system

Abstract

We provide the system. [Solution] A means of individually evaluating people's abilities using generative models, Means for generating personalized self-development programs based on said ability, Means for providing progress information for the program, A means for accumulating and analyzing growth data obtained based on the progress information, A means of providing leaders with insights from the growth data, 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, the method 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 in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern educational settings, there is a problem that it is difficult to cultivate diverse talents with a teaching method that is biased towards abilities evaluated by conventional numerical values. In particular, while the improvement of non-cognitive abilities is emphasized, there is a lack of specific methodologies for their cultivation. There is also a problem that the burden on teachers increases and it is difficult to efficiently provide education tailored to individual students.

Means for Solving the Problems

[0005] This invention efficiently generates personalized learning content by utilizing a generative model to analyze the characteristics of the subject in detail. This system provides tasks suitable for the subject and accumulates and analyzes developmental data based on the feedback obtained during the process. Furthermore, by providing educators with insights obtained from the accumulated data, it becomes possible to reduce the burden on teachers while supporting the effective development of non-cognitive abilities.

[0006] A "generative model" is an algorithm or network that creates new data or content based on input data.

[0007] "Traits" refer to the intrinsic attributes of individual subjects, such as their learning style, behavioral patterns, and personality traits.

[0008] "Learning content" refers to educational activities and tasks provided to subjects based on a specific purpose.

[0009] "Feedback" refers to the evaluation and advice given to a subject regarding their performance on a given task.

[0010] "Developmental data" refers to a collection of information that is gathered and stored to demonstrate the growth and improvement of a subject's abilities.

[0011] An "educator" is a teacher or instructor who is in a position to provide education and training to students.

[0012] "Insight" refers to the understanding and insights gained from accumulated data, which are useful for decision-making and guidance. [Brief explanation of the drawing]

[0013] [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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. <000...See full answer below: [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [[ID=二十一]] [[ID=二十二]] [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Embodiments for Carrying Out the Invention

[0014] 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.

[0015] First, the language used in the following description will be explained. [[ID=四十八]] [[ID=四十九]]

[0016] [[ID=五十]] In the following embodiments, the 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.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the 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.

[0019] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention is a system that provides an individualized education system using a generative model. This system consists of a server, terminals, and users, each with a specific role.

[0035] First, the server centrally stores various data about the subjects. This includes the subjects' daily learning records, feedback from teachers, and the results of questionnaires aimed at behavioral analysis. Based on this data, a generative model is used to analyze the characteristics of each subject.

[0036] Next, the device functions as a user interface, providing participants with personalized learning content. It displays tasks and activities that participants should work on and allows them to receive real-time feedback. For example, if analysis indicates that a participant needs to improve their communication skills, tasks such as conversational games or role-playing scenarios are presented through the device.

[0037] Through this system, users are expected to proactively address the tasks presented to them. For example, users can participate in group discussions suggested on their devices, record the insights gained and their own actions on the device, and receive further feedback.

[0038] Finally, the server collects feedback from participants after they complete the tasks and stores it in a database as developmental data. This data serves as material for further analysis and is used by teachers to gain detailed insights into the participants. For example, it may be recorded that a user has improved their cooperation skills through multiple tasks, which can later be used by teachers to determine teaching strategies.

[0039] Thus, the present invention utilizes generative AI to effectively cultivate non-cognitive abilities tailored to the characteristics of the subject.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server continuously collects and stores student basic data, learning history, evaluation comments, and other information in a database. This includes retrieving data through the school's electronic grade management system and online survey platforms.

[0043] Step 2:

[0044] The server uses the collected data to feed into a generative model, which analyzes the characteristics of each student. This model learns from past data and automatically generates student behavioral characteristics and ability profiles.

[0045] Step 3:

[0046] The device presents students with personalized learning programs created by a generating AI based on characteristic analysis results received from the server. Before the first class of the day, the device displays a list of assignments suitable for each student.

[0047] Step 4:

[0048] Users (students) work on the assigned tasks. They select tasks via their devices and complete them according to the instructions. Task progress is recorded in real time.

[0049] Step 5:

[0050] The device provides users with AI-generated feedback immediately after they complete a task. For example, it displays text-based evaluations of communication quality and suggestions for improvement.

[0051] Step 6:

[0052] The server receives feedback information and task results from the terminals and stores them in a database as developmental data.

[0053] Step 7:

[0054] The server analyzes the accumulated data and periodically provides teachers with reports on student development and insights. These reports can be viewed on the teacher's dashboard.

[0055] (Example 1)

[0056] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0057] In today's learning environment, providing educational content optimized for individual learners is crucial, but traditional education systems have struggled to adequately consider individual learner characteristics. Therefore, there is a need for a system that effectively delivers education tailored to individual learning needs.

[0058] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0059] In this invention, the server includes means for analyzing the characteristics of individual learners using a generative model, means for generating personalized learning content based on said characteristics, and means for providing and recording feedback on said learning content. This makes it possible to provide educational content optimized for each individual learner and to continuously provide feedback on the results.

[0060] A "generative model" is a type of machine learning algorithm that can analyze data and generate new data or results.

[0061] A "learner" is an individual who aims to improve their knowledge and skills through a specific educational program or activity.

[0062] "Characteristics" refers to the unique characteristics of each learner, such as their individual personality, abilities, and learning style.

[0063] "Learning content" refers to educational materials and activities designed to convey the knowledge and skills that learners should acquire through education.

[0064] "Feedback" refers to comments and evaluations given about the learning outcomes and process, and is important for promoting learner growth.

[0065] "Growth data" refers to information about the progress and results obtained through learners' educational activities.

[0066] "Education professionals" refers to experts who are involved in the learning process of learners and who play a role in confirming and guiding their outcomes.

[0067] "Insight" refers to valuable understanding and knowledge gained by analyzing collected data, which is useful for improving educational strategies.

[0068] This system consists of three main components: servers, terminals, and users.

[0069] The server functions as a database, collecting and storing a wide range of data about learners. This data includes learning history, past performance, teacher comments, and survey results. The server analyzes this data using generative AI models, such as language models, to derive individual learner characteristics. Advanced technologies such as GPT-4® are used for these generative AI models. An example of a prompt is, "Suggest the next learning step appropriate for this learner."

[0070] The device serves as a user interface, displaying personalized learning content provided by the server to the learner. The device also has the functionality to display learning tasks required by the learner and provide timely feedback. The software running on the device typically operates on the Android® or iOS platform. If the device analyzes that the learner needs to improve their communication skills, it will display interactive simulations or game-based tasks.

[0071] Users, or learners, use the system to work on the tasks presented to them. Learners record what they have learned and the results they have obtained on their devices and receive feedback. For example, users can gain further insights by participating in discussion activities on their devices and recording the content of those discussions.

[0072] Therefore, this system can provide learners with an individualized educational experience and support their growth.

[0073] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0074] Step 1:

[0075] The server collects learner data and stores it in a database. It receives learner learning history, past achievements, behavioral data, and survey results as input. This data is processed and organized into useful information. As output, the organized dataset is stored in the database. The server automatically imports new data daily to maintain data consistency.

[0076] Step 2:

[0077] The server applies a generative AI model based on the collected data to analyze the learner's characteristics. The previously accumulated dataset is used as input. The generative AI model is given the prompt, "Analyze this learner's strengths and weaknesses." The generative AI model processes the data and outputs the analysis results about the learner's characteristics. This output is used to generate personalized content.

[0078] Step 3:

[0079] The server generates personalized learning content based on the analysis results of the generated AI model. The input includes analyzed learner characteristic data. The server uses this data to select appropriate learning materials and activities, and generates learning content to send to the device as output. Specifically, the server places tasks based on learning objectives and sends real-time notifications to the device.

[0080] Step 4:

[0081] The terminal provides the learner with the personalized learning content it receives. The learning content sent from the server is used as input. The terminal displays this content on its interface, clearly indicating the tasks the learner needs to complete. The output provides a concrete interface that allows the learner to perform the tasks. The terminal displays progress in real time and provides hints and reminders as needed.

[0082] Step 5:

[0083] Users work on tasks presented through their devices. Input is the instruction and tasks received from the device. Learners perform activities based on this, inputting results and progress into the device along the way. Output is the generation of learner feedback and data on completed tasks. Specifically, users participate in interactive content and record comments and evaluations at the end of each session.

[0084] Step 6:

[0085] The server receives feedback data sent by users through their devices and stores it in a database. Inputs include learner feedback and activity completion data. The server analyzes this data and generates developmental data to track learner progress. The output is organized insight data, which is used by educators. Teachers use this data to adjust their teaching strategies.

[0086] (Application Example 1)

[0087] 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."

[0088] Traditional caregiving education systems provided uniform educational content, lacking a learning system tailored to the individual abilities and experience of care staff, resulting in inconsistent learning outcomes. Furthermore, there were insufficient objective means of evaluating growth and progress, hindering effective feedback for further skill development. These challenges raise concerns that the quality of care in caregiving settings may not be sufficiently improved.

[0089] 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.

[0090] In this invention, the server includes means for individually evaluating a person's abilities using a generative model, means for generating an individualized self-development program based on said abilities, and means for providing progress information for said program. This makes it possible to provide optimal educational content tailored to the abilities of each care staff member, and to improve the quality of care by providing feedback that corresponds to individual growth.

[0091] A "generative model" is a mathematical method for generating information tailored to a specific purpose based on data.

[0092] "Evaluating individual capabilities" is a process of analyzing and appropriately assessing the skills and knowledge levels of each person in detail.

[0093] A "self-development program" is a plan of learning and activities aimed at personal growth and skill improvement.

[0094] "Progress information" refers to data that shows the progress and results of learning or activities.

[0095] "Growth data" refers to information that shows how an individual has improved their abilities and skills from the past to the present.

[0096] "Providing insights to instructors from the growth data" means providing suggestions to instructors based on the obtained growth data to help them decide on their teaching methods and policies.

[0097] "Social adaptability" refers to the skills and attitudes necessary for an individual to interact effectively with others in a social environment.

[0098] In a system that implements this application example, a crucial process is the provision of individualized training programs for staff in care settings.

[0099] The server utilizes generative AI models to collect past work data and behavioral patterns of each care staff member and individually evaluates their abilities. Based on this evaluation, it is responsible for generating self-development programs optimized for each staff member. This server uses a standard computer server and software that drives generative AI models, such as the OpenAI® API, to collect and analyze data.

[0100] The generated program is provided to care staff via a smartphone. The device allows users to work on the assigned tasks, and progress information is displayed in real time. This allows users to immediately grasp their own progress and clearly identify areas where further effort is needed.

[0101] Furthermore, the system incorporates features to provide instructors with insights based on growth data. This growth data is stored on a server and can be accessed by instructors as needed to help them determine specific teaching strategies and improve educational content.

[0102] For example, if a staff member needs to acquire more advanced dementia care skills, the server will suggest an optimal training plan using a prompt such as, "Generate a learning program on dementia care for beginners, focusing on communication techniques." This allows care staff to receive learning opportunities tailored to their individual needs, and is expected to improve their practical skills in the field.

[0103] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0104] Step 1:

[0105] The server accesses a database of care staff to collect past work data and behavioral patterns. This information is used as input to organize and analyze data necessary for individual competency assessments. The output is a competency profile for each staff member.

[0106] Step 2:

[0107] The server driving the generative AI model takes the ability profile obtained in step 1 as input and generates a personalized self-development program. At this time, it selects the optimal learning content using prompt statements and generates a customized learning program as output.

[0108] Step 3:

[0109] The terminal receives a customized learning program provided by the server. Based on this program, it displays specific learning content and tasks to the care staff. When the user engages in learning activities based on this, the terminal obtains the learning program as input and data on the user's implementation status as output.

[0110] Step 4:

[0111] Users work on assignments according to a learning program on their devices and record their progress. The learning progress on the device is fed back as input, and progress information and growth data are sent to the server as output.

[0112] Step 5:

[0113] The server processes progress and growth data submitted by users and updates the stored database. This data is used as material to provide insights for mentors. As a result of the analysis, the output includes each staff member's level of growth and guidance for necessary follow-up.

[0114] 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.

[0115] This invention is an educational support system that integrates a generative model and an emotion engine, providing personalized education based on the characteristics and emotional state of each individual subject. The system consists of a server, terminals, and users, each playing a specific role.

[0116] First, the server collects basic data, learning history, and past behavioral data about the subject, and analyzes the subject's characteristics using a generative model. Furthermore, the server analyzes the subject's emotional data, which is acquired in real time, using an emotion engine. This emotional data is obtained by analyzing the subject's facial expressions and tone of voice using the device's camera and microphone.

[0117] Next, the device provides personalized learning content based on the acquired characteristic analysis results and emotional data. This process dynamically adjusts the content according to the user's emotional state, creating an optimal learning environment. For example, if the emotional engine determines that the user is feeling stressed, the device will suggest tasks that promote relaxation or activities that change focus.

[0118] The user works on a task presented via the device. While the user is working on the task, the emotion engine continuously monitors the user's emotional state. During or after the task, the user can receive immediate feedback, and the device provides feedback while taking into account the user's emotional changes.

[0119] Finally, the server stores feedback information and emotional data received from the terminal. This data is stored in a database as the subject's developmental data and is included in detailed reports that teachers can access through a dashboard. This allows teachers to gain insights into the subject's emotional health and responses, along with their learning performance, providing valuable information for adjusting teaching strategies.

[0120] Thus, the present invention combines generative AI and emotion recognition technology to achieve effective development of non-cognitive abilities tailored to the characteristics and emotions of the subject.

[0121] The following describes the processing flow.

[0122] Step 1:

[0123] The server collects basic student data, past learning history, and behavioral data, and stores it in a database. Then, it uses a generative model to analyze students' learning styles and characteristics. Based on this analysis, it generates a characteristic profile for each student.

[0124] Step 2:

[0125] The device uses its built-in camera and microphone to collect emotional data in real time from students' facial expressions and tone of voice. An emotion engine analyzes this data to identify the student's current emotional state.

[0126] Step 3:

[0127] The server combines trait profiles generated by generative models with emotional states generated by an emotion engine to create personalized learning plans. These learning plans include tasks and activities tailored to the student's traits and emotional state, and are sent to the device.

[0128] Step 4:

[0129] The device presents students with personalized learning tasks. Based on feedback from the emotion engine, it adjusts the difficulty and content of the tasks as needed to support learning.

[0130] Step 5:

[0131] The user (student) works on the assigned task. During the task, the device continuously monitors the student's emotional state and adjusts the learning content as needed.

[0132] Step 6:

[0133] The device evaluates the student's emotional state and task performance after task completion and provides immediate feedback. This feedback takes into account both the student's emotional response and task performance.

[0134] Step 7:

[0135] The server stores feedback information and emotional data sent from the terminal in a database. This data is saved as documentation showing the subject's developmental progress and is later converted into a report accessible to the teacher. Based on this report, the teacher can develop an instructional plan that addresses the student's learning and emotional changes.

[0136] (Example 2)

[0137] 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".

[0138] In today's educational environment, providing individualized learning methods is difficult because it is not tailored to the characteristics and emotional state of each student. Furthermore, there are challenges such as delays in appropriately adjusting learning content and providing feedback, making it difficult for educators to gain a detailed understanding of each student's developmental progress.

[0139] 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.

[0140] In this invention, the server includes means for analyzing the characteristics of a subject using a generative model, means for acquiring and analyzing the subject's emotional state in real time using an emotion analysis engine, and means for dynamically generating and providing personalized learning content based on the analysis results. This makes it possible to provide a learning environment optimized for the subject, thereby further enhancing educational effectiveness.

[0141] A "generative model" is an artificial intelligence technology that generates specific outputs based on input data, and is used to analyze the characteristics and behavioral patterns of subjects.

[0142] The "emotion analysis engine" is a technology that analyzes the emotional state of a subject from their facial expressions, tone of voice, etc., and plays a role in evaluating their psychological state in real time and reflecting that in the learning content.

[0143] "Subject characteristics" refer to data that shows each learner's learning style and cognitive patterns, and serve as fundamental information for individualized learning.

[0144] "Individualized learning content" refers to educational tasks and materials that are dynamically adjusted based on the characteristics and emotional state of the subject, providing an optimal learning experience.

[0145] "Feedback" refers to information collected from subjects regarding their responses and results to tasks they have undertaken, and used to make improvements and adjustments.

[0146] "Developmental data" refers to data that shows changes in a subject's learning and emotions, and is used for formulating and measuring the effectiveness of ongoing educational plans.

[0147] This invention, as an educational support system, consists of a server, a terminal, and a user. The server collects basic data, learning history, and past behavioral data of the subject, and uses a generative AI model to analyze the subject's characteristics based on this data. Specifically, it uses a database management system to collect and manage data, and the generative AI model functions as an inference engine.

[0148] Subsequently, the server analyzes real-time emotional data acquired from the device's camera and microphone through an emotion analysis engine. By using facial recognition software and voice tone analysis algorithms, it is possible to evaluate the user's stress level and concentration level.

[0149] Based on these analysis results, the device dynamically generates and presents personalized learning content to the user. For example, if a user experiences stress while solving a math problem, the device can offer simple games or practice problems to help them relax.

[0150] Users engage in personalized tasks via their devices, and throughout this process, an emotion analysis engine continuously collects and sends emotional data to the server. This provides immediate feedback and optimizes the user's learning process. For example, encouraging comments are displayed on the device based on the user's reading pace and level of understanding.

[0151] The server uses feedback information from the terminal and accumulated emotional data to store the subject's developmental data in a database. This allows teachers to understand the subject's learning progress and emotional changes through detailed reports and adjust the instruction plan as needed.

[0152] As a concrete example, the server could input the prompt "Please create a math problem for elementary school students. Include suggestions for relaxation activities to provide if the student is feeling stressed." into a generating AI model to create a task optimized for the subject. This process further enhances the system's dynamic adaptive capabilities.

[0153] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0154] Step 1:

[0155] The server collects basic data, learning history, and past behavioral data about the subjects. It receives data sets from the learning management system as input and stores them in a centralized database. Data processing mainly involves integration and imputation of missing values, resulting in a formatted dataset as output.

[0156] Step 2:

[0157] The server runs a generative AI model using a formatted dataset to analyze the characteristics of the subjects. It uses the subjects' historical data as input and prompts the generative model to perform characteristic analysis. During this process, the subjects' learning styles and cognitive characteristics are identified, and the analysis results are output.

[0158] Step 3:

[0159] The server receives data collected in real time from the terminal's camera and microphone, and analyzes the subject's emotions using an emotion analysis engine. Audio and video data are used as input, and the emotional state is calculated based on voice tone and facial expressions. The analysis results are output as data indicating the subject's current emotional state.

[0160] Step 4:

[0161] The device receives analyzed characteristic data and emotional state data from the server and generates personalized learning content. Using the analyzed and emotional data from the server as input, it dynamically creates appropriately customized tasks and learning materials based on the generated AI model. The generated learning content is then output to the user.

[0162] Step 5:

[0163] The user works on personalized learning tasks presented by the device. Learning content is provided from the device as input, and the user responds to it. The user's actions are sent to the server as feedback, and learning progress and task completion status are output.

[0164] Step 6:

[0165] The server stores feedback information and continuously collected emotional data in a database. It uses feedback and emotional data from the terminals as input, and performs analysis and storage processing. Finally, it outputs reports on the subjects' developmental data and emotional changes in a format accessible to teachers.

[0166] (Application Example 2)

[0167] 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".

[0168] In recent years, the importance of individualized education tailored to the unique personalities and emotions of each learner has been increasingly recognized in educational settings. However, existing educational systems have had limitations in responding to learners' real-time emotional states and characteristics. Furthermore, there are challenges in providing optimal learning environments due to insufficient feedback based on learning progress and inadequate efforts to boost motivation.

[0169] 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.

[0170] In this invention, the server includes means for analyzing the characteristics of individual subjects using a generative model, means for generating and dynamically adjusting personalized learning content based on emotional states obtained in real time, and means for recognizing the emotional states of subjects using a speech recognition device and an image acquisition device. This enables the provision of immediate feedback that reflects the learner's emotional state, thereby realizing an optimized learning environment.

[0171] A "generative model" is an information processing technique used to analyze the characteristics of subjects, and is a model used to analyze patterns and trends in data.

[0172] "Individualized learning content" refers to learning content designed to provide each learner with the most suitable learning tasks and materials, taking into account the characteristics of the subject and their real-time emotional state.

[0173] A "dynamic adjustment mechanism" is a function that can change the learning content provided according to the subject's emotional state and learning progress.

[0174] A "speech recognition device" is a hardware and software technology that analyzes a subject's voice and detects its content and emotional state.

[0175] An "image acquisition device" refers to a camera and related technologies used to acquire and analyze a subject's facial expressions and other visual data.

[0176] "Means for recognizing emotional states" refers to technologies that have the function of detecting emotions from a subject's facial expressions and voice and analyzing them in real time.

[0177] "Providing immediate feedback" is a feature that allows participants to receive real-time feedback on their progress and areas for improvement as they learn.

[0178] An "optimized learning environment" is an environment designed based on the characteristics and emotional state of the subject, which promotes effective and efficient learning for the learner.

[0179] This invention is a system that supports individualized education based on the characteristics and emotional state of the subject. Details are described below.

[0180] The server has the capability to analyze the characteristics of the subject using generative models and emotion engine software. Based on basic data, learning history, and behavioral data obtained from the subject, the server extracts the learner's characteristics through a generative AI model. Emotional data is acquired in real time using the device's camera and microphone, through analysis of facial expressions and voice tone. This allows for a comprehensive examination of factors that influence the subject's learning progress.

[0181] The device is equipped with a function that dynamically adjusts the user's learning content. Based on analyzed characteristics and emotional data, the device presents personalized learning materials. For example, if the user is feeling stressed, it will suggest activities that promote relaxation. This creates an optimal learning environment for the learner.

[0182] Users are continuously monitored by an emotion engine as they work on assigned tasks and activities. Immediate feedback is provided during or after tasks, and all of the user's emotional data is stored on the server. This allows the user's developmental data to be stored in a database, providing teachers with detailed reports through a dashboard and information to adjust teaching strategies.

[0183] For example, if a third-grade elementary school student is studying math at home and their facial expression shows signs of stress, the robot could suggest, "How about taking a 15-minute music break together?" An example of a prompt to input into the generative AI model could be, "A third-grade elementary school student is feeling stressed because they can't solve a math problem. Are there any more effective ways to motivate them?"

[0184] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0185] Step 1: The server acquires basic data, past learning history, and behavioral data about the subject. This data is supplied as input to the generating AI model to analyze the subject's characteristics. As a result of the analysis, characteristic data showing learning patterns and the learner's strengths and weaknesses is output.

[0186] Step 2: The server inputs real-time facial expression data and voice tone data of the subject, acquired via the device's camera and microphone, into the emotion engine. Based on this data, the current emotional state is analyzed, and emotional state data such as stress level and concentration level is output.

[0187] Step 3: The device receives trait and emotional state data transmitted from the server and generates personalized learning content based on it. This learning content is optimized for the subject and may include relaxation activities to reduce stress or tasks to improve concentration. The generated learning content is displayed on the device's screen.

[0188] Step 4: The user (learner) engages with the presented learning content. Throughout the learning process, the emotion engine continuously monitors the user's facial expressions and voice in real time and transmits this data to the server as emotion data. This data indicates the user's emotional changes during the learning process.

[0189] Step 5: Once the user's learning activity is complete, the server generates sentiment data and feedback on learning outcomes, which are provided to the user via the terminal. The feedback evaluates the user's learning progress and outcomes, and includes advice on areas for improvement and next steps.

[0190] Step 6: The server collects all feedback information and sentiment data and stores it in a database. This data is output as a report that teachers can view through a dashboard, and teachers can use it to adjust their teaching strategies for learners.

[0191] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0192] Data generation model 58 is a type of 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 those described above. 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 shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0193] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0194] [Second Embodiment]

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

[0196] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0197] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0198] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0199] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0200] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0201] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0202] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0203] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0204] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0205] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0206] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0207] This invention is a system that provides an individualized education system using a generative model. This system consists of a server, terminals, and users, each with a specific role.

[0208] First, the server centrally stores various data about the subjects. This includes the subjects' daily learning records, feedback from teachers, and the results of questionnaires aimed at behavioral analysis. Based on this data, a generative model is used to analyze the characteristics of each subject.

[0209] Next, the device functions as a user interface, providing participants with personalized learning content. It displays tasks and activities that participants should work on and allows them to receive real-time feedback. For example, if analysis indicates that a participant needs to improve their communication skills, tasks such as conversational games or role-playing scenarios are presented through the device.

[0210] Through this system, users are expected to proactively address the tasks presented to them. For example, users can participate in group discussions suggested on their devices, record the insights gained and their own actions on the device, and receive further feedback.

[0211] Finally, the server collects feedback from participants after they complete the tasks and stores it in a database as developmental data. This data serves as material for further analysis and is used by teachers to gain detailed insights into the participants. For example, it may be recorded that a user has improved their cooperation skills through multiple tasks, which can later be used by teachers to determine teaching strategies.

[0212] Thus, the present invention utilizes generative AI to effectively cultivate non-cognitive abilities tailored to the characteristics of the subject.

[0213] The following describes the processing flow.

[0214] Step 1:

[0215] The server continuously collects and stores student basic data, learning history, evaluation comments, and other information in a database. This includes retrieving data through the school's electronic grade management system and online survey platforms.

[0216] Step 2:

[0217] The server uses the collected data to feed into a generative model, which analyzes the characteristics of each student. This model learns from past data and automatically generates student behavioral characteristics and ability profiles.

[0218] Step 3:

[0219] The device presents students with personalized learning programs created by a generating AI based on characteristic analysis results received from the server. Before the first class of the day, the device displays a list of assignments suitable for each student.

[0220] Step 4:

[0221] Users (students) work on the assigned tasks. They select tasks via their devices and complete them according to the instructions. Task progress is recorded in real time.

[0222] Step 5:

[0223] The device provides users with AI-generated feedback immediately after they complete a task. For example, it displays text-based evaluations of communication quality and suggestions for improvement.

[0224] Step 6:

[0225] The server receives feedback information and task results from the terminals and stores them in a database as developmental data.

[0226] Step 7:

[0227] The server analyzes the accumulated data and periodically provides teachers with reports on student development and insights. These reports can be viewed on the teacher's dashboard.

[0228] (Example 1)

[0229] 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."

[0230] In today's learning environment, providing educational content optimized for individual learners is crucial, but traditional education systems have struggled to adequately consider individual learner characteristics. Therefore, there is a need for a system that effectively delivers education tailored to individual learning needs.

[0231] 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.

[0232] In this invention, the server includes means for analyzing the characteristics of individual learners using a generative model, means for generating personalized learning content based on said characteristics, and means for providing and recording feedback on said learning content. This makes it possible to provide educational content optimized for each individual learner and to continuously provide feedback on the results.

[0233] A "generative model" is a type of machine learning algorithm that can analyze data and generate new data or results.

[0234] A "learner" is an individual who aims to improve their knowledge and skills through a specific educational program or activity.

[0235] "Characteristics" refers to the unique characteristics of each learner, such as their individual personality, abilities, and learning style.

[0236] "Learning content" refers to educational materials and activities designed to convey the knowledge and skills that learners should acquire through education.

[0237] "Feedback" refers to comments and evaluations given about the learning outcomes and process, and is important for promoting learner growth.

[0238] "Growth data" refers to information about the progress and results obtained through learners' educational activities.

[0239] "Education professionals" refers to experts who are involved in the learning process of learners and who play a role in confirming and guiding their outcomes.

[0240] "Insight" refers to valuable understanding and knowledge gained by analyzing collected data, which is useful for improving educational strategies.

[0241] This system consists of three main components: servers, terminals, and users.

[0242] The server functions as a database, collecting and storing a wide range of data about learners. This data includes learning history, past performance, teacher comments, and survey results. The server analyzes this data using generative AI models, such as language models, to derive individual learner characteristics. Advanced technologies such as GPT-4 are used for these generative AI models. An example of a prompt is, "Suggest the next learning step appropriate for this learner."

[0243] The device serves as the user interface, displaying personalized learning content provided by the server to the learner. The device also has the functionality to display learning tasks required by the learner and provide timely feedback. The software running on the device typically operates on Android or iOS platforms. If the device analyzes that the learner needs to improve their communication skills, it will display interactive simulations or game-based tasks.

[0244] Users, or learners, use the system to work on the tasks presented to them. Learners record what they have learned and the results they have obtained on their devices and receive feedback. For example, users can gain further insights by participating in discussion activities on their devices and recording the content of those discussions.

[0245] Therefore, this system can provide learners with an individualized educational experience and support their growth.

[0246] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0247] Step 1:

[0248] The server collects learner data and stores it in a database. It receives learner learning history, past achievements, behavioral data, and survey results as input. This data is processed and organized into useful information. As output, the organized dataset is stored in the database. The server automatically imports new data daily to maintain data consistency.

[0249] Step 2:

[0250] The server applies a generative AI model based on the collected data to analyze the learner's characteristics. The previously accumulated dataset is used as input. The generative AI model is given the prompt, "Analyze this learner's strengths and weaknesses." The generative AI model processes the data and outputs the analysis results about the learner's characteristics. This output is used to generate personalized content.

[0251] Step 3:

[0252] The server generates personalized learning content based on the analysis results of the generated AI model. The input includes analyzed learner characteristic data. The server uses this data to select appropriate learning materials and activities, and generates learning content to send to the device as output. Specifically, the server places tasks based on learning objectives and sends real-time notifications to the device.

[0253] Step 4:

[0254] The terminal provides the learner with the personalized learning content it receives. The learning content sent from the server is used as input. The terminal displays this content on its interface, clearly indicating the tasks the learner needs to complete. The output provides a concrete interface that allows the learner to perform the tasks. The terminal displays progress in real time and provides hints and reminders as needed.

[0255] Step 5:

[0256] Users work on tasks presented through their devices. Input is the instruction and tasks received from the device. Learners perform activities based on this, inputting results and progress into the device along the way. Output is the generation of learner feedback and data on completed tasks. Specifically, users participate in interactive content and record comments and evaluations at the end of each session.

[0257] Step 6:

[0258] The server receives feedback data sent by users through their devices and stores it in a database. Inputs include learner feedback and activity completion data. The server analyzes this data and generates developmental data to track learner progress. The output is organized insight data, which is used by educators. Teachers use this data to adjust their teaching strategies.

[0259] (Application Example 1)

[0260] 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."

[0261] Traditional caregiving education systems provided uniform educational content, lacking a learning system tailored to the individual abilities and experience of care staff, resulting in inconsistent learning outcomes. Furthermore, there were insufficient objective means of evaluating growth and progress, hindering effective feedback for further skill development. These challenges raise concerns that the quality of care in caregiving settings may not be sufficiently improved.

[0262] 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.

[0263] In this invention, the server includes means for individually evaluating a person's abilities using a generative model, means for generating an individualized self-development program based on said abilities, and means for providing progress information for said program. This makes it possible to provide optimal educational content tailored to the abilities of each care staff member, and to improve the quality of care by providing feedback that corresponds to individual growth.

[0264] A "generative model" is a mathematical method for generating information tailored to a specific purpose based on data.

[0265] "Evaluating individual capabilities" is a process of analyzing and appropriately assessing the skills and knowledge levels of each person in detail.

[0266] A "self-development program" is a plan of learning and activities aimed at personal growth and skill improvement.

[0267] "Progress information" refers to data that shows the progress and results of learning or activities.

[0268] "Growth data" refers to information that shows how an individual has improved their abilities and skills from the past to the present.

[0269] "Providing insights to instructors from the growth data" means providing suggestions to instructors based on the obtained growth data to help them decide on their teaching methods and policies.

[0270] "Social adaptability" refers to the skills and attitudes necessary for an individual to interact effectively with others in a social environment.

[0271] In a system that implements this application example, a crucial process is the provision of individualized training programs for staff in care settings.

[0272] The server utilizes generative AI models to collect past work data and behavioral patterns of each care staff member and individually assesses their abilities. Based on this assessment, it is responsible for generating self-development programs optimized for each staff member. This server uses a standard computer server and software that drives generative AI models, such as the OpenAI API, to collect and analyze data.

[0273] The generated program is provided to care staff via a smartphone. The device allows users to work on the assigned tasks, and progress information is displayed in real time. This allows users to immediately grasp their own progress and clearly identify areas where further effort is needed.

[0274] Furthermore, the system incorporates features to provide instructors with insights based on growth data. This growth data is stored on a server and can be accessed by instructors as needed to help them determine specific teaching strategies and improve educational content.

[0275] For example, if a staff member needs to acquire more advanced dementia care skills, the server will suggest an optimal training plan using a prompt such as, "Generate a learning program on dementia care for beginners, focusing on communication techniques." This allows care staff to receive learning opportunities tailored to their individual needs, and is expected to improve their practical skills in the field.

[0276] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0277] Step 1:

[0278] The server accesses a database of care staff to collect past work data and behavioral patterns. This information is used as input to organize and analyze data necessary for individual competency assessments. The output is a competency profile for each staff member.

[0279] Step 2:

[0280] The server driving the generative AI model takes the ability profile obtained in step 1 as input and generates a personalized self-development program. At this time, it selects the optimal learning content using prompt statements and generates a customized learning program as output.

[0281] Step 3:

[0282] The terminal receives a customized learning program provided by the server. Based on this program, it displays specific learning content and tasks to the care staff. When the user engages in learning activities based on this, the terminal obtains the learning program as input and data on the user's implementation status as output.

[0283] Step 4:

[0284] The user works on tasks according to the learning program on the terminal and records the progress. The learning situation on the terminal is fed back as input, and progress information and growth data are sent to the server as output.

[0285] Step 5:

[0286] The server processes the progress information and growth data sent by the user and updates the accumulated database. This data is used as material to provide insights for the instructor. As a result of the analysis, the output includes the degree of growth of each staff member and guidelines for necessary follow-up.

[0287] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion.

[0288] The present invention is an education support system that integrates a generation model and an emotion engine, and provides individualized education based on the characteristics and emotional state of each subject. The system consists of a server, a terminal, and a user, each playing a specific role.

[0289] First, the server collects basic data, learning history, and past behavior data regarding the subject, and analyzes the characteristics of the subject using the generation model. Furthermore, the server analyzes the emotion data of the subject obtained in real time using the emotion engine. This emotion data is obtained by analyzing the subject's expression and voice tone using the camera and microphone of the terminal.

[0290] Next, the terminal provides individualized learning content based on the obtained characteristic analysis results and emotion data. This process dynamically adjusts the content according to the user's emotional state and creates an optimal learning environment. For example, if it is determined by the emotion engine that the user is feeling stressed, the terminal proposes tasks that promote relaxation or activities that change the focus.

[0291] The user works on a task presented via the device. While the user is working on the task, the emotion engine continuously monitors the user's emotional state. During or after the task, the user can receive immediate feedback, and the device provides feedback while taking into account the user's emotional changes.

[0292] Finally, the server stores feedback information and emotional data received from the terminal. This data is stored in a database as the subject's developmental data and is included in detailed reports that teachers can access through a dashboard. This allows teachers to gain insights into the subject's emotional health and responses, along with their learning performance, providing valuable information for adjusting teaching strategies.

[0293] Thus, the present invention combines generative AI and emotion recognition technology to achieve effective development of non-cognitive abilities tailored to the characteristics and emotions of the subject.

[0294] The following describes the processing flow.

[0295] Step 1:

[0296] The server collects basic student data, past learning history, and behavioral data, and stores it in a database. Then, it uses a generative model to analyze students' learning styles and characteristics. Based on this analysis, it generates a characteristic profile for each student.

[0297] Step 2:

[0298] The device uses its built-in camera and microphone to collect emotional data in real time from students' facial expressions and tone of voice. An emotion engine analyzes this data to identify the student's current emotional state.

[0299] Step 3:

[0300] The server combines the characteristic profile generated by the generation model and the emotional state by the emotion engine to create an individualized learning plan. The learning plan includes tasks and activities according to the characteristics and emotional state of the student and is transmitted to the terminal.

[0301] Step 4:

[0302] The terminal presents individualized learning tasks to the student. Based on the feedback from the emotion engine, the difficulty level and content of the tasks are adjusted as appropriate to support learning.

[0303] Step 5:

[0304] The user (student) undertakes the presented tasks. During the tasks, the terminal continuously monitors the student's emotional state and adjusts the learning content as necessary.

[0305] Step 6:

[0306] After the tasks are completed, the terminal evaluates the emotional state and the results of the tasks and provides immediate feedback. This feedback takes into account both the student's emotional reaction and task performance.

[0307] Step 7:

[0308] The server accumulates the feedback information and emotional data transmitted from the terminal in the database. These data are stored as materials indicating the development process of the subject and are later converted into reports accessible to teachers. Based on this report, teachers can formulate guidance plans corresponding to the changes in the learning and emotions of the students.

[0309] (Example 2)

[0310] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0311] In today's educational environment, providing individualized learning methods is difficult because it is not tailored to the characteristics and emotional state of each student. Furthermore, there are challenges such as delays in appropriately adjusting learning content and providing feedback, making it difficult for educators to gain a detailed understanding of each student's developmental progress.

[0312] 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.

[0313] In this invention, the server includes means for analyzing the characteristics of a subject using a generative model, means for acquiring and analyzing the subject's emotional state in real time using an emotion analysis engine, and means for dynamically generating and providing personalized learning content based on the analysis results. This makes it possible to provide a learning environment optimized for the subject, thereby further enhancing educational effectiveness.

[0314] A "generative model" is an artificial intelligence technology that generates specific outputs based on input data, and is used to analyze the characteristics and behavioral patterns of subjects.

[0315] The "emotion analysis engine" is a technology that analyzes the emotional state of a subject from their facial expressions, tone of voice, etc., and plays a role in evaluating their psychological state in real time and reflecting that in the learning content.

[0316] "Subject characteristics" refer to data that shows each learner's learning style and cognitive patterns, and serve as fundamental information for individualized learning.

[0317] "Individualized learning content" refers to educational tasks and materials that are dynamically adjusted based on the characteristics and emotional state of the subject, providing an optimal learning experience.

[0318] "Feedback" refers to information collected from subjects regarding their responses and results to tasks they have undertaken, and used to make improvements and adjustments.

[0319] "Developmental data" refers to data that shows changes in a subject's learning and emotions, and is used for formulating and measuring the effectiveness of ongoing educational plans.

[0320] This invention, as an educational support system, consists of a server, a terminal, and a user. The server collects basic data, learning history, and past behavioral data of the subject, and uses a generative AI model to analyze the subject's characteristics based on this data. Specifically, it uses a database management system to collect and manage data, and the generative AI model functions as an inference engine.

[0321] Subsequently, the server analyzes real-time emotional data acquired from the device's camera and microphone through an emotion analysis engine. By using facial recognition software and voice tone analysis algorithms, it is possible to evaluate the user's stress level and concentration level.

[0322] Based on these analysis results, the device dynamically generates and presents personalized learning content to the user. For example, if a user experiences stress while solving a math problem, the device can offer simple games or practice problems to help them relax.

[0323] Users engage in personalized tasks via their devices, and throughout this process, an emotion analysis engine continuously collects and sends emotional data to the server. This provides immediate feedback and optimizes the user's learning process. For example, encouraging comments are displayed on the device based on the user's reading pace and level of understanding.

[0324] The server uses feedback information from the terminal and accumulated emotional data to store the subject's developmental data in a database. This allows teachers to understand the subject's learning progress and emotional changes through detailed reports and adjust the instruction plan as needed.

[0325] As a concrete example, the server could input the prompt "Please create a math problem for elementary school students. Include suggestions for relaxation activities to provide if the student is feeling stressed." into a generating AI model to create a task optimized for the subject. This process further enhances the system's dynamic adaptive capabilities.

[0326] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0327] Step 1:

[0328] The server collects basic data, learning history, and past behavioral data about the subjects. It receives data sets from the learning management system as input and stores them in a centralized database. Data processing mainly involves integration and imputation of missing values, resulting in a formatted dataset as output.

[0329] Step 2:

[0330] The server runs a generative AI model using a formatted dataset to analyze the characteristics of the subjects. It uses the subjects' historical data as input and prompts the generative model to perform characteristic analysis. During this process, the subjects' learning styles and cognitive characteristics are identified, and the analysis results are output.

[0331] Step 3:

[0332] The server receives data collected in real time from the terminal's camera and microphone, and analyzes the subject's emotions using an emotion analysis engine. Audio and video data are used as input, and the emotional state is calculated based on voice tone and facial expressions. The analysis results are output as data indicating the subject's current emotional state.

[0333] Step 4:

[0334] The device receives analyzed characteristic data and emotional state data from the server and generates personalized learning content. Using the analyzed and emotional data from the server as input, it dynamically creates appropriately customized tasks and learning materials based on the generated AI model. The generated learning content is then output to the user.

[0335] Step 5:

[0336] The user works on personalized learning tasks presented by the device. Learning content is provided from the device as input, and the user responds to it. The user's actions are sent to the server as feedback, and learning progress and task completion status are output.

[0337] Step 6:

[0338] The server stores feedback information and continuously collected emotional data in a database. It uses feedback and emotional data from the terminals as input, and performs analysis and storage processing. Finally, it outputs reports on the subjects' developmental data and emotional changes in a format accessible to teachers.

[0339] (Application Example 2)

[0340] 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."

[0341] In recent years, the importance of individualized education tailored to the unique personalities and emotions of each learner has been increasingly recognized in educational settings. However, existing educational systems have had limitations in responding to learners' real-time emotional states and characteristics. Furthermore, there are challenges in providing optimal learning environments due to insufficient feedback based on learning progress and inadequate efforts to boost motivation.

[0342] 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.

[0343] In this invention, the server includes means for analyzing the characteristics of individual subjects using a generative model, means for generating and dynamically adjusting personalized learning content based on emotional states obtained in real time, and means for recognizing the emotional states of subjects using a speech recognition device and an image acquisition device. This enables the provision of immediate feedback that reflects the learner's emotional state, thereby realizing an optimized learning environment.

[0344] A "generative model" is an information processing technique used to analyze the characteristics of subjects, and is a model used to analyze patterns and trends in data.

[0345] "Individualized learning content" refers to learning content designed to provide each learner with the most suitable learning tasks and materials, taking into account the characteristics of the subject and their real-time emotional state.

[0346] A "dynamic adjustment mechanism" is a function that can change the learning content provided according to the subject's emotional state and learning progress.

[0347] A "speech recognition device" is a hardware and software technology that analyzes a subject's voice and detects its content and emotional state.

[0348] An "image acquisition device" refers to a camera and related technologies used to acquire and analyze a subject's facial expressions and other visual data.

[0349] "Means for recognizing emotional states" refers to technologies that have the function of detecting emotions from a subject's facial expressions and voice and analyzing them in real time.

[0350] "Providing immediate feedback" is a feature that allows participants to receive real-time feedback on their progress and areas for improvement as they learn.

[0351] An "optimized learning environment" is an environment designed based on the characteristics and emotional state of the subject, which promotes effective and efficient learning for the learner.

[0352] This invention is a system that supports individualized education based on the characteristics and emotional state of the subject. Details are described below.

[0353] The server has the capability to analyze the characteristics of the subject using generative models and emotion engine software. Based on basic data, learning history, and behavioral data obtained from the subject, the server extracts the learner's characteristics through a generative AI model. Emotional data is acquired in real time using the device's camera and microphone, through analysis of facial expressions and voice tone. This allows for a comprehensive examination of factors that influence the subject's learning progress.

[0354] The device is equipped with a function that dynamically adjusts the user's learning content. Based on analyzed characteristics and emotional data, the device presents personalized learning materials. For example, if the user is feeling stressed, it will suggest activities that promote relaxation. This creates an optimal learning environment for the learner.

[0355] Users are continuously monitored by an emotion engine as they work on assigned tasks and activities. Immediate feedback is provided during or after tasks, and all of the user's emotional data is stored on the server. This allows the user's developmental data to be stored in a database, providing teachers with detailed reports through a dashboard and information to adjust teaching strategies.

[0356] For example, if a third-grade elementary school student is studying math at home and their facial expression shows signs of stress, the robot could suggest, "How about taking a 15-minute music break together?" An example of a prompt to input into the generative AI model could be, "A third-grade elementary school student is feeling stressed because they can't solve a math problem. Are there any more effective ways to motivate them?"

[0357] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0358] Step 1: The server acquires basic data, past learning history, and behavioral data about the subject. This data is supplied as input to the generating AI model to analyze the subject's characteristics. As a result of the analysis, characteristic data showing learning patterns and the learner's strengths and weaknesses is output.

[0359] Step 2: The server inputs real-time facial expression data and voice tone data of the subject, acquired via the device's camera and microphone, into the emotion engine. Based on this data, the current emotional state is analyzed, and emotional state data such as stress level and concentration level is output.

[0360] Step 3: The device receives trait and emotional state data transmitted from the server and generates personalized learning content based on it. This learning content is optimized for the subject and may include relaxation activities to reduce stress or tasks to improve concentration. The generated learning content is displayed on the device's screen.

[0361] Step 4: The user (learner) engages with the presented learning content. Throughout the learning process, the emotion engine continuously monitors the user's facial expressions and voice in real time and transmits this data to the server as emotion data. This data indicates the user's emotional changes during the learning process.

[0362] Step 5: Once the user's learning activity is complete, the server generates sentiment data and feedback on learning outcomes, which are provided to the user via the terminal. The feedback evaluates the user's learning progress and outcomes, and includes advice on areas for improvement and next steps.

[0363] Step 6: The server collects all feedback information and sentiment data and stores it in a database. This data is output as a report that teachers can view through a dashboard, and teachers can use it to adjust their teaching strategies for learners.

[0364] 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.

[0365] 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 those described above. 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 shown 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.

[0366] 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.

[0367] [Third Embodiment]

[0368] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0369] 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.

[0370] 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).

[0371] 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.

[0372] 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.

[0373] 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).

[0374] 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.

[0375] 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.

[0376] 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.

[0377] 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.

[0378] 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.

[0379] 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".

[0380] This invention is a system that provides an individualized education system using a generative model. This system consists of a server, terminals, and users, each with a specific role.

[0381] First, the server centrally stores various data about the subjects. This includes the subjects' daily learning records, feedback from teachers, and the results of questionnaires aimed at behavioral analysis. Based on this data, a generative model is used to analyze the characteristics of each subject.

[0382] Next, the device functions as a user interface, providing participants with personalized learning content. It displays tasks and activities that participants should work on and allows them to receive real-time feedback. For example, if analysis indicates that a participant needs to improve their communication skills, tasks such as conversational games or role-playing scenarios are presented through the device.

[0383] Through this system, users are expected to proactively address the tasks presented to them. For example, users can participate in group discussions suggested on their devices, record the insights gained and their own actions on the device, and receive further feedback.

[0384] Finally, the server collects feedback from participants after they complete the tasks and stores it in a database as developmental data. This data serves as material for further analysis and is used by teachers to gain detailed insights into the participants. For example, it may be recorded that a user has improved their cooperation skills through multiple tasks, which can later be used by teachers to determine teaching strategies.

[0385] Thus, the present invention utilizes generative AI to effectively cultivate non-cognitive abilities tailored to the characteristics of the subject.

[0386] The following describes the processing flow.

[0387] Step 1:

[0388] The server continuously collects and stores student basic data, learning history, evaluation comments, and other information in a database. This includes retrieving data through the school's electronic grade management system and online survey platforms.

[0389] Step 2:

[0390] The server uses the collected data to feed into a generative model, which analyzes the characteristics of each student. This model learns from past data and automatically generates student behavioral characteristics and ability profiles.

[0391] Step 3:

[0392] The device presents students with personalized learning programs created by a generating AI based on characteristic analysis results received from the server. Before the first class of the day, the device displays a list of assignments suitable for each student.

[0393] Step 4:

[0394] Users (students) work on the assigned tasks. They select tasks via their devices and complete them according to the instructions. Task progress is recorded in real time.

[0395] Step 5:

[0396] The device provides users with AI-generated feedback immediately after they complete a task. For example, it displays text-based evaluations of communication quality and suggestions for improvement.

[0397] Step 6:

[0398] The server receives feedback information and task results from the terminals and stores them in a database as developmental data.

[0399] Step 7:

[0400] The server analyzes the accumulated data and periodically provides teachers with reports on student development and insights. These reports can be viewed on the teacher's dashboard.

[0401] (Example 1)

[0402] 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."

[0403] In today's learning environment, providing educational content optimized for individual learners is crucial, but traditional education systems have struggled to adequately consider individual learner characteristics. Therefore, there is a need for a system that effectively delivers education tailored to individual learning needs.

[0404] 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.

[0405] In this invention, the server includes means for analyzing the characteristics of individual learners using a generative model, means for generating personalized learning content based on said characteristics, and means for providing and recording feedback on said learning content. This makes it possible to provide educational content optimized for each individual learner and to continuously provide feedback on the results.

[0406] A "generative model" is a type of machine learning algorithm that can analyze data and generate new data or results.

[0407] A "learner" is an individual who aims to improve their knowledge and skills through a specific educational program or activity.

[0408] "Characteristics" refers to the unique characteristics of each learner, such as their individual personality, abilities, and learning style.

[0409] "Learning content" refers to educational materials and activities designed to convey the knowledge and skills that learners should acquire through education.

[0410] "Feedback" refers to comments and evaluations given about the learning outcomes and process, and is important for promoting learner growth.

[0411] "Growth data" refers to information about the progress and results obtained through learners' educational activities.

[0412] "Education professionals" refers to experts who are involved in the learning process of learners and who play a role in confirming and guiding their outcomes.

[0413] "Insight" refers to valuable understanding and knowledge gained by analyzing collected data, which is useful for improving educational strategies.

[0414] This system consists of three main components: servers, terminals, and users.

[0415] The server functions as a database, collecting and storing a wide range of data about learners. This data includes learning history, past performance, teacher comments, and survey results. The server analyzes this data using generative AI models, such as language models, to derive individual learner characteristics. Advanced technologies such as GPT-4 are used for these generative AI models. An example of a prompt is, "Suggest the next learning step appropriate for this learner."

[0416] The device serves as the user interface, displaying personalized learning content provided by the server to the learner. The device also has the functionality to display learning tasks required by the learner and provide timely feedback. The software running on the device typically operates on Android or iOS platforms. If the device analyzes that the learner needs to improve their communication skills, it will display interactive simulations or game-based tasks.

[0417] Users, or learners, use the system to work on the tasks presented to them. Learners record what they have learned and the results they have obtained on their devices and receive feedback. For example, users can gain further insights by participating in discussion activities on their devices and recording the content of those discussions.

[0418] Therefore, this system can provide learners with an individualized educational experience and support their growth.

[0419] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0420] Step 1:

[0421] The server collects learner data and stores it in a database. It receives learner learning history, past achievements, behavioral data, and survey results as input. This data is processed and organized into useful information. As output, the organized dataset is stored in the database. The server automatically imports new data daily to maintain data consistency.

[0422] Step 2:

[0423] The server applies a generative AI model based on the collected data to analyze the learner's characteristics. The previously accumulated dataset is used as input. The generative AI model is given the prompt, "Analyze this learner's strengths and weaknesses." The generative AI model processes the data and outputs the analysis results about the learner's characteristics. This output is used to generate personalized content.

[0424] Step 3:

[0425] The server generates personalized learning content based on the analysis results of the generated AI model. The input includes analyzed learner characteristic data. The server uses this data to select appropriate learning materials and activities, and generates learning content to send to the device as output. Specifically, the server places tasks based on learning objectives and sends real-time notifications to the device.

[0426] Step 4:

[0427] The terminal provides the learner with the personalized learning content it receives. The learning content sent from the server is used as input. The terminal displays this content on its interface, clearly indicating the tasks the learner needs to complete. The output provides a concrete interface that allows the learner to perform the tasks. The terminal displays progress in real time and provides hints and reminders as needed.

[0428] Step 5:

[0429] Users work on tasks presented through their devices. Input is the instruction and tasks received from the device. Learners perform activities based on this, inputting results and progress into the device along the way. Output is the generation of learner feedback and data on completed tasks. Specifically, users participate in interactive content and record comments and evaluations at the end of each session.

[0430] Step 6:

[0431] The server receives feedback data sent by users through their devices and stores it in a database. Inputs include learner feedback and activity completion data. The server analyzes this data and generates developmental data to track learner progress. The output is organized insight data, which is used by educators. Teachers use this data to adjust their teaching strategies.

[0432] (Application Example 1)

[0433] 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."

[0434] Traditional caregiving education systems provided uniform educational content, lacking a learning system tailored to the individual abilities and experience of care staff, resulting in inconsistent learning outcomes. Furthermore, there were insufficient objective means of evaluating growth and progress, hindering effective feedback for further skill development. These challenges raise concerns that the quality of care in caregiving settings may not be sufficiently improved.

[0435] 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.

[0436] In this invention, the server includes means for individually evaluating a person's abilities using a generative model, means for generating an individualized self-development program based on said abilities, and means for providing progress information for said program. This makes it possible to provide optimal educational content tailored to the abilities of each care staff member, and to improve the quality of care by providing feedback that corresponds to individual growth.

[0437] A "generative model" is a mathematical method for generating information tailored to a specific purpose based on data.

[0438] "Evaluating individual capabilities" is a process of analyzing and appropriately assessing the skills and knowledge levels of each person in detail.

[0439] A "self-development program" is a plan of learning and activities aimed at personal growth and skill improvement.

[0440] "Progress information" refers to data that shows the progress and results of learning or activities.

[0441] "Growth data" refers to information that shows how an individual has improved their abilities and skills from the past to the present.

[0442] "Providing insights to instructors from the growth data" means providing suggestions to instructors based on the obtained growth data to help them decide on their teaching methods and policies.

[0443] "Social adaptability" refers to the skills and attitudes necessary for an individual to interact effectively with others in a social environment.

[0444] In a system that implements this application example, a crucial process is the provision of individualized training programs for staff in care settings.

[0445] The server utilizes generative AI models to collect past work data and behavioral patterns of each care staff member and individually assesses their abilities. Based on this assessment, it is responsible for generating self-development programs optimized for each staff member. This server uses a standard computer server and software that drives generative AI models, such as the OpenAI API, to collect and analyze data.

[0446] The generated program is provided to care staff via a smartphone. The device allows users to work on the assigned tasks, and progress information is displayed in real time. This allows users to immediately grasp their own progress and clearly identify areas where further effort is needed.

[0447] Furthermore, the system incorporates features to provide instructors with insights based on growth data. This growth data is stored on a server and can be accessed by instructors as needed to help them determine specific teaching strategies and improve educational content.

[0448] For example, if a staff member needs to acquire more advanced dementia care skills, the server will suggest an optimal training plan using a prompt such as, "Generate a learning program on dementia care for beginners, focusing on communication techniques." This allows care staff to receive learning opportunities tailored to their individual needs, and is expected to improve their practical skills in the field.

[0449] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0450] Step 1:

[0451] The server accesses a database of care staff to collect past work data and behavioral patterns. This information is used as input to organize and analyze data necessary for individual competency assessments. The output is a competency profile for each staff member.

[0452] Step 2:

[0453] The server driving the generative AI model takes the ability profile obtained in step 1 as input and generates a personalized self-development program. At this time, it selects the optimal learning content using prompt statements and generates a customized learning program as output.

[0454] Step 3:

[0455] The terminal receives a customized learning program provided by the server. Based on this program, it displays specific learning content and tasks to the care staff. When the user engages in learning activities based on this, the terminal obtains the learning program as input and data on the user's implementation status as output.

[0456] Step 4:

[0457] Users work on assignments according to a learning program on their devices and record their progress. The learning progress on the device is fed back as input, and progress information and growth data are sent to the server as output.

[0458] Step 5:

[0459] The server processes progress and growth data submitted by users and updates the stored database. This data is used as material to provide insights for mentors. As a result of the analysis, the output includes each staff member's level of growth and guidance for necessary follow-up.

[0460] 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.

[0461] This invention is an educational support system that integrates a generative model and an emotion engine, providing personalized education based on the characteristics and emotional state of each individual subject. The system consists of a server, terminals, and users, each playing a specific role.

[0462] First, the server collects basic data, learning history, and past behavioral data about the subject, and analyzes the subject's characteristics using a generative model. Furthermore, the server analyzes the subject's emotional data, which is acquired in real time, using an emotion engine. This emotional data is obtained by analyzing the subject's facial expressions and tone of voice using the device's camera and microphone.

[0463] Next, the device provides personalized learning content based on the acquired characteristic analysis results and emotional data. This process dynamically adjusts the content according to the user's emotional state, creating an optimal learning environment. For example, if the emotional engine determines that the user is feeling stressed, the device will suggest tasks that promote relaxation or activities that change focus.

[0464] The user works on a task presented via the device. While the user is working on the task, the emotion engine continuously monitors the user's emotional state. During or after the task, the user can receive immediate feedback, and the device provides feedback while taking into account the user's emotional changes.

[0465] Finally, the server stores feedback information and emotional data received from the terminal. This data is stored in a database as the subject's developmental data and is included in detailed reports that teachers can access through a dashboard. This allows teachers to gain insights into the subject's emotional health and responses, along with their learning performance, providing valuable information for adjusting teaching strategies.

[0466] Thus, the present invention combines generative AI and emotion recognition technology to achieve effective development of non-cognitive abilities tailored to the characteristics and emotions of the subject.

[0467] The following describes the processing flow.

[0468] Step 1:

[0469] The server collects basic student data, past learning history, and behavioral data, and stores it in a database. Then, it uses a generative model to analyze students' learning styles and characteristics. Based on this analysis, it generates a characteristic profile for each student.

[0470] Step 2:

[0471] The device uses its built-in camera and microphone to collect emotional data in real time from students' facial expressions and tone of voice. An emotion engine analyzes this data to identify the student's current emotional state.

[0472] Step 3:

[0473] The server combines trait profiles generated by generative models with emotional states generated by an emotion engine to create personalized learning plans. These learning plans include tasks and activities tailored to the student's traits and emotional state, and are sent to the device.

[0474] Step 4:

[0475] The device presents students with personalized learning tasks. Based on feedback from the emotion engine, it adjusts the difficulty and content of the tasks as needed to support learning.

[0476] Step 5:

[0477] The user (student) works on the assigned task. During the task, the device continuously monitors the student's emotional state and adjusts the learning content as needed.

[0478] Step 6:

[0479] The device evaluates the student's emotional state and task performance after task completion and provides immediate feedback. This feedback takes into account both the student's emotional response and task performance.

[0480] Step 7:

[0481] The server stores feedback information and emotional data sent from the terminal in a database. This data is saved as documentation showing the subject's developmental progress and is later converted into a report accessible to the teacher. Based on this report, the teacher can develop an instructional plan that addresses the student's learning and emotional changes.

[0482] (Example 2)

[0483] 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."

[0484] In today's educational environment, providing individualized learning methods is difficult because it is not tailored to the characteristics and emotional state of each student. Furthermore, there are challenges such as delays in appropriately adjusting learning content and providing feedback, making it difficult for educators to gain a detailed understanding of each student's developmental progress.

[0485] 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.

[0486] In this invention, the server includes means for analyzing the characteristics of a subject using a generative model, means for acquiring and analyzing the subject's emotional state in real time using an emotion analysis engine, and means for dynamically generating and providing personalized learning content based on the analysis results. This makes it possible to provide a learning environment optimized for the subject, thereby further enhancing educational effectiveness.

[0487] A "generative model" is an artificial intelligence technology that generates specific outputs based on input data, and is used to analyze the characteristics and behavioral patterns of subjects.

[0488] The "emotion analysis engine" is a technology that analyzes the emotional state of a subject from their facial expressions, tone of voice, etc., and plays a role in evaluating their psychological state in real time and reflecting that in the learning content.

[0489] "Subject characteristics" refer to data that shows each learner's learning style and cognitive patterns, and serve as fundamental information for individualized learning.

[0490] "Individualized learning content" refers to educational tasks and materials that are dynamically adjusted based on the characteristics and emotional state of the subject, providing an optimal learning experience.

[0491] "Feedback" refers to information collected from subjects regarding their responses and results to tasks they have undertaken, and used to make improvements and adjustments.

[0492] "Developmental data" refers to data that shows changes in a subject's learning and emotions, and is used for formulating and measuring the effectiveness of ongoing educational plans.

[0493] This invention, as an educational support system, consists of a server, a terminal, and a user. The server collects basic data, learning history, and past behavioral data of the subject, and uses a generative AI model to analyze the subject's characteristics based on this data. Specifically, it uses a database management system to collect and manage data, and the generative AI model functions as an inference engine.

[0494] Subsequently, the server analyzes real-time emotional data acquired from the device's camera and microphone through an emotion analysis engine. By using facial recognition software and voice tone analysis algorithms, it is possible to evaluate the user's stress level and concentration level.

[0495] Based on these analysis results, the device dynamically generates and presents personalized learning content to the user. For example, if a user experiences stress while solving a math problem, the device can offer simple games or practice problems to help them relax.

[0496] Users engage in personalized tasks via their devices, and throughout this process, an emotion analysis engine continuously collects and sends emotional data to the server. This provides immediate feedback and optimizes the user's learning process. For example, encouraging comments are displayed on the device based on the user's reading pace and level of understanding.

[0497] The server uses feedback information from the terminal and accumulated emotional data to store the subject's developmental data in a database. This allows teachers to understand the subject's learning progress and emotional changes through detailed reports and adjust the instruction plan as needed.

[0498] As a concrete example, the server could input the prompt "Please create a math problem for elementary school students. Include suggestions for relaxation activities to provide if the student is feeling stressed." into a generating AI model to create a task optimized for the subject. This process further enhances the system's dynamic adaptive capabilities.

[0499] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0500] Step 1:

[0501] The server collects basic data, learning history, and past behavioral data about the subjects. It receives data sets from the learning management system as input and stores them in a centralized database. Data processing mainly involves integration and imputation of missing values, resulting in a formatted dataset as output.

[0502] Step 2:

[0503] The server runs a generative AI model using a formatted dataset to analyze the characteristics of the subjects. It uses the subjects' historical data as input and prompts the generative model to perform characteristic analysis. During this process, the subjects' learning styles and cognitive characteristics are identified, and the analysis results are output.

[0504] Step 3:

[0505] The server receives data collected in real time from the terminal's camera and microphone, and analyzes the subject's emotions using an emotion analysis engine. Audio and video data are used as input, and the emotional state is calculated based on voice tone and facial expressions. The analysis results are output as data indicating the subject's current emotional state.

[0506] Step 4:

[0507] The device receives analyzed characteristic data and emotional state data from the server and generates personalized learning content. Using the analyzed and emotional data from the server as input, it dynamically creates appropriately customized tasks and learning materials based on the generated AI model. The generated learning content is then output to the user.

[0508] Step 5:

[0509] The user works on personalized learning tasks presented by the device. Learning content is provided from the device as input, and the user responds to it. The user's actions are sent to the server as feedback, and learning progress and task completion status are output.

[0510] Step 6:

[0511] The server stores feedback information and continuously collected emotional data in a database. It uses feedback and emotional data from the terminals as input, and performs analysis and storage processing. Finally, it outputs reports on the subjects' developmental data and emotional changes in a format accessible to teachers.

[0512] (Application Example 2)

[0513] 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."

[0514] In recent years, the importance of individualized education tailored to the unique personalities and emotions of each learner has been increasingly recognized in educational settings. However, existing educational systems have had limitations in responding to learners' real-time emotional states and characteristics. Furthermore, there are challenges in providing optimal learning environments due to insufficient feedback based on learning progress and inadequate efforts to boost motivation.

[0515] 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.

[0516] In this invention, the server includes means for analyzing the characteristics of individual subjects using a generative model, means for generating and dynamically adjusting personalized learning content based on emotional states obtained in real time, and means for recognizing the emotional states of subjects using a speech recognition device and an image acquisition device. This enables the provision of immediate feedback that reflects the learner's emotional state, thereby realizing an optimized learning environment.

[0517] A "generative model" is an information processing technique used to analyze the characteristics of subjects, and is a model used to analyze patterns and trends in data.

[0518] "Individualized learning content" refers to learning content designed to provide each learner with the most suitable learning tasks and materials, taking into account the characteristics of the subject and their real-time emotional state.

[0519] A "dynamic adjustment mechanism" is a function that can change the learning content provided according to the subject's emotional state and learning progress.

[0520] A "speech recognition device" is a hardware and software technology that analyzes a subject's voice and detects its content and emotional state.

[0521] An "image acquisition device" refers to a camera and related technologies used to acquire and analyze a subject's facial expressions and other visual data.

[0522] "Means for recognizing emotional states" refers to technologies that have the function of detecting emotions from a subject's facial expressions and voice and analyzing them in real time.

[0523] "Providing immediate feedback" is a feature that allows participants to receive real-time feedback on their progress and areas for improvement as they learn.

[0524] An "optimized learning environment" is an environment designed based on the characteristics and emotional state of the subject, which promotes effective and efficient learning for the learner.

[0525] This invention is a system that supports individualized education based on the characteristics and emotional state of the subject. Details are described below.

[0526] The server has the capability to analyze the characteristics of the subject using generative models and emotion engine software. Based on basic data, learning history, and behavioral data obtained from the subject, the server extracts the learner's characteristics through a generative AI model. Emotional data is acquired in real time using the device's camera and microphone, through analysis of facial expressions and voice tone. This allows for a comprehensive examination of factors that influence the subject's learning progress.

[0527] The device is equipped with a function that dynamically adjusts the user's learning content. Based on analyzed characteristics and emotional data, the device presents personalized learning materials. For example, if the user is feeling stressed, it will suggest activities that promote relaxation. This creates an optimal learning environment for the learner.

[0528] Users are continuously monitored by an emotion engine as they work on assigned tasks and activities. Immediate feedback is provided during or after tasks, and all of the user's emotional data is stored on the server. This allows the user's developmental data to be stored in a database, providing teachers with detailed reports through a dashboard and information to adjust teaching strategies.

[0529] For example, if a third-grade elementary school student is studying math at home and their facial expression shows signs of stress, the robot could suggest, "How about taking a 15-minute music break together?" An example of a prompt to input into the generative AI model could be, "A third-grade elementary school student is feeling stressed because they can't solve a math problem. Are there any more effective ways to motivate them?"

[0530] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0531] Step 1: The server acquires basic data, past learning history, and behavioral data about the subject. This data is supplied as input to the generating AI model to analyze the subject's characteristics. As a result of the analysis, characteristic data showing learning patterns and the learner's strengths and weaknesses is output.

[0532] Step 2: The server inputs real-time facial expression data and voice tone data of the subject, acquired via the device's camera and microphone, into the emotion engine. Based on this data, the current emotional state is analyzed, and emotional state data such as stress level and concentration level is output.

[0533] Step 3: The device receives trait and emotional state data transmitted from the server and generates personalized learning content based on it. This learning content is optimized for the subject and may include relaxation activities to reduce stress or tasks to improve concentration. The generated learning content is displayed on the device's screen.

[0534] Step 4: The user (learner) engages with the presented learning content. Throughout the learning process, the emotion engine continuously monitors the user's facial expressions and voice in real time and transmits this data to the server as emotion data. This data indicates the user's emotional changes during the learning process.

[0535] Step 5: Once the user's learning activity is complete, the server generates sentiment data and feedback on learning outcomes, which are provided to the user via the terminal. The feedback evaluates the user's learning progress and outcomes, and includes advice on areas for improvement and next steps.

[0536] Step 6: The server collects all feedback information and sentiment data and stores it in a database. This data is output as a report that teachers can view through a dashboard, and teachers can use it to adjust their teaching strategies for learners.

[0537] 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.

[0538] 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 those described above. 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 shown 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.

[0539] 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.

[0540] [Fourth Embodiment]

[0541] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0542] 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.

[0543] 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).

[0544] 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.

[0545] 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.

[0546] 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).

[0547] 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.

[0548] 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.

[0549] 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.

[0550] 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.

[0551] 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.

[0552] 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.

[0553] 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".

[0554] This invention is a system that provides an individualized education system using a generative model. This system consists of a server, terminals, and users, each with a specific role.

[0555] First, the server centrally stores various data about the subjects. This includes the subjects' daily learning records, feedback from teachers, and the results of questionnaires aimed at behavioral analysis. Based on this data, a generative model is used to analyze the characteristics of each subject.

[0556] Next, the device functions as a user interface, providing participants with personalized learning content. It displays tasks and activities that participants should work on and allows them to receive real-time feedback. For example, if analysis indicates that a participant needs to improve their communication skills, tasks such as conversational games or role-playing scenarios are presented through the device.

[0557] Through this system, users are expected to proactively address the tasks presented to them. For example, users can participate in group discussions suggested on their devices, record the insights gained and their own actions on the device, and receive further feedback.

[0558] Finally, the server collects feedback from participants after they complete the tasks and stores it in a database as developmental data. This data serves as material for further analysis and is used by teachers to gain detailed insights into the participants. For example, it may be recorded that a user has improved their cooperation skills through multiple tasks, which can later be used by teachers to determine teaching strategies.

[0559] Thus, the present invention utilizes generative AI to effectively cultivate non-cognitive abilities tailored to the characteristics of the subject.

[0560] The following describes the processing flow.

[0561] Step 1:

[0562] The server continuously collects and stores student basic data, learning history, evaluation comments, and other information in a database. This includes retrieving data through the school's electronic grade management system and online survey platforms.

[0563] Step 2:

[0564] The server uses the collected data to feed into a generative model, which analyzes the characteristics of each student. This model learns from past data and automatically generates student behavioral characteristics and ability profiles.

[0565] Step 3:

[0566] The device presents students with personalized learning programs created by a generating AI based on characteristic analysis results received from the server. Before the first class of the day, the device displays a list of assignments suitable for each student.

[0567] Step 4:

[0568] Users (students) work on the assigned tasks. They select tasks via their devices and complete them according to the instructions. Task progress is recorded in real time.

[0569] Step 5:

[0570] The device provides users with AI-generated feedback immediately after they complete a task. For example, it displays text-based evaluations of communication quality and suggestions for improvement.

[0571] Step 6:

[0572] The server receives feedback information and task results from the terminals and stores them in a database as developmental data.

[0573] Step 7:

[0574] The server analyzes the accumulated data and periodically provides teachers with reports on student development and insights. These reports can be viewed on the teacher's dashboard.

[0575] (Example 1)

[0576] 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".

[0577] In today's learning environment, providing educational content optimized for individual learners is crucial, but traditional education systems have struggled to adequately consider individual learner characteristics. Therefore, there is a need for a system that effectively delivers education tailored to individual learning needs.

[0578] 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.

[0579] In this invention, the server includes means for analyzing the characteristics of individual learners using a generative model, means for generating personalized learning content based on said characteristics, and means for providing and recording feedback on said learning content. This makes it possible to provide educational content optimized for each individual learner and to continuously provide feedback on the results.

[0580] A "generative model" is a type of machine learning algorithm that can analyze data and generate new data or results.

[0581] A "learner" is an individual who aims to improve their knowledge and skills through a specific educational program or activity.

[0582] "Characteristics" refers to the unique characteristics of each learner, such as their individual personality, abilities, and learning style.

[0583] "Learning content" refers to educational materials and activities designed to convey the knowledge and skills that learners should acquire through education.

[0584] "Feedback" refers to comments and evaluations given about the learning outcomes and process, and is important for promoting learner growth.

[0585] "Growth data" refers to information about the progress and results obtained through learners' educational activities.

[0586] "Education professionals" refers to experts who are involved in the learning process of learners and who play a role in confirming and guiding their outcomes.

[0587] "Insight" refers to valuable understanding and knowledge gained by analyzing collected data, which is useful for improving educational strategies.

[0588] This system consists of three main components: servers, terminals, and users.

[0589] The server functions as a database, collecting and storing a wide range of data about learners. This data includes learning history, past performance, teacher comments, and survey results. The server analyzes this data using generative AI models, such as language models, to derive individual learner characteristics. Advanced technologies such as GPT-4 are used for these generative AI models. An example of a prompt is, "Suggest the next learning step appropriate for this learner."

[0590] The device serves as the user interface, displaying personalized learning content provided by the server to the learner. The device also has the functionality to display learning tasks required by the learner and provide timely feedback. The software running on the device typically operates on Android or iOS platforms. If the device analyzes that the learner needs to improve their communication skills, it will display interactive simulations or game-based tasks.

[0591] Users, or learners, use the system to work on the tasks presented to them. Learners record what they have learned and the results they have obtained on their devices and receive feedback. For example, users can gain further insights by participating in discussion activities on their devices and recording the content of those discussions.

[0592] Therefore, this system can provide learners with an individualized educational experience and support their growth.

[0593] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0594] Step 1:

[0595] The server collects learner data and stores it in a database. It receives learner learning history, past achievements, behavioral data, and survey results as input. This data is processed and organized into useful information. As output, the organized dataset is stored in the database. The server automatically imports new data daily to maintain data consistency.

[0596] Step 2:

[0597] The server applies a generative AI model based on the collected data to analyze the learner's characteristics. The previously accumulated dataset is used as input. The generative AI model is given the prompt, "Analyze this learner's strengths and weaknesses." The generative AI model processes the data and outputs the analysis results about the learner's characteristics. This output is used to generate personalized content.

[0598] Step 3:

[0599] The server generates personalized learning content based on the analysis results of the generated AI model. The input includes analyzed learner characteristic data. The server uses this data to select appropriate learning materials and activities, and generates learning content to send to the device as output. Specifically, the server places tasks based on learning objectives and sends real-time notifications to the device.

[0600] Step 4:

[0601] The terminal provides the learner with the personalized learning content it receives. The learning content sent from the server is used as input. The terminal displays this content on its interface, clearly indicating the tasks the learner needs to complete. The output provides a concrete interface that allows the learner to perform the tasks. The terminal displays progress in real time and provides hints and reminders as needed.

[0602] Step 5:

[0603] Users work on tasks presented through their devices. Input is the instruction and tasks received from the device. Learners perform activities based on this, inputting results and progress into the device along the way. Output is the generation of learner feedback and data on completed tasks. Specifically, users participate in interactive content and record comments and evaluations at the end of each session.

[0604] Step 6:

[0605] The server receives feedback data sent by users through their devices and stores it in a database. Inputs include learner feedback and activity completion data. The server analyzes this data and generates developmental data to track learner progress. The output is organized insight data, which is used by educators. Teachers use this data to adjust their teaching strategies.

[0606] (Application Example 1)

[0607] 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".

[0608] Traditional caregiving education systems provided uniform educational content, lacking a learning system tailored to the individual abilities and experience of care staff, resulting in inconsistent learning outcomes. Furthermore, there were insufficient objective means of evaluating growth and progress, hindering effective feedback for further skill development. These challenges raise concerns that the quality of care in caregiving settings may not be sufficiently improved.

[0609] 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.

[0610] In this invention, the server includes means for individually evaluating a person's abilities using a generative model, means for generating an individualized self-development program based on said abilities, and means for providing progress information for said program. This makes it possible to provide optimal educational content tailored to the abilities of each care staff member, and to improve the quality of care by providing feedback that corresponds to individual growth.

[0611] A "generative model" is a mathematical method for generating information tailored to a specific purpose based on data.

[0612] "Evaluating individual capabilities" is a process of analyzing and appropriately assessing the skills and knowledge levels of each person in detail.

[0613] A "self-development program" is a plan of learning and activities aimed at personal growth and skill improvement.

[0614] "Progress information" refers to data that shows the progress and results of learning or activities.

[0615] "Growth data" refers to information that shows how an individual has improved their abilities and skills from the past to the present.

[0616] "Providing insights to instructors from the growth data" means providing suggestions to instructors based on the obtained growth data to help them decide on their teaching methods and policies.

[0617] "Social adaptability" refers to the skills and attitudes necessary for an individual to interact effectively with others in a social environment.

[0618] In a system that implements this application example, a crucial process is the provision of individualized training programs for staff in care settings.

[0619] The server utilizes generative AI models to collect past work data and behavioral patterns of each care staff member and individually assesses their abilities. Based on this assessment, it is responsible for generating self-development programs optimized for each staff member. This server uses a standard computer server and software that drives generative AI models, such as the OpenAI API, to collect and analyze data.

[0620] The generated program is provided to care staff via a smartphone. The device allows users to work on the assigned tasks, and progress information is displayed in real time. This allows users to immediately grasp their own progress and clearly identify areas where further effort is needed.

[0621] Furthermore, the system incorporates features to provide instructors with insights based on growth data. This growth data is stored on a server and can be accessed by instructors as needed to help them determine specific teaching strategies and improve educational content.

[0622] For example, if a staff member needs to acquire more advanced dementia care skills, the server will suggest an optimal training plan using a prompt such as, "Generate a learning program on dementia care for beginners, focusing on communication techniques." This allows care staff to receive learning opportunities tailored to their individual needs, and is expected to improve their practical skills in the field.

[0623] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0624] Step 1:

[0625] The server accesses a database of care staff to collect past work data and behavioral patterns. This information is used as input to organize and analyze data necessary for individual competency assessments. The output is a competency profile for each staff member.

[0626] Step 2:

[0627] The server driving the generative AI model takes the ability profile obtained in step 1 as input and generates a personalized self-development program. At this time, it selects the optimal learning content using prompt statements and generates a customized learning program as output.

[0628] Step 3:

[0629] The terminal receives a customized learning program provided by the server. Based on this program, it displays specific learning content and tasks to the care staff. When the user engages in learning activities based on this, the terminal obtains the learning program as input and data on the user's implementation status as output.

[0630] Step 4:

[0631] Users work on assignments according to a learning program on their devices and record their progress. The learning progress on the device is fed back as input, and progress information and growth data are sent to the server as output.

[0632] Step 5:

[0633] The server processes progress and growth data submitted by users and updates the stored database. This data is used as material to provide insights for mentors. As a result of the analysis, the output includes each staff member's level of growth and guidance for necessary follow-up.

[0634] 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.

[0635] This invention is an educational support system that integrates a generative model and an emotion engine, providing personalized education based on the characteristics and emotional state of each individual subject. The system consists of a server, terminals, and users, each playing a specific role.

[0636] First, the server collects basic data, learning history, and past behavioral data about the subject, and analyzes the subject's characteristics using a generative model. Furthermore, the server analyzes the subject's emotional data, which is acquired in real time, using an emotion engine. This emotional data is obtained by analyzing the subject's facial expressions and tone of voice using the device's camera and microphone.

[0637] Next, the device provides personalized learning content based on the acquired characteristic analysis results and emotional data. This process dynamically adjusts the content according to the user's emotional state, creating an optimal learning environment. For example, if the emotional engine determines that the user is feeling stressed, the device will suggest tasks that promote relaxation or activities that change focus.

[0638] The user works on a task presented via the device. While the user is working on the task, the emotion engine continuously monitors the user's emotional state. During or after the task, the user can receive immediate feedback, and the device provides feedback while taking into account the user's emotional changes.

[0639] Finally, the server stores feedback information and emotional data received from the terminal. This data is stored in a database as the subject's developmental data and is included in detailed reports that teachers can access through a dashboard. This allows teachers to gain insights into the subject's emotional health and responses, along with their learning performance, providing valuable information for adjusting teaching strategies.

[0640] Thus, the present invention combines generative AI and emotion recognition technology to achieve effective development of non-cognitive abilities tailored to the characteristics and emotions of the subject.

[0641] The following describes the processing flow.

[0642] Step 1:

[0643] The server collects basic student data, past learning history, and behavioral data, and stores it in a database. Then, it uses a generative model to analyze students' learning styles and characteristics. Based on this analysis, it generates a characteristic profile for each student.

[0644] Step 2:

[0645] The device uses its built-in camera and microphone to collect emotional data in real time from students' facial expressions and tone of voice. An emotion engine analyzes this data to identify the student's current emotional state.

[0646] Step 3:

[0647] The server combines trait profiles generated by generative models with emotional states generated by an emotion engine to create personalized learning plans. These learning plans include tasks and activities tailored to the student's traits and emotional state, and are sent to the device.

[0648] Step 4:

[0649] The device presents students with personalized learning tasks. Based on feedback from the emotion engine, it adjusts the difficulty and content of the tasks as needed to support learning.

[0650] Step 5:

[0651] The user (student) works on the assigned task. During the task, the device continuously monitors the student's emotional state and adjusts the learning content as needed.

[0652] Step 6:

[0653] The device evaluates the student's emotional state and task performance after task completion and provides immediate feedback. This feedback takes into account both the student's emotional response and task performance.

[0654] Step 7:

[0655] The server stores feedback information and emotional data sent from the terminal in a database. This data is saved as documentation showing the subject's developmental progress and is later converted into a report accessible to the teacher. Based on this report, the teacher can develop an instructional plan that addresses the student's learning and emotional changes.

[0656] (Example 2)

[0657] 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".

[0658] In today's educational environment, providing individualized learning methods is difficult because it is not tailored to the characteristics and emotional state of each student. Furthermore, there are challenges such as delays in appropriately adjusting learning content and providing feedback, making it difficult for educators to gain a detailed understanding of each student's developmental progress.

[0659] 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.

[0660] In this invention, the server includes means for analyzing the characteristics of a subject using a generative model, means for acquiring and analyzing the subject's emotional state in real time using an emotion analysis engine, and means for dynamically generating and providing personalized learning content based on the analysis results. This makes it possible to provide a learning environment optimized for the subject, thereby further enhancing educational effectiveness.

[0661] A "generative model" is an artificial intelligence technology that generates specific outputs based on input data, and is used to analyze the characteristics and behavioral patterns of subjects.

[0662] The "emotion analysis engine" is a technology that analyzes the emotional state of a subject from their facial expressions, tone of voice, etc., and plays a role in evaluating their psychological state in real time and reflecting that in the learning content.

[0663] "Subject characteristics" refer to data that shows each learner's learning style and cognitive patterns, and serve as fundamental information for individualized learning.

[0664] "Individualized learning content" refers to educational tasks and materials that are dynamically adjusted based on the characteristics and emotional state of the subject, providing an optimal learning experience.

[0665] "Feedback" refers to information collected from subjects regarding their responses and results to tasks they have undertaken, and used to make improvements and adjustments.

[0666] "Developmental data" refers to data that shows changes in a subject's learning and emotions, and is used for formulating and measuring the effectiveness of ongoing educational plans.

[0667] This invention, as an educational support system, consists of a server, a terminal, and a user. The server collects basic data, learning history, and past behavioral data of the subject, and uses a generative AI model to analyze the subject's characteristics based on this data. Specifically, it uses a database management system to collect and manage data, and the generative AI model functions as an inference engine.

[0668] Subsequently, the server analyzes real-time emotional data acquired from the device's camera and microphone through an emotion analysis engine. By using facial recognition software and voice tone analysis algorithms, it is possible to evaluate the user's stress level and concentration level.

[0669] Based on these analysis results, the device dynamically generates and presents personalized learning content to the user. For example, if a user experiences stress while solving a math problem, the device can offer simple games or practice problems to help them relax.

[0670] Users engage in personalized tasks via their devices, and throughout this process, an emotion analysis engine continuously collects and sends emotional data to the server. This provides immediate feedback and optimizes the user's learning process. For example, encouraging comments are displayed on the device based on the user's reading pace and level of understanding.

[0671] The server uses feedback information from the terminal and accumulated emotional data to store the subject's developmental data in a database. This allows teachers to understand the subject's learning progress and emotional changes through detailed reports and adjust the instruction plan as needed.

[0672] As a concrete example, the server could input the prompt "Please create a math problem for elementary school students. Include suggestions for relaxation activities to provide if the student is feeling stressed." into a generating AI model to create a task optimized for the subject. This process further enhances the system's dynamic adaptive capabilities.

[0673] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0674] Step 1:

[0675] The server collects basic data, learning history, and past behavioral data about the subjects. It receives data sets from the learning management system as input and stores them in a centralized database. Data processing mainly involves integration and imputation of missing values, resulting in a formatted dataset as output.

[0676] Step 2:

[0677] The server runs a generative AI model using a formatted dataset to analyze the characteristics of the subjects. It uses the subjects' historical data as input and prompts the generative model to perform characteristic analysis. During this process, the subjects' learning styles and cognitive characteristics are identified, and the analysis results are output.

[0678] Step 3:

[0679] The server receives data collected in real time from the terminal's camera and microphone, and analyzes the subject's emotions using an emotion analysis engine. Audio and video data are used as input, and the emotional state is calculated based on voice tone and facial expressions. The analysis results are output as data indicating the subject's current emotional state.

[0680] Step 4:

[0681] The device receives analyzed characteristic data and emotional state data from the server and generates personalized learning content. Using the analyzed and emotional data from the server as input, it dynamically creates appropriately customized tasks and learning materials based on the generated AI model. The generated learning content is then output to the user.

[0682] Step 5:

[0683] The user works on personalized learning tasks presented by the device. Learning content is provided from the device as input, and the user responds to it. The user's actions are sent to the server as feedback, and learning progress and task completion status are output.

[0684] Step 6:

[0685] The server stores feedback information and continuously collected emotional data in a database. It uses feedback and emotional data from the terminals as input, and performs analysis and storage processing. Finally, it outputs reports on the subjects' developmental data and emotional changes in a format accessible to teachers.

[0686] (Application Example 2)

[0687] 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".

[0688] In recent years, the importance of individualized education tailored to the unique personalities and emotions of each learner has been increasingly recognized in educational settings. However, existing educational systems have had limitations in responding to learners' real-time emotional states and characteristics. Furthermore, there are challenges in providing optimal learning environments due to insufficient feedback based on learning progress and inadequate efforts to boost motivation.

[0689] 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.

[0690] In this invention, the server includes means for analyzing the characteristics of individual subjects using a generative model, means for generating and dynamically adjusting personalized learning content based on emotional states obtained in real time, and means for recognizing the emotional states of subjects using a speech recognition device and an image acquisition device. This enables the provision of immediate feedback that reflects the learner's emotional state, thereby realizing an optimized learning environment.

[0691] A "generative model" is an information processing technique used to analyze the characteristics of subjects, and is a model used to analyze patterns and trends in data.

[0692] "Individualized learning content" refers to learning content designed to provide each learner with the most suitable learning tasks and materials, taking into account the characteristics of the subject and their real-time emotional state.

[0693] A "dynamic adjustment mechanism" is a function that can change the learning content provided according to the subject's emotional state and learning progress.

[0694] A "speech recognition device" is a hardware and software technology that analyzes a subject's voice and detects its content and emotional state.

[0695] An "image acquisition device" refers to a camera and related technologies used to acquire and analyze a subject's facial expressions and other visual data.

[0696] "Means for recognizing emotional states" refers to technologies that have the function of detecting emotions from a subject's facial expressions and voice and analyzing them in real time.

[0697] "Providing immediate feedback" is a feature that allows participants to receive real-time feedback on their progress and areas for improvement as they learn.

[0698] An "optimized learning environment" is an environment designed based on the characteristics and emotional state of the subject, which promotes effective and efficient learning for the learner.

[0699] This invention is a system that supports individualized education based on the characteristics and emotional state of the subject. Details are described below.

[0700] The server has the capability to analyze the characteristics of the subject using generative models and emotion engine software. Based on basic data, learning history, and behavioral data obtained from the subject, the server extracts the learner's characteristics through a generative AI model. Emotional data is acquired in real time using the device's camera and microphone, through analysis of facial expressions and voice tone. This allows for a comprehensive examination of factors that influence the subject's learning progress.

[0701] The device is equipped with a function that dynamically adjusts the user's learning content. Based on analyzed characteristics and emotional data, the device presents personalized learning materials. For example, if the user is feeling stressed, it will suggest activities that promote relaxation. This creates an optimal learning environment for the learner.

[0702] Users are continuously monitored by an emotion engine as they work on assigned tasks and activities. Immediate feedback is provided during or after tasks, and all of the user's emotional data is stored on the server. This allows the user's developmental data to be stored in a database, providing teachers with detailed reports through a dashboard and information to adjust teaching strategies.

[0703] For example, if a third-grade elementary school student is studying math at home and their facial expression shows signs of stress, the robot could suggest, "How about taking a 15-minute music break together?" An example of a prompt to input into the generative AI model could be, "A third-grade elementary school student is feeling stressed because they can't solve a math problem. Are there any more effective ways to motivate them?"

[0704] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0705] Step 1: The server acquires basic data, past learning history, and behavioral data about the subject. This data is supplied as input to the generating AI model to analyze the subject's characteristics. As a result of the analysis, characteristic data showing learning patterns and the learner's strengths and weaknesses is output.

[0706] Step 2: The server inputs real-time facial expression data and voice tone data of the subject, acquired via the device's camera and microphone, into the emotion engine. Based on this data, the current emotional state is analyzed, and emotional state data such as stress level and concentration level is output.

[0707] Step 3: The device receives trait and emotional state data transmitted from the server and generates personalized learning content based on it. This learning content is optimized for the subject and may include relaxation activities to reduce stress or tasks to improve concentration. The generated learning content is displayed on the device's screen.

[0708] Step 4: The user (learner) engages with the presented learning content. Throughout the learning process, the emotion engine continuously monitors the user's facial expressions and voice in real time and transmits this data to the server as emotion data. This data indicates the user's emotional changes during the learning process.

[0709] Step 5: Once the user's learning activity is complete, the server generates sentiment data and feedback on learning outcomes, which are provided to the user via the terminal. The feedback evaluates the user's learning progress and outcomes, and includes advice on areas for improvement and next steps.

[0710] Step 6: The server collects all feedback information and sentiment data and stores it in a database. This data is output as a report that teachers can view through a dashboard, and teachers can use it to adjust their teaching strategies for learners.

[0711] 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.

[0712] 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 those described above. 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 shown 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.

[0713] 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.

[0714] 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.

[0715] 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.

[0716] 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.

[0717] 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.

[0718] 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.

[0719] 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."

[0720] 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.

[0721] 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.

[0722] 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.

[0723] 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.

[0724] 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.

[0725] 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.

[0726] 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.

[0727] 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.

[0728] 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.

[0729] 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.

[0730] 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.

[0731] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0732] The following is further disclosed regarding the embodiments described above.

[0733] (Claim 1)

[0734] A means of analyzing the characteristics of individual subjects using a generative model,

[0735] Means for generating personalized learning content based on the characteristics,

[0736] Means for providing feedback on the learning content,

[0737] A means for accumulating and analyzing developmental data obtained through the feedback,

[0738] A means of providing educators with insights from the developmental data,

[0739] A system that includes this.

[0740] (Claim 2)

[0741] The system according to claim 1, characterized in that the analysis of the aforementioned characteristics includes past performance data and behavioral data.

[0742] (Claim 3)

[0743] The system according to claim 1, characterized in that the learning content includes tasks designed to enhance the social skills of the subjects.

[0744] "Example 1"

[0745] (Claim 1)

[0746] A means of analyzing the characteristics of individual learners using generative models,

[0747] A means for generating personalized learning content based on the said characteristics,

[0748] A means for providing and recording feedback on the learning content,

[0749] Means for accumulating and analyzing growth data obtained through the feedback,

[0750] A means of providing insights to educators from the growth data,

[0751] A learning support system that includes this.

[0752] (Claim 2)

[0753] The learning support system according to claim 1, characterized in that the analysis of the aforementioned characteristics includes historical data and behavioral data.

[0754] (Claim 3)

[0755] The learning support system according to claim 1, characterized in that the learning content includes activities to enhance the learner's communication skills.

[0756] "Application Example 1"

[0757] (Claim 1)

[0758] A means of individually evaluating people's abilities using generative models,

[0759] Means for generating personalized self-development programs based on said ability,

[0760] Means for providing progress information for the program,

[0761] A means for accumulating and analyzing growth data obtained based on the progress information,

[0762] A means of providing leaders with insights from the growth data,

[0763] A system that includes this.

[0764] (Claim 2)

[0765] The system according to claim 1, characterized in that the evaluation of the aforementioned capabilities includes past business data and behavioral patterns.

[0766] (Claim 3)

[0767] The system according to claim 1, characterized in that the self-development program includes activities to improve a person's social adaptability.

[0768] "Example 2 of combining an emotion engine"

[0769] (Claim 1)

[0770] A means of analyzing the characteristics of subjects using a generative model,

[0771] A means of acquiring and analyzing the emotional state of a subject in real time using an emotion analysis engine,

[0772] A means for dynamically generating and providing personalized learning content based on analysis results,

[0773] A means of collecting user reactions to learning content as feedback, and accumulating and analyzing that feedback,

[0774] A means of providing educators with developmental information obtained from the aforementioned feedback and emotional data,

[0775] A system that includes this.

[0776] (Claim 2)

[0777] The system according to claim 1, characterized in that the characteristic analysis uses past learning history and behavioral data, and the emotion analysis is performed based on facial expressions and tone of voice.

[0778] (Claim 3)

[0779] The system according to claim 1, characterized in that the learning content includes dynamic tasks aimed at developing the cognitive and non-cognitive abilities of the subjects.

[0780] "Application example 2 when combining with an emotional engine"

[0781] (Claim 1)

[0782] A means of analyzing the characteristics of individual subjects using a generative model,

[0783] A means for generating and dynamically adjusting personalized learning content based on the characteristics and emotional states obtained in real time,

[0784] A means for recognizing the emotional state of a subject using a speech recognition device and an image acquisition device,

[0785] A means of providing immediate feedback while reflecting the subject's emotional changes in the learning content,

[0786] A means for accumulating developmental data obtained from such feedback and emotional data, and for providing educators with insights from such developmental data through detailed reports,

[0787] A system that includes this.

[0788] (Claim 2)

[0789] The system according to claim 1, characterized in that, in addition to the analysis of the aforementioned characteristics, it includes real-time emotion data obtained by analyzing voice and facial expressions.

[0790] (Claim 3)

[0791] The system according to claim 1, characterized in that the learning content includes activities to reduce stress and increase motivation, taking into account the emotional state of the subject. [Explanation of symbols]

[0792] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of individually evaluating people's abilities using generative models, Means for generating personalized self-development programs based on said ability, Means for providing progress information for the program, A means for accumulating and analyzing growth data obtained based on the progress information, A means of providing leaders with insights from the growth data, A system that includes this.

2. The system according to claim 1, characterized in that the evaluation of the aforementioned capabilities includes past work data and behavioral patterns.

3. The system according to claim 1, characterized in that the self-development program includes activities to improve a person's social adaptability.

Images