land, and selects the most efficient delivery route. Specifically, the server calculates the delivery route using the Google Maps API and notifies the logistics partner of the results.

[1541] Input: Information on the provided supplies and recipients

[1542] Output: Efficient logistics planning

[1543] Step 6:

[1544] Crediting and Feedback

[1545] Subject: Server

[1546] Once a relief effort is completed, local receipt confirmation data is sent to the server. The server uses this information to add credits to the user's account. It also provides feedback on the success of the relief effort, providing reference information for the user when planning their next relief effort. Specifically, the server analyzes the receipt confirmation data, updates the user's credits, and generates a report.

[1547] Input: Receipt confirmation data

[1548] Output: Credits added, feedback report

[1549] Step 7:

[1550] Real-time display on smart devices

[1551] Subject: Smart device (terminal)

[1552] The smart device displays real-time inventory status and delivery routes. To assist with the picking and delivery of relief supplies at the logistics center, the device incorporates OpenCV and Google Maps API. Specifically, the smart glasses overlay information on the user's field of vision based on data sent from the server.

[1553] Input: Shipping and inventory data from the server

[1554] Output: Real-time display on smart devices

[1555] 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.

[1556] This invention combines an emotion engine with a platform system that aims to effectively solve the problem of hunger using generative AI. Specific embodiments for implementing this system are described below.

[1557] System Configuration

[1558] This system is mainly composed of three entities: a server, a terminal, and a user. It also incorporates an emotion engine that recognizes the user's emotions.

[1559] Server: This is the central location for data collection, analysis, emotion recognition, and result management. This is where the generative AI model runs, generating regional hunger alerts and lists of supplies, and the emotion engine analyzes user feedback.

[1560] Terminal: A device where users access the system, input data, and view results. Here, analysis results are displayed through a visual dashboard, and users' emotional data is also entered.

[1561] Users: These are primarily companies and individuals who use the platform to participate in relief efforts. Users provide supplies and funds, enter emotional feedback, and receive records of their support and credits.

[1562] Program processing

[1563] Data collection and analysis

[1564] The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public agencies and non-governmental organizations (NGOs), including access to APIs and data storage.

[1565] The collected data is fed into a generative AI model, which analyzes the data and generates a regional hunger situation and a list of needed supplies.

[1566] Data Visualization

[1567] The analysis results are displayed in the form of a visual dashboard. The server creates visualization components such as graphs and maps based on the generated data and sends them to the device.

[1568] The dashboard displayed on the device allows users to see at a glance the hunger situation in each region, the types of supplies needed, and aid priorities.

[1569] Supply and matching

[1570] Users input details of the supplies and funds they can provide through their terminals and submit the information, which is then stored on the server.

[1571] The server uses a generative AI model to calculate the optimal recipient of aid based on the supply information provided by users, thereby matching the needs of each region with the supplies provided by users.

[1572] Logistics management

[1573] The server calculates the optimal support route and method, and develops an efficient logistics plan. Specifically, it evaluates delivery options by air, sea, and land, and selects the most efficient delivery route.

[1574] Details of the logistics plan will be communicated to the relevant logistics partners.

[1575] Crediting and Feedback

[1576] Once the relief effort is completed, the server receives local receipt confirmation data, which is used to confirm the relief effort has been completed and add a "credit" to the user's account.

[1577] The server also provides feedback on the results of the support activities, providing reference information for the user when planning their next support.

[1578] Emotion Recognition and Customized Feedback

[1579] The server uses an emotion engine to collect and analyze the user's emotional data when the user provides feedback, thereby identifying how the user feels about the support activity.

[1580] Based on the emotion data, the server provides customized feedback to the user, including encouragement and suggestions for improvement based on the user's emotions.

[1581] The analysis results of the emotion engine are used to optimize the next relief operation plan.

[1582] Specific examples

[1583] For example, consider a company that can donate 5,000 kg of rice. A company representative logs into the platform using a device and enters the details of the donation (e.g., 5,000 kg of rice). The server then receives the data, and based on the collected hunger situation data, the generative AI model calculates the optimal recipient (e.g., a specific region in Africa). The results are displayed on a dashboard, where the company representative can check the progress of the donation and logistics plans.

[1584] Once the donation is completed, receipt confirmation data from the site is sent to the server, and credits are added to the company's account. At the same time, the server uses an emotion engine to analyze the emotions of the person in charge. For example, if there are many positive emotions about the donation activity, the server will provide feedback emphasizing its success. Conversely, if there is a lot of feedback pointing out areas for improvement, the server will provide a report containing suggestions to help optimize the next donation activity. In this way, the entire system operates efficiently, aiming to increase user satisfaction while contributing to solving hunger.

[1585] The processing flow will be explained below.

[1586] Step 1:

[1587] The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public institutions and non-governmental organizations (NGOs) by sending requests to the United Nations Hunger Database API and the World Bank's data storage.

[1588] Step 2:

[1589] The server stores the collected data in an internal database. When storing the data, it formats and converts the data to maintain consistency. For example, it unifies data in different formats and extracts necessary indicators.

[1590] Step 3:

[1591] The server inputs the data retrieved from the database into the generative AI model, which then begins analysis. The generative AI model identifies the hunger situation in each region, a list of necessary supplies, infrastructure shortages, and other information, and generates a report.

[1592] Step 4:

[1593] The server converts the analysis results into a visual dashboard, specifically by creating visualization components such as graphs and maps and designing a user-friendly interface.

[1594] Step 5:

[1595] The server then sends the generated visual dashboard to the device, where users can access the dashboard and check the hunger situation in each region, the types of supplies needed, and the priority of aid.

[1596] Step 6:

[1597] The user uses the terminal to input and submit details of the goods and funds available for donation, including the quantity, quality, and period of time available.

[1598] Step 7:

[1599] The server receives the material data obtained from the user, stores it in a database, and converts the stored data into an appropriate format for analysis.

[1600] Step 8:

[1601] The server uses a generative AI model to match the items provided by users with local needs, specifically by comparing the provided items with local hunger data and identifying the best recipients.

[1602] Step 9:

[1603] Based on the matching results, the server calculates the appropriate delivery route and method for the goods, analyzes multiple logistics options (air transport, sea transport, land transport) and formulates an efficient transportation plan.

[1604] Step 10:

[1605] The server notifies the relevant logistics partners of the details of the logistics plan and begins preparations for delivery, monitoring the delivery status in real time and making adjustments as necessary.

[1606] Step 11:

[1607] Once the relief activities are completed, the server receives receipt confirmation data from the site, and uses this data to confirm the completion of the relief activities.

[1608] Step 12:

[1609] The server will add "credits" to the user's account for the support, which will then be reflected in the user's profile.

[1610] Step 13:

[1611] The server provides the user with feedback on the results of the support activities, along with analytical data to help them improve their next support efforts. The feedback report is displayed on the user's dashboard.

[1612] Step 14:

[1613] When a user inputs feedback, the server uses an emotion engine to collect the user's emotion data, for example, by analyzing the text of the feedback or voice input and classifying the emotion as positive, negative, etc.

[1614] Step 15:

[1615] The server analyzes the user's feedback in detail based on the emotion data analyzed by the emotion engine, thereby identifying how the user feels about the support activities.

[1616] Step 16:

[1617] The server then provides customized feedback to the user based on the emotional data, such as highlighting achievements when emotions are predominantly positive, or providing specific areas for improvement when emotions are predominantly negative.

[1618] Step 17:

[1619] The server uses the analysis results of the emotion engine to reflect user feedback in the next support activity plan, specifically identifying support methods to increase user motivation and issues that need improvement.

[1620] The above are the specific program processing steps of the system for implementing the invention.

[1621] Example 2

[1622] 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."

[1623] Hunger is becoming a serious problem around the world, and appropriate aid is urgently needed, especially in resource-limited areas. The current system involves a complex and cumbersome process, including the provision and delivery of aid supplies, on-site receipt confirmation, and feedback to donors, making it difficult to manage efficiently. Furthermore, emotional feedback on aid activities is not fully utilized, making it difficult to motivate donors. Therefore, a comprehensive system is needed that can provide effective aid against hunger and improve donor satisfaction.

[1624] 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.

[1625] In this invention, the server includes: means for collecting hunger status, food inventory data, infrastructure status, and logistics data; means for analyzing the collected data using a generative AI model to generate a list of hunger status and needed supplies for each region; means for visualizing the generated analysis results on a visual dashboard and sending them to a user's device; means for users to input the supplies and funds they can provide and match the supplies with recipients based on that information; means for analyzing the delivery route and method for the recommended supplies and formulating an efficient logistics plan; means for obtaining local receipt confirmation data after the completion of the support and issuing credits to the user's account; and means for collecting and analyzing emotional data when the user provides feedback and providing customized feedback. This makes it possible to provide effective support for hunger issues and further increase the satisfaction of supporters by analyzing users' emotions and customizing the feedback.

[1626] "Hunger Situation" is information that indicates the state and severity of food shortages in a particular area.

[1627] "Food inventory data" is information that indicates the current food supply and stockpiles in a particular region or organization.

[1628] "Infrastructure status" refers to information that indicates the status of the infrastructure needed to carry out relief activities, such as transportation and storage facilities, in a particular area.

[1629] "Logistics data" refers to information related to logistics activities, such as delivery routes, transportation methods, and delivery schedules for goods.

[1630] A "generative AI model" is an artificial intelligence model that performs analysis and predictions based on accumulated data, and is used to analyze hunger situations and select the most appropriate recipients of aid.

[1631] A "visual dashboard" is an interface for visually displaying analysis results, using graphs and maps to enable users to easily understand the data.

[1632] "Support recipient" refers to the target region or organization that receives supplies and funds.

[1633] "Matching" is the process of comparing the supplies and financial information of the aid provider with the needs of the recipient to determine the optimal combination.

[1634] "Logistics planning" is the activity of formulating schedules and procedures for delivering goods via the optimal routes and means.

[1635] "Credits" are evaluation points or rewards given to a user after completing a support activity, and serve as an incentive for the next support activity.

[1636] "Emotion data" is information that quantifies or classifies the emotional state or tendency shown by the user when providing feedback.

[1637] "Customized feedback" refers to feedback messages and advice that are individually tailored based on the user's emotional data, in order to optimize the next support activity.

[1638] This invention combines an emotion engine with a platform system that aims to effectively solve the hunger problem using a generative AI model. Specific embodiments for implementing this system are described below.

[1639] System Configuration

[1640] This system is mainly composed of three entities: a server, a terminal, and a user. It also incorporates an emotion engine that recognizes the user's emotions.

[1641] Server: This is the central location for data collection, analysis, emotion recognition, and result management. This is where the generative AI model runs to generate regional hunger alerts and lists of supplies, and the emotion engine analyzes user feedback. Software used includes Python, TensorFlow, Node.js, and Express.

[1642] Terminal: This is the device where users access the system, input data, and view results. Here, analysis results are displayed through a visual dashboard, and user sentiment data is also entered. Visualization is done using D3.js and Tableau.

[1643] Users: These are primarily companies and individuals who use the platform to participate in relief efforts. Users provide supplies and funds, enter emotional feedback, and receive records of their support and credits.

[1644] Program processing

[1645] Data collection and analysis

[1646] The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public institutions and NGOs. This collection is done using access to APIs and data storage. For example, it retrieves the latest hunger status data from the API of an international organization.

[1647] The collected data is fed into a generative AI model, which analyzes the data and generates a regional hunger situation and a list of needed supplies. Specifically, the model is built using Python and TensorFlow.

[1648] Data Visualization

[1649] The analysis results are displayed in the form of a visual dashboard. The server creates visualization components such as graphs and maps using D3.js or Tableau based on the generated data and sends them to the device.

[1650] The dashboard displayed on the device allows users to check the hunger situation in each region, the types of supplies needed, and aid priorities.

[1651] Supply and matching

[1652] Users input details of the supplies and funds they can provide through their terminals and submit them. For example, a company representative might input "5,000 kg of rice" into the platform.

[1653] The server uses a generative AI model to calculate the optimal recipient of aid based on the supply information provided by the user, effectively matching local needs with the supplies provided by the user.

[1654] Logistics management

[1655] The server calculates the optimal support route and method, develops an efficient logistics plan, and evaluates air, sea, and land delivery options to select the most efficient delivery route. Logistics partners are notified via a RESTful API.

[1656] Credit issuance and confirmation of support completion

[1657] Once the relief effort is complete, the server receives local receipt confirmation data, such as a receipt confirmation report sent from the site via API.

[1658] The server uses this data to add credits to the user's account, and also provides feedback on the results of the support activity, providing reference information for the user when planning their next support.

[1659] Emotion Recognition and Customized Feedback

[1660] The server uses an emotion engine to collect and analyze the user's emotional data when the user provides feedback, and provides customized feedback including encouragement and suggestions for improvement according to the user's emotions.

[1661] Data obtained from the emotion engine is used to optimize the next outreach plan.

[1662] Specific examples

[1663] For example, consider a company that can donate 5,000 kg of rice. The company's representative logs into the platform using a terminal and enters the details of the donation (e.g., 5,000 kg of rice). The server then receives the data, and based on the collected hunger situation data, the generative AI model calculates the optimal recipient (e.g., a specific region) of the donation. The results are displayed on a dashboard, where the company's representative can check the progress of the donation and the logistics plan. The log data contains the following prompt:

[1664] Example prompt sentence:

[1665] "We can provide 5,000 kg of rice. Please calculate the optimal recipient and propose a delivery plan."

[1666] Once the donation is completed, a receipt confirmation is sent from the site to the server, and a credit is added to the company's account. At the same time, the server uses an emotion engine to analyze the emotions of the person in charge. For example, if there are many positive emotions about the donation activity, the server will provide feedback that highlights the success. Conversely, if there is a lot of feedback pointing out areas for improvement, the server will provide a report with suggestions to help optimize the next donation activity.

[1667] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1668] Step 1: Data collection

[1669] The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public organizations and NGOs. Specifically, the server accesses API endpoints to retrieve this data. This input data includes real-time hunger status data and logistics data from international organizations. The collected data is stored in a database on the server. To collect data, the server uses a Python script to access the API using the requests library. As a result, the retrieved data is stored on the server in JSON format.

[1670] Step 2: Data analysis

[1671] The server inputs the collected data into a generative AI model. Specifically, the generative AI model built with TensorFlow inputs hunger situation data and food inventory data for analysis. The input data includes the hunger situation and inventory situation for each region. The server uses the generative AI model to calculate the hunger situation and list of needed supplies for each region. The output data is saved on the server as the analyzed hunger situation and supply list. This analysis is performed by running the analyze_data_with_AI() function, which supplies the data to the generative AI model.

[1672] Step 3: Visualize the data

[1673] The server displays the generated analysis results in the form of a visual dashboard. Specifically, the server generates graphs and maps using D3.js or Tableau and sends them to the terminal. The input data includes the JSON data of the analysis results. The server visualizes the data and converts it into a format that is easy for users to understand. The output data is sent to the terminal as visualized graphs and maps. For this process, the create_visuals_from_data() function is used to generate visualization components using D3.js.

[1674] Step 4: Enter your supply

[1675] The user inputs detailed information about the supplies and funds that can be provided through the terminal. Specifically, the type and amount of supplies are entered into the input form on the terminal and sent to the server. The input data includes the supplies that the user will provide (e.g., 5,000 kg of rice). The terminal sends this data to the server via the send button. The server stores the received data in a database. The user enters detailed information using the input form and sends the information to the server by clicking the "Send" button.

[1676] Step 5: Matching supplies with recipients

[1677] The server inputs the supply information provided by the user into the generative AI model and calculates the optimal recipients of support. Specifically, the server matches the supply data provided by the user with the collected hunger situation data. The input data includes the supply data provided by the user and the hunger situation data. The server uses the generative AI model to calculate the optimal recipients of support and generates a list of optimal recipients as output data. For this, it uses the match_supply_to_demand() function.

[1678] Step 6: Logistics Management

[1679] The server calculates the optimal support route and method and creates an efficient logistics plan. Specifically, it evaluates air, sea, and land options and selects the most efficient delivery route. Input data includes a list of optimal support destinations and logistics options. The server creates a delivery plan using a logistics optimization algorithm and generates optimal route information as output data. This information is notified to logistics partners via a RESTful API. The server optimizes the logistics route using the optimize_logistics_route() function.

[1680] Step 7: Credit issuance and confirmation of support completion

[1681] Once the relief activity is completed, the server obtains the local receipt confirmation data. Specifically, the receipt confirmation data sent from the local site is obtained using an API and processed on the server. The input data includes the local receipt confirmation report. The server adds credits to the user's account based on the receipt confirmation data. The output data is the updated user credit information. This process uses the verify_delivery() function to obtain the receipt confirmation data and add credits.

[1682] Step 8: Emotion Recognition and Customized Feedback

[1683] The server uses an emotion engine to collect and analyze emotion data when a user provides feedback. Specifically, it analyzes the feedback submitted by the user and extracts emotion data. The input data includes the user's feedback. The server generates a customized feedback message based on the analysis results. The output data is the customized feedback provided to the user. This process uses the analyze_feedback_emotions() function to perform emotion analysis.

[1684] (Application example 2)

[1685] 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."

[1686] To effectively solve hunger problems and efficiently manage relief supplies, it is necessary to quickly analyze collected data and develop distribution plans that meet local needs. It is also important to monitor the progress of relief activities in real time and provide appropriate feedback to relief workers. However, these processes in current systems are partial and fragmented, posing challenges to improving overall efficiency and user satisfaction.

[1687] 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 collecting hunger status, food inventory data, infrastructure status, and logistics data; means for analyzing the collected data using a generative AI model to generate a list of hunger status and needed supplies for each region; means for visualizing the generated analysis results on a visual dashboard and sending them to the user's terminal; means for users to input the supplies and funds they can provide and match supplies with recipients based on that information; means for calculating and executing the optimal logistics route by autonomous vehicles; means for issuing credits for the relief activities and providing feedback to the user after the relief activities are completed; and means for using an emotion engine to collect and analyze emotion data of the user's feedback and provide customized feedback based on that data. This enables more efficient relief activities and more effective distribution of supplies.

[1688] "Hunger Situation" is data showing the state of food shortages in a given area and their causes and effects.

[1689] "Food inventory data" is information about the amount and type of food currently available.

[1690] "Infrastructure status" is information that indicates the state of infrastructure related to transportation, such as logistics networks, roads, and bridges.

[1691] "Logistics data" refers to information related to the transportation of goods, including transportation routes, transportation means, transportation times, and the like.

[1692] A "generative AI model" is an artificial intelligence model used to analyze collected data and generate regional hunger situations and lists of needed supplies.

[1693] A "visual dashboard" is an interface for visually displaying analysis results, providing information in the form of graphs, maps, etc.

[1694] "User terminal" means a device used by a user to access and operate the system, including a smartphone or computer.

[1695] An "autonomous vehicle" is a vehicle that uses AI technology to operate autonomously and transport goods.

[1696] A "credit" is a unit of evaluation or reward given to a user who participates in a support activity.

[1697] An "emotion engine" is a software component that analyzes a user's feedback and identifies their emotional state.

[1698] "Customized feedback" refers to personalized feedback provided based on the user's emotional data.

[1699] This invention is a system that combines an emotion engine with a platform system that aims to effectively solve the hunger problem. This system has a wide range of functions as shown below.

[1700] System Configuration

[1701] This system is mainly composed of three entities: a server, a terminal, and a user. It also incorporates an emotion engine that recognizes the user's emotions.

[1702] Server: This is the central location for data collection, analysis, emotion recognition, and result management. This is where the generative AI model runs, generating regional hunger alerts and lists of supplies, and the emotion engine analyzes user feedback.

[1703] Software used: Generative AI model, emotion engine

[1704] Hardware used: High-performance server

[1705] Terminal: A device through which users access the system, input data, and view results. Analysis results are displayed through a visual dashboard, and users' emotional data is also entered.

[1706] Hardware used: smartphones, computers, smart glasses, etc.

[1707] Software used: Visual Dashboard

[1708] Users: These are primarily companies and individuals who use the platform to participate in relief efforts. Users provide supplies and funds, enter emotional feedback, and receive records of their support and credits.

[1709] Program processing explanation

[1710] 1. The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public institutions and non-governmental organizations (NGOs). The collected data is input into a generative AI model to generate hunger status and a list of needed supplies for each region.

[1711] 2. The analysis results are displayed in the form of a visual dashboard. The server creates visualization components such as graphs and maps based on the generated data and sends them to the device. The dashboard displayed on the device allows users to see at a glance the hunger situation in each region, the types of supplies needed, and aid priorities.

[1712] 3. The user inputs and submits detailed information about the supplies and funds they can provide via their device. This information is stored on the server. Based on the supply information provided by the user, the server uses a generative AI model to calculate the optimal recipient of support. This allows the system to match the needs of each region with the supplies provided by the user.

[1713] 4. Calculate optimal support routes and methods to develop efficient logistics plans, including evaluating air, sea, and land delivery options and selecting the most efficient delivery route, including autonomous vehicle delivery plans.

[1714] 5. Once the donation is completed, the server receives local receipt confirmation data. Based on this data, the server confirms the donation's completion and credits the user's account. The server also provides feedback on the success of the donation, providing reference information for the user when planning their next donation.

[1715] 6. The emotion engine is used to analyze the user's feedback and identify how the user feels about the support activity. Based on the emotion data, the server provides the user with customized feedback, including encouragement and suggestions for improvement based on the user's emotions.

[1716] Examples of concrete examples and prompts

[1717] For example, if a company can provide 5,000 kg of rice, the company's representative would enter the following:

[1718] Example prompt sentence:

[1719] We will provide 5000 kg of rice.

[1720] The server then receives the data, and the generative AI model calculates the optimal recipient of aid based on the collected hunger situation data. The results are displayed on a dashboard, allowing company personnel to check the progress of aid and logistics plans. Once aid is completed, receipt confirmation data from the site is sent to the server, and credits are added to the company's account. An emotion engine also analyzes the emotions of personnel and provides appropriate feedback.

[1721] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1722] Specific processing steps of the program

[1723] Step 1:

[1724] The server collects hunger status, food inventory data, infrastructure status, and logistics data from multiple public institutions and non-governmental organizations (NGOs) via APIs. The input data is often provided in JSON format. The server centralizes and stores this data. Specifically, it periodically sends HTTP requests to each data source to retrieve the latest data. The output is a centralized database of hunger-related data.

[1725] Step 2:

[1726] The server inputs the collected data into a generative AI model and analyzes the data. The generative AI model uses a machine learning algorithm to generate the hunger situation and list of needed supplies for each region. The input is the data collected in step 1, and the output is the analyzed hunger situation and list of needed supplies. Specifically, data preprocessing (filling in missing values, standardizing data, etc.) is performed, and the data is then input into the model.

[1727] Step 3:

[1728] The server converts the generated analysis results into a data format for the visual dashboard. The converted data is sent to the terminal in a format that is easy to understand visually, such as a graph or map. The input is the analysis results, and the output is data for displaying the visual dashboard. Specifically, the data is converted into HTML and JavaScript format and sent to the terminal via a Web API.

[1729] Step 4:

[1730] The user enters detailed information about the supplies and funds the...

Claims

1. means of collecting hunger status, food inventory data, infrastructure status, and logistics data; The collected data will be analyzed using a generative AI model to generate regional hunger situations and lists of necessary supplies. A means for visualizing the generated analysis results on a visual dashboard and transmitting the results to a user's device; A means for users to input the supplies and funds they can provide, and match supplies with recipients based on that information; A means of analyzing the routes and methods of delivery of the recommended supplies and developing an efficient logistics plan; After the support is completed, a means for issuing credit for the support activity and providing feedback to the user; A system including:

2. 10. The system of claim 1, further comprising means for recommending optimal food supply and relief efforts for a particular region based on the collected and analyzed data.

3. 10. The system of claim 1, further comprising means for notifying logistics partners and monitoring delivery status.

Images