system

Abstract

We provide the system. [Solution] A means for analyzing learner information received by a data processing device and generating an individualized learning plan, A means for dynamically generating test questions based on the generated learning plan, A means of monitoring learners' learning progress and providing real-time feedback, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a 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 learning in specialized fields such as qualification examinations, it has been difficult for conventional teaching materials and learning methods to provide effective learning adapted to the progress of individual learners and their weak fields. Also, problems have arisen such as the learning effect reaching a plateau due to fixed learning schedules and problem sets, and the large time and cost required for learning. Furthermore, means for maintaining learners' motivation have been limited, and continuous learning has been difficult.

Means for Solving the Problems

[0005] This invention provides a system that can analyze information acquired from learners using a data processing device and generate individually optimized learning plans. This system dynamically generates test questions according to the generated learning plan, addressing the diverse needs of each learner. Furthermore, it enhances learning effectiveness by monitoring learners' progress and providing real-time feedback as needed. It also promotes continuous learning by incorporating a reward system to maintain learner motivation.

[0006] A "data processing device" is a device, such as a computer system or server, that can receive data and perform analysis processing.

[0007] A "learner" refers to an individual who participates in educational programs such as qualification exams and engages in learning activities with the aim of acquiring specific knowledge or skills.

[0008] An "individualized learning plan" refers to a plan that includes a learning schedule and methods customized according to the learner's progress and needs.

[0009] "Examination questions" refer to questions or tasks used to evaluate knowledge and abilities related to a specific qualification examination.

[0010] "Dynamically generated" means that the content is not fixed, but rather changes and is generated in real time based on the learner's progress and needs.

[0011] "Monitoring" refers to the act or function within a system of monitoring learners' learning progress and activities and collecting necessary information.

[0012] "Feedback" refers to information that provides learners with evaluations and advice based on their learning activities, in order to encourage improvement in their learning.

[0013] A "reward system" is a mechanism that provides points or rewards based on learning progress and achievements in order to improve learners' motivation. [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] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes 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, and the like.

[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, 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 improving learning efficiency in qualification examinations. It uses a data processing device to collect and analyze learner information and provides personalized learning plans and practice questions. Specific embodiments are described below.

[0036] Users access the system for learning purposes, entering information about their target certification exam and their learning history. This allows the system to understand their learning needs and areas of weakness.

[0037] The server receives user input and analyzes the information using a specific algorithm. This generates a personalized learning plan optimized for the user's progress and needs. This plan includes specific learning topics, a daily schedule, and recommended supplementary materials.

[0038] The server also utilizes a generative AI model to dynamically generate different test questions for each user. This generation process takes into account past training data and analysis results to ensure the difficulty and content of the questions are best suited to the user.

[0039] As the user progresses through the learning process, the device records their learning progress in real time. Information such as learning time, the number of questions answered, and the correct answer rate are continuously collected.

[0040] Based on this progress information, the server provides timely feedback to the user. For example, it may suggest additional questions for topics with low correct answer rates or provide suggestions for improving learning methods. Such feedback is important for maximizing individual learning effectiveness.

[0041] Furthermore, to maintain and improve user motivation, the device includes a reward system. Points and badges are awarded based on learning progress, which encourages learners.

[0042] As a concrete example, when preparing for a qualification exam such as the "Bookkeeping Examination," the user accesses the system to identify areas they struggle with, such as "Financial Statements" and "Fixed Assets." Based on this, the server generates several related problems and develops a personalized practice plan for the user. During the learning process, the terminal analyzes the user's answers in real time and provides feedback on areas where understanding is insufficient.

[0043] Thus, the system of the present invention optimizes individual learning and provides efficient preparation for qualification examinations.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] Users access the system and log in with their registered accounts. They enter basic information such as the type of certification exam, exam date, past learning data, weak subjects, and goals. This data is securely stored in the system's database.

[0047] Step 2:

[0048] The server receives information sent by the user and accesses the database to retrieve relevant information. This identifies the user's learning tendencies and areas of difficulty. Specific machine learning algorithms are then used to analyze the user profile in detail.

[0049] Step 3:

[0050] The server analyzes the user's input data and generates a personalized learning plan based on the results. This includes a weekly or monthly learning schedule that focuses on topics the user struggles with. The generated plan is stored in a database and associated with the user's profile.

[0051] Step 4:

[0052] The server utilizes a generative AI model to generate test questions tailored to the learning plan. This process generates many questions that focus on areas where the user particularly needs improvement. Furthermore, the generated questions are regularly updated, ensuring that users always receive fresh content.

[0053] Step 5:

[0054] The device records user input (learning progress and answer status) in real time as the user progresses through the learning process. Data such as the time spent learning, the number of correct answers, and incorrect answers are automatically collected.

[0055] Step 6:

[0056] The server analyzes learning progress data collected in real time and provides users with sequential feedback. This includes strategies for strengthening weak areas and advice to improve learning effectiveness. It also dynamically adjusts the learning plan as needed.

[0057] Step 7:

[0058] The device activates a reward system for users based on their learning progress. This allows users to earn points and digital badges, providing a mechanism to maintain their motivation to learn.

[0059] (Example 1)

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

[0061] Preparing for certification exams presents challenges in creating optimal learning plans tailored to individual learners' needs, dynamically generating exam questions at appropriate difficulty levels, and providing effective real-time feedback while maintaining learner motivation. Therefore, there is a need to develop systems that provide personalized learning processes and improve learning efficiency.

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

[0063] In this invention, the server includes means for analyzing learner information to generate an individualized learning plan, means for dynamically generating test questions using a generation AI model based on prompt information, and means for monitoring learning progress in real time and providing feedback. This enables a learning process optimized for each learner, making efficient and effective preparation for qualification exams possible.

[0064] A "data processing mechanism" is a general term for systems and hardware used to analyze information received from learners.

[0065] An "individualized learning plan" is a learning plan that is customized according to each learner's learning needs and progress.

[0066] "Prompt information" refers to text data that is input to give specific instructions to a generative AI model.

[0067] A "generative AI model" is an artificial intelligence technology used to dynamically generate test questions tailored to the learner.

[0068] "Monitoring learning progress" refers to the process of tracking learners' learning activities in real time, collecting data, and analyzing it.

[0069] "Feedback" refers to information provided to learners regarding the evaluation of their learning outcomes and areas for improvement.

[0070] A "reward system" is a mechanism that awards points or badges based on progress in order to improve learners' motivation to learn.

[0071] This invention is a system for improving learning efficiency, particularly for qualification exam preparation. It analyzes learner information and provides an individualized learning plan and dynamically generated exam questions. Specific embodiments are shown below.

[0072] Users first access the system and input information about the target certification exam and their learning history. This helps identify their learning needs and areas of weakness.

[0073] The server receives and stores the input information using a data processing mechanism. It analyzes the information through a specific algorithm and generates a personalized learning plan optimized for the user. This plan includes learning topics, daily schedules, and recommended materials.

[0074] Furthermore, the server utilizes a generative AI model to dynamically generate test questions using prompts based on past training data and analysis results. For example, it might use a prompt such as, "Create an intermediate-level question about financial statements."

[0075] As the user progresses through the learning process, the device records their learning progress in real time, continuously collecting data such as learning time, the number of questions answered, and the accuracy rate.

[0076] Based on this progress data, the server provides users with timely feedback. This feedback includes additional questions for topics with low correct answer rates and suggestions for improving learning methods.

[0077] Furthermore, the device implements a reward system that awards points and badges to users based on their progress during the learning process. This feature contributes to maintaining and improving learners' motivation.

[0078] As a concrete example, in preparing for an accounting exam, the user inputs their weaknesses in the areas of "financial statements" and "fixed assets," and the server generates related problems based on that input and creates a personalized practice plan for the user. At that time, by inputting a prompt such as "Please create additional practice problems on financial statements," the AI ​​model generates and provides the problems.

[0079] Based on this embodiment of the invention, the system optimizes individual learning and enables efficient and effective preparation for qualification exams.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] Users access the system and provide input information such as qualification exam information and their learning history. This information includes the type of exam, learning progress, and areas of strength and weakness. This data is collected as necessary to understand the user's learning needs.

[0083] Step 2:

[0084] The server receives input information from the user through a data processing mechanism and stores it in a database. The stored information is then processed by a data analysis algorithm to analyze each user's learning needs. This analysis extracts the data necessary to generate a specific learning plan.

[0085] Step 3:

[0086] The server generates a personalized learning plan based on the analysis results. This plan generation process considers the user's learning progress and needs derived from the analysis to determine the optimal learning topics and daily schedule. A list of recommended learning materials is also created at this stage. The output provides a customized learning plan tailored to the user.

[0087] Step 4:

[0088] The server utilizes a generative AI model to dynamically generate exam questions based on the user's learning progress using prompts. It uses past learning data and prompts indicating specific instructions as input. For example, based on a prompt such as "Create a financial statement problem at an intermediate level," the server generates a problem best suited to the user. The output is a new exam question provided to the user.

[0089] Step 5:

[0090] The device monitors the user's learning activity in real time and records progress data such as learning time, the number of questions answered, and the correct answer rate. This data is used as input data to understand the user's learning status.

[0091] Step 6:

[0092] The server analyzes the collected progress data and provides timely feedback to the user. This feedback includes suggesting additional questions to address areas where the user's understanding is insufficient, as well as advice on effective learning methods. This feedback serves as output information to improve learning efficiency.

[0093] Step 7:

[0094] The device uses a reward system to maintain and improve the user's learning motivation by awarding points and badges based on their progress. This system aims to increase user motivation and allows for visual confirmation of learning outcomes.

[0095] (Application Example 1)

[0096] 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."

[0097] Individualized learning methods are in demand for qualification exams and various other forms of learning. However, conventional educational content presents a challenge in that all learners study the same content and at the same pace, making it difficult to provide optimal learning tailored to individual needs and progress. Furthermore, there has been a lack of means to promote effective learning while continuously maintaining learner motivation.

[0098] 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.

[0099] In this invention, the server includes means for analyzing educator information entered into a terminal device and generating an individualized educational plan, means for dynamically generating assessment questions based on the generated educational plan, and means for providing reward points or badges according to the educator's progress. This makes it possible to provide optimal learning tailored to each educator's needs and progress, enabling efficient learning while maintaining motivation.

[0100] A "terminal device" is an electronic device used by users to input information or check their learning progress, and includes devices such as smartphones and tablets.

[0101] "Educator information" refers to information that learners provide to the system regarding exams and learning materials, such as personal data, past learning history, and target skills and knowledge.

[0102] An "individualized learning plan" is a plan that outlines specific learning schedules and content optimized for each educator's learning needs and progress.

[0103] "Assessment questions" refer to test questions and practice problems that are dynamically generated by a server to measure the learning progress and understanding of educators.

[0104] "Progress" refers to the degree to which an educator has achieved or mastered the set goals in the process of learning.

[0105] "Reward points and badges" are symbols of achievement or incentives awarded to educators to enhance their motivation to learn and encourage continuous learning.

[0106] A "generative AI model" is an artificial intelligence computational model used to dynamically generate problems and other content tailored to the user's learning progress and needs.

[0107] A "prompt" is an instruction text provided to a generating AI model based on a specific topic or condition, and serves to indicate the conditions and content guidelines for problem generation.

[0108] The system implementing this invention begins with an educator inputting necessary information using a terminal device. The terminal device transmits the information obtained from the educator to a server. The server analyzes the received information from the educator and utilizes data analysis techniques to generate individualized educational plans optimized for each educator. The analysis uses the Python language and data analysis libraries.

[0109] Based on the generated educational plan, the server uses a generative AI model to create prompts and dynamically generate assessment questions. In doing so, the generative AI model adjusts the difficulty and content of the questions according to past learning data and the educator's progress. For example, a prompt such as "Generate questions about basic concepts and applications of financial statements" might be used.

[0110] As educators progress through the learning process, the terminal device monitors their learning progress in real time and transmits the data to a server. This data is used to generate feedback tailored to the educators' learning progress. The feedback is provided as specific suggestions to reinforce areas of insufficient understanding, or as additional practice problems.

[0111] Furthermore, to enhance educators' motivation to learn, the server has a reward system that awards reward points and badges based on the progress of their teaching. This allows educators to visually recognize their learning achievements and maintain their motivation for the next learning step.

[0112] As a result, educators can implement individually optimized learning processes and efficiently enhance knowledge.

[0113] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0114] Step 1:

[0115] The user uses a terminal device to input exam information and learning history. The terminal collects this information and sends it to the server. The input data includes the target exam subject area and past performance.

[0116] Step 2:

[0117] The server uses Python and data analysis libraries to generate personalized learning plans based on the information received from educators. It analyzes the input data to identify the educators' learning needs and areas of difficulty, and generates a corresponding schedule and recommended learning topics. As a result, a personalized learning plan is output.

[0118] Step 3:

[0119] The server uses a generative AI model to dynamically generate assessment questions based on personalized prompts. These prompts include specific themes based on the educator's progress and needs. The generated questions are adjusted to have appropriate difficulty and content for the educator. The output is a educator-specific list of questions.

[0120] Step 4:

[0121] As educators guide students through the learning process, the device monitors their progress in real time. Users answer questions, and the device sends data such as their answers and learning time to the server. The collected data is used to generate feedback for the next step.

[0122] Step 5:

[0123] The server analyzes the collected learning data and evaluates the educators' understanding. Using Python-based data analysis, it identifies topics with particularly low accuracy rates and generates focused feedback. This feedback includes suggestions for additional learning and reinforcing exercises. As output, personalized improvement suggestions are provided to the educators.

[0124] Step 6:

[0125] The server manages reward points and badges based on the educator's learning progress. Points are added according to progress data, and badges are awarded when certain conditions are met. This incentive is designed to improve the educator's motivation. As output, the reward information is reflected on the educator's device.

[0126] 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.

[0127] This invention combines an emotion engine with a learning system to provide a personalized learning experience based on the learner's emotional state. Specific embodiments are shown below.

[0128] When a user begins learning, they access the system and input their qualification exam information and past learning history. The device also uses a microphone and camera to collect the user's voice and facial expression data.

[0129] The server analyzes text and sensor data sent by the user to generate a user profile. Furthermore, the emotion engine analyzes this data to identify the user's current emotional state. For example, it can determine whether the user is "concentrating" or "stressed" based on their voice tone and facial expressions.

[0130] Once the user's emotional state is identified, the server dynamically adjusts the learning plan accordingly. For example, if the user is restless, it prioritizes displaying learning content with a relaxing effect. If the user is stressed, it adjusts the difficulty level of the learning to start with easier questions.

[0131] The server generates personalized learning plans and delivers learning content in a way that is optimal for the user's emotional state. Furthermore, dynamically generated test questions are tailored to the user's emotional state and adjusted to eliminate bias towards areas of weakness.

[0132] As learning progresses, the device records and analyzes the user's learning progress and emotional data in real time. Based on this data, the server continuously optimizes the learning plan and provides feedback. If necessary, it presents encouraging messages and interactive content that respond to the user's emotional state.

[0133] Furthermore, the reward system also works in conjunction with the emotion engine. When a user overcomes a specific emotional state and progresses in their learning, their efforts are recognized, and points or badges are awarded to improve their motivation.

[0134] As a concrete example, when a user experiences stress during a certification exam and studies at home, the system uses sensors to detect the tension in the user's face. Based on this, the server plays relaxing music in the background and presents simple practice problems, employing a strategy to enhance concentration during study.

[0135] Thus, this invention utilizes an emotion engine to realize a learning process that is attuned to the learner's emotions, thereby supporting efficient and effective preparation for qualification exams.

[0136] The following describes the processing flow.

[0137] Step 1:

[0138] The user logs into the learning system and enters information about the certification exam they are studying for, past learning data, and areas of difficulty. Once data entry is complete, the device automatically starts the data collection process.

[0139] Step 2:

[0140] The device collects user voice and facial expression data via microphones and cameras. This data is sent in real time to an emotion analysis engine, where it is analyzed to identify the user's emotional state.

[0141] Step 3:

[0142] The server analyzes the received user information and emotional data to determine the user's current emotional state. For example, it can set states such as "concentration," "stress," and "fatigue," and identify which state the user is in.

[0143] Step 4:

[0144] The server dynamically adjusts the learning plan based on the user's emotional state. It generates a personalized learning strategy, such as including relaxing content when stressed and providing more challenging problems when focused.

[0145] Step 5:

[0146] The server utilizes generative AI to dynamically generate test questions based on a tailored learning plan. This process takes into account emotional states and past learning history to create the optimal set of questions.

[0147] Step 6:

[0148] The device displays the user the adjusted learning content and questions. The user progresses through the presented learning material and deepens their learning by entering their answers into the device.

[0149] Step 7:

[0150] The device records the user's learning progress and updated sentiment data in real time. Learning results and sentiment changes are continuously transmitted to the server.

[0151] Step 8:

[0152] The server provides feedback to users based on the collected data. It sends encouraging messages as needed, refines the learning pace and strategy, and aims to maximize effectiveness.

[0153] Step 9:

[0154] The device rewards the user based on their learning progress. For example, if a positive change in emotional state is observed, points or other rewards may be awarded to support motivation maintenance.

[0155] (Example 2)

[0156] 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".

[0157] Traditional learning systems provide uniform learning plans and feedback without considering the user's emotional state, resulting in decreased learning efficiency and difficulty in maintaining user motivation. Furthermore, they are unable to provide personalized learning experiences because they cannot generate dynamic learning content based on user emotions or provide effective real-time feedback.

[0158] 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.

[0159] In this invention, the server includes means for analyzing user information and biometric data received by a data collection device to identify the user's emotional state; means for dynamically generating and adjusting an individualized learning plan based on the identified emotional state; and means for dynamically generating test questions according to the user's emotional state based on the generated learning plan. This makes it possible to provide an optimal learning plan tailored to each user's emotional state, thereby improving learning efficiency and motivation.

[0160] "Data acquisition equipment" is a general term for hardware and software used to acquire user information and biometric data.

[0161] "Emotional state" refers to the psychological and emotional state identified by analyzing the user's biometric data and input information obtained from data collection devices.

[0162] A "personalized learning plan" refers to a learning progress plan that is dynamically generated and adjusted based on the user's identified emotional state and learning needs.

[0163] "Dynamically generating" refers to the process of instantly generating adaptive content and issues in response to real-time user data and changing conditions.

[0164] "Feedback" refers to responses that include information and advice provided in real time, based on the user's learning progress and emotional state.

[0165] A "reward system" refers to a mechanism that provides rewards in accordance with the user's learning progress and improvement in their emotional state in order to motivate them.

[0166] This invention is a system that provides an individualized learning experience based on the user's emotional state. Specific embodiments of this system are described below.

[0167] First, the user accesses the system and inputs their learning objectives, past learning history, and current learning needs. The terminal collects the user's voice and facial expression data using a high-resolution camera and noise-canceling microphone, and transmits this biometric data to the server.

[0168] The server analyzes user information and biometric data received from data collection devices. Specifically, the server uses natural language processing and image recognition algorithms to extract voice and facial features, and an emotion engine to identify the user's real-time emotional state. For example, the server determines emotion labels such as "concentrated" or "stressed."

[0169] Next, the server dynamically generates and adjusts an individualized learning plan based on the identified emotional state. In this process, the server uses a generative AI model to select learning content suitable for the user and adjusts the difficulty level of the learning tasks accordingly. For example, for a user experiencing anxiety, it might start by presenting easy problems.

[0170] The device monitors the user's learning progress in real time, and the server provides feedback based on that information. This feedback includes encouraging messages tailored to the user's emotions and interactive learning content. When the user overcomes a specific emotional state, the server activates a reward system, boosting motivation by awarding points and badges.

[0171] For example, when a user experiencing stress related to a certification exam uses the system, the device's sensors detect tension in the user's face. Based on this information, the server plays relaxing music in the background and presents simple practice questions. In this way, the system helps the user concentrate and improves their learning experience.

[0172] An example of a prompt is, "Suggest learning support content to reduce user stress." Based on this prompt, the server utilizes a generative AI model to construct an appropriate learning plan.

[0173] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0174] Step 1:

[0175] Users input their learning objectives and past learning history through the terminal. Based on this input, the terminal forms the user's basic profile and sends it to the server. The input data provided by the user includes specific exam categories and priorities in a text form. Formatted data packets are sent to the server as output from the terminal.

[0176] Step 2:

[0177] The device uses a camera and microphone to collect user voice and facial expression data. The collected input data includes the intonation of the user's voice and changes in facial expressions. The device records this in real time using sensors and transfers the obtained biometric data to a server. The device then processes the sensing data and outputs it as digital data.

[0178] Step 3:

[0179] The server analyzes the user's text and biometric data received from the terminal. First, it uses natural language processing algorithms to understand the user's input text and extract the necessary information. This text data analysis includes tokenization and semantic analysis. For biometric data, image recognition and voice analysis technologies are used to identify the user's emotional state. Based on this analysis, the server outputs emotional labels such as "concentrated" or "stressed."

[0180] Step 4:

[0181] The server generates a personalized learning plan based on identified emotion labels and the user's known profile. This process utilizes a generative AI model to dynamically select the most suitable learning content for the user's needs. The AI ​​model takes emotion labels as input and generates a list of learning tasks and supplementary materials as output.

[0182] Step 5:

[0183] Based on instructions from the server, the device provides learning content tailored to the user. For example, background music corresponding to a specific emotion or focused exercises are displayed on the screen. In this operation, the device executes content delivery commands received from the server.

[0184] Step 6:

[0185] The device monitors the user's learning progress in real time and feeds the collected data back to the server. This progress data includes learning speed and accuracy, which the server uses to optimize its approach based on the user's progress. The server then generates adaptive feedback again and notifies the user through the device.

[0186] Step 7:

[0187] When a user overcomes a specific emotional state, the server triggers a reward system, awarding points or badges as motivation. This reward visualizes the user's efforts and increases their motivation. This result is ultimately output as the reward the user receives.

[0188] (Application Example 2)

[0189] 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".

[0190] Traditional learning systems have struggled to provide personalized learning experiences based on learners' emotional states, making it difficult to promote effective learning progress. Current systems lack the means to provide appropriate learning content according to learners' emotional states, resulting in decreased learning efficiency and motivation.

[0191] 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.

[0192] In this invention, the server includes means for analyzing learner information received by a data processing device and generating an individualized learning plan; means for dynamically generating test questions based on the generated learning plan; means for analyzing the learner's emotional state and dynamically adjusting the learning plan based on the analysis results; means for acquiring emotional data from the learner's expressions and voice and adaptively providing learning content based on said data; and means for monitoring the learner's learning progress and providing real-time feedback. This makes it possible to provide an optimal learning environment and content that is in line with the learner's emotional state.

[0193] A "data processing device" is a device that collects and analyzes learner information and generates individualized learning plans.

[0194] An "individualized learning plan" refers to a plan that includes learning content optimized based on the learner's individual information and emotional state.

[0195] "Means for dynamically generating exam questions" refers to a function that generates and provides exam questions in real time according to the learner's progress and status.

[0196] "Means for analyzing learners' emotional states" refers to technologies for identifying and analyzing learners' emotions based on their facial expressions and voice data.

[0197] "Means of adaptively providing learning content" refers to a function that provides optimized learning content according to the learner's emotional state.

[0198] "Means for monitoring learning progress and providing feedback" refers to a function that continuously monitors the learner's learning progress and provides real-time feedback according to that progress.

[0199] This invention realizes a system that provides a real-time, adaptive learning experience based on the learner's emotions. The server analyzes the learner's information using a data processing device and generates an individualized learning plan. The learner's voice and facial expression data are acquired through the device's microphone and camera. This data is analyzed using emotion analysis software. Specifically, the system uses Microsoft® Azure® emotion recognition API to analyze changes in the learner's voice tone and facial expressions to identify their emotional state.

[0200] The server dynamically adjusts the learning plan based on the analysis results. For example, if the server determines that the learner is stressed, it immediately provides learning content of a lower difficulty level. Furthermore, it adaptively displays the learning content and provides materials and videos in a way that is optimal for the learner's emotions.

[0201] The device incorporates nature imagery and calming music to help users relax through visual and auditory feedback. This allows users to learn more effectively. Learning progress is monitored by the server, and encouraging messages and notifications related to the reward system are displayed as needed.

[0202] As a concrete example, in an application for preparing for certification exams, when a user is feeling fatigued, the system provides a short video to encourage a brief refresh. This allows the user to mentally reset and maintain their motivation to continue learning.

[0203] An example of a prompt to input into a generative AI model is: "Based on the user's emotional data, please suggest learning support content that has a relaxing effect. Specifically, combine the viewing content with visual effects that have a relaxing effect." This prompt serves as a guide for generating content that is optimal for the learner.

[0204] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0205] Step 1:

[0206] The user initiates a learning session through their device. The device uses its microphone and camera to capture the user's voice and facial expression data. This allows for the collection of the user's emotional information in real time. The collected data is then sent to a server.

[0207] Step 2:

[0208] The server uses Microsoft Azure's emotion recognition API to analyze the acquired voice and facial expression data. To determine the emotional state, it analyzes changes in voice tone and facial expression from the input data to identify emotions such as "concentrated" or "stressed." Based on these analysis results, the user's current emotional state is output.

[0209] Step 3:

[0210] The server dynamically generates a personalized learning plan based on the analyzed emotional information. Specifically, if the user is feeling stressed, it selects easier problems and adjusts the learning plan to provide relaxing content. This learning plan is generated as output and sent to the user's device.

[0211] Step 4:

[0212] The device displays learning content provided by the server. Natural imagery and calming music are played in the background to help the user relax visually and aurally. Adaptive virtual effects are employed to alleviate the user's emotions.

[0213] Step 5:

[0214] During learning, the user's learning progress and emotional state are continuously monitored. The device sends progress data to the server, which uses this data to further optimize the learning plan. Appropriate feedback and encouraging messages are provided to the user according to their progress.

[0215] Step 6:

[0216] When a user achieves a specific emotional state or learning outcome, a reward system on the server is activated. This system fairly evaluates the user's efforts and motivates them to continue learning by awarding points or badges.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] [Second Embodiment]

[0221] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0222] 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.

[0223] 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).

[0224] 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.

[0225] 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.

[0226] 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).

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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".

[0233] This invention is a system for improving learning efficiency in qualification examinations. It uses a data processing device to collect and analyze learner information and provides personalized learning plans and practice questions. Specific embodiments are described below.

[0234] Users access the system for learning purposes, entering information about their target certification exam and their learning history. This allows the system to understand their learning needs and areas of weakness.

[0235] The server receives user input and analyzes the information using a specific algorithm. This generates a personalized learning plan optimized for the user's progress and needs. This plan includes specific learning topics, a daily schedule, and recommended supplementary materials.

[0236] The server also utilizes a generative AI model to dynamically generate different test questions for each user. This generation process takes into account past training data and analysis results to ensure the difficulty and content of the questions are best suited to the user.

[0237] As the user progresses through the learning process, the device records their learning progress in real time. Information such as learning time, the number of questions answered, and the correct answer rate are continuously collected.

[0238] Based on this progress information, the server provides timely feedback to the user. For example, it may suggest additional questions for topics with low correct answer rates or provide suggestions for improving learning methods. Such feedback is important for maximizing individual learning effectiveness.

[0239] Furthermore, to maintain and improve user motivation, the device includes a reward system. Points and badges are awarded based on learning progress, which encourages learners.

[0240] As a concrete example, when preparing for a qualification exam such as the "Bookkeeping Examination," the user accesses the system to identify areas they struggle with, such as "Financial Statements" and "Fixed Assets." Based on this, the server generates several related problems and develops a personalized practice plan for the user. During the learning process, the terminal analyzes the user's answers in real time and provides feedback on areas where understanding is insufficient.

[0241] Thus, the system of the present invention optimizes individual learning and provides efficient preparation for qualification examinations.

[0242] The following describes the processing flow.

[0243] Step 1:

[0244] Users access the system and log in with their registered accounts. They enter basic information such as the type of certification exam, exam date, past learning data, weak subjects, and goals. This data is securely stored in the system's database.

[0245] Step 2:

[0246] The server receives information sent by the user and accesses the database to retrieve relevant information. This identifies the user's learning tendencies and areas of difficulty. Specific machine learning algorithms are then used to analyze the user profile in detail.

[0247] Step 3:

[0248] The server analyzes the user's input data and generates a personalized learning plan based on the results. This includes a weekly or monthly learning schedule that focuses on topics the user struggles with. The generated plan is stored in a database and associated with the user's profile.

[0249] Step 4:

[0250] The server utilizes a generative AI model to generate test questions tailored to the learning plan. This process generates many questions that focus on areas where the user particularly needs improvement. Furthermore, the generated questions are regularly updated, ensuring that users always receive fresh content.

[0251] Step 5:

[0252] The device records user input (learning progress and answer status) in real time as the user progresses through the learning process. Data such as the time spent learning, the number of correct answers, and incorrect answers are automatically collected.

[0253] Step 6:

[0254] The server analyzes learning progress data collected in real time and provides users with sequential feedback. This includes strategies for strengthening weak areas and advice to improve learning effectiveness. It also dynamically adjusts the learning plan as needed.

[0255] Step 7:

[0256] The device activates a reward system for users based on their learning progress. This allows users to earn points and digital badges, providing a mechanism to maintain their motivation to learn.

[0257] (Example 1)

[0258] 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."

[0259] Preparing for certification exams presents challenges in creating optimal learning plans tailored to individual learners' needs, dynamically generating exam questions at appropriate difficulty levels, and providing effective real-time feedback while maintaining learner motivation. Therefore, there is a need to develop systems that provide personalized learning processes and improve learning efficiency.

[0260] 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.

[0261] In this invention, the server includes means for analyzing learner information to generate an individualized learning plan, means for dynamically generating test questions using a generation AI model based on prompt information, and means for monitoring learning progress in real time and providing feedback. This enables a learning process optimized for each learner, making efficient and effective preparation for qualification exams possible.

[0262] A "data processing mechanism" is a general term for systems and hardware used to analyze information received from learners.

[0263] An "individualized learning plan" is a learning plan that is customized according to each learner's learning needs and progress.

[0264] "Prompt information" refers to text data that is input to give specific instructions to a generative AI model.

[0265] A "generative AI model" is an artificial intelligence technology used to dynamically generate test questions tailored to the learner.

[0266] "Monitoring learning progress" refers to the process of tracking learners' learning activities in real time, collecting data, and analyzing it.

[0267] "Feedback" refers to information provided to learners regarding the evaluation of their learning outcomes and areas for improvement.

[0268] A "reward system" is a mechanism that awards points or badges based on progress in order to improve learners' motivation to learn.

[0269] This invention is a system for improving learning efficiency, particularly for qualification exam preparation. It analyzes learner information and provides an individualized learning plan and dynamically generated exam questions. Specific embodiments are shown below.

[0270] Users first access the system and input information about the target certification exam and their learning history. This helps identify their learning needs and areas of weakness.

[0271] The server receives and stores the input information using a data processing mechanism. It analyzes the information through a specific algorithm and generates a personalized learning plan optimized for the user. This plan includes learning topics, daily schedules, and recommended materials.

[0272] Furthermore, the server utilizes a generative AI model to dynamically generate test questions using prompts based on past training data and analysis results. For example, it might use a prompt such as, "Create an intermediate-level question about financial statements."

[0273] As the user progresses through the learning process, the device records their learning progress in real time, continuously collecting data such as learning time, the number of questions answered, and the accuracy rate.

[0274] Based on this progress data, the server provides users with timely feedback. This feedback includes additional questions for topics with low correct answer rates and suggestions for improving learning methods.

[0275] Furthermore, the device implements a reward system that awards points and badges to users based on their progress during the learning process. This feature contributes to maintaining and improving learners' motivation.

[0276] As a concrete example, in preparing for an accounting exam, the user inputs their weaknesses in the areas of "financial statements" and "fixed assets," and the server generates related problems based on that input and creates a personalized practice plan for the user. At that time, by inputting a prompt such as "Please create additional practice problems on financial statements," the AI ​​model generates and provides the problems.

[0277] Based on this embodiment of the invention, the system optimizes individual learning and enables efficient and effective preparation for qualification exams.

[0278] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0279] Step 1:

[0280] The user accesses the system and provides input information such as qualification exam information and previous learning history. This information includes the type of exam, progress of learning, strengths and weaknesses, etc. These data are collected as the data necessary to understand the user's learning needs.

[0281] Step 2:

[0282] The server receives the input information received from the user by the data processing mechanism and stores it in the database. The stored information is processed by a data analysis algorithm to analyze the learning needs of each user. From this analysis, the data necessary for generating a specific learning plan is extracted.

[0283] Step 3:

[0284] The server generates an individualized education plan based on the analysis results. In this plan generation, based on the user's learning situation and needs obtained from the analysis results, the optimal learning topics and daily schedules are planned. Also, a recommended teaching material list is created here. As output, a customized learning plan for the user is provided.

[0285] Step 4:

[0286] The server utilizes the generated AI model to dynamically generate exam questions according to the user's learning progress using prompt sentences. As input, past learning data and prompt sentences indicating specific instructions are used. For example, based on a prompt sentence such as "Please create intermediate-level financial statement questions", optimal questions for the user are generated. As output, new exam questions provided to the user are obtained.

[0287] Step 5:

[0288] The terminal monitors the user's learning activities in real time and records progress data such as learning time, number of questions answered, correct answer rate, etc. This data is used as input data to understand the user's learning situation.

[0289] Step 6:

[0290] The server analyzes the collected progress data and provides timely feedback to the user. This feedback includes suggesting additional questions to address areas where the user's understanding is insufficient, as well as advice on effective learning methods. This feedback serves as output information to improve learning efficiency.

[0291] Step 7:

[0292] The device uses a reward system to maintain and improve the user's learning motivation by awarding points and badges based on their progress. This system aims to increase user motivation and allows for visual confirmation of learning outcomes.

[0293] (Application Example 1)

[0294] 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."

[0295] Individualized learning methods are in demand for qualification exams and various other forms of learning. However, conventional educational content presents a challenge in that all learners study the same content and at the same pace, making it difficult to provide optimal learning tailored to individual needs and progress. Furthermore, there has been a lack of means to promote effective learning while continuously maintaining learner motivation.

[0296] 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.

[0297] In this invention, the server includes means for analyzing educator information entered into a terminal device and generating an individualized educational plan, means for dynamically generating assessment questions based on the generated educational plan, and means for providing reward points or badges according to the educator's progress. This makes it possible to provide optimal learning tailored to each educator's needs and progress, enabling efficient learning while maintaining motivation.

[0298] A "terminal device" is an electronic device used by users to input information or check their learning progress, and includes devices such as smartphones and tablets.

[0299] "Educator information" refers to information that learners provide to the system regarding exams and learning materials, such as personal data, past learning history, and target skills and knowledge.

[0300] An "individualized learning plan" is a plan that outlines specific learning schedules and content optimized for each educator's learning needs and progress.

[0301] "Assessment questions" refer to test questions and practice problems that are dynamically generated by a server to measure the learning progress and understanding of educators.

[0302] "Progress" refers to the degree to which an educator has achieved or mastered the set goals in the process of learning.

[0303] "Reward points and badges" are symbols of achievement or incentives awarded to educators to enhance their motivation to learn and encourage continuous learning.

[0304] A "generative AI model" is an artificial intelligence computational model used to dynamically generate problems and other content tailored to the user's learning progress and needs.

[0305] A "prompt sentence" is an instruction text provided to a generative AI model based on specific topics or conditions, and is used to indicate the conditions and content guidelines for question generation.

[0306] The system for implementing this invention begins with an educator inputting necessary information using a terminal device. The terminal device serves to transmit the information obtained from the educator to the server. The server analyzes the received educator information and utilizes data analysis techniques to generate an individualized educational plan optimized for each educator. Python language and data analysis libraries are used for the analysis.

[0307] Based on the generated educational plan, the server creates a prompt sentence using a generative AI model and dynamically generates evaluation questions. At that time, the generative AI model adjusts the difficulty level and content of the questions according to past learning data and the progress of the educator. For example, a prompt sentence such as "Please generate questions about basic concepts and applications related to financial statements" is used.

[0308] When the educator progresses in learning, the terminal device monitors the educator's learning progress in real time and transmits the data to the server. This data is used to generate feedback according to the educator's learning progress. The feedback is provided as specific suggestions for reinforcing insufficient understanding parts and additional practice questions.

[0309] Furthermore, in order to enhance the educator's learning motivation, the server has a reward system and awards reward points and badges based on the progress of education. As a result, the educator can visually recognize the results of their own learning and maintain their motivation for the next learning step.

[0310] As described above, the educator can realize an individually optimized learning process and efficiently enhance knowledge.

[0311] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0312] Step 1:

[0313] The user uses a terminal device to input exam information and learning history. The terminal collects this information and sends it to the server. The input data includes the target exam subject area and past performance.

[0314] Step 2:

[0315] The server uses Python and data analysis libraries to generate personalized learning plans based on the information received from educators. It analyzes the input data to identify the educators' learning needs and areas of difficulty, and generates a corresponding schedule and recommended learning topics. As a result, a personalized learning plan is output.

[0316] Step 3:

[0317] The server uses a generative AI model to dynamically generate assessment questions based on personalized prompts. These prompts include specific themes based on the educator's progress and needs. The generated questions are adjusted to have appropriate difficulty and content for the educator. The output is a educator-specific list of questions.

[0318] Step 4:

[0319] As educators guide students through the learning process, the device monitors their progress in real time. Users answer questions, and the device sends data such as their answers and learning time to the server. The collected data is used to generate feedback for the next step.

[0320] Step 5:

[0321] The server analyzes the collected learning data and evaluates the educators' understanding. Using Python-based data analysis, it identifies topics with particularly low accuracy rates and generates focused feedback. This feedback includes suggestions for additional learning and reinforcing exercises. As output, personalized improvement suggestions are provided to the educators.

[0322] Step 6:

[0323] The server manages reward points and badges based on the educator's learning progress. Points are added according to progress data, and badges are awarded when certain conditions are met. This incentive is designed to improve the educator's motivation. As output, the reward information is reflected on the educator's device.

[0324] 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.

[0325] This invention combines an emotion engine with a learning system to provide a personalized learning experience based on the learner's emotional state. Specific embodiments are shown below.

[0326] When a user begins learning, they access the system and input their qualification exam information and past learning history. The device also uses a microphone and camera to collect the user's voice and facial expression data.

[0327] The server analyzes text and sensor data sent by the user to generate a user profile. Furthermore, the emotion engine analyzes this data to identify the user's current emotional state. For example, it can determine whether the user is "concentrating" or "stressed" based on their voice tone and facial expressions.

[0328] Once the user's emotional state is identified, the server dynamically adjusts the learning plan accordingly. For example, if the user is restless, it prioritizes displaying learning content with a relaxing effect. If the user is stressed, it adjusts the difficulty level of the learning to start with easier questions.

[0329] The server generates personalized learning plans and delivers learning content in a way that is optimal for the user's emotional state. Furthermore, dynamically generated test questions are tailored to the user's emotional state and adjusted to eliminate bias towards areas of weakness.

[0330] As learning progresses, the device records and analyzes the user's learning progress and emotional data in real time. Based on this data, the server continuously optimizes the learning plan and provides feedback. If necessary, it presents encouraging messages and interactive content that respond to the user's emotional state.

[0331] Furthermore, the reward system also works in conjunction with the emotion engine. When a user overcomes a specific emotional state and progresses in their learning, their efforts are recognized, and points or badges are awarded to improve their motivation.

[0332] As a concrete example, when a user experiences stress during a certification exam and studies at home, the system uses sensors to detect the tension in the user's face. Based on this, the server plays relaxing music in the background and presents simple practice problems, employing a strategy to enhance concentration during study.

[0333] Thus, this invention utilizes an emotion engine to realize a learning process that is attuned to the learner's emotions, thereby supporting efficient and effective preparation for qualification exams.

[0334] The following describes the processing flow.

[0335] Step 1:

[0336] The user logs into the learning system and enters information about the certification exam they are studying for, past learning data, and areas of difficulty. Once data entry is complete, the device automatically starts the data collection process.

[0337] Step 2:

[0338] The device collects user voice and facial expression data via microphones and cameras. This data is sent in real time to an emotion analysis engine, where it is analyzed to identify the user's emotional state.

[0339] Step 3:

[0340] The server analyzes the received user information and emotional data to determine the user's current emotional state. For example, it can set states such as "concentration," "stress," and "fatigue," and identify which state the user is in.

[0341] Step 4:

[0342] The server dynamically adjusts the learning plan based on the user's emotional state. It generates a personalized learning strategy, such as including relaxing content when stressed and providing more challenging problems when focused.

[0343] Step 5:

[0344] The server utilizes generative AI to dynamically generate test questions based on a tailored learning plan. This process takes into account emotional states and past learning history to create the optimal set of questions.

[0345] Step 6:

[0346] The device displays the user the adjusted learning content and questions. The user progresses through the presented learning material and deepens their learning by entering their answers into the device.

[0347] Step 7:

[0348] The device records the user's learning progress and updated sentiment data in real time. Learning results and sentiment changes are continuously transmitted to the server.

[0349] Step 8:

[0350] The server provides feedback to users based on the collected data. It sends encouraging messages as needed, refines the learning pace and strategy, and aims to maximize effectiveness.

[0351] Step 9:

[0352] The device rewards the user based on their learning progress. For example, if a positive change in emotional state is observed, points or other rewards may be awarded to support motivation maintenance.

[0353] (Example 2)

[0354] 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".

[0355] Traditional learning systems provide uniform learning plans and feedback without considering the user's emotional state, resulting in decreased learning efficiency and difficulty in maintaining user motivation. Furthermore, they are unable to provide personalized learning experiences because they cannot generate dynamic learning content based on user emotions or provide effective real-time feedback.

[0356] 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.

[0357] In this invention, the server includes means for analyzing user information and biometric data received by a data collection device to identify the user's emotional state; means for dynamically generating and adjusting an individualized learning plan based on the identified emotional state; and means for dynamically generating test questions according to the user's emotional state based on the generated learning plan. This makes it possible to provide an optimal learning plan tailored to each user's emotional state, thereby improving learning efficiency and motivation.

[0358] "Data acquisition equipment" is a general term for hardware and software used to acquire user information and biometric data.

[0359] "Emotional state" refers to the psychological and emotional state identified by analyzing the user's biometric data and input information obtained from data collection devices.

[0360] A "personalized learning plan" refers to a learning progress plan that is dynamically generated and adjusted based on the user's identified emotional state and learning needs.

[0361] "Dynamically generating" refers to the process of instantly generating adaptive content and issues in response to real-time user data and changing conditions.

[0362] "Feedback" refers to responses that include information and advice provided in real time, based on the user's learning progress and emotional state.

[0363] A "reward system" refers to a mechanism that provides rewards in accordance with the user's learning progress and improvement in their emotional state in order to motivate them.

[0364] This invention is a system that provides an individualized learning experience based on the user's emotional state. Specific embodiments of this system are described below.

[0365] First, the user accesses the system and inputs their learning objectives, past learning history, and current learning needs. The terminal collects the user's voice and facial expression data using a high-resolution camera and noise-canceling microphone, and transmits this biometric data to the server.

[0366] The server analyzes user information and biometric data received from data collection devices. Specifically, the server uses natural language processing and image recognition algorithms to extract voice and facial features, and an emotion engine to identify the user's real-time emotional state. For example, the server determines emotion labels such as "concentrated" or "stressed."

[0367] Next, the server dynamically generates and adjusts an individualized learning plan based on the identified emotional state. In this process, the server uses a generative AI model to select learning content suitable for the user and adjusts the difficulty level of the learning tasks accordingly. For example, for a user experiencing anxiety, it might start by presenting easy problems.

[0368] The device monitors the user's learning progress in real time, and the server provides feedback based on that information. This feedback includes encouraging messages tailored to the user's emotions and interactive learning content. When the user overcomes a specific emotional state, the server activates a reward system, boosting motivation by awarding points and badges.

[0369] For example, when a user experiencing stress related to a certification exam uses the system, the device's sensors detect tension in the user's face. Based on this information, the server plays relaxing music in the background and presents simple practice questions. In this way, the system helps the user concentrate and improves their learning experience.

[0370] An example of a prompt is, "Suggest learning support content to reduce user stress." Based on this prompt, the server utilizes a generative AI model to construct an appropriate learning plan.

[0371] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0372] Step 1:

[0373] Users input their learning objectives and past learning history through the terminal. Based on this input, the terminal forms the user's basic profile and sends it to the server. The input data provided by the user includes specific exam categories and priorities in a text form. Formatted data packets are sent to the server as output from the terminal.

[0374] Step 2:

[0375] The device uses a camera and microphone to collect user voice and facial expression data. The collected input data includes the intonation of the user's voice and changes in facial expressions. The device records this in real time using sensors and transfers the obtained biometric data to a server. The device then processes the sensing data and outputs it as digital data.

[0376] Step 3:

[0377] The server analyzes the user's text and biometric data received from the terminal. First, it uses natural language processing algorithms to understand the user's input text and extract the necessary information. This text data analysis includes tokenization and semantic analysis. For biometric data, image recognition and voice analysis technologies are used to identify the user's emotional state. Based on this analysis, the server outputs emotional labels such as "concentrated" or "stressed."

[0378] Step 4:

[0379] The server generates a personalized learning plan based on identified emotion labels and the user's known profile. This process utilizes a generative AI model to dynamically select the most suitable learning content for the user's needs. The AI ​​model takes emotion labels as input and generates a list of learning tasks and supplementary materials as output.

[0380] Step 5:

[0381] Based on instructions from the server, the device provides learning content tailored to the user. For example, background music corresponding to a specific emotion or focused exercises are displayed on the screen. In this operation, the device executes content delivery commands received from the server.

[0382] Step 6:

[0383] The device monitors the user's learning progress in real time and feeds the collected data back to the server. This progress data includes learning speed and accuracy, which the server uses to optimize its approach based on the user's progress. The server then generates adaptive feedback again and notifies the user through the device.

[0384] Step 7:

[0385] When a user overcomes a specific emotional state, the server triggers a reward system, awarding points or badges as motivation. This reward visualizes the user's efforts and increases their motivation. This result is ultimately output as the reward the user receives.

[0386] (Application Example 2)

[0387] 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."

[0388] Traditional learning systems have struggled to provide personalized learning experiences based on learners' emotional states, making it difficult to promote effective learning progress. Current systems lack the means to provide appropriate learning content according to learners' emotional states, resulting in decreased learning efficiency and motivation.

[0389] 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.

[0390] In this invention, the server includes means for analyzing learner information received by a data processing device and generating an individualized learning plan; means for dynamically generating test questions based on the generated learning plan; means for analyzing the learner's emotional state and dynamically adjusting the learning plan based on the analysis results; means for acquiring emotional data from the learner's expressions and voice and adaptively providing learning content based on said data; and means for monitoring the learner's learning progress and providing real-time feedback. This makes it possible to provide an optimal learning environment and content that is in line with the learner's emotional state.

[0391] A "data processing device" is a device that collects and analyzes learner information and generates individualized learning plans.

[0392] An "individualized learning plan" refers to a plan that includes learning content optimized based on the learner's individual information and emotional state.

[0393] "Means for dynamically generating exam questions" refers to a function that generates and provides exam questions in real time according to the learner's progress and status.

[0394] "Means for analyzing learners' emotional states" refers to technologies for identifying and analyzing learners' emotions based on their facial expressions and voice data.

[0395] "Means of adaptively providing learning content" refers to a function that provides optimized learning content according to the learner's emotional state.

[0396] "Means for monitoring learning progress and providing feedback" refers to a function that continuously monitors the learner's learning progress and provides real-time feedback according to that progress.

[0397] This invention realizes a system that provides a real-time, adaptive learning experience based on the learner's emotions. The server analyzes the learner's information using a data processing device and generates an individualized learning plan. The learner's voice and facial expression data are acquired through the device's microphone and camera. This data is analyzed using emotion analysis software. Specifically, the Microsoft Azure emotion recognition API is used to analyze the learner's voice tone and changes in facial expressions to identify their emotional state.

[0398] The server dynamically adjusts the learning plan based on the analysis results. For example, if the server determines that the learner is stressed, it immediately provides learning content of a lower difficulty level. Furthermore, it adaptively displays the learning content and provides materials and videos in a way that is optimal for the learner's emotions.

[0399] The device incorporates nature imagery and calming music to help users relax through visual and auditory feedback. This allows users to learn more effectively. Learning progress is monitored by the server, and encouraging messages and notifications related to the reward system are displayed as needed.

[0400] As a concrete example, in an application for preparing for certification exams, when a user is feeling fatigued, the system provides a short video to encourage a brief refresh. This allows the user to mentally reset and maintain their motivation to continue learning.

[0401] An example of a prompt to input into a generative AI model is: "Based on the user's emotional data, please suggest learning support content that has a relaxing effect. Specifically, combine the viewing content with visual effects that have a relaxing effect." This prompt serves as a guide for generating content that is optimal for the learner.

[0402] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0403] Step 1:

[0404] The user initiates a learning session through their device. The device uses its microphone and camera to capture the user's voice and facial expression data. This allows for the collection of the user's emotional information in real time. The collected data is then sent to a server.

[0405] Step 2:

[0406] The server uses Microsoft Azure's emotion recognition API to analyze the acquired voice and facial expression data. To determine the emotional state, it analyzes changes in voice tone and facial expression from the input data to identify emotions such as "concentrated" or "stressed." Based on these analysis results, the user's current emotional state is output.

[0407] Step 3:

[0408] The server dynamically generates a personalized learning plan based on the analyzed emotional information. Specifically, if the user is feeling stressed, it selects easier problems and adjusts the learning plan to provide relaxing content. This learning plan is generated as output and sent to the user's device.

[0409] Step 4:

[0410] The device displays learning content provided by the server. Natural imagery and calming music are played in the background to help the user relax visually and aurally. Adaptive virtual effects are employed to alleviate the user's emotions.

[0411] Step 5:

[0412] During learning, the user's learning progress and emotional state are continuously monitored. The device sends progress data to the server, which uses this data to further optimize the learning plan. Appropriate feedback and encouraging messages are provided to the user according to their progress.

[0413] Step 6:

[0414] When a user achieves a specific emotional state or learning outcome, a reward system on the server is activated. This system fairly evaluates the user's efforts and motivates them to continue learning by awarding points or badges.

[0415] 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.

[0416] 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.

[0417] 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.

[0418] [Third Embodiment]

[0419] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0420] 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.

[0421] 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).

[0422] 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.

[0423] 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.

[0424] 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).

[0425] 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.

[0426] 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.

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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".

[0431] This invention is a system for improving learning efficiency in qualification examinations. It uses a data processing device to collect and analyze learner information and provides personalized learning plans and practice questions. Specific embodiments are described below.

[0432] Users access the system for learning purposes and input information about their target certification exam and their learning history. This allows the system to understand their learning needs and areas of weakness.

[0433] The server receives user input and analyzes the information using a specific algorithm. This generates a personalized learning plan optimized for the user's progress and needs. This plan includes specific learning topics, a daily schedule, and recommended supplementary materials.

[0434] The server also utilizes a generative AI model to dynamically generate different test questions for each user. This generation process takes into account past training data and analysis results to ensure the difficulty and content of the questions are best suited to the user.

[0435] As the user progresses through the learning process, the device records their learning progress in real time. Information such as learning time, the number of questions answered, and the correct answer rate are continuously collected.

[0436] Based on this progress information, the server provides timely feedback to the user. For example, it may suggest additional questions for topics with low correct answer rates or provide suggestions for improving learning methods. Such feedback is important for maximizing individual learning effectiveness.

[0437] Furthermore, to maintain and improve user motivation, the device includes a reward system. Points and badges are awarded based on learning progress, which encourages learners.

[0438] As a concrete example, when preparing for a qualification exam such as the "Bookkeeping Examination," the user accesses the system to identify areas they struggle with, such as "Financial Statements" and "Fixed Assets." Based on this, the server generates several related problems and develops a personalized practice plan for the user. During the learning process, the terminal analyzes the user's answers in real time and provides feedback on areas where understanding is insufficient.

[0439] Thus, the system of the present invention optimizes individual learning and provides efficient preparation for qualification examinations.

[0440] The following describes the processing flow.

[0441] Step 1:

[0442] Users access the system and log in with their registered accounts. They enter basic information such as the type of certification exam, exam date, past learning data, weak subjects, and goals. This data is securely stored in the system's database.

[0443] Step 2:

[0444] The server receives information sent by the user and accesses the database to retrieve relevant information. This identifies the user's learning tendencies and areas of difficulty. Specific machine learning algorithms are then used to analyze the user profile in detail.

[0445] Step 3:

[0446] The server analyzes the user's input data and generates a personalized learning plan based on the results. This includes a weekly or monthly learning schedule that focuses on topics the user struggles with. The generated plan is stored in a database and associated with the user's profile.

[0447] Step 4:

[0448] The server utilizes a generative AI model to generate test questions tailored to the learning plan. This process generates many questions that focus on areas where the user particularly needs improvement. Furthermore, the generated questions are regularly updated, ensuring that users always receive fresh content.

[0449] Step 5:

[0450] The device records user input (learning progress and answer status) in real time as the user progresses through the learning process. Data such as the time spent learning, the number of correct answers, and incorrect answers are automatically collected.

[0451] Step 6:

[0452] The server analyzes learning progress data collected in real time and provides users with sequential feedback. This includes strategies for strengthening weak areas and advice to improve learning effectiveness. It also dynamically adjusts the learning plan as needed.

[0453] Step 7:

[0454] The device activates a reward system for users based on their learning progress. This allows users to earn points and digital badges, providing a mechanism to maintain their motivation to learn.

[0455] (Example 1)

[0456] 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."

[0457] Preparing for certification exams presents challenges in creating optimal learning plans tailored to individual learners' needs, dynamically generating exam questions at appropriate difficulty levels, and providing effective real-time feedback while maintaining learner motivation. Therefore, there is a need to develop systems that provide personalized learning processes and improve learning efficiency.

[0458] 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.

[0459] In this invention, the server includes means for analyzing learner information to generate an individualized learning plan, means for dynamically generating test questions using a generation AI model based on prompt information, and means for monitoring learning progress in real time and providing feedback. This enables a learning process optimized for each learner, making efficient and effective preparation for qualification exams possible.

[0460] A "data processing mechanism" is a general term for systems and hardware used to analyze information received from learners.

[0461] An "individualized learning plan" is a learning plan that is customized according to each learner's learning needs and progress.

[0462] "Prompt information" refers to text data that is input to give specific instructions to a generative AI model.

[0463] A "generative AI model" is an artificial intelligence technology used to dynamically generate test questions tailored to the learner.

[0464] "Monitoring learning progress" refers to the process of tracking learners' learning activities in real time, collecting data, and analyzing it.

[0465] "Feedback" refers to information provided to learners regarding the evaluation of their learning outcomes and areas for improvement.

[0466] A "reward system" is a mechanism that awards points or badges based on progress in order to improve learners' motivation to learn.

[0467] This invention is a system for improving learning efficiency, particularly for qualification exam preparation. It analyzes learner information and provides an individualized learning plan and dynamically generated exam questions. Specific embodiments are shown below.

[0468] Users first access the system and input information about the target certification exam and their learning history. This helps identify their learning needs and areas of weakness.

[0469] The server receives and stores the input information using a data processing mechanism. It analyzes the information through a specific algorithm and generates a personalized learning plan optimized for the user. This plan includes learning topics, daily schedules, and recommended materials.

[0470] Furthermore, the server utilizes a generative AI model to dynamically generate test questions using prompts based on past training data and analysis results. For example, it might use a prompt such as, "Create an intermediate-level question about financial statements."

[0471] As the user progresses through the learning process, the device records their learning progress in real time, continuously collecting data such as learning time, the number of questions answered, and the accuracy rate.

[0472] Based on this progress data, the server provides users with timely feedback. This feedback includes additional questions for topics with low correct answer rates and suggestions for improving learning methods.

[0473] Furthermore, the device implements a reward system that awards points and badges to users based on their progress during the learning process. This feature contributes to maintaining and improving learners' motivation.

[0474] As a concrete example, in preparing for an accounting exam, the user inputs their weaknesses in the areas of "financial statements" and "fixed assets," and the server generates related problems based on that input and creates a personalized practice plan for the user. At that time, by inputting a prompt such as "Please create additional practice problems on financial statements," the AI ​​model generates and provides the problems.

[0475] Based on this embodiment of the invention, the system optimizes individual learning and enables efficient and effective preparation for qualification exams.

[0476] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0477] Step 1:

[0478] Users access the system and provide input information such as qualification exam information and their learning history. This information includes the type of exam, learning progress, and areas of strength and weakness. This data is collected as necessary to understand the user's learning needs.

[0479] Step 2:

[0480] The server receives input information from the user through a data processing mechanism and stores it in a database. The stored information is then processed by a data analysis algorithm to analyze each user's learning needs. This analysis extracts the data necessary to generate a specific learning plan.

[0481] Step 3:

[0482] The server generates a personalized learning plan based on the analysis results. This plan generation process considers the user's learning progress and needs derived from the analysis to determine the optimal learning topics and daily schedule. A list of recommended learning materials is also created at this stage. The output provides a customized learning plan tailored to the user.

[0483] Step 4:

[0484] The server utilizes a generative AI model to dynamically generate exam questions based on the user's learning progress using prompts. It uses past learning data and prompts indicating specific instructions as input. For example, based on a prompt such as "Create a financial statement problem at an intermediate level," the server generates a problem best suited to the user. The output is a new exam question provided to the user.

[0485] Step 5:

[0486] The device monitors the user's learning activity in real time and records progress data such as learning time, the number of questions answered, and the correct answer rate. This data is used as input data to understand the user's learning status.

[0487] Step 6:

[0488] The server analyzes the collected progress data and provides timely feedback to the user. This feedback includes suggesting additional questions to address areas where the user's understanding is insufficient, as well as advice on effective learning methods. This feedback serves as output information to improve learning efficiency.

[0489] Step 7:

[0490] The device uses a reward system to maintain and improve the user's learning motivation by awarding points and badges based on their progress. This system aims to increase user motivation and allows for visual confirmation of learning outcomes.

[0491] (Application Example 1)

[0492] 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."

[0493] Individualized learning methods are in demand for qualification exams and various other forms of learning. However, conventional educational content presents a challenge in that all learners study the same content and at the same pace, making it difficult to provide optimal learning tailored to individual needs and progress. Furthermore, there has been a lack of means to promote effective learning while continuously maintaining learner motivation.

[0494] 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.

[0495] In this invention, the server includes means for analyzing educator information entered into a terminal device and generating an individualized educational plan, means for dynamically generating assessment questions based on the generated educational plan, and means for providing reward points or badges according to the educator's progress. This makes it possible to provide optimal learning tailored to each educator's needs and progress, enabling efficient learning while maintaining motivation.

[0496] A "terminal device" is an electronic device used by users to input information or check their learning progress, and includes devices such as smartphones and tablets.

[0497] "Educator information" refers to information that learners provide to the system regarding exams and learning materials, such as personal data, past learning history, and target skills and knowledge.

[0498] An "individualized learning plan" is a plan that outlines specific learning schedules and content optimized for each educator's learning needs and progress.

[0499] "Assessment questions" refer to test questions and practice problems that are dynamically generated by a server to measure the learning progress and understanding of educators.

[0500] "Progress" refers to the degree to which an educator has achieved or mastered the set goals in the process of learning.

[0501] "Reward points and badges" are symbols of achievement or incentives awarded to educators to enhance their motivation to learn and encourage continuous learning.

[0502] A "generative AI model" is an artificial intelligence computational model used to dynamically generate problems and other content tailored to the user's learning progress and needs.

[0503] A "prompt" is an instruction text provided to a generating AI model based on a specific topic or condition, and serves to indicate the conditions and content guidelines for problem generation.

[0504] The system implementing this invention begins with an educator inputting necessary information using a terminal device. The terminal device transmits the information obtained from the educator to a server. The server analyzes the received information from the educator and utilizes data analysis techniques to generate individualized educational plans optimized for each educator. The analysis uses the Python language and data analysis libraries.

[0505] Based on the generated educational plan, the server uses a generative AI model to create prompts and dynamically generate assessment questions. In doing so, the generative AI model adjusts the difficulty and content of the questions according to past learning data and the educator's progress. For example, a prompt such as "Generate questions about basic concepts and applications of financial statements" might be used.

[0506] As educators progress through the learning process, the terminal device monitors their learning progress in real time and transmits the data to a server. This data is used to generate feedback tailored to the educators' learning progress. The feedback is provided as specific suggestions to reinforce areas of insufficient understanding, or as additional practice problems.

[0507] Furthermore, to enhance educators' motivation to learn, the server has a reward system that awards reward points and badges based on the progress of their teaching. This allows educators to visually recognize their learning achievements and maintain their motivation for the next learning step.

[0508] As a result, educators can implement individually optimized learning processes and efficiently enhance knowledge.

[0509] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0510] Step 1:

[0511] The user uses a terminal device to input exam information and learning history. The terminal collects this information and sends it to the server. The input data includes the target exam subject area and past performance.

[0512] Step 2:

[0513] The server uses Python and data analysis libraries to generate personalized learning plans based on the information received from educators. It analyzes the input data to identify the educators' learning needs and areas of difficulty, and generates a corresponding schedule and recommended learning topics. As a result, a personalized learning plan is output.

[0514] Step 3:

[0515] The server uses a generative AI model to dynamically generate assessment questions based on personalized prompts. These prompts include specific themes based on the educator's progress and needs. The generated questions are adjusted to have appropriate difficulty and content for the educator. The output is a educator-specific list of questions.

[0516] Step 4:

[0517] As educators guide students through the learning process, the device monitors their progress in real time. Users answer questions, and the device sends data such as their answers and learning time to the server. The collected data is used to generate feedback for the next step.

[0518] Step 5:

[0519] The server analyzes the collected learning data and evaluates the educators' understanding. Using Python-based data analysis, it identifies topics with particularly low accuracy rates and generates focused feedback. This feedback includes suggestions for additional learning and reinforcing exercises. As output, personalized improvement suggestions are provided to the educators.

[0520] Step 6:

[0521] The server manages reward points and badges based on the educator's learning progress. Points are added according to progress data, and badges are awarded when certain conditions are met. This incentive is designed to improve the educator's motivation. As output, the reward information is reflected on the educator's device.

[0522] 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.

[0523] This invention combines an emotion engine with a learning system to provide a personalized learning experience based on the learner's emotional state. Specific embodiments are shown below.

[0524] When a user begins learning, they access the system and input their qualification exam information and past learning history. The device also uses a microphone and camera to collect the user's voice and facial expression data.

[0525] The server analyzes text and sensor data sent by the user to generate a user profile. Furthermore, the emotion engine analyzes this data to identify the user's current emotional state. For example, it can determine whether the user is "concentrating" or "stressed" based on their voice tone and facial expressions.

[0526] Once the user's emotional state is identified, the server dynamically adjusts the learning plan accordingly. For example, if the user is restless, it prioritizes displaying learning content with a relaxing effect. If the user is stressed, it adjusts the difficulty level of the learning to start with easier questions.

[0527] The server generates personalized learning plans and delivers learning content in a way that is optimal for the user's emotional state. Furthermore, dynamically generated test questions are tailored to the user's emotional state and adjusted to eliminate bias towards areas of weakness.

[0528] As learning progresses, the device records and analyzes the user's learning progress and emotional data in real time. Based on this data, the server continuously optimizes the learning plan and provides feedback. If necessary, it presents encouraging messages and interactive content that respond to the user's emotional state.

[0529] Furthermore, the reward system also works in conjunction with the emotion engine. When a user overcomes a specific emotional state and progresses in their learning, their efforts are recognized, and points or badges are awarded to improve their motivation.

[0530] As a concrete example, when a user experiences stress during a certification exam and studies at home, the system uses sensors to detect the tension in the user's face. Based on this, the server plays relaxing music in the background and presents simple practice problems, employing a strategy to enhance concentration during study.

[0531] Thus, this invention utilizes an emotion engine to realize a learning process that is attuned to the learner's emotions, thereby supporting efficient and effective preparation for qualification exams.

[0532] The following describes the processing flow.

[0533] Step 1:

[0534] The user logs into the learning system and enters information about the certification exam they are studying for, past learning data, and areas of difficulty. Once data entry is complete, the device automatically starts the data collection process.

[0535] Step 2:

[0536] The device collects user voice and facial expression data via microphones and cameras. This data is sent in real time to an emotion analysis engine, where it is analyzed to identify the user's emotional state.

[0537] Step 3:

[0538] The server analyzes the received user information and emotional data to determine the user's current emotional state. For example, it can set states such as "concentration," "stress," and "fatigue," and identify which state the user is in.

[0539] Step 4:

[0540] The server dynamically adjusts the learning plan based on the user's emotional state. It generates a personalized learning strategy, such as including relaxing content when stressed and providing more challenging problems when focused.

[0541] Step 5:

[0542] The server utilizes generative AI to dynamically generate test questions based on a tailored learning plan. This process takes into account emotional states and past learning history to create the optimal set of questions.

[0543] Step 6:

[0544] The device displays the user the adjusted learning content and questions. The user progresses through the presented learning material and deepens their learning by entering their answers into the device.

[0545] Step 7:

[0546] The device records the user's learning progress and updated sentiment data in real time. Learning results and sentiment changes are continuously transmitted to the server.

[0547] Step 8:

[0548] The server provides feedback to users based on the collected data. It sends encouraging messages as needed, refines the learning pace and strategy, and aims to maximize effectiveness.

[0549] Step 9:

[0550] The device rewards the user based on their learning progress. For example, if a positive change in emotional state is observed, points or other rewards may be awarded to support motivation maintenance.

[0551] (Example 2)

[0552] 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."

[0553] Traditional learning systems provide uniform learning plans and feedback without considering the user's emotional state, resulting in decreased learning efficiency and difficulty in maintaining user motivation. Furthermore, they are unable to provide personalized learning experiences because they cannot generate dynamic learning content based on user emotions or provide effective real-time feedback.

[0554] 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.

[0555] In this invention, the server includes means for analyzing user information and biometric data received by a data collection device to identify the user's emotional state; means for dynamically generating and adjusting an individualized learning plan based on the identified emotional state; and means for dynamically generating test questions according to the user's emotional state based on the generated learning plan. This makes it possible to provide an optimal learning plan tailored to each user's emotional state, thereby improving learning efficiency and motivation.

[0556] "Data acquisition equipment" is a general term for hardware and software used to acquire user information and biometric data.

[0557] "Emotional state" refers to the psychological and emotional state identified by analyzing the user's biometric data and input information obtained from data collection devices.

[0558] A "personalized learning plan" refers to a learning progress plan that is dynamically generated and adjusted based on the user's identified emotional state and learning needs.

[0559] "Dynamically generating" refers to the process of instantly generating adaptive content and issues in response to real-time user data and changing conditions.

[0560] "Feedback" refers to responses that include information and advice provided in real time, based on the user's learning progress and emotional state.

[0561] A "reward system" refers to a mechanism that provides rewards in accordance with the user's learning progress and improvement in their emotional state in order to motivate them.

[0562] This invention is a system that provides an individualized learning experience based on the user's emotional state. Specific embodiments of this system are described below.

[0563] First, the user accesses the system and inputs their learning objectives, past learning history, and current learning needs. The terminal collects the user's voice and facial expression data using a high-resolution camera and noise-canceling microphone, and transmits this biometric data to the server.

[0564] The server analyzes user information and biometric data received from data collection devices. Specifically, the server uses natural language processing and image recognition algorithms to extract voice and facial features, and an emotion engine to identify the user's real-time emotional state. For example, the server determines emotion labels such as "concentrated" or "stressed."

[0565] Next, the server dynamically generates and adjusts an individualized learning plan based on the identified emotional state. In this process, the server uses a generative AI model to select learning content suitable for the user and adjusts the difficulty level of the learning tasks accordingly. For example, for a user experiencing anxiety, it might start by presenting easy problems.

[0566] The device monitors the user's learning progress in real time, and the server provides feedback based on that information. This feedback includes encouraging messages tailored to the user's emotions and interactive learning content. When the user overcomes a specific emotional state, the server activates a reward system, boosting motivation by awarding points and badges.

[0567] For example, when a user experiencing stress related to a certification exam uses the system, the device's sensors detect tension in the user's face. Based on this information, the server plays relaxing music in the background and presents simple practice questions. In this way, the system helps the user concentrate and improves their learning experience.

[0568] An example of a prompt is, "Suggest learning support content to reduce user stress." Based on this prompt, the server utilizes a generative AI model to construct an appropriate learning plan.

[0569] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0570] Step 1:

[0571] Users input their learning objectives and past learning history through the terminal. Based on this input, the terminal forms the user's basic profile and sends it to the server. The input data provided by the user includes specific exam categories and priorities in a text form. Formatted data packets are sent to the server as output from the terminal.

[0572] Step 2:

[0573] The device uses a camera and microphone to collect user voice and facial expression data. The collected input data includes the intonation of the user's voice and changes in facial expressions. The device records this in real time using sensors and transfers the obtained biometric data to a server. The device then processes the sensing data and outputs it as digital data.

[0574] Step 3:

[0575] The server analyzes the user's text and biometric data received from the terminal. First, it uses natural language processing algorithms to understand the user's input text and extract the necessary information. This text data analysis includes tokenization and semantic analysis. For biometric data, image recognition and voice analysis technologies are used to identify the user's emotional state. Based on this analysis, the server outputs emotional labels such as "concentrated" or "stressed."

[0576] Step 4:

[0577] The server generates a personalized learning plan based on identified emotion labels and the user's known profile. This process utilizes a generative AI model to dynamically select the most suitable learning content for the user's needs. The AI ​​model takes emotion labels as input and generates a list of learning tasks and supplementary materials as output.

[0578] Step 5:

[0579] Based on instructions from the server, the device provides learning content tailored to the user. For example, background music corresponding to a specific emotion or focused exercises are displayed on the screen. In this operation, the device executes content delivery commands received from the server.

[0580] Step 6:

[0581] The device monitors the user's learning progress in real time and feeds the collected data back to the server. This progress data includes learning speed and accuracy, which the server uses to optimize its approach based on the user's progress. The server then generates adaptive feedback again and notifies the user through the device.

[0582] Step 7:

[0583] When a user overcomes a specific emotional state, the server triggers a reward system, awarding points or badges as motivation. This reward visualizes the user's efforts and increases their motivation. This result is ultimately output as the reward the user receives.

[0584] (Application Example 2)

[0585] 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."

[0586] Traditional learning systems have struggled to provide personalized learning experiences based on learners' emotional states, making it difficult to promote effective learning progress. Current systems lack the means to provide appropriate learning content according to learners' emotional states, resulting in decreased learning efficiency and motivation.

[0587] 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.

[0588] In this invention, the server includes means for analyzing learner information received by a data processing device and generating an individualized learning plan; means for dynamically generating test questions based on the generated learning plan; means for analyzing the learner's emotional state and dynamically adjusting the learning plan based on the analysis results; means for acquiring emotional data from the learner's expressions and voice and adaptively providing learning content based on said data; and means for monitoring the learner's learning progress and providing real-time feedback. This makes it possible to provide an optimal learning environment and content that is in line with the learner's emotional state.

[0589] A "data processing device" is a device that collects and analyzes learner information and generates individualized learning plans.

[0590] An "individualized learning plan" refers to a plan that includes learning content optimized based on the learner's individual information and emotional state.

[0591] "Means for dynamically generating exam questions" refers to a function that generates and provides exam questions in real time according to the learner's progress and status.

[0592] "Means for analyzing learners' emotional states" refers to technologies for identifying and analyzing learners' emotions based on their facial expressions and voice data.

[0593] "Means of adaptively providing learning content" refers to a function that provides optimized learning content according to the learner's emotional state.

[0594] "Means for monitoring learning progress and providing feedback" refers to a function that continuously monitors the learner's learning progress and provides real-time feedback according to that progress.

[0595] This invention realizes a system that provides a real-time, adaptive learning experience based on the learner's emotions. The server analyzes the learner's information using a data processing device and generates an individualized learning plan. The learner's voice and facial expression data are acquired through the device's microphone and camera. This data is analyzed using emotion analysis software. Specifically, the Microsoft Azure emotion recognition API is used to analyze the learner's voice tone and changes in facial expressions to identify their emotional state.

[0596] The server dynamically adjusts the learning plan based on the analysis results. For example, if the server determines that the learner is stressed, it immediately provides learning content of a lower difficulty level. Furthermore, it adaptively displays the learning content and provides materials and videos in a way that is optimal for the learner's emotions.

[0597] The device incorporates nature imagery and calming music to help users relax through visual and auditory feedback. This allows users to learn more effectively. Learning progress is monitored by the server, and encouraging messages and notifications related to the reward system are displayed as needed.

[0598] As a concrete example, in an application for preparing for certification exams, when a user is feeling fatigued, the system provides a short video to encourage a brief refresh. This allows the user to mentally reset and maintain their motivation to continue learning.

[0599] An example of a prompt to input into a generative AI model is: "Based on the user's emotional data, please suggest learning support content that has a relaxing effect. Specifically, combine the viewing content with visual effects that have a relaxing effect." This prompt serves as a guide for generating content that is optimal for the learner.

[0600] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0601] Step 1:

[0602] The user initiates a learning session through their device. The device uses its microphone and camera to capture the user's voice and facial expression data. This allows for the collection of the user's emotional information in real time. The collected data is then sent to a server.

[0603] Step 2:

[0604] The server uses Microsoft Azure's emotion recognition API to analyze the acquired voice and facial expression data. To determine the emotional state, it analyzes changes in voice tone and facial expression from the input data to identify emotions such as "concentrated" or "stressed." Based on these analysis results, the user's current emotional state is output.

[0605] Step 3:

[0606] The server dynamically generates a personalized learning plan based on the analyzed emotional information. Specifically, if the user is feeling stressed, it selects easier problems and adjusts the learning plan to provide relaxing content. This learning plan is generated as output and sent to the user's device.

[0607] Step 4:

[0608] The device displays learning content provided by the server. Natural imagery and calming music are played in the background to help the user relax visually and aurally. Adaptive virtual effects are employed to alleviate the user's emotions.

[0609] Step 5:

[0610] During learning, the user's learning progress and emotional state are continuously monitored. The device sends progress data to the server, which uses this data to further optimize the learning plan. Appropriate feedback and encouraging messages are provided to the user according to their progress.

[0611] Step 6:

[0612] When a user achieves a specific emotional state or learning outcome, a reward system on the server is activated. This system fairly evaluates the user's efforts and motivates them to continue learning by awarding points or badges.

[0613] 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.

[0614] 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.

[0615] 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.

[0616] [Fourth Embodiment]

[0617] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0618] 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.

[0619] 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).

[0620] 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.

[0621] 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.

[0622] 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).

[0623] 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.

[0624] 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.

[0625] 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.

[0626] 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.

[0627] 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.

[0628] 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.

[0629] 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".

[0630] This invention is a system for improving learning efficiency in qualification examinations. It uses a data processing device to collect and analyze learner information and provides personalized learning plans and practice questions. Specific embodiments are described below.

[0631] Users access the system for learning purposes, entering information about their target certification exam and their learning history. This allows the system to understand their learning needs and areas of weakness.

[0632] The server receives user input and analyzes the information using a specific algorithm. This generates a personalized learning plan optimized for the user's progress and needs. This plan includes specific learning topics, a daily schedule, and recommended supplementary materials.

[0633] The server also utilizes a generative AI model to dynamically generate different test questions for each user. This generation process takes into account past training data and analysis results to ensure the difficulty and content of the questions are best suited to the user.

[0634] As the user progresses through the learning process, the device records their learning progress in real time. Information such as learning time, the number of questions answered, and the correct answer rate are continuously collected.

[0635] Based on this progress information, the server provides timely feedback to the user. For example, it may suggest additional questions for topics with low correct answer rates or provide suggestions for improving learning methods. Such feedback is important for maximizing individual learning effectiveness.

[0636] Furthermore, to maintain and improve user motivation, the device includes a reward system. Points and badges are awarded based on learning progress, which encourages learners.

[0637] As a concrete example, when preparing for a qualification exam such as the "Bookkeeping Examination," the user accesses the system to identify areas they struggle with, such as "Financial Statements" and "Fixed Assets." Based on this, the server generates several related problems and develops a personalized practice plan for the user. During the learning process, the terminal analyzes the user's answers in real time and provides feedback on areas where understanding is insufficient.

[0638] Thus, the system of the present invention optimizes individual learning and provides efficient preparation for qualification examinations.

[0639] The following describes the processing flow.

[0640] Step 1:

[0641] Users access the system and log in with their registered accounts. They enter basic information such as the type of certification exam, exam date, past learning data, weak subjects, and goals. This data is securely stored in the system's database.

[0642] Step 2:

[0643] The server receives information sent by the user and accesses the database to retrieve relevant information. This identifies the user's learning tendencies and areas of difficulty. Specific machine learning algorithms are then used to analyze the user profile in detail.

[0644] Step 3:

[0645] The server analyzes the user's input data and generates a personalized learning plan based on the results. This includes a weekly or monthly learning schedule that focuses on topics the user struggles with. The generated plan is stored in a database and associated with the user's profile.

[0646] Step 4:

[0647] The server utilizes a generative AI model to generate test questions tailored to the learning plan. This process generates many questions that focus on areas where the user particularly needs improvement. Furthermore, the generated questions are regularly updated, ensuring that users always receive fresh content.

[0648] Step 5:

[0649] The device records user input (learning progress and answer status) in real time as the user progresses through the learning process. Data such as the time spent learning, the number of correct answers, and incorrect answers are automatically collected.

[0650] Step 6:

[0651] The server analyzes learning progress data collected in real time and provides users with sequential feedback. This includes strategies for strengthening weak areas and advice to improve learning effectiveness. It also dynamically adjusts the learning plan as needed.

[0652] Step 7:

[0653] The device activates a reward system for users based on their learning progress. This allows users to earn points and digital badges, providing a mechanism to maintain their motivation to learn.

[0654] (Example 1)

[0655] 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".

[0656] Preparing for certification exams presents challenges in creating optimal learning plans tailored to individual learners' needs, dynamically generating exam questions at appropriate difficulty levels, and providing effective real-time feedback while maintaining learner motivation. Therefore, there is a need to develop systems that provide personalized learning processes and improve learning efficiency.

[0657] 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.

[0658] In this invention, the server includes means for analyzing learner information to generate an individualized learning plan, means for dynamically generating test questions using a generation AI model based on prompt information, and means for monitoring learning progress in real time and providing feedback. This enables a learning process optimized for each learner, making efficient and effective preparation for qualification exams possible.

[0659] A "data processing mechanism" is a general term for systems and hardware used to analyze information received from learners.

[0660] An "individualized learning plan" is a learning plan that is customized according to each learner's learning needs and progress.

[0661] "Prompt information" refers to text data that is input to give specific instructions to a generative AI model.

[0662] A "generative AI model" is an artificial intelligence technology used to dynamically generate test questions tailored to the learner.

[0663] "Monitoring learning progress" refers to the process of tracking learners' learning activities in real time, collecting data, and analyzing it.

[0664] "Feedback" refers to information provided to learners regarding the evaluation of their learning outcomes and areas for improvement.

[0665] A "reward system" is a mechanism that awards points or badges based on progress in order to improve learners' motivation to learn.

[0666] This invention is a system for improving learning efficiency, particularly for qualification exam preparation. It analyzes learner information and provides an individualized learning plan and dynamically generated exam questions. Specific embodiments are shown below.

[0667] Users first access the system and input information about the target certification exam and their learning history. This helps identify their learning needs and areas of weakness.

[0668] The server receives and stores the input information using a data processing mechanism. It analyzes the information through a specific algorithm and generates a personalized learning plan optimized for the user. This plan includes learning topics, daily schedules, and recommended materials.

[0669] Furthermore, the server utilizes a generative AI model to dynamically generate test questions using prompts based on past training data and analysis results. For example, it might use a prompt such as, "Create an intermediate-level question about financial statements."

[0670] As the user progresses through the learning process, the device records their learning progress in real time, continuously collecting data such as learning time, the number of questions answered, and the accuracy rate.

[0671] Based on this progress data, the server provides users with timely feedback. This feedback includes additional questions for topics with low correct answer rates and suggestions for improving learning methods.

[0672] Furthermore, the device implements a reward system that awards points and badges to users based on their progress during the learning process. This feature contributes to maintaining and improving learners' motivation.

[0673] As a concrete example, in preparing for an accounting exam, the user inputs their weaknesses in the areas of "financial statements" and "fixed assets," and the server generates related problems based on that input and creates a personalized practice plan for the user. At that time, by inputting a prompt such as "Please create additional practice problems on financial statements," the AI ​​model generates and provides the problems.

[0674] Based on this embodiment of the invention, the system optimizes individual learning and enables efficient and effective preparation for qualification exams.

[0675] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0676] Step 1:

[0677] Users access the system and provide input information such as qualification exam information and their learning history. This information includes the type of exam, learning progress, and areas of strength and weakness. This data is collected as necessary to understand the user's learning needs.

[0678] Step 2:

[0679] The server receives input information from the user through a data processing mechanism and stores it in a database. The stored information is then processed by a data analysis algorithm to analyze each user's learning needs. This analysis extracts the data necessary to generate a specific learning plan.

[0680] Step 3:

[0681] The server generates a personalized learning plan based on the analysis results. This plan generation process considers the user's learning progress and needs derived from the analysis to determine the optimal learning topics and daily schedule. A list of recommended learning materials is also created at this stage. The output provides a customized learning plan tailored to the user.

[0682] Step 4:

[0683] The server utilizes a generative AI model to dynamically generate exam questions based on the user's learning progress using prompts. It uses past learning data and prompts indicating specific instructions as input. For example, based on a prompt such as "Create a financial statement problem at an intermediate level," the server generates a problem best suited to the user. The output is a new exam question provided to the user.

[0684] Step 5:

[0685] The device monitors the user's learning activity in real time and records progress data such as learning time, the number of questions answered, and the correct answer rate. This data is used as input data to understand the user's learning status.

[0686] Step 6:

[0687] The server analyzes the collected progress data and provides timely feedback to the user. This feedback includes suggesting additional questions to address areas where the user's understanding is insufficient, as well as advice on effective learning methods. This feedback serves as output information to improve learning efficiency.

[0688] Step 7:

[0689] The device uses a reward system to maintain and improve the user's learning motivation by awarding points and badges based on their progress. This system aims to increase user motivation and allows for visual confirmation of learning outcomes.

[0690] (Application Example 1)

[0691] 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".

[0692] Individualized learning methods are in demand for qualification exams and various other forms of learning. However, conventional educational content presents a challenge in that all learners study the same content and at the same pace, making it difficult to provide optimal learning tailored to individual needs and progress. Furthermore, there has been a lack of means to promote effective learning while continuously maintaining learner motivation.

[0693] 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.

[0694] In this invention, the server includes means for analyzing educator information entered into a terminal device and generating an individualized educational plan, means for dynamically generating assessment questions based on the generated educational plan, and means for providing reward points or badges according to the educator's progress. This makes it possible to provide optimal learning tailored to each educator's needs and progress, enabling efficient learning while maintaining motivation.

[0695] A "terminal device" is an electronic device used by users to input information or check their learning progress, and includes devices such as smartphones and tablets.

[0696] "Educator information" refers to information that learners provide to the system regarding exams and learning materials, such as personal data, past learning history, and target skills and knowledge.

[0697] An "individualized learning plan" is a plan that outlines specific learning schedules and content optimized for each educator's learning needs and progress.

[0698] "Assessment questions" refer to test questions and practice problems that are dynamically generated by a server to measure the learning progress and understanding of educators.

[0699] "Progress" refers to the degree to which an educator has achieved or mastered the set goals in the process of learning.

[0700] "Reward points and badges" are symbols of achievement or incentives awarded to educators to enhance their motivation to learn and encourage continuous learning.

[0701] A "generative AI model" is an artificial intelligence computational model used to dynamically generate problems and other content tailored to the user's learning progress and needs.

[0702] A "prompt" is an instruction text provided to a generating AI model based on a specific topic or condition, and serves to indicate the conditions and content guidelines for problem generation.

[0703] The system implementing this invention begins with an educator inputting necessary information using a terminal device. The terminal device transmits the information obtained from the educator to a server. The server analyzes the received information from the educator and utilizes data analysis techniques to generate individualized educational plans optimized for each educator. The analysis uses the Python language and data analysis libraries.

[0704] Based on the generated educational plan, the server uses a generative AI model to create prompts and dynamically generate assessment questions. In doing so, the generative AI model adjusts the difficulty and content of the questions according to past learning data and the educator's progress. For example, a prompt such as "Generate questions about basic concepts and applications of financial statements" might be used.

[0705] As educators progress through the learning process, the terminal device monitors their learning progress in real time and transmits the data to a server. This data is used to generate feedback tailored to the educators' learning progress. The feedback is provided as specific suggestions to reinforce areas of insufficient understanding, or as additional practice problems.

[0706] Furthermore, to enhance educators' motivation to learn, the server has a reward system that awards reward points and badges based on the progress of their teaching. This allows educators to visually recognize their learning achievements and maintain their motivation for the next learning step.

[0707] As a result, educators can implement individually optimized learning processes and efficiently enhance knowledge.

[0708] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0709] Step 1:

[0710] The user uses a terminal device to input exam information and learning history. The terminal collects this information and sends it to the server. The input data includes the target exam subject area and past performance.

[0711] Step 2:

[0712] The server uses Python and data analysis libraries to generate personalized learning plans based on the information received from educators. It analyzes the input data to identify the educators' learning needs and areas of difficulty, and generates a corresponding schedule and recommended learning topics. As a result, a personalized learning plan is output.

[0713] Step 3:

[0714] The server uses a generative AI model to dynamically generate assessment questions based on personalized prompts. These prompts include specific themes based on the educator's progress and needs. The generated questions are adjusted to have appropriate difficulty and content for the educator. The output is a educator-specific list of questions.

[0715] Step 4:

[0716] As educators guide students through the learning process, the device monitors their progress in real time. Users answer questions, and the device sends data such as their answers and learning time to the server. The collected data is used to generate feedback for the next step.

[0717] Step 5:

[0718] The server analyzes the collected learning data and evaluates the educators' understanding. Using Python-based data analysis, it identifies topics with particularly low accuracy rates and generates focused feedback. This feedback includes suggestions for additional learning and reinforcing exercises. As output, personalized improvement suggestions are provided to the educators.

[0719] Step 6:

[0720] The server manages reward points and badges based on the educator's learning progress. Points are added according to progress data, and badges are awarded when certain conditions are met. This incentive is designed to improve the educator's motivation. As output, the reward information is reflected on the educator's device.

[0721] 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.

[0722] This invention combines an emotion engine with a learning system to provide a personalized learning experience based on the learner's emotional state. Specific embodiments are shown below.

[0723] When a user begins learning, they access the system and input their qualification exam information and past learning history. The device also uses a microphone and camera to collect the user's voice and facial expression data.

[0724] The server analyzes text and sensor data sent by the user to generate a user profile. Furthermore, the emotion engine analyzes this data to identify the user's current emotional state. For example, it can determine whether the user is "concentrating" or "stressed" based on their voice tone and facial expressions.

[0725] Once the user's emotional state is identified, the server dynamically adjusts the learning plan accordingly. For example, if the user is restless, it prioritizes displaying learning content with a relaxing effect. If the user is stressed, it adjusts the difficulty level of the learning to start with easier questions.

[0726] The server generates personalized learning plans and delivers learning content in a way that is optimal for the user's emotional state. Furthermore, dynamically generated test questions are tailored to the user's emotional state and adjusted to eliminate bias towards areas of weakness.

[0727] As learning progresses, the device records and analyzes the user's learning progress and emotional data in real time. Based on this data, the server continuously optimizes the learning plan and provides feedback. If necessary, it presents encouraging messages and interactive content that respond to the user's emotional state.

[0728] Furthermore, the reward system also works in conjunction with the emotion engine. When a user overcomes a specific emotional state and progresses in their learning, their efforts are recognized, and points or badges are awarded to improve their motivation.

[0729] As a concrete example, when a user experiences stress during a certification exam and studies at home, the system uses sensors to detect the tension in the user's face. Based on this, the server plays relaxing music in the background and presents simple practice problems, employing a strategy to enhance concentration during study.

[0730] Thus, this invention utilizes an emotion engine to realize a learning process that is attuned to the learner's emotions, thereby supporting efficient and effective preparation for qualification exams.

[0731] The following describes the processing flow.

[0732] Step 1:

[0733] The user logs into the learning system and enters information about the certification exam they are studying for, past learning data, and areas of difficulty. Once data entry is complete, the device automatically starts the data collection process.

[0734] Step 2:

[0735] The device collects user voice and facial expression data via microphones and cameras. This data is sent in real time to an emotion analysis engine, where it is analyzed to identify the user's emotional state.

[0736] Step 3:

[0737] The server analyzes the received user information and emotional data to determine the user's current emotional state. For example, it can set states such as "concentration," "stress," and "fatigue," and identify which state the user is in.

[0738] Step 4:

[0739] The server dynamically adjusts the learning plan based on the user's emotional state. It generates a personalized learning strategy, such as including relaxing content when stressed and providing more challenging problems when focused.

[0740] Step 5:

[0741] The server utilizes generative AI to dynamically generate test questions based on a tailored learning plan. This process takes into account emotional states and past learning history to create the optimal set of questions.

[0742] Step 6:

[0743] The device displays the user the adjusted learning content and questions. The user progresses through the presented learning material and deepens their learning by entering their answers into the device.

[0744] Step 7:

[0745] The device records the user's learning progress and updated sentiment data in real time. Learning results and sentiment changes are continuously transmitted to the server.

[0746] Step 8:

[0747] The server provides feedback to users based on the collected data. It sends encouraging messages as needed, refines the learning pace and strategy, and aims to maximize effectiveness.

[0748] Step 9:

[0749] The device rewards the user based on their learning progress. For example, if a positive change in emotional state is observed, points or other rewards may be awarded to support motivation maintenance.

[0750] (Example 2)

[0751] 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".

[0752] Traditional learning systems provide uniform learning plans and feedback without considering the user's emotional state, resulting in decreased learning efficiency and difficulty in maintaining user motivation. Furthermore, they are unable to provide personalized learning experiences because they cannot generate dynamic learning content based on user emotions or provide effective real-time feedback.

[0753] 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.

[0754] In this invention, the server includes means for analyzing user information and biometric data received by a data collection device to identify the user's emotional state; means for dynamically generating and adjusting an individualized learning plan based on the identified emotional state; and means for dynamically generating test questions according to the user's emotional state based on the generated learning plan. This makes it possible to provide an optimal learning plan tailored to each user's emotional state, thereby improving learning efficiency and motivation.

[0755] "Data acquisition equipment" is a general term for hardware and software used to acquire user information and biometric data.

[0756] "Emotional state" refers to the psychological and emotional state identified by analyzing the user's biometric data and input information obtained from data collection devices.

[0757] A "personalized learning plan" refers to a learning progress plan that is dynamically generated and adjusted based on the user's identified emotional state and learning needs.

[0758] "Dynamically generating" refers to the process of instantly generating adaptive content and issues in response to real-time user data and changing conditions.

[0759] "Feedback" refers to responses that include information and advice provided in real time, based on the user's learning progress and emotional state.

[0760] A "reward system" refers to a mechanism that provides rewards in accordance with the user's learning progress and improvement in their emotional state in order to motivate them.

[0761] This invention is a system that provides an individualized learning experience based on the user's emotional state. Specific embodiments of this system are described below.

[0762] First, the user accesses the system and inputs their learning objectives, past learning history, and current learning needs. The terminal collects the user's voice and facial expression data using a high-resolution camera and noise-canceling microphone, and transmits this biometric data to the server.

[0763] The server analyzes user information and biometric data received from data collection devices. Specifically, the server uses natural language processing and image recognition algorithms to extract voice and facial features, and an emotion engine to identify the user's real-time emotional state. For example, the server determines emotion labels such as "concentrated" or "stressed."

[0764] Next, the server dynamically generates and adjusts an individualized learning plan based on the identified emotional state. In this process, the server uses a generative AI model to select learning content suitable for the user and adjusts the difficulty level of the learning tasks accordingly. For example, for a user experiencing anxiety, it might start by presenting easy problems.

[0765] The device monitors the user's learning progress in real time, and the server provides feedback based on that information. This feedback includes encouraging messages tailored to the user's emotions and interactive learning content. When the user overcomes a specific emotional state, the server activates a reward system, boosting motivation by awarding points and badges.

[0766] For example, when a user experiencing stress related to a certification exam uses the system, the device's sensors detect tension in the user's face. Based on this information, the server plays relaxing music in the background and presents simple practice questions. In this way, the system helps the user concentrate and improves their learning experience.

[0767] An example of a prompt is, "Suggest learning support content to reduce user stress." Based on this prompt, the server utilizes a generative AI model to construct an appropriate learning plan.

[0768] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0769] Step 1:

[0770] Users input their learning objectives and past learning history through the terminal. Based on this input, the terminal forms the user's basic profile and sends it to the server. The input data provided by the user includes specific exam categories and priorities in a text form. Formatted data packets are sent to the server as output from the terminal.

[0771] Step 2:

[0772] The device uses a camera and microphone to collect user voice and facial expression data. The collected input data includes the intonation of the user's voice and changes in facial expressions. The device records this in real time using sensors and transfers the obtained biometric data to a server. The device then processes the sensing data and outputs it as digital data.

[0773] Step 3:

[0774] The server analyzes the user's text and biometric data received from the terminal. First, it uses natural language processing algorithms to understand the user's input text and extract the necessary information. This text data analysis includes tokenization and semantic analysis. For biometric data, image recognition and voice analysis technologies are used to identify the user's emotional state. Based on this analysis, the server outputs emotional labels such as "concentrated" or "stressed."

[0775] Step 4:

[0776] The server generates a personalized learning plan based on identified emotion labels and the user's known profile. This process utilizes a generative AI model to dynamically select the most suitable learning content for the user's needs. The AI ​​model takes emotion labels as input and generates a list of learning tasks and supplementary materials as output.

[0777] Step 5:

[0778] Based on instructions from the server, the device provides learning content tailored to the user. For example, background music corresponding to a specific emotion or focused exercises are displayed on the screen. In this operation, the device executes content delivery commands received from the server.

[0779] Step 6:

[0780] The device monitors the user's learning progress in real time and feeds the collected data back to the server. This progress data includes learning speed and accuracy, which the server uses to optimize its approach based on the user's progress. The server then generates adaptive feedback again and notifies the user through the device.

[0781] Step 7:

[0782] When a user overcomes a specific emotional state, the server triggers a reward system, awarding points or badges as motivation. This reward visualizes the user's efforts and increases their motivation. This result is ultimately output as the reward the user receives.

[0783] (Application Example 2)

[0784] 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".

[0785] Traditional learning systems have struggled to provide personalized learning experiences based on learners' emotional states, making it difficult to promote effective learning progress. Current systems lack the means to provide appropriate learning content according to learners' emotional states, resulting in decreased learning efficiency and motivation.

[0786] 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.

[0787] In this invention, the server includes means for analyzing learner information received by a data processing device and generating an individualized learning plan; means for dynamically generating test questions based on the generated learning plan; means for analyzing the learner's emotional state and dynamically adjusting the learning plan based on the analysis results; means for acquiring emotional data from the learner's expressions and voice and adaptively providing learning content based on said data; and means for monitoring the learner's learning progress and providing real-time feedback. This makes it possible to provide an optimal learning environment and content that is in line with the learner's emotional state.

[0788] A "data processing device" is a device that collects and analyzes learner information and generates individualized learning plans.

[0789] An "individualized learning plan" refers to a plan that includes learning content optimized based on the learner's individual information and emotional state.

[0790] "Means for dynamically generating exam questions" refers to a function that generates and provides exam questions in real time according to the learner's progress and status.

[0791] "Means for analyzing learners' emotional states" refers to technologies for identifying and analyzing learners' emotions based on their facial expressions and voice data.

[0792] "Means of adaptively providing learning content" refers to a function that provides optimized learning content according to the learner's emotional state.

[0793] "Means for monitoring learning progress and providing feedback" refers to a function that continuously monitors the learner's learning progress and provides real-time feedback according to that progress.

[0794] This invention realizes a system that provides a real-time, adaptive learning experience based on the learner's emotions. The server analyzes the learner's information using a data processing device and generates an individualized learning plan. The learner's voice and facial expression data are acquired through the device's microphone and camera. This data is analyzed using emotion analysis software. Specifically, the Microsoft Azure emotion recognition API is used to analyze the learner's voice tone and changes in facial expressions to identify their emotional state.

[0795] The server dynamically adjusts the learning plan based on the analysis results. For example, if the server determines that the learner is stressed, it immediately provides learning content of a lower difficulty level. Furthermore, it adaptively displays the learning content and provides materials and videos in a way that is optimal for the learner's emotions.

[0796] The device incorporates nature imagery and calming music to help users relax through visual and auditory feedback. This allows users to learn more effectively. Learning progress is monitored by the server, and encouraging messages and notifications related to the reward system are displayed as needed.

[0797] As a concrete example, in an application for preparing for certification exams, when a user is feeling fatigued, the system provides a short video to encourage a brief refresh. This allows the user to mentally reset and maintain their motivation to continue learning.

[0798] An example of a prompt to input into a generative AI model is: "Based on the user's emotional data, please suggest learning support content that has a relaxing effect. Specifically, combine the viewing content with visual effects that have a relaxing effect." This prompt serves as a guide for generating content that is optimal for the learner.

[0799] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0800] Step 1:

[0801] The user initiates a learning session through their device. The device uses its microphone and camera to capture the user's voice and facial expression data. This allows for the collection of the user's emotional information in real time. The collected data is then sent to a server.

[0802] Step 2:

[0803] The server uses Microsoft Azure's emotion recognition API to analyze the acquired voice and facial expression data. To determine the emotional state, it analyzes changes in voice tone and facial expression from the input data to identify emotions such as "concentrated" or "stressed." Based on these analysis results, the user's current emotional state is output.

[0804] Step 3:

[0805] The server dynamically generates a personalized learning plan based on the analyzed emotional information. Specifically, if the user is feeling stressed, it selects easier problems and adjusts the learning plan to provide relaxing content. This learning plan is generated as output and sent to the user's device.

[0806] Step 4:

[0807] The device displays learning content provided by the server. Natural imagery and calming music are played in the background to help the user relax visually and aurally. Adaptive virtual effects are employed to alleviate the user's emotions.

[0808] Step 5:

[0809] During learning, the user's learning progress and emotional state are continuously monitored. The device sends progress data to the server, which uses this data to further optimize the learning plan. Appropriate feedback and encouraging messages are provided to the user according to their progress.

[0810] Step 6:

[0811] When a user achieves a specific emotional state or learning outcome, a reward system on the server is activated. This system fairly evaluates the user's efforts and motivates them to continue learning by awarding points or badges.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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."

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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 as being incorporated by reference.

[0833] The following is further disclosed regarding the embodiments described above.

[0834] (Claim 1)

[0835] A means for analyzing learner information received by a data processing device and generating an individualized learning plan,

[0836] A means for dynamically generating test questions based on the generated learning plan,

[0837] A means of monitoring learners' learning progress and providing real-time feedback,

[0838] A system that includes this.

[0839] (Claim 2)

[0840] The system according to claim 1, further comprising means for adjusting the difficulty level of the generated problems according to the learner's progress.

[0841] (Claim 3)

[0842] The system according to claim 1, comprising a reward system for maintaining motivation for learners.

[0843] "Example 1"

[0844] (Claim 1)

[0845] A means for analyzing learner information received by a data processing mechanism and generating an individualized educational plan,

[0846] A means of dynamically generating test questions using a generative AI model based on prompt information,

[0847] A means of monitoring learners' progress and providing real-time feedback,

[0848] A means of showing learners the most suitable educational topics based on learning data,

[0849] A means of improving learners' motivation to learn by providing rewards according to their learning progress,

[0850] A system that includes this.

[0851] (Claim 2)

[0852] The system according to claim 1, further comprising means for adjusting the difficulty level of the generated problems according to the learner's progress.

[0853] (Claim 3)

[0854] The system according to claim 1, which provides a reward system for learners and maintains learner motivation.

[0855] "Application Example 1"

[0856] (Claim 1)

[0857] A means for analyzing educator information entered into a terminal device and generating an individualized educational plan,

[0858] A means for dynamically generating assessment questions based on the generated educational plan,

[0859] A means of monitoring educators' learning progress and providing real-time feedback,

[0860] A means of providing reward points or badges according to the progress of educators,

[0861] A system that includes this.

[0862] (Claim 2)

[0863] The system according to claim 1, further comprising means for adjusting the difficulty level of the generated problems according to the educator's progress.

[0864] (Claim 3)

[0865] The system according to claim 1, comprising means for generating a question on a specified topic using prompt statements based on a generative AI model.

[0866] "Example 2 of combining an emotion engine"

[0867] (Claim 1)

[0868] A means for analyzing user information and biometric data received by a data collection device to identify emotional states,

[0869] Means for dynamically generating and adjusting individualized learning plans based on identified emotional states,

[0870] A means for dynamically generating test questions based on the generated learning plan, according to the user's emotional state,

[0871] A means of monitoring users' learning progress and providing real-time feedback and sentiment-based interactive content,

[0872] A system that includes this.

[0873] (Claim 2)

[0874] The system according to claim 1, further comprising means for adjusting the difficulty level of the generated problems according to the user's emotional state and progress.

[0875] (Claim 3)

[0876] The system according to claim 1, comprising a reward system that provides a motivating reward when the user overcomes their emotional state.

[0877] "Application example 2 when combining with an emotional engine"

[0878] (Claim 1)

[0879] A means for analyzing learner information received by a data processing device and generating an individualized learning plan,

[0880] A means for dynamically generating test questions based on the generated learning plan,

[0881] A means for analyzing learners' emotional states and dynamically adjusting the learning plan based on the analysis results,

[0882] A means for acquiring emotional data from learners' expressions and voices, and adaptively providing learning content based on said data,

[0883] A means of monitoring learners' learning progress and providing real-time feedback,

[0884] A system that includes this.

[0885] (Claim 2)

[0886] The system according to claim 1, further comprising means for adjusting the difficulty level of the generated problems according to the learner's progress.

[0887] (Claim 3)

[0888] The system according to claim 1, comprising a reward system for maintaining motivation for learners. [Explanation of Symbols]

[0889] 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 for analyzing learner information received by a data processing device and generating an individualized learning plan, A means for dynamically generating test questions based on the generated learning plan, A means of monitoring learners' learning progress and providing real-time feedback, A system that includes this.

2. The system according to claim 1, further comprising means for adjusting the difficulty level of the generated problems according to the learner's progress.

3. The system according to claim 1, comprising a reward system for maintaining motivation for learners.

Images