system

Abstract

Provide a system. The solution includes: a means for analyzing data collected from the poor, non-governmental organizations, and governments, and allocating funds based on a specific methodology; means for storing and pre-processing the collected data; A means for generating a support plan using a machine learning algorithm; A means for determining allocation of funds based on the generated support plan and notifying the user; A means of gathering user feedback and adjusting assistance plans; A system including:

Description

[Technical Field]

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

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

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

[0004] In modern society, providing funds to the poor and providing effective support is a challenge. Traditional methods often result in inappropriate allocation of funds and in insufficient evaluation of the effectiveness of support. Furthermore, there is a lack of mechanisms for efficiently reflecting the funding and its results in feedback. This leads to problems such as the lack of sustained effectiveness of poverty reduction efforts and the difficulty of seeing social improvement. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means.

[0006] A system including a means for analyzing data collected from the poor, non-governmental organizations, and governments and allocating funds based on specific methods, a means for storing and pre-processing the collected data, a means for generating a support plan using a machine learning algorithm, a means for determining fund allocation based on the generated support plan and notifying users, and a means for collecting feedback from users and adjusting the support plan, enables efficient and effective provision of funds and support to the poor.

[0007] In particular, the closeness and accuracy of assistance can be improved by incorporating measures to collect activity reports from non-governmental organizations and use them to evaluate the effectiveness of assistance, as well as measures to generate optimal assistance plans from the collected data using machine learning algorithms.

[0008] This system will enable appropriate allocation of funds and rapid feedback, making it possible to sustain the effects of poverty reduction.

[0009] "Poor" refers to people or families who are financially disadvantaged and have difficulty meeting basic necessities of life.

[0010] A "non-governmental organization" is an organization that is not a government agency but has public interest goals such as social welfare, environmental protection, and human rights protection.

[0011] "Government" refers to public institutions such as national and local governments and the policies and programs implemented by those institutions.

[0012] "Data" is a record of information, a collection of facts, figures, text, etc. that has been measured in some way.

[0013] "Analysis" refers to the process of systematically examining collected data and extracting meanings and patterns from it.

[0014] "Fund allocation" refers to the allocation of a planned amount of funds for a specific purpose or target.

[0015] "Means" refers to the methods or devices used to achieve a particular purpose.

[0016] "Storage" refers to storing data so that it is not lost and making it available for retrieval when needed.

[0017] "Preprocessing" refers to preparatory work such as cleaning and formatting data before data analysis or machine learning.

[0018] A "machine learning algorithm" is a computer program that learns from data, recognizes patterns in it, and makes predictions or classifications.

[0019] A "support plan" refers to a specific plan for providing assistance and support to the poor.

[0020] "Notification" refers to a message or communication intended to convey specific information to a target audience.

[0021] "Feedback" refers to the process of collecting reactions and opinions on actions and results and reflecting them in future actions.

[0022] "Adjustment" refers to changing plans and methods to suit goals and conditions and to optimize them.

[0023] A "system" refers to a set of components that interact with each other and are integrated to perform a specific function. [Brief explanation of the drawings]

[0024] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram illustrating a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0025] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0027] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0028] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0029] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0030] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0031] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0032] [First embodiment]

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

[0034] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0035] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0036] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0037] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0038] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0039] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0041] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0042] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0043] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0044] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0045] This invention is a system for efficiently providing funds and support to the poor. This system mainly consists of four components: a data collection module, a fund management module, a user interface, and an algorithm module.

[0046] System Configuration

[0047] 1. Server: Data collection module

[0048] The server collects data from the poor, non-governmental organizations (NGOs), and governments. This data includes users' annual income, household composition, housing situation, health status, NGO activity reports, and government welfare policy data. For example, the server periodically sends questionnaire forms to users and stores the collected information in a database. It also obtains data in real time from NGOs and governments via APIs.

[0049] 2. Server: Funds Management Module

[0050] The server allocates funds to each user based on the collected data. The collected data is first preprocessed and stored in a database. Machine learning algorithms then analyze the data to generate a support plan that best suits each user's situation. For example, a specific household may receive 30,000 yen in monthly support, with additional funds allocated to education-related programs. This allocation of funds is done fairly and effectively based on the algorithm.

[0051] 3. Terminal: User Interface

[0052] An interface that displays the support results is provided on the device (user's mobile device or PC). Users can check the details of their support and provide feedback if necessary. For example, there is a function to report the status of fund use and whether additional support is needed. The user interface is also designed to be intuitive and easy to use, allowing users to quickly find the information they need.

[0053] 4. Server: Algorithm Module

[0054] The server uses machine learning algorithms to analyze the collected data and generate optimal support plans. The algorithms take into account past and current user data to predict the most effective support methods. For example, they could provide extra support to families experiencing a sudden drop in income and monitor the effectiveness of that support. This algorithm can improve the closeness and accuracy of support.

[0055] This system efficiently executes a series of processes, from data collection to generating assistance plans, allocating funds, and collecting and adjusting feedback. This optimizes the provision of funds and support to the poor and improves society. Specifically, the server collects and analyzes data, generates assistance plans based on the results, and notifies users. Users receive the assistance provided and send the results back to the server as feedback. In this way, the entire system is constantly updated, enabling it to continue providing optimal assistance.

[0056] The processing flow will be explained below.

[0057] Step 1: Collect data

[0058] The server collects questionnaires and registration information from the poor, with users entering information such as their annual income, household composition, housing situation, and health status.

[0059] The server receives activity reports from non-governmental organizations (NGOs), collecting data such as the type of support provided by the NGOs, the number of people who received support, and the success of their efforts.

[0060] The server retrieves policy information and assistance program data from public government databases, collecting information such as policy implementation status, budget allocation, and target demographics.

[0061] All collected data is stored in a database.

[0062] Step 2: Preprocessing the data

[0063] The server preprocesses all collected data, for example by imputing missing data and correcting outliers.

[0064] Once the data is cleansed, it is standardized and converted into a format that is easy for machine learning algorithms to process.

[0065] Step 3: Create a support plan

[0066] The server uses machine learning algorithms to generate a support plan that is optimal for each user's situation.

[0067] The algorithm uses past data and patterns to predict what type of support will be most effective.

[0068] For example, this includes specific measures such as "providing 30,000 yen in support per month" or "supporting participation in specific educational programs."

[0069] Step 4: Allocate funds

[0070] The server determines the specific allocation of funds to each user based on the generated support plan.

[0071] For example, a detailed funding allocation plan would be created, allocating additional support to families with children who earn below a certain monthly income.

[0072] Step 5: Notify and gather feedback

[0073] The device will then notify the user of the support plan and assistance details, which will then be displayed on the user's mobile device or PC.

[0074] Users can view details of their assigned assistance in the app or web portal.

[0075] Users provide feedback on how effective the support was, report on the use of funds, and whether they need additional assistance.

[0076] Step 6: Analyze feedback and adjust support plans

[0077] The server analyzes user feedback and evaluates the effectiveness of the support plan.

[0078] If necessary, update your support plan and adjust the next support offer.

[0079] For example, if a particular support is found to be ineffective, the content will be modified appropriately.

[0080] The system efficiently carries out a series of processes from data collection and analysis, to fund allocation, feedback collection, and further adjustments.

[0081] Example 1

[0082] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0083] In order to effectively and efficiently provide funding and support to the poor, a system that smoothly collects data, analyzes it, allocates funds, provides a user interface, and collects and evaluates feedback is required. Conventional systems have issues with uncertainty in data collection, fairness in fund allocation, and insufficient reflection of user feedback, making it difficult to provide optimal support.

[0084] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0085] In this invention, the server includes means for analyzing data collected from the poor, non-governmental organizations, and the government and allocating funds based on a specific methodology, means for storing and pre-processing the collected data, means for generating a support plan using a machine learning algorithm, means for determining fund allocation based on the generated support plan and notifying the user, means for collecting feedback via the user's terminal and adjusting the support plan, means for providing an intuitive and easy-to-use interface to the terminal, and means for the server to periodically distribute questionnaire forms to users to collect data. This enables efficient data collection, accurate fund allocation, and proactive feedback collection and evaluation.

[0086] "Data collection" is the process of gathering information of interest from various sources.

[0087] "Analysis" is the process of converting collected data into an understandable form and evaluating its content.

[0088] Funding allocation is the process of effectively allocating available funds according to user and organizational needs.

[0089] "Preprocessing" is the process of cleaning and transforming collected data to improve its quality.

[0090] A "machine learning algorithm" is a computational method that learns patterns and rules from data and makes predictions and judgments based on them.

[0091] A "support plan" is a plan that describes the specific content and methods of support to be provided to users and organizations based on the analyzed data.

[0092] "Notification" is the process by which the system notifies the user of information.

[0093] "Feedback" is the process by which a user provides a response or opinion to the system in response to the assistance provided.

[0094] An "interface" is a screen or operating means by which a user interacts with a system.

[0095] A "survey form" is a paper or electronic document containing specific questions that is used to collect information from a user.

[0096] This invention is a system for efficiently providing funding and support to the poor. The system consists of four main components: a data collection module, a fund management module, a user interface, and an algorithm module.

[0097] Data Collection Module

[0098] The server collects various data from the poor, non-governmental organizations (NGOs), and governments. This data includes users' annual income, household composition, housing situation, health status, NGO activity reports, and government welfare policy data. Specifically, the server periodically distributes questionnaire forms to users and stores the collected information in a database. Data is also obtained in real time from NGOs and governments via APIs. A database management system such as MySQL (registered trademark) is used to store the data.

[0099] For example, the server sends a push notification to the user asking, "What is your current income?", and when the user responds, the data is stored in a database. NGO activity reports are automatically collected and stored through API requests.

[0100] Money Management Module

[0101] The server preprocesses the collected data, stores it in a database, and then analyzes it using a machine learning algorithm. The results are used to generate a support plan that is optimal for each user's situation. The preprocessing uses Python's Pandas library to fill in missing data and remove outliers.

[0102] For example, the data is cleaned using Python and then input into a machine learning model using TENSORFLOW (registered trademark). This model generates a support plan, such as "If income is less than ¥100,000, provide ¥10,000 in support per month."

[0103] User Interface

[0104] The device provides a user interface on their mobile device or PC that displays details of their donation, allowing them to provide feedback on the status of fund use and whether additional donations are needed. This interface is built using front-end frameworks such as React.

[0105] For example, users can use an in-app form to answer the question "How did you use the funds you received?" and then send that feedback to the server.

[0106] Algorithm Module

[0107] The server then feeds the collected feedback data back into the algorithm to evaluate the effectiveness of the assistance provided. This analysis is performed using machine learning libraries such as TensorFlow and Scikit-learn. After evaluating the effectiveness, the assistance plan is adjusted as necessary.

[0108] For example, feedback data can be input into the model, and the model can be retrained based on newly acquired information to optimize the next assistance plan.

[0109] Prompt Sentence Examples

[0110] Prompt: Describe a system for providing optimal assistance plans to the poor. Using the data below, detail the process from collecting data to generating assistance plans, allocating funds, and gathering feedback.

[0111] User's annual income: 100,000 yen

[0112] Family composition: 5 people family

[0113] Housing Status: Rented

[0114] Health: Good

[0115] NGO Activity Report

[0116] Government welfare policy data

[0117] The system efficiently executes a series of processes, from data collection to generating support plans, allocating funds, and collecting and adjusting feedback, thereby optimizing funding and support for the poor and achieving social improvement.

[0118] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0119] Step 1: Data collection

[0120] The server collects data from poor users, non-governmental organizations (NGOs), and the government. This process involves sending periodic questionnaire forms and retrieving data in real time using an API. Specifically, the server sends a push notification to the user's smartphone asking, "What is your current income?" and stores the data the user responds to in a database. It also receives activity reports and welfare policy data in JSON format from the NGO and government via API, which it stores in the database. The input in this step is the questionnaire responses and JSON data retrieved from the API, and the output is data stored in the database.

[0121] Step 2: Data Preprocessing

[0122] The server preprocesses the collected data. Specifically, it completes missing data, removes outliers, and standardizes data formats. It uses Python's Pandas library to clean the data and, if necessary, completes missing data with average values. For example, if income data is missing, it completes the average income value. The input in this step is raw data obtained from the database, and the output is the clean data after preprocessing.

[0123] Step 3: Create a support plan

[0124] The server inputs the preprocessed data into a machine learning algorithm to generate an optimal support plan. The algorithm uses machine learning libraries such as TensorFlow and Scikit-learn. Specifically, it determines the optimal financial support amount and program for each user, taking into account factors such as income, family composition, housing situation, and health status. For example, it generates an output such as "If income is less than 100,000 yen, 10,000 yen in support will be provided per month." The input in this step is the clean data after preprocessing, and the output is the generated support plan.

[0125] Step 4: Notification of support plan

[0126] The server notifies the user's device of the details of the generated support plan. Specifically, it provides an interface for displaying the details of the support plan and funding allocation on the user's mobile device or PC. A front-end framework such as React is used to provide an intuitive and easy-to-use UI for the user. For example, when the user opens the app, it displays the message, "Your support plan is for a monthly funding of 10,000 yen." The input in this step is the generated support plan, and the output is a notification displayed on the user's device.

[0127] Step 5: Gather feedback

[0128] The terminal provides a function to collect feedback from users. Users can report on the support they received, their use of the funds, and the need for additional support. Specifically, users use a form within the app to answer questions such as "How did you use the funds you received?", and the feedback is sent to the server. The input in this step is the user's feedback, and the output is the feedback data sent to the server.

[0129] Step 6: Analyze feedback and refine your support plan

[0130] The server then inputs the collected feedback data back into the machine learning algorithm to evaluate the effectiveness of the support provided. Using the collected feedback data as new data points, the model is retrained and updated to the optimal support plan. Specifically, the information obtained from the feedback is analyzed, and the content and amount of support is readjusted if necessary. For example, if the feedback indicates that a particular household needs additional support, an additional 5,000 yen per month will be provided to that household. The input in this step is the feedback data, and the output is an updated support plan.

[0131] (Application example 1)

[0132] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0133] In modern society, providing support to the poor is an important issue, but doing so efficiently and effectively is difficult. In particular, advanced data analysis is required to allocate appropriate funds according to individual circumstances, and to quickly monitor and evaluate them. It is also necessary to ensure the transparency and fairness of support while appropriately adjusting support plans based on feedback from users. Conventional systems are unable to adequately resolve these issues, which often leads to a decline in the efficiency and effectiveness of support. Providing a user interface that allows users to intuitively understand the details of the support is also an important element.

[0134] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0135] In this invention, the server includes: means for analyzing data collected from the poor, non-governmental organizations, and governments and allocating funds based on a specific methodology; means for storing and pre-processing the collected data; means for generating a support plan using a machine learning algorithm; means for determining fund allocation based on the generated support plan and notifying users via an electronic device; means for collecting feedback from users and adjusting the support plan; means for predicting support amounts using a machine learning algorithm and calculating the optimal support amount for each user; means for analyzing support plans based on the generative AI model and presenting different support plans to each user; means for collecting user registration information and storing it in a database accessible from smartphones or other mobile devices; and means for displaying support history, thereby enabling appropriate and efficient support to the poor.

[0136] The "poor" are people who are socially and economically disadvantaged and do not have enough income to meet basic necessities of life.

[0137] A "non-governmental organization" is an organization established independently of the government that carries out activities for the public good or to solve social problems.

[0138] A "government" is a public institution that governs a country or region, enforces laws, and provides public services.

[0139] "Data analysis" is the process of processing collected information to gain meaningful insights.

[0140] "Fund allocation" is the act of appropriately distributing funds for specific purposes or targets.

[0141] A "machine learning algorithm" is a set of techniques that allow computers to learn from data and perform analyses such as predictions and classifications.

[0142] A "support plan" is a plan for specific support content for a target based on the target's specific situation and needs.

[0143] An "electronic terminal" is a device that processes and communicates digital information, such as a smartphone or personal computer.

[0144] "User" refers to the target or beneficiary of the system.

[0145] "Feedback" refers to opinions and evaluation information provided by users, which is used to improve the system.

[0146] A "generative AI model" is a computational model that is generated using artificial intelligence techniques to perform a specific task.

[0147] A "database" is a system for efficiently storing, searching, and managing data.

[0148] "Support history" is information that records the support provided in the past and the results thereof.

[0149] This will enable appropriate and efficient support to the poor.

[0150] The system that realizes this invention is composed of two main components, a server and a terminal, in order to efficiently provide funds and support to the poor.

[0151] Server Configuration

[0152] Data Collection Module

[0153] The server has multiple means for collecting data from the poor, non-governmental organizations, and governments. This data includes users' annual income, household composition, housing situation, and health status. Specifically, the server periodically sends users questionnaires and stores their responses in a database. Furthermore, the server obtains data in real time from non-governmental organizations and governments via APIs. For example, activity reports from non-governmental organizations and welfare policy data from governments are also collected.

[0154] Money Management Module

[0155] The server preprocesses the collected data, stores it in a database, and then analyzes it using machine learning algorithms. Based on this analysis, an effective support plan is generated. For example, a specific household could receive 30,000 yen per month in support and additionally allocate funds related to education. The algorithm ensures that such fund allocation is fair and effective.

[0156] User Interface

[0157] The device (such as the user's smartphone or computer) provides an interface that notifies the user of the support plan and the results of the allocation of funds. Through this interface, users can check the details of their support and provide feedback as needed. For example, the system has a function to report the status of fund use and whether additional support is needed. The interface is also intuitive, allowing users to quickly find the information they need.

[0158] Algorithm Module

[0159] The server uses machine learning algorithms to analyze the collected data and generate optimal support plans. The algorithms take into account past and current user data to predict the most effective support methods. For example, special support can be provided to families experiencing a sudden drop in income, and the effectiveness of such support can be monitored.

[0160] Specific examples

[0161] For example, the information a user must provide when registering with the system is as follows:

[0162] name

[0163] age

[0164] annual income

[0165] household composition

[0166] health status

[0167] Based on this data, the server generates a support plan as follows:

[0168] "Taro Tanaka, 45 years old, annual income 200,000 yen, household of four, healthy."

[0169] The server analyzes this information and determines that Taro Tanaka is to receive a monthly donation of 25,000 yen. This is notified through the user interface, and Taro Tanaka can not only receive the donation but also provide feedback.

[0170] Hardware and software used

[0171] Hardware: Servers, smartphones, PCs

[0172] Software: Python, Flask (web framework), SQLite (database), scikit-learn (machine learning library)

[0173] This system will enable appropriate and efficient support for the poor. By using generative AI models, effective support plans are quickly generated and the results are communicated via a user-friendly interface. This is expected to reduce uncertainty and enable concrete support to be provided promptly.

[0174] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0175] Step 1:

[0176] Data collection

[0177] The server collects data from the poor, non-governmental organizations, and governments. Specifically, it obtains information such as users' annual income, household composition, housing situation, and health status through a questionnaire form. It also obtains data in real time from non-governmental organizations and governments through APIs. The input is the user input form and data obtained through the API, and the output is preprocessed data.

[0178] Step 2:

[0179] Data preprocessing and storage

[0180] The collected data is pre-processed on the server, where incomplete data is filled in and the format is standardized. After this pre-processing, the data is stored in a database (e.g., SQLite). The input is the collected raw data, and the output is the cleaned data.

[0181] Step 3:

[0182] Training a machine learning model

[0183] The server uses the preprocessed data to train a machine learning algorithm (e.g., Linear Regression). The trained model is the basis for generating an optimal assistance plan. The input is the preprocessed data, and the output is the trained machine learning model.

[0184] Step 4:

[0185] Generate a support plan

[0186] The server uses a trained machine learning model to generate an optimal support plan based on each user's data. As a specific example, it inputs features such as income, household composition, and health status, and outputs a support amount. The input is feature data for each user (annual income, household composition, etc.), and the output is a support plan (e.g., ¥30,000 support per month).

[0187] Step 5:

[0188] Notification of support plan

[0189] The generated support plan is notified to the user via their device. The user can then check their support plan using a smartphone or computer. The input is the generated support plan, and the output is the support plan displayed on the user's device.

[0190] Step 6:

[0191] Gathering feedback

[0192] The user sends feedback on the support provided to the server through the terminal. For example, the user can report on the status of fund utilization or whether additional support is needed. The input is the user's feedback information, and the output is the collected feedback data.

[0193] Step 7:

[0194] Coordinating support plans

[0195] The server then readjusts the assistance plan based on the collected feedback, which may involve retraining the algorithm or assessing whether additional assistance is needed. The input is the collected feedback data, and the output is a new, adjusted assistance plan.

[0196] For example, if a user provides the following information to the system:

[0197] "Taro Tanaka, 45 years old, annual income 200,000 yen, household of four, healthy."

[0198] Using the generative AI model, the server decides to provide Taro Tanaka with ¥25,000 in monthly support and notifies him of this. Taro Tanaka then provides feedback on the effectiveness of the support, and the server uses this feedback to adjust the support plan.

[0199] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0200] The present invention aims to provide a system for efficiently providing funding and support to the poor, and to provide more effective support plans by combining it with an emotion engine that recognizes the user's emotions. This system mainly consists of the following components: a data collection module, a fund management module, a user interface, an algorithm module, and an emotion engine.

[0201] System Configuration

[0202] 1. Server: Data collection module

[0203] The server collects data from the poor, non-governmental organizations (NGOs), and governments. This data includes users' annual income, household composition, housing situation, health status, NGO activity reports, and government welfare policy data. The server periodically distributes questionnaire forms and stores the collected information in a database. It also obtains data in real time from NGOs and governments via APIs.

[0204] 2. Server: Funds Management Module

[0205] The server allocates funds to each user based on the collected data. First, the collected data is preprocessed and stored in a database. Then, machine learning algorithms analyze the data and generate a support plan that best suits each user's situation. For example, a specific household may receive 30,000 yen in monthly support and additional funds may be allocated to education-related programs. This allocation of funds is done fairly and effectively based on the algorithm.

[0206] 3. Terminal: User Interface

[0207] An interface is provided on the device (user's mobile device or PC) that displays the support results. Users can check the content of their support and provide feedback if necessary. For example, there is a function to report the status of fund use and whether additional support is needed. The user interface is also designed to be intuitive and easy to use, allowing users to quickly find the information they need.

[0208] 4. Server: Algorithm Module

[0209] The server uses machine learning algorithms to analyze the collected data and generate optimal support plans. The algorithms take into account past and current user data to predict the most effective support methods. For example, they could provide extra support to families who have experienced a sudden drop in income and monitor the effectiveness of the plan.

[0210] 5. Server: Emotion Engine

[0211] The server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's input data and feedback to recognize and quantify their emotional state. For example, the emotion engine evaluates stress and satisfaction levels based on the comments and evaluations written by the user, and reflects the results in the support plan. This allows for more detailed support that takes emotional aspects into account.

[0212] Specific operation of the system

[0213] 1. Data collection: The server collects data from users, NGOs, and governments and stores it in a database.

[0214] 2. Data preprocessing: The server preprocesses the collected data and converts it into a format that is easy to process with machine learning algorithms.

[0215] 3. Support plan generation: The server uses an algorithm to generate the optimal support plan.

[0216] 4. Fund allocation: The server determines the allocation of funds based on the generated support plan.

[0217] 5. Notification and feedback: The device notifies the user of the assistance provided, and the user provides feedback.

[0218] 6. Emotion analysis: The server uses an emotion engine to analyze the user's emotional state from their feedback and reflect this in the next support plan.

[0219] The system efficiently executes a series of processes, from data collection and analysis to fund allocation, emotional feedback collection, and further adjustments. This optimizes funding and support for the poor and promotes social improvement. For example, the server can use collected data to identify a user's stress level and provide additional support based on the results, thereby promoting psychological stability.

[0220] The processing flow will be explained below.

[0221] Step 1: Collect data

[0222] The server collects questionnaire forms and registration information from users. Users enter information such as annual income, family composition, housing situation, and health status into an online form.

[0223] The server receives activity reports from non-governmental organizations (NGOs) via API, automatically collecting data such as the type of support provided by the NGO, the number of people who received support, and the success of the measures.

[0224] The server retrieves policy information and assistance program data from public government databases, periodically downloading information on policy implementation status, budget allocations, target demographics, and more.

[0225] All collected data is stored in a database.

[0226] Step 2: Preprocessing the data

[0227] The server preprocesses all collected data, for example by imputing missing data and correcting outliers.

[0228] Once the data is cleansed, it is standardized and converted into a format that is easy for machine learning algorithms to process.

[0229] Step 3: Create a support plan

[0230] The server uses machine learning algorithms to generate a support plan that is optimal for each user's situation.

[0231] The algorithm uses past data and patterns to predict what type of support will be most effective.

[0232] For example, this includes specific measures such as "providing 30,000 yen in support per month" or "supporting participation in specific educational programs."

[0233] Step 4: Allocate funds

[0234] The server determines the specific allocation of funds to each user based on the generated support plan.

[0235] For example, a detailed funding allocation plan would be created, allocating additional support to families with children who earn below a certain monthly income.

[0236] Step 5: Notify and gather feedback

[0237] The device will then notify the user of the support plan and assistance details, which will then be displayed on the user's mobile device or PC.

[0238] Users can view details of their assigned assistance in the app or web portal.

[0239] Users provide feedback on how effective the support was, report on the use of funds, and whether they need additional assistance.

[0240] Step 6: Sentiment analysis with the sentiment engine

[0241] The server uses an emotion engine to analyze the user's feedback.

[0242] The emotion engine recognizes and quantifies emotions from comments and ratings written by users. For example, it can determine a user's stress or satisfaction level from the feedback text.

[0243] The analysis results of the emotion engine are stored in a database.

[0244] Step 7: Analyze feedback and adjust support plans

[0245] The server comprehensively analyzes user feedback, including the results of emotion analysis using an emotion engine, and evaluates the effectiveness of the support plan.

[0246] If necessary, update your support plan and adjust the next support offer.

[0247] For example, if a particular support is found to be ineffective, the content of the support will be changed appropriately. Also, if the user is under high stress, additional psychological support will be considered.

[0248] The system efficiently executes a series of processes, from data collection and analysis, to fund allocation, feedback collection and sentiment analysis, and further adjustment, optimizing funding and support for the poor and bringing about social improvements.

[0249] Example 2

[0250] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0251] In modern society, there is a need for effective funding and support for the poor. However, existing systems do not adequately analyze collected data or allocate funds appropriately, and they lack the ability to optimize support plans that take into account user emotions and feedback.

[0252] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for analyzing data collected from the poor, non-governmental organizations, and the government and allocating funds based on a specific method; means for storing and pre-processing the collected data; means for generating a support plan using a machine learning algorithm; means for determining the allocation of funds based on the support plan generated via a notification interface and notifying the user; and means for analyzing feedback from the user using an emotion engine, quantifying the emotional state, and adjusting the support plan. This allows a series of processes, from data collection and analysis, to fund allocation, emotional feedback collection, and further adjustment, to be carried out efficiently, enabling effective support for the poor.

[0253] "Poor" refers to individuals or families who are in financial difficulty and have difficulty accessing basic necessities and services.

[0254] "Non-governmental organizations" are non-governmental organizations that address social issues in a private capacity, often working in areas such as poverty, health, and the environment.

[0255] "Government" refers to a national or local public institution that promotes the public welfare through various policies and programs.

[0256] "Data collection" refers to the process of gathering information for a specific purpose, and includes methods such as surveys, API access, and sensors.

[0257] "Data preprocessing" refers to a series of operations that convert collected data into a format that is easier to analyze, including filling in missing values ​​and cleaning the data.

[0258] A "machine learning algorithm" refers to a computational method for learning from data and making predictions and classifications, and there are a variety of models and techniques.

[0259] A "support plan" is a plan that lays out the specific support content and methods to be provided to eligible individuals and families, and includes financial support and service provision.

[0260] A "notification interface" refers to a user interface used on mobile devices and PCs to display information and messages to users.

[0261] An "emotion engine" refers to algorithms and technologies for recognizing and analyzing a user's emotional state, quantifying emotions from user input and feedback.

[0262] "Feedback" refers to opinions and status reports provided by users, which are used to improve and adjust the system.

[0263] "Funding allocation" refers to the process of determining the amount and use of funds provided to specific individuals or households based on collected and analyzed data.

[0264] The present invention is a system for efficiently providing funds and support to the poor, and aims to provide more effective support plans by combining it with an emotion engine that recognizes the user's emotions. Detailed embodiments of this system will be described below.

[0265] System Configuration

[0266] This system mainly consists of a server, terminals, and users.

[0267] Data Collection Module

[0268] The server collects data from the poor, non-governmental organizations (NGOs), and governments. This data includes users' annual income, household composition, housing situation, health status, NGO activity reports, and government welfare policy data. The server periodically distributes questionnaire forms and stores the collected information in a database. It also obtains data in real time from NGOs and governments via APIs.

[0269] Example: Obtaining data from the government on unemployment rates and the number of people receiving welfare via an API.

[0270] Data Preprocessing Module

[0271] The server preprocesses the collected data and converts it into a format that is easy to process with machine learning algorithms. Preprocessing includes removing unnecessary data, filling in missing data, and standardizing data formats.

[0272] Example: The server imputes NULL values ​​in the data with the average value.

[0273] Algorithm Module

[0274] The server then uses a machine learning algorithm to generate an optimal support plan based on the preprocessed data. The algorithm compares past and current data to predict effective support methods.

[0275] Example: Using machine learning algorithms to generate special assistance plans for families who experience a sudden drop in income, providing them with $50,000 per month.

[0276] Money Management Module

[0277] The server determines how funds are allocated based on the generated support plan, ensuring that the allocation is fair and transparent, and that the necessary amount is distributed appropriately to each household.

[0278] Example: Based on a support plan generated by the server, a specific household is allocated 30,000 yen per month, plus an additional 10,000 yen for education-related support.

[0279] User Interface

[0280] The device (user's mobile device or PC) provides an interface that displays the support results. Through this interface, the user can check the support content and provide feedback as needed.

[0281] Example: The user's smartphone is notified of the support provided, and the user provides feedback through the application, such as "This support was helpful."

[0282] Emotion Engine

[0283] The server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's input data and feedback, recognizes and quantifies the user's emotional state, and reflects this in the next support plan.

[0284] Example: If a user comments, "I need more money for my child's education," the sentiment engine analyzes the content of the comment and reflects the addition of educational support in the next support plan.

[0285] Prompt Sentence Examples

[0286] "Please explain how you will use the collected data to generate optimal support plans for newly supported families and monitor their effectiveness."

[0287] By operating in this way, the system can effectively provide funding and support to the poor. In addition, by utilizing an emotion engine, it is possible to provide more detailed support that takes into account the user's emotions and feedback.

[0288] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0289] Step 1: Data collection

[0290] The server collects data from the poor, non-governmental organizations (NGOs), and governments. First, it periodically distributes questionnaire forms to users to collect information such as annual income, household composition, housing situation, and health status. It also obtains data from NGOs and governments in real time via APIs and stores the collected data in a database. This effectively integrates information from users, NGOs, and governments. The input is questionnaire responses and data from the API, and the output is data stored in the database.

[0291] Specific operation: The server obtains data on unemployment rates and the number of welfare recipients from the government via an API and stores it in a database.

[0292] Step 2: Data Preprocessing

[0293] The server preprocesses the collected data and converts it into a format that is easy to process with machine learning algorithms. Specifically, it deletes unnecessary data, fills in missing data, standardizes data formats, etc. The input is raw data, and the output is preprocessed data.

[0294] Specific operation: The server fills in NULL values ​​in the collected data with the average value, cleans the data, and standardizes the format.

[0295] Step 3: Create a support plan

[0296] The server uses a machine learning algorithm to generate an optimal support plan based on the preprocessed data. The algorithm compares past data with current data and predicts effective support methods. The input is the preprocessed data, and the output is the generated support plan.

[0297] How it works: Using machine learning algorithms, it generates special assistance plans for families who experience a sudden drop in income, providing them with assistance of 50,000 yen per month.

[0298] Step 4: Fund allocation

[0299] The server determines how to allocate funds based on the generated support plan. The allocation is fair and transparent, and the necessary amount is distributed appropriately to each household. The input is the generated support plan, and the output is the fund allocation result.

[0300] Specific operation: Based on the support plan, the server allocates 30,000 yen per month to each household, plus an additional 10,000 yen for education-related support.

[0301] Step 5: Notification and feedback

[0302] The device notifies the user of the assistance provided and provides an interface for the user to provide feedback. The user reports the usage status of the assistance and any additional needs through this interface. The input is the assistance provided and the user's feedback, and the output is the collected feedback.

[0303] Specific operation: The user's smartphone is notified of the support details, and the user provides feedback through the application, such as "This support was helpful."

[0304] Step 6: Sentiment analysis

[0305] The server uses an emotion engine to analyze the user's emotional state based on their feedback. The analysis results are reflected in the next support plan. The input is the user's feedback, and the output is the analyzed emotional data.

[0306] What it does: If a user comments, "I need more money for my child's education," the sentiment engine analyzes the content of the comment and reflects the addition of educational support in the next support plan.

[0307] Through this series of steps, the system can efficiently provide funding and support to the poor, with each step linking up with the others to effectively collect data, analyze it, allocate funds, collect emotional feedback, and make further adjustments.

[0308] (Application example 2)

[0309] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0310] Employee psychological fatigue and stress are serious problems that lead to decreased productivity and increased employee turnover. However, many current systems lack the ability to provide support based on emotion recognition, and do not adequately address the psychological challenges faced by employees. Therefore, a system that can properly recognize employees' emotions and provide appropriate support based on that recognition is needed.

[0311] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0312] In this invention, the server includes means for analyzing data collected from the poor, non-governmental organizations, and governments and allocating funds based on a specific methodology, means for storing and pre-processing the collected data, means for generating a support plan using a machine learning algorithm, means for determining fund allocation based on the generated support plan and notifying the user, means for collecting feedback from the user and adjusting the support plan, and means for analyzing the emotional state of employees and providing appropriate support for psychological fatigue and stress. This makes it possible to appropriately understand the emotional state of employees and provide psychological support, thereby reducing psychological fatigue and stress.

[0313] The "poor" are people who are financially disadvantaged and unable to obtain the basic necessities of life.

[0314] A "non-governmental organization" is an organization that operates independently of the government and primarily engages in activities such as solving social problems and supporting the poor.

[0315] A "government" is an institution that is responsible for running a nation, enacting and enforcing laws, and carrying out various activities related to the welfare of the people.

[0316] A "machine learning algorithm" is a method by which a computer learns from data and automatically recognizes patterns, allowing it to make predictions and classifications.

[0317] A "support plan" is a plan of assistance to be provided based on specific circumstances and needs, including allocation of funds and services.

[0318] "Emotional state" refers to the type and intensity of emotions experienced by an individual and consists of psychological states such as stress, happiness, and anxiety.

[0319] "Psychological fatigue" is a state in which mental energy is reduced and concentration and work efficiency are reduced due to long-term stress or strain.

[0320] "Stress" is a state of tension caused by mental or physical strain due to external pressures or demands.

[0321] "Feedback" refers to the evaluation or reaction of a system or individual to an action or result, and is information used for improvement or adjustment.

[0322] This invention is a system for reducing psychological fatigue and stress among employees, which analyzes data collected from the poor, non-governmental organizations, and governments, and allocates funds and support plans based on specific methods. The specific configuration and operation of the system are described below.

[0323] The server uses the following hardware and software:

[0324] Emotion recognition library: Used to analyze the user's emotional state. For example, we use a library called "EmotionRecognizer."

[0325] Machine learning algorithms are used to generate support plans, for example, using "Linear Regression" or other regression models.

[0326] Database: Stores data collected from users, non-governmental organizations, and governments.

[0327] Cloud servers: Perform data processing and analysis, for example, using Amazon Web Services (AWS®) or Google® Cloud Platform (GCP).

[0328] 1. Data Collection Module

[0329] The server collects real-time data from users, non-governmental organizations, and governments, and stores it in a database. Collected data includes employees' emotional states, stress levels, survey results, etc.

[0330] 2. Data Preprocessing

[0331] The server preprocesses the collected data, converting it into a format that is easier for machine learning algorithms to process, which includes steps such as tokenizing and quantifying the text data.

[0332] 3. Support plan generation

[0333] The server uses machine learning algorithms to generate a support plan that best suits each user's situation. For example, if an employee inputs, "I've been feeling very stressed lately," the system will suggest "psychological counseling."

[0334] 4. Allocation of funds and support

[0335] Based on the generated support plan, the server determines the allocation of funds and support and notifies the user of the details.

[0336] 5. Feedback collection and sentiment analysis

[0337] The device collects feedback from the user and sends the data to a server, which uses an emotion recognition library to analyze the user's emotional state and adjusts the support plan.

[0338] Specific examples

[0339] Example: If the input is "I've been feeling very stressed lately," the server will use "EmotionRecognizer" to recognize the emotion as "stress" and use "LinearRegression" to suggest a support plan such as "psychological counseling."

[0340] Example prompt: "An employee reports their recent emotional state in text: 'I've been feeling very stressed lately.' The system should suggest an appropriate support plan."

[0341] This system makes it possible to properly grasp the emotional state of employees and reduce psychological fatigue and stress.

[0342] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0343] Step 1:

[0344] The server collects data in real time from users, non-governmental organizations, and governments. Specifically, it collects data such as users' emotional state, stress levels, and survey results, and stores it in a database. The collected data is periodically retrieved using an API and stored in the database. The input is raw data provided by each entity, and the output is organized data stored in the database.

[0345] Step 2:

[0346] The server preprocesses the collected data. Specifically, it converts the raw data into a format that is easy for machine learning algorithms to process. This includes tokenizing and quantifying text data, filling in missing data, and normalizing the data. This generates data in a format suitable for machine learning models. The input is the raw data in the database, and the output is the preprocessed data.

[0347] Step 3:

[0348] The server uses the preprocessed data to apply a machine learning algorithm (e.g., Linear Regression) to generate a support plan that is optimal for each user's situation. For example, if an employee enters, "I've been feeling very stressed lately," the system analyzes it and suggests "psychological counseling." The input is the preprocessed data, and the output is the generated support plan.

[0349] Step 4:

[0350] The server determines the allocation of funds and support based on the generated support plan. Specifically, it plans the budget allocation and resource distribution corresponding to the support plan and stores the details in a database. The input is the generated support plan, and the output is the specific funding allocation and support details.

[0351] Step 5:

[0352] The terminal notifies the user of the details of the funds and support. The notified information includes details of the support plan and budget allocation. This allows the user to confirm their own support details and begin applying them. The input is the support plan and allocation information from the server, and the output is the notification to the user.

[0353] Step 6:

[0354] The terminal collects feedback from the user. The user can report whether the support plan is appropriate or whether additional support is needed. The collected feedback is sent to the server. The input is the user's feedback, and the output is the feedback data sent to the server.

[0355] Step 7:

[0356] The server uses an emotion recognition library (e.g., EmotionRecognizer) to analyze the user's emotional state from the feedback and adjusts the support plan based on the results. For example, if the feedback indicates that the user's stress level is still high, it provides additional support. The input is the feedback data, and the output is the adjusted support plan.

[0357] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0358] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0359] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0360] [Second embodiment]

[0361] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0362] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0363] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0364] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0365] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0366] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0367] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0368] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0369] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0370] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0371] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0372] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0373] This invention is a system for efficiently providing funds and support to the poor. This system mainly consists of four components: a data collection module, a fund management module, a user interface, and an algorithm module.

[0374] System Configuration

[0375] 1. Server: Data collection module

[0376] The server collects data from the poor, non-governmental organizations (NGOs), and governments. This data includes users' annual income, household composition, housing situation, health status, NGO activity reports, and government welfare policy data. For example, the server periodically sends questionnaire forms to users and stores the collected information in a database. It also obtains data in real time from NGOs and governments via APIs.

[0377] 2. Server: Funds Management Module

[0378] The server allocates funds to each user based on the collected data. The collected data is first preprocessed and stored in a database. Machine learning algorithms then analyze the data to generate a support plan that best suits each user's situation. For example, a specific household may receive 30,000 yen in monthly support, with additional funds allocated to education-related programs. This allocation of funds is done fairly and effectively based on the algorithm.

[0379] 3. Terminal: User Interface

[0380] An interface that displays the support results is provided on the device (user's mobile device or PC). Users can check the details of their support and provide feedback if necessary. For example, there is a function to report the status of fund use and whether additional support is needed. The user interface is also designed to be intuitive and easy to use, allowing users to quickly find the information they need.

[0381] 4. Server: Algorithm Module

[0382] The server uses machine learning algorithms to analyze the collected data and generate optimal support plans. The algorithms take into account past and current user data to predict the most effective support methods. For example, they could provide extra support to families experiencing a sudden drop in income and monitor the effectiveness of that support. This algorithm can improve the closeness and accuracy of support.

[0383] This system efficiently executes a series of processes, from data collection to generating assistance plans, allocating funds, and collecting and adjusting feedback. This optimizes the provision of funds and support to the poor and improves society. Specifically, the server collects and analyzes data, generates assistance plans based on the results, and notifies users. Users receive the assistance provided and send the results back to the server as feedback. In this way, the entire system is constantly updated, enabling it to continue providing optimal assistance.

[0384] The processing flow will be explained below.

[0385] Step 1: Collect data

[0386] The server collects questionnaires and registration information from the poor, with users entering information such as their annual income, household composition, housing situation, and health status.

[0387] The server receives activity reports from non-governmental organizations (NGOs), collecting data such as the type of support provided by the NGOs, the number of people who received support, and the success of their efforts.

[0388] The server retrieves policy information and assistance program data from public government databases, collecting information such as policy implementation status, budget allocation, and target demographics.

[0389] All collected data is stored in a database.

[0390] Step 2: Preprocessing the data

[0391] The server preprocesses all collected data, for example by imputing missing data and correcting outliers.

[0392] Once the data is cleansed, it is standardized and converted into a format that is easy for machine learning algorithms to process.

[0393] Step 3: Create a support plan

[0394] The server uses machine learning algorithms to generate a support plan that is optimal for each user's situation.

[0395] The algorithm uses past data and patterns to predict what type of support will be most effective.

[0396] For example, this includes specific measures such as "providing 30,000 yen in support per month" or "supporting participation in specific educational programs."

[0397] Step 4: Allocate funds

[0398] The server determines the specific allocation of funds to each user based on the generated support plan.

[0399] For example, a detailed funding allocation plan would be created, allocating additional support to families with children who earn below a certain monthly income.

[0400] Step 5: Notify and gather feedback

[0401] The device will then notify the user of the support plan and assistance details, which will then be displayed on the user's mobile device or PC.

[0402] Users can view details of their assigned assistance in the app or web portal.

[0403] Users provide feedback on how effective the support was, report on the use of funds, and whether they need additional assistance.

[0404] Step 6: Analyze feedback and adjust support plans

[0405] The server analyzes user feedback and evaluates the effectiveness of the support plan.

[0406] If necessary, update your support plan and adjust the next support offer.

[0407] For example, if a particular support is found to be ineffective, the content will be modified appropriately.

[0408] The system efficiently carries out a series of processes from data collection and analysis, to fund allocation, feedback collection, and further adjustments.

[0409] Example 1

[0410] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0411] In order to effectively and efficiently provide funding and support to the poor, a system that smoothly collects data, analyzes it, allocates funds, provides a user interface, and collects and evaluates feedback is required. Conventional systems have issues with uncertainty in data collection, fairness in fund allocation, and insufficient reflection of user feedback, making it difficult to provide optimal support.

[0412] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0413] In this invention, the server includes means for analyzing data collected from the poor, non-governmental organizations, and the government and allocating funds based on a specific methodology, means for storing and pre-processing the collected data, means for generating a support plan using a machine learning algorithm, means for determining fund allocation based on the generated support plan and notifying the user, means for collecting feedback via the user's terminal and adjusting the support plan, means for providing an intuitive and easy-to-use interface to the terminal, and means for the server to periodically distribute questionnaire forms to users to collect data. This enables efficient data collection, accurate fund allocation, and proactive feedback collection and evaluation.

[0414] "Data collection" is the process of gathering information of interest from various sources.

[0415] "Analysis" is the process of converting collected data into an understandable form and evaluating its content.

[0416] Funding allocation is the process of effectively allocating available funds according to user and organizational needs.

[0417] "Preprocessing" is the process of cleaning and transforming collected data to improve its quality.

[0418] A "machine learning algorithm" is a computational method that learns patterns and rules from data and makes predictions and judgments based on them.

[0419] A "support plan" is a plan that describes the specific content and methods of support to be provided to users and organizations based on the analyzed data.

[0420] "Notification" is the process by which the system notifies the user of information.

[0421] "Feedback" is the process by which a user provides a response or opinion to the system in response to the assistance provided.

[0422] An "interface" is a screen or operating means by which a user interacts with a system.

[0423] A "survey form" is a paper or electronic document containing specific questions that is used to collect information from a user.

[0424] This invention is a system for efficiently providing funding and support to the poor. The system consists of four main components: a data collection module, a fund management module, a user interface, and an algorithm module.

[0425] Data Collection Module

[0426] The server collects various data from the poor, non-governmental organizations (NGOs), and governments. This data includes users' annual income, household composition, housing situation, health status, NGO activity reports, and government welfare policy data. Specifically, the server periodically sends questionnaire forms to users and stores the collected information in a database. It also obtains data in real time from NGOs and governments via APIs. A database management system such as MySQL is used to store the data.

[0427] For example, the server sends a push notification to the user asking, "What is your current income?", and when the user responds, the data is stored in a database. NGO activity reports are automatically collected and stored through API requests.

[0428] Money Management Module

[0429] The server preprocesses the collected data, stores it in a database, and then analyzes it using a machine learning algorithm. The results are used to generate a support plan that is optimal for each user's situation. The preprocessing uses Python's Pandas library to fill in missing data and remove outliers.

[0430] For example, Python is used to clean the data and input it into a machine learning model using TensorFlow, which generates a support plan such as "If income is less than ¥100,000, provide ¥10,000 per month in support."

[0431] User Interface

[0432] The device provides a user interface on their mobile device or PC that displays details of their donation, allowing them to provide feedback on the status of fund use and whether additional donations are needed. This interface is built using front-end frameworks such as React.

[0433] For example, users can use an in-app form to answer the question "How did you use the funds you received?" and then send that feedback to the server.

[0434] Algorithm Module

[0435] The server then feeds the collected feedback data back into the algorithm to evaluate the effectiveness of the assistance provided. This analysis is performed using machine learning libraries such as TensorFlow and Scikit-learn. After evaluating the effectiveness, the assistance plan is adjusted as necessary.

[0436] For example, feedback data can be input into the model, and the model can be retrained based on newly acquired information to optimize the next assistance plan.

[0437] Prompt Sentence Examples

[0438] Prompt: Describe a system for providing optimal assistance plans to the poor. Using the data below, detail the process from collecting data to generating assistance plans, allocating funds, and gathering feedback.

[0439] User's annual income: 100,000 yen

[0440] Family composition: 5 people family

[0441] Housing Status: Rented

[0442] Health: Good

[0443] NGO Activity Report

[0444] Government welfare policy data

[0445] The system efficiently executes a series of processes, from data collection to generating support plans, allocating funds, and collecting and adjusting feedback, thereby optimizing funding and support for the poor and achieving social improvement.

[0446] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0447] Step 1: Data collection

[0448] The server collects data from poor users, non-governmental organizations (NGOs), and the government. This process involves sending periodic questionnaire forms and retrieving data in real time using an API. Specifically, the server sends a push notification to the user's smartphone asking, "What is your current income?" and stores the data the user responds to in a database. It also receives activity reports and welfare policy data in JSON format from the NGO and government via API, which it stores in the database. The input in this step is the questionnaire responses and JSON data retrieved from the API, and the output is data stored in the database.

[0449] Step 2: Data Preprocessing

[0450] The server preprocesses the collected data. Specifically, it completes missing data, removes outliers, and standardizes data formats. It uses Python's Pandas library to clean the data and, if necessary, completes missing data with average values. For example, if income data is missing, it completes the average income value. The input in this step is raw data obtained from the database, and the output is the clean data after preprocessing.

[0451] Step 3: Create a support plan

[0452] The server inputs the preprocessed data into a machine learning algorithm to generate an optimal support plan. The algorithm uses machine learning libraries such as TensorFlow and Scikit-learn. Specifically, it determines the optimal financial support amount and program for each user, taking into account factors such as income, family composition, housing situation, and health status. For example, it generates an output such as "If income is less than 100,000 yen, 10,000 yen in support will be provided per month." The input in this step is the clean data after preprocessing, and the output is the generated support plan.

[0453] Step 4: Notification of support plan

[0454] The server notifies the user's device of the details of the generated support plan. Specifically, it provides an interface for displaying the details of the support plan and funding allocation on the user's mobile device or PC. A front-end framework such as React is used to provide an intuitive and easy-to-use UI for the user. For example, when the user opens the app, it displays the message, "Your support plan is for a monthly funding of 10,000 yen." The input in this step is the generated support plan, and the output is a notification displayed on the user's device.

[0455] Step 5: Gather feedback

[0456] The terminal provides a function to collect feedback from users. Users can report on the support they received, their use of the funds, and the need for additional support. Specifically, users use a form within the app to answer questions such as "How did you use the funds you received?", and the feedback is sent to the server. The input in this step is the user's feedback, and the output is the feedback data sent to the server.

[0457] Step 6: Analyze feedback and refine your support plan

[0458] The server then inputs the collected feedback data back into the machine learning algorithm to evaluate the effectiveness of the support provided. Using the collected feedback data as new data points, the model is retrained and updated to the optimal support plan. Specifically, the information obtained from the feedback is analyzed, and the content and amount of support is readjusted if necessary. For example, if the feedback indicates that a particular household needs additional support, an additional 5,000 yen per month will be provided to that household. The input in this step is the feedback data, and the output is an updated support plan.

[0459] (Application example 1)

[0460] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0461] In modern society, providing support to the poor is an important issue, but doing so efficiently and effectively is difficult. In particular, advanced data analysis is required to allocate appropriate funds according to individual circumstances, and to quickly monitor and evaluate them. It is also necessary to ensure the transparency and fairness of support while appropriately adjusting support plans based on feedback from users. Conventional systems are unable to adequately resolve these issues, which often leads to a decline in the efficiency and effectiveness of support. Providing a user interface that allows users to intuitively understand the details of the support is also an important element.

[0462] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0463] In this invention, the server includes: means for analyzing data collected from the poor, non-governmental organizations, and governments and allocating funds based on a specific methodology; means for storing and pre-processing the collected data; means for generating a support plan using a machine learning algorithm; means for determining fund allocation based on the generated support plan and notifying users via an electronic device; means for collecting feedback from users and adjusting the support plan; means for predicting support amounts using a machine learning algorithm and calculating the optimal support amount for each user; means for analyzing support plans based on the generative AI model and presenting different support plans to each user; means for collecting user registration information and storing it in a database accessible from smartphones or other mobile devices; and means for displaying support history, thereby enabling appropriate and efficient support to the poor.

[0464] The "poor" are people who are socially and economically disadvantaged and do not have enough income to meet basic necessities of life.

[0465] A "non-governmental organization" is an organization established independently of the government that carries out activities for the public good or to solve social problems.

[0466] A "government" is a public institution that governs a country or region, enforces laws, and provides public services.

[0467] "Data analysis" is the process of processing collected information to gain meaningful insights.

[0468] "Fund allocation" is the act of appropriately distributing funds for specific purposes or targets.

[0469] A "machine learning algorithm" is a set of techniques that allow computers to learn from data and perform analyses such as predictions and classifications.

[0470] A "support plan" is a plan for specific support content for a target based on the target's specific situation and needs.

[0471] An "electronic terminal" is a device that processes and communicates digital information, such as a smartphone or personal computer.

[0472] "User" refers to the target or beneficiary of the system.

[0473] "Feedback" refers to opinions and evaluation information provided by users, which is used to improve the system.

[0474] A "generative AI model" is a computational model that is generated using artificial intelligence techniques to perform a specific task.

[0475] A "database" is a system for efficiently storing, searching, and managing data.

[0476] "Support history" is information that records the support provided in the past and the results thereof.

[0477] This will enable appropriate and efficient support to the poor.

[0478] The system that realizes this invention is composed of two main components, a server and a terminal, in order to efficiently provide funds and support to the poor.

[0479] Server Configuration

[0480] Data Collection Module

[0481] The server has multiple means for collecting data from the poor, non-governmental organizations, and governments. This data includes users' annual income, household composition, housing situation, and health status. Specifically, the server periodically sends users questionnaires and stores their responses in a database. Furthermore, the server obtains data in real time from non-governmental organizations and governments via APIs. For example, activity reports from non-governmental organizations and welfare policy data from governments are also collected.

[0482] Money Management Module

[0483] The server preprocesses the collected data, stores it in a database, and then analyzes it using machine learning algorithms. Based on this analysis, an effective support plan is generated. For example, a specific household could receive 30,000 yen per month in support and additionally allocate funds related to education. The algorithm ensures that such fund allocation is fair and effective.

[0484] User Interface

[0485] The device (such as the user's smartphone or computer) provides an interface that notifies the user of the support plan and the results of the allocation of funds. Through this interface, users can check the details of their support and provide feedback as needed. For example, the system has a function to report the status of fund use and whether additional support is needed. The interface is also intuitive, allowing users to quickly find the information they need.

[0486] Algorithm Module

[0487] The server uses machine learning algorithms to analyze the collected data and generate optimal support plans. The algorithms take into account past and current user data to predict the most effective support methods. For example, special support can be provided to families experiencing a sudden drop in income, and the effectiveness of such support can be monitored.

[0488] Specific examples

[0489] For example, the information a user must provide when registering with the system is as follows:

[0490] name

[0491] age

[0492] annual income

[0493] household composition

[0494] health status

[0495] Based on this data, the server generates a support plan as follows:

[0496] "Taro Tanaka, 45 years old, annual income 200,000 yen, household of four, healthy."

[0497] The server analyzes this information and determines that Taro Tanaka is to receive a monthly donation of 25,000 yen. This is notified through the user interface, and Taro Tanaka can not only receive the donation but also provide feedback.

[0498] Hardware and software used

[0499] Hardware: Servers, smartphones, PCs

[0500] Software: Python, Flask (web framework), SQLite (database), scikit-learn (machine learning library)

[0501] This system will enable appropriate and efficient support for the poor. By using generative AI models, effective support plans are quickly generated and the results are communicated via a user-friendly interface. This is expected to reduce uncertainty and enable concrete support to be provided promptly.

[0502] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0503] Step 1:

[0504] Data collection

[0505] The server collects data from the poor, non-governmental organizations, and governments. Specifically, it obtains information such as users' annual income, household composition, housing situation, and health status through a questionnaire form. It also obtains data in real time from non-governmental organizations and governments through APIs. The input is the user input form and data obtained through the API, and the output is preprocessed data.

[0506] Step 2:

[0507] Data preprocessing and storage

[0508] The collected data is pre-processed on the server, where incomplete data is filled in and the format is standardized. After this pre-processing, the data is stored in a database (e.g., SQLite). The input is the collected raw data, and the output is the cleaned data.

[0509] Step 3:

[0510] Training a machine learning model

[0511] The server uses the preprocessed data to train a machine learning algorithm (e.g., Linear Regression). The trained model is the basis for generating an optimal assistance plan. The input is the preprocessed data, and the output is the trained machine learning model.

[0512] Step 4:

[0513] Generate a support plan

[0514] The server uses a trained machine learning model to generate an optimal support plan based on each user's data. As a specific example, it inputs features such as income, household composition, and health status, and outputs a support amount. The input is feature data for each user (annual income, household composition, etc.), and the output is a support plan (e.g., ¥30,000 support per month).

[0515] Step 5:

[0516] Notification of support plan

[0517] The generated support plan is notified to the user via their device. The user can then check their support plan using a smartphone or computer. The input is the generated support plan, and the output is the support plan displayed on the user's device.

[0518] Step 6:

[0519] Gathering feedback

[0520] The user sends feedback on the support provided to the server through the terminal. For example, the user can report on the status of fund utilization or whether additional support is needed. The input is the user's feedback information, and the output is the collected feedback data.

[0521] Step 7:

[0522] Coordinating support plans

[0523] The server then readjusts the assistance plan based on the collected feedback, which may involve retraining the algorithm or assessing whether additional assistance is needed. The input is the collected feedback data, and the output is a new, adjusted assistance plan.

[0524] For example, if a user provides the following information to the system:

[0525] "Taro Tanaka, 45 years old, annual income 200,000 yen, household of four, healthy."

[0526] Using the generative AI model, the server decides to provide Taro Tanaka with ¥25,000 in monthly support and notifies him of this. Taro Tanaka then provides feedback on the effectiveness of the support, and the server uses this feedback to adjust the support plan.

[0527] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0528] The present invention aims to provide a system for efficiently providing funding and support to the poor, and to provide more effective support plans by combining it with an emotion engine that recognizes the user's emotions. This system mainly consists of the following components: a data collection module, a fund management module, a user interface, an algorithm module, and an emotion engine.

[0529] System Configuration

[0530] 1. Server: Data collection module

[0531] The server collects data from the poor, non-governmental organizations (NGOs), and governments. This data includes users' annual income, household composition, housing situation, health status, NGO activity reports, and government welfare policy data. The server periodically distributes questionnaire forms and stores the collected information in a database. It also obtains data in real time from NGOs and governments via APIs.

[0532] 2. Server: Funds Management Module

[0533] The server allocates funds to each user based on the collected data. First, the collected data is preprocessed and stored in a database. Then, machine learning algorithms analyze the data and generate a support plan that best suits each user's situation. For example, a specific household may receive 30,000 yen in monthly support and additional funds may be allocated to education-related programs. This allocation of funds is done fairly and effectively based on the algorithm.

[0534] 3. Terminal: User Interface

[0535] An interface is provided on the device (user's mobile device or PC) that displays the support results. Users can check the content of their support and provide feedback if necessary. For example, there is a function to report the status of fund use and whether additional support is needed. The user interface is also designed to be intuitive and easy to use, allowing users to quickly find the information they need.

[0536] 4. Server: Algorithm Module

[0537] The server uses machine learning algorithms to analyze the collected data and generate optimal support plans. The algorithms take into account past and current user data to predict the most effective support methods. For example, they could provide extra support to families who have experienced a sudden drop in income and monitor the effectiveness of the plan.

[0538] 5. Server: Emotion Engine

[0539] The server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's input data and feedback to recognize and quantify their emotional state. For example, the emotion engine evaluates stress and satisfaction levels based on the comments and evaluations written by the user, and reflects the results in the support plan. This allows for more detailed support that takes emotional aspects into account.

[0540] Specific operation of the system

[0541] 1. Data collection: The server collects data from users, NGOs, and governments and stores it in a database.

[0542] 2. Data preprocessing: The server preprocesses the collected data and converts it into a format that is easy to process with machine learning algorithms.

[0543] 3. Support plan generation: The server uses an algorithm to generate the optimal support plan.

[0544] 4. Fund allocation: The server determines the allocation of funds based on the generated support plan.

[0545] 5. Notification and feedback: The device notifies the user of the assistance provided, and the user provides feedback.

[0546] 6. Emotion analysis: The server uses an emotion engine to analyze the user's emotional state from their feedback and reflect this in the next support plan.

[0547] The system efficiently executes a series of processes, from data collection and analysis to fund allocation, emotional feedback collection, and further adjustments. This optimizes funding and support for the poor and promotes social improvement. For example, the server can use collected data to identify a user's stress level and provide additional support based on the results, thereby promoting psychological stability.

[0548] The processing flow will be explained below.

[0549] Step 1: Collect data

[0550] The server collects questionnaire forms and registration information from users. Users enter information such as annual income, family composition, housing situation, and health status into an online form.

[0551] The server receives activity reports from non-governmental organizations (NGOs) via API, automatically collecting data such as the type of support provided by the NGO, the number of people who received support, and the success of the measures.

[0552] The server retrieves policy information and assistance program data from public government databases, periodically downloading information on policy implementation status, budget allocations, target demographics, and more.

[0553] All collected data is stored in a database.

[0554] Step 2: Preprocessing the data

[0555] The server preprocesses all collected data, for example by imputing missing data and correcting outliers.

[0556] Once the data is cleansed, it is standardized and converted into a format that is easy for machine learning algorithms to process.

[0557] Step 3: Create a support plan

[0558] The server uses machine learning algorithms to generate a support plan that is optimal for each user's situation.

[0559] The algorithm uses past data and patterns to predict what type of support will be most effective.

[0560] For example, this includes specific measures such as "providing 30,000 yen in support per month" or "supporting participation in specific educational programs."

[0561] Step 4: Allocate funds

[0562] The server determines the specific allocation of funds to each user based on the generated support plan.

[0563] For example, a detailed funding allocation plan would be created, allocating additional support to families with children who earn below a certain monthly income.

[0564] Step 5: Notify and gather feedback

[0565] The device will then notify the user of the support plan and assistance details, which will then be displayed on the user's mobile device or PC.

[0566] Users can view details of their assigned assistance in the app or web portal.

[0567] Users provide feedback on how effective the support was, report on the use of funds, and whether they need additional assistance.

[0568] Step 6: Sentiment analysis with the sentiment engine

[0569] The server uses an emotion engine to analyze the user's feedback.

[0570] The emotion engine recognizes and quantifies emotions from comments and ratings written by users. For example, it can determine a user's stress or satisfaction level from the feedback text.

[0571] The analysis results of the emotion engine are stored in a database.

[0572] Step 7: Analyze feedback and adjust support plans

[0573] The server comprehensively analyzes user feedback, including the results of emotion analysis using an emotion engine, and evaluates the effectiveness of the support plan.

[0574] If necessary, update your support plan and adjust the next support offer.

[0575] For example, if a particular support is found to be ineffective, the content of the support will be changed appropriately. Also, if the user is under high stress, additional psychological support will be considered.

[0576] The system efficiently executes a series of processes, from data collection and analysis, to fund allocation, feedback collection and sentiment analysis, and further adjustment, optimizing funding and support for the poor and bringing about social improvements.

[0577] Example 2

[0578] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0579] In modern society, there is a need for effective funding and support for the poor. However, existing systems do not adequately analyze collected data or allocate funds appropriately, and they lack the ability to optimize support plans that take into account user emotions and feedback.

[0580] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for analyzing data collected from the poor, non-governmental organizations, and the government and allocating funds based on a specific method; means for storing and pre-processing the collected data; means for generating a support plan using a machine learning algorithm; means for determining the allocation of funds based on the support plan generated via a notification interface and notifying the user; and means for analyzing feedback from the user using an emotion engine, quantifying the emotional state, and adjusting the support plan. This allows a series of processes, from data collection and analysis, to fund allocation, emotional feedback collection, and further adjustment, to be carried out efficiently, enabling effective support for the poor.

[0581] "Poor" refers to individuals or families who are in financial difficulty and have difficulty accessing basic necessities and services.

[0582] "Non-governmental organizations" are non-governmental organizations that address social issues in a private capacity, often working in areas such as poverty, health, and the environment.

[0583] "Government" refers to a national or local public institution that promotes the public welfare through various policies and programs.

[0584] "Data collection" refers to the process of gathering information for a specific purpose, and includes methods such as surveys, API access, and sensors.

[0585] "Data preprocessing" refers to a series of operations that convert collected data into a format that is easier to analyze, including filling in missing values ​​and cleaning the data.

[0586] A "machine learning algorithm" refers to a computational method for learning from data and making predictions and classifications, and there are a variety of models and techniques.

[0587] A "support plan" is a plan that lays out the specific support content and methods to be provided to eligible individuals and families, and includes financial support and service provision.

[0588] A "notification interface" refers to a user interface used on mobile devices and PCs to display information and messages to users.

[0589] An "emotion engine" refers to algorithms and technologies for recognizing and analyzing a user's emotional state, quantifying emotions from user input and feedback.

[0590] "Feedback" refers to opinions and status reports provided by users, which are used to improve and adjust the system.

[0591] "Funding allocation" refers to the process of determining the amount and use of funds provided to specific individuals or households based on collected and analyzed data.

[0592] The present invention is a system for efficiently providing funds and support to the poor, and aims to provide more effective support plans by combining it with an emotion engine that recognizes the user's emotions. Detailed embodiments of this system will be described below.

[0593] System Configuration

[0594] This system mainly consists of a server, terminals, and users.

[0595] Data Collection Module

[0596] The server collects data from the poor, non-governmental organizations (NGOs), and governments. This data includes users' annual income, household composition, housing situation, health status, NGO activity reports, and government welfare policy data. The server periodically distributes questionnaire forms and stores the collected information in a database. It also obtains data in real time from NGOs and governments via APIs.

[0597] Example: Obtaining data from the government on unemployment rates and the number of people receiving welfare via an API.

[0598] Data Preprocessing Module

[0599] The server preprocesses the collected data and converts it into a format that is easy to process with machine learning algorithms. Preprocessing includes removing unnecessary data, filling in missing data, and standardizing data formats.

[0600] Example: The server imputes NULL values ​​in the data with the average value.

[0601] Algorithm Module

[0602] The server then uses a machine learning algorithm to generate an optimal support plan based on the preprocessed data. The algorithm compares past and current data to predict effective support methods.

[0603] Example: Using machine learning algorithms to generate special assistance plans for families who experience a sudden drop in income, providing them with $50,000 per month.

[0604] Money Management Module

[0605] The server determines how funds are allocated based on the generated support plan, ensuring that the allocation is fair and transparent, and that the necessary amount is distributed appropriately to each household.

[0606] Example: Based on a support plan generated by the server, a specific household is allocated 30,000 yen per month, plus an additional 10,000 yen for education-related support.

[0607] User Interface

[0608] The device (user's mobile device or PC) provides an interface that displays the support results. Through this interface, the user can check the support content and provide feedback as needed.

[0609] Example: The user's smartphone is notified of the support provided, and the user provides feedback through the application, such as "This support was helpful."

[0610] Emotion Engine

[0611] The server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's input data and feedback, recognizes and quantifies the user's emotional state, and reflects this in the next support plan.

[0612] Example: If a user comments, "I need more money for my child's education," the sentiment engine analyzes the content of the comment and reflects the addition of educational support in the next support plan.

[0613] Prompt Sentence Examples

[0614] "Please explain how you will use the collected data to generate optimal support plans for newly supported families and monitor their effectiveness."

[0615] By operating in this way, the system can effectively provide funding and support to the poor. In addition, by utilizing an emotion engine, it is possible to provide more detailed support that takes into account the user's emotions and feedback.

[0616] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0617] Step 1: Data collection

[0618] The server collects data from the poor, non-governmental organizations (NGOs), and governments. First, it periodically distributes questionnaire forms to users to collect information such as annual income, household composition, housing situation, and health status. It also obtains data from NGOs and governments in real time via APIs and stores the collected data in a database. This effectively integrates information from users, NGOs, and governments. The input is questionnaire responses and data from the API, and the output is data stored in the database.

[0619] Specific operation: The server obtains data on unemployment rates and the number of welfare recipients from the government via an API and stores it in a database.

[0620] Step 2: Data Preprocessing

[0621] The server preprocesses the collected data and converts it into a format that is easy to process with machine learning algorithms. Specifically, it deletes unnecessary data, fills in missing data, standardizes data formats, etc. The input is raw data, and the output is preprocessed data.

[0622] Specific operation: The server fills in NULL values ​​in the collected data with the average value, cleans the data, and standardizes the format.

[0623] Step 3: Create a support plan

[0624] The server uses a machine learning algorithm to generate an optimal support plan based on the preprocessed data. The algorithm compares past data with current data and predicts effective support methods. The input is the preprocessed data, and the output is the generated support plan.

[0625] How it works: Using machine learning algorithms, it generates special assistance plans for families who experience a sudden drop in income, providing them with assistance of 50,000 yen per month.

[0626] Step 4: Fund allocation

[0627] The server determines how to allocate funds based on the generated support plan. The allocation is fair and transparent, and the necessary amount is distributed appropriately to each household. The input is the generated support plan, and the output is the fund allocation result.

[0628] Specific operation: Based on the support plan, the server allocates 30,000 yen per month to each household, plus an additional 10,000 yen for education-related support.

[0629] Step 5: Notification and feedback

[0630] The device notifies the user of the assistance provided and provides an interface for the user to provide feedback. The user reports the usage status of the assistance and any additional needs through this interface. The input is the assistance provided and the user's feedback, and the output is the collected feedback.

[0631] Specific operation: The user's smartphone is notified of the support details, and the user provides feedback through the application, such as "This support was helpful."

[0632] Step 6: Sentiment analysis

[0633] The server uses an emotion engine to analyze the user's emotional state based on their feedback. The analysis results are reflected in the next support plan. The input is the user's feedback, and the output is the analyzed emotional data.

[0634] What it does: If a user comments, "I need more money for my child's education," the sentiment engine analyzes the content of the comment and reflects the addition of educational support in the next support plan.

[0635] Through this series of steps, the system can efficiently provide funding and support to the poor, with each step linking up with the others to effectively collect data, analyze it, allocate funds, collect emotional feedback, and make further adjustments.

[0636] (Application example 2)

[0637] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0638] Employee psychological fatigue and stress are serious problems that lead to decreased productivity and increased employee turnover. However, many current systems lack the ability to provide support based on emotion recognition, and do not adequately address the psychological challenges faced by employees. Therefore, a system that can properly recognize employees' emotions and provide appropriate support based on that recognition is needed.

[0639] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0640] In this invention, the server includes means for analyzing data collected from the poor, non-governmental organizations, and governments and allocating funds based on a specific methodology, means for storing and pre-processing the collected data, means for generating a support plan using a machine learning algorithm, means for determining fund allocation based on the generated support plan and notifying the user, means for collecting feedback from the user and adjusting the support plan, and means for analyzing the emotional state of employees and providing appropriate support for psychological fatigue and stress. This makes it possible to appropriately understand the emotional state of employees and provide psychological support, thereby reducing psychological fatigue and stress.

[0641] The "poor" are people who are financially disadvantaged and unable to obtain the basic necessities of life.

[0642] A "non-governmental organization" is an organization that operates independently of the government and primarily engages in activities such as solving social problems and supporting the poor.

[0643] A "government" is an institution that is responsible for running a nation, enacting and enforcing laws, and carrying out various activities related to the welfare of the people.

[0644] A "machine learning algorithm" is a method by which a computer learns from data and automatically recognizes patterns, allowing it to make predictions and classifications.

[0645] A "support plan" is a plan of assistance to be provided based on specific circumstances and needs, including allocation of funds and services.

[0646] "Emotional state" refers to the type and intensity of emotions experienced by an individual and consists of psychological states such as stress, happiness, and anxiety.

[0647] "Psychological fatigue" is a state in which mental energy is reduced and concentration and work efficiency are reduced due to long-term stress or strain.

[0648] "Stress" is a state of tension caused by mental or physical strain due to external pressures or demands.

[0649] "Feedback" refers to the evaluation or reaction of a system or individual to an action or result, and is information used for improvement or adjustment.

[0650] This invention is a system for reducing psychological fatigue and stress among employees, which analyzes data collected from the poor, non-governmental organizations, and governments, and allocates funds and support plans based on specific methods. The specific configuration and operation of the system are described below.

[0651] The server uses the following hardware and software:

[0652] Emotion recognition library: Used to analyze the user's emotional state. For example, we use a library called "EmotionRecognizer."

[0653] Machine learning algorithms are used to generate support plans, for example, using "Linear Regression" or other regression models.

[0654] Database: Stores data collected from users, non-governmental organizations, and governments.

[0655] Cloud servers: For data processing and analysis, for example, using Amazon Web Services (AWS) or Google Cloud Platform (GCP).

[0656] 1. Data Collection Module

[0657] The server collects real-time data from users, non-governmental organizations, and governments, and stores it in a database. Collected data includes employees' emotional states, stress levels, survey results, etc.

[0658] 2. Data Preprocessing

[0659] The server preprocesses the collected data, converting it into a format that is easier for machine learning algorithms to process, which includes steps such as tokenizing and quantifying the text data.

[0660] 3. Support plan generation

[0661] The server uses machine learning algorithms to generate a support plan that best suits each user's situation. For example, if an employee inputs, "I've been feeling very stressed lately," the system will suggest "psychological counseling."

[0662] 4. Allocation of funds and support

[0663] Based on the generated support plan, the server determines the allocation of funds and support and notifies the user of the details.

[0664] 5. Feedback collection and sentiment analysis

[0665] The device collects feedback from the user and sends the data to a server, which uses an emotion recognition library to analyze the user's emotional state and adjusts the support plan.

[0666] Specific examples

[0667] Example: If the input is "I've been feeling very stressed lately," the server will use "EmotionRecognizer" to recognize the emotion as "stress" and use "LinearRegression" to suggest a support plan such as "psychological counseling."

[0668] Example prompt: "An employee reports their recent emotional state in text: 'I've been feeling very stressed lately.' The system should suggest an appropriate support plan."

[0669] This system makes it possible to properly grasp the emotional state of employees and reduce psychological fatigue and stress.

[0670] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0671] Step 1:

[0672] The server collects data in real time from users, non-governmental organizations, and governments. Specifically, it collects data such as users' emotional state, stress levels, and survey results, and stores it in a database. The collected data is periodically retrieved using an API and stored in the database. The input is raw data provided by each entity, and the output is organized data stored in the database.

[0673] Step 2:

[0674] The server preprocesses the collected data. Specifically, it converts the raw data into a format that is easy for machine learning algorithms to process. This includes tokenizing and quantifying text data, filling in missing data, and normalizing the data. This generates data in a format suitable for machine learning models. The input is the raw data in the database, and the output is the preprocessed data.

[0675] Step 3:

[0676] The server uses the preprocessed data to apply a machine learning algorithm (e.g., Linear Regression) to generate a support plan that is optimal for each user's situation. For example, if an employee enters, "I've been feeling very stressed lately," the system analyzes it and suggests "psychological counseling." The input is the preprocessed data, and the output is the generated support plan.

[0677] Step 4:

[0678] The server determines the allocation of funds and support based on the generated support plan. Specifically, it plans the budget allocation and resource distribution corresponding to the support plan and stores the details in a database. The input is the generated support plan, and the output is the specific funding allocation and support details.

[0679] Step 5:

[0680] The terminal notifies the user of the details of the funds and support. The notified information includes details of the support plan and budget allocation. This allows the user to confirm their own support details and begin applying them. The input is the support plan and allocation information from the server, and the output is the notification to the user.

[0681] Step 6:

[0682] The terminal collects feedback from the user. The user can report whether the support plan is appropriate or whether additional support is needed. The collected feedback is sent to the server. The input is the user's feedback, and the output is the feedback data sent to the server.

[0683] Step 7:

[0684] The server uses an emotion recognition library (e.g., EmotionRecognizer) to analyze the user's emotional state from the feedback and adjusts the support plan based on the results. For example, if the feedback indicates that the user's stress level is still high, it provides additional support. The input is the feedback data, and the output is the adjusted support plan.

[0685] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0686] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0687] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0688] [Third embodiment]

[0689] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0690] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0691] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0692] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0693] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0694] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0695] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0696] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0697] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0698] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0699] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0700] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0701] This invention is a system for efficiently providing funds and support to the poor. This system mainly consists of four components: a data collection module, a fund management module, a user interface, and an algorithm module.

[0702] System Configuration

[0703] 1. Server: Data collection module

[0704] The server collects data from the poor, non-governmental organizations (NGOs), and governments. This data includes users' annual income, household composition, housing situation, health status, NGO activity reports, and government welfare policy data. For example, the server periodically sends questionnaire forms to users and stores the collected information in a database. It also obtains data in real time from NGOs and governments via APIs.

[0705] 2. Server: Funds Management Module

[0706] The server allocates funds to each user based on the collected data. The collected data is first preprocessed and stored in a database. Machine learning algorithms then analyze the data to generate a support plan that best suits each user's situation. For example, a specific household may receive 30,000 yen in monthly support, with additional funds allocated to education-related programs. This allocation of funds is done fairly and effectively based on the algorithm.

[0707] 3. Terminal: User Interface

[0708] An interface that displays the support results is provided on the device (user's mobile device or PC). Users can check the details of their support and provide feedback if necessary. For example, there is a function to report the status of fund use and whether additional support is needed. The user interface is also designed to be intuitive and easy to use, allowing users to quickly find the information they need.

[0709] 4. Server: Algorithm Module

[0710] The server uses machine learning algorithms to analyze the collected data and generate optimal support plans. The algorithms take into account past and current user data to predict the most effective support methods. For example, they could provide extra support to families experiencing a sudden drop in income and monitor the effectiveness of that support. This algorithm can improve the closeness and accuracy of support.

[0711] This system efficiently executes a series of processes, from data collection to generating assistance plans, allocating funds, and collecting and adjusting feedback. This optimizes the provision of funds and support to the poor and improves society. Specifically, the server collects and analyzes data, generates assistance plans based on the results, and notifies users. Users receive the assistance provided and send the results back to the server as feedback. In this way, the entire system is constantly updated, enabling it to continue providing optimal assistance.

[0712] The processing flow will be explained below.

[0713] Step 1: Collect data

[0714] The server collects questionnaires and registration information from the poor, with users entering information such as their annual income, household composition, housing situation, and health status.

[0715] The server receives activity reports from non-governmental organizations (NGOs), collecting data such as the type of support provided by the NGOs, the number of people who received support, and the success of their efforts.

[0716] The server retrieves policy information and assistance program data from public government databases, collecting information such as policy implementation status, budget allocation, and target demographics.

[0717] All collected data is stored in a database.

[0718] Step 2: Preprocessing the data

[0719] The server preprocesses all collected data, for example by imputing missing data and correcting outliers.

[0720] Once the data is cleansed, it is standardized and converted into a format that is easy for machine learning algorithms to process.

[0721] Step 3: Create a support plan

[0722] The server uses machine learning algorithms to generate a support plan that is optimal for each user's situation.

[0723] The algorithm uses past data and patterns to predict what type of support will be most effective.

[0724] For example, this includes specific measures such as "providing 30,000 yen in support per month" or "supporting participation in specific educational programs."

[0725] Step 4: Allocate funds

[0726] The server determines the specific allocation of funds to each user based on the generated support plan.

[0727] For example, a detailed funding allocation plan would be created, allocating additional support to families with children who earn below a certain monthly income.

[0728] Step 5: Notify and gather feedback

[0729] The device will then notify the user of the support plan and assistance details, which will then be displayed on the user's mobile device or PC.

[0730] Users can view details of their assigned assistance in the app or web portal.

[0731] Users provide feedback on how effective the support was, report on the use of funds, and whether they need additional assistance.

[0732] Step 6: Analyze feedback and adjust support plans

[0733] The server analyzes user feedback and evaluates the effectiveness of the support plan.

[0734] If necessary, update your support plan and adjust the next support offer.

[0735] For example, if a particular support is found to be ineffective, the content will be modified appropriately.

[0736] The system efficiently carries out a series of processes from data collection and analysis, to fund allocation, feedback collection, and further adjustments.

[0737] Example 1

[0738] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0739] In order to effectively and efficiently provide funding and support to the poor, a system that smoothly collects data, analyzes it, allocates funds, provides a user interface, and collects and evaluates feedback is required. Conventional systems have issues with uncertainty in data collection, fairness in fund allocation, and insufficient reflection of user feedback, making it difficult to provide optimal support.

[0740] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0741] In this invention, the server includes means for analyzing data collected from the poor, non-governmental organizations, and the government and allocating funds based on a specific methodology, means for storing and pre-processing the collected data, means for generating a support plan using a machine learning algorithm, means for determining fund allocation based on the generated support plan and notifying the user, means for collecting feedback via the user's terminal and adjusting the support plan, means for providing an intuitive and easy-to-use interface to the terminal, and means for the server to periodically distribute questionnaire forms to users to collect data. This enables efficient data collection, accurate fund allocation, and proactive feedback collection and evaluation.

[0742] "Data collection" is the process of gathering information of interest from various sources.

[0743] "Analysis" is the process of converting collected data into an understandable form and evaluating its content.

[0744] Funding allocation is the process of effectively allocating available funds according to user and organizational needs.

[0745] "Preprocessing" is the process of cleaning and transforming collected data to improve its quality.

[0746] A "machine learning algorithm" is a computational method that learns patterns and rules from data and makes predictions and judgments based on them.

[0747] A "support plan" is a plan that describes the specific content and methods of support to be provided to users and organizations based on the analyzed data.

[0748] "Notification" is the process by which the system notifies the user of information.

[0749] "Feedback" is the process by which a user provides a response or opinion to the system in response to the assistance provided.

[0750] An "interface" is a screen or operating means by which a user interacts with a system.

[0751] A "survey form" is a paper or electronic document containing specific questions that is used to collect information from a user.

[0752] This invention is a system for efficiently providing funding and support to the poor. The system consists of four main components: a data collection module, a fund management module, a user interface, and an algorithm module.

[0753] Data Collection Module

[0754] The server collects various data from the poor, non-governmental organizations (NGOs), and governments. This data includes users' annual income, household composition, housing situation, health status, NGO activity reports, and government welfare policy data. Specifically, the server periodically sends questionnaire forms to users and stores the collected information in a database. It also obtains data in real time from NGOs and governments via APIs. A database management system such as MySQL is used to store the data.

[0755] For example, the server sends a push notification to the user asking, "What is your current income?", and when the user responds, the data is stored in a database. NGO activity reports are automatically collected and stored through API requests.

[0756] Money Management Module

[0757] The server preprocesses the collected data, stores it in a database, and then analyzes it using a machine learning algorithm. The results are used to generate a support plan that is optimal for each user's situation. The preprocessing uses Python's Pandas library to fill in missing data and remove outliers.

[0758] For example, Python is used to clean the data and input it into a machine learning model using TensorFlow, which generates a support plan such as "If income is less than ¥100,000, provide ¥10,000 per month in support."

[0759] User Interface

[0760] The device provides a user interface on their mobile device or PC that displays details of their donation, allowing them to provide feedback on the status of fund use and whether additional donations are needed. This interface is built using front-end frameworks such as React.

[0761] For example, users can use an in-app form to answer the question "How did you use the funds you received?" and then send that feedback to the server.

[0762] Algorithm Module

[0763] The server then feeds the collected feedback data back into the algorithm to evaluate the effectiveness of the assistance provided. This analysis is performed using machine learning libraries such as TensorFlow and Scikit-learn. After evaluating the effectiveness, the assistance plan is adjusted as necessary.

[0764] For example, feedback data can be input into the model, and the model can be retrained based on newly acquired information to optimize the next assistance plan.

[0765] Prompt Sentence Examples

[0766] Prompt: Describe a system for providing optimal assistance plans to the poor. Using the data below, detail the process from collecting data to generating assistance plans, allocating funds, and gathering feedback.

[0767] User's annual income: 100,000 yen

[0768] Family composition: 5 people family

[0769] Housing Status: Rented

[0770] Health: Good

[0771] NGO Activity Report

[0772] Government welfare policy data

[0773] The system efficiently executes a series of processes, from data collection to generating support plans, allocating funds, and collecting and adjusting feedback, thereby optimizing funding and support for the poor and achieving social improvement.

[0774] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0775] Step 1: Data collection

[0776] The server collects data from poor users, non-governmental organizations (NGOs), and the government. This process involves sending periodic questionnaire forms and retrieving data in real time using an API. Specifically, the server sends a push notification to the user's smartphone asking, "What is your current income?" and stores the data the user responds to in a database. It also receives activity reports and welfare policy data in JSON format from the NGO and government via API, which it stores in the database. The input in this step is the questionnaire responses and JSON data retrieved from the API, and the output is data stored in the database.

[0777] Step 2: Data Preprocessing

[0778] The server preprocesses the collected data. Specifically, it completes missing data, removes outliers, and standardizes data formats. It uses Python's Pandas library to clean the data and, if necessary, completes missing data with average values. For example, if income data is missing, it completes the average income value. The input in this step is raw data obtained from the database, and the output is the clean data after preprocessing.

[0779] Step 3: Create a support plan

[0780] The server inputs the preprocessed data into a machine learning algorithm to generate an optimal support plan. The algorithm uses machine learning libraries such as TensorFlow and Scikit-learn. Specifically, it determines the optimal financial support amount and program for each user, taking into account factors such as income, family composition, housing situation, and health status. For example, it generates an output such as "If income is less than 100,000 yen, 10,000 yen in support will be provided per month." The input in this step is the clean data after preprocessing, and the output is the generated support plan.

[0781] Step 4: Notification of support plan

[0782] The server notifies the user's device of the details of the generated support plan. Specifically, it provides an interface for displaying the details of the support plan and funding allocation on the user's mobile device or PC. A front-end framework such as React is used to provide an intuitive and easy-to-use UI for the user. For example, when the user opens the app, it displays the message, "Your support plan is for a monthly funding of 10,000 yen." The input in this step is the generated support plan, and the output is a notification displayed on the user's device.

[0783] Step 5: Gather feedback

[0784] The terminal provides a function to collect feedback from users. Users can report on the support they received, their use of the funds, and the need for additional support. Specifically, users use a form within the app to answer questions such as "How did you use the funds you received?", and the feedback is sent to the server. The input in this step is the user's feedback, and the output is the feedback data sent to the server.

[0785] Step 6: Analyze feedback and refine your support plan

[0786] The server then inputs the collected feedback data back into the machine learning algorithm to evaluate the effectiveness of the support provided. Using the collected feedback data as new data points, the model is retrained and updated to the optimal support plan. Specifically, the information obtained from the feedback is analyzed, and the content and amount of support is readjusted if necessary. For example, if the feedback indicates that a particular household needs additional support, an additional 5,000 yen per month will be provided to that household. The input in this step is the feedback data, and the output is an updated support plan.

[0787] (Application example 1)

[0788] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0789] In modern society, providing support to the poor is an important issue, but doing so efficiently and effectively is difficult. In particular, advanced data analysis is required to allocate appropriate funds according to individual circumstances, and to quickly monitor and evaluate them. It is also necessary to ensure the transparency and fairness of support while appropriately adjusting support plans based on feedback from users. Conventional systems are unable to adequately resolve these issues, which often leads to a decline in the efficiency and effectiveness of support. Providing a user interface that allows users to intuitively understand the details of the support is also an important element.

[0790] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0791] In this invention, the server includes: means for analyzing data collected from the poor, non-governmental organizations, and governments and allocating funds based on a specific methodology; means for storing and pre-processing the collected data; means for generating a support plan using a machine learning algorithm; means for determining fund allocation based on the generated support plan and notifying users via an electronic device; means for collecting feedback from users and adjusting the support plan; means for predicting support amounts using a machine learning algorithm and calculating the optimal support amount for each user; means for analyzing support plans based on the generative AI model and presenting different support plans to each user; means for collecting user registration information and storing it in a database accessible from smartphones or other mobile devices; and means for displaying support history, thereby enabling appropriate and efficient support to the poor.

[0792] The "poor" are people who are socially and economically disadvantaged and do not have enough income to meet basic necessities of life.

[0793] A "non-governmental organization" is an organization established independently of the government that carries out activities for the public good or to solve social problems.

[0794] A "government" is a public institution that governs a country or region, enforces laws, and provides public services.

[0795] "Data analysis" is the process of processing collected information to gain meaningful insights.

[0796] "Fund allocation" is the act of appropriately distributing funds for specific purposes or targets.

[0797] A "machine learning algorithm" is a set of techniques that allow computers to learn from data and perform analyses such as predictions and classifications.

[0798] A "support plan" is a plan for specific support content for a target based on the target's specific situation and needs.

[0799] An "electronic terminal" is a device that processes and communicates digital information, such as a smartphone or personal computer.

[0800] "User" refers to the target or beneficiary of the system.

[0801] "Feedback" refers to opinions and evaluation information provided by users, which is used to improve the system.

[0802] A "generative AI model" is a computational model that is generated using artificial intelligence techniques to perform a specific task.

[0803] A "database" is a system for efficiently storing, searching, and managing data.

[0804] "Support history" is information that records the support provided in the past and the results thereof.

[0805] This will enable appropriate and efficient support to the poor.

[0806] The system that realizes this invention is composed of two main components, a server and a terminal, in order to efficiently provide funds and support to the poor.

[0807] Server Configuration

[0808] Data Collection Module

[0809] The server has multiple means for collecting data from the poor, non-governmental organizations, and governments. This data includes users' annual income, household composition, housing situation, and health status. Specifically, the server periodically sends users questionnaires and stores their responses in a database. Furthermore, the server obtains data in real time from non-governmental organizations and governments via APIs. For example, activity reports from non-governmental organizations and welfare policy data from governments are also collected.

[0810] Money Management Module

[0811] The server preprocesses the collected data, stores it in a database, and then analyzes it using machine learning algorithms. Based on this analysis, an effective support plan is generated. For example, a specific household could receive 30,000 yen per month in support and additionally allocate funds related to education. The algorithm ensures that such fund allocation is fair and effective.

[0812] User Interface

[0813] The device (such as the user's smartphone or computer) provides an interface that notifies the user of the support plan and the results of the allocation of funds. Through this interface, users can check the details of their support and provide feedback as needed. For example, the system has a function to report the status of fund use and whether additional support is needed. The interface is also intuitive, allowing users to quickly find the information they need.

[0814] Algorithm Module

[0815] The server uses machine learning algorithms to analyze the collected data and generate optimal support plans. The algorithms take into account past and current user data to predict the most effective support methods. For example, special support can be provided to families experiencing a sudden drop in income, and the effectiveness of such support can be monitored.

[0816] Specific examples

[0817] For example, the information a user must provide when registering with the system is as follows:

[0818] name

[0819] age

[0820] annual income

[0821] household composition

[0822] health status

[0823] Based on this data, the server generates a support plan as follows:

[0824] "Taro Tanaka, 45 years old, annual income 200,000 yen, household of four, healthy."

[0825] The server analyzes this information and determines that Taro Tanaka is to receive a monthly donation of 25,000 yen. This is notified through the user interface, and Taro Tanaka can not only receive the donation but also provide feedback.

[0826] Hardware and software used

[0827] Hardware: Servers, smartphones, PCs

[0828] Software: Python, Flask (web framework), SQLite (database), scikit-learn (machine learning library)

[0829] This system will enable appropriate and efficient support for the poor. By using generative AI models, effective support plans are quickly generated and the results are communicated via a user-friendly interface. This is expected to reduce uncertainty and enable concrete support to be provided promptly.

[0830] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0831] Step 1:

[0832] Data collection

[0833] The server collects data from the poor, non-governmental organizations, and governments. Specifically, it obtains information such as users' annual income, household composition, housing situation, and health status through a questionnaire form. It also obtains data in real time from non-governmental organizations and governments through APIs. The input is the user input form and data obtained through the API, and the output is preprocessed data.

[0834] Step 2:

[0835] Data preprocessing and storage

[0836] The collected data is pre-processed on the server, where incomplete data is filled in and the format is standardized. After this pre-processing, the data is stored in a database (e.g., SQLite). The input is the collected raw data, and the output is the cleaned data.

[0837] Step 3:

[0838] Training a machine learning model

[0839] The server uses the preprocessed data to train a machine learning algorithm (e.g., Linear Regression). The trained model is the basis for generating an optimal assistance plan. The input is the preprocessed data, and the output is the trained machine learning model.

[0840] Step 4:

[0841] Generate a support plan

[0842] The server uses a trained machine learning model to generate an optimal support plan based on each user's data. As a specific example, it inputs features such as income, household composition, and health status, and outputs a support amount. The input is feature data for each user (annual income, household composition, etc.), and the output is a support plan (e.g., ¥30,000 support per month).

[0843] Step 5:

[0844] Notification of support plan

[0845] The generated support plan is notified to the user via their device. The user can then check their support plan using a smartphone or computer. The input is the generated support plan, and the output is the support plan displayed on the user's device.

[0846] Step 6:

[0847] Gathering feedback

[0848] The user sends feedback on the support provided to the server through the terminal. For example, the user can report on the status of fund utilization or whether additional support is needed. The input is the user's feedback information, and the output is the collected feedback data.

[0849] Step 7:

[0850] Coordinating support plans

[0851] The server then readjusts the assistance plan based on the collected feedback, which may involve retraining the algorithm or assessing whether additional assistance is needed. The input is the collected feedback data, and the output is a new, adjusted assistance plan.

[0852] For example, if a user provides the following information to the system:

[0853] "Taro Tanaka, 45 years old, annual income 200,000 yen, household of four, healthy."

[0854] Using the generative AI model, the server decides to provide Taro Tanaka with ¥25,000 in monthly support and notifies him of this. Taro Tanaka then provides feedback on the effectiveness of the support, and the server uses this feedback to adjust the support plan.

[0855] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0856] The present invention aims to provide a system for efficiently providing funding and support to the poor, and to provide more effective support plans by combining it with an emotion engine that recognizes the user's emotions. This system mainly consists of the following components: a data collection module, a fund management module, a user interface, an algorithm module, and an emotion engine.

[0857] System Configuration

[0858] 1. Server: Data collection module

[0859] The server collects data from the poor, non-governmental organizations (NGOs), and governments. This data includes users' annual income, household composition, housing situation, health status, NGO activity reports, and government welfare policy data. The server periodically distributes questionnaire forms and stores the collected information in a database. It also obtains data in real time from NGOs and governments via APIs.

[0860] 2. Server: Funds Management Module

[0861] The server allocates funds to each user based on the collected data. First, the collected data is preprocessed and stored in a database. Then, machine learning algorithms analyze the data and generate a support plan that best suits each user's situation. For example, a specific household may receive 30,000 yen in monthly support and additional funds may be allocated to education-related programs. This allocation of funds is done fairly and effectively based on the algorithm.

[0862] 3. Terminal: User Interface

[0863] An interface is provided on the device (user's mobile device or PC) that displays the support results. Users can check the content of their support and provide feedback if necessary. For example, there is a function to report the status of fund use and whether additional support is needed. The user interface is also designed to be intuitive and easy to use, allowing users to quickly find the information they need.

[0864] 4. Server: Algorithm Module

[0865] The server uses machine learning algorithms to analyze the collected data and generate optimal support plans. The algorithms take into account past and current user data to predict the most effective support methods. For example, they could provide extra support to families who have experienced a sudden drop in income and monitor the effectiveness of the plan.

[0866] 5. Server: Emotion Engine

[0867] The server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's input data and feedback to recognize and quantify their emotional state. For example, the emotion engine evaluates stress and satisfaction levels based on the comments and evaluations written by the user, and reflects the results in the support plan. This allows for more detailed support that takes emotional aspects into account.

[0868] Specific operation of the system

[0869] 1. Data collection: The server collects data from users, NGOs, and governments and stores it in a database.

[0870] 2. Data preprocessing: The server preprocesses the collected data and converts it into a format that is easy to process with machine learning algorithms.

[0871] 3. Support plan generation: The server uses an algorithm to generate the optimal support plan.

[0872] 4. Fund allocation: The server determines the allocation of funds based on the generated support plan.

[0873] 5. Notification and feedback: The device notifies the user of the assistance provided, and the user provides feedback.

[0874] 6. Emotion analysis: The server uses an emotion engine to analyze the user's emotional state from their feedback and reflect this in the next support plan.

[0875] The system efficiently executes a series of processes, from data collection and analysis to fund allocation, emotional feedback collection, and further adjustments. This optimizes funding and support for the poor and promotes social improvement. For example, the server can use collected data to identify a user's stress level and provide additional support based on the results, thereby promoting psychological stability.

[0876] The processing flow will be explained below.

[0877] Step 1: Collect data

[0878] The server collects questionnaire forms and registration information from users. Users enter information such as annual income, family composition, housing situation, and health status into an online form.

[0879] The server receives activity reports from non-governmental organizations (NGOs) via API, automatically collecting data such as the type of support provided by the NGO, the number of people who received support, and the success of the measures.

[0880] The server retrieves policy information and assistance program data from public government databases, periodically downloading information on policy implementation status, budget allocations, target demographics, and more.

[0881] All collected data is stored in a database.

[0882] Step 2: Preprocessing the data

[0883] The server preprocesses all collected data, for example by imputing missing data and correcting outliers.

[0884] Once the data is cleansed, it is standardized and converted into a format that is easy for machine learning algorithms to process.

[0885] Step 3: Create a support plan

[0886] The server uses machine learning algorithms to generate a support plan that is optimal for each user's situation.

[0887] The algorithm uses past data and patterns to predict what type of support will be most effective.

[0888] For example, this includes specific measures such as "providing 30,000 yen in support per month" or "supporting participation in specific educational programs."

[0889] Step 4: Allocate funds

[0890] The server determines the specific allocation of funds to each user based on the generated support plan.

[0891] For example, a detailed funding allocation plan would be created, allocating additional support to families with children who earn below a certain monthly income.

[0892] Step 5: Notify and gather feedback

[0893] The device will then notify the user of the support plan and assistance details, which will then be displayed on the user's mobile device or PC.

[0894] Users can view details of their assigned assistance in the app or web portal.

[0895] Users provide feedback on how effective the support was, report on the use of funds, and whether they need additional assistance.

[0896] Step 6: Sentiment analysis with the sentiment engine

[0897] The server uses an emotion engine to analyze the user's feedback.

[0898] The emotion engine recognizes and quantifies emotions from comments and ratings written by users. For example, it can determine a user's stress or satisfaction level from the feedback text.

[0899] The analysis results of the emotion engine are stored in a database.

[0900] Step 7: Analyze feedback and adjust support plans

[0901] The server comprehensively analyzes user feedback, including the results of emotion analysis using an emotion engine, and evaluates the effectiveness of the support plan.

[0902] If necessary, update your support plan and adjust the next support offer.

[0903] For example, if a particular support is found to be ineffective, the content of the support will be changed appropriately. Also, if the user is under high stress, additional psychological support will be considered.

[0904] The system efficiently executes a series of processes, from data collection and analysis, to fund allocation, feedback collection and sentiment analysis, and further adjustment, optimizing funding and support for the poor and bringing about social improvements.

[0905] Example 2

[0906] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0907] In modern society, there is a need for effective funding and support for the poor. However, existing systems do not adequately analyze collected data or allocate funds appropriately, and they lack the ability to optimize support plans that take into account user emotions and feedback.

[0908] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for analyzing data collected from the poor, non-governmental organizations, and the government and allocating funds based on a specific method; means for storing and pre-processing the collected data; means for generating a support plan using a machine learning algorithm; means for determining the allocation of funds based on the support plan generated via a notification interface and notifying the user; and means for analyzing feedback from the user using an emotion engine, quantifying the emotional state, and adjusting the support plan. This allows a series of processes, from data collection and analysis, to fund allocation, emotional feedback collection, and further adjustment, to be carried out efficiently, enabling effective support for the poor.

[0909] "Poor" refers to individuals or families who are in financial difficulty and have difficulty accessing basic necessities and services.

[0910] "Non-governmental organizations" are non-governmental organizations that address social issues in a private capacity, often working in areas such as poverty, health, and the environment.

[0911] "Government" refers to a national or local public institution that promotes the public welfare through various policies and programs.

[0912] "Data collection" refers to the process of gathering information for a specific purpose, and includes methods such as surveys, API access, and sensors.

[0913] "Data preprocessing" refers to a series of operations that convert collected data into a format that is easier to analyze, including filling in missing values ​​and cleaning the data.

[0914] A "machine learning algorithm" refers to a computational method for learning from data and making predictions and classifications, and there are a variety of models and techniques.

[0915] A "support plan" is a plan that lays out the specific support content and methods to be provided to eligible individuals and families, and includes financial support and service provision.

[0916] A "notification interface" refers to a user interface used on mobile devices and PCs to display information and messages to users.

[0917] An "emotion engine" refers to algorithms and technologies for recognizing and analyzing a user's emotional state, quantifying emotions from user input and feedback.

[0918] "Feedback" refers to opinions and status reports provided by users, which are used to improve and adjust the system.

[0919] "Funding allocation" refers to the process of determining the amount and use of funds provided to specific individuals or households based on collected and analyzed data.

[0920] The present invention is a system for efficiently providing funds and support to the poor, and aims to provide more effective support plans by combining it with an emotion engine that recognizes the user's emotions. Detailed embodiments of this system will be described below.

[0921] System Configuration

[0922] This system mainly consists of a server, terminals, and users.

[0923] Data Collection Module

[0924] The server collects data from the poor, non-governmental organizations (NGOs), and governments. This data includes users' annual income, household composition, housing situation, health status, NGO activity reports, and government welfare policy data. The server periodically distributes questionnaire forms and stores the collected information in a database. It also obtains data in real time from NGOs and governments via APIs.

[0925] Example: Obtaining data from the government on unemployment rates and the number of people receiving welfare via an API.

[0926] Data Preprocessing Module

[0927] The server preprocesses the collected data and converts it into a format that is easy to process with machine learning algorithms. Preprocessing includes removing unnecessary data, filling in missing data, and standardizing data formats.

[0928] Example: The server imputes NULL values ​​in the data with the average value.

[0929] Algorithm Module

[0930] The server then uses a machine learning algorithm to generate an optimal support plan based on the preprocessed data. The algorithm compares past and current data to predict effective support methods.

[0931] Example: Using machine learning algorithms to generate special assistance plans for families who experience a sudden drop in income, providing them with $50,000 per month.

[0932] Money Management Module

[0933] The server determines how funds are allocated based on the generated support plan, ensuring that the allocation is fair and transparent, and that the necessary amount is distributed appropriately to each household.

[0934] Example: Based on a support plan generated by the server, a specific household is allocated 30,000 yen per month, plus an additional 10,000 yen for education-related support.

[0935] User Interface

[0936] The device (user's mobile device or PC) provides an interface that displays the support results. Through this interface, the user can check the support content and provide feedback as needed.

[0937] Example: The user's smartphone is notified of the support provided, and the user provides feedback through the application, such as "This support was helpful."

[0938] Emotion Engine

[0939] The server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's input data and feedback, recognizes and quantifies the user's emotional state, and reflects this in the next support plan.

[0940] Example: If a user comments, "I need more money for my child's education," the sentiment engine analyzes the content of the comment and reflects the addition of educational support in the next support plan.

[0941] Prompt Sentence Examples

[0942] "Please explain how you will use the collected data to generate optimal support plans for newly supported families and monitor their effectiveness."

[0943] By operating in this way, the system can effectively provide funding and support to the poor. In addition, by utilizing an emotion engine, it is possible to provide more detailed support that takes into account the user's emotions and feedback.

[0944] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0945] Step 1: Data collection

[0946] The server collects data from the poor, non-governmental organizations (NGOs), and governments. First, it periodically distributes questionnaire forms to users to collect information such as annual income, household composition, housing situation, and health status. It also obtains data from NGOs and governments in real time via APIs and stores the collected data in a database. This effectively integrates information from users, NGOs, and governments. The input is questionnaire responses and data from the API, and the output is data stored in the database.

[0947] Specific operation: The server obtains data on unemployment rates and the number of welfare recipients from the government via an API and stores it in a database.

[0948] Step 2: Data Preprocessing

[0949] The server preprocesses the collected data and converts it into a format that is easy to process with machine learning algorithms. Specifically, it deletes unnecessary data, fills in missing data, standardizes data formats, etc. The input is raw data, and the output is preprocessed data.

[0950] Specific operation: The server fills in NULL values ​​in the collected data with the average value, cleans the data, and standardizes the format.

[0951] Step 3: Create a support plan

[0952] The server uses a machine learning algorithm to generate an optimal support plan based on the preprocessed data. The algorithm compares past data with current data and predicts effective support methods. The input is the preprocessed data, and the output is the generated support plan.

[0953] How it works: Using machine learning algorithms, it generates special assistance plans for families who experience a sudden drop in income, providing them with assistance of 50,000 yen per month.

[0954] Step 4: Fund allocation

[0955] The server determines how to allocate funds based on the generated support plan. The allocation is fair and transparent, and the necessary amount is distributed appropriately to each household. The input is the generated support plan, and the output is the fund allocation result.

[0956] Specific operation: Based on the support plan, the server allocates 30,000 yen per month to each household, plus an additional 10,000 yen for education-related support.

[0957] Step 5: Notification and feedback

[0958] The device notifies the user of the assistance provided and provides an interface for the user to provide feedback. The user reports the usage status of the assistance and any additional needs through this interface. The input is the assistance provided and the user's feedback, and the output is the collected feedback.

[0959] Specific operation: The user's smartphone is notified of the support details, and the user provides feedback through the application, such as "This support was helpful."

[0960] Step 6: Sentiment analysis

[0961] The server uses an emotion engine to analyze the user's emotional state based on their feedback. The analysis results are reflected in the next support plan. The input is the user's feedback, and the output is the analyzed emotional data.

[0962] What it does: If a user comments, "I need more money for my child's education," the sentiment engine analyzes the content of the comment and reflects the addition of educational support in the next support plan.

[0963] Through this series of steps, the system can efficiently provide funding and support to the poor, with each step linking up with the others to effectively collect data, analyze it, allocate funds, collect emotional feedback, and make further adjustments.

[0964] (Application example 2)

[0965] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0966] Employee psychological fatigue and stress are serious problems that lead to decreased productivity and increased employee turnover. However, many current systems lack the ability to provide support based on emotion recognition, and do not adequately address the psychological challenges faced by employees. Therefore, a system that can properly recognize employees' emotions and provide appropriate support based on that recognition is needed.

[0967] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0968] In this invention, the server includes means for analyzing data collected from the poor, non-governmental organizations, and governments and allocating funds based on a specific methodology, means for storing and pre-processing the collected data, means for generating a support plan using a machine learning algorithm, means for determining fund allocation based on the generated support plan and notifying the user, means for collecting feedback from the user and adjusting the support plan, and means for analyzing the emotional state of employees and providing appropriate support for psychological fatigue and stress. This makes it possible to appropriately understand the emotional state of employees and provide psychological support, thereby reducing psychological fatigue and stress.

[0969] The "poor" are people who are financially disadvantaged and unable to obtain the basic necessities of life.

[0970] A "non-governmental organization" is an organization that operates independently of the government and primarily engages in activities such as solving social problems and supporting the poor.

[0971] A "government" is an institution that is responsible for running a nation, enacting and enforcing laws, and carrying out various activities related to the welfare of the people.

[0972] A "machine learning algorithm" is a method by which a computer learns from data and automatically recognizes patterns, allowing it to make predictions and classifications.

[0973] A "support plan" is a plan of assistance to be provided based on specific circumstances and needs, including allocation of funds and services.

[0974] "Emotional state" refers to the type and intensity of emotions experienced by an individual and consists of psychological states such as stress, happiness, and anxiety.

[0975] "Psychological fatigue" is a state in which mental energy is reduced and concentration and work efficiency are reduced due to long-term stress or strain.

[0976] "Stress" is a state of tension caused by mental or physical strain due to external pressures or demands.

[0977] "Feedback" refers to the evaluation or reaction of a system or individual to an action or result, and is information used for improvement or adjustment.

[0978] This invention is a system for reducing psychological fatigue and stress among employees, which analyzes data collected from the poor, non-governmental organizations, and governments, and allocates funds and support plans based on specific methods. The specific configuration and operation of the system are described below.

[0979] The server uses the following hardware and software:

[0980] Emotion recognition library: Used to analyze the user's emotional state. For example, we use a library called "EmotionRecognizer."

[0981] Machine learning algorithms are used to generate support plans, for example, using "Linear Regression" or other regression models.

[0982] Database: Stores data collected from users, non-governmental organizations, and governments.

[0983] Cloud servers: For data processing and analysis, for example, using Amazon Web Services (AWS) or Google Cloud Platform (GCP).

[0984] 1. Data Collection Module

[0985] The server collects real-time data from users, non-governmental organizations, and governments, and stores it in a database. Collected data includes employees' emotional states, stress levels, survey results, etc.

[0986] 2. Data Preprocessing

[0987] The server preprocesses the collected data, converting it into a format that is easier for machine learning algorithms to process, which includes steps such as tokenizing and quantifying the text data.

[0988] 3. Support plan generation

[0989] The server uses machine learning algorithms to generate a support plan that best suits each user's situation. For example, if an employee inputs, "I've been feeling very stressed lately," the system will suggest "psychological counseling."

[0990] 4. Allocation of funds and support

[0991] Based on the generated support plan, the server determines the allocation of funds and support and notifies the user of the details.

[0992] 5. Feedback collection and sentiment analysis

[0993] The device collects feedback from the user and sends the data to a server, which uses an emotion recognition library to analyze the user's emotional state and adjusts the support plan.

[0994] Specific examples

[0995] Example: If the input is "I've been feeling very stressed lately," the server will use "EmotionRecognizer" to recognize the emotion as "stress" and use "LinearRegression" to suggest a support plan such as "psychological counseling."

[0996] Example prompt: "An employee reports their recent emotional state in text: 'I've been feeling very stressed lately.' The system should suggest an appropriate support plan."

[0997] This system makes it possible to properly grasp the emotional state of employees and reduce psychological fatigue and stress.

[0998] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0999] Step 1:

[1000] The server collects data in real time from users, non-governmental organizations, and governments. Specifically, it collects data such as users' emotional state, stress levels, and survey results, and stores it in a database. The collected data is periodically retrieved using an API and stored in the database. The input is raw data provided by each entity, and the output is organized data stored in the database.

[1001] Step 2:

[1002] The server preprocesses the collected data. Specifically, it converts the raw data into a format that is easy for machine learning algorithms to process. This includes tokenizing and quantifying text data, filling in missing data, and normalizing the data. This generates data in a format suitable for machine learning models. The input is the raw data in the database, and the output is the preprocessed data.

[1003] Step 3:

[1004] The server uses the preprocessed data to apply a machine learning algorithm (e.g., Linear Regression) to generate a support plan that is optimal for each user's situation. For example, if an employee enters, "I've been feeling very stressed lately," the system analyzes it and suggests "psychological counseling." The input is the preprocessed data, and the output is the generated support plan.

[1005] Step 4:

[1006] The server determines the allocation of funds and support based on the generated support plan. Specifically, it plans the budget allocation and resource distribution corresponding to the support plan and stores the details in a database. The input is the generated support plan, and the output is the specific funding allocation and support details.

[1007] Step 5:

[1008] The terminal notifies the user of the details of the funds and support. The notified information includes details of the support plan and budget allocation. This allows the user to confirm their own support details and begin applying them. The input is the support plan and allocation information from the server, and the output is the notification to the user.

[1009] Step 6:

[1010] The terminal collects feedback from the user. The user can report whether the support plan is appropriate or whether additional support is needed. The collected feedback is sent to the server. The input is the user's feedback, and the output is the feedback data sent to the server.

[1011] Step 7:

[1012] The server uses an emotion recognition library (e.g., EmotionRecognizer) to analyze the user's emotional state from the feedback and adjusts the support plan based on the results. For example, if the feedback indicates that the user's stress level is still high, it provides additional support. The input is the feedback data, and the output is the adjusted support plan.

[1013] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1014] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1015] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1016] [Fourth embodiment]

[1017] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1018] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1019] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1020] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1021] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1022] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1023] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1024] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1025] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1026] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1027] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1028] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1029] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1030] This invention is a system for efficiently providing funds and support to the poor. This system mainly consists of four components: a data collection module, a fund management module, a user interface, and an algorithm module.

[1031] System Configuration

[1032] 1. Server: Data collection module

[1033] The server collects data from the poor, non-governmental organizations (NGOs), and governments. This data includes users' annual income, household composition, housing situation, health status, NGO activity reports, and government welfare policy data. For example, the server periodically sends questionnaire forms to users and stores the collected information in a database. It also obtains data in real time from NGOs and governments via APIs.

[1034] 2. Server: Funds Management Module

[1035] The server allocates funds to each user based on the collected data. The collected data is first preprocessed and stored in a database. Machine learning algorithms then analyze the data to generate a support plan that best suits each user's situation. For example, a specific household may receive 30,000 yen in monthly support, with additional funds allocated to education-related programs. This allocation of funds is done fairly and effectively based on the algorithm.

[1036] 3. Terminal: User Interface

[1037] An interface that displays the support results is provided on the device (user's mobile device or PC). Users can check the details of their support and provide feedback if necessary. For example, there is a function to report the status of fund use and whether additional support is needed. The user interface is also designed to be intuitive and easy to use, allowing users to quickly find the information they need.

[1038] 4. Server: Algorithm Module

[1039] The server uses machine learning algorithms to analyze the collected data and generate optimal support plans. The algorithms take into account past and current user data to predict the most effective support methods. For example, they could provide extra support to families experiencing a sudden drop in income and monitor the effectiveness of that support. This algorithm can improve the closeness and accuracy of support.

[1040] This system efficiently executes a series of processes, from data collection to generating assistance plans, allocating funds, and collecting and adjusting feedback. This optimizes the provision of funds and support to the poor and improves society. Specifically, the server collects and analyzes data, generates assistance plans based on the results, and notifies users. Users receive the assistance provided and send the results back to the server as feedback. In this way, the entire system is constantly updated, enabling it to continue providing optimal assistance.

[1041] The processing flow will be explained below.

[1042] Step 1: Collect data

[1043] The server collects questionnaires and registration information from the poor, with users entering information such as their annual income, household composition, housing situation, and health status.

[1044] The server receives activity reports from non-governmental organizations (NGOs), collecting data such as the type of support provided by the NGOs, the number of people who received support, and the success of their efforts.

[1045] The server retrieves policy information and assistance program data from public government databases, collecting information such as policy implementation status, budget allocation, and target demographics.

[1046] All collected data is stored in a database.

[1047] Step 2: Preprocessing the data

[1048] The server preprocesses all collected data, for example by imputing missing data and correcting outliers.

[1049] Once the data is cleansed, it is standardized and converted into a format that is easy for machine learning algorithms to process.

[1050] Step 3: Create a support plan

[1051] The server uses machine learning algorithms to generate a support plan that is optimal for each user's situation.

[1052] The algorithm uses past data and patterns to predict what type of support will be most effective.

[1053] For example, this includes specific measures such as "providing 30,000 yen in support per month" or "supporting participation in specific educational programs."

[1054] Step 4: Allocate funds

[1055] The server determines the specific allocation of funds to each user based on the generated support plan.

[1056] For example, a detailed funding allocation plan would be created, allocating additional support to families with children who earn below a certain monthly income.

[1057] Step 5: Notify and gather feedback

[1058] The device will then notify the user of the support plan and assistance details, which will then be displayed on the user's mobile device or PC.

[1059] Users can view details of their assigned assistance in the app or web portal.

[1060] Users provide feedback on how effective the support was, report on the use of funds, and whether they need additional assistance.

[1061] Step 6: Analyze feedback and adjust support plans

[1062] The server analyzes user feedback and evaluates the effectiveness of the support plan.

[1063] If necessary, update your support plan and adjust the next support offer.

[1064] For example, if a particular support is found to be ineffective, the content will be modified appropriately.

[1065] The system efficiently carries out a series of processes from data collection and analysis, to fund allocation, feedback collection, and further adjustments.

[1066] Example 1

[1067] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1068] In order to effectively and efficiently provide funding and support to the poor, a system that smoothly collects data, analyzes it, allocates funds, provides a user interface, and collects and evaluates feedback is required. Conventional systems have issues with uncertainty in data collection, fairness in fund allocation, and insufficient reflection of user feedback, making it difficult to provide optimal support.

[1069] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1070] In this invention, the server includes means for analyzing data collected from the poor, non-governmental organizations, and the government and allocating funds based on a specific methodology, means for storing and pre-processing the collected data, means for generating a support plan using a machine learning algorithm, means for determining fund allocation based on the generated support plan and notifying the user, means for collecting feedback via the user's terminal and adjusting the support plan, means for providing an intuitive and easy-to-use interface to the terminal, and means for the server to periodically distribute questionnaire forms to users to collect data. This enables efficient data collection, accurate fund allocation, and proactive feedback collection and evaluation.

[1071] "Data collection" is the process of gathering information of interest from various sources.

[1072] "Analysis" is the process of converting collected data into an understandable form and evaluating its content.

[1073] Funding allocation is the process of effectively allocating available funds according to user and organizational needs.

[1074] "Preprocessing" is the process of cleaning and transforming collected data to improve its quality.

[1075] A "machine learning algorithm" is a computational method that learns patterns and rules from data and makes predictions and judgments based on them.

[1076] A "support plan" is a plan that describes the specific content and methods of support to be provided to users and organizations based on the analyzed data.

[1077] "Notification" is the process by which the system notifies the user of information.

[1078] "Feedback" is the process by which a user provides a response or opinion to the system in response to the assistance provided.

[1079] An "interface" is a screen or operating means by which a user interacts with a system.

[1080] A "survey form" is a paper or electronic document containing specific questions that is used to collect information from a user.

[1081] This invention is a system for efficiently providing funding and support to the poor. The system consists of four main components: a data collection module, a fund management module, a user interface, and an algorithm module.

[1082] Data Collection Module

[1083] The server collects various data from the poor, non-governmental organizations (NGOs), and governments. This data includes users' annual income, household composition, housing situation, health status, NGO activity reports, and government welfare policy data. Specifically, the server periodically sends questionnaire forms to users and stores the collected information in a database. It also obtains data in real time from NGOs and governments via APIs. A database management system such as MySQL is used to store the data.

[1084] For example, the server sends a push notification to the user asking, "What is your current income?", and when the user responds, the data is stored in a database. NGO activity reports are automatically collected and stored through API requests.

[1085] Money Management Module

[1086] The server preprocesses the collected data, stores it in a database, and then analyzes it using a machine learning algorithm. The results are used to generate a support plan that is optimal for each user's situation. The preprocessing uses Python's Pandas library to fill in missing data and remove outliers.

[1087] For example, Python is used to clean the data and input it into a machine learning model using TensorFlow, which generates a support plan such as "If income is less than ¥100,000, provide ¥10,000 per month in support."

[1088] User Interface

[1089] The device provides a user interface on their mobile device or PC that displays details of their donation, allowing them to provide feedback on the status of fund use and whether additional donations are needed. This interface is built using front-end frameworks such as React.

[1090] For example, users can use an in-app form to answer the question "How did you use the funds you received?" and then send that feedback to the server.

[1091] Algorithm Module

[1092] The server then feeds the collected feedback data back into the algorithm to evaluate the effectiveness of the assistance provided. This analysis is performed using machine learning libraries such as TensorFlow and Scikit-learn. After evaluating the effectiveness, the assistance plan is adjusted as necessary.

[1093] For example, feedback data can be input into the model, and the model can be retrained based on newly acquired information to optimize the next assistance plan.

[1094] Prompt Sentence Examples

[1095] Prompt: Describe a system for providing optimal assistance plans to the poor. Using the data below, detail the process from collecting data to generating assistance plans, allocating funds, and gathering feedback.

[1096] User's annual income: 100,000 yen

[1097] Family composition: 5 people family

[1098] Housing Status: Rented

[1099] Health: Good

[1100] NGO Activity Report

[1101] Government welfare policy data

[1102] The system efficiently executes a series of processes, from data collection to generating support plans, allocating funds, and collecting and adjusting feedback, thereby optimizing funding and support for the poor and achieving social improvement.

[1103] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1104] Step 1: Data collection

[1105] The server collects data from poor users, non-governmental organizations (NGOs), and the government. This process involves sending periodic questionnaire forms and retrieving data in real time using an API. Specifically, the server sends a push notification to the user's smartphone asking, "What is your current income?" and stores the data the user responds to in a database. It also receives activity reports and welfare policy data in JSON format from the NGO and government via API, which it stores in the database. The input in this step is the questionnaire responses and JSON data retrieved from the API, and the output is data stored in the database.

[1106] Step 2: Data Preprocessing

[1107] The server preprocesses the collected data. Specifically, it completes missing data, removes outliers, and standardizes data formats. It uses Python's Pandas library to clean the data and, if necessary, completes missing data with average values. For example, if income data is missing, it completes the average income value. The input in this step is raw data obtained from the database, and the output is the clean data after preprocessing.

[1108] Step 3: Create a support plan

[1109] The server inputs the preprocessed data into a machine learning algorithm to generate an optimal support plan. The algorithm uses machine learning libraries such as TensorFlow and Scikit-learn. Specifically, it determines the optimal financial support amount and program for each user, taking into account factors such as income, family composition, housing situation, and health status. For example, it generates an output such as "If income is less than 100,000 yen, 10,000 yen in support will be provided per month." The input in this step is the clean data after preprocessing, and the output is the generated support plan.

[1110] Step 4: Notification of support plan

[1111] The server notifies the user's device of the details of the generated support plan. Specifically, it provides an interface for displaying the details of the support plan and funding allocation on the user's mobile device or PC. A front-end framework such as React is used to provide an intuitive and easy-to-use UI for the user. For example, when the user opens the app, it displays the message, "Your support plan is for a monthly funding of 10,000 yen." The input in this step is the generated support plan, and the output is a notification displayed on the user's device.

[1112] Step 5: Gather feedback

[1113] The terminal provides a function to collect feedback from users. Users can report on the support they received, their use of the funds, and the need for additional support. Specifically, users use a form within the app to answer questions such as "How did you use the funds you received?", and the feedback is sent to the server. The input in this step is the user's feedback, and the output is the feedback data sent to the server.

[1114] Step 6: Analyze feedback and refine your support plan

[1115] The server then inputs the collected feedback data back into the machine learning algorithm to evaluate the effectiveness of the support provided. Using the collected feedback data as new data points, the model is retrained and updated to the optimal support plan. Specifically, the information obtained from the feedback is analyzed, and the content and amount of support is readjusted if necessary. For example, if the feedback indicates that a particular household needs additional support, an additional 5,000 yen per month will be provided to that household. The input in this step is the feedback data, and the output is an updated support plan.

[1116] (Application example 1)

[1117] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1118] In modern society, providing support to the poor is an important issue, but doing so efficiently and effectively is difficult. In particular, advanced data analysis is required to allocate appropriate funds according to individual circumstances, and to quickly monitor and evaluate them. It is also necessary to ensure the transparency and fairness of support while appropriately adjusting support plans based on feedback from users. Conventional systems are unable to adequately resolve these issues, which often leads to a decline in the efficiency and effectiveness of support. Providing a user interface that allows users to intuitively understand the details of the support is also an important element.

[1119] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1120] In this invention, the server includes: means for analyzing data collected from the poor, non-governmental organizations, and governments and allocating funds based on a specific methodology; means for storing and pre-processing the collected data; means for generating a support plan using a machine learning algorithm; means for determining fund allocation based on the generated support plan and notifying users via an electronic device; means for collecting feedback from users and adjusting the support plan; means for predicting support amounts using a machine learning algorithm and calculating the optimal support amount for each user; means for analyzing support plans based on the generative AI model and presenting different support plans to each user; means for collecting user registration information and storing it in a database accessible from smartphones or other mobile devices; and means for displaying support history, thereby enabling appropriate and efficient support to the poor.

[1121] The "poor" are people who are socially and economically disadvantaged and do not have enough income to meet basic necessities of life.

[1122] A "non-governmental organization" is an organization established independently of the government that carries out activities for the public good or to solve social problems.

[1123] A "government" is a public institution that governs a country or region, enforces laws, and provides public services.

[1124] "Data analysis" is the process of processing collected information to gain meaningful insights.

[1125] "Fund allocation" is the act of appropriately distributing funds for specific purposes or targets.

[1126] A "machine learning algorithm" is a set of techniques that allow computers to learn from data and perform analyses such as predictions and classifications.

[1127] A "support plan" is a plan for specific support content for a target based on the target's specific situation and needs.

[1128] An "electronic terminal" is a device that processes and communicates digital information, such as a smartphone or personal computer.

[1129] "User" refers to the target or beneficiary of the system.

[1130] "Feedback" refers to opinions and evaluation information provided by users, which is used to improve the system.

[1131] A "generative AI model" is a computational model that is generated using artificial intelligence techniques to perform a specific task.

[1132] A "database" is a system for efficiently storing, searching, and managing data.

[1133] "Support history" is information that records the support provided in the past and the results thereof.

[1134] This will enable appropriate and efficient support to the poor.

[1135] The system that realizes this invention is composed of two main components, a server and a terminal, in order to efficiently provide funds and support to the poor.

[1136] Server Configuration

[1137] Data Collection Module

[1138] The server has multiple means for collecting data from the poor, non-governmental organizations, and governments. This data includes users' annual income, household composition, housing situation, and health status. Specifically, the server periodically sends users questionnaires and stores their responses in a database. Furthermore, the server obtains data in real time from non-governmental organizations and governments via APIs. For example, activity reports from non-governmental organizations and welfare policy data from governments are also collected.

[1139] Money Management Module

[1140] The server preprocesses the collected data, stores it in a database, and then analyzes it using machine learning algorithms. Based on this analysis, an effective support plan is generated. For example, a specific household could receive 30,000 yen per month in support and additionally allocate funds related to education. The algorithm ensures that such fund allocation is fair and effective.

[1141] User Interface

[1142] The device (such as the user's smartphone or computer) provides an interface that notifies the user of the support plan and the results of the allocation of funds. Through this interface, users can check the details of their support and provide feedback as needed. For example, the system has a function to report the status of fund use and whether additional support is needed. The interface is also intuitive, allowing users to quickly find the information they need.

[1143] Algorithm Module

[1144] The server uses machine learning algorithms to analyze the collected data and generate optimal support plans. The algorithms take into account past and current user data to predict the most effective support methods. For example, special support can be provided to families experiencing a sudden drop in income, and the effectiveness of such support can be monitored.

[1145] Specific examples

[1146] For example, the information a user must provide when registering with the system is as follows:

[1147] name

[1148] age

[1149] annual income

[1150] household composition

[1151] health status

[1152] Based on this data, the server generates a support plan as follows:

[1153] "Taro Tanaka, 45 years old, annual income 200,000 yen, household of four, healthy."

[1154] The server analyzes this information and determines that Taro Tanaka is to receive a monthly donation of 25,000 yen. This is notified through the user interface, and Taro Tanaka can not only receive the donation but also provide feedback.

[1155] Hardware and software used

[1156] Hardware: Servers, smartphones, PCs

[1157] Software: Python, Flask (web framework), SQLite (database), scikit-learn (machine learning library)

[1158] This system will enable appropriate and efficient support for the poor. By using generative AI models, effective support plans are quickly generated and the results are communicated via a user-friendly interface. This is expected to reduce uncertainty and enable concrete support to be provided promptly.

[1159] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1160] Step 1:

[1161] Data collection

[1162] The server collects data from the poor, non-governmental organizations, and governments. Specifically, it obtains information such as users' annual income, household composition, housing situation, and health status through a questionnaire form. It also obtains data in real time from non-governmental organizations and governments through APIs. The input is the user input form and data obtained through the API, and the output is preprocessed data.

[1163] Step 2:

[1164] Data preprocessing and storage

[1165] The collected data is pre-processed on the server, where incomplete data is filled in and the format is standardized. After this pre-processing, the data is stored in a database (e.g., SQLite). The input is the collected raw data, and the output is the cleaned data.

[1166] Step 3:

[1167] Training a machine learning model

[1168] The server uses the preprocessed data to train a machine learning algorithm (e.g., Linear Regression). The trained model is the basis for generating an optimal assistance plan. The input is the preprocessed data, and the output is the trained machine learning model.

[1169] Step 4:

[1170] Generate a support plan

[1171] The server uses a trained machine learning model to generate an optimal support plan based on each user's data. As a specific example, it inputs features such as income, household composition, and health status, and outputs a support amount. The input is feature data for each user (annual income, household composition, etc.), and the output is a support plan (e.g., ¥30,000 support per month).

[1172] Step 5:

[1173] Notification of support plan

[1174] The generated support plan is notified to the user via their device. The user can then check their support plan using a smartphone or computer. The input is the generated support plan, and the output is the support plan displayed on the user's device.

[1175] Step 6:

[1176] Gathering feedback

[1177] The user sends feedback on the support provided to the server through the terminal. For example, the user can report on the status of fund utilization or whether additional support is needed. The input is the user's feedback information, and the output is the collected feedback data.

[1178] Step 7:

[1179] Coordinating support plans

[1180] The server then readjusts the assistance plan based on the collected feedback, which may involve retraining the algorithm or assessing whether additional assistance is needed. The input is the collected feedback data, and the output is a new, adjusted assistance plan.

[1181] For example, if a user provides the following information to the system:

[1182] "Taro Tanaka, 45 years old, annual income 200,000 yen, household of four, healthy."

[1183] Using the generative AI model, the server decides to provide Taro Tanaka with ¥25,000 in monthly support and notifies him of this. Taro Tanaka then provides feedback on the effectiveness of the support, and the server uses this feedback to adjust the support plan.

[1184] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1185] The present invention aims to provide a system for efficiently providing funding and support to the poor, and to provide more effective support plans by combining it with an emotion engine that recognizes the user's emotions. This system mainly consists of the following components: a data collection module, a fund management module, a user interface, an algorithm module, and an emotion engine.

[1186] System Configuration

[1187] 1. Server: Data collection module

[1188] The server collects data from the poor, non-governmental organizations (NGOs), and governments. This data includes users' annual income, household composition, housing situation, health status, NGO activity reports, and government welfare policy data. The server periodically distributes questionnaire forms and stores the collected information in a database. It also obtains data in real time from NGOs and governments via APIs.

[1189] 2. Server: Funds Management Module

[1190] The server allocates funds to each user based on the collected data. First, the collected data is preprocessed and stored in a database. Then, machine learning algorithms analyze the data and generate a support plan that best suits each user's situation. For example, a specific household may receive 30,000 yen in monthly support and additional funds may be allocated to education-related programs. This allocation of funds is done fairly and effectively based on the algorithm.

[1191] 3. Terminal: User Interface

[1192] An interface is provided on the device (user's mobile device or PC) that displays the support results. Users can check the content of their support and provide feedback if necessary. For example, there is a function to report the status of fund use and whether additional support is needed. The user interface is also designed to be intuitive and easy to use, allowing users to quickly find the information they need.

[1193] 4. Server: Algorithm Module

[1194] The server uses machine learning algorithms to analyze the collected data and generate optimal support plans. The algorithms take into account past and current user data to predict the most effective support methods. For example, they could provide extra support to families who have experienced a sudden drop in income and monitor the effectiveness of the plan.

[1195] 5. Server: Emotion Engine

[1196] The server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's input data and feedback to recognize and quantify their emotional state. For example, the emotion engine evaluates stress and satisfaction levels based on the comments and evaluations written by the user, and reflects the results in the support plan. This allows for more detailed support that takes emotional aspects into account.

[1197] Specific operation of the system

[1198] 1. Data collection: The server collects data from users, NGOs, and governments and stores it in a database.

[1199] 2. Data preprocessing: The server preprocesses the collected data and converts it into a format that is easy to process with machine learning algorithms.

[1200] 3. Support plan generation: The server uses an algorithm to generate the optimal support plan.

[1201] 4. Fund allocation: The server determines the allocation of funds based on the generated support plan.

[1202] 5. Notification and feedback: The device notifies the user of the assistance provided, and the user provides feedback.

[1203] 6. Emotion analysis: The server uses an emotion engine to analyze the user's emotional state from their feedback and reflect this in the next support plan.

[1204] The system efficiently executes a series of processes, from data collection and analysis to fund allocation, emotional feedback collection, and further adjustments. This optimizes funding and support for the poor and promotes social improvement. For example, the server can use collected data to identify a user's stress level and provide additional support based on the results, thereby promoting psychological stability.

[1205] The processing flow will be explained below.

[1206] Step 1: Collect data

[1207] The server collects questionnaire forms and registration information from users. Users enter information such as annual income, family composition, housing situation, and health status into an online form.

[1208] The server receives activity reports from non-governmental organizations (NGOs) via API, automatically collecting data such as the type of support provided by the NGO, the number of people who received support, and the success of the measures.

[1209] The server retrieves policy information and assistance program data from public government databases, periodically downloading information on policy implementation status, budget allocations, target demographics, and more.

[1210] All collected data is stored in a database.

[1211] Step 2: Preprocessing the data

[1212] The server preprocesses all collected data, for example by imputing missing data and correcting outliers.

[1213] Once the data is cleansed, it is standardized and converted into a format that is easy for machine learning algorithms to process.

[1214] Step 3: Create a support plan

[1215] The server uses machine learning algorithms to generate a support plan that is optimal for each user's situation.

[1216] The algorithm uses past data and patterns to predict what type of support will be most effective.

[1217] For example, this includes specific measures such as "providing 30,000 yen in support per month" or "supporting participation in specific educational programs."

[1218] Step 4: Allocate funds

[1219] The server determines the specific allocation of funds to each user based on the generated support plan.

[1220] For example, a detailed funding allocation plan would be created, allocating additional support to families with children who earn below a certain monthly income.

[1221] Step 5: Notify and gather feedback

[1222] The device will then notify the user of the support plan and assistance details, which will then be displayed on the user's mobile device or PC.

[1223] Users can view details of their assigned assistance in the app or web portal.

[1224] Users provide feedback on how effective the support was, report on the use of funds, and whether they need additional assistance.

[1225] Step 6: Sentiment analysis with the sentiment engine

[1226] The server uses an emotion engine to analyze the user's feedback.

[1227] The emotion engine recognizes and quantifies emotions from comments and ratings written by users. For example, it can determine a user's stress or satisfaction level from the feedback text.

[1228] The analysis results of the emotion engine are stored in a database.

[1229] Step 7: Analyze feedback and adjust support plans

[1230] The server comprehensively analyzes user feedback, including the results of emotion analysis using an emotion engine, and evaluates the effectiveness of the support plan.

[1231] If necessary, update your support plan and adjust the next support offer.

[1232] For example, if a particular support is found to be ineffective, the content of the support will be changed appropriately. Also, if the user is under high stress, additional psychological support will be considered.

[1233] The system efficiently executes a series of processes, from data collection and analysis, to fund allocation, feedback collection and sentiment analysis, and further adjustment, optimizing funding and support for the poor and bringing about social improvements.

[1234] Example 2

[1235] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1236] In modern society, there is a need for effective funding and support for the poor. However, existing systems do not adequately analyze collected data or allocate funds appropriately, and they lack the ability to optimize support plans that take into account user emotions and feedback.

[1237] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for analyzing data collected from the poor, non-governmental organizations, and the government and allocating funds based on a specific method; means for storing and pre-processing the collected data; means for generating a support plan using a machine learning algorithm; means for determining the allocation of funds based on the support plan generated via a notification interface and notifying the user; and means for analyzing feedback from the user using an emotion engine, quantifying the emotional state, and adjusting the support plan. This allows a series of processes, from data collection and analysis, to fund allocation, emotional feedback collection, and further adjustment, to be carried out efficiently, enabling effective support for the poor.

[1238] "Poor" refers to individuals or families who are in financial difficulty and have difficulty accessing basic necessities and services.

[1239] "Non-governmental organizations" are non-governmental organizations that address social issues in a private capacity, often working in areas such as poverty, health, and the environment.

[1240] "Government" refers to a national or local public institution that promotes the public welfare through various policies and programs.

[1241] "Data collection" refers to the process of gathering information for a specific purpose, and includes methods such as surveys, API access, and sensors.

[1242] "Data preprocessing" refers to a series of operations that convert collected data into a format that is easier to analyze, including filling in missing values ​​and cleaning the data.

[1243] A "machine learning algorithm" refers to a computational method for learning from data and making predictions and classifications, and there are a variety of models and techniques.

[1244] A "support plan" is a plan that lays out the specific support content and methods to be provided to eligible individuals and families, and includes financial support and service provision.

[1245] A "notification interface" refers to a user interface used on mobile devices and PCs to display information and messages to users.

[1246] An "emotion engine" refers to algorithms and technologies for recognizing and analyzing a user's emotional state, quantifying emotions from user input and feedback.

[1247] "Feedback" refers to opinions and status reports provided by users, which are used to improve and adjust the system.

[1248] "Funding allocation" refers to the process of determining the amount and use of funds provided to specific individuals or households based on collected and analyzed data.

[1249] The present invention is a system for efficiently providing funds and support to the poor, and aims to provide more effective support plans by combining it with an emotion engine that recognizes the user's emotions. Detailed embodiments of this system will be described below.

[1250] System Configuration

[1251] This system mainly consists of a server, terminals, and users.

[1252] Data Collection Module

[1253] The server collects data from the poor, non-governmental organizations (NGOs), and governments. This data includes users' annual income, household composition, housing situation, health status, NGO activity reports, and government welfare policy data. The server periodically distributes questionnaire forms and stores the collected information in a database. It also obtains data in real time from NGOs and governments via APIs.

[1254] Example: Obtaining data from the government on unemployment rates and the number of people receiving welfare via an API.

[1255] Data Preprocessing Module

[1256] The server preprocesses the collected data and converts it into a format that is easy to process with machine learning algorithms. Preprocessing includes removing unnecessary data, filling in missing data, and standardizing data formats.

[1257] Example: The server imputes NULL values ​​in the data with the average value.

[1258] Algorithm Module

[1259] The server then uses a machine learning algorithm to generate an optimal support plan based on the preprocessed data. The algorithm compares past and current data to predict effective support methods.

[1260] Example: Using machine learning algorithms to generate special assistance plans for families who experience a sudden drop in income, providing them with $50,000 per month.

[1261] Money Management Module

[1262] The server determines how funds are allocated based on the generated support plan, ensuring that the allocation is fair and transparent, and that the necessary amount is distributed appropriately to each household.

[1263] Example: Based on a support plan generated by the server, a specific household is allocated 30,000 yen per month, plus an additional 10,000 yen for education-related support.

[1264] User Interface

[1265] The device (user's mobile device or PC) provides an interface that displays the support results. Through this interface, the user can check the support content and provide feedback as needed.

[1266] Example: The user's smartphone is notified of the support provided, and the user provides feedback through the application, such as "This support was helpful."

[1267] Emotion Engine

[1268] The server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's input data and feedback, recognizes and quantifies the user's emotional state, and reflects this in the next support plan.

[1269] Example: If a user comments, "I need more money for my child's education," the sentiment engine analyzes the content of the comment and reflects the addition of educational support in the next support plan.

[1270] Prompt Sentence Examples

[1271] "Please explain how you will use the collected data to generate optimal support plans for newly supported families and monitor their effectiveness."

[1272] By operating in this way, the system can effectively provide funding and support to the poor. In addition, by utilizing an emotion engine, it is possible to provide more detailed support that takes into account the user's emotions and feedback.

[1273] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1274] Step 1: Data collection

[1275] The server collects data from the poor, non-governmental organizations (NGOs), and governments. First, it periodically distributes questionnaire forms to users to collect information such as annual income, household composition, housing situation, and health status. It also obtains data from NGOs and governments in real time via APIs and stores the collected data in a database. This effectively integrates information from users, NGOs, and governments. The input is questionnaire responses and data from the API, and the output is data stored in the database.

[1276] Specific operation: The server obtains data on unemployment rates and the number of welfare recipients from the government via an API and stores it in a database.

[1277] Step 2: Data Preprocessing

[1278] The server preprocesses the collected data and converts it into a format that is easy to process with machine learning algorithms. Specifically, it deletes unnecessary data, fills in missing data, standardizes data formats, etc. The input is raw data, and the output is preprocessed data.

[1279] Specific operation: The server fills in NULL values ​​in the collected data with the average value, cleans the data, and standardizes the format.

[1280] Step 3: Create a support plan

[1281] The server uses a machine learning algorithm to generate an optimal support plan based on the preprocessed data. The algorithm compares past data with current data and predicts effective support methods. The input is the preprocessed data, and the output is the generated support plan.

[1282] How it works: Using machine learning algorithms, it generates special assistance plans for families who experience a sudden drop in income, providing them with assistance of 50,000 yen per month.

[1283] Step 4: Fund allocation

[1284] The server determines how to allocate funds based on the generated support plan. The allocation is fair and transparent, and the necessary amount is distributed appropriately to each household. The input is the generated support plan, and the output is the fund allocation result.

[1285] Specific operation: Based on the support plan, the server allocates 30,000 yen per month to each household, plus an additional 10,000 yen for education-related support.

[1286] Step 5: Notification and feedback

[1287] The device notifies the user of the assistance provided and provides an interface for the user to provide feedback. The user reports the usage status of the assistance and any additional needs through this interface. The input is the assistance provided and the user's feedback, and the output is the collected feedback.

[1288] Specific operation: The user's smartphone is notified of the support details, and the user provides feedback through the application, such as "This support was helpful."

[1289] Step 6: Sentiment analysis

[1290] The server uses an emotion engine to analyze the user's emotional state based on their feedback. The analysis results are reflected in the next support plan. The input is the user's feedback, and the output is the analyzed emotional data.

[1291] What it does: If a user comments, "I need more money for my child's education," the sentiment engine analyzes the content of the comment and reflects the addition of educational support in the next support plan.

[1292] Through this series of steps, the system can efficiently provide funding and support to the poor, with each step linking up with the others to effectively collect data, analyze it, allocate funds, collect emotional feedback, and make further adjustments.

[1293] (Application example 2)

[1294] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1295] Employee psychological fatigue and stress are serious problems that lead to decreased productivity and increased employee turnover. However, many current systems lack the ability to provide support based on emotion recognition, and do not adequately address the psychological challenges faced by employees. Therefore, a system that can properly recognize employees' emotions and provide appropriate support based on that recognition is needed.

[1296] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1297] In this invention, the server includes means for analyzing data collected from the poor, non-governmental organizations, and governments and allocating funds based on a specific methodology, means for storing and pre-processing the collected data, means for generating a support plan using a machine learning algorithm, means for determining fund allocation based on the generated support plan and notifying the user, means for collecting feedback from the user and adjusting the support plan, and means for analyzing the emotional state of employees and providing appropriate support for psychological fatigue and stress. This makes it possible to appropriately understand the emotional state of employees and provide psychological support, thereby reducing psychological fatigue and stress.

[1298] The "poor" are people who are financially disadvantaged and unable to obtain the basic necessities of life.

[1299] A "non-governmental organization" is an organization that operates independently of the government and primarily engages in activities such as solving social problems and supporting the poor.

[1300] A "government" is an institution that is responsible for running a nation, enacting and enforcing laws, and carrying out various activities related to the welfare of the people.

[1301] A "machine learning algorithm" is a method by which a computer learns from data and automatically recognizes patterns, allowing it to make predictions and classifications.

[1302] A "support plan" is a plan of assistance to be provided based on specific circumstances and needs, including allocation of funds and services.

[1303] "Emotional state" refers to the type and intensity of emotions experienced by an individual and consists of psychological states such as stress, happiness, and anxiety.

[1304] "Psychological fatigue" is a state in which mental energy is reduced and concentration and work efficiency are reduced due to long-term stress or strain.

[1305] "Stress" is a state of tension caused by mental or physical strain due to external pressures or demands.

[1306] "Feedback" refers to the evaluation or reaction of a system or individual to an action or result, and is information used for improvement or adjustment.

[1307] This invention is a system for reducing psychological fatigue and stress among employees, which analyzes data collected from the poor, non-governmental organizations, and governments, and allocates funds and support plans based on specific methods. The specific configuration and operation of the system are described below.

[1308] The server uses the following hardware and software:

[1309] Emotion recognition library: Used to analyze the user's emotional state. For example, we use a library called "EmotionRecognizer."

[1310] Machine learning algorithms are used to generate support plans, for example, using "Linear Regression" or other regression models.

[1311] Database: Stores data collected from users, non-governmental organizations, and governments.

[1312] Cloud servers: For data processing and analysis, for example, using Amazon Web Services (AWS) or Google Cloud Platform (GCP).

[1313] 1. Data Collection Module

[1314] The server collects real-time data from users, non-governmental organizations, and governments, and stores it in a database. Collected data includes employees' emotional states, stress levels, survey results, etc.

[1315] 2. Data Preprocessing

[1316] The server preprocesses the collected data, converting it into a format that is easier for machine learning algorithms to process, which includes steps such as tokenizing and quantifying the text data.

[1317] 3. Support plan generation

[1318] The server uses machine learning algorithms to generate a support plan that best suits each user's situation. For example, if an employee inputs, "I've been feeling very stressed lately," the system will suggest "psychological counseling."

[1319] 4. Allocation of funds and support

[1320] Based on the generated support plan, the server determines the allocation of funds and support and notifies the user of the details.

[1321] 5. Feedback collection and sentiment analysis

[1322] The device collects feedback from the user and sends the data to a server, which uses an emotion recognition library to analyze the user's emotional state and adjusts the support plan.

[1323] Specific examples

[1324] Example: If the input is "I've been feeling very stressed lately," the server will use "EmotionRecognizer" to recognize the emotion as "stress" and use "LinearRegression" to suggest a support plan such as "psychological counseling."

[1325] Example prompt: "An employee reports their recent emotional state in text: 'I've been feeling very stressed lately.' The system should suggest an appropriate support plan."

[1326] This system makes it possible to properly grasp the emotional state of employees and reduce psychological fatigue and stress.

[1327] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1328] Step 1:

[1329] The server collects data in real time from users, non-governmental organizations, and governments. Specifically, it collects data such as users' emotional state, stress levels, and survey results, and stores it in a database. The collected data is periodically retrieved using an API and stored in the database. The input is raw data provided by each entity, and the output is organized data stored in the database.

[1330] Step 2:

[1331] The server preprocesses the collected data. Specifically, it converts the raw data into a format that is easy for machine learning algorithms to process. This includes tokenizing and quantifying text data, filling in missing data, and normalizing the data. This generates data in a format suitable for machine learning models. The input is the raw data in the database, and the output is the preprocessed data.

[1332] Step 3:

[1333] The server uses the preprocessed data to apply a machine learning algorithm (e.g., Linear Regression) to generate a support plan that is optimal for each user's situation. For example, if an employee enters, "I've been feeling very stressed lately," the system analyzes it and suggests "psychological counseling." The input is the preprocessed data, and the output is the generated support plan.

[1334] Step 4:

[1335] The server determines the allocation of funds and support based on the generated support plan. Specifically, it plans the budget allocation and resource distribution corresponding to the support plan and stores the details in a database. The input is the generated support plan, and the output is the specific funding allocation and support details.

[1336] Step 5:

[1337] The terminal notifies the user of the details of the funds and support. The notified information includes details of the support plan and budget allocation. This allows the user to confirm their own support details and begin applying them. The input is the support plan and allocation information from the server, and the output is the notification to the user.

[1338] Step 6:

[1339] The terminal collects feedback from the user. The user can report whether the support plan is appropriate or whether additional support is needed. The collected feedback is sent to the server. The input is the user's feedback, and the output is the feedback data sent to the server.

[1340] Step 7:

[1341] The server uses an emotion recognition library (e.g., EmotionRecognizer) to analyze the user's emotional state from the feedback and adjusts the support plan based on the results. For example, if the feedback indicates that the user's stress level is still high, it provides additional support. The input is the feedback data, and the output is the adjusted support plan.

[1342] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1343] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1344] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1345] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1346] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1347] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1348] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1349] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1350] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1351] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1352] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1353] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1354] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1355] 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.

[1356] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1357] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1358] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1359] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1360] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1361] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1362] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1363] The following is further disclosed regarding the above embodiment.

[1364] (Claim 1)

[1365] A means of analysing data collected from the poor, non-governmental organisations and governments and allocating funds based on specific methodologies;

[1366] means for storing and pre-processing the collected data;

[1367] A means for generating a support plan using a machine learning algorithm;

[1368] A means for determining allocation of funds based on the generated support plan and notifying the user;

[1369] A means of gathering user feedback and adjusting assistance plans;

[1370] A system including:

[1371] (Claim 2)

[1372] 10. The system of claim 1, further comprising means for collecting activity reports from non-governmental organizations and means for evaluating the effectiveness of assistance based thereon.

[1373] (Claim 3)

[1374] 10. The system of claim 1, further comprising means for generating an optimal assistance plan from the collected data using a machine learning algorithm.

[1375] "Example 1"

[1376] (Claim 1)

[1377] A means of analysing data collected from the poor, non-governmental organisations and governments and allocating funds based on specific methodologies;

[1378] means for storing and pre-processing the collected data;

[1379] A means for generating a support plan using a machine learning algorithm;

[1380] A means for determining allocation of funds based on the generated support plan and notifying the user;

[1381] A means of collecting feedback through the user's device and adjusting the support plan;

[1382] A means of providing an intuitive and easy-to-use interface for the device;

[1383] A means for the server to periodically distribute a questionnaire form to users to collect data;

[1384] A system including:

[1385] (Claim 2)

[1386] 10. The system of claim 1, further comprising means for collecting activity reports from non-governmental organizations and means for evaluating the effectiveness of assistance based thereon.

[1387] (Claim 3)

[1388] 10. The system of claim 1, further comprising means for generating an optimal assistance plan from the collected data using a machine learning algorithm.

[1389] "Application Example 1"

[1390] (Claim 1)

[1391] A means of analysing data collected from the poor, non-governmental organisations and governments and allocating funds based on specific methodologies;

[1392] means for storing and pre-processing the collected data;

[1393] A means for generating a support plan using a machine learning algorithm;

[1394] A means for determining allocation of funds based on the generated support plan and notifying the user via an electronic terminal;

[1395] A means of gathering feedback from users and adjusting support plans;

[1396] A means for predicting the amount of support using a machine learning algorithm and calculating the optimal amount of support for each user;

[1397] A means for analyzing support plans based on the generative AI model and presenting different support plans to each user;

[1398] A means of collecting and storing user registration information in a database accessible from smartphones and other mobile devices;

[1399] a means for displaying the history of the support;

[1400] A system including:

[1401] (Claim 2)

[1402] 10. The system of claim 1, further comprising means for collecting activity reports from non-governmental organizations and means for evaluating the effectiveness of assistance based thereon.

[1403] (Claim 3)

[1404] 10. The system of claim 1, further comprising means for generating an optimal assistance plan from the collected data using a machine learning algorithm.

[1405] "Example 2: Combining Emotion Engines"

[1406] (Claim 1)

[1407] A means of analysing data collected from the poor, non-governmental organisations and governments and allocating funds based on specific methodologies;

[1408] means for storing and pre-processing the collected data;

[1409] A means for generating a support plan using a machine learning algorithm;

[1410] means for determining and notifying a user of an allocation of funds based on the support plan generated via the notification interface;

[1411] A means for analyzing user feedback using an emotion engine, quantifying the user's emotional state, and adjusting a support plan;

[1412] A system including:

[1413] (Claim 2)

[1414] 10. The system of claim 1, further comprising means for collecting activity reports from non-governmental organizations and means for evaluating the effectiveness of assistance based thereon.

[1415] (Claim 3)

[1416] 10. The system of claim 1, further comprising means for analyzing the user's emotional state based on the emotion engine and optimizing the assistance plan taking it into account.

[1417] "Application example 2 when combining emotion engines"

[1418] (Claim 1)

[1419] A means of analysing data collected from the poor, non-governmental organisations and governments and allocating funds based on specific methodologies;

[1420] means for storing and pre-processing the collected data;

[1421] A means for generating a support plan using a machine learning algorithm;

[1422] A means for determining allocation of funds based on the generated support plan and notifying the user;

[1423] A means of gathering user feedback and adjusting assistance plans;

[1424] A means of analyzing employees' emotional state and providing appropriate support for psychological fatigue and stress

[1425] A system including:

[1426] (Claim 2)

[1427] 10. The system of claim 1, further comprising means for collecting activity reports from non-governmental organizations and means for evaluating the effectiveness of assistance based thereon.

[1428] (Claim 3)

[1429] 10. The system of claim 1, further comprising means for assessing the employee's emotional state using an emotion recognition library and generating an assistance plan based thereon. [Explanation of symbols]

[1430] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of analysing data collected from the poor, non-governmental organisations and governments and allocating funds based on specific methodologies; means for storing and pre-processing the collected data; A means for generating a support plan using a machine learning algorithm; A means for determining allocation of funds based on the generated support plan and notifying the user; A means of gathering user feedback and adjusting assistance plans; A system including:

2. The system of claim 1 , further comprising means for collecting activity reports from non-governmental organizations and means for evaluating the effectiveness of support based thereon.

3. The system of claim 1 , further comprising means for generating an optimal assistance plan from the collected data using a machine learning algorithm.

Images