system

Abstract

We provide the system. [Solution] As a means of data collection, there is a means of acquiring disaster information, weather information, and human habitation information, formatting the data, and storing it in a database. A method for predicting the necessary supplies during a disaster using machine learning algorithms, A means of visualizing the demand information for supplies on maps, etc., and updating it in real time, A means of notifying supporters of the need for assistance and information on available supplies on their devices, A means by which users can select the type of support they receive and view their history, A system that includes a means of incorporating a portion of donations as an administrative fee into a new business model.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The opacity of the demand and supply of donations and relief supplies during disasters causes unbalanced support in many regions. Also, in shelters and the like, the distribution of relief supplies may not be adequately managed, and as a result of improper distribution, there may be a shortage of relief supplies or, conversely, an excess of supplies. In such situations, there are problems with the efficiency and fairness of relief activities, and many people cannot receive the necessary support.

Means for Solving the Problems

[0005] This invention collects a wide variety of disaster and population information as a data collection method, and uses machine learning algorithms to predict the demand for supplies based on this data. It provides a system that visualizes these prediction results and notifies supporters in real time. Furthermore, this notification enables supporters to make optimal support decisions, and by incorporating a portion of the donations as a management fee into a new business model, it ensures corporate sustainability. The aim is to improve the efficiency and fairness of support activities.

[0006] A "data collection method" refers to a system for collecting disaster information, weather information, and human habitation information, formatting them, and storing them in a database.

[0007] A "machine learning algorithm" is a computational method that learns from past data to predict the supplies needed during a disaster.

[0008] "Demand forecasting" is the activity of estimating in advance the amount of relief supplies needed in the event of a disaster.

[0009] A "visualization method" is a system that visually displays predicted material demand information using maps or dashboards.

[0010] A "notification method" is a system that sends information about the need for assistance and available supplies to the supporter's device.

[0011] A "supporter" is an individual or group that provides support during a disaster through means such as supplying goods or making donations.

[0012] "Administrative fees" are the costs incurred to set aside a portion of donations for operating expenses and profits.

[0013] A "business model" is a methodology for solving social problems while pursuing economic profit. [Brief explanation of the drawing]

[0014] [Figure 1]It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

MODE FOR CARRYING OUT THE INVENTION

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the 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.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0028] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention is a system that integrates multiple technological elements to streamline and improve the fairness of disaster relief activities. This system primarily consists of data collection, machine learning algorithms, information visualization, notification, supporter selection, and business model construction. Details of each technological element are provided below.

[0036] First, the server collects disaster information, weather information, and residential information from various data sources. This utilizes public databases and real-time APIs. The collected data is then formatted and stored in a database.

[0037] Next, the server uses machine learning algorithms to analyze the collected data. This allows it to predict the demand for relief supplies in the event of a disaster. This prediction utilizes a model based on data from past disaster patterns.

[0038] The prediction results are visualized by the server in an interactive user interface such as a dashboard. For example, a map can be used to color-code the shortages of supplies, intuitively displaying the situation in that region.

[0039] The server also notifies the supporter's terminal of this information in real time. The terminal provides the user with the received information and displays a list of areas and supplies that need assistance.

[0040] Based on the information provided through the device, users can decide which supplies to provide and in what quantities. In addition, they can review the history of their support and understand the results of their past assistance efforts.

[0041] Furthermore, the server will allocate a portion of the donations as an administrative fee to support the creation of a sustainable business model. This business model will also include the implementation of incentive programs to ensure the company's sustainability.

[0042] As a concrete example, consider a scenario where a major earthquake occurs in a certain region. The server immediately collects data and predicts the demand for drinking water and food. The prediction results are notified to the terminal, and the user makes a choice regarding assistance. This process enables rapid and appropriate assistance activities.

[0043] As described above, the system of the present invention makes it possible to effectively provide disaster relief by combining technical elements.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server collects relevant data such as disaster information, weather information, and population density from public databases and real-time APIs. This data is formatted and preprocessed, including imputation of missing values ​​and normalization. It is then stored in a database in preparation for subsequent processing.

[0047] Step 2:

[0048] The server uses the collected data as input to run a machine learning algorithm, which then uses it to predict the demand for supplies during disasters. The AI ​​model learns from past disaster patterns and is continuously updated to improve prediction accuracy.

[0049] Step 3:

[0050] The server uses visualization tools to display information on charts and maps based on predicted demand data for supplies. This visualization is updated in real time on the dashboard, visually indicating areas where supplies are in short supply.

[0051] Step 4:

[0052] The server pushes important information to the devices registered by the supporters. This notification includes details about the areas where assistance is needed and the types of supplies required.

[0053] Step 5:

[0054] The device provides the user with the received information. The user reviews the displayed information and decides how much material support to provide. Based on this information, the user can make an appropriate donation or provide materials.

[0055] Step 6:

[0056] Users can utilize a feature that allows them to check their support history on their device. This enables them to understand how the support they have provided is being used, ensuring transparency in their support activities.

[0057] Step 7:

[0058] The server incorporates a portion of the total donation amount as an administrative fee into its business model to ensure profitability as a company. This business model may include incentive programs for supporters to encourage participation in future charitable activities.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] While there is a need to improve the efficiency and fairness of support activities during disasters, conventional systems have faced challenges in collecting sufficient data, accurately forecasting demand, and providing timely information. Furthermore, building sustainable business models has been difficult.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes means for acquiring disaster information, weather information, and housing information as an information acquisition device, formatting the data, and storing it on a storage medium; means for estimating the demand for supplies during a disaster using a computational algorithm; and means for visualizing the demand information on a map and updating it in real time. This enables efficient and equitable disaster relief. Furthermore, by optimizing data processing using a generative model and incorporating a portion of donations as processing costs into the business model, it becomes possible to build a sustainable business model.

[0064] An "information acquisition device" is a device that acquires disaster information, weather information, and housing information, formats the data, and stores it on a storage medium.

[0065] A "computational algorithm" is a mathematical method used to estimate the demand for supplies during a disaster using collected data.

[0066] "Demand information" refers to information regarding the types and quantities of supplies needed in a specific area during a disaster.

[0067] "Visualization on a map" is a method of using maps to show the shortage of supplies and the areas that need assistance.

[0068] "Real-time updates" means that information is updated immediately as soon as data is acquired.

[0069] A "generative model" is a model that utilizes AI technology to learn generalized data patterns and make more accurate predictions.

[0070] A "storage medium" is a physical or electronic medium used to store data.

[0071] A "sustainable business model" is a business method that brings economic benefits to an organization in a way that can be sustained over the long term.

[0072] A "reward program" is a mechanism that provides incentives to support participants to encourage specific behaviors.

[0073] This invention is a system that enables efficient and equitable support activities during disasters. In this system, a server plays a central role. The server acquires disaster information, weather information, and housing information using public databases and real-time APIs. The server, functioning as an information acquisition device, formats this data and stores it on a storage medium. Specifically, the server collects weather data through the OpenWeatherMap API and acquires disaster information from local government databases.

[0074] The collected data is analyzed using machine learning algorithms. The server uses a generative AI model to learn from past disaster data and predict specific supply needs during disasters. This prediction calculates the demand for necessary supplies such as drinking water and food. For example, by referencing current weather conditions based on past typhoon data, the system can accurately estimate the supplies needed in disaster-stricken areas.

[0075] The analysis results are updated in real time by the server and visualized on a map. The server uses the map to color-code the areas where supplies are lacking, indicating which regions are in particular need of assistance. This makes it easier for users to intuitively understand the information. The server also notifies information terminals of detailed information regarding the need for assistance. Mobile push notifications and web notifications are used as needed.

[0076] Based on this information, users decide which supplies to provide and in what quantities. The user's device allows them to review their aid history, enabling them to understand what kind of assistance they have provided and to which regions.

[0077] Furthermore, the server incorporates a portion of donations as processing costs into its business model. This process supports the creation of a sustainable business model and includes an incentive program for supporters. This allows users to receive rewards such as points for their support activities.

[0078] As a concrete example, if a major earthquake occurs in a certain region, the server will immediately collect data on the damage and weather, and predict the demand for drinking water and food. The prediction results will be notified to the user's terminal, and the user can then quickly take action to provide assistance based on that information. An example of a prompt message for the generating AI model would be, "Based on past disaster data for region X, please predict the supplies that will be needed in the next week."

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The server, acting as an information acquisition device, retrieves disaster information, weather information, and housing information from public databases and real-time APIs. The input for this step consists of the latest information from multiple data sources. The acquired raw data is converted to a format and stored on the system's storage medium. Specifically, weather information is retrieved in JSON format from the OpenWeatherMap API, and the necessary items are extracted and stored in the database.

[0082] Step 2:

[0083] The server begins analyzing the collected data using a generative AI model. The input for this step is the disaster and weather data formatted in the previous step. The server uses machine learning algorithms to predict the demand for relief supplies during a disaster based on past disaster data. Through this process, it is possible to specifically identify areas where drinking water and food are particularly needed. The output is regional demand forecast data for supplies.

[0084] Step 3:

[0085] The server visualizes the analysis results on an interactive dashboard. The input for this step is the analyzed demand forecast data. The server displays this data on a map using color coding, visually highlighting areas of shortage. Specifically, areas shown in red indicate severe shortages, making it easy for users to understand intuitively. The output is visualized support information accessible to the user.

[0086] Step 4:

[0087] The server notifies information terminals of information generated in real time. The input for this step is information from a visualized map. Push notifications to mobile devices and pop-up notifications to web browsers are used as notification methods. Specifically, it sends specific alerts such as "There is a shortage of drinking water in area X." The output is detailed disaster relief information that can be viewed on the user's device.

[0088] Step 5:

[0089] The user decides which supplies to provide and in what quantities based on the information provided via the terminal. The input for this step is information about the assistance notified by the server. The user can open the terminal application, select the assistance content, and view the history. For example, the user might input the instruction, "Send 100 liters of drinking water to area X." The output is the specific assistance action based on the user's decision.

[0090] Step 6:

[0091] To ensure the sustainability of system operations, the server allocates a portion of donations as processing costs and establishes a business model. The input for this step is donation information from users. The server adds points to user accounts based on the donation amount, maintaining an incentive program. Specifically, processing is carried out based on the rule "award 1 point for every 100 yen donated." The output is incentive data to promote sustainable support activities.

[0092] (Application Example 1)

[0093] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0094] Disaster relief efforts require the rapid acquisition of accurate information and the appropriate allocation of resources based on that information. However, conventional systems are insufficient in terms of the speed of information gathering and notification, as well as the flexibility in selecting the type of support to provide. In particular, there are still challenges in providing real-time crisis management information using mobile devices. Furthermore, there is room for improvement in securing incentives for supporters and in the management system for donations.

[0095] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0096] In this invention, the server includes, as a data collection means, means for acquiring disaster information, weather information, and human habitation information, formatting the data, and storing it in a data management device; means for predicting the resources needed during a disaster using a machine learning algorithm; and means for providing crisis information to mobile information terminals in real time and issuing visual and audible warnings. This makes it possible to quickly and accurately acquire the information necessary for support activities and to provide effective notifications to supporters.

[0097] A "data collection means" is a device for acquiring disaster information, weather information, and human habitation information, formatting this data, and storing it in a data management device.

[0098] A "machine learning algorithm" is a method for learning past disaster patterns and predicting the resources needed during a disaster.

[0099] "Visualization methods" refer to technologies that visually display resource demand information using maps or other means, and update it in real time as it changes.

[0100] A "notification means" is a function that informs the support device of the need for support and resource information.

[0101] "Selection and confirmation means" refers to a mechanism that allows users to choose the type of support they received and review their history.

[0102] An "economic model" is a design that allows for sustainable business operations by allocating a portion of donations as administrative fees.

[0103] A "mobile information terminal" refers to a portable device that can be moved around and has the function of providing crisis information in real time and issuing warnings visually and audibly.

[0104] "Geospatial information" refers to information related to geographical location and is used to quickly grasp the situation during disasters.

[0105] A "merit program" is a system of incentives offered to supporters to encourage their participation in support activities.

[0106] The system for implementing this invention functions primarily around a server. The server first acquires disaster information, weather information, and human habitation information using data collection means, and then formats and stores them in a data management device. The collected data is analyzed by machine learning algorithms to predict the demand for necessary resources during a disaster. This prediction is visualized in real time on a map and presented to the user.

[0107] The server also has the ability to notify mobile devices of crisis information in real time and issue warnings using both visual and audible means. This allows users to immediately understand the crisis and choose appropriate support actions. For example, when an earthquake occurs in a certain area, predictions of shortages of drinking water and food can be quickly conveyed to the user in conjunction with a map.

[0108] Finally, supporters will benefit from a merit program to encourage active participation. This will create a mechanism to incorporate a portion of donations as an administrative fee into the new economic model. All of these processes will be server-centric and operated quickly and accurately.

[0109] By utilizing a generative AI model, efficient support activities are facilitated through prompt messages such as the following: "We are developing an application that uses machine learning to predict the demand for relief supplies in real time during disasters. Please tell us about the main functions of this application and the methods for user notifications."

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] The server retrieves disaster information, weather information, and human habitation information from multiple data sources. Input for this data comes from various APIs and public databases. The server formats this data and stores it in a unified format in a data management device. At this stage, the data is organized and immediately accessible.

[0113] Step 2:

[0114] The server applies a machine learning algorithm based on the stored data. The input is the data organized in Step 1, and the output is a prediction of resource demand during a disaster. The server uses past disaster patterns as a model to improve prediction accuracy. Specifically, it performs data calculations to simulate shortages of drinking water and food in a particular region.

[0115] Step 3:

[0116] The server visualizes the prediction results in real time. The input is the prediction data from step 2, and the output is resource demand information displayed on a map. The server provides information through a user interface, visually indicating shortages with colors and icons.

[0117] Step 4:

[0118] The server notifies the supporter's terminal of the information. The input at this time is the geographical information visualized in step 3, and the output is an alarm message displayed on the terminal's screen. The terminal issues an alarm using both visual and auditory information to prompt the supporter to take swift action.

[0119] Step 5:

[0120] The user selects support activities based on the information presented. The input consists of disaster situation and resource information displayed on the terminal, and the user decides which support to provide based on their own judgment. The output is the selected support content and a record of the history. Specifically, the user's actions send an indication of their intention to provide support supplies to the server.

[0121] Step 6:

[0122] The server applies a merit program and encourages supporter participation. The inputs are the supporter's selection history and donation amount, and the output is an incentive for the supporter. Based on an economic model, a portion of the donations is allocated as an administrative fee, ensuring sustainable support activities.

[0123] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0124] This invention is a system that combines an emotion engine to streamline, equitably, and effectively carry out disaster relief activities. The system mainly consists of data collection, machine learning algorithms, information visualization, notification, emotion recognition, supporter selection, and business model construction.

[0125] First, the server collects disaster information, weather information, and population information from various data sources. This data is formatted and stored in a database. Next, the server uses machine learning algorithms to predict the demand for supplies and builds a model based on past disaster patterns. The predicted information is visualized by the server on a dashboard and displayed intuitively using maps and other visuals. This visualization makes it possible to see at a glance which areas need assistance and which supplies are lacking.

[0126] In addition, the server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine evaluates the user's current emotional state based on their past response data and adjusts notification content and incentive programs accordingly. For example, if the server recognizes positive emotions, it will send proactive messages regarding support. This function facilitates the provision of support in a way that is optimal for each individual supporter.

[0127] Furthermore, the server tracks emotional states in real time to determine the appropriate timing for providing support. The emotion engine functions as a tool to support decision-making regarding material provision and donations, playing a role in guiding user decision-making.

[0128] As a concrete example, suppose a flood occurs in a certain area. The server quickly collects data and predicts the demand for drinking water. At this time, the emotion engine analyzes the emotions of the helpers and sends notifications to their devices prompting appropriate assistance as needed. For example, a message such as, "Many victims need assistance. Your help can make a big difference," might be sent. In this way, emotion-based information is provided, maximizing the effectiveness of the assistance.

[0129] This system aims not only to improve the efficiency of support activities but also to enable emotion-based, personalized support, thereby increasing social and economic value.

[0130] The following describes the processing flow.

[0131] Step 1:

[0132] The server collects disaster information, weather data, and human habitation information from public databases and APIs. The collected data is formatted and stored in a database. This provides a foundation for understanding the latest situation.

[0133] Step 2:

[0134] The server analyzes collected data using machine learning algorithms. It utilizes models trained on past disaster patterns to predict demand for supplies. These predictions are updated in real time, contributing to a rapid response during disasters.

[0135] Step 3:

[0136] The server visually displays predicted material demand data on a map. The displayed dashboard color-codes areas with high demand, allowing users to see at a glance where assistance is needed.

[0137] Step 4:

[0138] The server references the user's past emotional data and uses an emotion engine to analyze their current emotional state. This information is used to determine what kind of support the user desires.

[0139] Step 5:

[0140] The server sends customized messages to the device based on the user's emotional state. For example, if positive emotions are detected, an encouraging message will be sent. Incentives tailored to the emotions may also be offered.

[0141] Step 6:

[0142] The terminal displays a customized message sent from the server to the user. Based on this, the user decides what supplies to provide, in what quantities, or how much to donate.

[0143] Step 7:

[0144] Users can view their support history on their device to understand how their past support has been utilized. This historical information helps users plan how they will provide support in the future.

[0145] Step 8:

[0146] The server will allocate a portion of the donations as a management fee and incorporate it into a new business model. This model will include an incentive program to encourage future charitable activities.

[0147] (Example 2)

[0148] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0149] During disasters, there is a need to supply relief supplies quickly and accurately, and to carry out relief activities efficiently and effectively. Conventional systems have problems such as insufficient information gathering and visualization of relief efforts, and difficulty in promoting relief activities while considering the emotional state of individual supporters. This invention aims to solve these problems and realize efficient and emotion-based relief.

[0150] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0151] In this invention, the server includes information gathering means for collecting disaster-related information and storing it in a standard format, analysis means for predicting the supply and demand of goods using machine learning technology, and information visualization means for visually displaying and updating supply and demand information. This enables rapid information gathering and analysis, allows for the provision of emotion-based, personalized support, and improves the efficiency and effectiveness of support activities.

[0152] An "information gathering means" is a system component that has the function of collecting disaster-related information, organizing it in a standard format, and storing it.

[0153] "Analysis tools" refer to system components that analyze data collected using machine learning techniques to predict the supply and demand of goods.

[0154] An "information visualization tool" is a system component that visually displays analyzed supply and demand information so that users can understand it intuitively.

[0155] "Emotion recognition functionality" is a technology that analyzes the user's emotional state and provides personalized information notifications based on that analysis.

[0156] "Selection and confirmation means" refers to a system component that has the function of allowing supporters to decide what kind of support to provide and to check past support history.

[0157] "Commercial means" refers to system components that integrate a portion of donations as a fee into a new business model.

[0158] This invention is a system in which a server, a terminal, and a user work together in cooperation, and aims to efficiently and effectively carry out support activities during disasters. This system consists of information gathering functions, analysis functions, information visualization functions, and emotion recognition functions.

[0159] The server retrieves disaster information, weather information, and population information from various data sources. Specifically, it collects information from internet APIs, social networking services, and real-time data provided by local governments. This information is organized in a standard format and stored in a database.

[0160] Based on this data, the server uses machine learning algorithms to predict the supply and demand of goods. The software used will primarily include machine learning libraries such as TENSORFLOW® and PyTorch. The server learns from past disaster data and builds a predictive model to estimate the types and quantities of supplies needed.

[0161] The analyzed information is visualized by the server and displayed in charts and maps. Tools such as Google® Maps API and D3.js are used for visualization. This allows users to understand at a glance which areas require particular attention.

[0162] Through its emotion recognition function, the server analyzes the user's emotional state. The results of this analysis are sent to the user's device as personalized notification information. The emotion engine uses a machine learning model trained on past response data to quantify the user's emotions and propose appropriate notifications and incentives. These notifications maximize the user's motivation for support activities.

[0163] As a concrete example, consider a case where a flood occurs in a certain area. The server quickly collects and analyzes data from the affected area and predicts the demand for drinking water. At this time, the emotion engine analyzes the emotions of the helpers and sends notifications to the device that encourage the most appropriate support based on that analysis. For example, a message such as, "Many victims need help. Your support can make a big difference," might be sent. Other examples of prompts using the generative AI model include, "Please tell me how to streamline disaster relief activities," and "How can I build a model to predict the demand for relief supplies during a flood?"

[0164] This system enables rapid and effective support activities by providing individual supporters with emotionally appropriate support based on collected data and analytical information.

[0165] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0166] Step 1:

[0167] The server retrieves input data from multiple data sources. This input data includes disaster information, weather data, demographic data, and so on. The server processes this information into a standard format and outputs the formatted data to the database. Specifically, it retrieves data via an internet API and then processes and formats it.

[0168] Step 2:

[0169] The server takes formatted data stored in a database as input and applies a machine learning algorithm. The data calculation generates a predictive model based on past disaster data to forecast the supply and demand of goods. The output is the predicted supply and demand information; specifically, it outputs a list of the types and quantities of goods that will be needed next. The system uses a machine learning library to train the data and perform predictions.

[0170] Step 3:

[0171] The server receives predicted supply and demand information as input and passes it to visualization software. The output is specific information displayed as visualized maps and graphs. In operation, it uses a visualization library to display information on a map and updates the visual dashboard.

[0172] Step 4:

[0173] The server receives emotion data from the user database as input and performs analysis using an emotion engine. As part of data processing based on the input data, it generates a model using the user's past emotional response data to evaluate the user's emotional state. The output is a notification message optimized for the emotional state. The process involves executing an emotion recognition algorithm and generating notification content based on the analysis results.

[0174] Step 5:

[0175] The server takes the analysis results obtained from the emotion engine as input and sends notifications to the user's device as needed. Based on the input data, it generates personalized notification messages and outputs them to the device. As a concrete example of its operation, it sends a message to the device such as "Your help is needed. Your help will be a great help," encouraging the user to engage in support activities. In this process, prompt messages can also be utilized using a generative AI model.

[0176] (Application Example 2)

[0177] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0178] Traditional food delivery services have struggled to suggest the most suitable products based on customer emotions and individual needs, limiting their ability to improve customer satisfaction. Furthermore, the difficulty in accurately predicting deliveries while considering weather and congestion also limited service efficiency. Solving these challenges is necessary to optimize the customer experience and improve service efficiency and profitability.

[0179] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0180] In this invention, the server includes, as a data collection means, means for acquiring weather information, human residence information, order history, and customer sentiment information, formatting the data, and storing it in an information storage means; means for predicting demand using machine learning algorithms and building a model based on past patterns; and means for visually displaying demand information and weather information and communicating it intuitively to service providers. This enables optimal product suggestions that take into account the customer's emotional state and accurate delivery predictions according to weather and congestion levels.

[0181] "Data collection means" refers to technology that has the function of acquiring weather information, human residence information, order history, and customer sentiment information, formatting the data, and storing it in an information storage means.

[0182] A "machine learning algorithm" is a technology that uses mathematical methods to predict demand based on past patterns.

[0183] "Visual display means" refers to technologies for visually displaying demand information and weather information and communicating it intuitively to service providers.

[0184] A "sentiment analysis engine" is a technology that analyzes a customer's emotional state and generates individually optimized notification content.

[0185] An "incentive program" is a technology that provides benefits and rewards to users to encourage service usage.

[0186] "Information storage means" refers to technology that systematically organizes acquired data and stores it so that it can be used for later analysis and processing.

[0187] In this application, the system first uses a server to acquire weather information, human residence information, order history, and customer sentiment information using data collection means. Then, this information is formatted and stored in an information storage means. A relational database management system (RDBMS) can be used for data formatting.

[0188] The server then uses machine learning algorithms to predict demand based on past patterns. Machine learning libraries such as Scikit-learn are used in this process. The predicted demand and weather information are visually displayed on a dashboard using visual visualization tools. Data visualization tools such as Plotly can be used to implement this dashboard.

[0189] Furthermore, an emotion analysis engine is used to analyze the customer's emotional state and send notifications optimized for the user's information device. NLP libraries (such as NLTK and spaCy) are used for emotion analysis. The notification content is sent as a push notification to smartphones and other devices.

[0190] Users can select products suggested by the application based on the notifications sent and check their history. The server also has a function to implement incentive programs for users and promote service usage.

[0191] As a concrete example, on a rainy day, a server might send a message saying, "We recommend a hot pot dish." In this case, the following prompt would be used for the AI ​​generation model: "Based on the current weather information and the customer's order history, suggest the most suitable food delivery. Analyze how the customer's sentiment has changed compared to the previous year, and generate a notification message based on the results."

[0192] This will enable the provision of individualized services tailored to customer needs, leading to improved customer satisfaction and increased service efficiency.

[0193] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0194] Step 1:

[0195] The server uses data collection methods to gather weather information APIs, human location data, user order history data, and customer sentiment data. It uses online-accessible APIs and user input data as input, storing them in a unified database format. As output, it saves data in a format suitable for searching and analysis.

[0196] Step 2:

[0197] The server uses the collected data to perform demand forecasting using machine learning algorithms. Specifically, it uses libraries such as Scikit-learn to learn demand patterns from past order history and weather conditions. The input is a formatted dataset, and the output is the creation of a demand forecasting model. The resulting demand forecast is then used in the next processing step.

[0198] Step 3:

[0199] The server displays demand forecast and weather information on a dashboard using visual display means. Inputs are demand forecasting models and collected weather information, which are visualized in graph and map formats using visualization tools such as Plotly. Outputs are intuitively understandable visual data, simplifying data interpretation.

[0200] Step 4:

[0201] The server uses a sentiment analysis engine to analyze the customer sentiment data it receives. The input is text data from customer reviews and comments, and NLP is used to quantify or categorize the sentiment. The output is a sentiment score, which is used in the next step to generate notification content.

[0202] Step 5:

[0203] The server generates and sends push notification messages to the user's device based on emotional state and demand forecasts. The input is the emotional score and demand forecast results, and a generative AI model is used to generate notification messages based on prompts. The output is the notification message displayed on the user's device.

[0204] Step 6:

[0205] The user selects recommended products and confirms the order based on notifications received on their device. The input is a notification message from the server, and the user selects products using the application. The output is the selected products and their order information, which the server receives and processes.

[0206] Step 7:

[0207] The server provides incentive programs based on order history and customer sentiment to encourage service usage. Inputs are the customer's past order history and sentiment score, and an algorithm is used to present appropriate rewards. Outputs include the provision of new incentives and the resulting expected increase in service usage.

[0208] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0209] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0210] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0211] [Second Embodiment]

[0212] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0213] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0214] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0215] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0216] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0217] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0218] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0219] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0220] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0221] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0222] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0223] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0224] This invention is a system that integrates multiple technological elements to streamline and improve the fairness of disaster relief activities. This system primarily consists of data collection, machine learning algorithms, information visualization, notification, supporter selection, and business model construction. Details of each technological element are provided below.

[0225] First, the server collects disaster information, weather information, and residential information from various data sources. This utilizes public databases and real-time APIs. The collected data is then formatted and stored in a database.

[0226] Next, the server uses machine learning algorithms to analyze the collected data. This allows it to predict the demand for relief supplies in the event of a disaster. This prediction utilizes a model based on data from past disaster patterns.

[0227] The prediction results are visualized by the server in an interactive user interface such as a dashboard. For example, a map can be used to color-code the shortages of supplies, intuitively displaying the situation in that region.

[0228] The server also notifies the supporter's terminal of this information in real time. The terminal provides the user with the received information and displays a list of areas and supplies that need assistance.

[0229] Based on the information provided through the device, users can decide which supplies to provide and in what quantities. In addition, they can review the history of their support and understand the results of their past assistance efforts.

[0230] Furthermore, the server will allocate a portion of the donations as an administrative fee to support the creation of a sustainable business model. This business model will also include the implementation of incentive programs to ensure the company's sustainability.

[0231] As a concrete example, consider a scenario where a major earthquake occurs in a certain region. The server immediately collects data and predicts the demand for drinking water and food. The prediction results are notified to the terminal, and the user makes a choice regarding assistance. This process enables rapid and appropriate assistance activities.

[0232] As described above, the system of the present invention makes it possible to effectively provide disaster relief by combining technical elements.

[0233] The following describes the processing flow.

[0234] Step 1:

[0235] The server collects relevant data such as disaster information, weather information, and population density from public databases and real-time APIs. This data is formatted and preprocessed, including imputation of missing values ​​and normalization. It is then stored in a database in preparation for subsequent processing.

[0236] Step 2:

[0237] The server uses the collected data as input to run a machine learning algorithm, which then predicts the demand for supplies during a disaster. The AI ​​model learns from past disaster patterns and is continuously updated to improve prediction accuracy.

[0238] Step 3:

[0239] The server uses visualization tools to display information on charts and maps based on predicted demand data for supplies. This visualization is updated in real time on the dashboard, visually indicating areas where supplies are in short supply.

[0240] Step 4:

[0241] The server pushes important information to the devices registered by the supporters. This notification includes details about the areas where assistance is needed and the types of supplies required.

[0242] Step 5:

[0243] The device provides the user with the received information. The user reviews the displayed information and decides how much material support to provide. Based on this information, the user can make an appropriate donation or provide materials.

[0244] Step 6:

[0245] Users can utilize a feature that allows them to check their support history on their device. This enables them to understand how the support they have provided is being used, ensuring transparency in their support activities.

[0246] Step 7:

[0247] The server incorporates a portion of the total donation amount as an administrative fee into its business model to ensure profitability as a company. This business model may include incentive programs for supporters to encourage participation in future charitable activities.

[0248] (Example 1)

[0249] Next, we will describe Example 1. 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."

[0250] While there is a need to improve the efficiency and fairness of support activities during disasters, conventional systems have faced challenges in collecting sufficient data, accurately forecasting demand, and providing timely information. Furthermore, building sustainable business models has been difficult.

[0251] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0252] In this invention, the server includes means for acquiring disaster information, weather information, and housing information as an information acquisition device, formatting the data, and storing it on a storage medium; means for estimating the demand for supplies during a disaster using a computational algorithm; and means for visualizing the demand information on a map and updating it in real time. This enables efficient and equitable disaster relief. Furthermore, by optimizing data processing using a generative model and incorporating a portion of donations as processing costs into the business model, it becomes possible to build a sustainable business model.

[0253] An "information acquisition device" is a device that acquires disaster information, weather information, and housing information, formats the data, and stores it on a storage medium.

[0254] A "computational algorithm" is a mathematical method used to estimate the demand for supplies during a disaster using collected data.

[0255] "Demand information" refers to information regarding the types and quantities of supplies needed in a specific area during a disaster.

[0256] "Visualization on a map" is a method of using maps to show the shortage of supplies and the areas that need assistance.

[0257] "Real-time updates" means that information is updated immediately as soon as data is acquired.

[0258] A "generative model" is a model that utilizes AI technology to learn generalized data patterns and make more accurate predictions.

[0259] A "storage medium" is a physical or electronic medium used to store data.

[0260] A "sustainable business model" is a business method that brings economic benefits to an organization in a way that can be sustained over the long term.

[0261] A "reward program" is a mechanism that provides incentives to support participants to encourage specific behaviors.

[0262] This invention is a system that enables efficient and equitable support activities during disasters. In this system, a server plays a central role. The server acquires disaster information, weather information, and housing information using public databases and real-time APIs. The server, functioning as an information acquisition device, formats this data and stores it on a storage medium. Specifically, the server collects weather data through the OpenWeatherMap API and acquires disaster information from local government databases.

[0263] The collected data is analyzed using machine learning algorithms. The server uses a generative AI model to learn from past disaster data and predict specific supply needs during disasters. This prediction calculates the demand for necessary supplies such as drinking water and food. For example, by referencing current weather conditions based on past typhoon data, the system can accurately estimate the supplies needed in disaster-stricken areas.

[0264] The analysis results are updated in real time by the server and visualized on a map. The server uses the map to color-code the areas where supplies are lacking, indicating which regions are in particular need of assistance. This makes it easier for users to intuitively understand the information. The server also notifies information terminals of detailed information regarding the need for assistance. Mobile push notifications and web notifications are used as needed.

[0265] Based on this information, users decide which supplies to provide and in what quantities. The user's device allows them to review their aid history, enabling them to understand what kind of assistance they have provided and to which regions.

[0266] Furthermore, the server incorporates a portion of donations as processing costs into its business model. This process supports the creation of a sustainable business model and includes an incentive program for supporters. This allows users to receive rewards such as points for their support activities.

[0267] As a concrete example, if a major earthquake occurs in a certain region, the server will immediately collect data on the damage and weather, and predict the demand for drinking water and food. The prediction results will be notified to the user's terminal, and the user can then quickly take action to provide assistance based on that information. An example of a prompt message for the generating AI model would be, "Based on past disaster data for region X, please predict the supplies that will be needed in the next week."

[0268] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0269] Step 1:

[0270] The server, acting as an information acquisition device, retrieves disaster information, weather information, and housing information from public databases and real-time APIs. The input for this step consists of the latest information from multiple data sources. The acquired raw data is converted to a format and stored on the system's storage medium. Specifically, weather information is retrieved in JSON format from the OpenWeatherMap API, and the necessary items are extracted and stored in the database.

[0271] Step 2:

[0272] The server begins analyzing the collected data using a generative AI model. The input for this step is the disaster and weather data formatted in the previous step. The server uses machine learning algorithms to predict the demand for relief supplies during a disaster based on past disaster data. Through this process, it is possible to specifically identify areas where drinking water and food are particularly needed. The output is regional demand forecast data for supplies.

[0273] Step 3:

[0274] The server visualizes the analysis results on an interactive dashboard. The input for this step is the analyzed demand forecast data. The server displays this data on a map using color coding, visually highlighting areas of shortage. Specifically, areas shown in red indicate severe shortages, making it easy for users to understand intuitively. The output is visualized support information accessible to the user.

[0275] Step 4:

[0276] The server notifies information terminals of information generated in real time. The input for this step is information from a visualized map. Push notifications to mobile devices and pop-up notifications to web browsers are used as notification methods. Specifically, it sends specific alerts such as "There is a shortage of drinking water in area X." The output is detailed disaster relief information that can be viewed on the user's device.

[0277] Step 5:

[0278] The user decides which supplies to provide and in what quantities based on the information provided via the terminal. The input for this step is information about the assistance notified by the server. The user can open the terminal application, select the assistance content, and view the history. For example, the user might input the instruction, "Send 100 liters of drinking water to area X." The output is the specific assistance action based on the user's decision.

[0279] Step 6:

[0280] To ensure the sustainability of system operations, the server allocates a portion of donations as processing costs and establishes a business model. The input for this step is donation information from users. The server adds points to user accounts based on the donation amount, maintaining an incentive program. Specifically, processing is carried out based on the rule "award 1 point for every 100 yen donated." The output is incentive data to promote sustainable support activities.

[0281] (Application Example 1)

[0282] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0283] In disaster relief activities, the acquisition of prompt and accurate information and appropriate resource allocation based on it are required. However, in conventional systems, the speed of information collection and notification and the degree of freedom in selecting relief measures are insufficient, and there are still issues in providing real-time crisis management information using mobile terminals. Furthermore, there is room for improvement in ensuring incentives for supporters and the management system for donations.

[0284] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is realized by the following respective means.

[0285] In this invention, the server, as data collection means, acquires disaster information, weather information, and human settlement information, formats the data, and stores it in the data management apparatus; predicts necessary resources during a disaster using a machine learning algorithm; and provides real-time crisis information to a mobile information terminal and issues an alarm visually and audibly. As a result, it becomes possible to quickly and accurately acquire the information necessary for relief activities and effectively notify supporters.

[0286] The "data collection means" is a device for acquiring disaster information, weather information, and human settlement information, formatting these data, and storing them in the data management apparatus.

[0287] The "machine learning algorithm" is a method for learning past disaster patterns and predicting necessary resources during a disaster.

[0288] The "visualization means" is a technology for visually displaying demand information for resources using a map or the like and updating it in real time according to changes.

[0289] The "notification means" is a function for notifying a support apparatus of the necessity for support and resource information.

[0290] The "selection and confirmation means" is a mechanism for a user to select the content of support and check the history.

[0291] An "economic model" is a design that allows for sustainable business operations by allocating a portion of donations as administrative fees.

[0292] A "mobile information terminal" refers to a portable device that can be moved around and has the function of providing real-time crisis information and issuing warnings visually and audibly.

[0293] "Geospatial information" refers to information related to geographical location and is used to quickly grasp the situation during disasters.

[0294] A "merit program" is a system of incentives offered to supporters to encourage their participation in support activities.

[0295] The system for implementing this invention functions primarily around a server. The server first acquires disaster information, weather information, and human habitation information using data collection means, and then formats and stores them in a data management device. The collected data is analyzed by machine learning algorithms to predict the demand for necessary resources during a disaster. This prediction is visualized in real time on a map and presented to the user.

[0296] The server also has the ability to notify mobile devices of crisis information in real time and issue warnings using both visual and audible means. This allows users to immediately understand the crisis and choose appropriate support actions. For example, when an earthquake occurs in a certain area, predictions of shortages of drinking water and food can be quickly conveyed to the user in conjunction with a map.

[0297] Finally, supporters will benefit from a merit program to encourage active participation. This will create a mechanism to incorporate a portion of donations as an administrative fee into the new economic model. All of these processes will be server-centric and operated quickly and accurately.

[0298] By utilizing a generative AI model, efficient support activities are facilitated through prompt messages such as the following: "We are developing an application that uses machine learning to predict the demand for relief supplies in real time during disasters. Please tell us about the main functions of this application and the methods for user notifications."

[0299] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0300] Step 1:

[0301] The server retrieves disaster information, weather information, and human habitation information from multiple data sources. Input for this data comes from various APIs and public databases. The server formats this data and stores it in a unified format in a data management device. At this stage, the data is organized and immediately accessible.

[0302] Step 2:

[0303] The server applies a machine learning algorithm based on the stored data. The input is the data organized in Step 1, and the output is a prediction of resource demand during a disaster. The server uses past disaster patterns as a model to improve prediction accuracy. Specifically, it performs data calculations to simulate shortages of drinking water and food in a particular region.

[0304] Step 3:

[0305] The server visualizes the prediction results in real time. The input is the prediction data from step 2, and the output is resource demand information displayed on a map. The server provides information through a user interface, visually indicating shortages with colors and icons.

[0306] Step 4:

[0307] The server notifies the information to the supporter's terminal. The input at this time is the geographical information visualized in Step 3, and the output is the warning message displayed on the terminal's display. The terminal issues a warning using vision and voice to prompt the supporter to take prompt action.

[0308] Step 5:

[0309] The user selects a support activity based on the presented information. The input is the disaster situation and resource information displayed on the terminal, and the user decides which support to provide based on their own judgment. The output is recorded as the selected support content and history. Here, as a specific operation, the intention to provide support materials is transmitted to the server by the user's operation.

[0310] Step 6:

[0311] The server applies the points program to encourage the participation of supporters. The input at this time is the selection history and donation amount of the supporter, and the output is an incentive to the supporter. Based on the economic model, a part of the donation is accounted for as management fees, and sustainable support activities are carried out.

[0312] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0313] The present invention is a system that combines an emotion engine in order to streamline, make fair, and effective support activities during disasters. The system is mainly composed of data collection, machine learning algorithms, visualization of information, notification, emotion recognition, selection by supporters, and construction of a business model.

[0314] First, the server collects disaster information, weather information, and population information from various data sources. This data is formatted and stored in a database. Next, the server uses machine learning algorithms to predict the demand for supplies and builds a model based on past disaster patterns. The predicted information is visualized by the server on a dashboard and displayed intuitively using maps and other visuals. This visualization makes it possible to see at a glance which areas need assistance and which supplies are lacking.

[0315] In addition, the server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine evaluates the user's current emotional state based on their past response data and adjusts notification content and incentive programs accordingly. For example, if the server recognizes positive emotions, it will send proactive messages regarding support. This function facilitates the provision of support in the most optimal way for each individual supporter.

[0316] Furthermore, the server tracks emotional states in real time to determine the appropriate timing for providing support. The emotion engine functions as a tool to support decision-making regarding material provision and donations, playing a role in guiding user decision-making.

[0317] As a concrete example, suppose a flood occurs in a certain area. The server quickly collects data and predicts the demand for drinking water. At this time, the emotion engine analyzes the emotions of the helpers and sends notifications to their devices prompting appropriate assistance as needed. For example, a message such as, "Many victims need assistance. Your help can make a big difference," might be sent. In this way, emotion-based information is provided, maximizing the effectiveness of the assistance.

[0318] This system aims not only to improve the efficiency of support activities but also to enable emotion-based, personalized support, thereby increasing social and economic value.

[0319] The following describes the processing flow.

[0320] Step 1:

[0321] The server collects disaster information, weather data, and human habitation information from public databases and APIs. The collected data is formatted and stored in a database. This provides a foundation for understanding the latest situation.

[0322] Step 2:

[0323] The server analyzes collected data using machine learning algorithms. It utilizes models trained on past disaster patterns to predict demand for supplies. These predictions are updated in real time, contributing to a rapid response during disasters.

[0324] Step 3:

[0325] The server visually displays predicted material demand data on a map. The displayed dashboard color-codes areas with high demand, allowing users to see at a glance where assistance is needed.

[0326] Step 4:

[0327] The server references the user's past emotional data and uses an emotion engine to analyze their current emotional state. This information is used to determine what kind of support the user desires.

[0328] Step 5:

[0329] The server sends customized messages to the device based on the user's emotional state. For example, if positive emotions are detected, an encouraging message will be sent. Incentives tailored to the emotions may also be offered.

[0330] Step 6:

[0331] The terminal displays a customized message sent from the server to the user. Based on this, the user decides what supplies to provide, in what quantities, or how much to donate.

[0332] Step 7:

[0333] Users can view their support history on their device to understand how their past support has been utilized. This historical information helps users plan how they will provide support in the future.

[0334] Step 8:

[0335] The server will allocate a portion of the donations as a management fee and incorporate it into a new business model. This model will include an incentive program to encourage future charitable activities.

[0336] (Example 2)

[0337] Next, we will describe Example 2. 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".

[0338] During disasters, there is a need to supply relief supplies quickly and accurately, and to carry out relief activities efficiently and effectively. Conventional systems have problems such as insufficient information gathering and visualization of relief efforts, and difficulty in promoting relief activities while considering the emotional state of individual supporters. This invention aims to solve these problems and realize efficient and emotion-based relief.

[0339] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0340] In this invention, the server includes information gathering means for collecting disaster-related information and storing it in a standard format, analysis means for predicting the supply and demand of goods using machine learning technology, and information visualization means for visually displaying and updating supply and demand information. This enables rapid information gathering and analysis, allows for the provision of emotion-based, personalized support, and improves the efficiency and effectiveness of support activities.

[0341] An "information gathering means" is a system component that has the function of collecting disaster-related information, organizing it in a standard format, and storing it.

[0342] "Analysis tools" refer to system components that analyze data collected using machine learning techniques to predict the supply and demand of goods.

[0343] An "information visualization tool" is a system component that visually displays analyzed supply and demand information so that users can understand it intuitively.

[0344] "Emotion recognition functionality" is a technology that analyzes the user's emotional state and provides personalized information notifications based on that analysis.

[0345] "Selection and confirmation means" refers to a system component that has the function of allowing supporters to decide what kind of support to provide and to check past support history.

[0346] "Commercial means" refers to system components that integrate a portion of donations as a fee into a new business model.

[0347] This invention is a system in which a server, a terminal, and a user work together in cooperation, and aims to efficiently and effectively carry out support activities during disasters. This system consists of information gathering functions, analysis functions, information visualization functions, and emotion recognition functions.

[0348] The server retrieves disaster information, weather information, and population information from various data sources. Specifically, it collects information from internet APIs, social networking services, and real-time data provided by local governments. This information is organized in a standard format and stored in a database.

[0349] Based on this data, the server uses machine learning algorithms to predict the supply and demand of goods. The software used will primarily consist of machine learning libraries such as TensorFlow and PyTorch. The server learns from past disaster data and builds a predictive model to estimate the types and quantities of supplies needed.

[0350] The analyzed information is visualized by the server and displayed in charts and maps. Tools such as the Google Maps API and D3.js are used for visualization. This allows users to understand at a glance which areas require particular attention.

[0351] Through its emotion recognition function, the server analyzes the user's emotional state. The results of this analysis are sent to the user's device as personalized notification information. The emotion engine uses a machine learning model trained on past response data to quantify the user's emotions and propose appropriate notifications and incentives. These notifications maximize the user's motivation for support activities.

[0352] As a concrete example, consider a case where a flood occurs in a certain area. The server quickly collects and analyzes data from the affected area and predicts the demand for drinking water. At this time, the emotion engine analyzes the emotions of the helpers and sends notifications to the device that encourage the most appropriate support based on that analysis. For example, a message such as, "Many victims need help. Your support can make a big difference," might be sent. Other examples of prompts using the generative AI model include, "Please tell me how to streamline disaster relief activities," and "How can I build a model to predict the demand for relief supplies during a flood?"

[0353] This system enables rapid and effective support activities by providing individual supporters with emotionally appropriate support based on collected data and analytical information.

[0354] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0355] Step 1:

[0356] The server retrieves input data from multiple data sources. This input data includes disaster information, weather data, demographic data, and so on. The server processes this information into a standard format and outputs the formatted data to the database. Specifically, it retrieves data via an internet API and then processes and formats it.

[0357] Step 2:

[0358] The server takes formatted data stored in a database as input and applies a machine learning algorithm. The data calculation generates a predictive model based on past disaster data to forecast the supply and demand of goods. The output is the predicted supply and demand information; specifically, it outputs a list of the types and quantities of goods that will be needed next. The system uses a machine learning library to train the data and perform predictions.

[0359] Step 3:

[0360] The server receives predicted supply and demand information as input and passes it to visualization software. The output is specific information displayed as visualized maps and graphs. In operation, it uses a visualization library to display information on a map and updates the visual dashboard.

[0361] Step 4:

[0362] The server receives emotion data from the user database as input and performs analysis using an emotion engine. As part of data processing based on the input data, it generates a model using the user's past emotional response data to evaluate the user's emotional state. The output is a notification message optimized for the emotional state. The process involves executing an emotion recognition algorithm and generating notification content based on the analysis results.

[0363] Step 5:

[0364] The server takes the analysis results obtained from the emotion engine as input and sends notifications to the user's device as needed. Based on the input data, it generates personalized notification messages and outputs them to the device. As a concrete example of its operation, it sends a message to the device such as "Your help is needed. Your help will be a great help," encouraging the user to engage in support activities. In this process, prompt messages can also be utilized using a generative AI model.

[0365] (Application Example 2)

[0366] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0367] Traditional food delivery services have struggled to suggest the most suitable products based on customer emotions and individual needs, limiting their ability to improve customer satisfaction. Furthermore, the difficulty in accurately predicting deliveries while considering weather and congestion also limited service efficiency. Solving these challenges is necessary to optimize the customer experience and improve service efficiency and profitability.

[0368] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0369] In this invention, the server includes, as a data collection means, means for acquiring weather information, human residence information, order history, and customer sentiment information, formatting the data, and storing it in an information storage means; means for predicting demand using machine learning algorithms and building a model based on past patterns; and means for visually displaying demand information and weather information and communicating it intuitively to service providers. This enables optimal product suggestions that take into account the customer's emotional state and accurate delivery predictions according to weather and congestion levels.

[0370] "Data collection means" refers to technology that has the function of acquiring weather information, human residence information, order history, and customer sentiment information, formatting the data, and storing it in an information storage means.

[0371] A "machine learning algorithm" is a technology that uses mathematical methods to predict demand based on past patterns.

[0372] "Visual display means" refers to technologies for visually displaying demand information and weather information and communicating it intuitively to service providers.

[0373] A "sentiment analysis engine" is a technology that analyzes a customer's emotional state and generates individually optimized notification content.

[0374] An "incentive program" is a technology that provides benefits and rewards to users to encourage service usage.

[0375] "Information storage means" refers to technology that systematically organizes acquired data and stores it so that it can be used for later analysis and processing.

[0376] In this application, the system first uses a server to acquire weather information, human residence information, order history, and customer sentiment information using data collection means. Then, this information is formatted and stored in an information storage means. A relational database management system (RDBMS) can be used for data formatting.

[0377] The server then uses machine learning algorithms to predict demand based on past patterns. Machine learning libraries such as Scikit-learn are used in this process. The predicted demand and weather information are visually displayed on a dashboard using visual visualization tools. Data visualization tools such as Plotly can be used to implement this dashboard.

[0378] Furthermore, an emotion analysis engine is used to analyze the customer's emotional state and send optimized notifications to the user's information device. NLP libraries (such as NLTK and spaCy) are used for emotion analysis. The notification content is sent as a push notification to smartphones and other devices.

[0379] Based on the notifications sent, users can select products suggested by the application and review their history. The server also has the functionality to implement incentive programs for users and promote service usage.

[0380] As a concrete example, on a rainy day, a server might send a message saying, "We recommend a hot pot dish." In this case, the following prompt would be used for the AI ​​generation model: "Based on the current weather information and the customer's order history, suggest the most suitable food delivery. Analyze how the customer's sentiment has changed compared to the previous year, and generate a notification message based on the results."

[0381] This will enable the provision of individualized services tailored to customer needs, leading to improved customer satisfaction and increased service efficiency.

[0382] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0383] Step 1:

[0384] The server uses data collection methods to gather weather information APIs, human location data, user order history data, and customer sentiment data. It uses online-accessible APIs and user input data as input, storing them in a unified database format. As output, it saves data in a format suitable for searching and analysis.

[0385] Step 2:

[0386] The server uses the collected data to perform demand forecasting using machine learning algorithms. Specifically, it uses libraries such as Scikit-learn to learn demand patterns from past order history and weather conditions. The input is a formatted dataset, and the output is the creation of a demand forecasting model. The resulting demand forecast is then used in the next processing step.

[0387] Step 3:

[0388] The server displays demand forecast and weather information on a dashboard using visual display means. Inputs are demand forecasting models and collected weather information, which are visualized in graph and map formats using visualization tools such as Plotly. Outputs are intuitively understandable visual data, simplifying data interpretation.

[0389] Step 4:

[0390] The server uses a sentiment analysis engine to analyze the customer sentiment data it receives. The input is text data from customer reviews and comments, and NLP is used to quantify or categorize the sentiment. The output is a sentiment score, which is used in the next step to generate notification content.

[0391] Step 5:

[0392] The server generates and sends push notification messages to the user's device based on emotional state and demand forecasts. The input is the emotional score and demand forecast results, and a generative AI model is used to generate notification messages based on prompts. The output is the notification message displayed on the user's device.

[0393] Step 6:

[0394] The user selects recommended products and confirms the order based on notifications received on their device. The input is a notification message from the server, and the user selects products using the application. The output is the selected products and their order information, which the server receives and processes.

[0395] Step 7:

[0396] The server provides incentive programs based on order history and customer sentiment to encourage service usage. Inputs are the customer's past order history and sentiment score, and an algorithm is used to present appropriate rewards. Outputs include the provision of new incentives and the resulting expected increase in service usage.

[0397] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0398] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0399] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0400] [Third Embodiment]

[0401] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0402] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0403] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0404] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0405] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0406] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0407] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0408] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0409] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0410] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0411] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0412] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0413] This invention is a system that integrates multiple technological elements to streamline and improve the fairness of disaster relief activities. This system primarily consists of data collection, machine learning algorithms, information visualization, notification, supporter selection, and business model construction. Details of each technological element are provided below.

[0414] First, the server collects disaster information, weather information, and residential information from various data sources. This utilizes public databases and real-time APIs. The collected data is then formatted and stored in a database.

[0415] Next, the server uses machine learning algorithms to analyze the collected data. This allows it to predict the demand for relief supplies in the event of a disaster. This prediction utilizes a model based on data from past disaster patterns.

[0416] The prediction results are visualized by the server in an interactive user interface such as a dashboard. For example, a map can be used to color-code the shortages of supplies, intuitively displaying the situation in that region.

[0417] The server also notifies the supporter's terminal of this information in real time. The terminal provides the user with the received information and displays a list of areas and supplies that need assistance.

[0418] Based on the information provided through the device, users can decide which supplies to provide and in what quantities. In addition, they can review the history of their support and understand the results of their past assistance efforts.

[0419] Furthermore, the server will allocate a portion of the donations as an administrative fee to support the creation of a sustainable business model. This business model will also include the implementation of incentive programs to ensure the company's sustainability.

[0420] As a concrete example, consider a scenario where a major earthquake occurs in a certain region. The server immediately collects data and predicts the demand for drinking water and food. The prediction results are notified to the terminal, and the user makes a choice regarding assistance. This process enables rapid and appropriate assistance activities.

[0421] As described above, the system of the present invention makes it possible to effectively provide disaster relief by combining technical elements.

[0422] The following describes the processing flow.

[0423] Step 1:

[0424] The server collects relevant data such as disaster information, weather information, and population density from public databases and real-time APIs. This data is formatted and preprocessed, including imputation of missing values ​​and normalization. It is then stored in a database in preparation for subsequent processing.

[0425] Step 2:

[0426] The server uses the collected data as input to run a machine learning algorithm, which then predicts the demand for supplies during a disaster. The AI ​​model learns from past disaster patterns and is continuously updated to improve prediction accuracy.

[0427] Step 3:

[0428] The server uses visualization tools to display information on charts and maps based on predicted demand data for supplies. This visualization is updated in real time on the dashboard, visually indicating areas where supplies are in short supply.

[0429] Step 4:

[0430] The server pushes important information to the devices registered by the supporters. This notification includes details about the areas where assistance is needed and the types of supplies required.

[0431] Step 5:

[0432] The device provides the user with the received information. The user reviews the displayed information and decides how much material support to provide. Based on this information, the user can make an appropriate donation or provide materials.

[0433] Step 6:

[0434] Users can utilize a feature that allows them to check their support history on their device. This enables them to understand how the support they have provided is being used, ensuring transparency in their support activities.

[0435] Step 7:

[0436] The server incorporates a portion of the total donation amount as an administrative fee into its business model to ensure profitability as a company. This business model may include incentive programs for supporters to encourage participation in future charitable activities.

[0437] (Example 1)

[0438] Next, we will describe Example 1. 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."

[0439] While there is a need to improve the efficiency and fairness of support activities during disasters, conventional systems have faced challenges in collecting sufficient data, accurately forecasting demand, and providing timely information. Furthermore, building sustainable business models has been difficult.

[0440] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0441] In this invention, the server includes means for acquiring disaster information, weather information, and housing information as an information acquisition device, formatting the data, and storing it on a storage medium; means for estimating the demand for supplies during a disaster using a computational algorithm; and means for visualizing the demand information on a map and updating it in real time. This enables efficient and equitable disaster relief. Furthermore, by optimizing data processing using a generative model and incorporating a portion of donations as processing costs into the business model, it becomes possible to build a sustainable business model.

[0442] An "information acquisition device" is a device that acquires disaster information, weather information, and housing information, formats the data, and stores it on a storage medium.

[0443] A "computational algorithm" is a mathematical method used to estimate the demand for supplies during a disaster using collected data.

[0444] "Demand information" refers to information regarding the types and quantities of supplies needed in a specific area during a disaster.

[0445] "Visualization on a map" is a method of using maps to show the shortage of supplies and the areas that need assistance.

[0446] "Real-time updates" means that information is updated immediately as soon as data is acquired.

[0447] A "generative model" is a model that utilizes AI technology to learn generalized data patterns and make more accurate predictions.

[0448] A "storage medium" is a physical or electronic medium used to store data.

[0449] A "sustainable business model" is a business method that brings economic benefits to an organization in a way that can be sustained over the long term.

[0450] A "reward program" is a mechanism that provides incentives to support participants to encourage specific behaviors.

[0451] This invention is a system that enables efficient and equitable support activities during disasters. In this system, a server plays a central role. The server acquires disaster information, weather information, and housing information using public databases and real-time APIs. The server, functioning as an information acquisition device, formats this data and stores it on a storage medium. Specifically, the server collects weather data through the OpenWeatherMap API and acquires disaster information from local government databases.

[0452] The collected data is analyzed using machine learning algorithms. The server uses a generative AI model to learn from past disaster data and predict specific supply needs during disasters. This prediction calculates the demand for necessary supplies such as drinking water and food. For example, by referencing current weather conditions based on past typhoon data, the system can accurately estimate the supplies needed in disaster-stricken areas.

[0453] The analysis results are updated in real time by the server and visualized on a map. The server uses the map to color-code the areas where supplies are lacking, indicating which regions are in particular need of assistance. This makes it easier for users to intuitively understand the information. The server also notifies information terminals of detailed information regarding the need for assistance. Mobile push notifications and web notifications are used as needed.

[0454] Based on this information, users decide which supplies to provide and in what quantities. The user's device allows them to review their aid history, enabling them to understand what kind of assistance they have provided and to which regions.

[0455] Furthermore, the server incorporates a portion of donations as processing costs into its business model. This process supports the creation of a sustainable business model and includes an incentive program for supporters. This allows users to receive rewards such as points for their support activities.

[0456] As a concrete example, if a major earthquake occurs in a certain region, the server will immediately collect data on the damage and weather, and predict the demand for drinking water and food. The prediction results will be notified to the user's terminal, and the user can then quickly take action to provide assistance based on that information. An example of a prompt message for the generating AI model would be, "Based on past disaster data for region X, please predict the supplies that will be needed in the next week."

[0457] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0458] Step 1:

[0459] The server, acting as an information acquisition device, retrieves disaster information, weather information, and housing information from public databases and real-time APIs. The input for this step consists of the latest information from multiple data sources. The acquired raw data is converted to a format and stored on the system's storage medium. Specifically, weather information is retrieved in JSON format from the OpenWeatherMap API, and the necessary items are extracted and stored in the database.

[0460] Step 2:

[0461] The server begins analyzing the collected data using a generative AI model. The input for this step is the disaster and weather data formatted in the previous step. The server uses machine learning algorithms to predict the demand for relief supplies during a disaster based on past disaster data. Through this process, it is possible to specifically identify areas where drinking water and food are particularly needed. The output is regional demand forecast data for supplies.

[0462] Step 3:

[0463] The server visualizes the analysis results on an interactive dashboard. The input for this step is the analyzed demand forecast data. The server displays this data on a map using color coding, visually highlighting areas of shortage. Specifically, areas shown in red indicate severe shortages, making it easy for users to understand intuitively. The output is visualized support information accessible to the user.

[0464] Step 4:

[0465] The server notifies information terminals of information generated in real time. The input for this step is information from a visualized map. Push notifications to mobile devices and pop-up notifications to web browsers are used as notification methods. Specifically, it sends specific alerts such as "There is a shortage of drinking water in area X." The output is detailed disaster relief information that can be viewed on the user's device.

[0466] Step 5:

[0467] The user decides which supplies to provide and in what quantities based on the information provided via the terminal. The input for this step is information about the assistance notified by the server. The user can open the terminal application, select the assistance content, and view the history. For example, the user might input the instruction, "Send 100 liters of drinking water to area X." The output is the specific assistance action based on the user's decision.

[0468] Step 6:

[0469] To ensure the sustainability of system operations, the server allocates a portion of donations as processing costs and establishes a business model. The input for this step is donation information from users. The server adds points to user accounts based on the donation amount, maintaining an incentive program. Specifically, processing is carried out based on the rule "award 1 point for every 100 yen donated." The output is incentive data to promote sustainable support activities.

[0470] (Application Example 1)

[0471] Next, we will explain Application Example 1. In the following explanation, 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."

[0472] Disaster relief efforts require the rapid acquisition of accurate information and the appropriate allocation of resources based on that information. However, conventional systems are insufficient in terms of the speed of information gathering and notification, as well as the flexibility in selecting the type of support to provide. In particular, there are still challenges in providing real-time crisis management information using mobile devices. Furthermore, there is room for improvement in securing incentives for supporters and in the management system for donations.

[0473] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0474] In this invention, the server includes, as a data collection means, means for acquiring disaster information, weather information, and human habitation information, formatting the data, and storing it in a data management device; means for predicting the resources needed during a disaster using a machine learning algorithm; and means for providing crisis information to mobile information terminals in real time and issuing visual and audible warnings. This makes it possible to quickly and accurately acquire the information necessary for support activities and to provide effective notifications to supporters.

[0475] A "data collection means" is a device that acquires disaster information, weather information, and human habitation information, formats this data, and stores it in a data management device.

[0476] A "machine learning algorithm" is a method for learning past disaster patterns and predicting the resources needed during a disaster.

[0477] "Visualization methods" refer to technologies that visually display resource demand information using maps or other means, and update it in real time as it changes.

[0478] A "notification means" is a function that informs the support device of the need for support and resource information.

[0479] "Selection and confirmation means" refers to a mechanism that allows users to choose the type of support they received and review their history.

[0480] An "economic model" is a design that allows for sustainable business operations by allocating a portion of donations as administrative fees.

[0481] A "mobile information terminal" refers to a portable device that can be moved around and has the function of providing real-time crisis information and issuing warnings visually and audibly.

[0482] "Geospatial information" refers to information related to geographical location and is used to quickly grasp the situation during disasters.

[0483] A "merit program" is a system of incentives offered to supporters to encourage their participation in support activities.

[0484] The system for implementing this invention functions primarily around a server. The server first acquires disaster information, weather information, and human habitation information using data collection means, and then formats and stores them in a data management device. The collected data is analyzed by machine learning algorithms to predict the demand for necessary resources during a disaster. This prediction is visualized in real time on a map and presented to the user.

[0485] The server also has the ability to notify mobile devices of crisis information in real time and issue warnings using both visual and audible means. This allows users to immediately understand the crisis and choose appropriate support actions. For example, when an earthquake occurs in a certain area, predictions of shortages of drinking water and food can be quickly conveyed to the user in conjunction with a map.

[0486] Finally, supporters will benefit from a merit program to encourage active participation. This will create a mechanism to incorporate a portion of donations as an administrative fee into the new economic model. All of these processes will be server-centric and operated quickly and accurately.

[0487] By utilizing a generative AI model, efficient support activities are facilitated through prompt messages such as the following: "We are developing an application that uses machine learning to predict the demand for relief supplies in real time during disasters. Please tell us about the main functions of this application and the methods for user notifications."

[0488] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0489] Step 1:

[0490] The server retrieves disaster information, weather information, and human habitation information from multiple data sources. Input for this data comes from various APIs and public databases. The server formats this data and stores it in a unified format in a data management device. At this stage, the data is organized and immediately accessible.

[0491] Step 2:

[0492] The server applies a machine learning algorithm based on the stored data. The input is the data organized in Step 1, and the output is a prediction of resource demand during a disaster. The server uses past disaster patterns as a model to improve prediction accuracy. Specifically, it performs data calculations to simulate shortages of drinking water and food in a particular region.

[0493] Step 3:

[0494] The server visualizes the prediction results in real time. The input is the prediction data from step 2, and the output is resource demand information displayed on a map. The server provides information through a user interface, visually indicating shortages with colors and icons.

[0495] Step 4:

[0496] The server notifies the supporter's terminal of the information. The input at this time is the geographical information visualized in step 3, and the output is an alarm message displayed on the terminal's screen. The terminal issues an alarm using both visual and auditory information to prompt the supporter to take swift action.

[0497] Step 5:

[0498] The user selects support activities based on the information presented. The input consists of disaster situation and resource information displayed on the terminal, and the user decides which support to provide based on their own judgment. The output is the selected support content and a record of the history. Specifically, the user's actions send an indication of their intention to provide support supplies to the server.

[0499] Step 6:

[0500] The server applies a merit program and encourages supporter participation. The inputs are the supporter's selection history and donation amount, and the output is an incentive for the supporter. Based on an economic model, a portion of the donations is allocated as an administrative fee, ensuring sustainable support activities.

[0501] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0502] This invention is a system that combines an emotion engine to streamline, equitably, and effectively carry out disaster relief activities. The system mainly consists of data collection, machine learning algorithms, information visualization, notification, emotion recognition, supporter selection, and business model construction.

[0503] First, the server collects disaster information, weather information, and population information from various data sources. This data is formatted and stored in a database. Next, the server uses machine learning algorithms to predict the demand for supplies and builds a model based on past disaster patterns. The predicted information is visualized by the server on a dashboard and displayed intuitively using maps and other visuals. This visualization makes it possible to see at a glance which areas need assistance and which supplies are lacking.

[0504] In addition, the server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine evaluates the user's current emotional state based on their past response data and adjusts notification content and incentive programs accordingly. For example, if the server recognizes positive emotions, it will send proactive messages regarding support. This function facilitates the provision of support in the most optimal way for each individual supporter.

[0505] Furthermore, the server tracks emotional states in real time to determine the appropriate timing for providing support. The emotion engine functions as a tool to support decision-making regarding material provision and donations, playing a role in guiding user decision-making.

[0506] As a concrete example, suppose a flood occurs in a certain area. The server quickly collects data and predicts the demand for drinking water. At this time, the emotion engine analyzes the emotions of the helpers and sends notifications to their devices prompting appropriate assistance as needed. For example, a message such as, "Many victims need assistance. Your help can make a big difference," might be sent. In this way, emotion-based information is provided, maximizing the effectiveness of the assistance.

[0507] This system aims not only to improve the efficiency of support activities but also to enable emotion-based, personalized support, thereby increasing social and economic value.

[0508] The following describes the processing flow.

[0509] Step 1:

[0510] The server collects disaster information, weather data, and human habitation information from public databases and APIs. The collected data is formatted and stored in a database. This provides a foundation for understanding the latest situation.

[0511] Step 2:

[0512] The server analyzes collected data using machine learning algorithms. It utilizes models trained on past disaster patterns to predict demand for supplies. These predictions are updated in real time, contributing to a rapid response during disasters.

[0513] Step 3:

[0514] The server visually displays predicted material demand data on a map. The displayed dashboard color-codes areas with high demand, allowing users to see at a glance where assistance is needed.

[0515] Step 4:

[0516] The server references the user's past emotional data and uses an emotion engine to analyze their current emotional state. This information is used to determine what kind of support the user desires.

[0517] Step 5:

[0518] The server sends customized messages to the device based on the user's emotional state. For example, if positive emotions are detected, an encouraging message will be sent. Incentives tailored to the emotions may also be offered.

[0519] Step 6:

[0520] The terminal displays a customized message sent from the server to the user. Based on this, the user decides what supplies to provide, in what quantities, or how much to donate.

[0521] Step 7:

[0522] Users can view their support history on their device to understand how their past support has been utilized. This historical information helps users plan how they will provide support in the future.

[0523] Step 8:

[0524] The server will allocate a portion of the donations as a management fee and incorporate it into a new business model. This model will include an incentive program to encourage future charitable activities.

[0525] (Example 2)

[0526] Next, we will describe Example 2. 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."

[0527] During disasters, there is a need to supply relief supplies quickly and accurately, and to carry out relief activities efficiently and effectively. Conventional systems have problems such as insufficient information gathering and visualization of relief efforts, and difficulty in promoting relief activities while considering the emotional state of individual supporters. This invention aims to solve these problems and realize efficient and emotion-based relief.

[0528] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0529] In this invention, the server includes information gathering means for collecting disaster-related information and storing it in a standard format, analysis means for predicting the supply and demand of goods using machine learning technology, and information visualization means for visually displaying and updating supply and demand information. This enables rapid information gathering and analysis, allows for the provision of emotion-based, personalized support, and improves the efficiency and effectiveness of support activities.

[0530] An "information gathering means" is a system component that has the function of collecting disaster-related information, organizing it in a standard format, and storing it.

[0531] "Analysis tools" refer to system components that analyze data collected using machine learning techniques to predict the supply and demand of goods.

[0532] An "information visualization tool" is a system component that visually displays analyzed supply and demand information so that users can understand it intuitively.

[0533] "Emotion recognition functionality" is a technology that analyzes the user's emotional state and provides personalized information notifications based on that analysis.

[0534] "Selection and confirmation means" refers to a system component that has the function of allowing supporters to decide what kind of support to provide and to check past support history.

[0535] "Commercial means" refers to system components that integrate a portion of donations as a fee into a new business model.

[0536] This invention is a system in which a server, a terminal, and a user work together in cooperation, and aims to efficiently and effectively carry out support activities during disasters. This system consists of information gathering functions, analysis functions, information visualization functions, and emotion recognition functions.

[0537] The server retrieves disaster information, weather information, and population information from various data sources. Specifically, it collects information from internet APIs, social networking services, and real-time data provided by local governments. This information is organized in a standard format and stored in a database.

[0538] Based on this data, the server uses machine learning algorithms to predict the supply and demand of goods. The software used will primarily consist of machine learning libraries such as TensorFlow and PyTorch. The server learns from past disaster data and builds a predictive model to estimate the types and quantities of supplies needed.

[0539] The analyzed information is visualized by the server and displayed in charts and maps. Tools such as the Google Maps API and D3.js are used for visualization. This allows users to understand at a glance which areas require particular attention.

[0540] Through its emotion recognition function, the server analyzes the user's emotional state. The results of this analysis are sent to the user's device as personalized notification information. The emotion engine uses a machine learning model trained on past response data to quantify the user's emotions and propose appropriate notifications and incentives. These notifications maximize the user's motivation for support activities.

[0541] As a concrete example, consider a case where a flood occurs in a certain area. The server quickly collects and analyzes data from the affected area and predicts the demand for drinking water. At this time, the emotion engine analyzes the emotions of the helpers and sends notifications to the device that encourage the most appropriate support based on that analysis. For example, a message such as, "Many victims need help. Your support can make a big difference," might be sent. Other examples of prompts using the generative AI model include, "Please tell me how to streamline disaster relief activities," and "How can I build a model to predict the demand for relief supplies during a flood?"

[0542] This system enables rapid and effective support activities by providing individual supporters with emotionally appropriate support based on collected data and analytical information.

[0543] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0544] Step 1:

[0545] The server retrieves input data from multiple data sources. This input data includes disaster information, weather data, demographic data, and so on. The server processes this information into a standard format and outputs the formatted data to the database. Specifically, it retrieves data via an internet API and then processes and formats it.

[0546] Step 2:

[0547] The server takes formatted data stored in a database as input and applies a machine learning algorithm. The data calculation generates a predictive model based on past disaster data to forecast the supply and demand of goods. The output is the predicted supply and demand information; specifically, it outputs a list of the types and quantities of goods that will be needed next. The system uses a machine learning library to train the data and perform predictions.

[0548] Step 3:

[0549] The server receives predicted supply and demand information as input and passes it to visualization software. The output is specific information displayed as visualized maps and graphs. In operation, it uses a visualization library to display information on a map and updates the visual dashboard.

[0550] Step 4:

[0551] The server receives emotion data from the user database as input and performs analysis using an emotion engine. As part of data processing based on the input data, it generates a model using the user's past emotional response data to evaluate the user's emotional state. The output is a notification message optimized for the emotional state. The process involves executing an emotion recognition algorithm and generating notification content based on the analysis results.

[0552] Step 5:

[0553] The server takes the analysis results obtained from the emotion engine as input and sends notifications to the user's device as needed. Based on the input data, it generates personalized notification messages and outputs them to the device. As a concrete example of its operation, it sends a message to the device such as "Your help is needed. Your help will be a great help," encouraging the user to engage in support activities. In this process, prompt messages can also be utilized using a generative AI model.

[0554] (Application Example 2)

[0555] Next, we will explain application example 2. In the following explanation, 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."

[0556] Traditional food delivery services have struggled to suggest the most suitable products based on customer emotions and individual needs, limiting their ability to improve customer satisfaction. Furthermore, the difficulty in accurately predicting deliveries while considering weather and congestion also limited service efficiency. Solving these challenges is necessary to optimize the customer experience and improve service efficiency and profitability.

[0557] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0558] In this invention, the server includes, as a data collection means, means for acquiring weather information, human residence information, order history, and customer sentiment information, formatting the data, and storing it in an information storage means; means for predicting demand using machine learning algorithms and building a model based on past patterns; and means for visually displaying demand information and weather information and communicating it intuitively to service providers. This enables optimal product suggestions that take into account the customer's emotional state and accurate delivery predictions according to weather and congestion levels.

[0559] "Data collection means" refers to technology that has the function of acquiring weather information, human residence information, order history, and customer sentiment information, formatting the data, and storing it in an information storage means.

[0560] A "machine learning algorithm" is a technology that uses mathematical methods to predict demand based on past patterns.

[0561] "Visual display means" refers to technologies for visually displaying demand information and weather information and communicating it intuitively to service providers.

[0562] A "sentiment analysis engine" is a technology that analyzes a customer's emotional state and generates individually optimized notification content.

[0563] An "incentive program" is a technology that provides benefits and rewards to users to encourage service usage.

[0564] "Information storage means" refers to technology that systematically organizes acquired data and stores it so that it can be used for later analysis and processing.

[0565] In this application, the system first uses a server to acquire weather information, human residence information, order history, and customer sentiment information using data collection means. Then, this information is formatted and stored in an information storage means. A relational database management system (RDBMS) can be used for data formatting.

[0566] The server then uses machine learning algorithms to predict demand based on past patterns. Machine learning libraries such as Scikit-learn are used in this process. The predicted demand and weather information are visually displayed on a dashboard using visual visualization tools. Data visualization tools such as Plotly can be used to implement this dashboard.

[0567] Furthermore, an emotion analysis engine is used to analyze the customer's emotional state and send optimized notifications to the user's information device. NLP libraries (such as NLTK and spaCy) are used for emotion analysis. The notification content is sent as a push notification to smartphones and other devices.

[0568] Based on the notifications sent, users can select products suggested by the application and review their history. The server also has the functionality to implement incentive programs for users and promote service usage.

[0569] As a concrete example, on a rainy day, a server might send a message saying, "We recommend a hot pot dish." In this case, the following prompt would be used for the AI ​​generation model: "Based on the current weather information and the customer's order history, suggest the most suitable food delivery. Analyze how the customer's sentiment has changed compared to the previous year, and generate a notification message based on the results."

[0570] This will enable the provision of individualized services tailored to customer needs, leading to improved customer satisfaction and increased service efficiency.

[0571] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0572] Step 1:

[0573] The server uses data collection methods to gather weather information APIs, human location data, user order history data, and customer sentiment data. It uses online-accessible APIs and user input data as input, storing them in a unified database format. As output, it saves data in a format suitable for searching and analysis.

[0574] Step 2:

[0575] The server uses the collected data to perform demand forecasting using machine learning algorithms. Specifically, it uses libraries such as Scikit-learn to learn demand patterns from past order history and weather conditions. The input is a formatted dataset, and the output is the creation of a demand forecasting model. The resulting demand forecast is then used in the next processing step.

[0576] Step 3:

[0577] The server displays demand forecast and weather information on a dashboard using visual display means. Inputs are demand forecasting models and collected weather information, which are visualized in graph and map formats using visualization tools such as Plotly. Outputs are intuitively understandable visual data, simplifying data interpretation.

[0578] Step 4:

[0579] The server uses a sentiment analysis engine to analyze the customer sentiment data it receives. The input is text data from customer reviews and comments, and NLP is used to quantify or categorize the sentiment. The output is a sentiment score, which is used in the next step to generate notification content.

[0580] Step 5:

[0581] The server generates and sends push notification messages to the user's device based on emotional state and demand forecasts. The input is the emotional score and demand forecast results, and a generative AI model is used to generate notification messages based on prompts. The output is the notification message displayed on the user's device.

[0582] Step 6:

[0583] The user selects recommended products and confirms the order based on notifications received on their device. The input is a notification message from the server, and the user selects products using the application. The output is the selected products and their order information, which the server receives and processes.

[0584] Step 7:

[0585] The server provides incentive programs based on order history and customer sentiment to encourage service usage. Inputs are the customer's past order history and sentiment score, and an algorithm is used to present appropriate rewards. Outputs include the provision of new incentives and the resulting expected increase in service usage.

[0586] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0587] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0588] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0589] [Fourth Embodiment]

[0590] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0591] As shown in Figure 7, the 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.

[0592] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0593] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0594] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0595] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0596] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0597] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors in the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0598] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0599] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0600] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0601] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0602] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0603] This invention is a system that integrates multiple technological elements to streamline and improve the fairness of disaster relief activities. This system primarily consists of data collection, machine learning algorithms, information visualization, notification, supporter selection, and business model construction. Details of each technological element are provided below.

[0604] First, the server collects disaster information, weather information, and residential information from various data sources. This utilizes public databases and real-time APIs. The collected data is then formatted and stored in a database.

[0605] Next, the server uses machine learning algorithms to analyze the collected data. This allows it to predict the demand for relief supplies in the event of a disaster. This prediction utilizes a model based on data from past disaster patterns.

[0606] The prediction results are visualized by the server in an interactive user interface such as a dashboard. For example, a map can be used to color-code the shortages of supplies, intuitively displaying the situation in that region.

[0607] The server also notifies the supporter's terminal of this information in real time. The terminal provides the user with the received information and displays a list of areas and supplies that need assistance.

[0608] Based on the information provided through the device, users can decide which supplies to provide and in what quantities. In addition, they can review the history of their support and understand the results of their past assistance efforts.

[0609] Furthermore, the server will allocate a portion of the donations as an administrative fee to support the creation of a sustainable business model. This business model will also include the implementation of incentive programs to ensure the company's sustainability.

[0610] As a concrete example, consider a scenario where a major earthquake occurs in a certain region. The server immediately collects data and predicts the demand for drinking water and food. The prediction results are notified to the terminal, and the user makes a choice regarding assistance. This process enables rapid and appropriate assistance activities.

[0611] As described above, the system of the present invention makes it possible to effectively provide disaster relief by combining technical elements.

[0612] The following describes the processing flow.

[0613] Step 1:

[0614] The server collects relevant data such as disaster information, weather information, and population density from public databases and real-time APIs. This data is formatted and preprocessed, including imputation of missing values ​​and normalization. It is then stored in a database in preparation for subsequent processing.

[0615] Step 2:

[0616] The server uses the collected data as input to run a machine learning algorithm, which then predicts the demand for supplies during a disaster. The AI ​​model learns from past disaster patterns and is continuously updated to improve prediction accuracy.

[0617] Step 3:

[0618] The server uses visualization tools to display information on charts and maps based on predicted demand data for supplies. This visualization is updated in real time on the dashboard, visually indicating areas where supplies are in short supply.

[0619] Step 4:

[0620] The server pushes important information to the devices registered by the supporters. This notification includes details about the areas where assistance is needed and the types of supplies required.

[0621] Step 5:

[0622] The device provides the user with the received information. The user reviews the displayed information and decides how much material support to provide. Based on this information, the user can make an appropriate donation or provide materials.

[0623] Step 6:

[0624] Users can utilize a feature that allows them to check their support history on their device. This enables them to understand how the support they have provided is being used, ensuring transparency in their support activities.

[0625] Step 7:

[0626] The server incorporates a portion of the total donation amount as an administrative fee into its business model to ensure profitability as a company. This business model may include incentive programs for supporters to encourage participation in future charitable activities.

[0627] (Example 1)

[0628] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0629] While there is a need to improve the efficiency and fairness of support activities during disasters, conventional systems have faced challenges in collecting sufficient data, accurately forecasting demand, and providing timely information. Furthermore, building sustainable business models has been difficult.

[0630] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0631] In this invention, the server includes means for acquiring disaster information, weather information, and housing information as an information acquisition device, formatting the data, and storing it on a storage medium; means for estimating the demand for supplies during a disaster using a computational algorithm; and means for visualizing the demand information on a map and updating it in real time. This enables efficient and equitable disaster relief. Furthermore, by optimizing data processing using a generative model and incorporating a portion of donations as processing costs into the business model, it becomes possible to build a sustainable business model.

[0632] An "information acquisition device" is a device that acquires disaster information, weather information, and housing information, formats the data, and stores it on a storage medium.

[0633] A "computational algorithm" is a mathematical method used to estimate the demand for supplies during a disaster using collected data.

[0634] "Demand information" refers to information regarding the types and quantities of supplies needed in a specific area during a disaster.

[0635] "Visualization on a map" is a method of using maps to show the shortage of supplies and the areas that need assistance.

[0636] "Real-time updates" means that information is updated immediately as soon as data is acquired.

[0637] A "generative model" is a model that utilizes AI technology to learn generalized data patterns and make more accurate predictions.

[0638] A "storage medium" is a physical or electronic medium used to store data.

[0639] A "sustainable business model" is a business method that brings economic benefits to an organization in a way that can be sustained over the long term.

[0640] A "reward program" is a mechanism that provides incentives to support participants to encourage specific behaviors.

[0641] This invention is a system that enables efficient and equitable support activities during disasters. In this system, a server plays a central role. The server acquires disaster information, weather information, and housing information using public databases and real-time APIs. The server, functioning as an information acquisition device, formats this data and stores it on a storage medium. Specifically, the server collects weather data through the OpenWeatherMap API and acquires disaster information from local government databases.

[0642] The collected data is analyzed using machine learning algorithms. The server uses a generative AI model to learn from past disaster data and predict specific supply needs during disasters. This prediction calculates the demand for necessary supplies such as drinking water and food. For example, by referencing current weather conditions based on past typhoon data, the system can accurately estimate the supplies needed in disaster-stricken areas.

[0643] The analysis results are updated in real time by the server and visualized on a map. The server uses the map to color-code the areas where supplies are lacking, indicating which regions are in particular need of assistance. This makes it easier for users to intuitively understand the information. The server also notifies information terminals of detailed information regarding the need for assistance. Mobile push notifications and web notifications are used as needed.

[0644] Based on this information, users decide which supplies to provide and in what quantities. The user's device allows them to review their aid history, enabling them to understand what kind of assistance they have provided and to which regions.

[0645] Furthermore, the server incorporates a portion of donations as processing costs into its business model. This process supports the creation of a sustainable business model and includes an incentive program for supporters. This allows users to receive rewards such as points for their support activities.

[0646] As a concrete example, if a major earthquake occurs in a certain region, the server will immediately collect data on the damage and weather, and predict the demand for drinking water and food. The prediction results will be notified to the user's terminal, and the user can then quickly take action to provide assistance based on that information. An example of a prompt message for the generating AI model would be, "Based on past disaster data for region X, please predict the supplies that will be needed in the next week."

[0647] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0648] Step 1:

[0649] The server, acting as an information acquisition device, retrieves disaster information, weather information, and housing information from public databases and real-time APIs. The input for this step consists of the latest information from multiple data sources. The acquired raw data is converted to a format and stored on the system's storage medium. Specifically, weather information is retrieved in JSON format from the OpenWeatherMap API, and the necessary items are extracted and stored in the database.

[0650] Step 2:

[0651] The server begins analyzing the collected data using a generative AI model. The input for this step is the disaster and weather data formatted in the previous step. The server uses machine learning algorithms to predict the demand for relief supplies during a disaster based on past disaster data. Through this process, it is possible to specifically identify areas where drinking water and food are particularly needed. The output is regional demand forecast data for supplies.

[0652] Step 3:

[0653] The server visualizes the analysis results on an interactive dashboard. The input for this step is the analyzed demand forecast data. The server displays this data on a map using color coding, visually highlighting areas of shortage. Specifically, areas shown in red indicate severe shortages, making it easy for users to understand intuitively. The output is visualized support information accessible to the user.

[0654] Step 4:

[0655] The server notifies information terminals of information generated in real time. The input for this step is information from a visualized map. Push notifications to mobile devices and pop-up notifications to web browsers are used as notification methods. Specifically, it sends specific alerts such as "There is a shortage of drinking water in area X." The output is detailed disaster relief information that can be viewed on the user's device.

[0656] Step 5:

[0657] The user decides which supplies to provide and in what quantities based on the information provided via the terminal. The input for this step is information about the assistance notified by the server. The user can open the terminal application, select the assistance content, and view the history. For example, the user might input the instruction, "Send 100 liters of drinking water to area X." The output is the specific assistance action based on the user's decision.

[0658] Step 6:

[0659] To ensure the sustainability of system operations, the server allocates a portion of donations as processing costs and establishes a business model. The input for this step is donation information from users. The server adds points to user accounts based on the donation amount, maintaining an incentive program. Specifically, processing is carried out based on the rule "award 1 point for every 100 yen donated." The output is incentive data to promote sustainable support activities.

[0660] (Application Example 1)

[0661] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0662] Disaster relief efforts require the rapid acquisition of accurate information and the appropriate allocation of resources based on that information. However, conventional systems are insufficient in terms of the speed of information gathering and notification, as well as the flexibility in selecting the type of support to provide. In particular, there are still challenges in providing real-time crisis management information using mobile devices. Furthermore, there is room for improvement in securing incentives for supporters and in the management system for donations.

[0663] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0664] In this invention, the server includes, as a data collection means, means for acquiring disaster information, weather information, and human habitation information, formatting the data, and storing it in a data management device; means for predicting the resources needed during a disaster using a machine learning algorithm; and means for providing crisis information to mobile information terminals in real time and issuing visual and audible warnings. This makes it possible to quickly and accurately acquire the information necessary for support activities and to provide effective notifications to supporters.

[0665] A "data collection means" is a device that acquires disaster information, weather information, and human habitation information, formats this data, and stores it in a data management device.

[0666] A "machine learning algorithm" is a method for learning past disaster patterns and predicting the resources needed during a disaster.

[0667] "Visualization methods" refer to technologies that visually display resource demand information using maps or other means, and update it in real time as it changes.

[0668] A "notification means" is a function that informs the support device of the need for support and resource information.

[0669] "Selection and confirmation means" refers to a mechanism that allows users to choose the type of support they received and review their history.

[0670] An "economic model" is a design that allows for sustainable business operations by allocating a portion of donations as administrative fees.

[0671] A "mobile information terminal" refers to a portable device that can be moved around and has the function of providing real-time crisis information and issuing warnings visually and audibly.

[0672] "Geospatial information" refers to information related to geographical location and is used to quickly grasp the situation during disasters.

[0673] A "merit program" is a system of incentives offered to supporters to encourage their participation in support activities.

[0674] The system for implementing this invention functions primarily around a server. The server first acquires disaster information, weather information, and human habitation information using data collection means, and then formats and stores them in a data management device. The collected data is analyzed by machine learning algorithms to predict the demand for necessary resources during a disaster. This prediction is visualized in real time on a map and presented to the user.

[0675] The server also has the ability to notify mobile devices of crisis information in real time and issue warnings using both visual and audible means. This allows users to immediately understand the crisis and choose appropriate support actions. For example, when an earthquake occurs in a certain area, predictions of shortages of drinking water and food can be quickly conveyed to the user in conjunction with a map.

[0676] Finally, supporters will benefit from a merit program to encourage active participation. This will create a mechanism to incorporate a portion of donations as an administrative fee into the new economic model. All of these processes will be server-centric and operated quickly and accurately.

[0677] By utilizing a generative AI model, efficient support activities are facilitated through prompt messages such as the following: "We are developing an application that uses machine learning to predict the demand for relief supplies in real time during disasters. Please tell us about the main functions of this application and the methods for user notifications."

[0678] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0679] Step 1:

[0680] The server retrieves disaster information, weather information, and human habitation information from multiple data sources. Input for this data comes from various APIs and public databases. The server formats this data and stores it in a unified format in a data management device. At this stage, the data is organized and immediately accessible.

[0681] Step 2:

[0682] The server applies a machine learning algorithm based on the stored data. The input is the data organized in Step 1, and the output is a prediction of resource demand during a disaster. The server uses past disaster patterns as a model to improve prediction accuracy. Specifically, it performs data calculations to simulate shortages of drinking water and food in a particular region.

[0683] Step 3:

[0684] The server visualizes the prediction results in real time. The input is the prediction data from step 2, and the output is resource demand information displayed on a map. The server provides information through a user interface, visually indicating shortages with colors and icons.

[0685] Step 4:

[0686] The server notifies the supporter's terminal of the information. The input at this time is the geographical information visualized in step 3, and the output is an alarm message displayed on the terminal's screen. The terminal issues an alarm using both visual and auditory information to prompt the supporter to take swift action.

[0687] Step 5:

[0688] The user selects support activities based on the information presented. The input consists of disaster situation and resource information displayed on the terminal, and the user decides which support to provide based on their own judgment. The output is the selected support content and a record of the history. Specifically, the user's actions send an indication of their intention to provide support supplies to the server.

[0689] Step 6:

[0690] The server applies a merit program and encourages supporter participation. The inputs are the supporter's selection history and donation amount, and the output is an incentive for the supporter. Based on an economic model, a portion of the donations is allocated as an administrative fee, ensuring sustainable support activities.

[0691] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0692] This invention is a system that combines an emotion engine to streamline, equitably, and effectively carry out disaster relief activities. The system mainly consists of data collection, machine learning algorithms, information visualization, notification, emotion recognition, supporter selection, and business model construction.

[0693] First, the server collects disaster information, weather information, and population information from various data sources. This data is formatted and stored in a database. Next, the server uses machine learning algorithms to predict the demand for supplies and builds a model based on past disaster patterns. The predicted information is visualized by the server on a dashboard and displayed intuitively using maps and other visuals. This visualization makes it possible to see at a glance which areas need assistance and which supplies are lacking.

[0694] In addition, the server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine evaluates the user's current emotional state based on their past response data and adjusts notification content and incentive programs accordingly. For example, if the server recognizes positive emotions, it will send proactive messages regarding support. This function facilitates the provision of support in the most optimal way for each individual supporter.

[0695] Furthermore, the server tracks emotional states in real time to determine the appropriate timing for providing support. The emotion engine functions as a tool to support decision-making regarding material provision and donations, playing a role in guiding user decision-making.

[0696] As a concrete example, suppose a flood occurs in a certain area. The server quickly collects data and predicts the demand for drinking water. At this time, the emotion engine analyzes the emotions of the helpers and sends notifications to their devices prompting appropriate assistance as needed. For example, a message such as, "Many victims need assistance. Your help can make a big difference," might be sent. In this way, emotion-based information is provided, maximizing the effectiveness of the assistance.

[0697] This system aims not only to improve the efficiency of support activities but also to enable emotion-based, personalized support, thereby increasing social and economic value.

[0698] The following describes the processing flow.

[0699] Step 1:

[0700] The server collects disaster information, weather data, and human habitation information from public databases and APIs. The collected data is formatted and stored in a database. This provides a foundation for understanding the latest situation.

[0701] Step 2:

[0702] The server analyzes collected data using machine learning algorithms. It utilizes models trained on past disaster patterns to predict demand for supplies. These predictions are updated in real time, contributing to a rapid response during disasters.

[0703] Step 3:

[0704] The server visually displays predicted material demand data on a map. The displayed dashboard color-codes areas with high demand, allowing users to see at a glance where assistance is needed.

[0705] Step 4:

[0706] The server references the user's past emotional data and uses an emotion engine to analyze their current emotional state. This information is used to determine what kind of support the user desires.

[0707] Step 5:

[0708] The server sends customized messages to the device based on the user's emotional state. For example, if positive emotions are detected, an encouraging message will be sent. Incentives tailored to the emotions may also be offered.

[0709] Step 6:

[0710] The terminal displays a customized message sent from the server to the user. Based on this, the user decides what supplies to provide, in what quantities, or how much to donate.

[0711] Step 7:

[0712] Users can view their support history on their device to understand how their past support has been utilized. This historical information helps users plan how they will provide support in the future.

[0713] Step 8:

[0714] The server will allocate a portion of the donations as a management fee and incorporate it into a new business model. This model will include an incentive program to encourage future charitable activities.

[0715] (Example 2)

[0716] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0717] During disasters, there is a need to supply relief supplies quickly and accurately, and to carry out relief activities efficiently and effectively. Conventional systems have problems such as insufficient information gathering and visualization of relief efforts, and difficulty in promoting relief activities while considering the emotional state of individual supporters. This invention aims to solve these problems and realize efficient and emotion-based relief.

[0718] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0719] In this invention, the server includes information gathering means for collecting disaster-related information and storing it in a standard format, analysis means for predicting the supply and demand of goods using machine learning technology, and information visualization means for visually displaying and updating supply and demand information. This enables rapid information gathering and analysis, allows for the provision of emotion-based, personalized support, and improves the efficiency and effectiveness of support activities.

[0720] An "information gathering means" is a system component that has the function of collecting disaster-related information, organizing it in a standard format, and storing it.

[0721] "Analysis tools" refer to system components that analyze data collected using machine learning techniques to predict the supply and demand of goods.

[0722] An "information visualization tool" is a system component that visually displays analyzed supply and demand information so that users can understand it intuitively.

[0723] "Emotion recognition functionality" is a technology that analyzes the user's emotional state and provides personalized information notifications based on that analysis.

[0724] "Selection and confirmation means" refers to a system component that has the function of allowing supporters to decide what kind of support to provide and to check past support history.

[0725] "Commercial means" refers to system components that integrate a portion of donations as a fee into a new business model.

[0726] This invention is a system in which a server, a terminal, and a user work together in cooperation, and aims to efficiently and effectively carry out support activities during disasters. This system consists of information gathering functions, analysis functions, information visualization functions, and emotion recognition functions.

[0727] The server retrieves disaster information, weather information, and population information from various data sources. Specifically, it collects information from internet APIs, social networking services, and real-time data provided by local governments. This information is organized in a standard format and stored in a database.

[0728] Based on this data, the server uses machine learning algorithms to predict the supply and demand of goods. The software used will primarily consist of machine learning libraries such as TensorFlow and PyTorch. The server learns from past disaster data and builds a predictive model to estimate the types and quantities of supplies needed.

[0729] The analyzed information is visualized by the server and displayed in charts and maps. Tools such as the Google Maps API and D3.js are used for visualization. This allows users to understand at a glance which areas require particular attention.

[0730] Through its emotion recognition function, the server analyzes the user's emotional state. The results of this analysis are sent to the user's device as personalized notification information. The emotion engine uses a machine learning model trained on past response data to quantify the user's emotions and propose appropriate notifications and incentives. These notifications maximize the user's motivation for support activities.

[0731] As a concrete example, consider a case where a flood occurs in a certain area. The server quickly collects and analyzes data from the affected area and predicts the demand for drinking water. At this time, the emotion engine analyzes the emotions of the helpers and sends notifications to the device that encourage the most appropriate support based on that analysis. For example, a message such as, "Many victims need help. Your support can make a big difference," might be sent. Other examples of prompts using the generative AI model include, "Please tell me how to streamline disaster relief activities," and "How can I build a model to predict the demand for relief supplies during a flood?"

[0732] This system enables rapid and effective support activities by providing individual supporters with emotionally appropriate support based on collected data and analytical information.

[0733] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0734] Step 1:

[0735] The server retrieves input data from multiple data sources. This input data includes disaster information, weather data, demographic data, and so on. The server processes this information into a standard format and outputs the formatted data to the database. Specifically, it retrieves data via an internet API and then processes and formats it.

[0736] Step 2:

[0737] The server takes formatted data stored in a database as input and applies a machine learning algorithm. The data calculation generates a predictive model based on past disaster data to forecast the supply and demand of goods. The output is the predicted supply and demand information; specifically, it outputs a list of the types and quantities of goods that will be needed next. The system uses a machine learning library to train the data and perform predictions.

[0738] Step 3:

[0739] The server receives predicted supply and demand information as input and passes it to visualization software. The output is specific information displayed as visualized maps and graphs. In operation, it uses a visualization library to display information on a map and updates the visual dashboard.

[0740] Step 4:

[0741] The server receives emotion data from the user database as input and performs analysis using an emotion engine. As part of data processing based on the input data, it generates a model using the user's past emotional response data to evaluate the user's emotional state. The output is a notification message optimized for the emotional state. The process involves executing an emotion recognition algorithm and generating notification content based on the analysis results.

[0742] Step 5:

[0743] The server takes the analysis results obtained from the emotion engine as input and sends notifications to the user's device as needed. Based on the input data, it generates personalized notification messages and outputs them to the device. As a concrete example of its operation, it sends a message to the device such as "Your help is needed. Your help will be a great help," encouraging the user to engage in support activities. In this process, prompt messages can also be utilized using a generative AI model.

[0744] (Application Example 2)

[0745] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0746] Traditional food delivery services have struggled to suggest the most suitable products based on customer emotions and individual needs, limiting their ability to improve customer satisfaction. Furthermore, the difficulty in accurately predicting deliveries while considering weather and congestion also limited service efficiency. Solving these challenges is necessary to optimize the customer experience and improve service efficiency and profitability.

[0747] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0748] In this invention, the server includes, as a data collection means, means for acquiring weather information, human residence information, order history, and customer sentiment information, formatting the data, and storing it in an information storage means; means for predicting demand using machine learning algorithms and building a model based on past patterns; and means for visually displaying demand information and weather information and communicating it intuitively to service providers. This enables optimal product suggestions that take into account the customer's emotional state and accurate delivery predictions according to weather and congestion levels.

[0749] "Data collection means" refers to technology that has the function of acquiring weather information, human residence information, order history, and customer sentiment information, formatting the data, and storing it in an information storage means.

[0750] A "machine learning algorithm" is a technology that uses mathematical methods to predict demand based on past patterns.

[0751] "Visual display means" refers to technologies for visually displaying demand information and weather information and communicating it intuitively to service providers.

[0752] A "sentiment analysis engine" is a technology that analyzes a customer's emotional state and generates individually optimized notification content.

[0753] An "incentive program" is a technology that provides benefits and rewards to users to encourage service usage.

[0754] "Information storage means" refers to technology that systematically organizes acquired data and stores it so that it can be used for later analysis and processing.

[0755] In this application, the system first uses a server to acquire weather information, human residence information, order history, and customer sentiment information using data collection means. Then, this information is formatted and stored in an information storage means. A relational database management system (RDBMS) can be used for data formatting.

[0756] The server then uses machine learning algorithms to predict demand based on past patterns. Machine learning libraries such as Scikit-learn are used in this process. The predicted demand and weather information are visually displayed on a dashboard using visual visualization tools. Data visualization tools such as Plotly can be used to implement this dashboard.

[0757] Furthermore, an emotion analysis engine is used to analyze the customer's emotional state and send optimized notifications to the user's information device. NLP libraries (such as NLTK and spaCy) are used for emotion analysis. The notification content is sent as a push notification to smartphones and other devices.

[0758] Based on the notifications sent, users can select products suggested by the application and review their history. The server also has the functionality to implement incentive programs for users and promote service usage.

[0759] As a concrete example, on a rainy day, a server might send a message saying, "We recommend a hot pot dish." In this case, the following prompt would be used for the AI ​​generation model: "Based on the current weather information and the customer's order history, suggest the most suitable food delivery. Analyze how the customer's sentiment has changed compared to the previous year, and generate a notification message based on the results."

[0760] This will enable the provision of individualized services tailored to customer needs, leading to improved customer satisfaction and increased service efficiency.

[0761] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0762] Step 1:

[0763] The server uses data collection methods to gather weather information APIs, human location data, user order history data, and customer sentiment data. It uses online-accessible APIs and user input data as input, storing them in a unified database format. As output, it saves data in a format suitable for searching and analysis.

[0764] Step 2:

[0765] The server uses the collected data to perform demand forecasting using machine learning algorithms. Specifically, it uses libraries such as Scikit-learn to learn demand patterns from past order history and weather conditions. The input is a formatted dataset, and the output is the creation of a demand forecasting model. The resulting demand forecast is then used in the next processing step.

[0766] Step 3:

[0767] The server displays demand forecast and weather information on a dashboard using visual display means. Inputs are demand forecasting models and collected weather information, which are visualized in graph and map formats using visualization tools such as Plotly. Outputs are intuitively understandable visual data, simplifying data interpretation.

[0768] Step 4:

[0769] The server uses a sentiment analysis engine to analyze the customer sentiment data it receives. The input is text data from customer reviews and comments, and NLP is used to quantify or categorize the sentiment. The output is a sentiment score, which is used in the next step to generate notification content.

[0770] Step 5:

[0771] The server generates and sends push notification messages to the user's device based on emotional state and demand forecasts. The input is the emotional score and demand forecast results, and a generative AI model is used to generate notification messages based on prompts. The output is the notification message displayed on the user's device.

[0772] Step 6:

[0773] The user selects recommended products and confirms the order based on notifications received on their device. The input is a notification message from the server, and the user selects products using the application. The output is the selected products and their order information, which the server receives and processes.

[0774] Step 7:

[0775] The server provides incentive programs based on order history and customer sentiment to encourage service usage. Inputs are the customer's past order history and sentiment score, and an algorithm is used to present appropriate rewards. Outputs include the provision of new incentives and the resulting expected increase in service usage.

[0776] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0777] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0778] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0779] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0780] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0781] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0782] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0783] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0784] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0785] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0786] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0787] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0788] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0789] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0790] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0791] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0792] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0793] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0794] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0795] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0796] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0797] The following is further disclosed regarding the embodiments described above.

[0798] (Claim 1)

[0799] As a means of data collection, there is a means of acquiring disaster information, weather information, and human habitation information, formatting the data, and storing it in a database.

[0800] A method for predicting the necessary supplies during a disaster using machine learning algorithms,

[0801] A means of visualizing the demand information for supplies on maps, etc., and updating it in real time,

[0802] A means of notifying supporters of the need for assistance and information on available supplies on their devices,

[0803] A means by which users can select the type of support they receive and view their history,

[0804] A system that includes a means of incorporating a portion of donations as an administrative fee into a new business model.

[0805] (Claim 2)

[0806] The system according to claim 1, comprising an AI algorithm that learns past disaster patterns and means for predicting the demand for supplies.

[0807] (Claim 3)

[0808] The system according to claim 1, comprising means for providing an incentive program to supporters.

[0809] "Example 1"

[0810] (Claim 1)

[0811] As an information acquisition device, it includes means for acquiring disaster information, weather information, and housing information, formatting the data, and storing it on a storage medium.

[0812] A method for estimating the demand for supplies during a disaster using a computational algorithm,

[0813] A means of visualizing demand information on a map and updating it in real time,

[0814] A means of notifying information terminals of the need for assistance and information on available supplies,

[0815] A means by which the user can select the support content and check the history,

[0816] One way to incorporate a portion of the donations as processing costs into a new business model,

[0817] A system that includes means for optimizing data processing using generative models to improve system efficiency and fairness.

[0818] (Claim 2)

[0819] The system according to claim 1, which learns past disaster patterns and utilizes a generative AI model to predict supply demand with greater accuracy.

[0820] (Claim 3)

[0821] The system according to claim 1, further comprising means for providing a reward program to encourage action to support participants.

[0822] "Application Example 1"

[0823] (Claim 1)

[0824] The data collection means include acquiring disaster information, weather information, and human habitation information, formatting the data, and storing it in a data management device.

[0825] A method for predicting the resources needed during a disaster using machine learning algorithms,

[0826] A means of visualizing resource demand information on maps, etc., and updating it in real time,

[0827] A means of notifying the support device of the need for support and resource information,

[0828] A means by which users can select the type of support they receive and view their history,

[0829] One way to incorporate a portion of donations as an administrative fee into a new economic model,

[0830] A means of providing real-time crisis information to mobile information terminals and issuing warnings visually and audibly,

[0831] A means of comfortably understanding the situation using geospatial information,

[0832] A system that includes this.

[0833] (Claim 2)

[0834] The system according to claim 1, comprising an AI algorithm that learns past disaster patterns and means for predicting resource demand.

[0835] (Claim 3)

[0836] The system according to claim 1, comprising means for providing a merit program to supporters.

[0837] "Example 2 of combining an emotion engine"

[0838] (Claim 1)

[0839] Information gathering means for collecting disaster-related information and storing it in a standard format,

[0840] An analytical method for predicting the supply and demand of goods using machine learning technology,

[0841] A means of visually displaying and updating supply and demand information,

[0842] A communication method that uses emotion recognition functionality to provide personalized notifications to supporters,

[0843] Supporters can choose the content of their support and review the history of that support, and

[0844] A system that includes commercial methods that integrate donations as a portion of the fees into new business practices.

[0845] (Claim 2)

[0846] The system according to claim 1, which incorporates a machine learning function for predicting the demand for supplies based on a disaster.

[0847] (Claim 3)

[0848] The system according to claim 1, which analyzes the emotional state of supporters using an emotion engine and provides an incentive program.

[0849] "Application example 2 when combining with an emotional engine"

[0850] (Claim 1)

[0851] The data collection means includes acquiring weather information, human residence information, order history, and customer sentiment information, formatting the data, and storing it in an information storage means.

[0852] A method for predicting demand using machine learning algorithms and building models based on past patterns,

[0853] A means of visually displaying demand information and weather information and communicating it intuitively to service providers,

[0854] A means of notifying users of recommended products and their availability period on their information terminals,

[0855] A means by which users can select and view the history of proposed services,

[0856] A system that includes means for incorporating new business models based on usage patterns.

[0857] (Claim 2)

[0858] The system according to claim 1, comprising means for analyzing the customer's emotional state using an emotion analysis engine and optimizing the content of notifications.

[0859] (Claim 3)

[0860] The system according to claim 1, comprising means for providing an incentive program to users and promoting the use of the service. [Explanation of Symbols]

[0861] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. As a means of data collection, there is a means of acquiring disaster information, weather information, and human habitation information, formatting the data, and storing it in a database. A method for predicting the necessary supplies during a disaster using machine learning algorithms, A means of visualizing the demand information for supplies on maps, etc., and updating it in real time, A means of notifying supporters of the need for assistance and information on available supplies on their devices, A means by which users can select the type of support they receive and view their history, A system that includes a means of incorporating a portion of donations as an administrative fee into a new business model.

2. The system according to claim 1, comprising an AI algorithm that learns past disaster patterns and means for predicting the demand for supplies.

3. The system according to claim 1, comprising means for providing an incentive program to supporters.

Images