system

Abstract

We provide the system. [Solution] A means of recording and analyzing the user's learning progress, A means of automatically generating learning content tailored to the user's level of understanding using a generative model, A means of increasing engagement by incorporating game elements, Including a generative model that provides real-time answers to financial questions, A system using information processing equipment.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method 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 modern society, there is a problem that many people have difficulty making appropriate decisions due to insufficient understanding of financial products and services. In particular, the younger generation and general consumers have limited opportunities to receive sufficient financial education, and as a result, they have to rely on self-study. In addition, it is difficult to customize conventional learning methods according to individual comprehension levels, and it is difficult to achieve effective learning.

Means for Solving the Problems

[0005] This invention provides a means for recording and analyzing a user's learning progress using an information processing device. Furthermore, it automatically generates learning content tailored to the user's level of understanding using a generative model, realizing a personalized learning experience based on individual learning goals and areas of interest. It also incorporates game elements to enhance learning engagement, and provides real-time answers to users' financial questions using a generative model, thereby realizing effective and engaging financial education. In addition, it adds a means for providing rewards that enable the application of learning results to real-life financial activities, creating an environment where acquired knowledge can be usefully utilized.

[0006] "User learning progress" is an indicator that shows the results and progress a user has achieved during their learning process.

[0007] A "generative model" is an algorithm or technique that automatically generates output based on input data, and utilizes machine learning and artificial intelligence technologies.

[0008] "Learning content tailored to understanding level" refers to educational content that is adjusted based on the user's current knowledge level and understanding.

[0009] "Automatic generation" refers to the process by which a system creates content using a specific algorithm without prior manual input or configuration.

[0010] "Personalization" refers to optimizing content and services based on the individual needs and preferences of each user.

[0011] "Game elements" are elements that promote user interest and participation in the learning process through competition, rewards, and feedback.

[0012] "Real-time response" refers to a communication method that provides immediate answers to user questions and requests, with virtually no time delay.

[0013] A "means of providing rewards" refers to a mechanism that provides incentives or rewards to users when they actually apply the knowledge they have gained through learning. [Brief explanation of the drawing]

[0014] [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

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

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

[0017] In the following embodiments, 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.

[0018] 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.

[0019] 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.

[0020] 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).

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

[0022] [First Embodiment]

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

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

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

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

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

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0035] This invention is a system for providing effective and personalized financial education to users. Embodiments of this system are described below.

[0036] The server stores the information registered by users for learning in a database and builds a profile for each individual user. After a user logs in, the server starts each learning session and tracks learning progress in real time. Based on this progress data, the generative model evaluates the user's level of understanding and automatically generates problems and materials that are optimal for that learning level.

[0037] The terminal displays learning content provided by the server to the user and transmits user input to the server. Answers to questions and questions arising during the learning process are sent to the server via the terminal. The server analyzes the received questions using a generative model, generates appropriate answers in real time, and provides them to the user via the terminal.

[0038] For example, if a user wants to deepen their knowledge of "investment trusts," the server will sequentially provide information ranging from basic concepts to advanced case studies related to investment trusts. Furthermore, the server will award rewards and achievements according to the user's learning progress, displaying the results on the device. In this process, the server can also send messages to users who have reached a certain level of learning progress or achievement, suggesting benefits and privileges from partner financial institutions, for instance.

[0039] Users can further enhance their financial knowledge by learning through this system on a daily basis. Because the system supports users in progressing at their own pace and is designed to ensure that their learning is useful in actual financial activities, it will be a powerful tool for improving financial literacy.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The user logs into the system via their device and starts a learning session. The device sends login information to the server, which then authenticates the user.

[0043] Step 2:

[0044] The server retrieves the learning history from the authenticated user's profile and evaluates the user's current learning progress. Based on this, it determines what the user should learn next.

[0045] Step 3:

[0046] The server uses a generative model to automatically generate learning questions and materials tailored to the user's level of understanding. The generated content is optimized based on the user's preferences and progress.

[0047] Step 4:

[0048] The device displays learning content sent from the server to the user. The user answers the presented questions and, if they have any questions, can query the server through the device.

[0049] Step 5:

[0050] The server receives user response data and performs analysis using a generative model. Based on the accuracy rate and level of understanding, it updates the user's learning progress and plans the next learning step.

[0051] Step 6:

[0052] When a user asks a question about a specific financial product or information, the server instantly generates an answer using a generative model. The generated answer is then provided to the user in real time via the terminal.

[0053] Step 7:

[0054] The server awards rewards and achievements based on learning progress and displays leaderboards and reward information on the device. This provides a system that allows users to check their learning progress and further motivates them to learn.

[0055] (Example 1)

[0056] 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."

[0057] Traditional financial education systems have struggled to provide personalized learning experiences for individual users, failing to accommodate varying learning paces and levels of understanding. Furthermore, they lacked sufficient feedback based on user progress and inadequate incentives useful for real-world financial activities.

[0058] 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.

[0059] In this invention, the server includes a device for recording and analyzing the user's learning progress, a device for automatically generating learning content tailored to the user's level of understanding using a generative AI model, and a device for determining rewards and achievements based on learning progress. This enables a personalized learning experience based on each user's progress and level of understanding. It also provides support for applying the learning outcomes obtained by the user to real-world financial activities.

[0060] A "device for recording and analyzing user learning progress" is a device that records the learning content, time, and correct answer rate of users, and analyzes this data to understand how far each user has progressed in their learning.

[0061] A "device that automatically generates learning content tailored to the user's level of understanding using a generative AI model" is a device that utilizes artificial intelligence technology to evaluate the user's past learning data and current level of understanding, and dynamically generates optimal learning materials and problems accordingly.

[0062] A "device that determines rewards and achievements based on learning progress" is a device that determines the rewards and achievement indicators that can be obtained according to the user's learning results and progress, and presents them to the user.

[0063] A "device that uses artificial intelligence to generate real-time answers to users' financial questions" is a device that uses artificial intelligence technology to generate quick and appropriate answers to financial questions from users.

[0064] A "device that builds individual user profiles and provides personalized financial education based on them" is a device that creates individual profiles based on user information and learning history, and provides learning content that is suitable for that profile.

[0065] A "notification device that proposes benefits to users" is a device that notifies users who have achieved a certain level of learning outcomes, proposing benefits and preferential treatment from related organizations.

[0066] This invention is a system that personalizes and effectively supports users' financial education. This system mainly consists of a server, terminals, and a generative AI model.

[0067] The server stores user-registered information in a database and creates individual profiles. This allows for tracking each user's learning needs and progress. Furthermore, the server utilizes a generative AI model to automatically generate customized learning materials and problems tailored to the user's level of understanding. The generative AI model is designed to provide users with the most suitable learning content in real time, based on existing learning data. The generative AI model used in this system is based on advanced machine learning algorithms and analyzes users' past learning behavior.

[0068] The terminal displays learning materials provided by the server to the user, supporting interactive learning. It also plays a role in sending user input to the server, allowing for rapid processing of user responses and questions. For example, if a user asks a question about a financial concept they are unsure of, that information is sent to the server via the terminal, and a generative AI model instantly generates an appropriate answer.

[0069] For example, if a user is trying to learn about "stock investing," the server can provide information step-by-step, from basic knowledge to actual investment scenarios. Furthermore, it can evaluate the user's learning progress and offer rewards and benefits. In this way, users can learn at their own pace and be prepared to apply their knowledge to real-world financial activities.

[0070] An example of a prompt might be, "Generate learning materials that cover investment trusts from basic to advanced levels, and create questions tailored to the user's level of understanding." Based on this prompt, the generation AI model creates optimal learning content, enhancing the user's learning experience.

[0071] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0072] Step 1:

[0073] To begin learning, users enter basic information, including their name, email address, and the area of ​​finance they wish to study. The server receives this information and stores it in a database. This data is used to generate individual user profiles, which form the basis for future personalized learning.

[0074] Step 2:

[0075] When a user logs in, the server initiates a session. The server retrieves the user's profile from the database and uses that information to prompt a generating AI model. This model generates optimal learning materials and problem sets based on the user's understanding and interests. This output is used in subsequent learning sessions.

[0076] Step 3:

[0077] The generated learning content is sent from the server to the terminal, which then presents it to the user. The user then proceeds with their learning using the presented materials. This allows the user to absorb information and work on the presented problems at their own pace.

[0078] Step 4:

[0079] When a user enters an answer to a question, the device sends the answer to the server. The server analyzes the answer and automatically evaluates it using a generative AI model. Based on this evaluation, the user's learning progress is updated, and additional feedback and supplementary materials are provided as needed. In this process, data such as the user's accuracy rate and the time taken to answer are important factors.

[0080] Step 5:

[0081] The server comprehensively evaluates the user's learning performance and determines rewards and achievements according to the progress achieved. This reward information is sent to the device and displayed to the user. The server also notifies the user of information about benefits from partner institutions according to their learning progress. This increases user motivation and encourages continued learning.

[0082] (Application Example 1)

[0083] 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."

[0084] In modern society, improving financial literacy is crucial, but there is a lack of effective and engaging educational methods tailored to individual users. Furthermore, general financial education is uniform, making it difficult to provide personalized learning experiences linked to users' individual purchasing activities and interests.

[0085] 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.

[0086] In this invention, the server includes means for recording and analyzing the user's learning progress, means for automatically generating learning content tailored to the user's level of understanding using a generative model, and means for generating learning content based on purchase history. This enables users to receive personalized financial education linked to their purchasing activities and effectively enhance their financial knowledge.

[0087] "Means for recording and analyzing users' learning progress" refers to a function of a system that records the progress of individual users' learning activities and analyzes that progress based on that data.

[0088] "Means of automatically generating learning content tailored to the user's level of understanding using generative models" refers to a function that uses artificial intelligence to automatically generate appropriate learning materials and problems according to the user's level of understanding and learning progress.

[0089] "Methods to enhance engagement by incorporating game elements" refer to features that integrate game elements into the learning process to attract user interest and increase their motivation to participate in learning.

[0090] A "generative model that provides real-time answers to financial questions" is an artificial intelligence model that instantly generates and presents appropriate answers to financial questions that users have.

[0091] "Means for generating learning content based on purchase history" refers to a function that generates learning content based on the user's past purchase activity data, taking into account the relationships between those activities.

[0092] This invention is a personalized educational system for improving financial literacy and is implemented in a form that includes the following elements:

[0093] The server records and analyzes the user's learning progress. As the user progresses, the progress data is stored in a database, and a user profile is generated. Based on this profile, the server uses a generative AI model to automatically generate optimal learning content tailored to the user's level of understanding and interests. Specifically, it utilizes OpenAI's GPT as the generative AI model and creates learning content based on the user's purchase history data, etc. This learning content provides unique and user-relevant material, functioning not merely as education, but as an element that attracts the user's interest.

[0094] The server also features engagement enhancements that incorporate game elements. Here, gamification, including a point system and level-up function, is used to support users' continuous learning. Real-time answers to financial questions are provided by a generative AI model. When a user submits an inquiry, the server immediately analyzes the content, generates an appropriate answer, and provides it to the user through their device.

[0095] For example, if a user seeks a deeper understanding of "long-term savings planning," the server will generate a case study linked to their individual purchase history. It can also present investment information related to products the user has previously purchased, suggesting its application to investment decisions. In this case, an example prompt might be, "Translate the user's purchase history into a financial education module related to smart investments in electronics." This allows the user to gain personalized, practical financial knowledge.

[0096] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0097] Step 1:

[0098] The server receives initial information when a user logs into the application and retrieves the user's past learning progress and purchase history data from the database. This input information forms the basis for subsequent personalized content generation. Based on this data, the server updates the individual learning profile in real time.

[0099] Step 2:

[0100] The server invokes a generative AI model based on the updated learning profile to form prompt sentences. The generative AI model generates new learning content using prompts related to the user's learning needs and purchase history. Specifically, it extracts information according to the user's areas of interest and uses natural language processing to generate learning materials.

[0101] Step 3:

[0102] The generated learning content is displayed to the user through their device. This display process presents information through an intuitively understandable interface. Based on the displayed content, the user can begin learning and provide relevant questions and feedback.

[0103] Step 4:

[0104] When a user's question or feedback is sent to the server via their device, the server uses a generative AI model to generate a response. Here, the user's input data is analyzed, and appropriate answers and additional training materials are prepared in real time. The generated response is then immediately provided to the user via their device.

[0105] Step 5:

[0106] Based on the user's learning progress and responses, the server automatically designs the next learning step and incorporates game elements as needed to continuously support the user's learning. Specifically, it displays points and level-up notifications on the device according to the user's achievements to increase the user's motivation to learn.

[0107] 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.

[0108] This invention is a system that further personalizes and enhances the user's learning experience by incorporating an emotion engine that recognizes the user's emotions.

[0109] First, when a user begins learning, the server activates an emotion engine using audio and video data collected from the device. This emotion engine utilizes machine learning algorithms to accurately recognize the user's emotional state from their tone of voice, facial expressions, and context. As a result, it extracts diverse emotional data such as excitement, interest, attention, boredom, and stress.

[0110] This emotional data is fed back into the learning process in real time by the server. If the emotional engine determines that the user is experiencing stress during learning, the server controls the generative model and temporarily switches the learning content to lighter problems or more engaging content. Conversely, if the user shows interest, providing more challenging problems can create an environment that encourages learning challenges.

[0111] For example, if the emotion engine detects that a user's concentration is waning while they are learning about the "basics of the stock market," the server will change the learning topic and rekindle the user's interest by inserting interesting anecdotes and real-world examples related to stocks. As a result, learning never becomes monotonous and is always delivered in a way that fits the user's mood.

[0112] Furthermore, the emotion engine is also used to adjust game elements. For example, when a user achieves a sense of accomplishment, the server automatically adjusts the reward settings, celebrates the achievement, and sends a notification to the device to reinforce motivation for the next step.

[0113] This system allows users to experience a learning path tailored to their emotional state during the financial education process, resulting in sustained and effective improvement in financial literacy.

[0114] The following describes the processing flow.

[0115] Step 1:

[0116] The user initiates a learning session through their device. The device collects audio and video data and sends it to the server.

[0117] Step 2:

[0118] The server inputs the received data into an emotion engine, which analyzes the user's emotions from their voice tone and facial expressions. This identifies emotional states such as excitement, stress, and level of concentration.

[0119] Step 3:

[0120] The server uses a generative model to automatically generate optimal learning content based on the user's current learning progress and emotional state. The content is adjusted according to the user's interests and level of understanding.

[0121] Step 4:

[0122] The device displays personalized learning content sent from the server to the user. The user can answer questions and also provide feedback to the device in real time about their feelings.

[0123] Step 5:

[0124] The server uses real-time emotional data obtained through the emotion engine to dynamically change learning content and game elements as needed. This includes, for example, providing relaxing content if the user's stress level is high.

[0125] Step 6:

[0126] The server provides rewards to the user according to their learning progress and achievements. The device notifies the user of these rewards and progress, encouraging further learning.

[0127] Step 7:

[0128] Through their devices, users can review the rewards they've earned and new learning targets, and plan for their next learning session. In this way, a sustained learning loop is formed that takes into account the user's emotional state.

[0129] (Example 2)

[0130] 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".

[0131] Traditional learning systems offer limited personalization based on users' learning progress and areas of interest, lacking dynamic adjustments to maximize learning effectiveness. Furthermore, they fail to adapt to users' emotional states during learning, leading to decreased motivation and increased stress. Moreover, the lack of effective solutions makes it difficult to provide a learning experience that fully meets individual needs.

[0132] 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.

[0133] In this invention, the server includes means for recording and analyzing the user's learning progress, means for automatically generating learning content according to the user's level of understanding using a generative model, means for enhancing engagement by incorporating game elements, means for recognizing the user's emotional state and dynamically adjusting the learning content based on it, and means for providing prompts to the generative model. This makes it possible to adjust the learning content based on the user's individual learning goals, areas of interest, and emotional state, thereby maximizing learning effectiveness and maintaining sustained motivation to learn.

[0134] "Means for recording and analyzing user learning progress" refers to a function that records the process and results of a user's learning activities as data and uses that data to evaluate their learning progress.

[0135] "A means of automatically generating learning content tailored to the user's level of understanding using a generative model" refers to a function that automatically constructs and presents learning materials and assignments based on the user's level of understanding. The generative model generates optimal content according to the user's learning tendencies.

[0136] "Methods to enhance engagement by incorporating game elements" refer to functions that promote user participation and continued engagement by incorporating entertaining elements and structures into learning.

[0137] "Means of recognizing emotional states and dynamically adjusting learning content based on them" refers to a function that analyzes the user's emotions and changes the difficulty level and content of learning in real time according to the results.

[0138] "Means of providing prompts to a generative model" refers to functions that input instructions and information into a generative model according to the user's learning progress and requests. Prompts serve as triggers for the generative model to obtain appropriate output.

[0139] An "information processing device" refers to a mechanical means for inputting, processing, storing, and outputting data, and includes various hardware and software such as computers and servers.

[0140] This invention provides a system that operates on an information processing device to improve the user's learning experience. The system mainly consists of a server and a user terminal.

[0141] When a user begins learning, the server collects audio and video data from the device. This uses the device's built-in microphone and camera, and the data is transmitted in real time. This data is analyzed by an emotion engine that uses machine learning algorithms. The emotion engine processes the user's voice tone, facial expressions, and contextual information to determine the user's emotional state.

[0142] Based on this emotional data, the server utilizes a generative AI model to automatically generate learning content tailored to the user's level of understanding and emotional state. The generated content is delivered to the user via their device, allowing them to receive a learning experience suited to their individual needs. The server, receiving feedback from the emotional engine, dynamically adjusts the learning content to maintain the user's interest.

[0143] For example, if the server detects that a user's concentration has waned while learning the "basics of the stock market," it will lighten the topic and insert interesting anecdotes and real-world examples related to stocks. This will rekindle the user's interest and facilitate the learning process.

[0144] Furthermore, the server enhances engagement by incorporating game elements, adjusts reward settings when users feel a sense of accomplishment, and improves motivation for the next learning step.

[0145] As an example of a prompt, the AI ​​model is given instructions such as, "How can we rekindle a user's interest when they lose interest while learning the basics of the stock market?" This prompts the model to generate appropriate learning content. As a result, users can experience a learning path that is individually optimized, leading to sustained motivation and effective learning outcomes.

[0146] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0147] Step 1:

[0148] When a user begins learning, the server collects audio and video data from the device. The user's audio and video are sent to the server as input via the device's microphone and camera. Upon receiving this data, the server performs preprocessing such as data format conversion and noise reduction to create a format suitable for analyzing emotional states.

[0149] Step 2:

[0150] The server inputs pre-processed audio and video data into the emotion engine. Based on the input data, machine learning algorithms are used to analyze the user's voice tone, facial expressions, and context. As a result of the analysis, emotional states such as excitement, interest, attention, boredom, and stress are output. Specific operations include clustering of voice pitch and facial expressions.

[0151] Step 3:

[0152] The server activates a mechanism to provide appropriate prompts to the generative AI model based on the emotional state data output from the emotion engine. It receives emotional data as input and generates prompt sentences tailored to the user's understanding and emotions. These prompt sentences serve as triggers for generating appropriate learning content.

[0153] Step 4:

[0154] The server collects learning content generated by the generative AI model and adjusts it according to the user's learning progress. The learning content dynamically changes to suit the user's emotional state, including difficulty adjustments and engagement-enhancing content at appropriate times. The output is the adjusted learning content displayed on the device.

[0155] Step 5:

[0156] The server evaluates the tailored learning content, incorporates game elements as needed, and sets rewards to enhance user motivation. It references the latest learning outcome data as input and generates rewards and notifications based on success and achievement. The output is a message reflecting the reward displayed on the user's device.

[0157] Step 6:

[0158] The device visually and audibly presents the user with the provided learning content and reward information, motivating them to progress to the next learning stage. The output from the device is an intuitive and easy-to-understand interface for the user. This improves the user's learning experience and allows for more efficient learning.

[0159] (Application Example 2)

[0160] 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".

[0161] There is a challenge in the lack of means to personalize learners' learning experiences and achieve high effectiveness. In particular, technologies that grasp learners' emotions in real time and dynamically adjust learning content based on them are immature, and there is a need for systems that provide efficient learning while maintaining learner motivation.

[0162] 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.

[0163] In this invention, the server includes means for recording and analyzing the user's learning progress, means for automatically generating learning content according to the user's level of understanding using a generation device, means for increasing participation by incorporating game elements, means for processing audio and video data for recognizing the user's emotions, and means for dynamically adjusting the learning content based on the user's emotional evaluation. This makes it possible to provide a highly personalized learning environment that responds to the individual emotional state of the learner.

[0164] A "user" refers to an individual learner who utilizes the learning system.

[0165] "Learning progress" refers to the level of understanding and progress made on assignments achieved by the user through learning activities.

[0166] A "generation device" refers to a device that uses technology to automatically create user learning content.

[0167] "Game elements" refer to entertaining elements used to increase user engagement and interest in learning.

[0168] "Participation level" represents the degree to which a user is involved in a learning activity.

[0169] "Audio data" refers to digital information related to sound collected from users.

[0170] "Video data" refers to visual information used to capture the user's facial expressions and movements.

[0171] "Sentimental assessment" refers to the process of identifying and analyzing a user's emotional state from various data.

[0172] "Dynamic adjustment" means that the system instantly changes its content and functions in response to the user's real-time reactions and status.

[0173] "Learning environment" refers to the overall settings regarding how the interface and content are presented to users when they are learning.

[0174] The system implementing this invention is centered around a server that recognizes emotions in real time through audio and video data in order to highly personalize the user's learning experience. The server collects audio and video data from the user's terminal and analyzes the user's emotional state using an emotion recognition engine.

[0175] The server controls the generated AI model based on the analysis results, dynamically adjusting the learning content to match the user's emotions. Specifically, if it determines that the user is interested, it will provide additional content that increases the difficulty level; conversely, if the user seems bored, it will insert visually appealing material or interesting anecdotes. This will increase the user's learning progress and engagement.

[0176] The hardware used by users consists of standard computer terminals or smart devices. These devices capture the user's voice and facial expressions and supply them to the emotion recognition engine. The software used includes "EmotionEngine" and "ContentServer," which are technological platforms that enable emotion analysis and flexible content delivery.

[0177] For example, if the emotion engine determines that a user is bored while learning a foreign language, the server can immediately play a video clip of a comedy scene to rekindle the user's interest. This approach can maintain and improve learning efficiency.

[0178] Examples of prompts to input into a generative AI model include the following:

[0179] "If users get bored while learning English, provide entertainment to help them change their mood."

[0180] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0181] Step 1:

[0182] The server collects audio and video data from the user's device. This data reflects the user's tone of voice and facial expressions. The input is real-time captured audio and video data, which is then used to prepare the system for pre-processing for emotion recognition.

[0183] Step 2:

[0184] The server uses an emotion engine to analyze the collected audio and video data and evaluate the user's emotional state. The input is the audio and video data prepared in step 1, and the output is data indicating the user's emotional state. Specifically, this data is passed through an emotion recognition algorithm to perform tone analysis and facial expression analysis.

[0185] Step 3:

[0186] The server controls the generative AI model, dynamically generating or adjusting learning content based on the user's emotions. The input here is the emotion evaluation data obtained in step 2. Based on the emotion data, data calculations are performed to adjust the difficulty and type of learning content, and personalized learning content is provided as output. For example, if the server perceives that the user is bored, it adjusts the parameters of the generative model to lighten the content.

[0187] Step 4:

[0188] The device presents the user with adjusted learning content based on instructions from the server. The input is the adjusted learning content sent from the server in step 3, and the output is the information the user receives visually and aurally. In this step, the content is displayed through the user interface, and actions are taken to enable interaction that enhances user engagement.

[0189] Step 5:

[0190] The user responds to the presented learning content through voice or actions. The device captures this data again and sends it to the server. This allows step 1 of the next cycle to resume, providing a continuously adaptable learning experience for the user. The input also serves as user feedback data, which is used for adjustments in the next session.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] [Second Embodiment]

[0195] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0196] 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.

[0197] 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).

[0198] 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.

[0199] 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.

[0200] 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).

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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".

[0207] This invention is a system for providing effective and personalized financial education to users. Embodiments of this system are described below.

[0208] The server stores the information registered by users for learning in a database and builds a profile for each individual user. After a user logs in, the server starts each learning session and tracks learning progress in real time. Based on this progress data, the generative model evaluates the user's level of understanding and automatically generates problems and materials that are optimal for that learning level.

[0209] The terminal displays learning content provided by the server to the user and transmits user input to the server. Answers to questions and questions arising during the learning process are sent to the server via the terminal. The server analyzes the received questions using a generative model, generates appropriate answers in real time, and provides them to the user via the terminal.

[0210] For example, if a user wants to deepen their knowledge of "investment trusts," the server will sequentially provide information ranging from basic concepts to advanced case studies related to investment trusts. Furthermore, the server will award rewards and achievements according to the user's learning progress, displaying the results on the device. In this process, the server can also send messages to users who have reached a certain level of learning progress or achievement, suggesting benefits and privileges from partner financial institutions, for instance.

[0211] Users can further enhance their financial knowledge by learning through this system on a daily basis. Because the system supports users in progressing at their own pace and is designed to ensure that their learning is useful in actual financial activities, it will be a powerful tool for improving financial literacy.

[0212] The following describes the processing flow.

[0213] Step 1:

[0214] The user logs into the system via their device and starts a learning session. The device sends login information to the server, which then authenticates the user.

[0215] Step 2:

[0216] The server retrieves the learning history from the authenticated user's profile and evaluates the user's current learning progress. Based on this, it determines what the user should learn next.

[0217] Step 3:

[0218] The server uses a generative model to automatically generate learning questions and materials tailored to the user's level of understanding. The generated content is optimized based on the user's preferences and progress.

[0219] Step 4:

[0220] The device displays learning content sent from the server to the user. The user answers the presented questions and, if they have any questions, can query the server through the device.

[0221] Step 5:

[0222] The server receives user response data and performs analysis using a generative model. Based on the accuracy rate and level of understanding, it updates the user's learning progress and plans the next learning step.

[0223] Step 6:

[0224] When a user asks a question about a specific financial product or information, the server instantly generates an answer using a generative model. The generated answer is then provided to the user in real time via the terminal.

[0225] Step 7:

[0226] The server awards rewards and achievements based on learning progress and displays leaderboards and reward information on the device. This provides a system that allows users to check their learning progress and further motivates them to learn.

[0227] (Example 1)

[0228] 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."

[0229] Traditional financial education systems have struggled to provide personalized learning experiences for individual users, failing to accommodate varying learning paces and levels of understanding. Furthermore, they lacked sufficient feedback based on user progress and inadequate incentives useful for real-world financial activities.

[0230] 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.

[0231] In this invention, the server includes a device for recording and analyzing the user's learning progress, a device for automatically generating learning content tailored to the user's level of understanding using a generative AI model, and a device for determining rewards and achievements based on learning progress. This enables a personalized learning experience based on each user's progress and level of understanding. It also provides support for applying the learning outcomes obtained by the user to real-world financial activities.

[0232] A "device for recording and analyzing user learning progress" is a device that records the learning content, time, and correct answer rate of users, and analyzes this data to understand how far each user has progressed in their learning.

[0233] A "device that automatically generates learning content tailored to the user's level of understanding using a generative AI model" is a device that utilizes artificial intelligence technology to evaluate the user's past learning data and current level of understanding, and dynamically generates optimal learning materials and problems accordingly.

[0234] A "device that determines rewards and achievements based on learning progress" is a device that determines the rewards and achievement indicators that can be obtained according to the user's learning results and progress, and presents them to the user.

[0235] A "device that uses artificial intelligence to generate real-time answers to users' financial questions" is a device that uses artificial intelligence technology to generate quick and appropriate answers to financial questions from users.

[0236] A "device that builds individual user profiles and provides personalized financial education based on them" is a device that creates individual profiles based on user information and learning history, and provides learning content that is suitable for that profile.

[0237] A "notification device that proposes benefits to users" is a device that notifies users who have achieved a certain level of learning outcomes, proposing benefits and preferential treatment from related organizations.

[0238] This invention is a system that personalizes and effectively supports users' financial education. This system mainly consists of a server, terminals, and a generative AI model.

[0239] The server stores user-registered information in a database and creates individual profiles. This allows for tracking each user's learning needs and progress. Furthermore, the server utilizes a generative AI model to automatically generate customized learning materials and problems tailored to the user's level of understanding. The generative AI model is designed to provide users with the most suitable learning content in real time, based on existing learning data. The generative AI model used in this system is based on advanced machine learning algorithms and analyzes users' past learning behavior.

[0240] The terminal displays learning materials provided by the server to the user, supporting interactive learning. It also plays a role in sending user input to the server, allowing for rapid processing of user responses and questions. For example, if a user asks a question about a financial concept they are unsure of, that information is sent to the server via the terminal, and a generative AI model instantly generates an appropriate answer.

[0241] For example, if a user is trying to learn about "stock investing," the server can provide information step-by-step, from basic knowledge to actual investment scenarios. Furthermore, it can evaluate the user's learning progress and offer rewards and benefits. In this way, users can learn at their own pace and be prepared to apply their knowledge to real-world financial activities.

[0242] An example of a prompt might be, "Generate learning materials that cover investment trusts from basic to advanced levels, and create questions tailored to the user's level of understanding." Based on this prompt, the generation AI model creates optimal learning content, enhancing the user's learning experience.

[0243] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0244] Step 1:

[0245] To begin learning, users enter basic information, including their name, email address, and the area of ​​finance they wish to study. The server receives this information and stores it in a database. This data is used to generate individual user profiles, which form the basis for future personalized learning.

[0246] Step 2:

[0247] When a user logs in, the server initiates a session. The server retrieves the user's profile from the database and uses that information to prompt a generating AI model. This model generates optimal learning materials and problem sets based on the user's understanding and interests. This output is used in subsequent learning sessions.

[0248] Step 3:

[0249] The generated learning content is sent from the server to the terminal, which then presents it to the user. The user then proceeds with their learning using the presented materials. This allows the user to absorb information and work on the presented problems at their own pace.

[0250] Step 4:

[0251] When a user enters an answer to a question, the device sends the answer to the server. The server analyzes the answer and automatically evaluates it using a generative AI model. Based on this evaluation, the user's learning progress is updated, and additional feedback and supplementary materials are provided as needed. In this process, data such as the user's accuracy rate and the time taken to answer are important factors.

[0252] Step 5:

[0253] The server comprehensively evaluates the user's learning performance and determines rewards and achievements according to the progress achieved. This reward information is sent to the device and displayed to the user. The server also notifies the user of information about benefits from partner institutions according to their learning progress. This increases user motivation and encourages continued learning.

[0254] (Application Example 1)

[0255] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0256] In modern society, improving financial literacy is crucial, but there is a lack of effective and engaging educational methods tailored to individual users. Furthermore, general financial education is uniform, making it difficult to provide personalized learning experiences linked to users' individual purchasing activities and interests.

[0257] 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.

[0258] In this invention, the server includes means for recording and analyzing the user's learning progress, means for automatically generating learning content tailored to the user's level of understanding using a generative model, and means for generating learning content based on purchase history. This enables users to receive personalized financial education linked to their purchasing activities and effectively enhance their financial knowledge.

[0259] "Means for recording and analyzing users' learning progress" refers to a function of a system that records the progress of individual users' learning activities and analyzes that progress based on that data.

[0260] "Means of automatically generating learning content tailored to the user's level of understanding using generative models" refers to a function that uses artificial intelligence to automatically generate appropriate learning materials and problems according to the user's level of understanding and learning progress.

[0261] "Methods to enhance engagement by incorporating game elements" refer to features that integrate game elements into the learning process to attract user interest and increase their motivation to participate in learning.

[0262] A "generative model that provides real-time answers to financial questions" is an artificial intelligence model that instantly generates and presents appropriate answers to financial questions that users have.

[0263] "Means for generating learning content based on purchase history" refers to a function that generates learning content based on the user's past purchase activity data, taking into account the relationships between those activities.

[0264] This invention is a personalized educational system for improving financial literacy and is implemented in a form that includes the following elements:

[0265] The server records and analyzes the user's learning progress. As the user progresses, the progress data is stored in a database, and a user profile is generated. Based on this profile, the server uses a generative AI model to automatically generate optimal learning content tailored to the user's level of understanding and interests. Specifically, it utilizes OpenAI's GPT as the generative AI model and creates learning content based on the user's purchase history data, etc. This learning content provides unique and user-relevant material, functioning not merely as education, but as an element that attracts the user's interest.

[0266] The server also features engagement enhancements that incorporate game elements. Here, gamification, including a point system and level-up function, is used to support users' continuous learning. Real-time answers to financial questions are provided by a generative AI model. When a user submits an inquiry, the server immediately analyzes the content, generates an appropriate answer, and provides it to the user through their device.

[0267] For example, if a user seeks a deeper understanding of "long-term savings planning," the server will generate a case study linked to their individual purchase history. It can also present investment information related to products the user has previously purchased, suggesting its application to investment decisions. In this case, an example prompt might be, "Translate the user's purchase history into a financial education module related to smart investments in electronics." This allows the user to gain personalized, practical financial knowledge.

[0268] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0269] Step 1:

[0270] The server receives initial information when a user logs into the application and retrieves the user's past learning progress and purchase history data from the database. This input information forms the basis for subsequent personalized content generation. Based on this data, the server updates the individual learning profile in real time.

[0271] Step 2:

[0272] The server invokes a generative AI model based on the updated learning profile to form prompt sentences. The generative AI model generates new learning content using prompts related to the user's learning needs and purchase history. Specifically, it extracts information according to the user's areas of interest and uses natural language processing to generate learning materials.

[0273] Step 3:

[0274] The generated learning content is displayed to the user through their device. This display process presents information through an intuitively understandable interface. Based on the displayed content, the user can begin learning and provide relevant questions and feedback.

[0275] Step 4:

[0276] When a user's question or feedback is sent to the server via their device, the server uses a generative AI model to generate a response. Here, the user's input data is analyzed, and appropriate answers and additional training materials are prepared in real time. The generated response is then immediately provided to the user via their device.

[0277] Step 5:

[0278] Based on the user's learning progress and responses, the server automatically designs the next learning step and incorporates game elements as needed to continuously support the user's learning. Specifically, it displays points and level-up notifications on the device according to the user's achievements to increase the user's motivation to learn.

[0279] 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.

[0280] This invention is a system that further personalizes and enhances the user's learning experience by incorporating an emotion engine that recognizes the user's emotions.

[0281] First, when a user begins learning, the server activates an emotion engine using audio and video data collected from the device. This emotion engine utilizes machine learning algorithms to accurately recognize the user's emotional state from their tone of voice, facial expressions, and context. As a result, it extracts diverse emotional data such as excitement, interest, attention, boredom, and stress.

[0282] This emotional data is fed back into the learning process in real time by the server. If the emotional engine determines that the user is experiencing stress during learning, the server controls the generative model and temporarily switches the learning content to lighter problems or more engaging content. Conversely, if the user shows interest, providing more challenging problems can create an environment that encourages learning challenges.

[0283] For example, if the emotion engine detects that a user's concentration is waning while they are learning about the "basics of the stock market," the server will change the learning topic and rekindle the user's interest by inserting interesting anecdotes and real-world examples related to stocks. As a result, learning never becomes monotonous and is always delivered in a way that fits the user's mood.

[0284] Furthermore, the emotion engine is also used to adjust game elements. For example, when the user achieves a sense of accomplishment, the server automatically adjusts the reward settings, celebrates the achievement, and sends a notification to the terminal to strengthen the motivation for the next step.

[0285] With this system, users can experience a learning path suitable for their emotional state during the process of financial education, and as a result, achieve sustainable and effective improvement in financial literacy.

[0286] The following describes the processing flow.

[0287] Step 1:

[0288] The user starts a learning session through the terminal. The terminal collects voice and video data and sends it to the server.

[0289] Step 2:

[0290] The server inputs the received data into the emotion engine and analyzes the emotion from the tone of the user's voice and expression. This identifies the emotional state such as excitement, stress, and concentration.

[0291] Step 3:

[0292] The server uses a generation model to automatically generate optimal learning content based on the user's current learning progress and emotional state. The content is adjusted according to the user's interests and understanding.

[0293] Step 4:

[0294] The terminal displays the personalized learning content sent from the server to the user. The user can answer questions and also provide feedback to the terminal about the emotions felt in real time.

[0295] Step 5:

[0296] The server uses real-time emotional data obtained through the emotion engine to dynamically change learning content and game elements as needed. This includes, for example, providing relaxing content if the user's stress level is high.

[0297] Step 6:

[0298] The server provides rewards to the user according to their learning progress and achievements. The device notifies the user of these rewards and progress, encouraging further learning.

[0299] Step 7:

[0300] Through their devices, users can review the rewards they've earned and new learning targets, and plan for their next learning session. In this way, a sustained learning loop is formed that takes into account the user's emotional state.

[0301] (Example 2)

[0302] 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".

[0303] Traditional learning systems offer limited personalization based on users' learning progress and areas of interest, lacking dynamic adjustments to maximize learning effectiveness. Furthermore, they fail to adapt to users' emotional states during learning, leading to decreased motivation and increased stress. Moreover, the lack of effective solutions makes it difficult to provide a learning experience that fully meets individual needs.

[0304] 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.

[0305] In this invention, the server includes means for recording and analyzing the learning progress of the user, means for automatically generating learning content according to the user's level of understanding using a generation model, means for enhancing engagement by incorporating game elements, means for recognizing the emotional state and dynamically adjusting the learning content based thereon, and means for providing a prompt to the generation model. Thereby, it becomes possible to adjust the learning content based on the individual learning goals, areas of interest, and emotional state of the user, maximizing the learning effect and maintaining a continuous learning motivation.

[0306] The "means for recording and analyzing the learning progress of the user" refers to the function of recording the process and results of the learning activities carried out by the user as data and using that data to evaluate the progress of learning.

[0307] The "means for automatically generating learning content according to the user's level of understanding using a generation model" refers to the function of automatically constructing and presenting teaching materials and tasks based on the user's level of understanding. The generation model generates optimal content according to the user's learning tendency.

[0308] The "means for enhancing engagement by incorporating game elements" refers to the function of promoting the user's willingness to participate and continuous involvement by incorporating entertaining elements and structures into learning.

[0309] The "means for recognizing the emotional state and dynamically adjusting the learning content based thereon" refers to the function of analyzing the user's emotions and changing the difficulty level and content of learning in real time according to the results.

[0310] The "means for providing a prompt to the generation model" refers to the function of inputting instructions and information according to the user's learning situation and requirements into the generation model. The prompt serves as a trigger for the generation model to obtain an appropriate output.

[0311] The "information processing device" refers to mechanical means for inputting, processing, storing, and outputting data, including various hardware and software such as computers and servers.

[0312] This invention provides a system that operates on an information processing device to improve the user's learning experience. The system mainly consists of a server and a user terminal.

[0313] When a user begins learning, the server collects audio and video data from the device. This uses the device's built-in microphone and camera, and the data is transmitted in real time. This data is analyzed by an emotion engine that uses machine learning algorithms. The emotion engine processes the user's voice tone, facial expressions, and contextual information to determine the user's emotional state.

[0314] Based on this emotional data, the server utilizes a generative AI model to automatically generate learning content tailored to the user's level of understanding and emotional state. The generated content is delivered to the user via their device, allowing them to receive a learning experience suited to their individual needs. The server, receiving feedback from the emotional engine, dynamically adjusts the learning content to maintain the user's interest.

[0315] For example, if the server detects that a user's concentration has waned while learning the "basics of the stock market," it will lighten the topic and insert interesting anecdotes and real-world examples related to stocks. This will rekindle the user's interest and facilitate the learning process.

[0316] Furthermore, the server enhances engagement by incorporating game elements, adjusts reward settings when users feel a sense of accomplishment, and improves motivation for the next learning step.

[0317] As an example of a prompt, the AI ​​model is given instructions such as, "How can we rekindle a user's interest when they lose interest while learning the basics of the stock market?" This prompts the model to generate appropriate learning content. As a result, users can experience a learning path that is individually optimized, leading to sustained motivation and effective learning outcomes.

[0318] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0319] Step 1:

[0320] When a user begins learning, the server collects audio and video data from the device. The user's audio and video are sent to the server as input via the device's microphone and camera. Upon receiving this data, the server performs preprocessing such as data format conversion and noise reduction to create a format suitable for analyzing emotional states.

[0321] Step 2:

[0322] The server inputs pre-processed audio and video data into the emotion engine. Based on the input data, machine learning algorithms are used to analyze the user's voice tone, facial expressions, and context. As a result of the analysis, emotional states such as excitement, interest, attention, boredom, and stress are output. Specific operations include clustering of voice pitch and facial expressions.

[0323] Step 3:

[0324] The server activates a mechanism to provide appropriate prompts to the generative AI model based on the emotional state data output from the emotion engine. It receives emotional data as input and generates prompt sentences tailored to the user's understanding and emotions. These prompt sentences serve as triggers for generating appropriate learning content.

[0325] Step 4:

[0326] The server collects learning content generated by the generative AI model and adjusts it according to the user's learning progress. The learning content dynamically changes to suit the user's emotional state, including difficulty adjustments and engagement-enhancing content at appropriate times. The output is the adjusted learning content displayed on the device.

[0327] Step 5:

[0328] The server evaluates the tailored learning content, incorporates game elements as needed, and sets rewards to enhance user motivation. It references the latest learning outcome data as input and generates rewards and notifications based on success and achievement. The output is a message reflecting the reward displayed on the user's device.

[0329] Step 6:

[0330] The device visually and audibly presents the user with the provided learning content and reward information, motivating them to progress to the next learning stage. The output from the device is an intuitive and easy-to-understand interface for the user. This improves the user's learning experience and allows for more efficient learning.

[0331] (Application Example 2)

[0332] 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."

[0333] There is a challenge in the lack of means to personalize learners' learning experiences and achieve high effectiveness. In particular, technologies that grasp learners' emotions in real time and dynamically adjust learning content based on them are immature, and there is a need for systems that provide efficient learning while maintaining learner motivation.

[0334] 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.

[0335] In this invention, the server includes means for recording and analyzing the user's learning progress, means for automatically generating learning content according to the user's level of understanding using a generation device, means for increasing participation by incorporating game elements, means for processing audio and video data for recognizing the user's emotions, and means for dynamically adjusting the learning content based on the user's emotional evaluation. This makes it possible to provide a highly personalized learning environment that responds to the individual emotional state of the learner.

[0336] A "user" refers to an individual learner who utilizes the learning system.

[0337] "Learning progress" refers to the level of understanding and progress made on assignments achieved by the user through learning activities.

[0338] A "generation device" refers to a device that uses technology to automatically create user learning content.

[0339] "Game elements" refer to entertaining elements used to increase user engagement and interest in learning.

[0340] "Participation level" represents the degree to which a user is involved in a learning activity.

[0341] "Audio data" refers to digital information related to sound collected from users.

[0342] "Video data" refers to visual information used to capture the user's facial expressions and movements.

[0343] "Sentimental assessment" refers to the process of identifying and analyzing a user's emotional state from various data.

[0344] "Dynamic adjustment" means that the system instantly changes its content and functions in response to the user's real-time reactions and status.

[0345] "Learning environment" refers to the overall settings regarding how the interface and content are presented to users when they are learning.

[0346] The system implementing this invention is centered around a server that recognizes emotions in real time through audio and video data in order to highly personalize the user's learning experience. The server collects audio and video data from the user's terminal and analyzes the user's emotional state using an emotion recognition engine.

[0347] The server controls the generated AI model based on the analysis results, dynamically adjusting the learning content to match the user's emotions. Specifically, if it determines that the user is interested, it will provide additional content that increases the difficulty level; conversely, if the user seems bored, it will insert visually appealing material or interesting anecdotes. This will increase the user's learning progress and engagement.

[0348] The hardware used by users consists of standard computer terminals or smart devices. These devices capture the user's voice and facial expressions and supply them to the emotion recognition engine. The software used includes "EmotionEngine" and "ContentServer," which are technological platforms that enable emotion analysis and flexible content delivery.

[0349] For example, if the emotion engine determines that a user is bored while learning a foreign language, the server can immediately play a video clip of a comedy scene to rekindle the user's interest. This approach can maintain and improve learning efficiency.

[0350] Examples of prompts to input into a generative AI model include the following:

[0351] "If users get bored while learning English, provide entertainment to help them change their mood."

[0352] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0353] Step 1:

[0354] The server collects audio and video data from the user's device. This data reflects the user's tone of voice and facial expressions. The input is real-time captured audio and video data, which is then used to prepare the system for pre-processing for emotion recognition.

[0355] Step 2:

[0356] The server uses an emotion engine to analyze the collected audio and video data and evaluate the user's emotional state. The input is the audio and video data prepared in step 1, and the output is data indicating the user's emotional state. Specifically, this data is passed through an emotion recognition algorithm to perform tone analysis and facial expression analysis.

[0357] Step 3:

[0358] The server controls the generative AI model, dynamically generating or adjusting learning content based on the user's emotions. The input here is the emotion evaluation data obtained in step 2. Based on the emotion data, data calculations are performed to adjust the difficulty and type of learning content, and personalized learning content is provided as output. For example, if the server perceives that the user is bored, it adjusts the parameters of the generative model to lighten the content.

[0359] Step 4:

[0360] The device presents the user with adjusted learning content based on instructions from the server. The input is the adjusted learning content sent from the server in step 3, and the output is the information the user receives visually and aurally. In this step, the content is displayed through the user interface, and actions are taken to enable interaction that enhances user engagement.

[0361] Step 5:

[0362] The user responds to the presented learning content through voice or actions. The device captures this data again and sends it to the server. This allows step 1 of the next cycle to resume, providing a continuously adaptable learning experience for the user. The input also serves as user feedback data, which is used for adjustments in the next session.

[0363] 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.

[0364] 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.

[0365] 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.

[0366] [Third Embodiment]

[0367] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0368] 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.

[0369] 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).

[0370] 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.

[0371] 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.

[0372] 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).

[0373] 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.

[0374] 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.

[0375] 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.

[0376] 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.

[0377] 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.

[0378] 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".

[0379] This invention is a system for providing effective and personalized financial education to users. Embodiments of this system are described below.

[0380] The server stores the information registered by users for learning in a database and builds a profile for each individual user. After a user logs in, the server starts each learning session and tracks learning progress in real time. Based on this progress data, the generative model evaluates the user's level of understanding and automatically generates problems and materials that are optimal for that learning level.

[0381] The terminal displays learning content provided by the server to the user and transmits user input to the server. Answers to questions and questions arising during the learning process are sent to the server via the terminal. The server analyzes the received questions using a generative model, generates appropriate answers in real time, and provides them to the user via the terminal.

[0382] For example, if a user wants to deepen their knowledge of "investment trusts," the server will sequentially provide information ranging from basic concepts to advanced case studies related to investment trusts. Furthermore, the server will award rewards and achievements according to the user's learning progress, displaying the results on the device. In this process, the server can also send messages to users who have reached a certain level of learning progress or achievement, suggesting benefits and privileges from partner financial institutions, for instance.

[0383] Users can further enhance their financial knowledge by learning through this system on a daily basis. Because the system supports users in progressing at their own pace and is designed to ensure that their learning is useful in actual financial activities, it will be a powerful tool for improving financial literacy.

[0384] The following describes the processing flow.

[0385] Step 1:

[0386] The user logs into the system via their device and starts a learning session. The device sends login information to the server, which then authenticates the user.

[0387] Step 2:

[0388] The server retrieves the learning history from the authenticated user's profile and evaluates the user's current learning progress. Based on this, it determines what the user should learn next.

[0389] Step 3:

[0390] The server uses a generative model to automatically generate learning questions and materials tailored to the user's level of understanding. The generated content is optimized based on the user's preferences and progress.

[0391] Step 4:

[0392] The device displays learning content sent from the server to the user. The user answers the presented questions and, if they have any questions, can query the server through the device.

[0393] Step 5:

[0394] The server receives user response data and performs analysis using a generative model. Based on the accuracy rate and level of understanding, it updates the user's learning progress and plans the next learning step.

[0395] Step 6:

[0396] When a user asks a question about a specific financial product or information, the server instantly generates an answer using a generative model. The generated answer is then provided to the user in real time via the terminal.

[0397] Step 7:

[0398] The server awards rewards and achievements based on learning progress and displays leaderboards and reward information on the device. This provides a system that allows users to check their learning progress and further motivates them to learn.

[0399] (Example 1)

[0400] 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."

[0401] Traditional financial education systems have struggled to provide personalized learning experiences for individual users, failing to accommodate varying learning paces and levels of understanding. Furthermore, they lacked sufficient feedback based on user progress and inadequate incentives useful for real-world financial activities.

[0402] 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.

[0403] In this invention, the server includes a device for recording and analyzing the user's learning progress, a device for automatically generating learning content tailored to the user's level of understanding using a generative AI model, and a device for determining rewards and achievements based on learning progress. This enables a personalized learning experience based on each user's progress and level of understanding. It also provides support for applying the learning outcomes obtained by the user to real-world financial activities.

[0404] A "device for recording and analyzing user learning progress" is a device that records the learning content, time, and correct answer rate of users, and analyzes this data to understand how far each user has progressed in their learning.

[0405] A "device that automatically generates learning content tailored to the user's level of understanding using a generative AI model" is a device that utilizes artificial intelligence technology to evaluate the user's past learning data and current level of understanding, and dynamically generates optimal learning materials and problems accordingly.

[0406] A "device that determines rewards and achievements based on learning progress" is a device that determines the rewards and achievement indicators that can be obtained according to the user's learning results and progress, and presents them to the user.

[0407] A "device that uses artificial intelligence to generate real-time answers to users' financial questions" is a device that uses artificial intelligence technology to generate quick and appropriate answers to financial questions from users.

[0408] A "device that builds individual user profiles and provides personalized financial education based on them" is a device that creates individual profiles based on user information and learning history, and provides learning content that is suitable for that profile.

[0409] A "notification device that proposes benefits to users" is a device that notifies users who have achieved a certain level of learning outcomes, proposing benefits and preferential treatment from related organizations.

[0410] This invention is a system that personalizes and effectively supports users' financial education. This system mainly consists of a server, terminals, and a generative AI model.

[0411] The server stores user-registered information in a database and creates individual profiles. This allows for tracking each user's learning needs and progress. Furthermore, the server utilizes a generative AI model to automatically generate customized learning materials and problems tailored to the user's level of understanding. The generative AI model is designed to provide users with the most suitable learning content in real time, based on existing learning data. The generative AI model used in this system is based on advanced machine learning algorithms and analyzes users' past learning behavior.

[0412] The terminal displays learning materials provided by the server to the user, supporting interactive learning. It also plays a role in sending user input to the server, allowing for rapid processing of user responses and questions. For example, if a user asks a question about a financial concept they are unsure of, that information is sent to the server via the terminal, and a generative AI model instantly generates an appropriate answer.

[0413] For example, if a user is trying to learn about "stock investing," the server can provide information step-by-step, from basic knowledge to actual investment scenarios. Furthermore, it can evaluate the user's learning progress and offer rewards and benefits. In this way, users can learn at their own pace and be prepared to apply their knowledge to real-world financial activities.

[0414] An example of a prompt might be, "Generate learning materials that cover investment trusts from basic to advanced levels, and create questions tailored to the user's level of understanding." Based on this prompt, the generation AI model creates optimal learning content, enhancing the user's learning experience.

[0415] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0416] Step 1:

[0417] To begin learning, users enter basic information, including their name, email address, and the area of ​​finance they wish to study. The server receives this information and stores it in a database. This data is used to generate individual user profiles, which form the basis for future personalized learning.

[0418] Step 2:

[0419] When a user logs in, the server initiates a session. The server retrieves the user's profile from the database and uses that information to prompt a generating AI model. This model generates optimal learning materials and problem sets based on the user's understanding and interests. This output is used in subsequent learning sessions.

[0420] Step 3:

[0421] The generated learning content is sent from the server to the terminal, which then presents it to the user. The user then proceeds with their learning using the presented materials. This allows the user to absorb information and work on the presented problems at their own pace.

[0422] Step 4:

[0423] When a user enters an answer to a question, the device sends the answer to the server. The server analyzes the answer and automatically evaluates it using a generative AI model. Based on this evaluation, the user's learning progress is updated, and additional feedback and supplementary materials are provided as needed. In this process, data such as the user's accuracy rate and the time taken to answer are important factors.

[0424] Step 5:

[0425] The server comprehensively evaluates the user's learning performance and determines rewards and achievements according to the progress achieved. This reward information is sent to the device and displayed to the user. The server also notifies the user of information about benefits from partner institutions according to their learning progress. This increases user motivation and encourages continued learning.

[0426] (Application Example 1)

[0427] 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."

[0428] In modern society, improving financial literacy is crucial, but there is a lack of effective and engaging educational methods tailored to individual users. Furthermore, general financial education is uniform, making it difficult to provide personalized learning experiences linked to users' individual purchasing activities and interests.

[0429] 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.

[0430] In this invention, the server includes means for recording and analyzing the user's learning progress, means for automatically generating learning content tailored to the user's level of understanding using a generative model, and means for generating learning content based on purchase history. This enables users to receive personalized financial education linked to their purchasing activities and effectively enhance their financial knowledge.

[0431] "Means for recording and analyzing users' learning progress" refers to a function of a system that records the progress of individual users' learning activities and analyzes that progress based on that data.

[0432] "Means of automatically generating learning content tailored to the user's level of understanding using generative models" refers to a function that uses artificial intelligence to automatically generate appropriate learning materials and problems according to the user's level of understanding and learning progress.

[0433] "Methods to enhance engagement by incorporating game elements" refer to features that integrate game elements into the learning process to attract user interest and increase their motivation to participate in learning.

[0434] A "generative model that provides real-time answers to financial questions" is an artificial intelligence model that instantly generates and presents appropriate answers to financial questions that users have.

[0435] "Means for generating learning content based on purchase history" refers to a function that generates learning content based on the user's past purchase activity data, taking into account the relationships between those activities.

[0436] This invention is a personalized educational system for improving financial literacy and is implemented in a form that includes the following elements:

[0437] The server records and analyzes the user's learning progress. As the user progresses, the progress data is stored in a database, and a user profile is generated. Based on this profile, the server uses a generative AI model to automatically generate optimal learning content tailored to the user's level of understanding and interests. Specifically, it utilizes OpenAI's GPT as the generative AI model and creates learning content based on the user's purchase history data, etc. This learning content provides unique and user-relevant material, functioning not merely as education, but as an element that attracts the user's interest.

[0438] The server also features engagement enhancements that incorporate game elements. Here, gamification, including a point system and level-up function, is used to support users' continuous learning. Real-time answers to financial questions are provided by a generative AI model. When a user submits an inquiry, the server immediately analyzes the content, generates an appropriate answer, and provides it to the user through their device.

[0439] For example, if a user seeks a deeper understanding of "long-term savings planning," the server will generate a case study linked to their individual purchase history. It can also present investment information related to products the user has previously purchased, suggesting its application to investment decisions. In this case, an example prompt might be, "Translate the user's purchase history into a financial education module related to smart investments in electronics." This allows the user to gain personalized, practical financial knowledge.

[0440] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0441] Step 1:

[0442] The server receives initial information when a user logs into the application and retrieves the user's past learning progress and purchase history data from the database. This input information forms the basis for subsequent personalized content generation. Based on this data, the server updates the individual learning profile in real time.

[0443] Step 2:

[0444] The server invokes a generative AI model based on the updated learning profile to form prompt sentences. The generative AI model generates new learning content using prompts related to the user's learning needs and purchase history. Specifically, it extracts information according to the user's areas of interest and uses natural language processing to generate learning materials.

[0445] Step 3:

[0446] The generated learning content is displayed to the user through their device. This display process presents information through an intuitively understandable interface. Based on the displayed content, the user can begin learning and provide relevant questions and feedback.

[0447] Step 4:

[0448] When a user's question or feedback is sent to the server via their device, the server uses a generative AI model to generate a response. Here, the user's input data is analyzed, and appropriate answers and additional training materials are prepared in real time. The generated response is then immediately provided to the user via their device.

[0449] Step 5:

[0450] Based on the user's learning progress and responses, the server automatically designs the next learning step and incorporates game elements as needed to continuously support the user's learning. Specifically, it displays points and level-up notifications on the device according to the user's achievements to increase the user's motivation to learn.

[0451] 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.

[0452] This invention is a system that further personalizes and enhances the user's learning experience by incorporating an emotion engine that recognizes the user's emotions.

[0453] First, when a user begins learning, the server activates an emotion engine using audio and video data collected from the device. This emotion engine utilizes machine learning algorithms to accurately recognize the user's emotional state from their tone of voice, facial expressions, and context. As a result, it extracts diverse emotional data such as excitement, interest, attention, boredom, and stress.

[0454] This emotional data is fed back into the learning process in real time by the server. If the emotional engine determines that the user is experiencing stress during learning, the server controls the generative model and temporarily switches the learning content to lighter problems or more engaging content. Conversely, if the user shows interest, providing more challenging problems can create an environment that encourages learning challenges.

[0455] For example, if the emotion engine detects that a user's concentration is waning while they are learning about the "basics of the stock market," the server will change the learning topic and rekindle the user's interest by inserting interesting anecdotes and real-world examples related to stocks. As a result, learning never becomes monotonous and is always delivered in a way that fits the user's mood.

[0456] Furthermore, the emotion engine is also used to adjust game elements. For example, when a user achieves a sense of accomplishment, the server automatically adjusts the reward settings, celebrates the achievement, and sends a notification to the device to reinforce motivation for the next step.

[0457] This system allows users to experience a learning path tailored to their emotional state during the financial education process, resulting in sustained and effective improvement in financial literacy.

[0458] The following describes the processing flow.

[0459] Step 1:

[0460] The user initiates a learning session through their device. The device collects audio and video data and sends it to the server.

[0461] Step 2:

[0462] The server inputs the received data into an emotion engine, which analyzes the user's emotions from their voice tone and facial expressions. This identifies emotional states such as excitement, stress, and level of concentration.

[0463] Step 3:

[0464] The server uses a generative model to automatically generate optimal learning content based on the user's current learning progress and emotional state. The content is adjusted according to the user's interests and level of understanding.

[0465] Step 4:

[0466] The device displays personalized learning content sent from the server to the user. The user can answer questions and also provide feedback to the device in real time about their feelings.

[0467] Step 5:

[0468] The server uses real-time emotional data obtained through the emotion engine to dynamically change learning content and game elements as needed. This includes, for example, providing relaxing content if the user's stress level is high.

[0469] Step 6:

[0470] The server provides rewards to the user according to their learning progress and achievements. The device notifies the user of these rewards and progress, encouraging further learning.

[0471] Step 7:

[0472] Through their devices, users can review the rewards they've earned and new learning targets, and plan for their next learning session. In this way, a sustained learning loop is formed that takes into account the user's emotional state.

[0473] (Example 2)

[0474] 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."

[0475] Traditional learning systems offer limited personalization based on users' learning progress and areas of interest, lacking dynamic adjustments to maximize learning effectiveness. Furthermore, they fail to adapt to users' emotional states during learning, leading to decreased motivation and increased stress. Moreover, the lack of effective solutions makes it difficult to provide a learning experience that fully meets individual needs.

[0476] 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.

[0477] In this invention, the server includes means for recording and analyzing the user's learning progress, means for automatically generating learning content according to the user's level of understanding using a generative model, means for enhancing engagement by incorporating game elements, means for recognizing the user's emotional state and dynamically adjusting the learning content based on it, and means for providing prompts to the generative model. This makes it possible to adjust the learning content based on the user's individual learning goals, areas of interest, and emotional state, thereby maximizing learning effectiveness and maintaining sustained motivation to learn.

[0478] "Means for recording and analyzing user learning progress" refers to a function that records the process and results of a user's learning activities as data and uses that data to evaluate their learning progress.

[0479] "A means of automatically generating learning content tailored to the user's level of understanding using a generative model" refers to a function that automatically constructs and presents learning materials and assignments based on the user's level of understanding. The generative model generates optimal content according to the user's learning tendencies.

[0480] "Methods to enhance engagement by incorporating game elements" refer to functions that promote user participation and continued engagement by incorporating entertaining elements and structures into learning.

[0481] "Means of recognizing emotional states and dynamically adjusting learning content based on them" refers to a function that analyzes the user's emotions and changes the difficulty level and content of learning in real time according to the results.

[0482] "Means of providing prompts to a generative model" refers to functions that input instructions and information into a generative model according to the user's learning progress and requests. Prompts serve as triggers for the generative model to obtain appropriate output.

[0483] An "information processing device" refers to a mechanical means for inputting, processing, storing, and outputting data, and includes various hardware and software such as computers and servers.

[0484] This invention provides a system that operates on an information processing device to improve the user's learning experience. The system mainly consists of a server and a user terminal.

[0485] When a user begins learning, the server collects audio and video data from the device. This uses the device's built-in microphone and camera, and the data is transmitted in real time. This data is analyzed by an emotion engine that uses machine learning algorithms. The emotion engine processes the user's voice tone, facial expressions, and contextual information to determine the user's emotional state.

[0486] Based on this emotional data, the server utilizes a generative AI model to automatically generate learning content tailored to the user's level of understanding and emotional state. The generated content is delivered to the user via their device, allowing them to receive a learning experience suited to their individual needs. The server, receiving feedback from the emotional engine, dynamically adjusts the learning content to maintain the user's interest.

[0487] For example, if the server detects that a user's concentration has waned while learning the "basics of the stock market," it will lighten the topic and insert interesting anecdotes and real-world examples related to stocks. This will rekindle the user's interest and facilitate the learning process.

[0488] Furthermore, the server enhances engagement by incorporating game elements, adjusts reward settings when users feel a sense of accomplishment, and improves motivation for the next learning step.

[0489] As an example of a prompt, the AI ​​model is given instructions such as, "How can we rekindle a user's interest when they lose interest while learning the basics of the stock market?" This prompts the model to generate appropriate learning content. As a result, users can experience a learning path that is individually optimized, leading to sustained motivation and effective learning outcomes.

[0490] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0491] Step 1:

[0492] When a user begins learning, the server collects audio and video data from the device. The user's audio and video are sent to the server as input via the device's microphone and camera. Upon receiving this data, the server performs preprocessing such as data format conversion and noise reduction to create a format suitable for analyzing emotional states.

[0493] Step 2:

[0494] The server inputs pre-processed audio and video data into the emotion engine. Based on the input data, machine learning algorithms are used to analyze the user's voice tone, facial expressions, and context. As a result of the analysis, emotional states such as excitement, interest, attention, boredom, and stress are output. Specific operations include clustering of voice pitch and facial expressions.

[0495] Step 3:

[0496] The server activates a mechanism to provide appropriate prompts to the generative AI model based on the emotional state data output from the emotion engine. It receives emotional data as input and generates prompt sentences tailored to the user's understanding and emotions. These prompt sentences serve as triggers for generating appropriate learning content.

[0497] Step 4:

[0498] The server collects learning content generated by the generative AI model and adjusts it according to the user's learning progress. The learning content dynamically changes to suit the user's emotional state, including difficulty adjustments and engagement-enhancing content at appropriate times. The output is the adjusted learning content displayed on the device.

[0499] Step 5:

[0500] The server evaluates the tailored learning content, incorporates game elements as needed, and sets rewards to enhance user motivation. It references the latest learning outcome data as input and generates rewards and notifications based on success and achievement. The output is a message reflecting the reward displayed on the user's device.

[0501] Step 6:

[0502] The device visually and audibly presents the user with the provided learning content and reward information, motivating them to progress to the next learning stage. The output from the device is an intuitive and easy-to-understand interface for the user. This improves the user's learning experience and allows for more efficient learning.

[0503] (Application Example 2)

[0504] 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."

[0505] There is a challenge in the lack of means to personalize learners' learning experiences and achieve high effectiveness. In particular, technologies that grasp learners' emotions in real time and dynamically adjust learning content based on them are immature, and there is a need for systems that provide efficient learning while maintaining learner motivation.

[0506] 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.

[0507] In this invention, the server includes means for recording and analyzing the user's learning progress, means for automatically generating learning content according to the user's level of understanding using a generation device, means for increasing participation by incorporating game elements, means for processing audio and video data for recognizing the user's emotions, and means for dynamically adjusting the learning content based on the user's emotional evaluation. This makes it possible to provide a highly personalized learning environment that responds to the individual emotional state of the learner.

[0508] A "user" refers to an individual learner who utilizes the learning system.

[0509] "Learning progress" refers to the level of understanding and progress made on assignments achieved by the user through learning activities.

[0510] A "generation device" refers to a device that uses technology to automatically create user learning content.

[0511] "Game elements" refer to entertaining elements used to increase user engagement and interest in learning.

[0512] "Participation level" represents the degree to which a user is involved in a learning activity.

[0513] "Audio data" refers to digital information related to sound collected from users.

[0514] "Video data" refers to visual information used to capture the user's facial expressions and movements.

[0515] "Sentimental assessment" refers to the process of identifying and analyzing a user's emotional state from various data.

[0516] "Dynamic adjustment" means that the system instantly changes its content and functions in response to the user's real-time reactions and status.

[0517] "Learning environment" refers to the overall settings regarding how the interface and content are presented to users when they are learning.

[0518] The system implementing this invention is centered around a server that recognizes emotions in real time through audio and video data in order to highly personalize the user's learning experience. The server collects audio and video data from the user's terminal and analyzes the user's emotional state using an emotion recognition engine.

[0519] The server controls the generated AI model based on the analysis results, dynamically adjusting the learning content to match the user's emotions. Specifically, if it determines that the user is interested, it will provide additional content that increases the difficulty level; conversely, if the user seems bored, it will insert visually appealing material or interesting anecdotes. This will increase the user's learning progress and engagement.

[0520] The hardware used by users consists of standard computer terminals or smart devices. These devices capture the user's voice and facial expressions and supply them to the emotion recognition engine. The software used includes "EmotionEngine" and "ContentServer," which are technological platforms that enable emotion analysis and flexible content delivery.

[0521] For example, if the emotion engine determines that a user is bored while learning a foreign language, the server can immediately play a video clip of a comedy scene to rekindle the user's interest. This approach can maintain and improve learning efficiency.

[0522] Examples of prompts to input into a generative AI model include the following:

[0523] "If users get bored while learning English, provide entertainment to help them change their mood."

[0524] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0525] Step 1:

[0526] The server collects audio and video data from the user's device. This data reflects the user's tone of voice and facial expressions. The input is real-time captured audio and video data, which is then used to prepare the system for pre-processing for emotion recognition.

[0527] Step 2:

[0528] The server uses an emotion engine to analyze the collected audio and video data and evaluate the user's emotional state. The input is the audio and video data prepared in step 1, and the output is data indicating the user's emotional state. Specifically, this data is passed through an emotion recognition algorithm to perform tone analysis and facial expression analysis.

[0529] Step 3:

[0530] The server controls the generative AI model, dynamically generating or adjusting learning content based on the user's emotions. The input here is the emotion evaluation data obtained in step 2. Based on the emotion data, data calculations are performed to adjust the difficulty and type of learning content, and personalized learning content is provided as output. For example, if the server perceives that the user is bored, it adjusts the parameters of the generative model to lighten the content.

[0531] Step 4:

[0532] The device presents the user with adjusted learning content based on instructions from the server. The input is the adjusted learning content sent from the server in step 3, and the output is the information the user receives visually and aurally. In this step, the content is displayed through the user interface, and actions are taken to enable interaction that enhances user engagement.

[0533] Step 5:

[0534] The user responds to the presented learning content through voice or actions. The device captures this data again and sends it to the server. This allows step 1 of the next cycle to resume, providing a continuously adaptable learning experience for the user. The input also serves as user feedback data, which is used for adjustments in the next session.

[0535] 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.

[0536] 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.

[0537] 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.

[0538] [Fourth Embodiment]

[0539] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0540] 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.

[0541] 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).

[0542] 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.

[0543] 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.

[0544] 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).

[0545] 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.

[0546] 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.

[0547] 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.

[0548] 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.

[0549] 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.

[0550] 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.

[0551] 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".

[0552] This invention is a system for providing effective and personalized financial education to users. Embodiments of this system are described below.

[0553] The server stores the information registered by users for learning in a database and builds a profile for each individual user. After a user logs in, the server starts each learning session and tracks learning progress in real time. Based on this progress data, the generative model evaluates the user's level of understanding and automatically generates problems and materials that are optimal for that learning level.

[0554] The terminal displays learning content provided by the server to the user and transmits user input to the server. Answers to questions and questions arising during the learning process are sent to the server via the terminal. The server analyzes the received questions using a generative model, generates appropriate answers in real time, and provides them to the user via the terminal.

[0555] For example, if a user wants to deepen their knowledge of "investment trusts," the server will sequentially provide information ranging from basic concepts to advanced case studies related to investment trusts. Furthermore, the server will award rewards and achievements according to the user's learning progress, displaying the results on the device. In this process, the server can also send messages to users who have reached a certain level of learning progress or achievement, suggesting benefits and privileges from partner financial institutions, for instance.

[0556] Users can further enhance their financial knowledge by learning through this system on a daily basis. Because the system supports users in progressing at their own pace and is designed to ensure that their learning is useful in actual financial activities, it will be a powerful tool for improving financial literacy.

[0557] The following describes the processing flow.

[0558] Step 1:

[0559] The user logs into the system via their device and starts a learning session. The device sends login information to the server, which then authenticates the user.

[0560] Step 2:

[0561] The server retrieves the learning history from the authenticated user's profile and evaluates the user's current learning progress. Based on this, it determines what the user should learn next.

[0562] Step 3:

[0563] The server uses a generative model to automatically generate learning questions and materials tailored to the user's level of understanding. The generated content is optimized based on the user's preferences and progress.

[0564] Step 4:

[0565] The device displays learning content sent from the server to the user. The user answers the presented questions and, if they have any questions, can query the server through the device.

[0566] Step 5:

[0567] The server receives user response data and performs analysis using a generative model. Based on the accuracy rate and level of understanding, it updates the user's learning progress and plans the next learning step.

[0568] Step 6:

[0569] When a user asks a question about a specific financial product or information, the server instantly generates an answer using a generative model. The generated answer is then provided to the user in real time via the terminal.

[0570] Step 7:

[0571] The server awards rewards and achievements based on learning progress and displays leaderboards and reward information on the device. This provides a system that allows users to check their learning progress and further motivates them to learn.

[0572] (Example 1)

[0573] 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".

[0574] Traditional financial education systems have struggled to provide personalized learning experiences for individual users, failing to accommodate varying learning paces and levels of understanding. Furthermore, they lacked sufficient feedback based on user progress and inadequate incentives useful for real-world financial activities.

[0575] 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.

[0576] In this invention, the server includes a device for recording and analyzing the user's learning progress, a device for automatically generating learning content tailored to the user's level of understanding using a generative AI model, and a device for determining rewards and achievements based on learning progress. This enables a personalized learning experience based on each user's progress and level of understanding. It also provides support for applying the learning outcomes obtained by the user to real-world financial activities.

[0577] A "device for recording and analyzing user learning progress" is a device that records the learning content, time, and correct answer rate of users, and analyzes this data to understand how far each user has progressed in their learning.

[0578] A "device that automatically generates learning content tailored to the user's level of understanding using a generative AI model" is a device that utilizes artificial intelligence technology to evaluate the user's past learning data and current level of understanding, and dynamically generates optimal learning materials and problems accordingly.

[0579] A "device that determines rewards and achievements based on learning progress" is a device that determines the rewards and achievement indicators that can be obtained according to the user's learning results and progress, and presents them to the user.

[0580] A "device that uses artificial intelligence to generate real-time answers to users' financial questions" is a device that uses artificial intelligence technology to generate quick and appropriate answers to financial questions from users.

[0581] A "device that builds individual user profiles and provides personalized financial education based on them" is a device that creates individual profiles based on user information and learning history, and provides learning content that is suitable for that profile.

[0582] A "notification device that proposes benefits to users" is a device that notifies users who have achieved a certain level of learning outcomes, proposing benefits and preferential treatment from related organizations.

[0583] This invention is a system that personalizes and effectively supports users' financial education. This system mainly consists of a server, terminals, and a generative AI model.

[0584] The server stores user-registered information in a database and creates individual profiles. This allows for tracking each user's learning needs and progress. Furthermore, the server utilizes a generative AI model to automatically generate customized learning materials and problems tailored to the user's level of understanding. The generative AI model is designed to provide users with the most suitable learning content in real time, based on existing learning data. The generative AI model used in this system is based on advanced machine learning algorithms and analyzes users' past learning behavior.

[0585] The terminal displays learning materials provided by the server to the user, supporting interactive learning. It also plays a role in sending user input to the server, allowing for rapid processing of user responses and questions. For example, if a user asks a question about a financial concept they are unsure of, that information is sent to the server via the terminal, and a generative AI model instantly generates an appropriate answer.

[0586] For example, if a user is trying to learn about "stock investing," the server can provide information step-by-step, from basic knowledge to actual investment scenarios. Furthermore, it can evaluate the user's learning progress and offer rewards and benefits. In this way, users can learn at their own pace and be prepared to apply their knowledge to real-world financial activities.

[0587] An example of a prompt might be, "Generate learning materials that cover investment trusts from basic to advanced levels, and create questions tailored to the user's level of understanding." Based on this prompt, the generation AI model creates optimal learning content, enhancing the user's learning experience.

[0588] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0589] Step 1:

[0590] To begin learning, users enter basic information, including their name, email address, and the area of ​​finance they wish to study. The server receives this information and stores it in a database. This data is used to generate individual user profiles, which form the basis for future personalized learning.

[0591] Step 2:

[0592] When a user logs in, the server initiates a session. The server retrieves the user's profile from the database and uses that information to prompt a generating AI model. This model generates optimal learning materials and problem sets based on the user's understanding and interests. This output is used in subsequent learning sessions.

[0593] Step 3:

[0594] The generated learning content is sent from the server to the terminal, which then presents it to the user. The user then proceeds with their learning using the presented materials. This allows the user to absorb information and work on the presented problems at their own pace.

[0595] Step 4:

[0596] When a user enters an answer to a question, the device sends the answer to the server. The server analyzes the answer and automatically evaluates it using a generative AI model. Based on this evaluation, the user's learning progress is updated, and additional feedback and supplementary materials are provided as needed. In this process, data such as the user's accuracy rate and the time taken to answer are important factors.

[0597] Step 5:

[0598] The server comprehensively evaluates the user's learning performance and determines rewards and achievements according to the progress achieved. This reward information is sent to the device and displayed to the user. The server also notifies the user of information about benefits from partner institutions according to their learning progress. This increases user motivation and encourages continued learning.

[0599] (Application Example 1)

[0600] 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".

[0601] In modern society, improving financial literacy is crucial, but there is a lack of effective and engaging educational methods tailored to individual users. Furthermore, general financial education is uniform, making it difficult to provide personalized learning experiences linked to users' individual purchasing activities and interests.

[0602] 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.

[0603] In this invention, the server includes means for recording and analyzing the user's learning progress, means for automatically generating learning content tailored to the user's level of understanding using a generative model, and means for generating learning content based on purchase history. This enables users to receive personalized financial education linked to their purchasing activities and effectively enhance their financial knowledge.

[0604] "Means for recording and analyzing users' learning progress" refers to a function of a system that records the progress of individual users' learning activities and analyzes that progress based on that data.

[0605] "Means of automatically generating learning content tailored to the user's level of understanding using generative models" refers to a function that uses artificial intelligence to automatically generate appropriate learning materials and problems according to the user's level of understanding and learning progress.

[0606] "Methods to enhance engagement by incorporating game elements" refer to features that integrate game elements into the learning process to attract user interest and increase their motivation to participate in learning.

[0607] A "generative model that provides real-time answers to financial questions" is an artificial intelligence model that instantly generates and presents appropriate answers to financial questions that users have.

[0608] "Means for generating learning content based on purchase history" refers to a function that generates learning content based on the user's past purchase activity data, taking into account the relationships between those activities.

[0609] This invention is a personalized educational system for improving financial literacy and is implemented in a form that includes the following elements:

[0610] The server records and analyzes the user's learning progress. As the user progresses, the progress data is stored in a database, and a user profile is generated. Based on this profile, the server uses a generative AI model to automatically generate optimal learning content tailored to the user's level of understanding and interests. Specifically, it utilizes OpenAI's GPT as the generative AI model and creates learning content based on the user's purchase history data, etc. This learning content provides unique and user-relevant material, functioning not merely as education, but as an element that attracts the user's interest.

[0611] The server also features engagement enhancements that incorporate game elements. Here, gamification, including a point system and level-up function, is used to support users' continuous learning. Real-time answers to financial questions are provided by a generative AI model. When a user submits an inquiry, the server immediately analyzes the content, generates an appropriate answer, and provides it to the user through their device.

[0612] For example, if a user seeks a deeper understanding of "long-term savings planning," the server will generate a case study linked to their individual purchase history. It can also present investment information related to products the user has previously purchased, suggesting its application to investment decisions. In this case, an example prompt might be, "Translate the user's purchase history into a financial education module related to smart investments in electronics." This allows the user to gain personalized, practical financial knowledge.

[0613] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0614] Step 1:

[0615] The server receives initial information when a user logs into the application and retrieves the user's past learning progress and purchase history data from the database. This input information forms the basis for subsequent personalized content generation. Based on this data, the server updates the individual learning profile in real time.

[0616] Step 2:

[0617] The server invokes a generative AI model based on the updated learning profile to form prompt sentences. The generative AI model generates new learning content using prompts related to the user's learning needs and purchase history. Specifically, it extracts information according to the user's areas of interest and uses natural language processing to generate learning materials.

[0618] Step 3:

[0619] The generated learning content is displayed to the user through their device. This display process presents information through an intuitively understandable interface. Based on the displayed content, the user can begin learning and provide relevant questions and feedback.

[0620] Step 4:

[0621] When a user's question or feedback is sent to the server via their device, the server uses a generative AI model to generate a response. Here, the user's input data is analyzed, and appropriate answers and additional training materials are prepared in real time. The generated response is then immediately provided to the user via their device.

[0622] Step 5:

[0623] Based on the user's learning progress and responses, the server automatically designs the next learning step and incorporates game elements as needed to continuously support the user's learning. Specifically, it displays points and level-up notifications on the device according to the user's achievements to increase the user's motivation to learn.

[0624] 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.

[0625] This invention is a system that further personalizes and enhances the user's learning experience by incorporating an emotion engine that recognizes the user's emotions.

[0626] First, when a user begins learning, the server activates an emotion engine using audio and video data collected from the device. This emotion engine utilizes machine learning algorithms to accurately recognize the user's emotional state from their tone of voice, facial expressions, and context. As a result, it extracts diverse emotional data such as excitement, interest, attention, boredom, and stress.

[0627] This emotional data is fed back into the learning process in real time by the server. If the emotional engine determines that the user is experiencing stress during learning, the server controls the generative model and temporarily switches the learning content to lighter problems or more engaging content. Conversely, if the user shows interest, providing more challenging problems can create an environment that encourages learning challenges.

[0628] For example, if the emotion engine detects that a user's concentration is waning while they are learning about the "basics of the stock market," the server will change the learning topic and rekindle the user's interest by inserting interesting anecdotes and real-world examples related to stocks. As a result, learning never becomes monotonous and is always delivered in a way that fits the user's mood.

[0629] Furthermore, the emotion engine is also used to adjust game elements. For example, when a user achieves a sense of accomplishment, the server automatically adjusts the reward settings, celebrates the achievement, and sends a notification to the device to reinforce motivation for the next step.

[0630] This system allows users to experience a learning path tailored to their emotional state during the financial education process, resulting in sustained and effective improvement in financial literacy.

[0631] The following describes the processing flow.

[0632] Step 1:

[0633] The user initiates a learning session through their device. The device collects audio and video data and sends it to the server.

[0634] Step 2:

[0635] The server inputs the received data into an emotion engine, which analyzes the user's emotions from their voice tone and facial expressions. This identifies emotional states such as excitement, stress, and level of concentration.

[0636] Step 3:

[0637] The server uses a generative model to automatically generate optimal learning content based on the user's current learning progress and emotional state. The content is adjusted according to the user's interests and level of understanding.

[0638] Step 4:

[0639] The device displays personalized learning content sent from the server to the user. The user can answer questions and also provide feedback to the device in real time about their feelings.

[0640] Step 5:

[0641] The server uses real-time emotional data obtained through the emotion engine to dynamically change learning content and game elements as needed. This includes, for example, providing relaxing content if the user's stress level is high.

[0642] Step 6:

[0643] The server provides rewards to the user according to their learning progress and achievements. The device notifies the user of these rewards and progress, encouraging further learning.

[0644] Step 7:

[0645] Through their devices, users can review the rewards they've earned and new learning targets, and plan for their next learning session. In this way, a sustained learning loop is formed that takes into account the user's emotional state.

[0646] (Example 2)

[0647] 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".

[0648] Traditional learning systems offer limited personalization based on users' learning progress and areas of interest, lacking dynamic adjustments to maximize learning effectiveness. Furthermore, they fail to adapt to users' emotional states during learning, leading to decreased motivation and increased stress. Moreover, the lack of effective solutions makes it difficult to provide a learning experience that fully meets individual needs.

[0649] 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.

[0650] In this invention, the server includes means for recording and analyzing the user's learning progress, means for automatically generating learning content according to the user's level of understanding using a generative model, means for enhancing engagement by incorporating game elements, means for recognizing the user's emotional state and dynamically adjusting the learning content based on it, and means for providing prompts to the generative model. This makes it possible to adjust the learning content based on the user's individual learning goals, areas of interest, and emotional state, thereby maximizing learning effectiveness and maintaining sustained motivation to learn.

[0651] "Means for recording and analyzing user learning progress" refers to a function that records the process and results of a user's learning activities as data and uses that data to evaluate their learning progress.

[0652] "A means of automatically generating learning content tailored to the user's level of understanding using a generative model" refers to a function that automatically constructs and presents learning materials and assignments based on the user's level of understanding. The generative model generates optimal content according to the user's learning tendencies.

[0653] "Methods to enhance engagement by incorporating game elements" refer to functions that promote user participation and continued engagement by incorporating entertaining elements and structures into learning.

[0654] "Means of recognizing emotional states and dynamically adjusting learning content based on them" refers to a function that analyzes the user's emotions and changes the difficulty level and content of learning in real time according to the results.

[0655] "Means of providing prompts to a generative model" refers to functions that input instructions and information into a generative model according to the user's learning progress and requests. Prompts serve as triggers for the generative model to obtain appropriate output.

[0656] An "information processing device" refers to a mechanical means for inputting, processing, storing, and outputting data, and includes various hardware and software such as computers and servers.

[0657] This invention provides a system that operates on an information processing device to improve the user's learning experience. The system mainly consists of a server and a user terminal.

[0658] When a user begins learning, the server collects audio and video data from the device. This uses the device's built-in microphone and camera, and the data is transmitted in real time. This data is analyzed by an emotion engine that uses machine learning algorithms. The emotion engine processes the user's voice tone, facial expressions, and contextual information to determine the user's emotional state.

[0659] Based on this emotional data, the server utilizes a generative AI model to automatically generate learning content tailored to the user's level of understanding and emotional state. The generated content is delivered to the user via their device, allowing them to receive a learning experience suited to their individual needs. The server, receiving feedback from the emotional engine, dynamically adjusts the learning content to maintain the user's interest.

[0660] For example, if the server detects that a user's concentration has waned while learning the "basics of the stock market," it will lighten the topic and insert interesting anecdotes and real-world examples related to stocks. This will rekindle the user's interest and facilitate the learning process.

[0661] Furthermore, the server enhances engagement by incorporating game elements, adjusts reward settings when users feel a sense of accomplishment, and improves motivation for the next learning step.

[0662] As an example of a prompt, the AI ​​model is given instructions such as, "How can we rekindle a user's interest when they lose interest while learning the basics of the stock market?" This prompts the model to generate appropriate learning content. As a result, users can experience a learning path that is individually optimized, leading to sustained motivation and effective learning outcomes.

[0663] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0664] Step 1:

[0665] When a user begins learning, the server collects audio and video data from the device. The user's audio and video are sent to the server as input via the device's microphone and camera. Upon receiving this data, the server performs preprocessing such as data format conversion and noise reduction to create a format suitable for analyzing emotional states.

[0666] Step 2:

[0667] The server inputs pre-processed audio and video data into the emotion engine. Based on the input data, machine learning algorithms are used to analyze the user's voice tone, facial expressions, and context. As a result of the analysis, emotional states such as excitement, interest, attention, boredom, and stress are output. Specific operations include clustering of voice pitch and facial expressions.

[0668] Step 3:

[0669] The server activates a mechanism to provide appropriate prompts to the generative AI model based on the emotional state data output from the emotion engine. It receives emotional data as input and generates prompt sentences tailored to the user's understanding and emotions. These prompt sentences serve as triggers for generating appropriate learning content.

[0670] Step 4:

[0671] The server collects learning content generated by the generative AI model and adjusts it according to the user's learning progress. The learning content dynamically changes to suit the user's emotional state, including difficulty adjustments and engagement-enhancing content at appropriate times. The output is the adjusted learning content displayed on the device.

[0672] Step 5:

[0673] The server evaluates the tailored learning content, incorporates game elements as needed, and sets rewards to enhance user motivation. It references the latest learning outcome data as input and generates rewards and notifications based on success and achievement. The output is a message reflecting the reward displayed on the user's device.

[0674] Step 6:

[0675] The device visually and audibly presents the user with the provided learning content and reward information, motivating them to progress to the next learning stage. The output from the device is an intuitive and easy-to-understand interface for the user. This improves the user's learning experience and allows for more efficient learning.

[0676] (Application Example 2)

[0677] 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".

[0678] There is a challenge in the lack of means to personalize learners' learning experiences and achieve high effectiveness. In particular, technologies that grasp learners' emotions in real time and dynamically adjust learning content based on them are immature, and there is a need for systems that provide efficient learning while maintaining learner motivation.

[0679] 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.

[0680] In this invention, the server includes means for recording and analyzing the user's learning progress, means for automatically generating learning content according to the user's level of understanding using a generation device, means for increasing participation by incorporating game elements, means for processing audio and video data for recognizing the user's emotions, and means for dynamically adjusting the learning content based on the user's emotional evaluation. This makes it possible to provide a highly personalized learning environment that responds to the individual emotional state of the learner.

[0681] A "user" refers to an individual learner who utilizes the learning system.

[0682] "Learning progress" refers to the level of understanding and progress made on assignments achieved by the user through learning activities.

[0683] A "generation device" refers to a device that uses technology to automatically create user learning content.

[0684] "Game elements" refer to entertaining elements used to increase user engagement and interest in learning.

[0685] "Participation level" represents the degree to which a user is involved in a learning activity.

[0686] "Audio data" refers to digital information related to sound collected from users.

[0687] "Video data" refers to visual information used to capture the user's facial expressions and movements.

[0688] "Sentimental assessment" refers to the process of identifying and analyzing a user's emotional state from various data.

[0689] "Dynamic adjustment" means that the system instantly changes its content and functions in response to the user's real-time reactions and status.

[0690] "Learning environment" refers to the overall settings regarding how the interface and content are presented to users when they are learning.

[0691] The system implementing this invention is centered around a server that recognizes emotions in real time through audio and video data in order to highly personalize the user's learning experience. The server collects audio and video data from the user's terminal and analyzes the user's emotional state using an emotion recognition engine.

[0692] The server controls the generated AI model based on the analysis results, dynamically adjusting the learning content to match the user's emotions. Specifically, if it determines that the user is interested, it will provide additional content that increases the difficulty level; conversely, if the user seems bored, it will insert visually appealing material or interesting anecdotes. This will increase the user's learning progress and engagement.

[0693] The hardware used by users consists of standard computer terminals or smart devices. These devices capture the user's voice and facial expressions and supply them to the emotion recognition engine. The software used includes "EmotionEngine" and "ContentServer," which are technological platforms that enable emotion analysis and flexible content delivery.

[0694] For example, if the emotion engine determines that a user is bored while learning a foreign language, the server can immediately play a video clip of a comedy scene to rekindle the user's interest. This approach can maintain and improve learning efficiency.

[0695] Examples of prompts to input into a generative AI model include the following:

[0696] "If users get bored while learning English, provide entertainment to help them change their mood."

[0697] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0698] Step 1:

[0699] The server collects audio and video data from the user's device. This data reflects the user's tone of voice and facial expressions. The input is real-time captured audio and video data, which is then used to prepare the system for pre-processing for emotion recognition.

[0700] Step 2:

[0701] The server uses an emotion engine to analyze the collected audio and video data and evaluate the user's emotional state. The input is the audio and video data prepared in step 1, and the output is data indicating the user's emotional state. Specifically, this data is passed through an emotion recognition algorithm to perform tone analysis and facial expression analysis.

[0702] Step 3:

[0703] The server controls the generative AI model, dynamically generating or adjusting learning content based on the user's emotions. The input here is the emotion evaluation data obtained in step 2. Based on the emotion data, data calculations are performed to adjust the difficulty and type of learning content, and personalized learning content is provided as output. For example, if the server perceives that the user is bored, it adjusts the parameters of the generative model to lighten the content.

[0704] Step 4:

[0705] The device presents the user with adjusted learning content based on instructions from the server. The input is the adjusted learning content sent from the server in step 3, and the output is the information the user receives visually and aurally. In this step, the content is displayed through the user interface, and actions are taken to enable interaction that enhances user engagement.

[0706] Step 5:

[0707] The user responds to the presented learning content through voice or actions. The device captures this data again and sends it to the server. This allows step 1 of the next cycle to resume, providing a continuously adaptable learning experience for the user. The input also serves as user feedback data, which is used for adjustments in the next session.

[0708] 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.

[0709] 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.

[0710] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0711] 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.

[0712] 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.

[0713] 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.

[0714] 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.

[0715] 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.

[0716] 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."

[0717] 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.

[0718] 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.

[0719] 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.

[0720] 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.

[0721] 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.

[0722] 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.

[0723] 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.

[0724] 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.

[0725] 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.

[0726] 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.

[0727] 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.

[0728] 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.

[0729] The following is further disclosed regarding the embodiments described above.

[0730] (Claim 1)

[0731] A means of recording and analyzing the user's learning progress,

[0732] A means of automatically generating learning content tailored to the user's level of understanding using a generative model,

[0733] A means of increasing engagement by incorporating game elements,

[0734] Including a generative model that provides real-time answers to financial questions,

[0735] A system using information processing equipment.

[0736] (Claim 2)

[0737] The system according to claim 1, wherein the learning content is personalized based on the user's individual learning goals and areas of interest.

[0738] (Claim 3)

[0739] The system according to claim 1, comprising means for providing benefits to enable the application of the user's learning results to real-world financial activities.

[0740] "Example 1"

[0741] (Claim 1)

[0742] A device for recording and analyzing the user's learning progress,

[0743] A device that automatically generates learning content tailored to the user's level of understanding using a generative AI model,

[0744] A device that determines rewards and achievements based on learning progress,

[0745] A device that uses artificial intelligence to generate real-time answers to users' questions about finance,

[0746] A device that builds individual user profiles and provides personalized financial education based on them,

[0747] A system including a notification device that proposes special offers to users.

[0748] (Claim 2)

[0749] The system according to claim 1, wherein the learning content is personalized based on the user's registration information.

[0750] (Claim 3)

[0751] The system according to claim 1, comprising means for providing a reward that enables the user's learning results to be applied to real-world activities.

[0752] "Application Example 1"

[0753] (Claim 1)

[0754] A means of recording and analyzing the user's learning progress,

[0755] A means of automatically generating learning content tailored to the user's level of understanding using a generative model,

[0756] A means of increasing engagement by incorporating game elements,

[0757] A generative model that provides real-time answers to financial questions,

[0758] A system that includes means for generating learning content based on purchase history.

[0759] (Claim 2)

[0760] The system according to claim 1, wherein the learning content is personalized based on the user's individual educational goals and areas of interest.

[0761] (Claim 3)

[0762] The system according to claim 1, comprising means for providing rewards to enable the application of users' learning results to real-world economic activities.

[0763] "Example 2 of combining an emotion engine"

[0764] (Claim 1)

[0765] A means of recording and analyzing the user's learning progress,

[0766] A means of automatically generating learning content tailored to the user's level of understanding using a generative model,

[0767] A means of increasing engagement by incorporating game elements,

[0768] A means of recognizing emotional states and dynamically adjusting learning content based on them,

[0769] Means for providing prompts to the generative model,

[0770] A system using information processing equipment.

[0771] (Claim 2)

[0772] The system according to claim 1, wherein the learning content is personalized based on the user's individual learning goals, areas of interest, and emotional state.

[0773] (Claim 3)

[0774] The system according to claim 1, comprising means for providing benefits to enable the application of the user's learning results to real-world financial activities.

[0775] "Application example 2 when combining with an emotional engine"

[0776] (Claim 1)

[0777] A means of recording and analyzing the user's learning progress,

[0778] A means for automatically generating learning content according to the user's level of understanding using a generation device,

[0779] A means of increasing participation by incorporating game elements,

[0780] Including a generator that provides immediate answers to financial questions,

[0781] A means for processing audio and video data to recognize the user's emotions,

[0782] A means of dynamically adjusting learning content based on the user's emotional evaluation,

[0783] A system that includes this.

[0784] (Claim 2)

[0785] The system according to claim 1, wherein the learning content is adjusted based on the user's individual learning goals and areas of interest, and optimized based on sentiment analysis.

[0786] (Claim 3)

[0787] The system according to claim 1, comprising means for providing rewards to enable the application of users' learning results to real-world financial activities. [Explanation of Symbols]

[0788] 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 means of recording and analyzing the user's learning progress, A means of automatically generating learning content tailored to the user's level of understanding using a generative model, A means of increasing engagement by incorporating game elements, Including a generative model that provides real-time answers to financial questions, A system using information processing equipment.

2. The system according to claim 1, wherein the learning content is personalized based on the user's individual learning goals and areas of interest.

3. The system according to claim 1, comprising means for providing benefits to enable the application of the user's learning results to real-world financial activities.

Images