system

Abstract

Provide a system. A means for a user to register with the system; means for collecting basic information and survey responses from users; a means for storing the collected information in a database; A means of analyzing the stored information to identify the user's values ​​and needs; a means of generating policy proposals based on identified values ​​and needs; means for notifying and displaying the generated policy proposals to the user; a means for collecting feedback from users; The collected feedback will be analyzed and reflected in the next proposal. 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 traditional policymaking, it was difficult to propose policies that accurately reflected the values ​​and needs of each individual citizen. As a result, diverse opinions of citizens could not be fully incorporated, resulting in problems such as a decline in the effectiveness of policies and a decline in citizen satisfaction. In addition, opportunities for citizens to participate in policymaking were limited, and the realization of democracy and the promotion of citizen participation were not fully achieved. [Means for solving the problem]

[0005] The present invention solves these problems by providing a system that includes a means for users to register with the system and collect basic information and questionnaire responses, a means for storing the collected information in a database, a means for analyzing the stored information to identify the user's values ​​and needs, a means for generating policy proposals based on the identified values ​​and needs and notifying and displaying them to the user, and a means for collecting feedback from users, analyzing the collected feedback, and reflecting it in future proposals. This enables policy proposals tailored to individual citizens and promotes policy formation that reflects the diverse opinions of citizens. Furthermore, by incorporating user feedback as needed, the quality of policy proposals can be improved, making it possible to realize democracy and promote citizen participation.

[0006] "User" refers to an individual who uses the system and provides basic information and questionnaire responses.

[0007] The "system" refers to a set of programs and hardware that collects and analyzes user information, and generates and notifies policy proposals based on the results of that analysis.

[0008] "Basic information" refers to personal information such as name, address, age, and occupation that a user provides when registering with the system.

[0009] "Questionnaire response" refers to response data entered by a user in response to questions presented by the system.

[0010] The "database" is an information management system for storing basic information and questionnaire responses collected from users.

[0011] "Analysis" is the process of processing data to identify user values ​​and needs based on collected data.

[0012] "Policy proposal" refers to specific policy content presented to the user based on the analysis results.

[0013] "Notification" is an act of informing the user of the generated policy proposal.

[0014] "Display" refers to the act of visually showing the contents of a policy proposal on a user's terminal.

[0015] "Feedback" refers to the opinions and thoughts that users provide to the system about policy proposals.

[0016] "Machine learning algorithms" are data analysis models and methods used to analyze user data and identify values ​​and needs. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11]FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] This invention is a policy proposal system using AI that proposes policies based on the values ​​and needs of each user. The system includes the following main means and processes:

[0039] User Registration

[0040] First, a user accesses the system and creates an account, which allows the user to enter their basic information into the system, which is then sent to the server and stored in the database.

[0041] Polyseasonal Bayesian Data Collection

[0042] The server periodically sends users survey notifications, which include questions about social issues, taxes, welfare systems, etc. Users answer the surveys through their devices, and the responses are sent to the server and stored.

[0043] Data analysis and policy proposal generation

[0044] The server uses machine learning algorithms to analyze the collected basic information and survey responses of users. As a result of the analysis, each user's values ​​and needs are identified. Based on these results, the server generates optimal policy proposals for the user.

[0045] Notification and display of policy proposals

[0046] The generated policy proposal is sent from the server to the user's device, where it is displayed to the user and provides an interface visually displaying the details of the policy proposal. The user can then review the proposal contents through this interface.

[0047] Gathering and implementing feedback

[0048] Users provide feedback to the system, including their opinions and thoughts on policy proposals. The feedback is sent from the device to the server and analyzed. As a result, the server can reflect the user's feedback in the next policy proposal.

[0049] Specific examples

[0050] Scenario: Welfare policy proposal for the elderly

[0051] 1. An elderly user registers with the system and enters basic information (e.g., age 75, retired, living alone).

[0052] 2. Users use the device to fill out a questionnaire and answer questions about their health issues and financial situation.

[0053] 3. The server analyzes the user's basic information and questionnaire responses to determine the user's characteristics, such as "low income" or "health problems."

[0054] 4. The server generates policy proposals tailored to the user, such as medical expense subsidy systems for the elderly.

[0055] 5. The terminal displays the generated policy proposal to the user, who then checks the details.

[0056] 6. The user provides feedback on the suggestion, such as "very helpful."

[0057] 7. The server collects feedback, updates the AI ​​model with the latest information, and provides a policy proposal report to government officials.

[0058] In this way, the system aims to realize democracy and promote citizen participation by making policy proposals that reflect the diverse opinions of citizens by making policy proposals that meet the needs of each individual user.The system also aims to continuously improve the quality of policy proposals through a feedback function.

[0059] The processing flow will be explained below.

[0060] Step 1: User registers with the system

[0061] 1. A user visits a web page or app and selects "Create a new account."

[0062] 2. The device displays a registration form to the user, asking them to enter basic information such as their name, address, age, occupation, and email address.

[0063] 3. The user enters the required information and clicks "Submit."

[0064] 4. The terminal sends the entered data to the server.

[0065] 5. The server stores the received basic information in a database.

[0066] Step 2: Send out the survey and collect responses

[0067] 1. The server periodically generates and prepares to send surveys to registered users.

[0068] 2. The device displays a notification to the user saying "There is a new survey."

[0069] 3. The user clicks on the notification and opens the survey page.

[0070] 4. The terminal displays the survey form and the user answers the questions.

[0071] 5. The user answers the questions and clicks "Submit."

[0072] 6. The device sends the user's response data to the server.

[0073] 7. The server stores the received response data in a database.

[0074] Step 3: Data analysis

[0075] 1. The server reads the user's basic information and survey responses from the database.

[0076] 2. The server applies machine learning algorithms to analyze each user's values ​​and needs.

[0077] 3. The server updates each user's profile based on the analysis results.

[0078] Step 4: Generate policy proposals

[0079] 1. The server begins generating policy proposals based on the user's profile.

[0080] 2. The policy proposals generated by the server include specific policy explanations, expected effects, advantages and disadvantages, etc.

[0081] 3. The server stores the generated policy proposals for each user.

[0082] Step 5: Notification and display of policy proposals

[0083] 1. The server prepares to send the stored policy proposal to the corresponding user.

[0084] 2. The device displays a notification to the user saying, "New policy proposals available."

[0085] 3. The user clicks on the notification to view the details of the policy proposal.

[0086] 4. The device displays details of the policy proposal to the user, providing a convenient UI.

[0087] Step 6: Gather feedback

[0088] 1. Users view the policy proposal and enter their opinions and thoughts in the feedback section.

[0089] 2. The user submits feedback.

[0090] 3. The device sends the feedback data to the server.

[0091] 4. The server stores the received feedback data in a database.

[0092] Step 7: Analyze and incorporate feedback

[0093] 1. The server analyzes the feedback data and updates the AI ​​model.

[0094] 2. The server stores the analysis results so that the user's feedback can be reflected in the next policy proposal.

[0095] 3. The server generates a report that provides the user feedback results to government officials.

[0096] Example 1

[0097] 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."

[0098] The current policy proposal system has difficulty in fully reflecting the values ​​and needs of each citizen, resulting in problems with proposed policies that do not adequately address individual citizens. Another issue is that collected feedback is not adequately reflected in subsequent proposals, resulting in a lack of improvement in the quality of policy proposals. Furthermore, there is also the problem that generated policy proposals are not effectively provided to government agencies.

[0099] 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.

[0100] In this invention, the server includes a means for users to register with the system, a means for collecting basic information and questionnaire responses from users, a means for storing the collected information in a database, a means for analyzing the stored information using a machine learning algorithm to identify users' values ​​and needs, a means for generating policy proposals based on the identified values ​​and needs, a means for notifying and displaying the generated policy proposals to users, a means for collecting feedback from users, a means for analyzing the collected feedback and updating the generative AI model to reflect the feedback in the next proposal, and a means for providing the generated policy proposals to government agencies. This enables highly accurate policy proposals that are in line with individual users' values ​​and needs, and the quality of policy proposals is improved by continuously incorporating feedback. Furthermore, by effectively providing the generated policy proposals to government agencies, they can contribute to actual policy formation.

[0101] "Means for Users to Register with the System" refers to the process and interface through which a User can access the System and enter the required basic information to create an account.

[0102] "Means for collecting basic information and questionnaire responses from users" refers to the process or mechanism for presenting questions to users and collecting their responses along with their attribute information.

[0103] "Means for storing collected information in a database" refers to a database management system and related operations for persistently storing basic information and survey responses obtained from users.

[0104] "Means of analyzing stored information using machine learning algorithms to identify users' values ​​and needs" refers to machine learning technology and its execution environment for analyzing collected data and clarifying individual users' characteristics and requirements.

[0105] "Means for generating policy proposals based on identified values ​​and needs" refers to processes or algorithms that formulate optimal policies for users based on the results of analysis and automatically generate proposals.

[0106] "Means for notifying and displaying the generated policy proposal to the user" refers to a notification system and display interface for notifying the user's terminal of the generated policy proposal and allowing the user to visually confirm it.

[0107] "Means for collecting feedback from users" refers to the process or interface through which users can input their opinions and thoughts about policy proposals and receive them into the system.

[0108] "Means for analyzing collected feedback and updating the generative AI model to reflect it in the next proposal" refers to the process and techniques for analyzing feedback provided by users and retraining the machine learning model as needed to improve the accuracy of the next policy proposal.

[0109] "Means for providing generated policy proposals to government agencies" refers to the processes and mechanisms for officially transmitting policy proposals created by the system to government agencies and utilizing them in the policy-making process.

[0110] This invention is a system for making policy proposals based on users' values ​​and needs. The system consists of the following processes: user registration, data collection, data analysis, policy proposal generation, notification, and feedback collection. A specific embodiment of this system is described below.

[0111] User Registration

[0112] First, the user accesses the system via the Internet and uses a web browser to access the registration screen. The registration screen displays a form for entering basic information (name, age, occupation, area of ​​residence, etc.). When the user enters the information and presses the "Submit" button, the information is sent to the server and stored in a database. This database uses a common database management system such as MySQL (registered trademark) or PostgreSQL.

[0113] Polyseasonal Bayesian Data Collection

[0114] The server automatically generates survey notification emails to users at regular intervals. These notifications include questions about social issues, taxes, welfare systems, etc. The notification emails are sent via an SMTP server. When a user clicks on the link in the email and accesses the survey page, the page is displayed on the device. When the user answers the survey and presses the "Submit" button, the answers are sent to the server and stored in a database.

[0115] Data analysis and policy proposal generation

[0116] The server inputs the collected basic information and survey responses into a machine learning algorithm. The analysis is performed using Python and machine learning libraries such as TENSORFLOW (registered trademark) and Scikit-learn. This allows the user's values ​​and needs to be identified using clustering and regression analysis techniques. The Python script then generates optimal policy proposals based on the analysis results and stores them in a database.

[0117] Notification and display of policy proposals

[0118] The generated policy proposal is then sent back to the user's device from the server. The notification email includes a link to view the details of the proposal. The user can click the link to access the policy proposal details page and view the details. This page provides an interface that visually displays the proposal contents.

[0119] Gathering and implementing feedback

[0120] Users provide feedback on policy proposals, including their opinions and thoughts. Feedback is sent via an input form on the details page. The feedback sent from the device is received by the server and stored in a database. The server then analyzes the feedback. This analysis uses text analysis techniques. The machine learning model is retrained based on the analysis results, improving the accuracy of the next policy proposal.

[0121] The generated policy proposals are automatically provided to government agencies, with the hope that they will be utilized in actual policy formation.

[0122] Specific examples

[0123] Scenario: Welfare policy proposal for the elderly

[0124] 1. An elderly user registers in the system and enters basic information (e.g., age 75, retired, living alone).

[0125] 2. Users fill out a survey and provide information about their health issues and financial situation.

[0126] 3. The server analyzes this information and identifies characteristics of the user, such as whether they have a low income or health problems.

[0127] 4. The server generates policy proposals tailored to the user, such as medical expense subsidy systems for the elderly.

[0128] 5. The user reviews the policy proposals generated on the device and provides feedback such as "very helpful."

[0129] 6. The server collects feedback, updates the AI ​​model, and provides a policy proposal report to government agencies.

[0130] Prompt Sentence Examples

[0131] "Generate policy proposals for a medical expense subsidy system for the elderly based on basic information and survey responses."

[0132] In this way, the system can provide policy proposals tailored to the individual needs of each user, and through feedback functions, the quality of the policy proposals can be continuously improved.

[0133] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0134] Step 1: User Registration

[0135] A user accesses the system's URL using a web browser. The user enters basic information (such as name, age, occupation, and area of ​​residence) on the registration screen. The entered basic information is sent from the terminal to the server when the user presses the "Submit" button. The server receives the sent basic information and saves it in a database. This stores the user's basic information in the database and makes it available for future processing.

[0136] Input: Basic information entered by the user

[0137] Data calculation: Send input data to the server and save it in the database

[0138] Output: Basic user information stored in the database

[0139] Step 2: Polyseasonal Bayesian data collection

[0140] The server periodically generates and sends survey notification emails to users. These emails contain a URL for a survey containing questions about social issues, taxes, welfare systems, etc. When a user clicks on the link in the email, they access the survey page. The user answers the survey using their device and presses the "Submit" button, which sends the answers from the device to the server. The server receives the answers and stores them in a database.

[0141] Input: Server-generated survey notification email

[0142] Data calculation: Sending user answers to the server and storing them in a database

[0143] Output: Survey responses stored in a database

[0144] Step 3: Data analysis and policy proposal generation

[0145] The server runs a machine learning algorithm to analyze the collected basic information and survey responses. The analysis is performed using Python and libraries such as TensorFlow and Scikit-learn. The server reads the user's basic information and survey responses from the database and inputs them into a machine learning model. The algorithm performs clustering and regression analysis to identify the user's values ​​and needs. Based on the analysis results, optimal policy proposals are generated. These proposals are then saved back to the database.

[0146] Input: User basic information and survey responses stored in the database

[0147] Data Computing: Analyzing data and generating policy recommendations using machine learning algorithms

[0148] Output: Generated policy proposals

[0149] Step 4: Notification and presentation of policy proposals

[0150] The generated policy proposal is notified to the user's device by the server. The server generates a policy proposal notification email and sends it to the user. The notification email contains a link to view the details of the proposal. When the user clicks the link, they can access the policy proposal details page. The device displays this page, allowing the user to visually confirm the proposal contents.

[0151] Input: Generated policy proposals

[0152] Data calculation: Generate and send policy proposal notification emails

[0153] Output: Policy proposal details page displayed on the user's device

[0154] Step 5: Gather and incorporate feedback

[0155] Users provide their opinions and thoughts on policy proposals as feedback through an input form on the details page. When the user presses the "Submit" button, the feedback is sent from the device to the server. The server then stores the received feedback in a database. The server then analyzes it and uses text analysis techniques to analyze the feedback content. Based on the analysis results, the machine learning model is retrained. This improves the accuracy of the next policy proposal.

[0156] Input: User feedback

[0157] Data calculation: storing and analyzing feedback in a database

[0158] Output: Improved policy proposals for the next round

[0159] Step 6: Submitting policy proposals to government agencies

[0160] Finally, the generated policy proposals are provided to government agencies. The server generates a policy proposal report and automatically sends it to the appropriate government agency. This report contains detailed policy proposals based on the analysis results, which will help the policy proposals to be used in actual policy formation.

[0161] Input: Generated policy proposals

[0162] Data Computing: Generate and send policy proposal reports

[0163] Output: Policy proposals provided to government agencies

[0164] (Application example 1)

[0165] 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."

[0166] Current policy proposal systems are designed for general users and are unable to fully reflect the specific needs of elderly people and users with physical limitations. Furthermore, they lack the functionality to provide appropriate assistance services in real time, especially for users using autonomous vehicles. This has led to problems such as delays and inappropriate recommendations and guidance for welfare support and medical services needed by elderly people and users with physical limitations.

[0167] 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.

[0168] In this invention, the server includes means for users to register with the system, means for collecting basic information and questionnaire responses from users, means for saving the collected information in a database, means for analyzing the saved information and identifying the user's values ​​and needs, means for generating policy proposals based on the identified values ​​and needs, means for notifying and displaying the generated policy proposals to the user, means for collecting feedback from the user, means for analyzing the collected feedback and reflecting it in the next proposal, and means for analyzing usage information and health status data collected by the autonomous mobile device and proposing optimal welfare support services to the user while riding. This makes it possible to provide appropriate welfare support services in real time to elderly and physically limited users, and to create an environment in which users can use the autonomous mobile device with peace of mind.

[0169] An "autonomous vehicle" is a means of transportation that uses artificial intelligence and sensor technology to operate automatically and travel to a destination without human intervention.

[0170] "Usage information" is data generated when a user uses an autonomous driving device, and includes information such as travel route, boarding and disembarking times, and riding frequency.

[0171] "Health condition data" refers to information relating to the user's health, and includes biometric data such as blood pressure, heart rate, and body temperature, as well as health status evaluation results based on questionnaire results and the like.

[0172] "Welfare support services" are support measures and services provided to users with specific needs, such as the elderly and people with disabilities, and include medical assistance, transportation assistance, and lifestyle support.

[0173] "Analysis" is the process of applying machine learning algorithms and statistical methods to analyze information based on collected data to identify specific values ​​and needs.

[0174] "Policy proposals" are proposals that present optimal policies and support measures to users based on the analysis results, and include information on specific measures and services.

[0175] "Feedback" refers to information such as opinions, impressions, and evaluations provided by users, and is useful for improving the system and increasing the accuracy of future policy proposals.

[0176] This invention applies an AI-based policy proposal system to an autonomous driving device to provide optimal welfare support services in real time to elderly people and users with physical limitations. The system includes the following main components:

[0177] 1. User Registration

[0178] The server provides a means for users to register with the system through the terminal of the autonomous driving device. The user can then enter their basic information and register with the system. The user's basic information includes age, gender, health condition, etc.

[0179] 2. Data Collection

[0180] The server uses the terminal to collect basic information and questionnaire responses from users, including usage information, health status data, and questionnaires about their living conditions. The data is collected periodically, sent to the server, and stored in a database.

[0181] 3. Data analysis and policy proposal generation

[0182] The server analyzes the collected data using machine learning algorithms. Specifically, it uses platforms such as NVIDIA Jetson to identify the user's values ​​and needs. Based on these values ​​and needs, it generates optimal welfare support services and policies.

[0183] 4. Notification and Display of Policy Proposals

[0184] The server notifies the autonomous driving device of the generated policy proposals. The device then displays the proposals visually and audibly to the user through a display and audio guide. It is also possible to link with smart glasses or a head-mounted display to display the proposals in real time.

[0185] 5. Gather and incorporate feedback

[0186] The server collects the feedback provided by users and incorporates this information into the next policy proposal, allowing for continuous improvement of the quality of the proposal.

[0187] Examples:

[0188] Elderly person A (75 years old) rides an autonomous driving device and answers a questionnaire about his / her health condition and lifestyle through a linked application. The server analyzes the collected data in real time and suggests "priority access to medical institutions" and "low-cost transportation support plans." This allows Elderly Person A to receive appropriate support services based on his / her health condition.

[0189] Example prompt sentence:

[0190] "Data analysis prompt to propose a medical assistance system for elderly users: Generate appropriate policy proposals based on information such as age, living situation, health status, and facilities (medical institutions, public services) that users frequently access. Example: 75 years old, living alone, with chronic illnesses, and needing to visit hospitals frequently."

[0191] This system enables elderly people and people with physical limitations who use autonomous vehicles to receive optimal welfare support services in real time. The generated policy proposals are also customized to the needs of each user, providing optimal support for each user.

[0192] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0193] Step 1:

[0194] The server provides a means for users to register with the system. Users enter basic information such as age, gender, and health status through the terminal of the autonomous driving device. The server stores this basic information in a database.

[0195] Input: User's basic information (age, gender, health status, etc.)

[0196] Output: Basic information stored in the database

[0197] Specific operation: The user enters information into the registration screen displayed on the terminal and sends it to the server, which then stores the received information in a database.

[0198] Step 2:

[0199] The server periodically sends questionnaires to users to collect usage information and health status data. Users respond to the questionnaires and send the data from their terminals to the server.

[0200] Input: Survey responses, usage information (route, boarding and disembarking times, etc.), health status data (blood pressure, heart rate, etc.)

[0201] Output: Survey responses, usage information, and health status data stored in a database

[0202] Specific operation: A questionnaire is presented to the user via the device's display or audio guide. The user answers the questionnaire and sends the data to the server.

[0203] Step 3:

[0204] The server analyzes the collected data using machine learning algorithms (e.g., NVIDIA Jetson), processes the data, and identifies the user's values ​​and needs.

[0205] Input: Basic information, survey responses, usage information, health status data

[0206] Output: User values ​​and needs

[0207] How it works: The server retrieves the collected data from the database, inputs it into a machine learning algorithm, and analyzes it. From the analysis results, the user's specific values ​​and needs are extracted.

[0208] Step 4:

[0209] The server generates optimal welfare support services and policy proposals based on the analysis results.

[0210] Input: User values ​​and needs

[0211] Output: Generated policy proposals

[0212] Specific operation: Based on the analysis results, the server uses a specific algorithm to generate optimal policy proposals for the user.

[0213] Step 5:

[0214] The server notifies the device of the generated policy proposals and displays them to the user. The device then provides the proposals to the user using a display or audio guide. The device also works with smart glasses or a head-mounted display to display the proposals in real time.

[0215] Input: Generated policy proposals

[0216] Output: Policy proposals displayed to the user

[0217] Specific operation: Policy proposals are displayed on the device screen and explained via audio guidance. When using smart glasses or a head-mounted display, the proposals are displayed in real time.

[0218] Step 6:

[0219] Users provide feedback on the presented policy proposals through their terminals, and the server collects the feedback and stores it in a database.

[0220] Input: User feedback

[0221] Output: Feedback stored in a database

[0222] Specific operation: The user can easily input feedback through the terminal interface, and the server receives the feedback and stores it in a database.

[0223] Step 7:

[0224] The server analyzes the collected feedback and reflects it in the next policy proposal.

[0225] Input: Feedback stored in the database

[0226] Output: Improved policy recommendations

[0227] Specific operation: The server analyzes the feedback and updates the machine learning model based on the results. The analysis results are reflected in the next policy proposal to make it more accurate.

[0228] 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.

[0229] This invention is a policy proposal system that uses AI and an emotion engine to propose policies that take into account the emotional state as well as the values ​​and needs of each individual user. The system includes the following main means and processes:

[0230] User Registration

[0231] First, a user accesses the system and creates an account, which allows the user to enter their basic information into the system, which is then sent to the server and stored in the database.

[0232] Polyseasonal Bayesian Data Collection

[0233] The server periodically sends users survey notifications, which include questions about social issues, taxes, welfare systems, etc. Users answer the surveys through their devices, and the responses are sent to the server and stored.

[0234] Data analysis and emotion recognition

[0235] The server uses machine learning algorithms and an emotion engine to analyze the collected user information and survey responses. As a result of the analysis, each user's values ​​and needs are identified. At the same time, the emotion engine evaluates the user's emotional state based on their feedback and interactions.

[0236] Generate policy proposals

[0237] The server generates policy proposals based on the user's values, needs, and assessed emotional state, ensuring that the proposed policies are in line with the user's actual emotions.

[0238] Notification and display of policy proposals

[0239] The generated policy proposal is sent from the server to the user's device, where it is displayed to the user as a notification and provides an interface with detailed visual information. The interface's display method is also adjusted according to the user's emotional state.

[0240] Gathering and implementing feedback

[0241] Users provide their opinions and thoughts on policy proposals as feedback to the system. The feedback is sent from the device to the server and analyzed. As a result, the server can reflect the user's feedback and emotional state in the next policy proposal.

[0242] Specific examples

[0243] Scenario: Welfare policy proposal for the elderly

[0244] 1. An elderly user registers with the system and enters basic information (e.g., age 75, retired, living alone).

[0245] 2. Users use the device to fill out a questionnaire and answer questions about their health issues and financial situation.

[0246] 3. The server analyzes the user's basic information and questionnaire responses to determine the user's characteristics, such as "low income" or "health problems."

[0247] 4. The emotion engine evaluates the emotional state from the user's feedback and interactions and sends it to the server.

[0248] 5. The server generates policy proposals tailored to the user, such as medical subsidy programs for the elderly, and adjusts the proposals to take into account the user's emotional state.

[0249] 6. The terminal displays the generated policy proposal to the user, who can then check the details. Based on the emotion engine, the display method is optimized to the user's emotional state.

[0250] 7. The user provides feedback on the suggestion, such as "very helpful."

[0251] 8. The server collects feedback, updates the AI ​​model and emotion engine with the latest information, and provides a policy proposal report to government officials.

[0252] This system will propose policies that take into account the needs and emotional state of each user, enabling policy formation that reflects the diverse opinions and emotions of citizens. Furthermore, through a feedback function, the quality of policy proposals can be continuously improved, promoting the realization of democracy and citizen participation.

[0253] The processing flow will be explained below.

[0254] Step 1: User registers with the system

[0255] 1. A user visits a web page or app and selects "Create a new account."

[0256] 2. The device displays a registration form to the user, asking them to enter basic information such as their name, address, age, occupation, and email address.

[0257] 3. The user enters the required information and clicks "Submit."

[0258] 4. The terminal sends the entered data to the server.

[0259] 5. The server stores the received basic information in a database.

[0260] Step 2: Send out the survey and collect responses

[0261] 1. The server periodically generates and prepares to send surveys to registered users.

[0262] 2. The device displays a notification to the user saying "There is a new survey."

[0263] 3. The user clicks on the notification and opens the survey page.

[0264] 4. The terminal displays the survey form and the user answers the questions.

[0265] 5. The user answers the questions and clicks "Submit."

[0266] 6. The device sends the user's response data to the server.

[0267] 7. The server stores the received response data in a database.

[0268] Step 3: Data analysis and emotion recognition

[0269] 1. The server reads the user's basic information and survey responses from the database.

[0270] 2. The server applies machine learning algorithms to analyze each user's values ​​and needs.

[0271] 3. The server updates each user's profile based on the analysis results.

[0272] 4. The server uses an emotion engine to evaluate the emotional state from the user's feedback and interactions.

[0273] 5. The server adds the emotional state assessment to the profile.

[0274] Step 4: Generate policy proposals

[0275] 1. The server starts generating policy suggestions based on the user's profile and emotional state.

[0276] 2. The policy proposals generated by the server include specific policy explanations, expected effects, advantages and disadvantages, etc.

[0277] 3. The server stores the generated policy proposals for each user.

[0278] Step 5: Notification and display of policy proposals

[0279] 1. The server prepares to send the stored policy proposal to the corresponding user.

[0280] 2. The device displays a notification to the user saying, "New policy proposals available."

[0281] 3. The user clicks on the notification to view the details of the policy proposal.

[0282] 4. The device displays details of policy proposals to the user and provides a convenient UI that adapts to their emotional state.

[0283] Step 6: Gather feedback

[0284] 1. Users view the policy proposal and enter their opinions and thoughts in the feedback section.

[0285] 2. The user submits feedback.

[0286] 3. The device sends the feedback data to the server.

[0287] 4. The server stores the received feedback data in a database.

[0288] 5. The server uses the emotion engine to analyze the feedback content.

[0289] Step 7: Analyze and incorporate feedback

[0290] 1. The server analyzes the feedback data and updates the AI ​​model and emotion engine.

[0291] 2. The server stores the analysis results so that the next policy proposal will reflect the user's feedback and emotional state.

[0292] 3. The server generates a report that provides the user feedback results to government officials.

[0293] Examples:

[0294] Scenario: Welfare policy proposal for the elderly

[0295] 1. An elderly user registers with the system and enters basic information (e.g., age 75, retired, living alone).

[0296] 2. The user uses the device to answer a questionnaire and enter their opinions about health issues and financial situations.

[0297] 3. The server stores the user's basic information and survey response data in a database.

[0298] 4. The server uses machine learning algorithms and an emotion engine to analyze the user's values, needs, and emotional state.

[0299] 5. Based on the analysis results, the server generates proposals for medical subsidy programs for the elderly, adjusting the content of the proposals to take into account the emotional state.

[0300] 6. The device notifies the user of the generated policy proposal and visually displays the details. Based on the emotion engine, the display method is optimized to the user's emotional state.

[0301] 7. The user reviews the suggestion and provides feedback that it is "very helpful."

[0302] 8. The server collects feedback and updates the AI ​​model and emotion engine with the latest information.

[0303] 9. The server provides policy proposal reports to government officials to help them formulate policies.

[0304] In this way, policy proposals that take into account the user's emotional state can be more personalized, reflecting the diverse opinions and emotions of citizens, and continuously improving the quality of policy proposals through feedback and sentiment analysis.

[0305] Example 2

[0306] 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."

[0307] Conventional policy proposal systems make proposals based only on the user's basic information and questionnaire responses, which means they are inadequately able to adapt to fluctuations in an individual user's emotional state and feedback. As a result, it is difficult to generate policy proposals that are appropriate for the user's actual interests and emotional state. Furthermore, there is a lack of a method to maintain consistency by incorporating feedback into the next proposal.

[0308] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0309] In this invention, the server includes means for users to register with the system, means for collecting basic information and questionnaire responses from users, means for storing the collected information in a database, means for analyzing the stored information using a machine learning algorithm to identify the user's values ​​and needs, means for evaluating the user's emotional state using an emotion recognition engine, means for generating policy proposals using a generative AI model based on the identified values ​​and needs and the evaluated emotional state, means for notifying and displaying the generated policy proposals to the user, and means for collecting feedback from the user and reflecting the feedback in the next policy proposal, thereby enabling personalized policy proposals based on the user's values ​​and emotional state.

[0310] "User" refers to an individual person who uses the system.

[0311] "System" refers to an environment that includes a set of software and hardware for communicating information between users and a server and generating policy proposals.

[0312] "Basic information" refers to personal information such as the user's name, age, gender, and address.

[0313] "Survey responses" refer to responses to questions asked by users regarding social issues, taxes, welfare systems, etc.

[0314] "Database" refers to a system that organizes and stores collected data such as basic user information and questionnaire responses.

[0315] "Machine learning algorithms" refer to techniques that analyze large amounts of data for patterns and trends, and specifically include technologies such as TensorFlow.

[0316] "Emotion recognition engine" refers to a system that assesses a user's emotional state from their feedback and interactions. Examples include the IBM Watson® Tone Analyzer.

[0317] "Generative AI model" refers to an artificial intelligence algorithm that generates text or suggestions based on collected and analyzed data, including, for example, GPT-4 (registered trademark).

[0318] "Policy proposals" refer to specific policy proposals generated based on the user's basic information, survey responses, and emotional state.

[0319] "Notification" refers to the system's ability to notify users of new information or offers.

[0320] "Display" refers to the user being able to visually confirm the details of information and suggestions through the system.

[0321] "Feedback" refers to the user providing the system with their opinions and thoughts about the proposal.

[0322] This invention is a policy proposal system that uses AI and an emotion engine to propose policies that take into account the emotional state of each user, along with their values ​​and needs. Specific means for implementing this system and its operation are described below.

[0323] User Registration

[0324] First, a user accesses the system using a web browser or smartphone app and creates a new account. The user enters basic information such as name, age, gender, and address. The basic information entered from the device is sent to the server using the HTTPS protocol. The server then stores the received basic information in a database (e.g., MongoDB, MySQL).

[0325] Polyseasonal Bayesian Data Collection

[0326] Next, the server uses a scheduling service (e.g., Cron job) to periodically send survey notifications to users. The surveys include questions about social issues, taxes, welfare systems, etc. Users answer the surveys using their devices, and the responses are sent from the devices to the server. The server then stores the survey response data in a database.

[0327] Data analysis and emotion recognition

[0328] The server uses a machine learning algorithm (e.g., TensorFlow) to analyze the user's basic information and survey responses. As a result of the analysis, each user's values ​​and needs are identified. At the same time, the server uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to evaluate the user's emotional state from their feedback and interactions. The analysis results are stored in a database as the user's individual profile.

[0329] Generate policy proposals

[0330] The server then uses a generative AI model (e.g., GPT-4) to generate policy proposals based on the analysis results and the user's emotional state. These proposals are tailored to the user's values ​​and needs, and are adjusted according to the user's emotional state.

[0331] Notification and display of policy proposals

[0332] The generated policy proposals are sent from the server to the user's device. The device notifies the user of the received policy proposals and displays details. The display method of the device's interface is also adjusted based on the user's emotional state. For example, if the emotional state is determined to be "stressed," the interface color scheme and font style are changed to something more relaxing.

[0333] Gathering and implementing feedback

[0334] Finally, the user provides feedback to the system, including their opinions and thoughts on the policy proposals. This feedback is sent from the device to the server, where it is analyzed and reflected in the next policy proposal. This allows the system to continually make proposals that incorporate the user's latest needs and emotional state.

[0335] Specific examples

[0336] Scenario: Welfare policy proposal for the elderly

[0337] 1. An elderly user registers in the system and enters basic information (e.g., age 75, retired, living alone).

[0338] 2. Users use the device to fill out a questionnaire and answer questions about their health issues and financial situation.

[0339] 3. The server analyzes the user's basic information and questionnaire responses to determine the user's characteristics, such as "low income" or "health problems."

[0340] 4. The emotion engine evaluates the emotional state from the user's feedback and interactions and sends it to the server.

[0341] 5. The server generates tailored policy proposals for the user, such as medical subsidy programs for the elderly, and the proposals are adjusted based on the user's emotional state.

[0342] 6. The terminal displays the generated policy proposal to the user, who can then check the details. Based on the emotion engine, the display method is optimized to the user's emotional state.

[0343] 7. The user provides feedback on the suggestion, such as "very helpful."

[0344] 8. The server collects feedback and updates the AI ​​model and emotion engine with the latest information.

[0345] Prompt Sentence Examples

[0346] "Please propose a welfare policy suitable for seniors who have retired at age 75. Consider the following conditions: low income, health problems."

[0347] "Use AI and emotion engines to generate policy recommendations that take into account the user's values ​​and emotional state."

[0348] This system realizes personalized policy proposals that take into account the needs and emotional state of each user, enabling policy formation that reflects the diverse opinions and emotions of citizens. Furthermore, through a feedback function, the quality of policy proposals can be continuously improved, promoting the realization of democracy and citizen participation.

[0349] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0350] Step 1: User Registration

[0351] Users access the system using a web browser or smartphone app and create a new account.

[0352] Input: User's basic information (name, age, gender, address, etc.)

[0353] Output: Basic user information stored in the database

[0354] How it works: A user fills out a form with basic information and clicks the submit button. The device sends the information to the server via HTTPS. The server validates the received information and stores it in a database.

[0355] Step 2: Polyseasonal Bayesian data collection

[0356] The server periodically sends survey notifications to users.

[0357] Input: Survey data, user basic information

[0358] Output: Survey responses stored in a database

[0359] How it works: The server uses a scheduling service to send a survey notification to the user's device at a specific time. The user receives the notification and opens the survey screen. They answer the survey, and the device sends the response data to the server. The server stores the received response data in a database.

[0360] Step 3: Data analysis and emotion recognition

[0361] The server uses machine learning algorithms to analyze the user's basic information and questionnaire responses, and uses an emotion engine to evaluate their emotional state.

[0362] Input: User basic information, survey responses, feedback

[0363] Output: Analyzed user values, needs and emotional state

[0364] How it works: The server uses TensorFlow to analyze user data. As a result of the analysis, each user's values ​​and needs are identified. At the same time, an emotion recognition engine (e.g., emotion analysis API) evaluates the user's emotional state based on their feedback and interaction data. The evaluation results are saved as a personalized profile for the user.

[0365] Step 4: Generate policy proposals

[0366] The server generates policy proposals using a generative AI model based on the analysis results and emotional state.

[0367] Input: Analyzed user values, needs, and emotional state

[0368] Output: Generated policy proposals

[0369] How it works: The server takes the analysis results and the user's emotional state as input and uses a generative AI model (e.g., GPT-4) to generate policy proposals. The proposals include specific policy content and are adjusted according to the user's emotional state.

[0370] Step 5: Notification and presentation of policy proposals

[0371] The server sends the generated policy proposal to the user's terminal, which notifies the user of the policy proposal and displays the details.

[0372] Input: Generated policy proposals

[0373] Output: Policy proposals communicated and displayed to the user

[0374] How it works: The server converts the generated policy proposal into JSON format and sends it to the user's device. The device then notifies the user of the new policy proposal via push notifications or in-app notifications. The proposal details are displayed on a details screen, and the interface color scheme and font style are adjusted according to the user's emotional state.

[0375] Step 6: Gather and incorporate feedback

[0376] Users provide feedback on policy proposals, including their opinions and thoughts. The server collects the feedback and reflects it in the next policy proposal.

[0377] Input: User feedback

[0378] Output: Updated user profile, feedback to be reflected in next proposal

[0379] How it works: A user enters their opinions and thoughts into the feedback form on the policy proposal details screen and clicks the submit button. The device sends the feedback to the server. The server analyzes the received feedback and updates the user profile. This updated information is taken into account the next time a policy proposal is generated.

[0380] Through these steps, the system realizes personalized policy proposals based on the user's values ​​and emotional state.

[0381] (Application example 2)

[0382] 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."

[0383] Existing policy and content proposal systems can analyze users' values ​​and needs, but they struggle to make proposals that take into account the user's emotional state. This can lead to lower acceptability and satisfaction. Furthermore, there is a lack of effective ways to incorporate user feedback into future proposals, making it difficult to improve the quality of proposals.

[0384] 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.

[0385] In this invention, the server includes: a means for users to register with the system; a means for collecting basic information and questionnaire responses from users; a means for storing the collected information in a database; a means for analyzing the stored information to identify the user's values ​​and needs; a means for generating policy or content proposals based on the identified values ​​and needs and the evaluated emotional state; a means for notifying and displaying the generated policy or content proposals to the user; a means for adjusting the display method based on the user's feedback and emotional state; a means for collecting user feedback; and a means for analyzing the collected feedback and emotional state data and reflecting it in subsequent proposals. This enables policy and content proposals to be tailored to the user's emotional state, thereby improving the acceptability and satisfaction of the proposals. Furthermore, effectively reflecting feedback in subsequent proposals also improves the quality of the proposals.

[0386] A "user" is an individual or group that uses the system and provides data such as basic information and questionnaire responses.

[0387] The "system" is a set of mechanisms for generating, notifying, and displaying policy or content suggestions based on the user's values, needs, and emotional state, and for collecting feedback to be reflected in future suggestions.

[0388] "Policy proposals" are the contents of plans and measures provided by governments and public institutions that are generated based on the user's values, needs, and emotional state.

[0389] "Content suggestions" are entertainment and informational content such as movies, music, and news articles that are generated based on the user's values, needs, and emotional state.

[0390] "Emotional state" refers to the psychological state or feeling that is assessed through user feedback and interaction.

[0391] A "database" is an information collection that allows the system to store and manage collected basic information, questionnaire responses, feedback, etc. from users.

[0392] "Feedback" refers to opinions and thoughts provided by users regarding policy proposals or content proposals, and is data that will be reflected in the next proposal.

[0393] "Machine learning algorithms" refer to mathematical methods and techniques for analyzing large amounts of data and finding patterns and trends.

[0394] An "emotion recognition engine" refers to software or hardware that analyzes and evaluates a user's emotional state from text, speech, or other input.

[0395] "Interface" refers to the screen or operating system through which a user views and provides feedback on a policy or content proposal.

[0396] This invention is a system that uses AI and an emotion engine to make policy and content proposals that take into account the user's values, needs, and emotional state. Specific embodiments for implementing this invention are described below.

[0397] First, users access the system and create an account. They enter the necessary basic information, which is then sent to the server and stored in a database. They also periodically answer surveys via their devices. The surveys include questions about social issues, content interests, emotional states, and more.

[0398] The server analyzes the basic information and survey responses collected from the user using machine learning algorithms and emotion recognition engines. Known machine learning libraries (e.g., scikit-learn) and emotion recognition models (e.g., emotion recognition models from the transformers library) are used. The analysis results identify the user's values, needs, and emotional state.

[0399] The server then generates policy or content recommendations based on these analysis results, and the recommendations are tailored to reflect the user's emotional state. For example, if the user is in a "sad" emotional state, comforting content will be suggested.

[0400] The suggestions are sent to the device, and the user confirms them through the interface. The interface adjusts its display based on the user's emotional state. An emotion recognition engine evaluates the user's emotional state from their feedback and interactions, and the interface is optimized accordingly.

[0401] Users provide feedback on the suggestions. This feedback is sent to the server and stored in a database. The server analyzes the collected feedback and reflects it in the next suggestion. During this process, a generative AI model is used to create prompts to generate optimal suggestions.

[0402] For example, in the following example, in response to feedback such as "I was moved! It brought me to tears!", the emotion recognition model detects the emotion "sad." Based on this, other inspiring movies and content are suggested.

[0403] Example prompt sentence:

[0404] User feedback: "I was moved! It brought me to tears!"

[0405] Sentiment analysis result: "Sad"

[0406] Suggested content list:

[0407] 1. "In This Corner of the World" - A moving story set in Hiroshima during the war

[0408] 2. "The Wind Rises" - A story of an airplane designer's dreams and love

[0409] As described above, the present invention provides a specific method for realizing a system that makes suggestions based on the user's values, needs, and emotional state, thereby increasing user satisfaction.

[0410] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0411] Step 1: A user registers with the system.

[0412] Input: User's basic information (name, age, gender, etc.)

[0413] Process: A user accesses the system from a terminal, creates an account, and enters basic information, which is then sent to the server.

[0414] Output: The server stores the collected basic information in a database.

[0415] Step 2: Collect survey responses.

[0416] Input: User survey responses (social issues, content interests, emotional state, etc.)

[0417] Processing: The server periodically sends a survey notification to the user. The user answers the survey through their terminal and sends the results to the server.

[0418] Output: The server stores the collected survey responses in a database.

[0419] Step 3: Data analysis.

[0420] Input: User basic information stored in the database, survey responses, and emotional feedback

[0421] Processing: The server analyzes the data using machine learning algorithms (scikit-learn) to identify the user's values ​​and needs, and analyzes the user's emotional state using an emotion engine (transformers library).

[0422] Output: Identified user values, needs, and emotional state.

[0423] Step 4: Generate policy or content proposals.

[0424] Input: Identified values, needs, and emotional states

[0425] Processing: The server uses the generative AI model to generate optimized policy or content recommendations based on the user's values ​​and emotional state. For example, if the emotional state is rated as "sad," inspirational movies or content will be suggested.

[0426] Output: Generated policy or content proposals

[0427] Step 5: Notification and display of proposals.

[0428] Input: Generated policy proposals or content proposals, emotional states

[0429] Processing: The server sends the generated suggestions to the user's device. The device notifies the user of the suggestions and displays details through a display interface. Based on the emotion engine, the display method is optimized according to the user's emotional state.

[0430] Output: An interface for the user to visually confirm the proposal

[0431] Step 6: Gather feedback.

[0432] Input: User feedback

[0433] Processing: The user provides their opinions and feedback on the proposals through their device. The feedback is sent to the server and stored in a database.

[0434] Output: Collected feedback

[0435] Step 7: Analyze the feedback and incorporate it into your next proposal.

[0436] Input: collected feedback, emotional state data

[0437] Processing: The server analyzes the collected feedback and emotional state data and reflects it in the next suggestion. It also uses a generative AI model to create prompts to generate optimal suggestions.

[0438] Output: Improved next policy or content proposal

[0439] Through each of the above steps, the system can make policy and content suggestions that are in line with the user's values, needs, and emotional state, thereby increasing the acceptability and satisfaction of the suggestions.

[0440] 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.

[0441] 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.

[0442] 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.

[0443] [Second embodiment]

[0444] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0445] 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.

[0446] 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).

[0447] 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.

[0448] 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.

[0449] 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).

[0450] 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.

[0451] 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.

[0452] 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.

[0453] 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.

[0454] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0455] 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."

[0456] This invention is a policy proposal system using AI that proposes policies based on the values ​​and needs of each user. The system includes the following main means and processes:

[0457] User Registration

[0458] First, a user accesses the system and creates an account, which allows the user to enter their basic information into the system, which is then sent to the server and stored in the database.

[0459] Polyseasonal Bayesian Data Collection

[0460] The server periodically sends users survey notifications, which include questions about social issues, taxes, welfare systems, etc. Users answer the surveys through their devices, and the responses are sent to the server and stored.

[0461] Data analysis and policy proposal generation

[0462] The server uses machine learning algorithms to analyze the collected basic information and survey responses of users. As a result of the analysis, each user's values ​​and needs are identified. Based on these results, the server generates optimal policy proposals for the user.

[0463] Notification and display of policy proposals

[0464] The generated policy proposal is sent from the server to the user's device, where it is displayed to the user and provides an interface visually displaying the details of the policy proposal. The user can then review the proposal contents through this interface.

[0465] Gathering and implementing feedback

[0466] Users provide feedback to the system, including their opinions and thoughts on policy proposals. The feedback is sent from the device to the server and analyzed. As a result, the server can reflect the user's feedback in the next policy proposal.

[0467] Specific examples

[0468] Scenario: Welfare policy proposal for the elderly

[0469] 1. An elderly user registers with the system and enters basic information (e.g., age 75, retired, living alone).

[0470] 2. Users use the device to fill out a questionnaire and answer questions about their health issues and financial situation.

[0471] 3. The server analyzes the user's basic information and questionnaire responses to determine the user's characteristics, such as "low income" or "health problems."

[0472] 4. The server generates policy proposals tailored to the user, such as medical expense subsidy systems for the elderly.

[0473] 5. The terminal displays the generated policy proposal to the user, who then checks the details.

[0474] 6. The user provides feedback on the suggestion, such as "very helpful."

[0475] 7. The server collects feedback, updates the AI ​​model with the latest information, and provides a policy proposal report to government officials.

[0476] In this way, the system aims to realize democracy and promote citizen participation by making policy proposals that reflect the diverse opinions of citizens by making policy proposals that meet the needs of each individual user.The system also aims to continuously improve the quality of policy proposals through a feedback function.

[0477] The processing flow will be explained below.

[0478] Step 1: User registers with the system

[0479] 1. A user visits a web page or app and selects "Create a new account."

[0480] 2. The device displays a registration form to the user, asking them to enter basic information such as their name, address, age, occupation, and email address.

[0481] 3. The user enters the required information and clicks "Submit."

[0482] 4. The terminal sends the entered data to the server.

[0483] 5. The server stores the received basic information in a database.

[0484] Step 2: Send out the survey and collect responses

[0485] 1. The server periodically generates and prepares to send surveys to registered users.

[0486] 2. The device displays a notification to the user saying "There is a new survey."

[0487] 3. The user clicks on the notification and opens the survey page.

[0488] 4. The terminal displays the survey form and the user answers the questions.

[0489] 5. The user answers the questions and clicks "Submit."

[0490] 6. The device sends the user's response data to the server.

[0491] 7. The server stores the received response data in a database.

[0492] Step 3: Data analysis

[0493] 1. The server reads the user's basic information and survey responses from the database.

[0494] 2. The server applies machine learning algorithms to analyze each user's values ​​and needs.

[0495] 3. The server updates each user's profile based on the analysis results.

[0496] Step 4: Generate policy proposals

[0497] 1. The server begins generating policy proposals based on the user's profile.

[0498] 2. The policy proposals generated by the server include specific policy explanations, expected effects, advantages and disadvantages, etc.

[0499] 3. The server stores the generated policy proposals for each user.

[0500] Step 5: Notification and display of policy proposals

[0501] 1. The server prepares to send the stored policy proposal to the corresponding user.

[0502] 2. The device displays a notification to the user saying, "New policy proposals available."

[0503] 3. The user clicks on the notification to view the details of the policy proposal.

[0504] 4. The device displays details of the policy proposal to the user, providing a convenient UI.

[0505] Step 6: Gather feedback

[0506] 1. Users view the policy proposal and enter their opinions and thoughts in the feedback section.

[0507] 2. The user submits feedback.

[0508] 3. The device sends the feedback data to the server.

[0509] 4. The server stores the received feedback data in a database.

[0510] Step 7: Analyze and incorporate feedback

[0511] 1. The server analyzes the feedback data and updates the AI ​​model.

[0512] 2. The server stores the analysis results so that the user's feedback can be reflected in the next policy proposal.

[0513] 3. The server generates a report that provides the user feedback results to government officials.

[0514] Example 1

[0515] 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."

[0516] The current policy proposal system has difficulty in fully reflecting the values ​​and needs of each citizen, resulting in problems with proposed policies that do not adequately address individual citizens. Another issue is that collected feedback is not adequately reflected in subsequent proposals, resulting in a lack of improvement in the quality of policy proposals. Furthermore, there is also the problem that generated policy proposals are not effectively provided to government agencies.

[0517] 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.

[0518] In this invention, the server includes a means for users to register with the system, a means for collecting basic information and questionnaire responses from users, a means for storing the collected information in a database, a means for analyzing the stored information using a machine learning algorithm to identify users' values ​​and needs, a means for generating policy proposals based on the identified values ​​and needs, a means for notifying and displaying the generated policy proposals to users, a means for collecting feedback from users, a means for analyzing the collected feedback and updating the generative AI model to reflect the feedback in the next proposal, and a means for providing the generated policy proposals to government agencies. This enables highly accurate policy proposals that are in line with individual users' values ​​and needs, and the quality of policy proposals is improved by continuously incorporating feedback. Furthermore, by effectively providing the generated policy proposals to government agencies, they can contribute to actual policy formation.

[0519] "Means for Users to Register with the System" refers to the process and interface through which a User can access the System and enter the required basic information to create an account.

[0520] "Means for collecting basic information and questionnaire responses from users" refers to the process or mechanism for presenting questions to users and collecting their responses along with their attribute information.

[0521] "Means for storing collected information in a database" refers to a database management system and related operations for persistently storing basic information and survey responses obtained from users.

[0522] "Means of analyzing stored information using machine learning algorithms to identify users' values ​​and needs" refers to machine learning technology and its execution environment for analyzing collected data and clarifying individual users' characteristics and requirements.

[0523] "Means for generating policy proposals based on identified values ​​and needs" refers to processes or algorithms that formulate optimal policies for users based on the results of analysis and automatically generate proposals.

[0524] "Means for notifying and displaying the generated policy proposal to the user" refers to a notification system and display interface for notifying the user's terminal of the generated policy proposal and allowing the user to visually confirm it.

[0525] "Means for collecting feedback from users" refers to the process or interface through which users can input their opinions and thoughts about policy proposals and receive them into the system.

[0526] "Means for analyzing collected feedback and updating the generative AI model to reflect it in the next proposal" refers to the process and techniques for analyzing feedback provided by users and retraining the machine learning model as needed to improve the accuracy of the next policy proposal.

[0527] "Means for providing generated policy proposals to government agencies" refers to the processes and mechanisms for officially transmitting policy proposals created by the system to government agencies and utilizing them in the policy-making process.

[0528] This invention is a system for making policy proposals based on users' values ​​and needs. The system consists of the following processes: user registration, data collection, data analysis, policy proposal generation, notification, and feedback collection. A specific embodiment of this system is described below.

[0529] User Registration

[0530] First, the user accesses the system via the Internet and uses a web browser to access the registration screen. The registration screen displays a form where basic information (name, age, occupation, area of ​​residence, etc.) is entered. When the user enters the information and presses the "Submit" button, the information is sent to the server and stored in a database. This database uses a common database management system such as MySQL or PostgreSQL.

[0531] Polyseasonal Bayesian Data Collection

[0532] The server automatically generates survey notification emails to users at regular intervals. These notifications include questions about social issues, taxes, welfare systems, etc. The notification emails are sent via an SMTP server. When a user clicks on the link in the email and accesses the survey page, the page is displayed on the device. When the user answers the survey and presses the "Submit" button, the answers are sent to the server and stored in a database.

[0533] Data analysis and policy proposal generation

[0534] The server inputs the collected basic information and survey responses into a machine learning algorithm. The analysis is performed using Python and machine learning libraries such as TensorFlow and Scikit-learn. This allows the user's values ​​and needs to be identified using clustering and regression analysis techniques. The Python script then generates optimal policy proposals based on the analysis results and stores them in a database.

[0535] Notification and display of policy proposals

[0536] The generated policy proposal is then sent back to the user's device from the server. The notification email includes a link to view the details of the proposal. The user can click the link to access the policy proposal details page and view the details. This page provides an interface that visually displays the proposal contents.

[0537] Gathering and implementing feedback

[0538] Users provide feedback on policy proposals, including their opinions and thoughts. Feedback is sent via an input form on the details page. The feedback sent from the device is received by the server and stored in a database. The server then analyzes the feedback. This analysis uses text analysis techniques. The machine learning model is retrained based on the analysis results, improving the accuracy of the next policy proposal.

[0539] The generated policy proposals are automatically provided to government agencies, with the hope that they will be utilized in actual policy formation.

[0540] Specific examples

[0541] Scenario: Welfare policy proposal for the elderly

[0542] 1. An elderly user registers in the system and enters basic information (e.g., age 75, retired, living alone).

[0543] 2. Users fill out a survey and provide information about their health issues and financial situation.

[0544] 3. The server analyzes this information and identifies characteristics of the user, such as whether they have a low income or health problems.

[0545] 4. The server generates policy proposals tailored to the user, such as medical expense subsidy systems for the elderly.

[0546] 5. The user reviews the policy proposals generated on the device and provides feedback such as "very helpful."

[0547] 6. The server collects feedback, updates the AI ​​model, and provides a policy proposal report to government agencies.

[0548] Prompt Sentence Examples

[0549] "Generate policy proposals for a medical expense subsidy system for the elderly based on basic information and survey responses."

[0550] In this way, the system can provide policy proposals tailored to the individual needs of each user, and through feedback functions, the quality of the policy proposals can be continuously improved.

[0551] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0552] Step 1: User Registration

[0553] A user accesses the system's URL using a web browser. The user enters basic information (such as name, age, occupation, and area of ​​residence) on the registration screen. The entered basic information is sent from the terminal to the server when the user presses the "Submit" button. The server receives the sent basic information and saves it in a database. This stores the user's basic information in the database and makes it available for future processing.

[0554] Input: Basic information entered by the user

[0555] Data calculation: Send input data to the server and save it in the database

[0556] Output: Basic user information stored in the database

[0557] Step 2: Polyseasonal Bayesian data collection

[0558] The server periodically generates and sends survey notification emails to users. These emails contain a URL for a survey containing questions about social issues, taxes, welfare systems, etc. When a user clicks on the link in the email, they access the survey page. The user answers the survey using their device and presses the "Submit" button, which sends the answers from the device to the server. The server receives the answers and stores them in a database.

[0559] Input: Server-generated survey notification email

[0560] Data calculation: Sending user answers to the server and storing them in a database

[0561] Output: Survey responses stored in a database

[0562] Step 3: Data analysis and policy proposal generation

[0563] The server runs a machine learning algorithm to analyze the collected basic information and survey responses. The analysis is performed using Python and libraries such as TensorFlow and Scikit-learn. The server reads the user's basic information and survey responses from the database and inputs them into a machine learning model. The algorithm performs clustering and regression analysis to identify the user's values ​​and needs. Based on the analysis results, optimal policy proposals are generated. These proposals are then saved back to the database.

[0564] Input: User basic information and survey responses stored in the database

[0565] Data Computing: Analyzing data and generating policy recommendations using machine learning algorithms

[0566] Output: Generated policy proposals

[0567] Step 4: Notification and presentation of policy proposals

[0568] The generated policy proposal is notified to the user's device by the server. The server generates a policy proposal notification email and sends it to the user. The notification email contains a link to view the details of the proposal. When the user clicks the link, they can access the policy proposal details page. The device displays this page, allowing the user to visually confirm the proposal contents.

[0569] Input: Generated policy proposals

[0570] Data calculation: Generate and send policy proposal notification emails

[0571] Output: Policy proposal details page displayed on the user's device

[0572] Step 5: Gather and incorporate feedback

[0573] Users provide their opinions and thoughts on policy proposals as feedback through an input form on the details page. When the user presses the "Submit" button, the feedback is sent from the device to the server. The server then stores the received feedback in a database. The server then analyzes it and uses text analysis techniques to analyze the feedback content. Based on the analysis results, the machine learning model is retrained. This improves the accuracy of the next policy proposal.

[0574] Input: User feedback

[0575] Data calculation: storing and analyzing feedback in a database

[0576] Output: Improved policy proposals for the next round

[0577] Step 6: Submitting policy proposals to government agencies

[0578] Finally, the generated policy proposals are provided to government agencies. The server generates a policy proposal report and automatically sends it to the appropriate government agency. This report contains detailed policy proposals based on the analysis results, which will help the policy proposals to be used in actual policy formation.

[0579] Input: Generated policy proposals

[0580] Data Computing: Generate and send policy proposal reports

[0581] Output: Policy proposals provided to government agencies

[0582] (Application example 1)

[0583] 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."

[0584] Current policy proposal systems are designed for general users and are unable to fully reflect the specific needs of elderly people and users with physical limitations. Furthermore, they lack the functionality to provide appropriate assistance services in real time, especially for users using autonomous vehicles. This has led to problems such as delays and inappropriate recommendations and guidance for welfare support and medical services needed by elderly people and users with physical limitations.

[0585] 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.

[0586] In this invention, the server includes means for users to register with the system, means for collecting basic information and questionnaire responses from users, means for saving the collected information in a database, means for analyzing the saved information and identifying the user's values ​​and needs, means for generating policy proposals based on the identified values ​​and needs, means for notifying and displaying the generated policy proposals to the user, means for collecting feedback from the user, means for analyzing the collected feedback and reflecting it in the next proposal, and means for analyzing usage information and health status data collected by the autonomous mobile device and proposing optimal welfare support services to the user while riding. This makes it possible to provide appropriate welfare support services in real time to elderly and physically limited users, and to create an environment in which users can use the autonomous mobile device with peace of mind.

[0587] An "autonomous vehicle" is a means of transportation that uses artificial intelligence and sensor technology to operate automatically and travel to a destination without human intervention.

[0588] "Usage information" is data generated when a user uses an autonomous driving device, and includes information such as travel route, boarding and disembarking times, and riding frequency.

[0589] "Health condition data" refers to information relating to the user's health, and includes biometric data such as blood pressure, heart rate, and body temperature, as well as health status evaluation results based on questionnaire results and the like.

[0590] "Welfare support services" are support measures and services provided to users with specific needs, such as the elderly and people with disabilities, and include medical assistance, transportation assistance, and lifestyle support.

[0591] "Analysis" is the process of applying machine learning algorithms and statistical methods to analyze information based on collected data to identify specific values ​​and needs.

[0592] "Policy proposals" are proposals that present optimal policies and support measures to users based on the analysis results, and include information on specific measures and services.

[0593] "Feedback" refers to information such as opinions, impressions, and evaluations provided by users, and is useful for improving the system and increasing the accuracy of future policy proposals.

[0594] This invention applies an AI-based policy proposal system to an autonomous driving device to provide optimal welfare support services in real time to elderly people and users with physical limitations. The system includes the following main components:

[0595] 1. User Registration

[0596] The server provides a means for users to register with the system through the terminal of the autonomous driving device. The user can then enter their basic information and register with the system. The user's basic information includes age, gender, health condition, etc.

[0597] 2. Data Collection

[0598] The server uses the terminal to collect basic information and questionnaire responses from users, including usage information, health status data, and questionnaires about their living conditions. The data is collected periodically, sent to the server, and stored in a database.

[0599] 3. Data analysis and policy proposal generation

[0600] The server analyzes the collected data using machine learning algorithms. Specifically, it uses platforms such as NVIDIA Jetson to identify the user's values ​​and needs. Based on these values ​​and needs, it generates optimal welfare support services and policies.

[0601] 4. Notification and Display of Policy Proposals

[0602] The server notifies the autonomous driving device of the generated policy proposals. The device then displays the proposals visually and audibly to the user through a display and audio guide. It is also possible to link with smart glasses or a head-mounted display to display the proposals in real time.

[0603] 5. Gather and incorporate feedback

[0604] The server collects the feedback provided by users and incorporates this information into the next policy proposal, allowing for continuous improvement of the quality of the proposal.

[0605] Examples:

[0606] Elderly person A (75 years old) rides an autonomous driving device and answers a questionnaire about his / her health condition and lifestyle through a linked application. The server analyzes the collected data in real time and suggests "priority access to medical institutions" and "low-cost transportation support plans." This allows Elderly Person A to receive appropriate support services based on his / her health condition.

[0607] Example prompt sentence:

[0608] "Data analysis prompt to propose a medical assistance system for elderly users: Generate appropriate policy proposals based on information such as age, living situation, health status, and facilities (medical institutions, public services) that users frequently access. Example: 75 years old, living alone, with chronic illnesses, and needing to visit hospitals frequently."

[0609] This system enables elderly people and people with physical limitations who use autonomous vehicles to receive optimal welfare support services in real time. The generated policy proposals are also customized to the needs of each user, providing optimal support for each user.

[0610] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0611] Step 1:

[0612] The server provides a means for users to register with the system. Users enter basic information such as age, gender, and health status through the terminal of the autonomous driving device. The server stores this basic information in a database.

[0613] Input: User's basic information (age, gender, health status, etc.)

[0614] Output: Basic information stored in the database

[0615] Specific operation: The user enters information into the registration screen displayed on the terminal and sends it to the server, which then stores the received information in a database.

[0616] Step 2:

[0617] The server periodically sends questionnaires to users to collect usage information and health status data. Users respond to the questionnaires and send the data from their terminals to the server.

[0618] Input: Survey responses, usage information (route, boarding and disembarking times, etc.), health status data (blood pressure, heart rate, etc.)

[0619] Output: Survey responses, usage information, and health status data stored in a database

[0620] Specific operation: A questionnaire is presented to the user via the device's display or audio guide. The user answers the questionnaire and sends the data to the server.

[0621] Step 3:

[0622] The server analyzes the collected data using machine learning algorithms (e.g., NVIDIA Jetson), processes the data, and identifies the user's values ​​and needs.

[0623] Input: Basic information, survey responses, usage information, health status data

[0624] Output: User values ​​and needs

[0625] How it works: The server retrieves the collected data from the database, inputs it into a machine learning algorithm, and analyzes it. From the analysis results, the user's specific values ​​and needs are extracted.

[0626] Step 4:

[0627] The server generates optimal welfare support services and policy proposals based on the analysis results.

[0628] Input: User values ​​and needs

[0629] Output: Generated policy proposals

[0630] Specific operation: Based on the analysis results, the server uses a specific algorithm to generate optimal policy proposals for the user.

[0631] Step 5:

[0632] The server notifies the device of the generated policy proposals and displays them to the user. The device then provides the proposals to the user using a display or audio guide. The device also works with smart glasses or a head-mounted display to display the proposals in real time.

[0633] Input: Generated policy proposals

[0634] Output: Policy proposals displayed to the user

[0635] Specific operation: Policy proposals are displayed on the device screen and explained via audio guidance. When using smart glasses or a head-mounted display, the proposals are displayed in real time.

[0636] Step 6:

[0637] Users provide feedback on the presented policy proposals through their terminals, and the server collects the feedback and stores it in a database.

[0638] Input: User feedback

[0639] Output: Feedback stored in a database

[0640] Specific operation: The user can easily input feedback through the terminal interface, and the server receives the feedback and stores it in a database.

[0641] Step 7:

[0642] The server analyzes the collected feedback and reflects it in the next policy proposal.

[0643] Input: Feedback stored in the database

[0644] Output: Improved policy recommendations

[0645] Specific operation: The server analyzes the feedback and updates the machine learning model based on the results. The analysis results are reflected in the next policy proposal to make it more accurate.

[0646] 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.

[0647] This invention is a policy proposal system that uses AI and an emotion engine to propose policies that take into account the emotional state as well as the values ​​and needs of each individual user. The system includes the following main means and processes:

[0648] User Registration

[0649] First, a user accesses the system and creates an account, which allows the user to enter their basic information into the system, which is then sent to the server and stored in the database.

[0650] Polyseasonal Bayesian Data Collection

[0651] The server periodically sends users survey notifications, which include questions about social issues, taxes, welfare systems, etc. Users answer the surveys through their devices, and the responses are sent to the server and stored.

[0652] Data analysis and emotion recognition

[0653] The server uses machine learning algorithms and an emotion engine to analyze the collected user information and survey responses. As a result of the analysis, each user's values ​​and needs are identified. At the same time, the emotion engine evaluates the user's emotional state based on their feedback and interactions.

[0654] Generate policy proposals

[0655] The server generates policy proposals based on the user's values, needs, and assessed emotional state, ensuring that the proposed policies are in line with the user's actual emotions.

[0656] Notification and display of policy proposals

[0657] The generated policy proposal is sent from the server to the user's device, where it is displayed to the user as a notification and provides an interface with detailed visual information. The interface's display method is also adjusted according to the user's emotional state.

[0658] Gathering and implementing feedback

[0659] Users provide their opinions and thoughts on policy proposals as feedback to the system. The feedback is sent from the device to the server and analyzed. As a result, the server can reflect the user's feedback and emotional state in the next policy proposal.

[0660] Specific examples

[0661] Scenario: Welfare policy proposal for the elderly

[0662] 1. An elderly user registers with the system and enters basic information (e.g., age 75, retired, living alone).

[0663] 2. Users use the device to fill out a questionnaire and answer questions about their health issues and financial situation.

[0664] 3. The server analyzes the user's basic information and questionnaire responses to determine the user's characteristics, such as "low income" or "health problems."

[0665] 4. The emotion engine evaluates the emotional state from the user's feedback and interactions and sends it to the server.

[0666] 5. The server generates policy proposals tailored to the user, such as medical subsidy programs for the elderly, and adjusts the proposals to take into account the user's emotional state.

[0667] 6. The terminal displays the generated policy proposal to the user, who can then check the details. Based on the emotion engine, the display method is optimized to the user's emotional state.

[0668] 7. The user provides feedback on the suggestion, such as "very helpful."

[0669] 8. The server collects feedback, updates the AI ​​model and emotion engine with the latest information, and provides a policy proposal report to government officials.

[0670] This system will propose policies that take into account the needs and emotional state of each user, enabling policy formation that reflects the diverse opinions and emotions of citizens. Furthermore, through a feedback function, the quality of policy proposals can be continuously improved, promoting the realization of democracy and citizen participation.

[0671] The processing flow will be explained below.

[0672] Step 1: User registers with the system

[0673] 1. A user visits a web page or app and selects "Create a new account."

[0674] 2. The device displays a registration form to the user, asking them to enter basic information such as their name, address, age, occupation, and email address.

[0675] 3. The user enters the required information and clicks "Submit."

[0676] 4. The terminal sends the entered data to the server.

[0677] 5. The server stores the received basic information in a database.

[0678] Step 2: Send out the survey and collect responses

[0679] 1. The server periodically generates and prepares to send surveys to registered users.

[0680] 2. The device displays a notification to the user saying "There is a new survey."

[0681] 3. The user clicks on the notification and opens the survey page.

[0682] 4. The terminal displays the survey form and the user answers the questions.

[0683] 5. The user answers the questions and clicks "Submit."

[0684] 6. The device sends the user's response data to the server.

[0685] 7. The server stores the received response data in a database.

[0686] Step 3: Data analysis and emotion recognition

[0687] 1. The server reads the user's basic information and survey responses from the database.

[0688] 2. The server applies machine learning algorithms to analyze each user's values ​​and needs.

[0689] 3. The server updates each user's profile based on the analysis results.

[0690] 4. The server uses an emotion engine to evaluate the emotional state from the user's feedback and interactions.

[0691] 5. The server adds the emotional state assessment to the profile.

[0692] Step 4: Generate policy proposals

[0693] 1. The server starts generating policy suggestions based on the user's profile and emotional state.

[0694] 2. The policy proposals generated by the server include specific policy explanations, expected effects, advantages and disadvantages, etc.

[0695] 3. The server stores the generated policy proposals for each user.

[0696] Step 5: Notification and display of policy proposals

[0697] 1. The server prepares to send the stored policy proposal to the corresponding user.

[0698] 2. The device displays a notification to the user saying, "New policy proposals available."

[0699] 3. The user clicks on the notification to view the details of the policy proposal.

[0700] 4. The device displays details of policy proposals to the user and provides a convenient UI that adapts to their emotional state.

[0701] Step 6: Gather feedback

[0702] 1. Users view the policy proposal and enter their opinions and thoughts in the feedback section.

[0703] 2. The user submits feedback.

[0704] 3. The device sends the feedback data to the server.

[0705] 4. The server stores the received feedback data in a database.

[0706] 5. The server uses the emotion engine to analyze the feedback content.

[0707] Step 7: Analyze and incorporate feedback

[0708] 1. The server analyzes the feedback data and updates the AI ​​model and emotion engine.

[0709] 2. The server stores the analysis results so that the next policy proposal will reflect the user's feedback and emotional state.

[0710] 3. The server generates a report that provides the user feedback results to government officials.

[0711] Examples:

[0712] Scenario: Welfare policy proposal for the elderly

[0713] 1. An elderly user registers with the system and enters basic information (e.g., age 75, retired, living alone).

[0714] 2. The user uses the device to answer a questionnaire and enter their opinions about health issues and financial situations.

[0715] 3. The server stores the user's basic information and survey response data in a database.

[0716] 4. The server uses machine learning algorithms and an emotion engine to analyze the user's values, needs, and emotional state.

[0717] 5. Based on the analysis results, the server generates proposals for medical subsidy programs for the elderly, adjusting the content of the proposals to take into account the emotional state.

[0718] 6. The device notifies the user of the generated policy proposal and visually displays the details. Based on the emotion engine, the display method is optimized to the user's emotional state.

[0719] 7. The user reviews the suggestion and provides feedback that it is "very helpful."

[0720] 8. The server collects feedback and updates the AI ​​model and emotion engine with the latest information.

[0721] 9. The server provides policy proposal reports to government officials to help them formulate policies.

[0722] In this way, policy proposals that take into account the user's emotional state can be more personalized, reflecting the diverse opinions and emotions of citizens, and continuously improving the quality of policy proposals through feedback and sentiment analysis.

[0723] Example 2

[0724] 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."

[0725] Conventional policy proposal systems make proposals based only on the user's basic information and questionnaire responses, which means they are inadequately able to adapt to fluctuations in an individual user's emotional state and feedback. As a result, it is difficult to generate policy proposals that are appropriate for the user's actual interests and emotional state. Furthermore, there is a lack of a method to maintain consistency by incorporating feedback into the next proposal.

[0726] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0727] In this invention, the server includes means for users to register with the system, means for collecting basic information and questionnaire responses from users, means for storing the collected information in a database, means for analyzing the stored information using a machine learning algorithm to identify the user's values ​​and needs, means for evaluating the user's emotional state using an emotion recognition engine, means for generating policy proposals using a generative AI model based on the identified values ​​and needs and the evaluated emotional state, means for notifying and displaying the generated policy proposals to the user, and means for collecting feedback from the user and reflecting the feedback in the next policy proposal, thereby enabling personalized policy proposals based on the user's values ​​and emotional state.

[0728] "User" refers to an individual person who uses the system.

[0729] "System" refers to an environment that includes a set of software and hardware for communicating information between users and a server and generating policy proposals.

[0730] "Basic information" refers to personal information such as the user's name, age, gender, and address.

[0731] "Survey responses" refer to responses to questions asked by users regarding social issues, taxes, welfare systems, etc.

[0732] "Database" refers to a system that organizes and stores collected data such as basic user information and questionnaire responses.

[0733] "Machine learning algorithms" refer to techniques that analyze large amounts of data for patterns and trends, and specifically include technologies such as TensorFlow.

[0734] "Emotion recognition engine" refers to a system that assesses the emotional state of a user from their feedback and interactions. Examples include the IBM Watson Tone Analyzer.

[0735] "Generative AI models" refer to artificial intelligence algorithms that generate text or suggestions based on collected and analyzed data, including GPT-4.

[0736] "Policy proposals" refer to specific policy proposals generated based on the user's basic information, survey responses, and emotional state.

[0737] "Notification" refers to the system's ability to notify users of new information or offers.

[0738] "Display" refers to the user being able to visually confirm the details of information and suggestions through the system.

[0739] "Feedback" refers to the user providing the system with their opinions and thoughts about the proposal.

[0740] This invention is a policy proposal system that uses AI and an emotion engine to propose policies that take into account the emotional state of each user, along with their values ​​and needs. Specific means for implementing this system and its operation are described below.

[0741] User Registration

[0742] First, a user accesses the system using a web browser or smartphone app and creates a new account. The user enters basic information such as name, age, gender, and address. The basic information entered from the device is sent to the server using the HTTPS protocol. The server then stores the received basic information in a database (e.g., MongoDB, MySQL).

[0743] Polyseasonal Bayesian Data Collection

[0744] Next, the server uses a scheduling service (e.g., Cron job) to periodically send survey notifications to users. The surveys include questions about social issues, taxes, welfare systems, etc. Users answer the surveys using their devices, and the responses are sent from the devices to the server. The server then stores the survey response data in a database.

[0745] Data analysis and emotion recognition

[0746] The server uses a machine learning algorithm (e.g., TensorFlow) to analyze the user's basic information and survey responses. As a result of the analysis, each user's values ​​and needs are identified. At the same time, the server uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to evaluate the user's emotional state from their feedback and interactions. The analysis results are stored in a database as the user's individual profile.

[0747] Generate policy proposals

[0748] The server then uses a generative AI model (e.g., GPT-4) to generate policy proposals based on the analysis results and the user's emotional state. These proposals are tailored to the user's values ​​and needs, and are adjusted according to the user's emotional state.

[0749] Notification and display of policy proposals

[0750] The generated policy proposals are sent from the server to the user's device. The device notifies the user of the received policy proposals and displays details. The display method of the device's interface is also adjusted based on the user's emotional state. For example, if the emotional state is determined to be "stressed," the interface color scheme and font style are changed to something more relaxing.

[0751] Gathering and implementing feedback

[0752] Finally, the user provides feedback to the system, including their opinions and thoughts on the policy proposals. This feedback is sent from the device to the server, where it is analyzed and reflected in the next policy proposal. This allows the system to continually make proposals that incorporate the user's latest needs and emotional state.

[0753] Specific examples

[0754] Scenario: Welfare policy proposal for the elderly

[0755] 1. An elderly user registers in the system and enters basic information (e.g., age 75, retired, living alone).

[0756] 2. Users use the device to fill out a questionnaire and answer questions about their health issues and financial situation.

[0757] 3. The server analyzes the user's basic information and questionnaire responses to determine the user's characteristics, such as "low income" or "health problems."

[0758] 4. The emotion engine evaluates the emotional state from the user's feedback and interactions and sends it to the server.

[0759] 5. The server generates tailored policy proposals for the user, such as medical subsidy programs for the elderly, and the proposals are adjusted based on the user's emotional state.

[0760] 6. The terminal displays the generated policy proposal to the user, who can then check the details. Based on the emotion engine, the display method is optimized to the user's emotional state.

[0761] 7. The user provides feedback on the suggestion, such as "very helpful."

[0762] 8. The server collects feedback and updates the AI ​​model and emotion engine with the latest information.

[0763] Prompt Sentence Examples

[0764] "Please propose a welfare policy suitable for seniors who have retired at age 75. Consider the following conditions: low income, health problems."

[0765] "Use AI and emotion engines to generate policy recommendations that take into account the user's values ​​and emotional state."

[0766] This system realizes personalized policy proposals that take into account the needs and emotional state of each user, enabling policy formation that reflects the diverse opinions and emotions of citizens. Furthermore, through a feedback function, the quality of policy proposals can be continuously improved, promoting the realization of democracy and citizen participation.

[0767] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0768] Step 1: User Registration

[0769] Users access the system using a web browser or smartphone app and create a new account.

[0770] Input: User's basic information (name, age, gender, address, etc.)

[0771] Output: Basic user information stored in the database

[0772] How it works: A user fills out a form with basic information and clicks the submit button. The device sends the information to the server via HTTPS. The server validates the received information and stores it in a database.

[0773] Step 2: Polyseasonal Bayesian data collection

[0774] The server periodically sends survey notifications to users.

[0775] Input: Survey data, user basic information

[0776] Output: Survey responses stored in a database

[0777] How it works: The server uses a scheduling service to send a survey notification to the user's device at a specific time. The user receives the notification and opens the survey screen. They answer the survey, and the device sends the response data to the server. The server stores the received response data in a database.

[0778] Step 3: Data analysis and emotion recognition

[0779] The server uses machine learning algorithms to analyze the user's basic information and questionnaire responses, and uses an emotion engine to evaluate their emotional state.

[0780] Input: User basic information, survey responses, feedback

[0781] Output: Analyzed user values, needs and emotional state

[0782] How it works: The server uses TensorFlow to analyze user data. As a result of the analysis, each user's values ​​and needs are identified. At the same time, an emotion recognition engine (e.g., emotion analysis API) evaluates the user's emotional state based on their feedback and interaction data. The evaluation results are saved as a personalized profile for the user.

[0783] Step 4: Generate policy proposals

[0784] The server generates policy proposals using a generative AI model based on the analysis results and emotional state.

[0785] Input: Analyzed user values, needs, and emotional state

[0786] Output: Generated policy proposals

[0787] How it works: The server takes the analysis results and the user's emotional state as input and uses a generative AI model (e.g., GPT-4) to generate policy proposals. The proposals include specific policy content and are adjusted according to the user's emotional state.

[0788] Step 5: Notification and presentation of policy proposals

[0789] The server sends the generated policy proposal to the user's terminal, which notifies the user of the policy proposal and displays the details.

[0790] Input: Generated policy proposals

[0791] Output: Policy proposals communicated and displayed to the user

[0792] How it works: The server converts the generated policy proposal into JSON format and sends it to the user's device. The device then notifies the user of the new policy proposal via push notifications or in-app notifications. The proposal details are displayed on a details screen, and the interface color scheme and font style are adjusted according to the user's emotional state.

[0793] Step 6: Gather and incorporate feedback

[0794] Users provide feedback on policy proposals, including their opinions and thoughts. The server collects the feedback and reflects it in the next policy proposal.

[0795] Input: User feedback

[0796] Output: Updated user profile, feedback to be reflected in next proposal

[0797] How it works: A user enters their opinions and thoughts into the feedback form on the policy proposal details screen and clicks the submit button. The device sends the feedback to the server. The server analyzes the received feedback and updates the user profile. This updated information is taken into account the next time a policy proposal is generated.

[0798] Through these steps, the system realizes personalized policy proposals based on the user's values ​​and emotional state.

[0799] (Application example 2)

[0800] 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."

[0801] Existing policy and content proposal systems can analyze users' values ​​and needs, but they struggle to make proposals that take into account the user's emotional state. This can lead to lower acceptability and satisfaction. Furthermore, there is a lack of effective ways to incorporate user feedback into future proposals, making it difficult to improve the quality of proposals.

[0802] 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.

[0803] In this invention, the server includes: a means for users to register with the system; a means for collecting basic information and questionnaire responses from users; a means for storing the collected information in a database; a means for analyzing the stored information to identify the user's values ​​and needs; a means for generating policy or content proposals based on the identified values ​​and needs and the evaluated emotional state; a means for notifying and displaying the generated policy or content proposals to the user; a means for adjusting the display method based on the user's feedback and emotional state; a means for collecting user feedback; and a means for analyzing the collected feedback and emotional state data and reflecting it in subsequent proposals. This enables policy and content proposals to be tailored to the user's emotional state, thereby improving the acceptability and satisfaction of the proposals. Furthermore, effectively reflecting feedback in subsequent proposals also improves the quality of the proposals.

[0804] A "user" is an individual or group that uses the system and provides data such as basic information and questionnaire responses.

[0805] The "system" is a set of mechanisms for generating, notifying, and displaying policy or content suggestions based on the user's values, needs, and emotional state, and for collecting feedback to be reflected in future suggestions.

[0806] "Policy proposals" are the contents of plans and measures provided by governments and public institutions that are generated based on the user's values, needs, and emotional state.

[0807] "Content suggestions" are entertainment and informational content such as movies, music, and news articles that are generated based on the user's values, needs, and emotional state.

[0808] "Emotional state" refers to the psychological state or feeling that is assessed through user feedback and interaction.

[0809] A "database" is an information collection that allows the system to store and manage collected basic information, questionnaire responses, feedback, etc. from users.

[0810] "Feedback" refers to opinions and thoughts provided by users regarding policy proposals or content proposals, and is data that will be reflected in the next proposal.

[0811] "Machine learning algorithms" refer to mathematical methods and techniques for analyzing large amounts of data and finding patterns and trends.

[0812] An "emotion recognition engine" refers to software or hardware that analyzes and evaluates a user's emotional state from text, speech, or other input.

[0813] "Interface" refers to the screen or operating system through which a user views and provides feedback on a policy or content proposal.

[0814] This invention is a system that uses AI and an emotion engine to make policy and content proposals that take into account the user's values, needs, and emotional state. Specific embodiments for implementing this invention are described below.

[0815] First, users access the system and create an account. They enter the necessary basic information, which is then sent to the server and stored in a database. They also periodically answer surveys via their devices. The surveys include questions about social issues, content interests, emotional states, and more.

[0816] The server analyzes the basic information and survey responses collected from the user using machine learning algorithms and emotion recognition engines. Known machine learning libraries (e.g., scikit-learn) and emotion recognition models (e.g., emotion recognition models from the transformers library) are used. The analysis results identify the user's values, needs, and emotional state.

[0817] The server then generates policy or content recommendations based on these analysis results, and the recommendations are tailored to reflect the user's emotional state. For example, if the user is in a "sad" emotional state, comforting content will be suggested.

[0818] The suggestions are sent to the device, and the user confirms them through the interface. The interface adjusts its display based on the user's emotional state. An emotion recognition engine evaluates the user's emotional state from their feedback and interactions, and the interface is optimized accordingly.

[0819] Users provide feedback on the suggestions. This feedback is sent to the server and stored in a database. The server analyzes the collected feedback and reflects it in the next suggestion. During this process, a generative AI model is used to create prompts to generate optimal suggestions.

[0820] For example, in the following example, in response to feedback such as "I was moved! It brought me to tears!", the emotion recognition model detects the emotion "sad." Based on this, other inspiring movies and content are suggested.

[0821] Example prompt sentence:

[0822] User feedback: "I was moved! It brought me to tears!"

[0823] Sentiment analysis result: "Sad"

[0824] Suggested content list:

[0825] 1. "In This Corner of the World" - A moving story set in Hiroshima during the war

[0826] 2. "The Wind Rises" - A story of an airplane designer's dreams and love

[0827] As described above, the present invention provides a specific method for realizing a system that makes suggestions based on the user's values, needs, and emotional state, thereby increasing user satisfaction.

[0828] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0829] Step 1: A user registers with the system.

[0830] Input: User's basic information (name, age, gender, etc.)

[0831] Process: A user accesses the system from a terminal, creates an account, and enters basic information, which is then sent to the server.

[0832] Output: The server stores the collected basic information in a database.

[0833] Step 2: Collect survey responses.

[0834] Input: User survey responses (social issues, content interests, emotional state, etc.)

[0835] Processing: The server periodically sends a survey notification to the user. The user answers the survey through their terminal and sends the results to the server.

[0836] Output: The server stores the collected survey responses in a database.

[0837] Step 3: Data analysis.

[0838] Input: User basic information stored in the database, survey responses, and emotional feedback

[0839] Processing: The server analyzes the data using machine learning algorithms (scikit-learn) to identify the user's values ​​and needs, and analyzes the user's emotional state using an emotion engine (transformers library).

[0840] Output: Identified user values, needs, and emotional state.

[0841] Step 4: Generate policy or content proposals.

[0842] Input: Identified values, needs, and emotional states

[0843] Processing: The server uses the generative AI model to generate optimized policy or content recommendations based on the user's values ​​and emotional state. For example, if the emotional state is rated as "sad," inspirational movies or content will be suggested.

[0844] Output: Generated policy or content proposals

[0845] Step 5: Notification and display of proposals.

[0846] Input: Generated policy proposals or content proposals, emotional states

[0847] Processing: The server sends the generated suggestions to the user's device. The device notifies the user of the suggestions and displays details through a display interface. Based on the emotion engine, the display method is optimized according to the user's emotional state.

[0848] Output: An interface for the user to visually confirm the proposal

[0849] Step 6: Gather feedback.

[0850] Input: User feedback

[0851] Processing: The user provides their opinions and feedback on the proposals through their device. The feedback is sent to the server and stored in a database.

[0852] Output: Collected feedback

[0853] Step 7: Analyze the feedback and incorporate it into your next proposal.

[0854] Input: collected feedback, emotional state data

[0855] Processing: The server analyzes the collected feedback and emotional state data and reflects it in the next suggestion. It also uses a generative AI model to create prompts to generate optimal suggestions.

[0856] Output: Improved next policy or content proposal

[0857] Through each of the above steps, the system can make policy and content suggestions that are in line with the user's values, needs, and emotional state, thereby increasing the acceptability and satisfaction of the suggestions.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] [Third embodiment]

[0862] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0863] 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.

[0864] 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).

[0865] 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.

[0866] 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.

[0867] 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).

[0868] 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.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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."

[0874] This invention is a policy proposal system using AI that proposes policies based on the values ​​and needs of each user. The system includes the following main means and processes:

[0875] User Registration

[0876] First, a user accesses the system and creates an account, which allows the user to enter their basic information into the system, which is then sent to the server and stored in the database.

[0877] Polyseasonal Bayesian Data Collection

[0878] The server periodically sends users survey notifications, which include questions about social issues, taxes, welfare systems, etc. Users answer the surveys through their devices, and the responses are sent to the server and stored.

[0879] Data analysis and policy proposal generation

[0880] The server uses machine learning algorithms to analyze the collected basic information and survey responses of users. As a result of the analysis, each user's values ​​and needs are identified. Based on these results, the server generates optimal policy proposals for the user.

[0881] Notification and display of policy proposals

[0882] The generated policy proposal is sent from the server to the user's device, where it is displayed to the user and provides an interface visually displaying the details of the policy proposal. The user can then review the proposal contents through this interface.

[0883] Gathering and implementing feedback

[0884] Users provide feedback to the system, including their opinions and thoughts on policy proposals. The feedback is sent from the device to the server and analyzed. As a result, the server can reflect the user's feedback in the next policy proposal.

[0885] Specific examples

[0886] Scenario: Welfare policy proposal for the elderly

[0887] 1. An elderly user registers with the system and enters basic information (e.g., age 75, retired, living alone).

[0888] 2. Users use the device to fill out a questionnaire and answer questions about their health issues and financial situation.

[0889] 3. The server analyzes the user's basic information and questionnaire responses to determine the user's characteristics, such as "low income" or "health problems."

[0890] 4. The server generates policy proposals tailored to the user, such as medical expense subsidy systems for the elderly.

[0891] 5. The terminal displays the generated policy proposal to the user, who then checks the details.

[0892] 6. The user provides feedback on the suggestion, such as "very helpful."

[0893] 7. The server collects feedback, updates the AI ​​model with the latest information, and provides a policy proposal report to government officials.

[0894] In this way, the system aims to realize democracy and promote citizen participation by making policy proposals that reflect the diverse opinions of citizens by making policy proposals that meet the needs of each individual user.The system also aims to continuously improve the quality of policy proposals through a feedback function.

[0895] The processing flow will be explained below.

[0896] Step 1: User registers with the system

[0897] 1. A user visits a web page or app and selects "Create a new account."

[0898] 2. The device displays a registration form to the user, asking them to enter basic information such as their name, address, age, occupation, and email address.

[0899] 3. The user enters the required information and clicks "Submit."

[0900] 4. The terminal sends the entered data to the server.

[0901] 5. The server stores the received basic information in a database.

[0902] Step 2: Send out the survey and collect responses

[0903] 1. The server periodically generates and prepares to send surveys to registered users.

[0904] 2. The device displays a notification to the user saying "There is a new survey."

[0905] 3. The user clicks on the notification and opens the survey page.

[0906] 4. The terminal displays the survey form and the user answers the questions.

[0907] 5. The user answers the questions and clicks "Submit."

[0908] 6. The device sends the user's response data to the server.

[0909] 7. The server stores the received response data in a database.

[0910] Step 3: Data analysis

[0911] 1. The server reads the user's basic information and survey responses from the database.

[0912] 2. The server applies machine learning algorithms to analyze each user's values ​​and needs.

[0913] 3. The server updates each user's profile based on the analysis results.

[0914] Step 4: Generate policy proposals

[0915] 1. The server begins generating policy proposals based on the user's profile.

[0916] 2. The policy proposals generated by the server include specific policy explanations, expected effects, advantages and disadvantages, etc.

[0917] 3. The server stores the generated policy proposals for each user.

[0918] Step 5: Notification and display of policy proposals

[0919] 1. The server prepares to send the stored policy proposal to the corresponding user.

[0920] 2. The device displays a notification to the user saying, "New policy proposals available."

[0921] 3. The user clicks on the notification to view the details of the policy proposal.

[0922] 4. The device displays details of the policy proposal to the user, providing a convenient UI.

[0923] Step 6: Gather feedback

[0924] 1. Users view the policy proposal and enter their opinions and thoughts in the feedback section.

[0925] 2. The user submits feedback.

[0926] 3. The device sends the feedback data to the server.

[0927] 4. The server stores the received feedback data in a database.

[0928] Step 7: Analyze and incorporate feedback

[0929] 1. The server analyzes the feedback data and updates the AI ​​model.

[0930] 2. The server stores the analysis results so that the user's feedback can be reflected in the next policy proposal.

[0931] 3. The server generates a report that provides the user feedback results to government officials.

[0932] Example 1

[0933] 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."

[0934] The current policy proposal system has difficulty in fully reflecting the values ​​and needs of each citizen, resulting in problems with proposed policies that do not adequately address individual citizens. Another issue is that collected feedback is not adequately reflected in subsequent proposals, resulting in a lack of improvement in the quality of policy proposals. Furthermore, there is also the problem that generated policy proposals are not effectively provided to government agencies.

[0935] 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.

[0936] In this invention, the server includes a means for users to register with the system, a means for collecting basic information and questionnaire responses from users, a means for storing the collected information in a database, a means for analyzing the stored information using a machine learning algorithm to identify users' values ​​and needs, a means for generating policy proposals based on the identified values ​​and needs, a means for notifying and displaying the generated policy proposals to users, a means for collecting feedback from users, a means for analyzing the collected feedback and updating the generative AI model to reflect the feedback in the next proposal, and a means for providing the generated policy proposals to government agencies. This enables highly accurate policy proposals that are in line with individual users' values ​​and needs, and the quality of policy proposals is improved by continuously incorporating feedback. Furthermore, by effectively providing the generated policy proposals to government agencies, they can contribute to actual policy formation.

[0937] "Means for Users to Register with the System" refers to the process and interface through which a User can access the System and enter the required basic information to create an account.

[0938] "Means for collecting basic information and questionnaire responses from users" refers to the process or mechanism for presenting questions to users and collecting their responses along with their attribute information.

[0939] "Means for storing collected information in a database" refers to a database management system and related operations for persistently storing basic information and survey responses obtained from users.

[0940] "Means of analyzing stored information using machine learning algorithms to identify users' values ​​and needs" refers to machine learning technology and its execution environment for analyzing collected data and clarifying individual users' characteristics and requirements.

[0941] "Means for generating policy proposals based on identified values ​​and needs" refers to processes or algorithms that formulate optimal policies for users based on the results of analysis and automatically generate proposals.

[0942] "Means for notifying and displaying the generated policy proposal to the user" refers to a notification system and display interface for notifying the user's terminal of the generated policy proposal and allowing the user to visually confirm it.

[0943] "Means for collecting feedback from users" refers to the process or interface through which users can input their opinions and thoughts about policy proposals and receive them into the system.

[0944] "Means for analyzing collected feedback and updating the generative AI model to reflect it in the next proposal" refers to the process and techniques for analyzing feedback provided by users and retraining the machine learning model as needed to improve the accuracy of the next policy proposal.

[0945] "Means for providing generated policy proposals to government agencies" refers to the processes and mechanisms for officially transmitting policy proposals created by the system to government agencies and utilizing them in the policy-making process.

[0946] This invention is a system for making policy proposals based on users' values ​​and needs. The system consists of the following processes: user registration, data collection, data analysis, policy proposal generation, notification, and feedback collection. A specific embodiment of this system is described below.

[0947] User Registration

[0948] First, the user accesses the system via the Internet and uses a web browser to access the registration screen. The registration screen displays a form where basic information (name, age, occupation, area of ​​residence, etc.) is entered. When the user enters the information and presses the "Submit" button, the information is sent to the server and stored in a database. This database uses a common database management system such as MySQL or PostgreSQL.

[0949] Polyseasonal Bayesian Data Collection

[0950] The server automatically generates survey notification emails to users at regular intervals. These notifications include questions about social issues, taxes, welfare systems, etc. The notification emails are sent via an SMTP server. When a user clicks on the link in the email and accesses the survey page, the page is displayed on the device. When the user answers the survey and presses the "Submit" button, the answers are sent to the server and stored in a database.

[0951] Data analysis and policy proposal generation

[0952] The server inputs the collected basic information and survey responses into a machine learning algorithm. The analysis is performed using Python and machine learning libraries such as TensorFlow and Scikit-learn. This allows the user's values ​​and needs to be identified using clustering and regression analysis techniques. The Python script then generates optimal policy proposals based on the analysis results and stores them in a database.

[0953] Notification and display of policy proposals

[0954] The generated policy proposal is then sent back to the user's device from the server. The notification email includes a link to view the details of the proposal. The user can click the link to access the policy proposal details page and view the details. This page provides an interface that visually displays the proposal contents.

[0955] Gathering and implementing feedback

[0956] Users provide feedback on policy proposals, including their opinions and thoughts. Feedback is sent via an input form on the details page. The feedback sent from the device is received by the server and stored in a database. The server then analyzes the feedback. This analysis uses text analysis techniques. The machine learning model is retrained based on the analysis results, improving the accuracy of the next policy proposal.

[0957] The generated policy proposals are automatically provided to government agencies, with the hope that they will be utilized in actual policy formation.

[0958] Specific examples

[0959] Scenario: Welfare policy proposal for the elderly

[0960] 1. An elderly user registers in the system and enters basic information (e.g., age 75, retired, living alone).

[0961] 2. Users fill out a survey and provide information about their health issues and financial situation.

[0962] 3. The server analyzes this information and identifies characteristics of the user, such as whether they have a low income or health problems.

[0963] 4. The server generates policy proposals tailored to the user, such as medical expense subsidy systems for the elderly.

[0964] 5. The user reviews the policy proposals generated on the device and provides feedback such as "very helpful."

[0965] 6. The server collects feedback, updates the AI ​​model, and provides a policy proposal report to government agencies.

[0966] Prompt Sentence Examples

[0967] "Generate policy proposals for a medical expense subsidy system for the elderly based on basic information and survey responses."

[0968] In this way, the system can provide policy proposals tailored to the individual needs of each user, and through feedback functions, the quality of the policy proposals can be continuously improved.

[0969] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0970] Step 1: User Registration

[0971] A user accesses the system's URL using a web browser. The user enters basic information (such as name, age, occupation, and area of ​​residence) on the registration screen. The entered basic information is sent from the terminal to the server when the user presses the "Submit" button. The server receives the sent basic information and saves it in a database. This stores the user's basic information in the database and makes it available for future processing.

[0972] Input: Basic information entered by the user

[0973] Data calculation: Send input data to the server and save it in the database

[0974] Output: Basic user information stored in the database

[0975] Step 2: Polyseasonal Bayesian data collection

[0976] The server periodically generates and sends survey notification emails to users. These emails contain a URL for a survey containing questions about social issues, taxes, welfare systems, etc. When a user clicks on the link in the email, they access the survey page. The user answers the survey using their device and presses the "Submit" button, which sends the answers from the device to the server. The server receives the answers and stores them in a database.

[0977] Input: Server-generated survey notification email

[0978] Data calculation: Sending user answers to the server and storing them in a database

[0979] Output: Survey responses stored in a database

[0980] Step 3: Data analysis and policy proposal generation

[0981] The server runs a machine learning algorithm to analyze the collected basic information and survey responses. The analysis is performed using Python and libraries such as TensorFlow and Scikit-learn. The server reads the user's basic information and survey responses from the database and inputs them into a machine learning model. The algorithm performs clustering and regression analysis to identify the user's values ​​and needs. Based on the analysis results, optimal policy proposals are generated. These proposals are then saved back to the database.

[0982] Input: User basic information and survey responses stored in the database

[0983] Data Computing: Analyzing data and generating policy recommendations using machine learning algorithms

[0984] Output: Generated policy proposals

[0985] Step 4: Notification and presentation of policy proposals

[0986] The generated policy proposal is notified to the user's device by the server. The server generates a policy proposal notification email and sends it to the user. The notification email contains a link to view the details of the proposal. When the user clicks the link, they can access the policy proposal details page. The device displays this page, allowing the user to visually confirm the proposal contents.

[0987] Input: Generated policy proposals

[0988] Data calculation: Generate and send policy proposal notification emails

[0989] Output: Policy proposal details page displayed on the user's device

[0990] Step 5: Gather and incorporate feedback

[0991] Users provide their opinions and thoughts on policy proposals as feedback through an input form on the details page. When the user presses the "Submit" button, the feedback is sent from the device to the server. The server then stores the received feedback in a database. The server then analyzes it and uses text analysis techniques to analyze the feedback content. Based on the analysis results, the machine learning model is retrained. This improves the accuracy of the next policy proposal.

[0992] Input: User feedback

[0993] Data calculation: storing and analyzing feedback in a database

[0994] Output: Improved policy proposals for the next round

[0995] Step 6: Submitting policy proposals to government agencies

[0996] Finally, the generated policy proposals are provided to government agencies. The server generates a policy proposal report and automatically sends it to the appropriate government agency. This report contains detailed policy proposals based on the analysis results, which will help the policy proposals to be used in actual policy formation.

[0997] Input: Generated policy proposals

[0998] Data Computing: Generate and send policy proposal reports

[0999] Output: Policy proposals provided to government agencies

[1000] (Application example 1)

[1001] 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."

[1002] Current policy proposal systems are designed for general users and are unable to fully reflect the specific needs of elderly people and users with physical limitations. Furthermore, they lack the functionality to provide appropriate assistance services in real time, especially for users using autonomous vehicles. This has led to problems such as delays and inappropriate recommendations and guidance for welfare support and medical services needed by elderly people and users with physical limitations.

[1003] 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.

[1004] In this invention, the server includes means for users to register with the system, means for collecting basic information and questionnaire responses from users, means for saving the collected information in a database, means for analyzing the saved information and identifying the user's values ​​and needs, means for generating policy proposals based on the identified values ​​and needs, means for notifying and displaying the generated policy proposals to the user, means for collecting feedback from the user, means for analyzing the collected feedback and reflecting it in the next proposal, and means for analyzing usage information and health status data collected by the autonomous mobile device and proposing optimal welfare support services to the user while riding. This makes it possible to provide appropriate welfare support services in real time to elderly and physically limited users, and to create an environment in which users can use the autonomous mobile device with peace of mind.

[1005] An "autonomous vehicle" is a means of transportation that uses artificial intelligence and sensor technology to operate automatically and travel to a destination without human intervention.

[1006] "Usage information" is data generated when a user uses an autonomous driving device, and includes information such as travel route, boarding and disembarking times, and riding frequency.

[1007] "Health condition data" refers to information relating to the user's health, and includes biometric data such as blood pressure, heart rate, and body temperature, as well as health status evaluation results based on questionnaire results and the like.

[1008] "Welfare support services" are support measures and services provided to users with specific needs, such as the elderly and people with disabilities, and include medical assistance, transportation assistance, and lifestyle support.

[1009] "Analysis" is the process of applying machine learning algorithms and statistical methods to analyze information based on collected data to identify specific values ​​and needs.

[1010] "Policy proposals" are proposals that present optimal policies and support measures to users based on the analysis results, and include information on specific measures and services.

[1011] "Feedback" refers to information such as opinions, impressions, and evaluations provided by users, and is useful for improving the system and increasing the accuracy of future policy proposals.

[1012] This invention applies an AI-based policy proposal system to an autonomous driving device to provide optimal welfare support services in real time to elderly people and users with physical limitations. The system includes the following main components:

[1013] 1. User Registration

[1014] The server provides a means for users to register with the system through the terminal of the autonomous driving device. The user can then enter their basic information and register with the system. The user's basic information includes age, gender, health condition, etc.

[1015] 2. Data Collection

[1016] The server uses the terminal to collect basic information and questionnaire responses from users, including usage information, health status data, and questionnaires about their living conditions. The data is collected periodically, sent to the server, and stored in a database.

[1017] 3. Data analysis and policy proposal generation

[1018] The server analyzes the collected data using machine learning algorithms. Specifically, it uses platforms such as NVIDIA Jetson to identify the user's values ​​and needs. Based on these values ​​and needs, it generates optimal welfare support services and policies.

[1019] 4. Notification and Display of Policy Proposals

[1020] The server notifies the autonomous driving device of the generated policy proposals. The device then displays the proposals visually and audibly to the user through a display and audio guide. It is also possible to link with smart glasses or a head-mounted display to display the proposals in real time.

[1021] 5. Gather and incorporate feedback

[1022] The server collects the feedback provided by users and incorporates this information into the next policy proposal, allowing for continuous improvement of the quality of the proposal.

[1023] Examples:

[1024] Elderly person A (75 years old) rides an autonomous driving device and answers a questionnaire about his / her health condition and lifestyle through a linked application. The server analyzes the collected data in real time and suggests "priority access to medical institutions" and "low-cost transportation support plans." This allows Elderly Person A to receive appropriate support services based on his / her health condition.

[1025] Example prompt sentence:

[1026] "Data analysis prompt to propose a medical assistance system for elderly users: Generate appropriate policy proposals based on information such as age, living situation, health status, and facilities (medical institutions, public services) that users frequently access. Example: 75 years old, living alone, with chronic illnesses, and needing to visit hospitals frequently."

[1027] This system enables elderly people and people with physical limitations who use autonomous vehicles to receive optimal welfare support services in real time. The generated policy proposals are also customized to the needs of each user, providing optimal support for each user.

[1028] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1029] Step 1:

[1030] The server provides a means for users to register with the system. Users enter basic information such as age, gender, and health status through the terminal of the autonomous driving device. The server stores this basic information in a database.

[1031] Input: User's basic information (age, gender, health status, etc.)

[1032] Output: Basic information stored in the database

[1033] Specific operation: The user enters information into the registration screen displayed on the terminal and sends it to the server, which then stores the received information in a database.

[1034] Step 2:

[1035] The server periodically sends questionnaires to users to collect usage information and health status data. Users respond to the questionnaires and send the data from their terminals to the server.

[1036] Input: Survey responses, usage information (route, boarding and disembarking times, etc.), health status data (blood pressure, heart rate, etc.)

[1037] Output: Survey responses, usage information, and health status data stored in a database

[1038] Specific operation: A questionnaire is presented to the user via the device's display or audio guide. The user answers the questionnaire and sends the data to the server.

[1039] Step 3:

[1040] The server analyzes the collected data using machine learning algorithms (e.g., NVIDIA Jetson), processes the data, and identifies the user's values ​​and needs.

[1041] Input: Basic information, survey responses, usage information, health status data

[1042] Output: User values ​​and needs

[1043] How it works: The server retrieves the collected data from the database, inputs it into a machine learning algorithm, and analyzes it. From the analysis results, the user's specific values ​​and needs are extracted.

[1044] Step 4:

[1045] The server generates optimal welfare support services and policy proposals based on the analysis results.

[1046] Input: User values ​​and needs

[1047] Output: Generated policy proposals

[1048] Specific operation: Based on the analysis results, the server uses a specific algorithm to generate optimal policy proposals for the user.

[1049] Step 5:

[1050] The server notifies the device of the generated policy proposals and displays them to the user. The device then provides the proposals to the user using a display or audio guide. The device also works with smart glasses or a head-mounted display to display the proposals in real time.

[1051] Input: Generated policy proposals

[1052] Output: Policy proposals displayed to the user

[1053] Specific operation: Policy proposals are displayed on the device screen and explained via audio guidance. When using smart glasses or a head-mounted display, the proposals are displayed in real time.

[1054] Step 6:

[1055] Users provide feedback on the presented policy proposals through their terminals, and the server collects the feedback and stores it in a database.

[1056] Input: User feedback

[1057] Output: Feedback stored in a database

[1058] Specific operation: The user can easily input feedback through the terminal interface, and the server receives the feedback and stores it in a database.

[1059] Step 7:

[1060] The server analyzes the collected feedback and reflects it in the next policy proposal.

[1061] Input: Feedback stored in the database

[1062] Output: Improved policy recommendations

[1063] Specific operation: The server analyzes the feedback and updates the machine learning model based on the results. The analysis results are reflected in the next policy proposal to make it more accurate.

[1064] 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.

[1065] This invention is a policy proposal system that uses AI and an emotion engine to propose policies that take into account the emotional state as well as the values ​​and needs of each individual user. The system includes the following main means and processes:

[1066] User Registration

[1067] First, a user accesses the system and creates an account, which allows the user to enter their basic information into the system, which is then sent to the server and stored in the database.

[1068] Polyseasonal Bayesian Data Collection

[1069] The server periodically sends users survey notifications, which include questions about social issues, taxes, welfare systems, etc. Users answer the surveys through their devices, and the responses are sent to the server and stored.

[1070] Data analysis and emotion recognition

[1071] The server uses machine learning algorithms and an emotion engine to analyze the collected user information and survey responses. As a result of the analysis, each user's values ​​and needs are identified. At the same time, the emotion engine evaluates the user's emotional state based on their feedback and interactions.

[1072] Generate policy proposals

[1073] The server generates policy proposals based on the user's values, needs, and assessed emotional state, ensuring that the proposed policies are in line with the user's actual emotions.

[1074] Notification and display of policy proposals

[1075] The generated policy proposal is sent from the server to the user's device, where it is displayed to the user as a notification and provides an interface with detailed visual information. The interface's display method is also adjusted according to the user's emotional state.

[1076] Gathering and implementing feedback

[1077] Users provide their opinions and thoughts on policy proposals as feedback to the system. The feedback is sent from the device to the server and analyzed. As a result, the server can reflect the user's feedback and emotional state in the next policy proposal.

[1078] Specific examples

[1079] Scenario: Welfare policy proposal for the elderly

[1080] 1. An elderly user registers with the system and enters basic information (e.g., age 75, retired, living alone).

[1081] 2. Users use the device to fill out a questionnaire and answer questions about their health issues and financial situation.

[1082] 3. The server analyzes the user's basic information and questionnaire responses to determine the user's characteristics, such as "low income" or "health problems."

[1083] 4. The emotion engine evaluates the emotional state from the user's feedback and interactions and sends it to the server.

[1084] 5. The server generates policy proposals tailored to the user, such as medical subsidy programs for the elderly, and adjusts the proposals to take into account the user's emotional state.

[1085] 6. The terminal displays the generated policy proposal to the user, who can then check the details. Based on the emotion engine, the display method is optimized to the user's emotional state.

[1086] 7. The user provides feedback on the suggestion, such as "very helpful."

[1087] 8. The server collects feedback, updates the AI ​​model and emotion engine with the latest information, and provides a policy proposal report to government officials.

[1088] This system will propose policies that take into account the needs and emotional state of each user, enabling policy formation that reflects the diverse opinions and emotions of citizens. Furthermore, through a feedback function, the quality of policy proposals can be continuously improved, promoting the realization of democracy and citizen participation.

[1089] The processing flow will be explained below.

[1090] Step 1: User registers with the system

[1091] 1. A user visits a web page or app and selects "Create a new account."

[1092] 2. The device displays a registration form to the user, asking them to enter basic information such as their name, address, age, occupation, and email address.

[1093] 3. The user enters the required information and clicks "Submit."

[1094] 4. The terminal sends the entered data to the server.

[1095] 5. The server stores the received basic information in a database.

[1096] Step 2: Send out the survey and collect responses

[1097] 1. The server periodically generates and prepares to send surveys to registered users.

[1098] 2. The device displays a notification to the user saying "There is a new survey."

[1099] 3. The user clicks on the notification and opens the survey page.

[1100] 4. The terminal displays the survey form and the user answers the questions.

[1101] 5. The user answers the questions and clicks "Submit."

[1102] 6. The device sends the user's response data to the server.

[1103] 7. The server stores the received response data in a database.

[1104] Step 3: Data analysis and emotion recognition

[1105] 1. The server reads the user's basic information and survey responses from the database.

[1106] 2. The server applies machine learning algorithms to analyze each user's values ​​and needs.

[1107] 3. The server updates each user's profile based on the analysis results.

[1108] 4. The server uses an emotion engine to evaluate the emotional state from the user's feedback and interactions.

[1109] 5. The server adds the emotional state assessment to the profile.

[1110] Step 4: Generate policy proposals

[1111] 1. The server starts generating policy suggestions based on the user's profile and emotional state.

[1112] 2. The policy proposals generated by the server include specific policy explanations, expected effects, advantages and disadvantages, etc.

[1113] 3. The server stores the generated policy proposals for each user.

[1114] Step 5: Notification and display of policy proposals

[1115] 1. The server prepares to send the stored policy proposal to the corresponding user.

[1116] 2. The device displays a notification to the user saying, "New policy proposals available."

[1117] 3. The user clicks on the notification to view the details of the policy proposal.

[1118] 4. The device displays details of policy proposals to the user and provides a convenient UI that adapts to their emotional state.

[1119] Step 6: Gather feedback

[1120] 1. Users view the policy proposal and enter their opinions and thoughts in the feedback section.

[1121] 2. The user submits feedback.

[1122] 3. The device sends the feedback data to the server.

[1123] 4. The server stores the received feedback data in a database.

[1124] 5. The server uses the emotion engine to analyze the feedback content.

[1125] Step 7: Analyze and incorporate feedback

[1126] 1. The server analyzes the feedback data and updates the AI ​​model and emotion engine.

[1127] 2. The server stores the analysis results so that the next policy proposal will reflect the user's feedback and emotional state.

[1128] 3. The server generates a report that provides the user feedback results to government officials.

[1129] Examples:

[1130] Scenario: Welfare policy proposal for the elderly

[1131] 1. An elderly user registers with the system and enters basic information (e.g., age 75, retired, living alone).

[1132] 2. The user uses the device to answer a questionnaire and enter their opinions about health issues and financial situations.

[1133] 3. The server stores the user's basic information and survey response data in a database.

[1134] 4. The server uses machine learning algorithms and an emotion engine to analyze the user's values, needs, and emotional state.

[1135] 5. Based on the analysis results, the server generates proposals for medical subsidy programs for the elderly, adjusting the content of the proposals to take into account the emotional state.

[1136] 6. The device notifies the user of the generated policy proposal and visually displays the details. Based on the emotion engine, the display method is optimized to the user's emotional state.

[1137] 7. The user reviews the suggestion and provides feedback that it is "very helpful."

[1138] 8. The server collects feedback and updates the AI ​​model and emotion engine with the latest information.

[1139] 9. The server provides policy proposal reports to government officials to help them formulate policies.

[1140] In this way, policy proposals that take into account the user's emotional state can be more personalized, reflecting the diverse opinions and emotions of citizens, and continuously improving the quality of policy proposals through feedback and sentiment analysis.

[1141] Example 2

[1142] 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."

[1143] Conventional policy proposal systems make proposals based only on the user's basic information and questionnaire responses, which means they are inadequately able to adapt to fluctuations in an individual user's emotional state and feedback. As a result, it is difficult to generate policy proposals that are appropriate for the user's actual interests and emotional state. Furthermore, there is a lack of a method to maintain consistency by incorporating feedback into the next proposal.

[1144] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1145] In this invention, the server includes means for users to register with the system, means for collecting basic information and questionnaire responses from users, means for storing the collected information in a database, means for analyzing the stored information using a machine learning algorithm to identify the user's values ​​and needs, means for evaluating the user's emotional state using an emotion recognition engine, means for generating policy proposals using a generative AI model based on the identified values ​​and needs and the evaluated emotional state, means for notifying and displaying the generated policy proposals to the user, and means for collecting feedback from the user and reflecting the feedback in the next policy proposal, thereby enabling personalized policy proposals based on the user's values ​​and emotional state.

[1146] "User" refers to an individual person who uses the system.

[1147] "System" refers to an environment that includes a set of software and hardware for communicating information between users and a server and generating policy proposals.

[1148] "Basic information" refers to personal information such as the user's name, age, gender, and address.

[1149] "Survey responses" refer to responses to questions asked by users regarding social issues, taxes, welfare systems, etc.

[1150] "Database" refers to a system that organizes and stores collected data such as basic user information and questionnaire responses.

[1151] "Machine learning algorithms" refer to techniques that analyze large amounts of data for patterns and trends, and specifically include technologies such as TensorFlow.

[1152] "Emotion recognition engine" refers to a system that assesses the emotional state of a user from their feedback and interactions. Examples include the IBM Watson Tone Analyzer.

[1153] "Generative AI models" refer to artificial intelligence algorithms that generate text or suggestions based on collected and analyzed data, including GPT-4.

[1154] "Policy proposals" refer to specific policy proposals generated based on the user's basic information, survey responses, and emotional state.

[1155] "Notification" refers to the system's ability to notify users of new information or offers.

[1156] "Display" refers to the user being able to visually confirm the details of information and suggestions through the system.

[1157] "Feedback" refers to the user providing the system with their opinions and thoughts about the proposal.

[1158] This invention is a policy proposal system that uses AI and an emotion engine to propose policies that take into account the emotional state of each user, along with their values ​​and needs. Specific means for implementing this system and its operation are described below.

[1159] User Registration

[1160] First, a user accesses the system using a web browser or smartphone app and creates a new account. The user enters basic information such as name, age, gender, and address. The basic information entered from the device is sent to the server using the HTTPS protocol. The server then stores the received basic information in a database (e.g., MongoDB, MySQL).

[1161] Polyseasonal Bayesian Data Collection

[1162] Next, the server uses a scheduling service (e.g., Cron job) to periodically send survey notifications to users. The surveys include questions about social issues, taxes, welfare systems, etc. Users answer the surveys using their devices, and the responses are sent from the devices to the server. The server then stores the survey response data in a database.

[1163] Data analysis and emotion recognition

[1164] The server uses a machine learning algorithm (e.g., TensorFlow) to analyze the user's basic information and survey responses. As a result of the analysis, each user's values ​​and needs are identified. At the same time, the server uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to evaluate the user's emotional state from their feedback and interactions. The analysis results are stored in a database as the user's individual profile.

[1165] Generate policy proposals

[1166] The server then uses a generative AI model (e.g., GPT-4) to generate policy proposals based on the analysis results and the user's emotional state. These proposals are tailored to the user's values ​​and needs, and are adjusted according to the user's emotional state.

[1167] Notification and display of policy proposals

[1168] The generated policy proposals are sent from the server to the user's device. The device notifies the user of the received policy proposals and displays details. The display method of the device's interface is also adjusted based on the user's emotional state. For example, if the emotional state is determined to be "stressed," the interface color scheme and font style are changed to something more relaxing.

[1169] Gathering and implementing feedback

[1170] Finally, the user provides feedback to the system, including their opinions and thoughts on the policy proposals. This feedback is sent from the device to the server, where it is analyzed and reflected in the next policy proposal. This allows the system to continually make proposals that incorporate the user's latest needs and emotional state.

[1171] Specific examples

[1172] Scenario: Welfare policy proposal for the elderly

[1173] 1. An elderly user registers in the system and enters basic information (e.g., age 75, retired, living alone).

[1174] 2. Users use the device to fill out a questionnaire and answer questions about their health issues and financial situation.

[1175] 3. The server analyzes the user's basic information and questionnaire responses to determine the user's characteristics, such as "low income" or "health problems."

[1176] 4. The emotion engine evaluates the emotional state from the user's feedback and interactions and sends it to the server.

[1177] 5. The server generates tailored policy proposals for the user, such as medical subsidy programs for the elderly, and the proposals are adjusted based on the user's emotional state.

[1178] 6. The terminal displays the generated policy proposal to the user, who can then check the details. Based on the emotion engine, the display method is optimized to the user's emotional state.

[1179] 7. The user provides feedback on the suggestion, such as "very helpful."

[1180] 8. The server collects feedback and updates the AI ​​model and emotion engine with the latest information.

[1181] Prompt Sentence Examples

[1182] "Please propose a welfare policy suitable for seniors who have retired at age 75. Consider the following conditions: low income, health problems."

[1183] "Use AI and emotion engines to generate policy recommendations that take into account the user's values ​​and emotional state."

[1184] This system realizes personalized policy proposals that take into account the needs and emotional state of each user, enabling policy formation that reflects the diverse opinions and emotions of citizens. Furthermore, through a feedback function, the quality of policy proposals can be continuously improved, promoting the realization of democracy and citizen participation.

[1185] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1186] Step 1: User Registration

[1187] Users access the system using a web browser or smartphone app and create a new account.

[1188] Input: User's basic information (name, age, gender, address, etc.)

[1189] Output: Basic user information stored in the database

[1190] How it works: A user fills out a form with basic information and clicks the submit button. The device sends the information to the server via HTTPS. The server validates the received information and stores it in a database.

[1191] Step 2: Polyseasonal Bayesian data collection

[1192] The server periodically sends survey notifications to users.

[1193] Input: Survey data, user basic information

[1194] Output: Survey responses stored in a database

[1195] How it works: The server uses a scheduling service to send a survey notification to the user's device at a specific time. The user receives the notification and opens the survey screen. They answer the survey, and the device sends the response data to the server. The server stores the received response data in a database.

[1196] Step 3: Data analysis and emotion recognition

[1197] The server uses machine learning algorithms to analyze the user's basic information and questionnaire responses, and uses an emotion engine to evaluate their emotional state.

[1198] Input: User basic information, survey responses, feedback

[1199] Output: Analyzed user values, needs and emotional state

[1200] How it works: The server uses TensorFlow to analyze user data. As a result of the analysis, each user's values ​​and needs are identified. At the same time, an emotion recognition engine (e.g., emotion analysis API) evaluates the user's emotional state based on their feedback and interaction data. The evaluation results are saved as a personalized profile for the user.

[1201] Step 4: Generate policy proposals

[1202] The server generates policy proposals using a generative AI model based on the analysis results and emotional state.

[1203] Input: Analyzed user values, needs, and emotional state

[1204] Output: Generated policy proposals

[1205] How it works: The server takes the analysis results and the user's emotional state as input and uses a generative AI model (e.g., GPT-4) to generate policy proposals. The proposals include specific policy content and are adjusted according to the user's emotional state.

[1206] Step 5: Notification and presentation of policy proposals

[1207] The server sends the generated policy proposal to the user's terminal, which notifies the user of the policy proposal and displays the details.

[1208] Input: Generated policy proposals

[1209] Output: Policy proposals communicated and displayed to the user

[1210] How it works: The server converts the generated policy proposal into JSON format and sends it to the user's device. The device then notifies the user of the new policy proposal via push notifications or in-app notifications. The proposal details are displayed on a details screen, and the interface color scheme and font style are adjusted according to the user's emotional state.

[1211] Step 6: Gather and incorporate feedback

[1212] Users provide feedback on policy proposals, including their opinions and thoughts. The server collects the feedback and reflects it in the next policy proposal.

[1213] Input: User feedback

[1214] Output: Updated user profile, feedback to be reflected in next proposal

[1215] How it works: A user enters their opinions and thoughts into the feedback form on the policy proposal details screen and clicks the submit button. The device sends the feedback to the server. The server analyzes the received feedback and updates the user profile. This updated information is taken into account the next time a policy proposal is generated.

[1216] Through these steps, the system realizes personalized policy proposals based on the user's values ​​and emotional state.

[1217] (Application example 2)

[1218] 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."

[1219] Existing policy and content proposal systems can analyze users' values ​​and needs, but they struggle to make proposals that take into account the user's emotional state. This can lead to lower acceptability and satisfaction. Furthermore, there is a lack of effective ways to incorporate user feedback into future proposals, making it difficult to improve the quality of proposals.

[1220] 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.

[1221] In this invention, the server includes: a means for users to register with the system; a means for collecting basic information and questionnaire responses from users; a means for storing the collected information in a database; a means for analyzing the stored information to identify the user's values ​​and needs; a means for generating policy or content proposals based on the identified values ​​and needs and the evaluated emotional state; a means for notifying and displaying the generated policy or content proposals to the user; a means for adjusting the display method based on the user's feedback and emotional state; a means for collecting user feedback; and a means for analyzing the collected feedback and emotional state data and reflecting it in subsequent proposals. This enables policy and content proposals to be tailored to the user's emotional state, thereby improving the acceptability and satisfaction of the proposals. Furthermore, effectively reflecting feedback in subsequent proposals also improves the quality of the proposals.

[1222] A "user" is an individual or group that uses the system and provides data such as basic information and questionnaire responses.

[1223] The "system" is a set of mechanisms for generating, notifying, and displaying policy or content suggestions based on the user's values, needs, and emotional state, and for collecting feedback to be reflected in future suggestions.

[1224] "Policy proposals" are the contents of plans and measures provided by governments and public institutions that are generated based on the user's values, needs, and emotional state.

[1225] "Content suggestions" are entertainment and informational content such as movies, music, and news articles that are generated based on the user's values, needs, and emotional state.

[1226] "Emotional state" refers to the psychological state or feeling that is assessed through user feedback and interaction.

[1227] A "database" is an information collection that allows the system to store and manage collected basic information, questionnaire responses, feedback, etc. from users.

[1228] "Feedback" refers to opinions and thoughts provided by users regarding policy proposals or content proposals, and is data that will be reflected in the next proposal.

[1229] "Machine learning algorithms" refer to mathematical methods and techniques for analyzing large amounts of data and finding patterns and trends.

[1230] An "emotion recognition engine" refers to software or hardware that analyzes and evaluates a user's emotional state from text, speech, or other input.

[1231] "Interface" refers to the screen or operating system through which a user views and provides feedback on a policy or content proposal.

[1232] This invention is a system that uses AI and an emotion engine to make policy and content proposals that take into account the user's values, needs, and emotional state. Specific embodiments for implementing this invention are described below.

[1233] First, users access the system and create an account. They enter the necessary basic information, which is then sent to the server and stored in a database. They also periodically answer surveys via their devices. The surveys include questions about social issues, content interests, emotional states, and more.

[1234] The server analyzes the basic information and survey responses collected from the user using machine learning algorithms and emotion recognition engines. Known machine learning libraries (e.g., scikit-learn) and emotion recognition models (e.g., emotion recognition models from the transformers library) are used. The analysis results identify the user's values, needs, and emotional state.

[1235] The server then generates policy or content recommendations based on these analysis results, and the recommendations are tailored to reflect the user's emotional state. For example, if the user is in a "sad" emotional state, comforting content will be suggested.

[1236] The suggestions are sent to the device, and the user confirms them through the interface. The interface adjusts its display based on the user's emotional state. An emotion recognition engine evaluates the user's emotional state from their feedback and interactions, and the interface is optimized accordingly.

[1237] Users provide feedback on the suggestions. This feedback is sent to the server and stored in a database. The server analyzes the collected feedback and reflects it in the next suggestion. During this process, a generative AI model is used to create prompts to generate optimal suggestions.

[1238] For example, in the following example, in response to feedback such as "I was moved! It brought me to tears!", the emotion recognition model detects the emotion "sad." Based on this, other inspiring movies and content are suggested.

[1239] Example prompt sentence:

[1240] User feedback: "I was moved! It brought me to tears!"

[1241] Sentiment analysis result: "Sad"

[1242] Suggested content list:

[1243] 1. "In This Corner of the World" - A moving story set in Hiroshima during the war

[1244] 2. "The Wind Rises" - A story of an airplane designer's dreams and love

[1245] As described above, the present invention provides a specific method for realizing a system that makes suggestions based on the user's values, needs, and emotional state, thereby increasing user satisfaction.

[1246] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1247] Step 1: A user registers with the system.

[1248] Input: User's basic information (name, age, gender, etc.)

[1249] Process: A user accesses the system from a terminal, creates an account, and enters basic information, which is then sent to the server.

[1250] Output: The server stores the collected basic information in a database.

[1251] Step 2: Collect survey responses.

[1252] Input: User survey responses (social issues, content interests, emotional state, etc.)

[1253] Processing: The server periodically sends a survey notification to the user. The user answers the survey through their terminal and sends the results to the server.

[1254] Output: The server stores the collected survey responses in a database.

[1255] Step 3: Data analysis.

[1256] Input: User basic information stored in the database, survey responses, and emotional feedback

[1257] Processing: The server analyzes the data using machine learning algorithms (scikit-learn) to identify the user's values ​​and needs, and analyzes the user's emotional state using an emotion engine (transformers library).

[1258] Output: Identified user values, needs, and emotional state.

[1259] Step 4: Generate policy or content proposals.

[1260] Input: Identified values, needs, and emotional states

[1261] Processing: The server uses the generative AI model to generate optimized policy or content recommendations based on the user's values ​​and emotional state. For example, if the emotional state is rated as "sad," inspirational movies or content will be suggested.

[1262] Output: Generated policy or content proposals

[1263] Step 5: Notification and display of proposals.

[1264] Input: Generated policy proposals or content proposals, emotional states

[1265] Processing: The server sends the generated suggestions to the user's device. The device notifies the user of the suggestions and displays details through a display interface. Based on the emotion engine, the display method is optimized according to the user's emotional state.

[1266] Output: An interface for the user to visually confirm the proposal

[1267] Step 6: Gather feedback.

[1268] Input: User feedback

[1269] Processing: The user provides their opinions and feedback on the proposals through their device. The feedback is sent to the server and stored in a database.

[1270] Output: Collected feedback

[1271] Step 7: Analyze the feedback and incorporate it into your next proposal.

[1272] Input: collected feedback, emotional state data

[1273] Processing: The server analyzes the collected feedback and emotional state data and reflects it in the next suggestion. It also uses a generative AI model to create prompts to generate optimal suggestions.

[1274] Output: Improved next policy or content proposal

[1275] Through each of the above steps, the system can make policy and content suggestions that are in line with the user's values, needs, and emotional state, thereby increasing the acceptability and satisfaction of the suggestions.

[1276] 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.

[1277] 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.

[1278] 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.

[1279] [Fourth embodiment]

[1280] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1281] 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.

[1282] 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).

[1283] 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.

[1284] 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.

[1285] 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).

[1286] 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.

[1287] 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.

[1288] 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.

[1289] 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.

[1290] 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.

[1291] 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.

[1292] 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."

[1293] This invention is a policy proposal system using AI that proposes policies based on the values ​​and needs of each user. The system includes the following main means and processes:

[1294] User Registration

[1295] First, a user accesses the system and creates an account, which allows the user to enter their basic information into the system, which is then sent to the server and stored in the database.

[1296] Polyseasonal Bayesian Data Collection

[1297] The server periodically sends users survey notifications, which include questions about social issues, taxes, welfare systems, etc. Users answer the surveys through their devices, and the responses are sent to the server and stored.

[1298] Data analysis and policy proposal generation

[1299] The server uses machine learning algorithms to analyze the collected basic information and survey responses of users. As a result of the analysis, each user's values ​​and needs are identified. Based on these results, the server generates optimal policy proposals for the user.

[1300] Notification and display of policy proposals

[1301] The generated policy proposal is sent from the server to the user's device, where it is displayed to the user and provides an interface visually displaying the details of the policy proposal. The user can then review the proposal contents through this interface.

[1302] Gathering and implementing feedback

[1303] Users provide feedback to the system, including their opinions and thoughts on policy proposals. The feedback is sent from the device to the server and analyzed. As a result, the server can reflect the user's feedback in the next policy proposal.

[1304] Specific examples

[1305] Scenario: Welfare policy proposal for the elderly

[1306] 1. An elderly user registers with the system and enters basic information (e.g., age 75, retired, living alone).

[1307] 2. Users use the device to fill out a questionnaire and answer questions about their health issues and financial situation.

[1308] 3. The server analyzes the user's basic information and questionnaire responses to determine the user's characteristics, such as "low income" or "health problems."

[1309] 4. The server generates policy proposals tailored to the user, such as medical expense subsidy systems for the elderly.

[1310] 5. The terminal displays the generated policy proposal to the user, who then checks the details.

[1311] 6. The user provides feedback on the suggestion, such as "very helpful."

[1312] 7. The server collects feedback, updates the AI ​​model with the latest information, and provides a policy proposal report to government officials.

[1313] In this way, the system aims to realize democracy and promote citizen participation by making policy proposals that reflect the diverse opinions of citizens by making policy proposals that meet the needs of each individual user.The system also aims to continuously improve the quality of policy proposals through a feedback function.

[1314] The processing flow will be explained below.

[1315] Step 1: User registers with the system

[1316] 1. A user visits a web page or app and selects "Create a new account."

[1317] 2. The device displays a registration form to the user, asking them to enter basic information such as their name, address, age, occupation, and email address.

[1318] 3. The user enters the required information and clicks "Submit."

[1319] 4. The terminal sends the entered data to the server.

[1320] 5. The server stores the received basic information in a database.

[1321] Step 2: Send out the survey and collect responses

[1322] 1. The server periodically generates and prepares to send surveys to registered users.

[1323] 2. The device displays a notification to the user saying "There is a new survey."

[1324] 3. The user clicks on the notification and opens the survey page.

[1325] 4. The terminal displays the survey form and the user answers the questions.

[1326] 5. The user answers the questions and clicks "Submit."

[1327] 6. The device sends the user's response data to the server.

[1328] 7. The server stores the received response data in a database.

[1329] Step 3: Data analysis

[1330] 1. The server reads the user's basic information and survey responses from the database.

[1331] 2. The server applies machine learning algorithms to analyze each user's values ​​and needs.

[1332] 3. The server updates each user's profile based on the analysis results.

[1333] Step 4: Generate policy proposals

[1334] 1. The server begins generating policy proposals based on the user's profile.

[1335] 2. The policy proposals generated by the server include specific policy explanations, expected effects, advantages and disadvantages, etc.

[1336] 3. The server stores the generated policy proposals for each user.

[1337] Step 5: Notification and display of policy proposals

[1338] 1. The server prepares to send the stored policy proposal to the corresponding user.

[1339] 2. The device displays a notification to the user saying, "New policy proposals available."

[1340] 3. The user clicks on the notification to view the details of the policy proposal.

[1341] 4. The device displays details of the policy proposal to the user, providing a convenient UI.

[1342] Step 6: Gather feedback

[1343] 1. Users view the policy proposal and enter their opinions and thoughts in the feedback section.

[1344] 2. The user submits feedback.

[1345] 3. The device sends the feedback data to the server.

[1346] 4. The server stores the received feedback data in a database.

[1347] Step 7: Analyze and incorporate feedback

[1348] 1. The server analyzes the feedback data and updates the AI ​​model.

[1349] 2. The server stores the analysis results so that the user's feedback can be reflected in the next policy proposal.

[1350] 3. The server generates a report that provides the user feedback results to government officials.

[1351] Example 1

[1352] 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."

[1353] The current policy proposal system has difficulty in fully reflecting the values ​​and needs of each citizen, resulting in problems with proposed policies that do not adequately address individual citizens. Another issue is that collected feedback is not adequately reflected in subsequent proposals, resulting in a lack of improvement in the quality of policy proposals. Furthermore, there is also the problem that generated policy proposals are not effectively provided to government agencies.

[1354] 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.

[1355] In this invention, the server includes a means for users to register with the system, a means for collecting basic information and questionnaire responses from users, a means for storing the collected information in a database, a means for analyzing the stored information using a machine learning algorithm to identify users' values ​​and needs, a means for generating policy proposals based on the identified values ​​and needs, a means for notifying and displaying the generated policy proposals to users, a means for collecting feedback from users, a means for analyzing the collected feedback and updating the generative AI model to reflect the feedback in the next proposal, and a means for providing the generated policy proposals to government agencies. This enables highly accurate policy proposals that are in line with individual users' values ​​and needs, and the quality of policy proposals is improved by continuously incorporating feedback. Furthermore, by effectively providing the generated policy proposals to government agencies, they can contribute to actual policy formation.

[1356] "Means for Users to Register with the System" refers to the process and interface through which a User can access the System and enter the required basic information to create an account.

[1357] "Means for collecting basic information and questionnaire responses from users" refers to the process or mechanism for presenting questions to users and collecting their responses along with their attribute information.

[1358] "Means for storing collected information in a database" refers to a database management system and related operations for persistently storing basic information and survey responses obtained from users.

[1359] "Means of analyzing stored information using machine learning algorithms to identify users' values ​​and needs" refers to machine learning technology and its execution environment for analyzing collected data and clarifying individual users' characteristics and requirements.

[1360] "Means for generating policy proposals based on identified values ​​and needs" refers to processes or algorithms that formulate optimal policies for users based on the results of analysis and automatically generate proposals.

[1361] "Means for notifying and displaying the generated policy proposal to the user" refers to a notification system and display interface for notifying the user's terminal of the generated policy proposal and allowing the user to visually confirm it.

[1362] "Means for collecting feedback from users" refers to the process or interface through which users can input their opinions and thoughts about policy proposals and receive them into the system.

[1363] "Means for analyzing collected feedback and updating the generative AI model to reflect it in the next proposal" refers to the process and techniques for analyzing feedback provided by users and retraining the machine learning model as needed to improve the accuracy of the next policy proposal.

[1364] "Means for providing generated policy proposals to government agencies" refers to the processes and mechanisms for officially transmitting policy proposals created by the system to government agencies and utilizing them in the policy-making process.

[1365] This invention is a system for making policy proposals based on users' values ​​and needs. The system consists of the following processes: user registration, data collection, data analysis, policy proposal generation, notification, and feedback collection. A specific embodiment of this system is described below.

[1366] User Registration

[1367] First, the user accesses the system via the Internet and uses a web browser to access the registration screen. The registration screen displays a form where basic information (name, age, occupation, area of ​​residence, etc.) is entered. When the user enters the information and presses the "Submit" button, the information is sent to the server and stored in a database. This database uses a common database management system such as MySQL or PostgreSQL.

[1368] Polyseasonal Bayesian Data Collection

[1369] The server automatically generates survey notification emails to users at regular intervals. These notifications include questions about social issues, taxes, welfare systems, etc. The notification emails are sent via an SMTP server. When a user clicks on the link in the email and accesses the survey page, the page is displayed on the device. When the user answers the survey and presses the "Submit" button, the answers are sent to the server and stored in a database.

[1370] Data analysis and policy proposal generation

[1371] The server inputs the collected basic information and survey responses into a machine learning algorithm. The analysis is performed using Python and machine learning libraries such as TensorFlow and Scikit-learn. This allows the user's values ​​and needs to be identified using clustering and regression analysis techniques. The Python script then generates optimal policy proposals based on the analysis results and stores them in a database.

[1372] Notification and display of policy proposals

[1373] The generated policy proposal is then sent back to the user's device from the server. The notification email includes a link to view the details of the proposal. The user can click the link to access the policy proposal details page and view the details. This page provides an interface that visually displays the proposal contents.

[1374] Gathering and implementing feedback

[1375] Users provide feedback on policy proposals, including their opinions and thoughts. Feedback is sent via an input form on the details page. The feedback sent from the device is received by the server and stored in a database. The server then analyzes the feedback. This analysis uses text analysis techniques. The machine learning model is retrained based on the analysis results, improving the accuracy of the next policy proposal.

[1376] The generated policy proposals are automatically provided to government agencies, with the hope that they will be utilized in actual policy formation.

[1377] Specific examples

[1378] Scenario: Welfare policy proposal for the elderly

[1379] 1. An elderly user registers in the system and enters basic information (e.g., age 75, retired, living alone).

[1380] 2. Users fill out a survey and provide information about their health issues and financial situation.

[1381] 3. The server analyzes this information and identifies characteristics of the user, such as whether they have a low income or health problems.

[1382] 4. The server generates policy proposals tailored to the user, such as medical expense subsidy systems for the elderly.

[1383] 5. The user reviews the policy proposals generated on the device and provides feedback such as "very helpful."

[1384] 6. The server collects feedback, updates the AI ​​model, and provides a policy proposal report to government agencies.

[1385] Prompt Sentence Examples

[1386] "Generate policy proposals for a medical expense subsidy system for the elderly based on basic information and survey responses."

[1387] In this way, the system can provide policy proposals tailored to the individual needs of each user, and through feedback functions, the quality of the policy proposals can be continuously improved.

[1388] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1389] Step 1: User Registration

[1390] A user accesses the system's URL using a web browser. The user enters basic information (such as name, age, occupation, and area of ​​residence) on the registration screen. The entered basic information is sent from the terminal to the server when the user presses the "Submit" button. The server receives the sent basic information and saves it in a database. This stores the user's basic information in the database and makes it available for future processing.

[1391] Input: Basic information entered by the user

[1392] Data calculation: Send input data to the server and save it in the database

[1393] Output: Basic user information stored in the database

[1394] Step 2: Polyseasonal Bayesian data collection

[1395] The server periodically generates and sends survey notification emails to users. These emails contain a URL for a survey containing questions about social issues, taxes, welfare systems, etc. When a user clicks on the link in the email, they access the survey page. The user answers the survey using their device and presses the "Submit" button, which sends the answers from the device to the server. The server receives the answers and stores them in a database.

[1396] Input: Server-generated survey notification email

[1397] Data calculation: Sending user answers to the server and storing them in a database

[1398] Output: Survey responses stored in a database

[1399] Step 3: Data analysis and policy proposal generation

[1400] The server runs a machine learning algorithm to analyze the collected basic information and survey responses. The analysis is performed using Python and libraries such as TensorFlow and Scikit-learn. The server reads the user's basic information and survey responses from the database and inputs them into a machine learning model. The algorithm performs clustering and regression analysis to identify the user's values ​​and needs. Based on the analysis results, optimal policy proposals are generated. These proposals are then saved back to the database.

[1401] Input: User basic information and survey responses stored in the database

[1402] Data Computing: Analyzing data and generating policy recommendations using machine learning algorithms

[1403] Output: Generated policy proposals

[1404] Step 4: Notification and presentation of policy proposals

[1405] The generated policy proposal is notified to the user's device by the server. The server generates a policy proposal notification email and sends it to the user. The notification email contains a link to view the details of the proposal. When the user clicks the link, they can access the policy proposal details page. The device displays this page, allowing the user to visually confirm the proposal contents.

[1406] Input: Generated policy proposals

[1407] Data calculation: Generate and send policy proposal notification emails

[1408] Output: Policy proposal details page displayed on the user's device

[1409] Step 5: Gather and incorporate feedback

[1410] Users provide their opinions and thoughts on policy proposals as feedback through an input form on the details page. When the user presses the "Submit" button, the feedback is sent from the device to the server. The server then stores the received feedback in a database. The server then analyzes it and uses text analysis techniques to analyze the feedback content. Based on the analysis results, the machine learning model is retrained. This improves the accuracy of the next policy proposal.

[1411] Input: User feedback

[1412] Data calculation: storing and analyzing feedback in a database

[1413] Output: Improved policy proposals for the next round

[1414] Step 6: Submitting policy proposals to government agencies

[1415] Finally, the generated policy proposals are provided to government agencies. The server generates a policy proposal report and automatically sends it to the appropriate government agency. This report contains detailed policy proposals based on the analysis results, which will help the policy proposals to be used in actual policy formation.

[1416] Input: Generated policy proposals

[1417] Data Computing: Generate and send policy proposal reports

[1418] Output: Policy proposals provided to government agencies

[1419] (Application example 1)

[1420] 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."

[1421] Current policy proposal systems are designed for general users and are unable to fully reflect the specific needs of elderly people and users with physical limitations. Furthermore, they lack the functionality to provide appropriate assistance services in real time, especially for users using autonomous vehicles. This has led to problems such as delays and inappropriate recommendations and guidance for welfare support and medical services needed by elderly people and users with physical limitations.

[1422] 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.

[1423] In this invention, the server includes means for users to register with the system, means for collecting basic information and questionnaire responses from users, means for saving the collected information in a database, means for analyzing the saved information and identifying the user's values ​​and needs, means for generating policy proposals based on the identified values ​​and needs, means for notifying and displaying the generated policy proposals to the user, means for collecting feedback from the user, means for analyzing the collected feedback and reflecting it in the next proposal, and means for analyzing usage information and health status data collected by the autonomous mobile device and proposing optimal welfare support services to the user while riding. This makes it possible to provide appropriate welfare support services in real time to elderly and physically limited users, and to create an environment in which users can use the autonomous mobile device with peace of mind.

[1424] An "autonomous vehicle" is a means of transportation that uses artificial intelligence and sensor technology to operate automatically and travel to a destination without human intervention.

[1425] "Usage information" is data generated when a user uses an autonomous driving device, and includes information such as travel route, boarding and disembarking times, and riding frequency.

[1426] "Health condition data" refers to information relating to the user's health, and includes biometric data such as blood pressure, heart rate, and body temperature, as well as health status evaluation results based on questionnaire results and the like.

[1427] "Welfare support services" are support measures and services provided to users with specific needs, such as the elderly and people with disabilities, and include medical assistance, transportation assistance, and lifestyle support.

[1428] "Analysis" is the process of applying machine learning algorithms and statistical methods to analyze information based on collected data to identify specific values ​​and needs.

[1429] "Policy proposals" are proposals that present optimal policies and support measures to users based on the analysis results, and include information on specific measures and services.

[1430] "Feedback" refers to information such as opinions, impressions, and evaluations provided by users, and is useful for improving the system and increasing the accuracy of future policy proposals.

[1431] This invention applies an AI-based policy proposal system to an autonomous driving device to provide optimal welfare support services in real time to elderly people and users with physical limitations. The system includes the following main components:

[1432] 1. User Registration

[1433] The server provides a means for users to register with the system through the terminal of the autonomous driving device. The user can then enter their basic information and register with the system. The user's basic information includes age, gender, health condition, etc.

[1434] 2. Data Collection

[1435] The server uses the terminal to collect basic information and questionnaire responses from users, including usage information, health status data, and questionnaires about their living conditions. The data is collected periodically, sent to the server, and stored in a database.

[1436] 3. Data analysis and policy proposal generation

[1437] The server analyzes the collected data using machine learning algorithms. Specifically, it uses platforms such as NVIDIA Jetson to identify the user's values ​​and needs. Based on these values ​​and needs, it generates optimal welfare support services and policies.

[1438] 4. Notification and Display of Policy Proposals

[1439] The server notifies the autonomous driving device of the generated policy proposals. The device then displays the proposals visually and audibly to the user through a display and audio guide. It is also possible to link with smart glasses or a head-mounted display to display the proposals in real time.

[1440] 5. Gather and incorporate feedback

[1441] The server collects the feedback provided by users and incorporates this information into the next policy proposal, allowing for continuous improvement of the quality of the proposal.

[1442] Examples:

[1443] Elderly person A (75 years old) rides an autonomous driving device and answers a questionnaire about his / her health condition and lifestyle through a linked application. The server analyzes the collected data in real time and suggests "priority access to medical institutions" and "low-cost transportation support plans." This allows Elderly Person A to receive appropriate support services based on his / her health condition.

[1444] Example prompt sentence:

[1445] "Data analysis prompt to propose a medical assistance system for elderly users: Generate appropriate policy proposals based on information such as age, living situation, health status, and facilities (medical institutions, public services) that users frequently access. Example: 75 years old, living alone, with chronic illnesses, and needing to visit hospitals frequently."

[1446] This system enables elderly people and people with physical limitations who use autonomous vehicles to receive optimal welfare support services in real time. The generated policy proposals are also customized to the needs of each user, providing optimal support for each user.

[1447] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1448] Step 1:

[1449] The server provides a means for users to register with the system. Users enter basic information such as age, gender, and health status through the terminal of the autonomous driving device. The server stores this basic information in a database.

[1450] Input: User's basic information (age, gender, health status, etc.)

[1451] Output: Basic information stored in the database

[1452] Specific operation: The user enters information into the registration screen displayed on the terminal and sends it to the server, which then stores the received information in a database.

[1453] Step 2:

[1454] The server periodically sends questionnaires to users to collect usage information and health status data. Users respond to the questionnaires and send the data from their terminals to the server.

[1455] Input: Survey responses, usage information (route, boarding and disembarking times, etc.), health status data (blood pressure, heart rate, etc.)

[1456] Output: Survey responses, usage information, and health status data stored in a database

[1457] Specific operation: A questionnaire is presented to the user via the device's display or audio guide. The user answers the questionnaire and sends the data to the server.

[1458] Step 3:

[1459] The server analyzes the collected data using machine learning algorithms (e.g., NVIDIA Jetson), processes the data, and identifies the user's values ​​and needs.

[1460] Input: Basic information, survey responses, usage information, health status data

[1461] Output: User values ​​and needs

[1462] How it works: The server retrieves the collected data from the database, inputs it into a machine learning algorithm, and analyzes it. From the analysis results, the user's specific values ​​and needs are extracted.

[1463] Step 4:

[1464] The server generates optimal welfare support services and policy proposals based on the analysis results.

[1465] Input: User values ​​and needs

[1466] Output: Generated policy proposals

[1467] Specific operation: Based on the analysis results, the server uses a specific algorithm to generate optimal policy proposals for the user.

[1468] Step 5:

[1469] The server notifies the device of the generated policy proposals and displays them to the user. The device then provides the proposals to the user using a display or audio guide. The device also works with smart glasses or a head-mounted display to display the proposals in real time.

[1470] Input: Generated policy proposals

[1471] Output: Policy proposals displayed to the user

[1472] Specific operation: Policy proposals are displayed on the device screen and explained via audio guidance. When using smart glasses or a head-mounted display, the proposals are displayed in real time.

[1473] Step 6:

[1474] Users provide feedback on the presented policy proposals through their terminals, and the server collects the feedback and stores it in a database.

[1475] Input: User feedback

[1476] Output: Feedback stored in a database

[1477] Specific operation: The user can easily input feedback through the terminal interface, and the server receives the feedback and stores it in a database.

[1478] Step 7:

[1479] The server analyzes the collected feedback and reflects it in the next policy proposal.

[1480] Input: Feedback stored in the database

[1481] Output: Improved policy recommendations

[1482] Specific operation: The server analyzes the feedback and updates the machine learning model based on the results. The analysis results are reflected in the next policy proposal to make it more accurate.

[1483] 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.

[1484] This invention is a policy proposal system that uses AI and an emotion engine to propose policies that take into account the emotional state as well as the values ​​and needs of each individual user. The system includes the following main means and processes:

[1485] User Registration

[1486] First, a user accesses the system and creates an account, which allows the user to enter their basic information into the system, which is then sent to the server and stored in the database.

[1487] Polyseasonal Bayesian Data Collection

[1488] The server periodically sends users survey notifications, which include questions about social issues, taxes, welfare systems, etc. Users answer the surveys through their devices, and the responses are sent to the server and stored.

[1489] Data analysis and emotion recognition

[1490] The server uses machine learning algorithms and an emotion engine to analyze the collected user information and survey responses. As a result of the analysis, each user's values ​​and needs are identified. At the same time, the emotion engine evaluates the user's emotional state based on their feedback and interactions.

[1491] Generate policy proposals

[1492] The server generates policy proposals based on the user's values, needs, and assessed emotional state, ensuring that the proposed policies are in line with the user's actual emotions.

[1493] Notification and display of policy proposals

[1494] The generated policy proposal is sent from the server to the user's device, where it is displayed to the user as a notification and provides an interface with detailed visual information. The interface's display method is also adjusted according to the user's emotional state.

[1495] Gathering and implementing feedback

[1496] Users provide their opinions and thoughts on policy proposals as feedback to the system. The feedback is sent from the device to the server and analyzed. As a result, the server can reflect the user's feedback and emotional state in the next policy proposal.

[1497] Specific examples

[1498] Scenario: Welfare policy proposal for the elderly

[1499] 1. An elderly user registers with the system and enters basic information (e.g., age 75, retired, living alone).

[1500] 2. Users use the device to fill out a questionnaire and answer questions about their health issues and financial situation.

[1501] 3. The server analyzes the user's basic information and questionnaire responses to determine the user's characteristics, such as "low income" or "health problems."

[1502] 4. The emotion engine evaluates the emotional state from the user's feedback and interactions and sends it to the server.

[1503] 5. The server generates policy proposals tailored to the user, such as medical subsidy programs for the elderly, and adjusts the proposals to take into account the user's emotional state.

[1504] 6. The terminal displays the generated policy proposal to the user, who can then check the details. Based on the emotion engine, the display method is optimized to the user's emotional state.

[1505] 7. The user provides feedback on the suggestion, such as "very helpful."

[1506] 8. The server collects feedback, updates the AI ​​model and emotion engine with the latest information, and provides a policy proposal report to government officials.

[1507] This system will propose policies that take into account the needs and emotional state of each user, enabling policy formation that reflects the diverse opinions and emotions of citizens. Furthermore, through a feedback function, the quality of policy proposals can be continuously improved, promoting the realization of democracy and citizen participation.

[1508] The processing flow will be explained below.

[1509] Step 1: User registers with the system

[1510] 1. A user visits a web page or app and selects "Create a new account."

[1511] 2. The device displays a registration form to the user, asking them to enter basic information such as their name, address, age, occupation, and email address.

[1512] 3. The user enters the required information and clicks "Submit."

[1513] 4. The terminal sends the entered data to the server.

[1514] 5. The server stores the received basic information in a database.

[1515] Step 2: Send out the survey and collect responses

[1516] 1. The server periodically generates and prepares to send surveys to registered users.

[1517] 2. The device displays a notification to the user saying "There is a new survey."

[1518] 3. The user clicks on the notification and opens the survey page.

[1519] 4. The terminal displays the survey form and the user answers the questions.

[1520] 5. The user answers the questions and clicks "Submit."

[1521] 6. The device sends the user's response data to the server.

[1522] 7. The server stores the received response data in a database.

[1523] Step 3: Data analysis and emotion recognition

[1524] 1. The server reads the user's basic information and survey responses from the database.

[1525] 2. The server applies machine learning algorithms to analyze each user's values ​​and needs.

[1526] 3. The server updates each user's profile based on the analysis results.

[1527] 4. The server uses an emotion engine to evaluate the emotional state from the user's feedback and interactions.

[1528] 5. The server adds the emotional state assessment to the profile.

[1529] Step 4: Generate policy proposals

[1530] 1. The server starts generating policy suggestions based on the user's profile and emotional state.

[1531] 2. The policy proposals generated by the server include specific policy explanations, expected effects, advantages and disadvantages, etc.

[1532] 3. The server stores the generated policy proposals for each user.

[1533] Step 5: Notification and display of policy proposals

[1534] 1. The server prepares to send the stored policy proposal to the corresponding user.

[1535] 2. The device displays a notification to the user saying, "New policy proposals available."

[1536] 3. The user clicks on the notification to view the details of the policy proposal.

[1537] 4. The device displays details of policy proposals to the user and provides a convenient UI that adapts to their emotional state.

[1538] Step 6: Gather feedback

[1539] 1. Users view the policy proposal and enter their opinions and thoughts in the feedback section.

[1540] 2. The user submits feedback.

[1541] 3. The device sends the feedback data to the server.

[1542] 4. The server stores the received feedback data in a database.

[1543] 5. The server uses the emotion engine to analyze the feedback content.

[1544] Step 7: Analyze and incorporate feedback

[1545] 1. The server analyzes the feedback data and updates the AI ​​model and emotion engine.

[1546] 2. The server stores the analysis results so that the next policy proposal will reflect the user's feedback and emotional state.

[1547] 3. The server generates a report that provides the user feedback results to government officials.

[1548] Examples:

[1549] Scenario: Welfare policy proposal for the elderly

[1550] 1. An elderly user registers with the system and enters basic information (e.g., age 75, retired, living alone).

[1551] 2. The user uses the device to answer a questionnaire and enter their opinions about health issues and financial situations.

[1552] 3. The server stores the user's basic information and survey response data in a database.

[1553] 4. The server uses machine learning algorithms and an emotion engine to analyze the user's values, needs, and emotional state.

[1554] 5. Based on the analysis results, the server generates proposals for medical subsidy programs for the elderly, adjusting the content of the proposals to take into account the emotional state.

[1555] 6. The device notifies the user of the generated policy proposal and visually displays the details. Based on the emotion engine, the display method is optimized to the user's emotional state.

[1556] 7. The user reviews the suggestion and provides feedback that it is "very helpful."

[1557] 8. The server collects feedback and updates the AI ​​model and emotion engine with the latest information.

[1558] 9. The server provides policy proposal reports to government officials to help them formulate policies.

[1559] In this way, policy proposals that take into account the user's emotional state can be more personalized, reflecting the diverse opinions and emotions of citizens, and continuously improving the quality of policy proposals through feedback and sentiment analysis.

[1560] Example 2

[1561] 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."

[1562] Conventional policy proposal systems make proposals based only on the user's basic information and questionnaire responses, which means they are inadequately able to adapt to fluctuations in an individual user's emotional state and feedback. As a result, it is difficult to generate policy proposals that are appropriate for the user's actual interests and emotional state. Furthermore, there is a lack of a method to maintain consistency by incorporating feedback into the next proposal.

[1563] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1564] In this invention, the server includes means for users to register with the system, means for collecting basic information and questionnaire responses from users, means for storing the collected information in a database, means for analyzing the stored information using a machine learning algorithm to identify the user's values ​​and needs, means for evaluating the user's emotional state using an emotion recognition engine, means for generating policy proposals using a generative AI model based on the identified values ​​and needs and the evaluated emotional state, means for notifying and displaying the generated policy proposals to the user, and means for collecting feedback from the user and reflecting the feedback in the next policy proposal, thereby enabling personalized policy proposals based on the user's values ​​and emotional state.

[1565] "User" refers to an individual person who uses the system.

[1566] "System" refers to an environment that includes a set of software and hardware for communicating information between users and a server and generating policy proposals.

[1567] "Basic information" refers to personal information such as the user's name, age, gender, and address.

[1568] "Survey responses" refer to responses to questions asked by users regarding social issues, taxes, welfare systems, etc.

[1569] "Database" refers to a system that organizes and stores collected data such as basic user information and questionnaire responses.

[1570] "Machine learning algorithms" refer to techniques that analyze large amounts of data for patterns and trends, and specifically include technologies such as TensorFlow.

[1571] "Emotion recognition engine" refers to a system that assesses the emotional state of a user from their feedback and interactions. Examples include the IBM Watson Tone Analyzer.

[1572] "Generative AI models" refer to artificial intelligence algorithms that generate text or suggestions based on collected and analyzed data, including GPT-4.

[1573] "Policy proposals" refer to specific policy proposals generated based on the user's basic information, survey responses, and emotional state.

[1574] "Notification" refers to the system's ability to notify users of new information or offers.

[1575] "Display" refers to the user being able to visually confirm the details of information and suggestions through the system.

[1576] "Feedback" refers to the user providing the system with their opinions and thoughts about the proposal.

[1577] This invention is a policy proposal system that uses AI and an emotion engine to propose policies that take into account the emotional state of each user, along with their values ​​and needs. Specific means for implementing this system and its operation are described below.

[1578] User Registration

[1579] First, a user accesses the system using a web browser or smartphone app and creates a new account. The user enters basic information such as name, age, gender, and address. The basic information entered from the device is sent to the server using the HTTPS protocol. The server then stores the received basic information in a database (e.g., MongoDB, MySQL).

[1580] Polyseasonal Bayesian Data Collection

[1581] Next, the server uses a scheduling service (e.g., Cron job) to periodically send survey notifications to users. The surveys include questions about social issues, taxes, welfare systems, etc. Users answer the surveys using their devices, and the responses are sent from the devices to the server. The server then stores the survey response data in a database.

[1582] Data analysis and emotion recognition

[1583] The server uses a machine learning algorithm (e.g., TensorFlow) to analyze the user's basic information and survey responses. As a result of the analysis, each user's values ​​and needs are identified. At the same time, the server uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to evaluate the user's emotional state from their feedback and interactions. The analysis results are stored in a database as the user's individual profile.

[1584] Generate policy proposals

[1585] The server then uses a generative AI model (e.g., GPT-4) to generate policy proposals based on the analysis results and the user's emotional state. These proposals are tailored to the user's values ​​and needs, and are adjusted according to the user's emotional state.

[1586] Notification and display of policy proposals

[1587] The generated policy proposals are sent from the server to the user's device. The device notifies the user of the received policy proposals and displays details. The display method of the device's interface is also adjusted based on the user's emotional state. For example, if the emotional state is determined to be "stressed," the interface color scheme and font style are changed to something more relaxing.

[1588] Gathering and implementing feedback

[1589] Finally, the user provides feedback to the system, including their opinions and thoughts on the policy proposals. This feedback is sent from the device to the server, where it is analyzed and reflected in the next policy proposal. This allows the system to continually make proposals that incorporate the user's latest needs and emotional state.

[1590] Specific examples

[1591] Scenario: Welfare policy proposal for the elderly

[1592] 1. An elderly user registers in the system and enters basic information (e.g., age 75, retired, living alone).

[1593] 2. Users use the device to fill out a questionnaire and answer questions about their health issues and financial situation.

[1594] 3. The server analyzes the user's basic information and questionnaire responses to determine the user's characteristics, such as "low income" or "health problems."

[1595] 4. The emotion engine evaluates the emotional state from the user's feedback and interactions and sends it to the server.

[1596] 5. The server generates tailored policy proposals for the user, such as medical subsidy programs for the elderly, and the proposals are adjusted based on the user's emotional state.

[1597] 6. The terminal displays the generated policy proposal to the user, who can then check the details. Based on the emotion engine, the display method is optimized to the user's emotional state.

[1598] 7. The user provides feedback on the suggestion, such as "very helpful."

[1599] 8. The server collects feedback and updates the AI ​​model and emotion engine with the latest information.

[1600] Prompt Sentence Examples

[1601] "Please propose a welfare policy suitable for seniors who have retired at age 75. Consider the following conditions: low income, health problems."

[1602] "Use AI and emotion engines to generate policy recommendations that take into account the user's values ​​and emotional state."

[1603] This system realizes personalized policy proposals that take into account the needs and emotional state of each user, enabling policy formation that reflects the diverse opinions and emotions of citizens. Furthermore, through a feedback function, the quality of policy proposals can be continuously improved, promoting the realization of democracy and citizen participation.

[1604] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1605] Step 1: User Registration

[1606] Users access the system using a web browser or smartphone app and create a new account.

[1607] Input: User's basic information (name, age, gender, address, etc.)

[1608] Output: Basic user information stored in the database

[1609] How it works: A user fills out a form with basic information and clicks the submit button. The device sends the information to the server via HTTPS. The server validates the received information and stores it in a database.

[1610] Step 2: Polyseasonal Bayesian data collection

[1611] The server periodically sends survey notifications to users.

[1612] Input: Survey data, user basic information

[1613] Output: Survey responses stored in a database

[1614] How it works: The server uses a scheduling service to send a survey notification to the user's device at a specific time. The user receives the notification and opens the survey screen. They answer the survey, and the device sends the response data to the server. The server stores the received response data in a database.

[1615] Step 3: Data analysis and emotion recognition

[1616] The server uses machine learning algorithms to analyze the user's basic information and questionnaire responses, and uses an emotion engine to evaluate their emotional state.

[1617] Input: User basic information, survey responses, feedback

[1618] Output: Analyzed user values, needs and emotional state

[1619] How it works: The server uses TensorFlow to analyze user data. As a result of the analysis, each user's values ​​and needs are identified. At the same time, an emotion recognition engine (e.g., emotion analysis API) evaluates the user's emotional state based on their feedback and interaction data. The evaluation results are saved as a personalized profile for the user.

[1620] Step 4: Generate policy proposals

[1621] The server generates policy proposals using a generative AI model based on the analysis results and emotional state.

[1622] Input: Analyzed user values, needs, and emotional state

[1623] Output: Generated policy proposals

[1624] How it works: The server takes the analysis results and the user's emotional state as input and uses a generative AI model (e.g., GPT-4) to generate policy proposals. The proposals include specific policy content and are adjusted according to the user's emotional state.

[1625] Step 5: Notification and presentation of policy proposals

[1626] The server sends the generated policy proposal to the user's terminal, which notifies the user of the policy proposal and displays the details.

[1627] Input: Generated policy proposals

[1628] Output: Policy proposals communicated and displayed to the user

[1629] How it works: The server converts the generated policy proposal into JSON format and sends it to the user's device. The device then notifies the user of the new policy proposal via push notifications or in-app notifications. The proposal details are displayed on a details screen, and the interface color scheme and font style are adjusted according to the user's emotional state.

[1630] Step 6: Gather and incorporate feedback

[1631] Users provide feedback on policy proposals, including their opinions and thoughts. The server collects the feedback and reflects it in the next policy proposal.

[1632] Input: User feedback

[1633] Output: Updated user profile, feedback to be reflected in next proposal

[1634] How it works: A user enters their opinions and thoughts into the feedback form on the policy proposal details screen and clicks the submit button. The device sends the feedback to the server. The server analyzes the received feedback and updates the user profile. This updated information is taken into account the next time a policy proposal is generated.

[1635] Through these steps, the system realizes personalized policy proposals based on the user's values ​​and emotional state.

[1636] (Application example 2)

[1637] 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."

[1638] Existing policy and content proposal systems can analyze users' values ​​and needs, but they struggle to make proposals that take into account the user's emotional state. This can lead to lower acceptability and satisfaction. Furthermore, there is a lack of effective ways to incorporate user feedback into future proposals, making it difficult to improve the quality of proposals.

[1639] 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.

[1640] In this invention, the server includes: a means for users to register with the system; a means for collecting basic information and questionnaire responses from users; a means for storing the collected information in a database; a means for analyzing the stored information to identify the user's values ​​and needs; a means for generating policy or content proposals based on the identified values ​​and needs and the evaluated emotional state; a means for notifying and displaying the generated policy or content proposals to the user; a means for adjusting the display method based on the user's feedback and emotional state; a means for collecting user feedback; and a means for analyzing the collected feedback and emotional state data and reflecting it in subsequent proposals. This enables policy and content proposals to be tailored to the user's emotional state, thereby improving the acceptability and satisfaction of the proposals. Furthermore, effectively reflecting feedback in subsequent proposals also improves the quality of the proposals.

[1641] A "user" is an individual or group that uses the system and provides data such as basic information and questionnaire responses.

[1642] The "system" is a set of mechanisms for generating, notifying, and displaying policy or content suggestions based on the user's values, needs, and emotional state, and for collecting feedback to be reflected in future suggestions.

[1643] "Policy proposals" are the contents of plans and measures provided by governments and public institutions that are generated based on the user's values, needs, and emotional state.

[1644] "Content suggestions" are entertainment and informational content such as movies, music, and news articles that are generated based on the user's values, needs, and emotional state.

[1645] "Emotional state" refers to the psychological state or feeling that is assessed through user feedback and interaction.

[1646] A "database" is an information collection that allows the system to store and manage collected basic information, questionnaire responses, feedback, etc. from users.

[1647] "Feedback" refers to opinions and thoughts provided by users regarding policy proposals or content proposals, and is data that will be reflected in the next proposal.

[1648] "Machine learning algorithms" refer to mathematical methods and techniques for analyzing large amounts of data and finding patterns and trends.

[1649] An "emotion recognition engine" refers to software or hardware that analyzes and evaluates a user's emotional state from text, speech, or other input.

[1650] "Interface" refers to the screen or operating system through which a user views and provides feedback on a policy or content proposal.

[1651] This invention is a system that uses AI and an emotion engine to make policy and content proposals that take into account the user's values, needs, and emotional state. Specific embodiments for implementing this invention are described below.

[1652] First, users access the system and create an account. They enter the necessary basic information, which is then sent to the server and stored in a database. They also periodically answer surveys via their devices. The surveys include questions about social issues, content interests, emotional states, and more.

[1653] The server analyzes the basic information and survey responses collected from the user using machine learning algorithms and emotion recognition engines. Known machine learning libraries (e.g., scikit-learn) and emotion recognition models (e.g., emotion recognition models from the transformers library) are used. The analysis results identify the user's values, needs, and emotional state.

[1654] The server then generates policy or content recommendations based on these analysis results, and the recommendations are tailored to reflect the user's emotional state. For example, if the user is in a "sad" emotional state, comforting content will be suggested.

[1655] The suggestions are sent to the device, and the user confirms them through the interface. The interface adjusts its display based on the user's emotional state. An emotion recognition engine evaluates the user's emotional state from their feedback and interactions, and the interface is optimized accordingly.

[1656] Users provide feedback on the suggestions. This feedback is sent to the server and stored in a database. The server analyzes the collected feedback and reflects it in the next suggestion. During this process, a generative AI model is used to create prompts to generate optimal suggestions.

[1657] For example, in the following example, in response to feedback such as "I was moved! It brought me to tears!", the emotion recognition model detects the emotion "sad." Based on this, other inspiring movies and content are suggested.

[1658] Example prompt sentence:

[1659] User feedback: "I was moved! It brought me to tears!"

[1660] Sentiment analysis result: "Sad"

[1661] Suggested content list:

[1662] 1. "In This Corner of the World" - A moving story set in Hiroshima during the war

[1663] 2. "The Wind Rises" - A story of an airplane designer's dreams and love

[1664] As described above, the present invention provides a specific method for realizing a system that makes suggestions based on the user's values, needs, and emotional state, thereby increasing user satisfaction.

[1665] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1666] Step 1: A user registers with the system.

[1667] Input: User's basic information (name, age, gender, etc.)

[1668] Process: A user accesses the system from a terminal, creates an account, and enters basic information, which is then sent to the server.

[1669] Output: The server stores the collected basic information in a database.

[1670] Step 2: Collect survey responses.

[1671] Input: User survey responses (social issues, content interests, emotional state, etc.)

[1672] Processing: The server periodically sends a survey notification to the user. The user answers the survey through their terminal and sends the results to the server.

[1673] Output: The server stores the collected survey responses in a database.

[1674] Step 3: Data analysis.

[1675] Input: User basic information stored in the database, survey responses, and emotional feedback

[1676] Processing: The server analyzes the data using machine learning algorithms (scikit-learn) to identify the user's values ​​and needs, and analyzes the user's emotional state using an emotion engine (transformers library).

[1677] Output: Identified user values, needs, and emotional state.

[1678] Step 4: Generate policy or content proposals.

[1679] Input: Identified values, needs, and emotional states

[1680] Processing: The server uses the generative AI model to generate optimized policy or content recommendations based on the user's values ​​and emotional state. For example, if the emotional state is rated as "sad," inspirational movies or content will be suggested.

[1681] Output: Generated policy or content proposals

[1682] Step 5: Notification and display of proposals.

[1683] Input: Generated policy proposals or content proposals, emotional states

[1684] Processing: The server sends the generated suggestions to the user's device. The device notifies the user of the suggestions and displays details through a display interface. Based on the emotion engine, the display method is optimized according to the user's emotional state.

[1685] Output: An interface for the user to visually confirm the proposal

[1686] Step 6: Gather feedback.

[1687] Input: User feedback

[1688] Processing: The user provides their opinions and feedback on the proposals through their device. The feedback is sent to the server and stored in a database.

[1689] Output: Collected feedback

[1690] Step 7: Analyze the feedback and incorporate it into your next proposal.

[1691] Input: collected feedback, emotional state data

[1692] Processing: The server analyzes the collected feedback and emotional state data and reflects it in the next suggestion. It also uses a generative AI model to create prompts to generate optimal suggestions.

[1693] Output: Improved next policy or content proposal

[1694] Through each of the above steps, the system can make policy and content suggestions that are in line with the user's values, needs, and emotional state, thereby increasing the acceptability and satisfaction of the suggestions.

[1695] 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.

[1696] 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.

[1697] 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 robot 414.

[1698] 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.

[1699] FIG. 9 illustrates 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 behaviors 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.

[1700] 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.

[1701] 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).

[1702] 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.

[1703] 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."

[1704] 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.

[1705] 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).

[1706] 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.

[1707] 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.

[1708] 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.

[1709] 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.

[1710] 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.

[1711] 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.

[1712] 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.

[1713] 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.

[1714] 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.

[1715] 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.

[1716] The following is further disclosed regarding the above embodiment.

[1717] (Claim 1)

[1718] a means for users to register with the system;

[1719] means for collecting basic information and survey responses from users;

[1720] a means for storing the collected information in a database;

[1721] A means of analyzing the stored information to identify the user's values ​​and needs;

[1722] a means of generating policy proposals based on identified values ​​and needs;

[1723] means for notifying and displaying the generated policy proposals to the user;

[1724] a means for collecting feedback from users;

[1725] A way to analyze the collected feedback and incorporate it into the next proposal

[1726] A system including:

[1727] (Claim 2)

[1728] The system according to claim 1, wherein the system performs data analysis by applying a machine learning algorithm based on the user's basic information and questionnaire responses.

[1729] (Claim 3)

[1730] 10. The system of claim 1, further comprising: notifying a user of a policy proposal and providing an interface for the user to review the proposal.

[1731] "Example 1"

[1732] (Claim 1)

[1733] a means for users to register with the system;

[1734] means for collecting basic information and survey responses from users;

[1735] a means for storing the collected information in a database;

[1736] A means of analyzing stored information using machine learning algorithms to identify user values ​​and needs;

[1737] a means of generating policy proposals based on identified values ​​and needs;

[1738] means for notifying and displaying the generated policy proposals to the user;

[1739] a means for collecting feedback from users;

[1740] A way to analyze the collected feedback and update the generative AI model to reflect it in the next proposal.

[1741] A means of providing generated policy proposals to government agencies

[1742] A system including:

[1743] (Claim 2)

[1744] The system according to claim 1, wherein data analysis is performed by applying a machine learning algorithm based on the user's basic information and questionnaire responses.

[1745] (Claim 3)

[1746] 10. The system of claim 1, further comprising: notifying a user of a policy proposal and providing an interface for the user to review the proposal.

[1747] "Application Example 1"

[1748] (Claim 1)

[1749] a means for users to register with the system;

[1750] means for collecting basic information and survey responses from users;

[1751] a means for storing the collected information in a database;

[1752] A means of analyzing the stored information to identify the user's values ​​and needs;

[1753] a means of generating policy proposals based on identified values ​​and needs;

[1754] means for notifying and displaying the generated policy proposals to the user;

[1755] a means for collecting feedback from users;

[1756] A way to analyze the collected feedback and incorporate it into the next proposal,

[1757] Analyzing usage information and health status data collected from the autonomous driving device;

[1758] A means of proposing optimal welfare support services to users while they are in the vehicle

[1759] A system including:

[1760] (Claim 2)

[1761] The system according to claim 1, wherein the system performs data analysis by applying a machine learning algorithm based on the user's basic information and questionnaire responses.

[1762] (Claim 3)

[1763] 10. The system of claim 1, further comprising: notifying a user of a policy proposal and providing an interface for the user to review the proposal.

[1764] "Example 2: Combining Emotion Engines"

[1765] (Claim 1)

[1766] a means for users to register with the system;

[1767] means for collecting basic information and survey responses from users;

[1768] a means for storing the collected information in a database;

[1769] A means of analyzing stored information using machine learning algorithms to identify user values ​​and needs;

[1770] means for assessing the emotional state of a user using an emotion recognition engine;

[1771] A means of generating policy recommendations using a generative AI model based on identified values ​​and needs and assessed emotional states; and

[1772] means for notifying and displaying the generated policy proposals to the user;

[1773] A system that includes a means of collecting feedback from users and incorporating that feedback into future policy proposals.

[1774] (Claim 2)

[1775] The system of claim 1, wherein the system applies machine learning algorithms and emotion recognition engines to perform data analysis based on the user's basic information, questionnaire responses, and feedback.

[1776] (Claim 3)

[1777] 10. The system of claim 1, wherein the system notifies the user of policy suggestions and provides an interface optimized for the user's emotional state.

[1778] "Application example 2 when combining emotion engines"

[1779] (Claim 1)

[1780] a means for users to register with the system;

[1781] means for collecting basic information and survey responses from users;

[1782] a means for storing the collected information in a database;

[1783] A means of analyzing the stored information to identify the user's values ​​and needs;

[1784] a means for generating policy or content proposals based on identified values ​​and needs and assessed emotional states;

[1785] means for notifying and displaying the generated policy or content proposals to the user;

[1786] means for adjusting the display based on the user's feedback and emotional state;

[1787] a means for collecting feedback from users;

[1788] A way to analyze collected feedback and emotional state data and incorporate it into future proposals

[1789] A system including:

[1790] (Claim 2)

[1791] 10. The system of claim 1, wherein the system applies machine learning algorithms and emotion recognition engines to analyze data based on the user's basic information, questionnaire responses, and emotional state.

[1792] (Claim 3)

[1793] 10. The system of claim 1, wherein the system notifies the user of policy or content suggestions, provides an interface for the user to review the suggestions, and adjusts the display of the interface depending on the user's emotional state. [Explanation of symbols]

[1794] 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 for users to register with the system; means for collecting basic information and survey responses from users; a means for storing the collected information in a database; A means of analyzing the stored information to identify the user's values ​​and needs; a means of generating policy proposals based on identified values ​​and needs; means for notifying and displaying the generated policy proposals to the user; a means for collecting feedback from users; The collected feedback will be analyzed and reflected in the next proposal. A system including:

2. The system according to claim 1, wherein the system performs data analysis by applying a machine learning algorithm based on the user's basic information and questionnaire responses.

3. The system of claim 1 , further comprising: notifying a user of a policy proposal and providing an interface for the user to review the proposal.

Images