system

Abstract

We provide the system. [Solution] A method for inputting multiple user data and performing an initial evaluation, A means of generating a learning plan based on user evaluations and providing information in an interactive format using a selected artificial intelligence model, A means of evaluating the user's level of understanding from the conversation history and providing feedback, A means of suggesting specific financial services according to the user's level of understanding, Means to support participation in proposed financial services A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] [In Japan, due to insufficient financial literacy, many citizens are passive in using the financial system, and there is a problem that asset formation does not progress. This problem has particularly become a factor causing economic insecurity in old age and a decline in the quality of life. Therefore, there is a need to develop a system that effectively provides financial education, enables citizens to have correct financial knowledge, and promotes proactive efforts in future asset formation.]

Means for Solving the Problems

[0005] [This invention provides a system that evaluates financial literacy using user data and generates personalized educational plans based on that evaluation. A selected artificial intelligence model provides information in an interactive format, allowing users to acquire financial knowledge in a natural way. Furthermore, by evaluating the level of understanding from the conversation history and providing appropriate feedback and financial service suggestions, the system supports users in actually starting to build their assets. This will help address the lack of financial education and contribute to the economic stability of the nation.]

[0006] "User data" refers to information about individual users and is used for financial literacy assessments and the generation of learning plans.

[0007] "Initial assessment" is an evaluation process conducted to determine the user's level of financial knowledge and to provide an appropriate learning plan.

[0008] An "artificial intelligence model" is a machine learning algorithm used to provide financial information to users in an interactive format.

[0009] "Dialogue format" refers to a communication method in which the user and the artificial intelligence model exchange information bidirectionally.

[0010] "Assessing comprehension" is a process that analyzes the level of financial knowledge acquired by the user and determines the next learning step.

[0011] "Feedback" refers to evaluation results and advice provided to users, which serve as information to be used for future learning and actions.

[0012] "Financial services" is a general term for the systems and products available for investment and asset management.

[0013] A "personalized education plan" is a customized educational content and schedule tailored to each user's financial literacy level.

[0014] "Asset building" is the process of systematically increasing one's assets with the aim of achieving future financial stability. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention provides a system for improving users' financial knowledge, and is particularly characterized by its interactive educational approach using an artificial intelligence model. The system's program is described below in natural language.

[0037] The server first receives basic information and self-assessment data about finances provided by the user and performs an initial assessment. This assessment forms the basis for understanding the user's current level of financial literacy and creating an appropriate educational plan.

[0038] Next, the server creates a personalized learning plan based on the initial evaluation results. Specifically, it selects the optimal artificial intelligence model according to each user's knowledge level and interests, and designs a learning course using that model. This plan includes the topics and schedule necessary for the user's learning.

[0039] Once a user begins learning based on this plan, the device will provide information in an interactive format using a selected artificial intelligence model. Users can ask questions through the device, and the AI ​​model will respond in real time, supporting the expansion of the user's financial knowledge.

[0040] For example, if a user asks the device, "I want to know about NISA," the artificial intelligence model will respond with something like, "NISA is a small-amount investment tax exemption system that offers tax benefits for specific investments." This allows users to obtain specific and easy-to-understand information through direct dialogue.

[0041] After a certain period of conversation, the server analyzes the history and evaluates the user's level of knowledge acquisition. Based on this evaluation, the terminal provides feedback to the user to encourage further understanding. Furthermore, depending on the evaluation results, it suggests appropriate financial services related to investment and asset management and provides support when the user takes actual action.

[0042] In this way, the system provides an effective learning environment that gradually improves users' financial literacy and leads to actual asset building.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server receives basic information and a self-assessment questionnaire about finances from users when they register for the app. This provides a basis for an initial assessment of the user's current financial literacy level.

[0046] Step 2:

[0047] The server generates a customized learning plan for each user based on an initial assessment. This plan designs the optimal artificial intelligence model and learning course to match the user's knowledge level and interests.

[0048] Step 3:

[0049] The terminal presents the user with a learning plan generated on the server and provides an interface to encourage them to start learning. The user can then begin a learning session based on this plan.

[0050] Step 4:

[0051] Once a user begins a learning session, the device uses a selected artificial intelligence model to provide financial information through interaction with the user. The user asks questions and receives immediate responses from the device, thus advancing the learning process.

[0052] Step 5:

[0053] The server analyzes the user's learning history and dialogue to assess the user's level of understanding. Based on this assessment, it determines the user's progress level and decides on a course of action for further learning or correction.

[0054] Step 6:

[0055] The terminal provides the user with feedback based on the evaluation results provided by the server. It offers advice to help with future learning and information to improve understanding.

[0056] Step 7:

[0057] Once the server determines that the user has acquired sufficient knowledge, it will suggest specific financial services to the user (e.g., investment programs or account opening procedures).

[0058] Step 8:

[0059] The terminal presents the user with specific information about the proposed financial services and provides an interface to support the next action. The user uses this information to select specific investment and asset management actions.

[0060] Step 9:

[0061] If the user takes action based on the suggestion, the device will guide them through the necessary steps and provide ongoing support.

[0062] (Example 1)

[0063] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0064] In modern society, financial literacy is becoming increasingly important, yet many people lack sufficient financial literacy and are unable to manage their assets effectively. To address this problem, there is a need for a system that provides learning methods optimized for individual users and effectively improves their financial knowledge.

[0065] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0066] In this invention, the server includes means for inputting user information and self-assessment information into an information processing device and performing an initial assessment; means for generating an individualized learning plan based on the user's initial assessment and providing information in an interactive format using a selected machine learning model; and means for analyzing the user's level of knowledge acquisition from the dialogue history and providing feedback based on the assessment results. This makes it possible to efficiently improve financial literacy through a learning plan optimized for each individual user.

[0067] An "information processing device" is an electronic device that receives and processes input information from a user.

[0068] "User information" refers to personal data and attributes related to individual users.

[0069] "Self-assessment information" refers to data about financial knowledge and skills as assessed by the user themselves.

[0070] "Initial assessment" is an analysis based on user information and self-assessment information to understand the user's current level of financial knowledge.

[0071] A "learning plan" is an educational program designed individually based on the user's evaluation results.

[0072] A "machine learning model" is an intelligent system composed of algorithms used to analyze data and make predictions or decisions.

[0073] "Dialogue format" refers to a method in which the user and the system exchange information through questions and answers.

[0074] "Dialogue history" refers to a record of questions and answers exchanged between the user and the system.

[0075] "Knowledge acquisition level" is an indicator that shows how much knowledge a user has gained through learning.

[0076] "Feedback" refers to evaluations and advice provided based on the user's learning outcomes.

[0077] "Financial activities" refer to economic transactions and actions such as asset management and investment.

[0078] One embodiment of this invention is an interactive educational system for improving users' financial literacy. Specifically, the user, terminal, and server work together.

[0079] The server first receives information collected from the user through an information processing device, which includes self-assessment data on age, occupation, and current financial knowledge. The server then performs an initial assessment to analyze the user's financial knowledge level and create an individualized learning plan. In this process, the Python Pandas library is used as a data analysis tool to develop a learning plan based on the assessment.

[0080] The terminal is responsible for executing the learning plan received from the server and providing information to the user in an interactive format. Questions from the user are input through the terminal and sent as prompts to the generating AI model, generating responses in real time. For example, an open-source neural network framework is used for the AI ​​model. As a concrete example, when the user inputs the prompt "Please tell me about how the stock market works," the AI ​​model responds.

[0081] Users can learn about financial concepts and specific products through their devices. The level of knowledge acquired during the learning process is evaluated by the server analyzing the history of conversations between the user and the AI ​​model. The evaluation results are sent to the device as feedback to support the user's further improvement of financial knowledge. For example, if a user asks, "I want to know about NISA," the AI ​​model will respond, "NISA is a small-amount investment tax exemption system that offers tax benefits for certain investments."

[0082] This system can provide a comprehensive learning environment by suggesting appropriate financial activities to users and encouraging their participation in those activities.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] The server receives basic information and self-assessment data provided by the user through an information processing device as input. This includes age, occupation, income, and self-assessment of financial knowledge. The server stores this data in a database and uses it as foundational information for initial assessment. The data is preprocessed using the Pandas library and prepared in a parseable format.

[0086] Step 2:

[0087] The server performs an initial assessment based on the data collected in Step 1. This initial assessment involves statistical analysis to measure the user's current financial literacy level. The results of this analysis are then output, evaluating the user's financial knowledge level in numerical and categorical formats, and a report is generated.

[0088] Step 3:

[0089] The server generates a personalized learning plan based on the results of the initial assessment. Using the assessment results as input, it constructs an optimal learning course tailored to the user's knowledge level and interests. Specifically, it uses machine learning algorithms to select the most suitable generative AI model for the user and designs learning topics and schedules. This plan is output as a digital document and sent to the terminal.

[0090] Step 4:

[0091] The terminal provides information to the user in an interactive format based on a learning plan received from the server. The user enters prompts on the terminal to begin interacting with the generating AI model. The model receives user questions as input and generates immediate responses using interactive natural language processing. These responses are displayed on the terminal, allowing the user to expand their financial knowledge.

[0092] Step 5:

[0093] As user interactions on their devices accumulate, the server analyzes this dialogue history. It takes past dialogue data as input and applies data mining techniques to evaluate the user's knowledge acquisition level. The evaluation results are generated on the server and output as feedback to the user.

[0094] Step 6:

[0095] Based on the evaluation results from Step 5, the server provides feedback to the user and suggests specific financial activities and services. This helps the user to have opportunities to participate in more practical financial activities. The suggested activities are notified to the user via the terminal, encouraging them to take concrete action.

[0096] (Application Example 1)

[0097] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0098] A challenge exists in that users with insufficient financial literacy find it difficult to select appropriate electronic transactions and use services wisely. Therefore, there is a need for a system that provides information and transaction suggestions tailored to the user's knowledge level, thereby improving their individual financial literacy.

[0099] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0100] In this invention, the server includes: a device means for inputting multiple user data and performing an initial evaluation; a device means for generating a learning plan based on the user evaluation and providing information in an interactive format using a selected machine learning model; and an information providing device means for presenting the optimal electronic transaction to the user. This enables users to improve their individual financial knowledge while obtaining appropriate information to select the optimal electronic transaction.

[0101] "User data" refers to information related to individual users that the system collects for initial evaluation.

[0102] "Initial assessment" is a process to understand users' financial literacy levels and needs based on collected user data.

[0103] A "learning plan" is an educational program designed to meet individual needs and interests, based on the user's evaluation results.

[0104] A "machine learning model" is a program that uses artificial intelligence technology selected to provide knowledge through interaction with users.

[0105] A "device that provides information in an interactive format" is a system that has an interface for transmitting necessary knowledge and information through interaction with the user.

[0106] An "information provision device" is a device that has the function of providing information to enable users to understand and select the most suitable electronic transaction based on their individual needs.

[0107] "Electronic trading" refers to a method of transaction for providing and using financial products and services electronically.

[0108] The system for realizing this invention mainly consists of a server and a user terminal. The server receives user data and performs an initial evaluation using an AI model. This makes it possible to understand the user's financial knowledge level and generate an individualized learning plan.

[0109] Specifically, the server first analyzes basic information and self-assessment data on finances provided by the user, and then sets a customized learning plan based on the initial assessment results. The technology used here is a generative AI model, which provides information to the user in an interactive format.

[0110] The user terminal is designed as a smartphone application, allowing users to ask questions through the device. A conversational agent using a selected machine learning model provides real-time answers to user questions. Through this interaction, users can expand their financial knowledge and gain a deeper understanding of electronic trading and investment.

[0111] As a concrete example, consider a scenario where a user enters "What is the most efficient way to accumulate points?" into their terminal. The server's generated AI model responds, "You can maximize savings and rewards by combining different credit cards." This allows the user to gain practical knowledge to make appropriate decisions when conducting electronic transactions.

[0112] Furthermore, the user's learning progress and interaction history are analyzed on the server, and based on this evaluation, feedback and optimal suggestions regarding electronic transactions are provided to the user. In this way, an environment is provided in which users can continuously improve their financial knowledge.

[0113] An example of a prompt might be, "Please give me advice on how to optimize my points system, especially regarding the use of multiple credit cards." Based on this prompt, the AI ​​model generates an appropriate response and provides information to the user.

[0114] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0115] Step 1:

[0116] The server receives basic information and self-assessment data regarding finances provided by the user. This provides the foundational data needed to understand the user's current status. The inputs here are the user's personal information and self-assessment data, and the assessment data is stored on the server as output.

[0117] Step 2:

[0118] The server uses a generative AI model to perform an initial financial literacy assessment based on the received evaluation data. This process analyzes the input data, processes it to identify the user's financial knowledge level, and outputs the evaluation result.

[0119] Step 3:

[0120] The server generates a personalized learning plan based on the initial assessment results. Here, it determines the learning content tailored to each user's knowledge level and interests. It uses the assessment results as input and outputs a learning plan based on them.

[0121] Step 4:

[0122] The terminal uses a selected generative AI model to provide information to the user in an interactive format. The user asks questions by entering prompts through the terminal, and the AI ​​generates answers in real time. The input is the user's prompt, and the output is the answer generated by the AI.

[0123] Step 5:

[0124] The server analyzes the user's dialogue history and learning progress to evaluate their level of understanding. Based on this analysis, the server generates feedback. The input is the dialogue history, and the output is feedback information.

[0125] Step 6:

[0126] The server provides information to the user to offer appropriate electronic transaction suggestions based on the user's level of understanding. At this stage, the evaluated level of understanding is used as input to output suggestions for the most suitable transactions and services.

[0127] Step 7:

[0128] When a user participates in a proposed electronic transaction, the terminal provides support. It receives user actions as input and supports smooth transactions by confirming participation in the transaction and outputting necessary information.

[0129] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0130] This invention aims to provide a more personalized learning experience by combining an emotional engine with an educational system designed to improve users' financial literacy. The program of this system is described below in natural language.

[0131] The server receives basic information and self-assessment data provided by the user and performs an initial evaluation. Based on this evaluation, it determines the user's financial literacy level and generates a personalized learning plan. This plan selects the optimal artificial intelligence model for each user and forms a framework for providing learning in an interactive format.

[0132] The emotion engine is built into the user's device and estimates the user's emotional state in real time from data such as voice tone, facial expressions, and input speed during interactions. This information is sent to a server and used to adjust the learning plan.

[0133] Specifically, if the device detects that the user is experiencing stress, it will slow down the learning pace and adjust to provide more relaxing content. This makes the user's learning experience more comfortable and effective.

[0134] On the other hand, if a user shows interest, the server can capitalize on this positive sentiment and provide more in-depth information or additional learning opportunities. For example, if a user asks, "I want to know more about NISA," and shows curiosity, the server will present detailed information about the benefits and uses of NISA to help them understand investing.

[0135] Using the history of the dialogue session and the user's sentiment information, the server more accurately assesses the user's level of understanding. Based on this assessment, it provides feedback and suggests necessary improvements and supplementary information to help the user progress to the next learning stage.

[0136] Furthermore, once the server determines that the user has acquired sufficient knowledge, it will suggest specific financial services. These suggestions are customized to take into account the user's emotional state and level of understanding, and are delivered at the optimal time and with the most relevant content.

[0137] Ultimately, the device guides users through the process of implementing the proposed financial services, providing emotional support to help them successfully build their wealth. In this way, the system aims to improve users' financial knowledge while also providing emotional support, thereby promoting sustainable learning and action.

[0138] The following describes the processing flow.

[0139] Step 1:

[0140] The server receives basic information and a self-assessment questionnaire about finances when a user registers for the app. This provides a basis for an initial assessment of the user's financial knowledge level.

[0141] Step 2:

[0142] The server generates a learning plan based on initial evaluation data. It selects an AI model suitable for each user and builds a system to support learning through dialogue.

[0143] Step 3:

[0144] The device activates the emotion engine along with the generated learning plan, preparing the user to begin the learning session.

[0145] Step 4:

[0146] During learning, the emotion engine analyzes the user's voice tone, facial expressions, and input speed in real time to estimate the user's emotional state.

[0147] Step 5:

[0148] The device adjusts the content of the conversation according to the estimated emotional state. For example, if the user is feeling stressed, it will slow down the conversation and provide relaxing content.

[0149] Step 6:

[0150] If a user shows interest or a positive response, the server will use this information to provide additional materials and specific examples, thereby deepening the user's understanding.

[0151] Step 7:

[0152] As the learning session progresses, the server integrates dialogue and sentiment data to evaluate the user's level of understanding.

[0153] Step 8:

[0154] The device provides feedback to the user based on the evaluation results, pointing out areas for further learning and improvement.

[0155] Step 9:

[0156] Once sufficient user knowledge is confirmed, the server takes their emotional state into consideration and suggests available financial services. These suggestions are customized to suit the user's emotions and level of understanding.

[0157] Step 10:

[0158] The terminal provides users with details of the proposed financial services and guides them to support their implementation. This includes the steps to take to participate in the appropriate financial services.

[0159] Step 11:

[0160] As users select a service and begin taking action, the device provides real-time support, including emotional support as needed.

[0161] Through this series of steps, the system expands users' financial knowledge and supports sustainable and effective wealth building.

[0162] (Example 2)

[0163] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0164] In recent years, numerous educational programs aimed at improving individual financial literacy have been offered. However, traditional systems often provide learning content in a uniform manner, which has the drawback of not adequately addressing the individual understanding levels and emotional responses of learners. Furthermore, there is a need for a system that can immediately adapt to emotional stress and changes in understanding during the learning process.

[0165] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0166] In this invention, the server includes means for inputting multiple pieces of information and performing a basic assessment; means for generating an educational plan based on the assessment and providing the content in an interactive format using a selected machine learning model; and means for analyzing the emotional state and dynamically adjusting the educational plan based on this. This makes it possible to provide a personalized educational experience that is tailored to the individual emotional state and level of understanding of each learner.

[0167] "Information" includes basic data about the user and data based on self-assessment.

[0168] "Basic assessment" is the process of determining the user's knowledge level and learning needs using the information provided.

[0169] An "educational plan" is an individualized learning plan created according to the user's learning needs and knowledge level.

[0170] A "machine learning model" is an artificial intelligence technology used to provide learning content and to interact with users.

[0171] "Emotional state" refers to the psychological and emotional state estimated from data such as the user's voice tone, facial expressions, and typing speed.

[0172] "Dynamic adjustment" refers to a process where the educational plan changes in real time according to the user's emotional state and level of understanding.

[0173] "Comprehension level" refers to the degree to which a user understands the learning material.

[0174] Personalization is the process of providing a learning experience optimized for each individual user.

[0175] A description of the embodiment for carrying out the invention will be provided.

[0176] In this system, the server collects information provided by the user and performs a basic user assessment based on that information. The server utilizes a database to manage the user's basic data and self-assessment data. For the initial assessment, a computer algorithm is used to analyze this data and clearly determine the user's level of financial knowledge.

[0177] Subsequently, the server generates an educational plan based on the user's evaluation results. This plan utilizes a generative AI model as a machine learning model. For example, the OpenAI® language model can be used as the generative AI model. This AI model provides learning content to the user in an interactive format, facilitating a personalized educational experience.

[0178] The device has a built-in emotion engine that analyzes data such as voice tone, facial expressions, and input speed in real time during interactions with the user to estimate their emotional state. The emotional information detected by the device is sent to a server, which dynamically adjusts the learning plan based on this information. For example, if the user is feeling stressed, the difficulty level of the learning material is lowered and the content is switched to something more relaxing.

[0179] As users progress through interactive sessions, they receive feedback on what they understand and get suggestions for moving on to the next learning stage. If a user uses the prompt "I want to know more about NISA," the server can respond to this request by providing detailed information and examples of its use.

[0180] In this way, the system efficiently improves users' financial knowledge while providing a personalized learning experience that also takes their emotional state into consideration. This mechanism allows users to receive continuous education in a stress-free manner.

[0181] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0182] Step 1:

[0183] The server receives basic information and self-assessment data from the user. This data includes age, occupation, and financial knowledge level. The server stores this information in a database and uses it as input for the initial assessment. The server uses computer algorithms to analyze this data and determine the user's financial literacy level. The analysis results in an assessment of the user's financial knowledge level.

[0184] Step 2:

[0185] The server generates individualized learning plans based on the user's evaluation results. The input is the previously obtained financial literacy level data. The output is a user-specific learning plan, with learning content prepared interactively by a selected generative AI model. For example, learning scenarios and specific learning materials are determined using the generative AI model.

[0186] Step 3:

[0187] The device uses an emotion engine to analyze the user's emotional state in real time. Inputs include the user's voice tone, facial expression data, and input speed. The output obtained by analyzing this data is an estimate of the user's emotional state. This information is transmitted to the server in real time and used to adjust the learning plan.

[0188] Step 4:

[0189] The server receives emotional state data transmitted from the terminal and dynamically adjusts the educational plan. The input used is an estimated emotional state. Based on this data, the server adjusts the plan to ease the learning content if the user is stressed, and to provide more detailed information if they are interested. As a result, the learning materials and their pace provided to the user are optimized.

[0190] Step 5:

[0191] Users learn by interacting with the generative AI model. They can request additional information or support using prompts. Input includes user questions and requests. The generative AI model processes data based on these inputs and outputs the necessary information. For example, if the user enters the prompt "I want to know more about NISA," detailed information and specific examples will be presented.

[0192] Step 6:

[0193] The server evaluates the user's understanding using the history of conversation sessions and sentiment data. Input includes past conversation history and real-time sentiment data. The evaluation results are output as an indicator of how well the user understands the learning material. Based on this evaluation, feedback and suggestions for the next learning steps are provided.

[0194] Step 7:

[0195] Once the server determines that the user has acquired sufficient knowledge, it suggests appropriate financial services, taking into account the user's level of understanding and emotional state. The input data for the suggestions includes the user's understanding assessment and emotional data, while the output includes individually customized service suggestions. Based on this, the user can choose to take further action.

[0196] (Application Example 2)

[0197] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0198] In educational programs aimed at improving users' financial literacy, it is difficult to provide an optimal learning experience tailored to each user's level of understanding and interests. Furthermore, it is necessary to grasp the user's emotional state in real time and adjust the learning content accordingly, but effective means of achieving this are limited. This invention aims to solve these problems and enhance the learning effectiveness and satisfaction of users.

[0199] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0200] In this invention, the server includes: a device means for inputting multiple individual registration information and performing an initial evaluation; a device means for generating a learning plan based on the registrant's evaluation and providing information in response format using a selected intelligent model; and a device means for analyzing emotions using speech recognition and facial recognition devices and dynamically adjusting the content of the information provided in response format based on the results. This makes it possible to provide an individualized and optimal learning experience while taking into account the user's emotional state.

[0201] "Individual registration information" refers to information entered based on each user's characteristics and needs, and is used to understand the individual characteristics of each user.

[0202] "Initial assessment" is a process of making a preliminary determination of a user's current knowledge and skills based on the individual registration information they provide.

[0203] A "learning plan" is a plan that outlines individualized steps and a curriculum to help users achieve their learning goals, based on their evaluation results.

[0204] An "intelligent model" is a program or algorithm that uses artificial intelligence to support user learning and has the function of providing information tailored to the individual needs of the user.

[0205] "Response format" refers to the form of interaction with the user, a process that provides information through dialogue and supports smooth learning.

[0206] "Speech recognition" is a technology that analyzes a user's speech and converts its content into text data or semantic data.

[0207] A "face recognition device" is a device that uses a camera and software to detect and analyze a user's facial expressions and emotions, and to utilize this information for learning purposes.

[0208] "Emotional analysis" is a process that estimates and evaluates users' emotional states based on their voice and facial expression data.

[0209] "Response history" refers to records of past conversations with the user and is data used to understand the user's learning process and level of comprehension.

[0210] "Asset management services" refer to financial products and programs designed to efficiently manage and increase a user's assets, and are proposed according to the user's needs.

[0211] This invention aims to realize a financial literacy improvement system that utilizes emotion analysis. The system is built through the interaction of a server, terminal, and user, providing users with a personalized financial learning experience.

[0212] First, the user accesses the system using a smart device. The device uses the Google® Cloud Speech-to-Text API to convert speech into text data and the Azure® Face API to analyze the user's facial expressions through video data acquired from the camera. This data is sent to a server and used to estimate the user's emotional state in real time.

[0213] The server uses the OpenAI GPT model to generate optimal learning content based on the user's emotional state and past response history. The information displayed in an interactive format is adjusted according to the user's emotional state, providing relaxing content to stressed users and detailed information to users who show interest.

[0214] As a concrete example, if a user says, "I want to learn about Tsumitate NISA," the system will provide a basic explanation if the user appears nervous, but if they seem to understand more, it will present deeper knowledge and practical examples. The generating AI model uses prompts to provide information. Prompts such as, "Please explain Tsumitate NISA simply for beginners. Use language that will help the user relax," will be used.

[0215] This system allows users with different learning levels and emotional states to receive an optimal learning experience, thereby enabling them to improve their financial skills.

[0216] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0217] Step 1:

[0218] Users log in to the system via their smart devices. The input here is the user's individual registration information, forming a user profile. This profile collects the user's past history and basic information. The output is a dataset for initial evaluation.

[0219] Step 2:

[0220] The device uses the Google Cloud Speech-to-Text API to convert the user's voice data into text data. The input is an audio signal, which is converted into text using speech recognition technology. The output is text data that reflects the user's intent.

[0221] Step 3:

[0222] The device analyzes the user's facial expressions through video data acquired from the camera using the Azure Face API. The input is a video signal, and facial recognition technology extracts information about the user's emotions. The output is a dataset showing the user's current emotional state.

[0223] Step 4:

[0224] The server generates appropriate training content using the OpenAI GPT model, based on the user intent and sentiment data obtained in steps 2 and 3. In this process, the user's intent (prompt text) and sentiment state are provided as input. The model analyzes this and selects the most suitable content for the user. The output is text data containing the specific training content.

[0225] Step 5:

[0226] The device displays text data sent from the server to the user. The displayed content is tailored based on the user's emotional state and presented in an easy-to-understand format. The input is learning content from the server, and the output is learning navigation that facilitates user understanding.

[0227] Step 6:

[0228] Based on user responses and new questions, the process from steps 2 to 5 is repeated, and learning progresses. The server manages this cycle and provides feedback sentences and new learning options based on the generated AI model as needed.

[0229] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0230] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0231] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0232] [Second Embodiment]

[0233] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0234] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0235] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0236] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0237] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0238] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0239] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0240] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0241] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0242] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0243] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0244] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0245] This invention provides a system for improving users' financial knowledge, and is particularly characterized by its interactive educational approach using an artificial intelligence model. The system's program is described below in natural language.

[0246] The server first receives basic information and self-assessment data about finances provided by the user and performs an initial assessment. This assessment forms the basis for understanding the user's current level of financial literacy and creating an appropriate educational plan.

[0247] Next, the server creates a personalized learning plan based on the initial evaluation results. Specifically, it selects the optimal artificial intelligence model according to each user's knowledge level and interests, and designs a learning course using that model. This plan includes the topics and schedule necessary for the user's learning.

[0248] Once a user begins learning based on this plan, the device will provide information in an interactive format using a selected artificial intelligence model. Users can ask questions through the device, and the AI ​​model will respond in real time, supporting the expansion of the user's financial knowledge.

[0249] For example, if a user asks the device, "I want to know about NISA," the artificial intelligence model will respond with something like, "NISA is a small-amount investment tax exemption system that offers tax benefits for specific investments." This allows users to obtain specific and easy-to-understand information through direct dialogue.

[0250] After a certain period of conversation, the server analyzes the history and evaluates the user's level of knowledge acquisition. Based on this evaluation, the terminal provides feedback to the user to encourage further understanding. Furthermore, depending on the evaluation results, it suggests appropriate financial services related to investment and asset management and provides support when the user takes actual action.

[0251] In this way, the system provides an effective learning environment that gradually improves users' financial literacy and leads to actual asset building.

[0252] The following describes the processing flow.

[0253] Step 1:

[0254] The server receives basic information and a self-assessment questionnaire about finances from users when they register for the app. This provides a basis for an initial assessment of the user's current financial literacy level.

[0255] Step 2:

[0256] The server generates a customized learning plan for each user based on an initial assessment. This plan designs the optimal artificial intelligence model and learning course to match the user's knowledge level and interests.

[0257] Step 3:

[0258] The terminal presents the user with a learning plan generated on the server and provides an interface to encourage them to start learning. The user can then begin a learning session based on this plan.

[0259] Step 4:

[0260] Once a user begins a learning session, the device uses a selected artificial intelligence model to provide financial information through interaction with the user. The user asks questions and receives immediate responses from the device, thus advancing the learning process.

[0261] Step 5:

[0262] The server analyzes the user's learning history and dialogue to assess the user's level of understanding. Based on this assessment, it determines the user's progress level and decides on a course of action for further learning or correction.

[0263] Step 6:

[0264] The terminal provides the user with feedback based on the evaluation results provided by the server. It offers advice to help with future learning and information to improve understanding.

[0265] Step 7:

[0266] Once the server determines that the user has acquired sufficient knowledge, it will suggest specific financial services to the user (e.g., investment programs or account opening procedures).

[0267] Step 8:

[0268] The terminal presents the user with specific information about the proposed financial services and provides an interface to support the next action. The user uses this information to select specific investment and asset management actions.

[0269] Step 9:

[0270] If the user takes action based on the suggestion, the device will guide them through the necessary steps and provide ongoing support.

[0271] (Example 1)

[0272] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0273] In modern society, financial literacy is becoming increasingly important, yet many people lack sufficient financial literacy and are unable to manage their assets effectively. To address this problem, there is a need for a system that provides learning methods optimized for individual users and effectively improves their financial knowledge.

[0274] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0275] In this invention, the server includes means for inputting user information and self-assessment information into an information processing device and performing an initial assessment; means for generating an individualized learning plan based on the user's initial assessment and providing information in an interactive format using a selected machine learning model; and means for analyzing the user's level of knowledge acquisition from the dialogue history and providing feedback based on the assessment results. This makes it possible to efficiently improve financial literacy through a learning plan optimized for each individual user.

[0276] An "information processing device" is an electronic device that receives input information from a user and performs processing.

[0277] "User information" refers to personal data and attributes related to individual users.

[0278] "Self-evaluation information" is data related to the financial knowledge and skills evaluated by the user himself / herself.

[0279] "Initial evaluation" is an analysis for grasping the current financial knowledge level of a user based on user information and self-evaluation information.

[0280] "Learning plan" is an educational progress program designed individually based on the evaluation results of a user.

[0281] "Machine learning model" is an intelligent system composed of algorithms for analyzing data and making predictions or decisions.

[0282] "Dialogue form" is a method in which a user and a system exchange information through questions and answers.

[0283] "Dialogue history" is a record of questions and responses made between a user and a system.

[0284] "Knowledge acquisition degree" is an index indicating how much knowledge a user has obtained through learning.

[0285] "Feedback" refers to evaluations and advice provided based on the learning results of a user. <![CDATA[ ]]

[0286] "Financial activities" refer to economic transactions and actions such as asset management and investment.

[0287] The form for implementing this invention is an interactive education system for improving the financial literacy of users. Specifically, a user, a terminal, and a server cooperate to perform operations.

[0288] The server first receives information collected from the user through an information processing device, which includes self-assessment data on age, occupation, and current financial knowledge. The server then performs an initial assessment to analyze the user's financial knowledge level and create an individualized learning plan. In this process, the Python Pandas library is used as a data analysis tool to develop a learning plan based on the assessment.

[0289] The terminal is responsible for executing the learning plan received from the server and providing information to the user in an interactive format. Questions from the user are input through the terminal and sent as prompts to the generating AI model, generating responses in real time. For example, an open-source neural network framework is used for the AI ​​model. As a concrete example, when the user inputs the prompt "Please tell me about how the stock market works," the AI ​​model responds.

[0290] Users can learn about financial concepts and specific products through their devices. The level of knowledge acquired during the learning process is evaluated by the server analyzing the history of conversations between the user and the AI ​​model. The evaluation results are sent to the device as feedback to support the user's further improvement of financial knowledge. For example, if a user asks, "I want to know about NISA," the AI ​​model will respond, "NISA is a small-amount investment tax exemption system that offers tax benefits for certain investments."

[0291] This system can provide a comprehensive learning environment by suggesting appropriate financial activities to users and encouraging their participation in those activities.

[0292] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0293] Step 1:

[0294] The server receives basic information and self-assessment data provided by the user through an information processing device as input. This includes age, occupation, income, and self-assessment of financial knowledge. The server stores this data in a database and uses it as foundational information for initial assessment. The data is preprocessed using the Pandas library and prepared in a parseable format.

[0295] Step 2:

[0296] The server performs an initial assessment based on the data collected in Step 1. This initial assessment involves statistical analysis to measure the user's current financial literacy level. The results of this analysis are then output, evaluating the user's financial knowledge level in numerical and categorical formats, and a report is generated.

[0297] Step 3:

[0298] The server generates a personalized learning plan based on the results of the initial assessment. Using the assessment results as input, it constructs an optimal learning course tailored to the user's knowledge level and interests. Specifically, it uses machine learning algorithms to select the most suitable generative AI model for the user and designs learning topics and schedules. This plan is output as a digital document and sent to the terminal.

[0299] Step 4:

[0300] The terminal provides information to the user in an interactive format based on a learning plan received from the server. The user enters prompts on the terminal to begin interacting with the generating AI model. The model receives user questions as input and generates immediate responses using interactive natural language processing. These responses are displayed on the terminal, allowing the user to expand their financial knowledge.

[0301] Step 5:

[0302] When interactions on the user's terminal are accumulated, the server analyzes this conversation history. It takes in past conversation data as input and applies data mining techniques to evaluate the user's knowledge acquisition level. The evaluation results are generated on the server and output as feedback to the user.

[0303] Step 6:

[0304] Based on the evaluation results in Step 5, the server provides feedback to the user and proposes specific financial activities and services. This enables the user to be assisted in obtaining opportunities to participate in more practical financial activities. The proposed activities are notified to the user via the terminal to facilitate specific actions.

[0305] (Application Example 1)

[0306] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0307] There is an issue that users with insufficient financial literacy have difficulty selecting appropriate electronic transactions and using services wisely. Therefore, there is a need for a system that provides information and transaction proposals according to the user's knowledge level to achieve individual financial knowledge improvement.

[0308] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0309] In this invention, the server includes [device means for inputting multiple user data and performing an initial evaluation, [device means for generating a learning plan based on the user's evaluation and providing information in an interactive form using a selected machine learning model, [device means for providing information for presenting an optimal electronic transaction to the user. This enables the user to obtain appropriate information for selecting an optimal electronic transaction while improving individual financial knowledge.

[0310] "User data" refers to information related to individual users that the system collects for initial evaluation.

[0311] "Initial assessment" is a process to understand users' financial literacy levels and needs based on collected user data.

[0312] A "learning plan" is an educational program designed to meet individual needs and interests, based on the user's evaluation results.

[0313] A "machine learning model" is a program that uses artificial intelligence technology selected to provide knowledge through interaction with users.

[0314] A "device that provides information in an interactive format" is a system that has an interface for transmitting necessary knowledge and information through interaction with the user.

[0315] An "information provision device" is a device that has the function of providing information to enable users to understand and select the most suitable electronic transaction based on their individual needs.

[0316] "Electronic trading" refers to a method of transaction for providing and using financial products and services electronically.

[0317] The system for realizing this invention mainly consists of a server and a user terminal. The server receives user data and performs an initial evaluation using an AI model. This makes it possible to understand the user's financial knowledge level and generate an individualized learning plan.

[0318] Specifically, the server first analyzes basic information and self-assessment data on finances provided by the user, and then sets a customized learning plan based on the initial assessment results. The technology used here is a generative AI model, which provides information to the user in an interactive format.

[0319] The user terminal is designed as a smartphone application, allowing users to ask questions through the device. A conversational agent using a selected machine learning model provides real-time answers to user questions. Through this interaction, users can expand their financial knowledge and gain a deeper understanding of electronic trading and investment.

[0320] As a concrete example, consider a scenario where a user enters "What is the most efficient way to accumulate points?" into their terminal. The server's generated AI model responds, "You can maximize savings and rewards by combining different credit cards." This allows the user to gain practical knowledge to make appropriate decisions when conducting electronic transactions.

[0321] Furthermore, the user's learning progress and interaction history are analyzed on the server, and based on this evaluation, feedback and optimal suggestions regarding electronic transactions are provided to the user. In this way, an environment is provided in which users can continuously improve their financial knowledge.

[0322] An example of a prompt might be, "Please give me advice on how to optimize my points system, especially regarding the use of multiple credit cards." Based on this prompt, the AI ​​model generates an appropriate response and provides information to the user.

[0323] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0324] Step 1:

[0325] The server receives basic information and self-assessment data regarding finances provided by the user. This provides the foundational data needed to understand the user's current status. The inputs here are the user's personal information and self-assessment data, and the assessment data is stored on the server as output.

[0326] Step 2:

[0327] The server uses a generative AI model to perform an initial financial literacy assessment based on the received evaluation data. This process analyzes the input data, processes it to identify the user's financial knowledge level, and outputs the evaluation result.

[0328] Step 3:

[0329] The server generates a personalized learning plan based on the initial assessment results. Here, it determines the learning content tailored to each user's knowledge level and interests. It uses the assessment results as input and outputs a learning plan based on them.

[0330] Step 4:

[0331] The terminal uses a selected generative AI model to provide information to the user in an interactive format. The user asks questions by entering prompts through the terminal, and the AI ​​generates answers in real time. The input is the user's prompt, and the output is the answer generated by the AI.

[0332] Step 5:

[0333] The server analyzes the user's dialogue history and learning progress to evaluate their level of understanding. Based on this analysis, the server generates feedback. The input is the dialogue history, and the output is feedback information.

[0334] Step 6:

[0335] The server provides information to the user to offer appropriate electronic transaction suggestions based on the user's level of understanding. At this stage, the evaluated level of understanding is used as input to output suggestions for the most suitable transactions and services.

[0336] Step 7:

[0337] When a user participates in a proposed electronic transaction, the terminal provides support. It receives user actions as input and supports smooth transactions by confirming participation in the transaction and outputting necessary information.

[0338] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0339] This invention aims to provide a more personalized learning experience by combining an emotional engine with an educational system designed to improve users' financial literacy. The program of this system is described below in natural language.

[0340] The server receives basic information and self-assessment data provided by the user and performs an initial evaluation. Based on this evaluation, it determines the user's financial literacy level and generates a personalized learning plan. This plan selects the optimal artificial intelligence model for each user and forms a framework for providing learning in an interactive format.

[0341] The emotion engine is built into the user's device and estimates the user's emotional state in real time from data such as voice tone, facial expressions, and input speed during interactions. This information is sent to a server and used to adjust the learning plan.

[0342] Specifically, if the device detects that the user is experiencing stress, it will slow down the learning pace and adjust to provide more relaxing content. This makes the user's learning experience more comfortable and effective.

[0343] On the other hand, if a user shows interest, the server can capitalize on this positive sentiment and provide more in-depth information or additional learning opportunities. For example, if a user asks, "I want to know more about NISA," and shows curiosity, the server will present detailed information about the benefits and uses of NISA to help them understand investing.

[0344] Using the history of the dialogue session and the user's sentiment information, the server more accurately assesses the user's level of understanding. Based on this assessment, it provides feedback and suggests necessary improvements and supplementary information to help the user progress to the next learning stage.

[0345] Furthermore, once the server determines that the user has acquired sufficient knowledge, it will suggest specific financial services. These suggestions are customized to take into account the user's emotional state and level of understanding, and are delivered at the optimal time and with the most relevant content.

[0346] Ultimately, the device guides users through the process of implementing the proposed financial services, providing emotional support to help them successfully build their wealth. In this way, the system aims to improve users' financial knowledge while also providing emotional support, thereby promoting sustainable learning and action.

[0347] The following describes the processing flow.

[0348] Step 1:

[0349] The server receives basic information and a self-assessment questionnaire about finances when a user registers for the app. This provides a basis for an initial assessment of the user's financial knowledge level.

[0350] Step 2:

[0351] The server generates a learning plan based on initial evaluation data. It selects an AI model suitable for each user and builds a system to support learning through dialogue.

[0352] Step 3:

[0353] The device activates the emotion engine along with the generated learning plan, preparing the user to begin the learning session.

[0354] Step 4:

[0355] During learning, the emotion engine analyzes the user's voice tone, facial expressions, and input speed in real time to estimate the user's emotional state.

[0356] Step 5:

[0357] The device adjusts the conversation content according to the estimated emotional state. For example, if the user is feeling stressed, it will slow down the conversation and provide relaxing content.

[0358] Step 6:

[0359] If a user shows interest or a positive response, the server will use this information to provide additional materials and specific examples, thereby deepening the user's understanding.

[0360] Step 7:

[0361] As the learning session progresses, the server integrates dialogue and sentiment data to evaluate the user's level of understanding.

[0362] Step 8:

[0363] The device provides feedback to the user based on the evaluation results, pointing out areas for further learning and improvement.

[0364] Step 9:

[0365] Once sufficient user knowledge is confirmed, the server takes their emotional state into consideration and suggests available financial services. These suggestions are customized to suit the user's emotions and level of understanding.

[0366] Step 10:

[0367] The terminal provides users with details of the proposed financial services and guides them to support their implementation. This includes the steps to take to participate in the appropriate financial services.

[0368] Step 11:

[0369] As users select a service and begin taking action, the device provides real-time support, including emotional support as needed.

[0370] Through this series of steps, the system expands users' financial knowledge and supports sustainable and effective wealth building.

[0371] (Example 2)

[0372] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0373] In recent years, numerous educational programs aimed at improving individual financial literacy have been offered. However, traditional systems often provide learning content in a uniform manner, which has the drawback of not adequately addressing the individual understanding levels and emotional responses of learners. Furthermore, there is a need for a system that can immediately adapt to emotional stress and changes in understanding during the learning process.

[0374] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0375] In this invention, the server includes means for inputting multiple pieces of information and performing a basic assessment; means for generating an educational plan based on the assessment and providing the content in an interactive format using a selected machine learning model; and means for analyzing the emotional state and dynamically adjusting the educational plan based on this. This makes it possible to provide a personalized educational experience that is tailored to the individual emotional state and level of understanding of each learner.

[0376] "Information" includes basic data about the user and data based on self-assessment.

[0377] "Basic assessment" is the process of determining the user's knowledge level and learning needs using the information provided.

[0378] An "educational plan" is an individualized learning plan created according to the user's learning needs and knowledge level.

[0379] A "machine learning model" is an artificial intelligence technology used to provide learning content and to interact with users.

[0380] "Emotional state" refers to the psychological and emotional state estimated from data such as the user's voice tone, facial expressions, and typing speed.

[0381] "Dynamic adjustment" refers to a process where the educational plan changes in real time according to the user's emotional state and level of understanding.

[0382] "Comprehension level" refers to the degree to which a user understands the learning material.

[0383] Personalization is the process of providing a learning experience optimized for each individual user.

[0384] A description of the embodiment for carrying out the invention will be provided.

[0385] In this system, the server collects information provided by the user and performs a basic user assessment based on that information. The server utilizes a database to manage the user's basic data and self-assessment data. For the initial assessment, a computer algorithm is used to analyze this data and clearly determine the user's level of financial knowledge.

[0386] Subsequently, the server generates an educational plan based on the user's evaluation results. This plan utilizes a generative AI model as a machine learning model. For example, OpenAI's language model can be used as the generative AI model. This AI model provides learning content to the user in an interactive format, facilitating a personalized educational experience.

[0387] The device has a built-in emotion engine that analyzes data such as voice tone, facial expressions, and input speed in real time during interactions with the user to estimate their emotional state. The emotional information detected by the device is sent to a server, which dynamically adjusts the learning plan based on this information. For example, if the user is feeling stressed, the difficulty level of the learning material is lowered and the content is switched to something more relaxing.

[0388] As users progress through interactive sessions, they receive feedback on what they understand and get suggestions for moving on to the next learning stage. If a user uses the prompt "I want to know more about NISA," the server can respond to this request by providing detailed information and examples of its use.

[0389] In this way, the system efficiently improves users' financial knowledge while providing a personalized learning experience that also takes their emotional state into consideration. This mechanism allows users to receive continuous education in a stress-free manner.

[0390] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0391] Step 1:

[0392] The server receives basic information and self-assessment data from the user. This data includes age, occupation, and financial knowledge level. The server stores this information in a database and uses it as input for the initial assessment. The server uses computer algorithms to analyze this data and determine the user's financial literacy level. The analysis results in an assessment of the user's financial knowledge level.

[0393] Step 2:

[0394] The server generates individualized learning plans based on the user's evaluation results. The input is the previously obtained financial literacy level data. The output is a user-specific learning plan, with learning content prepared interactively by a selected generative AI model. For example, learning scenarios and specific learning materials are determined using the generative AI model.

[0395] Step 3:

[0396] The device uses an emotion engine to analyze the user's emotional state in real time. Inputs include the user's voice tone, facial expression data, and input speed. The output obtained by analyzing this data is an estimate of the user's emotional state. This information is transmitted to the server in real time and used to adjust the learning plan.

[0397] Step 4:

[0398] The server receives emotional state data transmitted from the terminal and dynamically adjusts the educational plan. The input used is an estimated emotional state. Based on this data, the server adjusts the plan to ease the learning content if the user is stressed, and to provide more detailed information if they are interested. As a result, the learning materials and their pace provided to the user are optimized.

[0399] Step 5:

[0400] Users learn by interacting with the generative AI model. They can request additional information or support using prompts. Input includes user questions and requests. The generative AI model processes data based on these inputs and outputs the necessary information. For example, if the user enters the prompt "I want to know more about NISA," detailed information and specific examples will be presented.

[0401] Step 6:

[0402] The server evaluates the user's understanding using the history of conversation sessions and sentiment data. Input includes past conversation history and real-time sentiment data. The evaluation results are output as an indicator of how well the user understands the learning material. Based on this evaluation, feedback and suggestions for the next learning steps are provided.

[0403] Step 7:

[0404] Once the server determines that the user has acquired sufficient knowledge, it suggests appropriate financial services, taking into account the user's level of understanding and emotional state. The input data for the suggestions includes the user's understanding assessment and emotional data, while the output includes individually customized service suggestions. Based on this, the user can choose to take further action.

[0405] (Application Example 2)

[0406] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0407] In educational programs aimed at improving users' financial literacy, it is difficult to provide an optimal learning experience tailored to each user's level of understanding and interests. Furthermore, it is necessary to grasp the user's emotional state in real time and adjust the learning content accordingly, but effective means of achieving this are limited. This invention aims to solve these problems and enhance the learning effectiveness and satisfaction of users.

[0408] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0409] In this invention, the server includes: a device means for inputting multiple individual registration information and performing an initial evaluation; a device means for generating a learning plan based on the registrant's evaluation and providing information in response format using a selected intelligent model; and a device means for analyzing emotions using speech recognition and facial recognition devices and dynamically adjusting the content of the information provided in response format based on the results. This makes it possible to provide an individualized and optimal learning experience while taking into account the user's emotional state.

[0410] "Individual registration information" refers to information entered based on each user's characteristics and needs, and is used to understand the individual characteristics of each user.

[0411] "Initial assessment" is a process of making a preliminary determination of a user's current knowledge and skills based on the individual registration information they provide.

[0412] A "learning plan" is a plan that outlines individualized steps and a curriculum to help users achieve their learning goals, based on their evaluation results.

[0413] An "intelligent model" is a program or algorithm that uses artificial intelligence to support user learning and has the function of providing information tailored to the individual needs of the user.

[0414] "Response format" refers to the form of interaction with the user, a process that provides information through dialogue and supports smooth learning.

[0415] "Speech recognition" is a technology that analyzes a user's speech and converts its content into text data or semantic data.

[0416] A "face recognition device" is a device that uses a camera and software to detect and analyze a user's facial expressions and emotions, and to utilize this information for learning purposes.

[0417] "Emotional analysis" is a process that estimates and evaluates users' emotional states based on their voice and facial expression data.

[0418] "Response history" refers to records of past conversations with the user and is data used to understand the user's learning process and level of comprehension.

[0419] "Asset management services" refer to financial products and programs designed to efficiently manage and increase a user's assets, and are proposed according to the user's needs.

[0420] This invention aims to realize a financial literacy improvement system that utilizes emotion analysis. The system is built through the interaction of a server, terminal, and user, providing users with a personalized financial learning experience.

[0421] First, the user accesses the system using a smart device. The device uses the Google Cloud Speech-to-Text API to convert speech into text data and the Azure Face API to analyze the user's facial expressions through video data acquired from the camera. This data is sent to a server and used to estimate the user's emotional state in real time.

[0422] The server uses the OpenAI GPT model to generate optimal learning content based on the user's emotional state and past response history. The information displayed in an interactive format is adjusted according to the user's emotional state, providing relaxing content to stressed users and detailed information to users who are interested.

[0423] As a concrete example, if a user says, "I want to learn about Tsumitate NISA," the system will provide a basic explanation if the user appears nervous, but if they seem to understand more, it will present deeper knowledge and practical examples. The generating AI model uses prompts to provide information. Prompts such as, "Please explain Tsumitate NISA simply for beginners. Use language that will help the user relax," will be used.

[0424] This system allows users with different learning levels and emotional states to receive an optimal learning experience, thereby enabling them to improve their financial skills.

[0425] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0426] Step 1:

[0427] Users log in to the system via their smart devices. The input here is the user's individual registration information, forming a user profile. This profile collects the user's past history and basic information. The output is a dataset for initial evaluation.

[0428] Step 2:

[0429] The device uses the Google Cloud Speech-to-Text API to convert the user's voice data into text data. The input is an audio signal, which is converted into text using speech recognition technology. The output is text data that reflects the user's intent.

[0430] Step 3:

[0431] The device analyzes the user's facial expressions through video data acquired from the camera using the Azure Face API. The input is a video signal, and facial recognition technology extracts information about the user's emotions. The output is a dataset showing the user's current emotional state.

[0432] Step 4:

[0433] The server generates appropriate training content using the OpenAI GPT model, based on the user intent and sentiment data obtained in steps 2 and 3. In this process, the user's intent (prompt text) and sentiment state are provided as input. The model analyzes this and selects the most suitable content for the user. The output is text data containing the specific training content.

[0434] Step 5:

[0435] The device displays text data sent from the server to the user. The displayed content is tailored based on the user's emotional state and presented in an easy-to-understand format. The input is learning content from the server, and the output is learning navigation that facilitates user understanding.

[0436] Step 6:

[0437] Based on user responses and new questions, the process from steps 2 to 5 is repeated, and learning progresses. The server manages this cycle and provides feedback sentences and new learning options based on the generated AI model as needed.

[0438] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0439] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0440] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0441] [Third Embodiment]

[0442] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0443] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0444] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0445] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0446] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0447] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0448] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0449] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0450] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0451] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0452] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0453] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0454] This invention provides a system for improving users' financial knowledge, and is particularly characterized by its interactive educational approach using an artificial intelligence model. The system's program is described below in natural language.

[0455] The server first receives basic information and self-assessment data about finances provided by the user and performs an initial assessment. This assessment forms the basis for understanding the user's current level of financial literacy and creating an appropriate educational plan.

[0456] Next, the server creates a personalized learning plan based on the initial evaluation results. Specifically, it selects the optimal artificial intelligence model according to each user's knowledge level and interests, and designs a learning course using that model. This plan includes the topics and schedule necessary for the user's learning.

[0457] Once a user begins learning based on this plan, the device will provide information in an interactive format using a selected artificial intelligence model. Users can ask questions through the device, and the AI ​​model will respond in real time, supporting the expansion of the user's financial knowledge.

[0458] For example, if a user asks the device, "I want to know about NISA," the artificial intelligence model will respond with something like, "NISA is a small-amount investment tax exemption system that offers tax benefits for specific investments." This allows users to obtain specific and easy-to-understand information through direct dialogue.

[0459] After a certain period of conversation, the server analyzes the history and evaluates the user's level of knowledge acquisition. Based on this evaluation, the terminal provides feedback to the user to encourage further understanding. Furthermore, depending on the evaluation results, it suggests appropriate financial services related to investment and asset management and provides support when the user takes actual action.

[0460] In this way, the system provides an effective learning environment that gradually improves users' financial literacy and leads to actual asset building.

[0461] The following describes the processing flow.

[0462] Step 1:

[0463] The server receives basic information and a self-assessment questionnaire about finances from users when they register for the app. This provides a basis for an initial assessment of the user's current financial literacy level.

[0464] Step 2:

[0465] The server generates a customized learning plan for each user based on an initial assessment. This plan designs the optimal artificial intelligence model and learning course to match the user's knowledge level and interests.

[0466] Step 3:

[0467] The terminal presents the user with a learning plan generated on the server and provides an interface to encourage them to start learning. The user can then begin a learning session based on this plan.

[0468] Step 4:

[0469] Once a user begins a learning session, the device uses a selected artificial intelligence model to provide financial information through interaction with the user. The user asks questions and receives immediate responses from the device, thus advancing the learning process.

[0470] Step 5:

[0471] The server analyzes the user's learning history and dialogue to assess the user's level of understanding. Based on this assessment, it determines the user's progress level and decides on a course of action for further learning or correction.

[0472] Step 6:

[0473] The terminal provides the user with feedback based on the evaluation results provided by the server. It offers advice to help with future learning and information to improve understanding.

[0474] Step 7:

[0475] Once the server determines that the user has acquired sufficient knowledge, it will suggest specific financial services to the user (e.g., investment programs or account opening procedures).

[0476] Step 8:

[0477] The terminal presents the user with specific information about the proposed financial services and provides an interface to support the next action. The user uses this information to select specific investment and asset management actions.

[0478] Step 9:

[0479] If the user takes action based on the suggestion, the device will guide them through the necessary steps and provide ongoing support.

[0480] (Example 1)

[0481] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0482] In modern society, financial literacy is becoming increasingly important, yet many people lack sufficient financial literacy and are unable to manage their assets effectively. To address this problem, there is a need for a system that provides learning methods optimized for individual users and effectively improves their financial knowledge.

[0483] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0484] In this invention, the server includes means for inputting user information and self-assessment information into an information processing device and performing an initial assessment; means for generating an individualized learning plan based on the user's initial assessment and providing information in an interactive format using a selected machine learning model; and means for analyzing the user's level of knowledge acquisition from the dialogue history and providing feedback based on the assessment results. This makes it possible to efficiently improve financial literacy through a learning plan optimized for each individual user.

[0485] An "information processing device" is an electronic device that receives and processes input information from a user.

[0486] "User information" refers to personal data and attributes related to individual users.

[0487] "Self-assessment information" refers to data about financial knowledge and skills as assessed by the user themselves.

[0488] "Initial assessment" is an analysis based on user information and self-assessment information to understand the user's current level of financial knowledge.

[0489] A "learning plan" is an educational program designed individually based on the user's evaluation results.

[0490] A "machine learning model" is an intelligent system composed of algorithms used to analyze data and make predictions or decisions.

[0491] "Dialogue format" refers to a method in which the user and the system exchange information through questions and answers.

[0492] "Dialogue history" refers to a record of questions and answers exchanged between the user and the system.

[0493] "Knowledge acquisition level" is an indicator that shows how much knowledge a user has gained through learning.

[0494] "Feedback" refers to evaluations and advice provided based on the user's learning outcomes.

[0495] "Financial activities" refer to economic transactions and actions such as asset management and investment.

[0496] One embodiment of this invention is an interactive educational system for improving users' financial literacy. Specifically, the user, terminal, and server work together.

[0497] The server first receives information collected from the user through an information processing device, which includes self-assessment data on age, occupation, and current financial knowledge. The server then performs an initial assessment to analyze the user's financial knowledge level and create an individualized learning plan. In this process, the Python Pandas library is used as a data analysis tool to develop a learning plan based on the assessment.

[0498] The terminal is responsible for executing the learning plan received from the server and providing information to the user in an interactive format. Questions from the user are input through the terminal and sent as prompts to the generating AI model, generating responses in real time. For example, an open-source neural network framework is used for the AI ​​model. As a concrete example, when the user inputs the prompt "Please tell me about how the stock market works," the AI ​​model responds.

[0499] Users can learn about financial concepts and specific products through their devices. The level of knowledge acquired during the learning process is evaluated by the server analyzing the history of conversations between the user and the AI ​​model. The evaluation results are sent to the device as feedback to support the user's further improvement of financial knowledge. For example, if a user asks, "I want to know about NISA," the AI ​​model will respond, "NISA is a small-amount investment tax exemption system that offers tax benefits for certain investments."

[0500] This system can provide a comprehensive learning environment by suggesting appropriate financial activities to users and encouraging their participation in those activities.

[0501] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0502] Step 1:

[0503] The server receives basic information and self-assessment data provided by the user through an information processing device as input. This includes age, occupation, income, and self-assessment of financial knowledge. The server stores this data in a database and uses it as foundational information for initial assessment. The data is preprocessed using the Pandas library and prepared in a parseable format.

[0504] Step 2:

[0505] The server performs an initial assessment based on the data collected in Step 1. This initial assessment involves statistical analysis to measure the user's current financial literacy level. The results of this analysis are then output, evaluating the user's financial knowledge level in numerical and categorical formats, and a report is generated.

[0506] Step 3:

[0507] The server generates a personalized learning plan based on the results of the initial assessment. Using the assessment results as input, it constructs an optimal learning course tailored to the user's knowledge level and interests. Specifically, it uses machine learning algorithms to select the most suitable generative AI model for the user and designs learning topics and schedules. This plan is output as a digital document and sent to the terminal.

[0508] Step 4:

[0509] The terminal provides information to the user in an interactive format based on a learning plan received from the server. The user enters prompts on the terminal to begin interacting with the generating AI model. The model receives user questions as input and generates immediate responses using interactive natural language processing. These responses are displayed on the terminal, allowing the user to expand their financial knowledge.

[0510] Step 5:

[0511] As user interactions on their devices accumulate, the server analyzes this dialogue history. It takes past dialogue data as input and applies data mining techniques to evaluate the user's knowledge acquisition level. The evaluation results are generated on the server and output as feedback to the user.

[0512] Step 6:

[0513] Based on the evaluation results from Step 5, the server provides feedback to the user and suggests specific financial activities and services. This helps the user to have opportunities to participate in more practical financial activities. The suggested activities are notified to the user via the terminal, encouraging them to take concrete action.

[0514] (Application Example 1)

[0515] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0516] A challenge exists in that users with insufficient financial literacy find it difficult to select appropriate electronic transactions and use services wisely. Therefore, there is a need for a system that provides information and transaction suggestions tailored to the user's knowledge level, thereby improving their individual financial literacy.

[0517] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0518] In this invention, the server includes: a device means for inputting multiple user data and performing an initial evaluation; a device means for generating a learning plan based on the user evaluation and providing information in an interactive format using a selected machine learning model; and an information providing device means for presenting the optimal electronic transaction to the user. This enables users to improve their individual financial knowledge while obtaining appropriate information to select the optimal electronic transaction.

[0519] "User data" refers to information related to individual users that the system collects for initial evaluation.

[0520] "Initial assessment" is a process to understand users' financial literacy levels and needs based on collected user data.

[0521] A "learning plan" is an educational program designed to meet individual needs and interests, based on the user's evaluation results.

[0522] A "machine learning model" is a program that uses artificial intelligence technology selected to provide knowledge through interaction with users.

[0523] A "device that provides information in an interactive format" is a system that has an interface for transmitting necessary knowledge and information through interaction with the user.

[0524] An "information provision device" is a device that has the function of providing information to enable users to understand and select the most suitable electronic transaction based on their individual needs.

[0525] "Electronic trading" refers to a method of transaction for providing and using financial products and services electronically.

[0526] The system for realizing this invention mainly consists of a server and a user terminal. The server receives user data and performs an initial evaluation using an AI model. This makes it possible to understand the user's financial knowledge level and generate an individualized learning plan.

[0527] Specifically, the server first analyzes basic information and self-assessment data on finances provided by the user, and then sets a customized learning plan based on the initial assessment results. The technology used here is a generative AI model, which provides information to the user in an interactive format.

[0528] The user terminal is designed as a smartphone application, allowing users to ask questions through the device. A conversational agent using a selected machine learning model provides real-time answers to user questions. Through this interaction, users can expand their financial knowledge and gain a deeper understanding of electronic trading and investment.

[0529] As a concrete example, consider a scenario where a user enters "What is the most efficient way to accumulate points?" into their terminal. The server's generated AI model responds, "You can maximize savings and rewards by combining different credit cards." This allows the user to gain practical knowledge to make appropriate decisions when conducting electronic transactions.

[0530] Furthermore, the user's learning progress and interaction history are analyzed on the server, and based on this evaluation, feedback and optimal suggestions regarding electronic transactions are provided to the user. In this way, an environment is provided in which users can continuously improve their financial knowledge.

[0531] An example of a prompt might be, "Please give me advice on how to optimize my points system, especially regarding the use of multiple credit cards." Based on this prompt, the AI ​​model generates an appropriate response and provides information to the user.

[0532] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0533] Step 1:

[0534] The server receives basic information and self-assessment data regarding finances provided by the user. This provides the foundational data needed to understand the user's current status. The inputs here are the user's personal information and self-assessment data, and the assessment data is stored on the server as output.

[0535] Step 2:

[0536] The server uses a generative AI model to perform an initial financial literacy assessment based on the received evaluation data. This process analyzes the input data, processes it to identify the user's financial knowledge level, and outputs the evaluation result.

[0537] Step 3:

[0538] The server generates a personalized learning plan based on the initial assessment results. Here, it determines the learning content tailored to each user's knowledge level and interests. It uses the assessment results as input and outputs a learning plan based on them.

[0539] Step 4:

[0540] The terminal uses a selected generative AI model to provide information to the user in an interactive format. The user asks questions by entering prompts through the terminal, and the AI ​​generates answers in real time. The input is the user's prompt, and the output is the answer generated by the AI.

[0541] Step 5:

[0542] The server analyzes the user's dialogue history and learning progress to evaluate their level of understanding. Based on this analysis, the server generates feedback. The input is the dialogue history, and the output is feedback information.

[0543] Step 6:

[0544] The server provides information to the user to offer appropriate electronic transaction suggestions based on the user's level of understanding. At this stage, the evaluated level of understanding is used as input to output suggestions for the most suitable transactions and services.

[0545] Step 7:

[0546] When a user participates in a proposed electronic transaction, the terminal provides support. It receives user actions as input and supports smooth transactions by confirming participation in the transaction and outputting necessary information.

[0547] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0548] This invention aims to provide a more personalized learning experience by combining an emotional engine with an educational system designed to improve users' financial literacy. The program of this system is described below in natural language.

[0549] The server receives basic information and self-assessment data provided by the user and performs an initial evaluation. Based on this evaluation, it determines the user's financial literacy level and generates a personalized learning plan. This plan selects the optimal artificial intelligence model for each user and forms a framework for providing learning in an interactive format.

[0550] The emotion engine is built into the user's device and estimates the user's emotional state in real time from data such as voice tone, facial expressions, and input speed during interactions. This information is sent to a server and used to adjust the learning plan.

[0551] Specifically, if the device detects that the user is experiencing stress, it will slow down the learning pace and adjust to provide more relaxing content. This makes the user's learning experience more comfortable and effective.

[0552] On the other hand, if a user shows interest, the server can capitalize on this positive sentiment and provide more in-depth information or additional learning opportunities. For example, if a user asks, "I want to know more about NISA," and shows curiosity, the server will present detailed information about the benefits and uses of NISA to help them understand investing.

[0553] Using the history of the dialogue session and the user's sentiment information, the server more accurately assesses the user's level of understanding. Based on this assessment, it provides feedback and suggests necessary improvements and supplementary information to help the user progress to the next learning stage.

[0554] Furthermore, once the server determines that the user has acquired sufficient knowledge, it will suggest specific financial services. These suggestions are customized to take into account the user's emotional state and level of understanding, and are delivered at the optimal time and with the most relevant content.

[0555] Ultimately, the device guides users through the process of implementing the proposed financial services, providing emotional support to help them successfully build their wealth. In this way, the system aims to improve users' financial knowledge while also providing emotional support, thereby promoting sustainable learning and action.

[0556] The following describes the processing flow.

[0557] Step 1:

[0558] The server receives basic information and a self-assessment questionnaire about finances when a user registers for the app. This provides a basis for an initial assessment of the user's financial knowledge level.

[0559] Step 2:

[0560] The server generates a learning plan based on initial evaluation data. It selects an AI model suitable for each user and builds a system to support learning through dialogue.

[0561] Step 3:

[0562] The device activates the emotion engine along with the generated learning plan, preparing the user to begin the learning session.

[0563] Step 4:

[0564] During learning, the emotion engine analyzes the user's voice tone, facial expressions, and input speed in real time to estimate the user's emotional state.

[0565] Step 5:

[0566] The device adjusts the content of the conversation according to the estimated emotional state. For example, if the user is feeling stressed, it will slow down the conversation and provide relaxing content.

[0567] Step 6:

[0568] If a user shows interest or a positive response, the server will use this information to provide additional materials and specific examples, thereby deepening the user's understanding.

[0569] Step 7:

[0570] As the learning session progresses, the server integrates dialogue and sentiment data to evaluate the user's level of understanding.

[0571] Step 8:

[0572] The device provides feedback to the user based on the evaluation results, pointing out areas for further learning and improvement.

[0573] Step 9:

[0574] Once sufficient user knowledge is confirmed, the server takes their emotional state into consideration and suggests available financial services. These suggestions are customized to suit the user's emotions and level of understanding.

[0575] Step 10:

[0576] The terminal provides users with details of the proposed financial services and guides them to support their implementation. This includes the steps to take to participate in the appropriate financial services.

[0577] Step 11:

[0578] As users select a service and begin taking action, the device provides real-time support, including emotional support as needed.

[0579] Through this series of steps, the system expands users' financial knowledge and supports sustainable and effective wealth building.

[0580] (Example 2)

[0581] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0582] In recent years, numerous educational programs aimed at improving individual financial literacy have been offered. However, traditional systems often provide learning content in a uniform manner, which has the drawback of not adequately addressing the individual understanding levels and emotional responses of learners. Furthermore, there is a need for a system that can immediately adapt to emotional stress and changes in understanding during the learning process.

[0583] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0584] In this invention, the server includes means for inputting multiple pieces of information and performing a basic assessment; means for generating an educational plan based on the assessment and providing the content in an interactive format using a selected machine learning model; and means for analyzing the emotional state and dynamically adjusting the educational plan based on this. This makes it possible to provide a personalized educational experience that is tailored to the individual emotional state and level of understanding of each learner.

[0585] "Information" includes basic data about the user and data based on self-assessment.

[0586] "Basic assessment" is the process of determining the user's knowledge level and learning needs using the information provided.

[0587] An "educational plan" is an individualized learning plan created according to the user's learning needs and knowledge level.

[0588] A "machine learning model" is an artificial intelligence technology used to provide learning content and to interact with users.

[0589] "Emotional state" refers to the psychological and emotional state estimated from data such as the user's voice tone, facial expressions, and typing speed.

[0590] "Dynamic adjustment" refers to a process where the educational plan changes in real time according to the user's emotional state and level of understanding.

[0591] "Comprehension level" refers to the degree to which a user understands the learning material.

[0592] Personalization is the process of providing a learning experience optimized for each individual user.

[0593] A description of the embodiment for carrying out the invention will be provided.

[0594] In this system, the server collects information provided by the user and performs a basic user assessment based on that information. The server utilizes a database to manage the user's basic data and self-assessment data. For the initial assessment, a computer algorithm is used to analyze this data and clearly determine the user's level of financial knowledge.

[0595] Subsequently, the server generates an educational plan based on the user's evaluation results. This plan utilizes a generative AI model as a machine learning model. For example, OpenAI's language model can be used as the generative AI model. This AI model provides learning content to the user in an interactive format, facilitating a personalized educational experience.

[0596] The device has a built-in emotion engine that analyzes data such as voice tone, facial expressions, and input speed in real time during interactions with the user to estimate their emotional state. The emotional information detected by the device is sent to a server, which dynamically adjusts the learning plan based on this information. For example, if the user is feeling stressed, the difficulty level of the learning material is lowered and the content is switched to something more relaxing.

[0597] As users progress through interactive sessions, they receive feedback on what they understand and get suggestions for moving on to the next learning stage. If a user uses the prompt "I want to know more about NISA," the server can respond to this request by providing detailed information and examples of its use.

[0598] In this way, the system efficiently improves users' financial knowledge while providing a personalized learning experience that also takes their emotional state into consideration. This mechanism allows users to receive continuous education in a stress-free manner.

[0599] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0600] Step 1:

[0601] The server receives basic information and self-assessment data from the user. This data includes age, occupation, and financial knowledge level. The server stores this information in a database and uses it as input for the initial assessment. The server uses computer algorithms to analyze this data and determine the user's financial literacy level. The analysis results in an assessment of the user's financial knowledge level.

[0602] Step 2:

[0603] The server generates individualized learning plans based on the user's evaluation results. The input is the previously obtained financial literacy level data. The output is a user-specific learning plan, with learning content prepared interactively by a selected generative AI model. For example, learning scenarios and specific learning materials are determined using the generative AI model.

[0604] Step 3:

[0605] The device uses an emotion engine to analyze the user's emotional state in real time. Inputs include the user's voice tone, facial expression data, and input speed. The output obtained by analyzing this data is an estimate of the user's emotional state. This information is transmitted to the server in real time and used to adjust the learning plan.

[0606] Step 4:

[0607] The server receives emotional state data transmitted from the terminal and dynamically adjusts the educational plan. The input used is an estimated emotional state. Based on this data, the server adjusts the plan to ease the learning content if the user is stressed, and to provide more detailed information if they are interested. As a result, the learning materials and their pace provided to the user are optimized.

[0608] Step 5:

[0609] Users learn by interacting with the generative AI model. They can request additional information or support using prompts. Input includes user questions and requests. The generative AI model processes data based on these inputs and outputs the necessary information. For example, if the user enters the prompt "I want to know more about NISA," detailed information and specific examples will be presented.

[0610] Step 6:

[0611] The server evaluates the user's understanding using the history of conversation sessions and sentiment data. Input includes past conversation history and real-time sentiment data. The evaluation results are output as an indicator of how well the user understands the learning material. Based on this evaluation, feedback and suggestions for the next learning steps are provided.

[0612] Step 7:

[0613] Once the server determines that the user has acquired sufficient knowledge, it suggests appropriate financial services, taking into account the user's level of understanding and emotional state. The input data for the suggestions includes the user's understanding assessment and emotional data, while the output includes individually customized service suggestions. Based on this, the user can choose to take further action.

[0614] (Application Example 2)

[0615] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0616] In educational programs aimed at improving users' financial literacy, it is difficult to provide an optimal learning experience tailored to each user's level of understanding and interests. Furthermore, it is necessary to grasp the user's emotional state in real time and adjust the learning content accordingly, but effective means of achieving this are limited. This invention aims to solve these problems and enhance the learning effectiveness and satisfaction of users.

[0617] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0618] In this invention, the server includes: a device means for inputting multiple individual registration information and performing an initial evaluation; a device means for generating a learning plan based on the registrant's evaluation and providing information in response format using a selected intelligent model; and a device means for analyzing emotions using speech recognition and facial recognition devices and dynamically adjusting the content of the information provided in response format based on the results. This makes it possible to provide an individualized and optimal learning experience while taking into account the user's emotional state.

[0619] "Individual registration information" refers to information entered based on each user's characteristics and needs, and is used to understand the individual characteristics of each user.

[0620] "Initial assessment" is a process of making a preliminary determination of a user's current knowledge and skills based on the individual registration information they provide.

[0621] A "learning plan" is a plan that outlines individualized steps and a curriculum to help users achieve their learning goals, based on their evaluation results.

[0622] An "intelligent model" is a program or algorithm that uses artificial intelligence to support user learning and has the function of providing information tailored to the individual needs of the user.

[0623] "Response format" refers to the form of interaction with the user, a process that provides information through dialogue and supports smooth learning.

[0624] "Speech recognition" is a technology that analyzes a user's speech and converts its content into text data or semantic data.

[0625] A "face recognition device" is a device that uses a camera and software to detect and analyze a user's facial expressions and emotions, and to utilize this information for learning purposes.

[0626] "Emotional analysis" is a process that estimates and evaluates users' emotional states based on their voice and facial expression data.

[0627] "Response history" refers to records of past conversations with the user and is data used to understand the user's learning process and level of comprehension.

[0628] "Asset management services" refer to financial products and programs designed to efficiently manage and increase a user's assets, and are proposed according to the user's needs.

[0629] This invention aims to realize a financial literacy improvement system that utilizes emotion analysis. The system is built through the interaction of a server, terminal, and user, providing users with a personalized financial learning experience.

[0630] First, the user accesses the system using a smart device. The device uses the Google Cloud Speech-to-Text API to convert speech into text data and the Azure Face API to analyze the user's facial expressions through video data acquired from the camera. This data is sent to a server and used to estimate the user's emotional state in real time.

[0631] The server uses the OpenAI GPT model to generate optimal learning content based on the user's emotional state and past response history. The information displayed in an interactive format is adjusted according to the user's emotional state, providing relaxing content to stressed users and detailed information to users who show interest.

[0632] As a concrete example, if a user says, "I want to learn about Tsumitate NISA," the system will provide a basic explanation if the user appears nervous, but if they seem to understand more, it will present deeper knowledge and practical examples. The generating AI model uses prompts to provide information. Prompts such as, "Please explain Tsumitate NISA simply for beginners. Use language that will help the user relax," will be used.

[0633] This system allows users with different learning levels and emotional states to receive an optimal learning experience, thereby enabling them to improve their financial skills.

[0634] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0635] Step 1:

[0636] Users log in to the system via their smart devices. The input here is the user's individual registration information, forming a user profile. This profile collects the user's past history and basic information. The output is a dataset for initial evaluation.

[0637] Step 2:

[0638] The device uses the Google Cloud Speech-to-Text API to convert the user's voice data into text data. The input is an audio signal, which is converted into text using speech recognition technology. The output is text data that reflects the user's intent.

[0639] Step 3:

[0640] The device analyzes the user's facial expressions through video data acquired from the camera using the Azure Face API. The input is a video signal, and facial recognition technology extracts information about the user's emotions. The output is a dataset showing the user's current emotional state.

[0641] Step 4:

[0642] The server generates appropriate training content using the OpenAI GPT model, based on the user intent and sentiment data obtained in steps 2 and 3. In this process, the user's intent (prompt text) and sentiment state are provided as input. The model analyzes this and selects the most suitable content for the user. The output is text data containing the specific training content.

[0643] Step 5:

[0644] The device displays text data sent from the server to the user. The displayed content is tailored based on the user's emotional state and presented in an easy-to-understand format. The input is learning content from the server, and the output is learning navigation that facilitates user understanding.

[0645] Step 6:

[0646] Based on user responses and new questions, the process from steps 2 to 5 is repeated, and learning progresses. The server manages this cycle and provides feedback sentences and new learning options based on the generated AI model as needed.

[0647] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0648] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0649] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0650] [Fourth Embodiment]

[0651] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0652] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0653] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0654] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0655] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0656] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0657] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0658] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0659] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0660] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0661] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0662] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0663] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0664] This invention provides a system for improving users' financial knowledge, and is particularly characterized by its interactive educational approach using an artificial intelligence model. The system's program is described below in natural language.

[0665] The server first receives basic information and self-assessment data about finances provided by the user and performs an initial assessment. This assessment forms the basis for understanding the user's current level of financial literacy and creating an appropriate educational plan.

[0666] Next, the server creates a personalized learning plan based on the initial evaluation results. Specifically, it selects the optimal artificial intelligence model according to each user's knowledge level and interests, and designs a learning course using that model. This plan includes the topics and schedule necessary for the user's learning.

[0667] Once a user begins learning based on this plan, the device will provide information in an interactive format using a selected artificial intelligence model. Users can ask questions through the device, and the AI ​​model will respond in real time, supporting the expansion of the user's financial knowledge.

[0668] For example, if a user asks the device, "I want to know about NISA," the artificial intelligence model will respond with something like, "NISA is a small-amount investment tax exemption system that offers tax benefits for specific investments." This allows users to obtain specific and easy-to-understand information through direct dialogue.

[0669] After a certain period of conversation, the server analyzes the history and evaluates the user's level of knowledge acquisition. Based on this evaluation, the terminal provides feedback to the user to encourage further understanding. Furthermore, depending on the evaluation results, it suggests appropriate financial services related to investment and asset management and provides support when the user takes actual action.

[0670] In this way, the system provides an effective learning environment that gradually improves users' financial literacy and leads to actual asset building.

[0671] The following describes the processing flow.

[0672] Step 1:

[0673] The server receives basic information and a self-assessment questionnaire about finances from users when they register for the app. This provides a basis for an initial assessment of the user's current financial literacy level.

[0674] Step 2:

[0675] The server generates a customized learning plan for each user based on an initial assessment. This plan designs the optimal artificial intelligence model and learning course to match the user's knowledge level and interests.

[0676] Step 3:

[0677] The terminal presents the user with a learning plan generated on the server and provides an interface to encourage them to start learning. The user can then begin a learning session based on this plan.

[0678] Step 4:

[0679] Once a user begins a learning session, the device uses a selected artificial intelligence model to provide financial information through interaction with the user. The user asks questions and receives immediate responses from the device, thus advancing the learning process.

[0680] Step 5:

[0681] The server analyzes the user's learning history and dialogue to assess the user's level of understanding. Based on this assessment, it determines the user's progress level and decides on a course of action for further learning or correction.

[0682] Step 6:

[0683] The terminal provides the user with feedback based on the evaluation results provided by the server. It offers advice to help with future learning and information to improve understanding.

[0684] Step 7:

[0685] Once the server determines that the user has acquired sufficient knowledge, it will suggest specific financial services to the user (e.g., investment programs or account opening procedures).

[0686] Step 8:

[0687] The terminal presents the user with specific information about the proposed financial services and provides an interface to support the next action. The user uses this information to select specific investment and asset management actions.

[0688] Step 9:

[0689] If the user takes action based on the suggestion, the device will guide them through the necessary steps and provide ongoing support.

[0690] (Example 1)

[0691] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0692] In modern society, financial literacy is becoming increasingly important, yet many people lack sufficient financial literacy and are unable to manage their assets effectively. To address this problem, there is a need for a system that provides learning methods optimized for individual users and effectively improves their financial knowledge.

[0693] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0694] In this invention, the server includes means for inputting user information and self-assessment information into an information processing device and performing an initial assessment; means for generating an individualized learning plan based on the user's initial assessment and providing information in an interactive format using a selected machine learning model; and means for analyzing the user's level of knowledge acquisition from the dialogue history and providing feedback based on the assessment results. This makes it possible to efficiently improve financial literacy through a learning plan optimized for each individual user.

[0695] An "information processing device" is an electronic device that receives and processes input information from a user.

[0696] "User information" refers to personal data and attributes related to individual users.

[0697] "Self-assessment information" refers to data about financial knowledge and skills as assessed by the user themselves.

[0698] "Initial assessment" is an analysis based on user information and self-assessment information to understand the user's current level of financial knowledge.

[0699] A "learning plan" is an educational program designed individually based on the user's evaluation results.

[0700] A "machine learning model" is an intelligent system composed of algorithms used to analyze data and make predictions or decisions.

[0701] "Dialogue format" refers to a method in which the user and the system exchange information through questions and answers.

[0702] "Dialogue history" refers to a record of questions and answers exchanged between the user and the system.

[0703] "Knowledge acquisition level" is an indicator that shows how much knowledge a user has gained through learning.

[0704] "Feedback" refers to evaluations and advice provided based on the user's learning outcomes.

[0705] "Financial activities" refer to economic transactions and actions such as asset management and investment.

[0706] One embodiment of this invention is an interactive educational system for improving users' financial literacy. Specifically, the user, terminal, and server work together.

[0707] The server first receives information collected from the user through an information processing device, which includes self-assessment data on age, occupation, and current financial knowledge. The server then performs an initial assessment to analyze the user's financial knowledge level and create an individualized learning plan. In this process, the Python Pandas library is used as a data analysis tool to develop a learning plan based on the assessment.

[0708] The terminal is responsible for executing the learning plan received from the server and providing information to the user in an interactive format. Questions from the user are input through the terminal and sent as prompts to the generating AI model, generating responses in real time. For example, an open-source neural network framework is used for the AI ​​model. As a concrete example, when the user inputs the prompt "Please tell me about how the stock market works," the AI ​​model responds.

[0709] Users can learn about financial concepts and specific products through their devices. The level of knowledge acquired during the learning process is evaluated by the server analyzing the history of conversations between the user and the AI ​​model. The evaluation results are sent to the device as feedback to support the user's further improvement of financial knowledge. For example, if a user asks, "I want to know about NISA," the AI ​​model will respond, "NISA is a small-amount investment tax exemption system that offers tax benefits for certain investments."

[0710] This system can provide a comprehensive learning environment by suggesting appropriate financial activities to users and encouraging their participation in those activities.

[0711] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0712] Step 1:

[0713] The server receives basic information and self-assessment data provided by the user through an information processing device as input. This includes age, occupation, income, and self-assessment of financial knowledge. The server stores this data in a database and uses it as foundational information for initial assessment. The data is preprocessed using the Pandas library and prepared in a parseable format.

[0714] Step 2:

[0715] The server performs an initial assessment based on the data collected in Step 1. This initial assessment involves statistical analysis to measure the user's current financial literacy level. The results of this analysis are then output, evaluating the user's financial knowledge level in numerical and categorical formats, and a report is generated.

[0716] Step 3:

[0717] The server generates a personalized learning plan based on the results of the initial assessment. Using the assessment results as input, it constructs an optimal learning course tailored to the user's knowledge level and interests. Specifically, it uses machine learning algorithms to select the most suitable generative AI model for the user and designs learning topics and schedules. This plan is output as a digital document and sent to the terminal.

[0718] Step 4:

[0719] The terminal provides information to the user in an interactive format based on a learning plan received from the server. The user enters prompts on the terminal to begin interacting with the generating AI model. The model receives user questions as input and generates immediate responses using interactive natural language processing. These responses are displayed on the terminal, allowing the user to expand their financial knowledge.

[0720] Step 5:

[0721] As user interactions on their devices accumulate, the server analyzes this dialogue history. It takes past dialogue data as input and applies data mining techniques to evaluate the user's knowledge acquisition level. The evaluation results are generated on the server and output as feedback to the user.

[0722] Step 6:

[0723] Based on the evaluation results from Step 5, the server provides feedback to the user and suggests specific financial activities and services. This helps the user to have opportunities to participate in more practical financial activities. The suggested activities are notified to the user via the terminal, encouraging them to take concrete action.

[0724] (Application Example 1)

[0725] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0726] A challenge exists in that users with insufficient financial literacy find it difficult to select appropriate electronic transactions and use services wisely. Therefore, there is a need for a system that provides information and transaction suggestions tailored to the user's knowledge level, thereby improving their individual financial literacy.

[0727] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0728] In this invention, the server includes: a device means for inputting multiple user data and performing an initial evaluation; a device means for generating a learning plan based on the user evaluation and providing information in an interactive format using a selected machine learning model; and an information providing device means for presenting the optimal electronic transaction to the user. This enables users to improve their individual financial knowledge while obtaining appropriate information to select the optimal electronic transaction.

[0729] "User data" refers to information related to individual users that the system collects for initial evaluation.

[0730] "Initial assessment" is a process to understand users' financial literacy levels and needs based on collected user data.

[0731] A "learning plan" is an educational program designed to meet individual needs and interests, based on the user's evaluation results.

[0732] A "machine learning model" is a program that uses artificial intelligence technology selected to provide knowledge through interaction with users.

[0733] A "device that provides information in an interactive format" is a system that has an interface for transmitting necessary knowledge and information through interaction with the user.

[0734] An "information provision device" is a device that has the function of providing information to enable users to understand and select the most suitable electronic transaction based on their individual needs.

[0735] "Electronic trading" refers to a method of transaction for providing and using financial products and services electronically.

[0736] The system for realizing this invention mainly consists of a server and a user terminal. The server receives user data and performs an initial evaluation using an AI model. This makes it possible to understand the user's financial knowledge level and generate an individualized learning plan.

[0737] Specifically, the server first analyzes basic information and self-assessment data on finances provided by the user, and then sets a customized learning plan based on the initial assessment results. The technology used here is a generative AI model, which provides information to the user in an interactive format.

[0738] The user terminal is designed as a smartphone application, allowing users to ask questions through the device. A conversational agent using a selected machine learning model provides real-time answers to user questions. Through this interaction, users can expand their financial knowledge and gain a deeper understanding of electronic trading and investment.

[0739] As a concrete example, consider a scenario where a user enters "What is the most efficient way to accumulate points?" into their terminal. The server's generated AI model responds, "You can maximize savings and rewards by combining different credit cards." This allows the user to gain practical knowledge to make appropriate decisions when conducting electronic transactions.

[0740] Furthermore, the user's learning progress and interaction history are analyzed on the server, and based on this evaluation, feedback and optimal suggestions regarding electronic transactions are provided to the user. In this way, an environment is provided in which users can continuously improve their financial knowledge.

[0741] An example of a prompt might be, "Please give me advice on how to optimize my points system, especially regarding the use of multiple credit cards." Based on this prompt, the AI ​​model generates an appropriate response and provides information to the user.

[0742] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0743] Step 1:

[0744] The server receives basic information and self-assessment data regarding finances provided by the user. This provides the foundational data needed to understand the user's current status. The inputs here are the user's personal information and self-assessment data, and the assessment data is stored on the server as output.

[0745] Step 2:

[0746] The server uses a generative AI model to perform an initial financial literacy assessment based on the received evaluation data. This process analyzes the input data, processes it to identify the user's financial knowledge level, and outputs the evaluation result.

[0747] Step 3:

[0748] The server generates a personalized learning plan based on the initial assessment results. Here, it determines the learning content tailored to each user's knowledge level and interests. It uses the assessment results as input and outputs a learning plan based on them.

[0749] Step 4:

[0750] The terminal uses a selected generative AI model to provide information to the user in an interactive format. The user asks questions by entering prompts through the terminal, and the AI ​​generates answers in real time. The input is the user's prompt, and the output is the answer generated by the AI.

[0751] Step 5:

[0752] The server analyzes the user's dialogue history and learning progress to evaluate their level of understanding. Based on this analysis, the server generates feedback. The input is the dialogue history, and the output is feedback information.

[0753] Step 6:

[0754] The server provides information to the user to offer appropriate electronic transaction suggestions based on the user's level of understanding. At this stage, the evaluated level of understanding is used as input to output suggestions for the most suitable transactions and services.

[0755] Step 7:

[0756] When a user participates in a proposed electronic transaction, the terminal provides support. It receives user actions as input and supports smooth transactions by confirming participation in the transaction and outputting necessary information.

[0757] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0758] This invention aims to provide a more personalized learning experience by combining an emotional engine with an educational system designed to improve users' financial literacy. The program of this system is described below in natural language.

[0759] The server receives basic information and self-assessment data provided by the user and performs an initial evaluation. Based on this evaluation, it determines the user's financial literacy level and generates a personalized learning plan. This plan selects the optimal artificial intelligence model for each user and forms a framework for providing learning in an interactive format.

[0760] The emotion engine is built into the user's device and estimates the user's emotional state in real time from data such as voice tone, facial expressions, and input speed during interactions. This information is sent to a server and used to adjust the learning plan.

[0761] Specifically, if the device detects that the user is experiencing stress, it will slow down the learning pace and adjust to provide more relaxing content. This makes the user's learning experience more comfortable and effective.

[0762] On the other hand, if a user shows interest, the server can capitalize on this positive sentiment and provide more in-depth information or additional learning opportunities. For example, if a user asks, "I want to know more about NISA," and shows curiosity, the server will present detailed information about the benefits and uses of NISA to help them understand investing.

[0763] Using the history of the dialogue session and the user's sentiment information, the server more accurately assesses the user's level of understanding. Based on this assessment, it provides feedback and suggests necessary improvements and supplementary information to help the user progress to the next learning stage.

[0764] Furthermore, once the server determines that the user has acquired sufficient knowledge, it will suggest specific financial services. These suggestions are customized to take into account the user's emotional state and level of understanding, and are delivered at the optimal time and with the most relevant content.

[0765] Ultimately, the device guides users through the process of implementing the proposed financial services, providing emotional support to help them successfully build their wealth. In this way, the system aims to improve users' financial knowledge while also providing emotional support, thereby promoting sustainable learning and action.

[0766] The following describes the processing flow.

[0767] Step 1:

[0768] The server receives basic information and a self-assessment questionnaire about finances when a user registers for the app. This provides a basis for an initial assessment of the user's financial knowledge level.

[0769] Step 2:

[0770] The server generates a learning plan based on initial evaluation data. It selects an AI model suitable for each user and builds a system to support learning through dialogue.

[0771] Step 3:

[0772] The device activates the emotion engine along with the generated learning plan, preparing the user to begin the learning session.

[0773] Step 4:

[0774] During learning, the emotion engine analyzes the user's voice tone, facial expressions, and input speed in real time to estimate the user's emotional state.

[0775] Step 5:

[0776] The device adjusts the content of the conversation according to the estimated emotional state. For example, if the user is feeling stressed, it will slow down the conversation and provide relaxing content.

[0777] Step 6:

[0778] If a user shows interest or a positive response, the server will use this information to provide additional materials and specific examples, thereby deepening the user's understanding.

[0779] Step 7:

[0780] As the learning session progresses, the server integrates dialogue and sentiment data to evaluate the user's level of understanding.

[0781] Step 8:

[0782] The device provides feedback to the user based on the evaluation results, pointing out areas for further learning and improvement.

[0783] Step 9:

[0784] Once sufficient user knowledge is confirmed, the server takes their emotional state into consideration and suggests available financial services. These suggestions are customized to suit the user's emotions and level of understanding.

[0785] Step 10:

[0786] The terminal provides users with details of the proposed financial services and guides them to support their implementation. This includes the steps to take to participate in the appropriate financial services.

[0787] Step 11:

[0788] As users select a service and begin taking action, the device provides real-time support, including emotional support as needed.

[0789] Through this series of steps, the system expands users' financial knowledge and supports sustainable and effective wealth building.

[0790] (Example 2)

[0791] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0792] In recent years, numerous educational programs aimed at improving individual financial literacy have been offered. However, traditional systems often provide learning content in a uniform manner, which has the drawback of not adequately addressing the individual understanding levels and emotional responses of learners. Furthermore, there is a need for a system that can immediately adapt to emotional stress and changes in understanding during the learning process.

[0793] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0794] In this invention, the server includes means for inputting multiple pieces of information and performing a basic assessment; means for generating an educational plan based on the assessment and providing the content in an interactive format using a selected machine learning model; and means for analyzing the emotional state and dynamically adjusting the educational plan based on this. This makes it possible to provide a personalized educational experience that is tailored to the individual emotional state and level of understanding of each learner.

[0795] "Information" includes basic data about the user and data based on self-assessment.

[0796] "Basic assessment" is the process of determining the user's knowledge level and learning needs using the information provided.

[0797] An "educational plan" is an individualized learning plan created according to the user's learning needs and knowledge level.

[0798] A "machine learning model" is an artificial intelligence technology used to provide learning content and to interact with users.

[0799] "Emotional state" refers to the psychological and emotional state estimated from data such as the user's voice tone, facial expressions, and typing speed.

[0800] "Dynamic adjustment" refers to a process where the educational plan changes in real time according to the user's emotional state and level of understanding.

[0801] "Comprehension level" refers to the degree to which a user understands the learning material.

[0802] Personalization is the process of providing a learning experience optimized for each individual user.

[0803] A description of the embodiment for carrying out the invention will be provided.

[0804] In this system, the server collects information provided by the user and performs a basic user assessment based on that information. The server utilizes a database to manage the user's basic data and self-assessment data. For the initial assessment, a computer algorithm is used to analyze this data and clearly determine the user's level of financial knowledge.

[0805] Subsequently, the server generates an educational plan based on the user's evaluation results. This plan utilizes a generative AI model as a machine learning model. For example, OpenAI's language model can be used as the generative AI model. This AI model provides learning content to the user in an interactive format, facilitating a personalized educational experience.

[0806] The device has a built-in emotion engine that analyzes data such as voice tone, facial expressions, and input speed in real time during interactions with the user to estimate their emotional state. The emotional information detected by the device is sent to a server, which dynamically adjusts the learning plan based on this information. For example, if the user is feeling stressed, the difficulty level of the learning material is lowered and the content is switched to something more relaxing.

[0807] As users progress through interactive sessions, they receive feedback on what they understand and get suggestions for moving on to the next learning stage. If a user uses the prompt "I want to know more about NISA," the server can respond to this request by providing detailed information and examples of its use.

[0808] In this way, the system efficiently improves users' financial knowledge while providing a personalized learning experience that also takes their emotional state into consideration. This mechanism allows users to receive continuous education in a stress-free manner.

[0809] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0810] Step 1:

[0811] The server receives basic information and self-assessment data from the user. This data includes age, occupation, and financial knowledge level. The server stores this information in a database and uses it as input for the initial assessment. The server uses computer algorithms to analyze this data and determine the user's financial literacy level. The analysis results in an assessment of the user's financial knowledge level.

[0812] Step 2:

[0813] The server generates individualized learning plans based on the user's evaluation results. The input is the previously obtained financial literacy level data. The output is a user-specific learning plan, with learning content prepared interactively by a selected generative AI model. For example, learning scenarios and specific learning materials are determined using the generative AI model.

[0814] Step 3:

[0815] The device uses an emotion engine to analyze the user's emotional state in real time. Inputs include the user's voice tone, facial expression data, and input speed. The output obtained by analyzing this data is an estimate of the user's emotional state. This information is transmitted to the server in real time and used to adjust the learning plan.

[0816] Step 4:

[0817] The server receives emotional state data transmitted from the terminal and dynamically adjusts the educational plan. The input used is an estimated emotional state. Based on this data, the server adjusts the plan to ease the learning content if the user is stressed, and to provide more detailed information if they are interested. As a result, the learning materials and their pace provided to the user are optimized.

[0818] Step 5:

[0819] Users learn by interacting with the generative AI model. They can request additional information or support using prompts. Input includes user questions and requests. The generative AI model processes data based on these inputs and outputs the necessary information. For example, if the user enters the prompt "I want to know more about NISA," detailed information and specific examples will be presented.

[0820] Step 6:

[0821] The server evaluates the user's understanding using the history of conversation sessions and sentiment data. Input includes past conversation history and real-time sentiment data. The evaluation results are output as an indicator of how well the user understands the learning material. Based on this evaluation, feedback and suggestions for the next learning steps are provided.

[0822] Step 7:

[0823] Once the server determines that the user has acquired sufficient knowledge, it suggests appropriate financial services, taking into account the user's level of understanding and emotional state. The input data for the suggestions includes the user's understanding assessment and emotional data, while the output includes individually customized service suggestions. Based on this, the user can choose to take further action.

[0824] (Application Example 2)

[0825] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0826] In educational programs aimed at improving users' financial literacy, it is difficult to provide an optimal learning experience tailored to each user's level of understanding and interests. Furthermore, it is necessary to grasp the user's emotional state in real time and adjust the learning content accordingly, but effective means of achieving this are limited. This invention aims to solve these problems and enhance the learning effectiveness and satisfaction of users.

[0827] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0828] In this invention, the server includes: a device means for inputting multiple individual registration information and performing an initial evaluation; a device means for generating a learning plan based on the registrant's evaluation and providing information in response format using a selected intelligent model; and a device means for analyzing emotions using speech recognition and facial recognition devices and dynamically adjusting the content of the information provided in response format based on the results. This makes it possible to provide an individualized and optimal learning experience while taking into account the user's emotional state.

[0829] "Individual registration information" refers to information entered based on each user's characteristics and needs, and is used to understand the individual characteristics of each user.

[0830] "Initial assessment" is a process of making a preliminary determination of a user's current knowledge and skills based on the individual registration information they provide.

[0831] A "learning plan" is a plan that outlines individualized steps and a curriculum to help users achieve their learning goals, based on their evaluation results.

[0832] An "intelligent model" is a program or algorithm that uses artificial intelligence to support user learning and has the function of providing information tailored to the individual needs of the user.

[0833] "Response format" refers to the form of interaction with the user, a process that provides information through dialogue and supports smooth learning.

[0834] "Speech recognition" is a technology that analyzes a user's speech and converts its content into text data or semantic data.

[0835] A "face recognition device" is a device that uses a camera and software to detect and analyze a user's facial expressions and emotions, and to utilize this information for learning purposes.

[0836] "Emotional analysis" is a process that estimates and evaluates users' emotional states based on their voice and facial expression data.

[0837] "Response history" refers to records of past conversations with the user and is data used to understand the user's learning process and level of comprehension.

[0838] "Asset management services" refer to financial products and programs designed to efficiently manage and increase a user's assets, and are proposed according to the user's needs.

[0839] This invention aims to realize a financial literacy improvement system that utilizes emotion analysis. The system is built through the interaction of a server, terminal, and user, providing users with a personalized financial learning experience.

[0840] First, the user accesses the system using a smart device. The device uses the Google Cloud Speech-to-Text API to convert speech into text data and the Azure Face API to analyze the user's facial expressions through video data acquired from the camera. This data is sent to a server and used to estimate the user's emotional state in real time.

[0841] The server uses the OpenAI GPT model to generate optimal learning content based on the user's emotional state and past response history. The information displayed in an interactive format is adjusted according to the user's emotional state, providing relaxing content to stressed users and detailed information to users who show interest.

[0842] As a concrete example, if a user says, "I want to learn about Tsumitate NISA," the system will provide a basic explanation if the user appears nervous, but if they seem to understand more, it will present deeper knowledge and practical examples. The generating AI model uses prompts to provide information. Prompts such as, "Please explain Tsumitate NISA simply for beginners. Use language that will help the user relax," will be used.

[0843] This system allows users with different learning levels and emotional states to receive an optimal learning experience, thereby enabling them to improve their financial skills.

[0844] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0845] Step 1:

[0846] Users log in to the system via their smart devices. The input here is the user's individual registration information, forming a user profile. This profile collects the user's past history and basic information. The output is a dataset for initial evaluation.

[0847] Step 2:

[0848] The device uses the Google Cloud Speech-to-Text API to convert the user's voice data into text data. The input is an audio signal, which is converted into text using speech recognition technology. The output is text data that reflects the user's intent.

[0849] Step 3:

[0850] The device analyzes the user's facial expressions through video data acquired from the camera using the Azure Face API. The input is a video signal, and facial recognition technology extracts information about the user's emotions. The output is a dataset showing the user's current emotional state.

[0851] Step 4:

[0852] The server generates appropriate training content using the OpenAI GPT model, based on the user intent and sentiment data obtained in steps 2 and 3. In this process, the user's intent (prompt text) and sentiment state are provided as input. The model analyzes this and selects the most suitable content for the user. The output is text data containing the specific training content.

[0853] Step 5:

[0854] The device displays text data sent from the server to the user. The displayed content is tailored based on the user's emotional state and presented in an easy-to-understand format. The input is learning content from the server, and the output is learning navigation that facilitates user understanding.

[0855] Step 6:

[0856] Based on user responses and new questions, the process from steps 2 to 5 is repeated, and learning progresses. The server manages this cycle and provides feedback sentences and new learning options based on the generated AI model as needed.

[0857] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0858] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0859] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0860] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0861] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0862] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0863] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0864] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0865] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0866] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0867] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0868] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0869] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0870] 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.

[0871] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0872] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0873] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0874] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0875] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0876] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0877] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0878] The following is further disclosed regarding the embodiments described above.

[0879] (Claim 1)

[0880] [A means of inputting multiple user data and performing an initial evaluation]

[0881] [A means of generating a learning plan based on user evaluations and providing information in an interactive format using a selected artificial intelligence model]

[0882] [A means of evaluating the user's level of understanding from the conversation history and providing feedback]

[0883] [A means of suggesting specific financial services according to the user's level of understanding],

[0884] [Means of supporting participation in proposed financial services]

[0885] A system that includes this.

[0886] (Claim 2)

[0887] [The system according to claim 1 that generates an educational plan aimed at improving the financial literacy of users.

[0888] (Claim 3)

[0889] [The system according to claim 1, which uses an artificial intelligence model to support the enhancement of a user's financial knowledge.

[0890] "Example 1"

[0891] (Claim 1)

[0892] [A means of inputting user information and self-assessment information into an information processing device and performing an initial evaluation]

[0893] [A means of generating individual learning plans based on the user's initial evaluation and providing information in an interactive format using a selected machine learning model]

[0894] [A means of analyzing the user's level of knowledge acquisition from the conversation history and providing feedback based on the evaluation results]

[0895] [A means of suggesting specific financial activities according to the user's level of knowledge],

[0896] [Means to promote participation in proposed financial activities]

[0897] A system that includes this.

[0898] (Claim 2)

[0899] [The system according to claim 1 that generates an educational plan aimed at improving the user's financial knowledge.

[0900] (Claim 3)

[0901] [The system according to claim 1, which uses a machine learning model to help improve a user's financial knowledge.

[0902] "Application Example 1"

[0903] (Claim 1)

[0904] [A device that inputs data from multiple users and performs an initial evaluation,

[0905] [An apparatus that generates a learning plan based on user evaluations and provides information in an interactive format using a selected machine learning model,

[0906] [A device that evaluates the user's level of understanding from dialogue records and provides feedback,

[0907] [A device that proposes specific financial activities according to the user's level of understanding,

[0908] [A device and means to support the proposed involvement in financial activities,

[0909] [Information provision device means for presenting the optimal electronic transaction to the user,

[0910] A system that includes this.

[0911] (Claim 2)

[0912] [The system according to claim 1, which generates an educational plan aimed at improving users' financial literacy and provides advice on electronic transactions using an interactive learning model.

[0913] (Claim 3)

[0914] [The system according to claim 1, which uses a generative AI model to support the expansion of users' financial knowledge and to support optimal choices in electronic transactions.]

[0915] "Example 2 of combining an emotion engine"

[0916] (Claim 1)

[0917] [A means of inputting multiple pieces of information and conducting a basic evaluation]

[0918] [Means for generating educational plans based on evaluations and providing content interactively using selected machine learning models]

[0919] [Means for analyzing emotional states and dynamically adjusting educational plans based on these findings]

[0920] [A means of evaluating the level of understanding from dialogue history and emotional information, and providing feedback]

[0921] [A means of suggesting specific services based on the level of understanding and supporting participation in the suggested services.]

[0922] A system that includes this.

[0923] (Claim 2)

[0924] [The system according to claim 1, which uses emotional data to personalize the learning experience.

[0925] (Claim 3)

[0926] [The system according to claim 1, which uses a machine learning model to support knowledge expansion and take emotional states into consideration.]

[0927] "Application example 2 when combining with an emotional engine"

[0928] (Claim 1)

[0929] [A device that inputs multiple individual registration information and performs an initial evaluation]

[0930] [A device that generates a learning plan based on the registered user's evaluation and provides information in a responsive format using a selected intelligent model]

[0931] [A device that analyzes emotions using voice recognition and facial recognition devices and dynamically adjusts the content of information provided in response format based on the results]

[0932] [A device that evaluates the registrant's level of understanding from their response history and provides feedback],

[0933] [A device that proposes specific asset management services according to the registered user's level of understanding],

[0934] [Device to support the use of proposed asset management services]

[0935] A system that includes this.

[0936] (Claim 2)

[0937] The system according to claim 1, which generates an educational plan aimed at improving registered users' financial understanding and provides personalized response content based on sentiment analysis.

[0938] (Claim 3)

[0939] [The system according to claim 1, which uses an intelligent model to support the deepening of registered users' financial knowledge and provides dynamic information based on the results of sentiment analysis. [Explanation of Symbols]

[0940] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A method for inputting multiple user data and performing an initial evaluation, A means of generating a learning plan based on user evaluations and providing information in an interactive format using a selected artificial intelligence model, A means of evaluating the user's level of understanding from the conversation history and providing feedback, A means of suggesting specific financial services according to the user's level of understanding, Means to support participation in proposed financial services A system that includes this.

2. The system according to claim 1, which generates an educational plan aimed at improving users' financial literacy.

3. The system according to claim 1, which uses an artificial intelligence model to support the expansion of a user's financial knowledge.

Images