system

Abstract

We provide the system. [Solution] A means of analyzing learners' abilities based on user information, A means for generating adaptive educational content based on the aforementioned learner ability analysis, A means for generating answers to questions from learners based on the aforementioned generated educational content, A means for generating an appropriate review schedule based on the learner's learning progress, A means for detecting the learner's pronunciation via a voice control component and providing real-time feedback, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional educational systems, since the individual abilities and comprehension levels of learners are not fully considered, the learning effects are not uniform, and some learners may have insufficient understanding. Also, it is difficult to provide the appropriate timing for review for learners, and it is difficult to memorize the learning content in the long term. Therefore, there is a need for an educational system that can effectively and efficiently fix knowledge while accommodating individual learning needs.

Means for Solving the Problems

[0005] This invention solves this problem by analyzing learners' abilities based on user information and generating adaptive educational content based on the analysis results. Furthermore, the generated educational content is provided in various media formats, including text, images, and videos, to deepen learners' understanding. In addition, it has a function to generate appropriate answers to learners' questions and resolve their doubts. Moreover, it supports the long-term retention of learned content by generating a review schedule tailored to each individual learner based on a curve that optimizes memory retention. This makes it possible to provide effective learning support optimized for each individual learner.

[0006] "User information" refers to information about learners, such as personal data, learning history, and ability level.

[0007] "Learner competency analysis" refers to the process of evaluating a learner's current knowledge and skills based on user information, and determining their level of understanding and potential for further development.

[0008] "Adaptive educational content" refers to learning materials and assignments that are optimized for individual learners based on the results of an analysis of their abilities.

[0009] "Media format" refers to the diverse forms of expression, such as text, images, and videos, used as means of conveying learning content.

[0010] "Generating answers to questions" refers to the process of receiving questions from learners and providing appropriate information and explanations in response.

[0011] A "review schedule" refers to the time and frequency of review sessions planned to effectively reinforce what learners have acquired.

[0012] The "curve for optimizing memory retention" refers to a model, similar to Ebbinghaus's forgetting curve, that guides users on the most effective timing for review, based on theories and research regarding human memory retention. [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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] 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, etc.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[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] The present invention is implemented as a system that provides adaptive educational content for each learner. This system mainly consists of server, terminal, and user interaction, and its specific embodiments are described below.

[0035] The server first stores the learner's user information, obtained via the terminal, in a database. This user information includes the learner's age, past learning history, and test results. The server analyzes this information to evaluate the learner's abilities. Natural language processing techniques and machine learning algorithms can be used for ability evaluation.

[0036] Next, the server automatically generates educational content optimized for the learner based on the evaluation results. This educational content is presented in various media formats, including text, images, and videos, to accommodate different learning styles. The generated materials are then delivered to the learner via their device.

[0037] Users can learn at their own pace using their devices. During learning, users can input questions into their devices. The devices send the questions to the server, which uses AI to generate appropriate answers. The generated answers, along with supplementary materials as needed, are returned to the devices and presented to the user.

[0038] Furthermore, the server constantly monitors the learner's progress and develops an optimal review schedule based on factors such as Ebbinghaus's forgetting curve. The terminal notifies the user of this schedule, thereby supporting long-term retention of the learned material.

[0039] As a concrete example, consider a scenario where a user studies history on their device. The server prepares appropriate reading materials and video resources related to history based on information obtained from the user's past learning history. In response to questions posed by the user, the AI ​​provides real-time explanations of the historical background and related events, promoting a deeper understanding.

[0040] Thus, the present invention enables efficient learning tailored to individual learning needs and helps learners retain their knowledge.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The user starts up the device and logs into the learning application. The device sends the user's login information to the server and requests authentication.

[0044] Step 2:

[0045] The server compares the received login information with the database to authenticate the user. If authentication is successful, it retrieves the user's user information and sends the authentication result back to the terminal.

[0046] Step 3:

[0047] The user selects the subjects or topics they want to learn through their device. The device then sends the selection information to the server.

[0048] Step 4:

[0049] The server analyzes the learner's abilities based on user information and selection information, and generates adaptive educational content. The generated content is available in various media formats, including text, images, and videos.

[0050] Step 5:

[0051] The server generates educational content and sends it to the terminal. The terminal visually displays the received content to the user and initiates learning.

[0052] Step 6:

[0053] As the user progresses through the learning process, they can input any questions or doubts into their device. The device then sends the question to the server.

[0054] Step 7:

[0055] The server receives questions from users and uses generative AI to generate appropriate answers. The answers include additional information as needed.

[0056] Step 8:

[0057] The server sends the generated answer to the terminal. The terminal displays the received answer to the user, resolving their question.

[0058] Step 9:

[0059] The server monitors the user's learning progress and creates a review schedule based on Ebbinghaus's forgetting curve. The created schedule is then sent to the user's device.

[0060] Step 10:

[0061] The terminal notifies the user of the review schedule received from the server. The user then reviews according to this schedule.

[0062] (Example 1)

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

[0064] In the education industry, providing educational content tailored to each individual learner is crucial, but a fixed curriculum faces the challenge of failing to address individual learning needs. Furthermore, it is difficult to respond quickly and accurately to learners' questions and to appropriately present review plans that match their learning progress. There is also a need to provide diverse media formats that suit the preferences and learning styles of individual learners.

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

[0066] In this invention, the server includes means for evaluating learners' abilities based on user information, means for generating adaptive educational resources based on the learners' ability evaluation, and means for generating responses to learners' inquiries based on the generated educational resources. This makes it possible to provide customized educational content that meets the individual needs of each learner, thereby realizing more effective learning support.

[0067] "User information" refers to information related to each individual learner, such as their age, learning history, and test results.

[0068] "Competency assessment" is the process of analyzing and evaluating the skill and knowledge levels of learners, either quantitatively or qualitatively.

[0069] "Educational resources" refer to the educational content provided to learners, and include various formats such as text, still images, and videos.

[0070] "Inquiries" refer to questions or doubts that arise during the learning process, and their purpose is to deepen the learner's understanding of the material.

[0071] A "review plan" is a schedule outlining the timing and content of reviews, designed to help learners retain previously learned material in their long-term memory.

[0072] Artificial intelligence is a type of technology in which computers imitate human intellectual activity, using data and algorithms to learn and reason.

[0073] "Media format" refers to the form in which information is presented visually or audibly, and includes text, still images, and moving images.

[0074] This system is built around server, terminal, and user interaction to provide adaptive educational resources tailored to each learner. The server retrieves learner user information via the terminal and stores it in a database. The stored information is analyzed using the Python library scikit-learn to assess the learner's abilities.

[0075] The server generates adaptive educational resources based on the evaluation results. In this process, it utilizes a generative AI model to automatically generate content optimized for the learner using prompts. For example, the prompt "Generate the most suitable educational content on history based on the user's learning history" is input to the AI ​​model, providing customized educational content.

[0076] Educational resources are provided in diverse media formats, including text, still images, and videos, accommodating different learning styles. The generated resources are delivered to learners via their devices, allowing users to learn at their own pace.

[0077] Furthermore, when a user enters a question during learning, the device sends it to the server. The server uses artificial intelligence technology to generate an appropriate response to the question and returns it to the device. This allows the user to progress through the learning process while resolving their questions.

[0078] Furthermore, the server monitors the learner's progress and creates an optimal review plan based on Ebbinghaus's forgetting curve and other factors. The terminal notifies the user of this plan, thereby supporting long-term retention of the learned material.

[0079] As a concrete example, when a user is learning history, the server prepares appropriate resources related to history based on user information and provides the user with information in real time. In this way, the present invention realizes effective learning tailored to the needs of each learner.

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

[0081] Step 1:

[0082] The server obtains user information from learners via the terminal. This information includes the learner's age, past learning history, and test results. The server stores this data in a database. The input at this stage is the learner's personal information, and the output is database storage. Specifically, the user enters information into an input form on the terminal, and the terminal sends this information to the server.

[0083] Step 2:

[0084] The server analyzes stored user information and evaluates the learner's abilities. Here, the scikit-learn library in Python is used to process the data and identify the learner's strengths and weaknesses. The input is user information stored in the database, and the output is the evaluation result. Specifically, the server executes a process of analyzing the data by applying a particular algorithm.

[0085] Step 3:

[0086] The server generates adaptive educational resources based on the evaluation results. This process utilizes a generative AI model and uses prompts to generate appropriate educational content. The input is the evaluation results, and the output is the generated educational resources. Specifically, the server sends a prompt to the AI ​​model such as "Generate the best educational content on history," and retrieves the generated text and materials.

[0087] Step 4:

[0088] The server delivers the generated educational resources to the terminal. The terminal receives these resources, and the user uses the terminal to proceed with their learning. The input is the generated educational resources, and the output is the data delivery to the terminal. In specific operations, the terminal downloads the educational content, and the user views it on the screen.

[0089] Step 5:

[0090] When a user enters a question during training, the device sends it to the server. The server uses artificial intelligence technology to generate an appropriate response to the question and returns it to the device. The input is the question from the user, and the output is the generated response. Specifically, the device sends question data to the server, the server analyzes it, and then returns a response in text.

[0091] Step 6:

[0092] The server monitors the learner's progress and creates an optimal review plan based on Ebbinghaus's forgetting curve. The terminal notifies the user of this plan. The input is learning history data, and the output is the review plan. Specifically, the server analyzes progress data, calculates the optimal review timing, and sends a notification to the terminal.

[0093] (Application Example 1)

[0094] 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."

[0095] Traditional education systems struggle to provide personalized feedback to each learner, particularly lacking real-time feedback on pronunciation and physical expression. This results in insufficient learning efficiency and challenges in retaining learners' skills and knowledge.

[0096] 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.

[0097] In this invention, the server includes means for analyzing the learner's abilities based on user information, means for generating adaptive educational content, means for generating an appropriate review schedule based on the learner's learning progress, and means for detecting the learner's pronunciation via a voice control member and providing real-time feedback. This makes it possible to provide individually customized educational content to learners and promote skill improvement through real-time voice feedback.

[0098] "User information" refers to data about learners, such as age, past learning history, and test results, and is basic information for analyzing an individual's learning ability and characteristics.

[0099] "Learner ability analysis" is a process of evaluating a learner's learning ability and characteristics based on their learning history and user information.

[0100] "Adaptive educational content" refers to teaching materials and learning programs that are optimized based on the results of an analysis of each learner's abilities, and are provided in a variety of media formats.

[0101] A "review schedule" is a plan designed to manage the time and frequency of review sessions, optimized for learners' memory retention.

[0102] A "voice control component" is hardware or software that has the function of detecting and analyzing the learner's voice and providing real-time feedback based on that analysis.

[0103] "Real-time feedback" refers to the ability to respond immediately to a learner's pronunciation and behavior, and to provide immediate feedback and evaluations on areas for improvement.

[0104] The system implementing this invention consists of a server, a terminal, and user interaction. The server is the main data processing center and analyzes the learner's abilities based on user information. The database stores the learner's age, past learning history, test results, etc., and uses natural language processing technology and machine learning algorithms to evaluate abilities based on this data.

[0105] Subsequently, the server generates educational content in adaptive and diverse media formats based on the evaluation results and provides it to learners through their devices. The devices receive the educational content, allowing users to learn at their own pace. During learning, when a user enters a question into the device, the server uses a generative AI model to generate an appropriate answer, and returns supplementary materials to the device as needed.

[0106] Furthermore, the server constantly monitors the learner's progress and develops a schedule that takes review into account to optimize memory retention. This schedule is notified to the user via their device, supporting the long-term retention of the learned material.

[0107] The voice control component in this system detects the user's pronunciation in real time and provides immediate feedback. This allows the user to improve their pronunciation and accuracy. For example, when a learner asks "What is the French Revolution?", the prompt "The user wants to know about the background and impact of the French Revolution. Please provide a concise explanation of this historical topic." is used, and the AI ​​provides a detailed historical explanation.

[0108] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0109] Step 1:

[0110] The server collects user information via the terminal. Inputs include the learner's age, past learning history, and test results, which are then stored in a database. Data processing involves organizing the information as structured data and optimizing it for future analysis.

[0111] Step 2:

[0112] The server analyzes learners' abilities using the collected information. Using learner information stored in a database as input, and applying natural language processing techniques and machine learning algorithms, it generates ability assessment results as output.

[0113] Step 3:

[0114] The server generates adaptive educational content based on the assessment results. The input is the competency assessment results, which are converted into plain text, image, and video formats for output. Personalized content generation algorithms are used for data processing.

[0115] Step 4:

[0116] The terminal receives educational content sent from the server and presents it to the user. The input is educational content from the server, and the output is provided to the user as visual and audio information on the screen. The operation involves displaying the learning content in an appropriate media format.

[0117] Step 5:

[0118] When a user enters a question into the terminal, that question is sent to the server. The input is a text question from the user, and preprocessing is performed to pass the prompt text to the AI ​​model, which then sends its output to the server.

[0119] Step 6:

[0120] The server uses a generation AI model to generate answers to questions. The input is the user's question, and a prompt based on that question is sent to the generation AI model, which then outputs a specific answer.

[0121] Step 7:

[0122] The device that receives the response will present the answer to the user, along with supplementary materials as needed. The input is the response from the server, and the output provides the response in visual and audio formats.

[0123] Step 8:

[0124] The server monitors the learner's learning progress. It receives learning history information sent from the terminal as input, calculates an optimal review schedule based on Ebbinghaus's forgetting curve, and generates the schedule as output.

[0125] Step 9:

[0126] The terminal notifies the user of the generated review schedule. The input is the schedule provided by the server, and the output is a notification message displayed to the user.

[0127] Step 10:

[0128] The voice control component detects the user's pronunciation in real time and provides immediate feedback based on that data. The input is voice data, and the feedback is output based on voice analysis.

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

[0130] This invention provides a system that offers learners an individualized learning experience, aiming to more appropriately adjust educational content using emotion recognition. This system mainly consists of a server, terminals, an emotion engine, and user interaction.

[0131] The server analyzes learners' abilities based on user information obtained through their terminals. This user information includes not only learning history and test results, but also sentiment data acquired in real time. The server analyzes this information to generate personalized educational content.

[0132] The emotion engine analyzes the user's visual or auditory data to recognize their emotional state in real time. This allows the server to determine how learners are feeling about the learning materials and adjust the educational content as needed. For example, if a user is feeling frustrated with difficult content, the system can sense this and provide simpler explanations or additional hints.

[0133] As users progress through their learning using their devices, the emotion engine continuously monitors their emotions and detects any changes. Based on this, the server readjusts the educational content and delivers new content to the device. Furthermore, the review schedule is flexibly adjusted according to the learner's emotions, maximizing learning efficiency.

[0134] As a concrete example, consider a scenario where a user is tackling a difficult mathematical problem. The device uses the user's camera and microphone to record their facial expressions and tone of voice, and an emotion engine identifies the user's anxiety or confusion. As a result, the server generates new educational content in the form of step-by-step explanations of the problem or similar problems, and provides it in an easy-to-understand format for the learner.

[0135] Thus, by using emotion recognition technology, the present invention provides adaptive educational services that take into account the learner's psychological state, thereby deepening the learner's understanding and creating an environment where learning can proceed smoothly.

[0136] The following describes the processing flow.

[0137] Step 1:

[0138] The user starts up the device and logs into the learning application. The device receives the user's authentication information as input and sends it to the server.

[0139] Step 2:

[0140] The server verifies the login information against the database to authenticate the user. If authentication is successful, it retrieves the user information and past learning history and sends them to the terminal.

[0141] Step 3:

[0142] The user selects the subjects or topics they wish to study through their device. The device then sends this selection information to the server, communicating the user's preferences.

[0143] Step 4:

[0144] The server analyzes the learner's abilities based on user information and topic selection. Based on the analysis results, the server generates educational content in text, image, and video formats.

[0145] Step 5:

[0146] The device's built-in emotion engine uses the built-in camera and microphone to record the user's facial expressions and voice tone in real time.

[0147] Step 6:

[0148] The emotion engine analyzes the collected data to recognize the user's current emotional state. The recognized emotional data is then sent to the server.

[0149] Step 7:

[0150] The server receives emotional data and adjusts the educational content based on the user's psychological state. For example, if it determines that the user is confused, it generates educational content that includes more detailed explanations and hints.

[0151] Step 8:

[0152] The server sends the adjusted educational content to the device. The device displays the updated content to the user, supporting their learning.

[0153] Step 9:

[0154] If a user's understanding or emotional state does not improve as they progress through the learning process, the emotion engine continues to monitor the user's state and sends new emotional data to the server.

[0155] Step 10:

[0156] The server continues to adjust the educational content based on sentiment data and changes the review schedule as needed. The terminal notifies the user of these changes and provides an optimal learning environment.

[0157] (Example 2)

[0158] 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".

[0159] Traditional education systems have struggled to provide appropriate educational content tailored to learners' abilities and emotional states, sometimes leading to decreased learning efficiency. Furthermore, insufficient optimization of review schedules to consider learners' emotions resulted in underutilized learning outcomes.

[0160] 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.

[0161] In this invention, the server includes means for analyzing a learner's abilities based on user information, means for generating personalized educational content based on the learner's ability analysis and emotional data, and an emotion analysis device for recognizing the learner's emotional state in real time. This enables the provision of educational content adapted to each learner's abilities and emotional state, thereby improving learning efficiency and maximizing results.

[0162] "User information" is a general term for data that includes learners' learning history, test results, and real-time sentiment data.

[0163] "Learner's competence" refers to the level of knowledge and skills a learner possesses, and it is the fundamental information upon which adaptive educational content is generated.

[0164] "Emotional data" refers to information that indicates a learner's emotional state, and is acquired through visual or auditory methods.

[0165] "Individualized educational content" refers to learning materials that are tailored based on learners' ability and emotional data, and are provided in a way that is optimized for each individual learner.

[0166] An "emotion analysis device" is a device that detects and analyzes changes in a learner's emotions in real time, based on their visual and auditory perceptions.

[0167] A "review schedule" is a flexible plan for reviewing learned material, generated based on the learner's learning progress and emotional information.

[0168] This invention is a system that adaptively provides educational content based on the learner's emotional state and personal abilities. The entire system consists of a server, terminals, an emotion analysis device, and user interaction.

[0169] The server aggregates information from users through terminals and analyzes learners' ability and emotional data. This includes data processing using generative AI models, which process learning history and real-time emotional data. Based on the analyzed information, the server generates personalized educational content and sends that content to the terminal.

[0170] The emotion analysis device receives visual or auditory data from the user as input and analyzes their emotional state in real time. This device uses data obtained from the user's camera and microphone to analyze facial expressions and voice tone, thereby evaluating the learner's psychological state.

[0171] Users use a device to receive personalized educational content provided by the server and proceed with their learning. The device continuously monitors the user's learning progress and emotional changes, and sends the collected data to the server. This server-side process dynamically adjusts the educational content and presents it in a way that is easy for the learner to understand.

[0172] As a concrete example, when a user is learning a new mathematical concept, if the device's emotion analysis device detects that the user's facial expression indicates confusion, it will use a generative AI model to generate additional hints or video tutorials about that concept and present them to the user.

[0173] An example of a prompt might be: "If a user indicates that they are having difficulty understanding a new mathematical concept, explain how you will generate personalized educational content based on their sentiment data and past learning history."

[0174] This system enables learners to progress through their studies more smoothly and deepen their understanding, providing an effective educational environment.

[0175] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0176] Step 1:

[0177] The user activates the device and starts a learning session. The device collects the user's learning history, current learning progress, and emotional data as input. It uses the camera and microphone to acquire real-time facial expression and voice tone data and sends it to the server. Specifically, it performs facial recognition and voice analysis of the user and formats it as digital data.

[0178] Step 2:

[0179] The server analyzes the input data received from the terminal. It integrates learning history, progress, and collected sentiment data, and analyzes this information using a generative AI model. Data processing includes evaluating past learning performance and detecting real-time changes in sentiment. The output is an assessment of the learner's abilities and emotional state.

[0180] Step 3:

[0181] The server generates personalized educational content based on the analysis results. Inputs include ability and emotion assessments. A generative AI model is used to select or generate adaptive learning materials. Specific actions include selecting relevant text, image, and video resources. The output is personalized educational content.

[0182] Step 4:

[0183] The terminal delivers educational content sent from the server to the user. During this process, the terminal continuously monitors the user's reactions and records new emotional states. This is done in real time using an emotion analysis device, leading to highly effective understanding enhancement. The output consists of new learner feedback and emotional data.

[0184] Step 5:

[0185] The server further refines the educational content based on feedback and sentiment data from the device. It utilizes the information received as input to improve the content again using a generative AI model, and updates it as needed. For example, if a learner finds a particular unit difficult to understand, it might add more detailed explanations or practice problems. The output is the updated educational content.

[0186] This processing flow provides learners with an adaptive and effective educational experience.

[0187] (Application Example 2)

[0188] 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".

[0189] To enhance the learning effectiveness of educators, it is necessary to consider the psychological state of each learner and provide appropriate teaching materials and environmental adjustments. However, the current education system sometimes fails to adequately consider the emotional state of learners, and the provision of fixed teaching materials can lead to decreased learning efficiency. Furthermore, there are cases where care tailored to the emotional needs of those receiving care is insufficient, and solutions to this problem are needed.

[0190] 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.

[0191] In this invention, the server includes means for analyzing the abilities of the person being educated based on user information, means for acquiring emotional data and recognizing the emotional state of the person being educated in real time, and means for generating adaptive and emotionally responsive educational content based on the analysis of the person being educated. This makes it possible to provide educational content that is tailored to the emotional state of each individual learner, and to realize appropriate care based on the psychological state of the person being cared for.

[0192] "User information" refers to all data concerning the student, and specifically includes learning history, test results, and sentiment data acquired in real time.

[0193] "The learner's ability" refers to the level of knowledge and skills possessed by the learner, and is analyzed based on user information.

[0194] "Adaptive educational content" refers to teaching materials and learning plans that are optimized according to the abilities and emotional state of the students.

[0195] "Emotional data" refers to information about the psychological state of the person being educated, analyzed based on visual or auditory information.

[0196] "Emotional state" refers to the psychological state of an educated person, obtained by analyzing emotional data, and includes emotions such as anxiety and happiness.

[0197] A "review schedule" is a plan for reviewing what has been learned at appropriate times, based on the learner's progress.

[0198] "Environmental settings" refer to the surrounding conditions that can be adjusted according to the emotional state of the person being educated, and specifically include elements such as music and lighting.

[0199] The system for realizing this invention mainly consists of a server, a terminal, and an emotion recognition engine. The server has the function of analyzing the learner's abilities based on user information and generating adaptive educational content. This ability analysis includes learning history, test results, and emotion data. Based on the analysis results, the server generates personalized educational content and delivers it to the terminal.

[0200] The device uses its camera and microphone to acquire visual and auditory information from the learner and transmits it to an emotion recognition engine. The emotion recognition engine analyzes this data and identifies the user's emotional state in real time. Based on this emotional state, the server readjusts the educational content and review schedule, providing the learner with the most effective educational content.

[0201] The emotion recognition engine can utilize software such as Microsoft's Emotion API, enabling advanced emotion recognition. By using hardware such as smart glasses, applications in the field of elderly care are also possible. For example, if a learner faces a difficult problem and experiences anxiety or stress, the emotion recognition engine can detect this, and the server can generate learning materials that include simpler explanations and additional support.

[0202] In addition, when a caregiver recognizes that the person being cared for is feeling restless, they adjust environmental settings such as music and lighting.

[0203] Example of a prompt:

[0204] "We're looking for ideas for a smart glasses app that uses emotion recognition technology to understand the emotions of the person receiving care in real time and suggest appropriate care methods."

[0205] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0206] Step 1:

[0207] The device uses a camera and microphone to acquire visual and auditory information from the student. Input is video and audio of the student's face, and output is data converted into an appropriate digital format for transmission to the server. Data acquisition and format conversion occur in real time.

[0208] Step 2:

[0209] The server receives visual and audio information transmitted from the terminal and inputs it into the emotion recognition engine. The input is digitized video and audio data, and the output is the analyzed emotional state. The emotion recognition engine uses image analysis and audio analysis algorithms to identify specific emotions (e.g., anxiety, concentration, excitement, etc.).

[0210] Step 3:

[0211] The server analyzes the learner's abilities by combining their emotional state with past learning history and test results, and generates adaptive educational content. Inputs are learning history, test results, and emotional states, and output is customized learning materials tailored to the learner's emotions and abilities. Data combination and computation are performed using database queries and machine learning algorithms.

[0212] Step 4:

[0213] The server delivers the generated educational content to the terminal, which then displays it to the learner. The input is customized learning materials, and the output is the educational content displayed on the terminal's screen. Data transmission and display are instantaneous, allowing learners to begin learning immediately.

[0214] Step 5:

[0215] The user (learner) progresses through the learning process via a terminal and inputs questions if necessary. The input is the learner's question, and the output is the answer generated by the server. The server extracts appropriate information from its accumulated knowledge database based on the question content and forms the answer.

[0216] Step 6:

[0217] The server continuously monitors the learner's emotional state and learning progress, and readjusts the review schedule as needed. Input is real-time emotional data and progress information, while output is an updated review schedule tailored to the learner's level of understanding. Data collection and schedule updates are performed through the progress management system.

[0218] 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.

[0219] 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 the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0220] 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.

[0221] [Second Embodiment]

[0222] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0223] 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.

[0224] 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).

[0225] 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.

[0226] 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.

[0227] 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).

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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".

[0234] The present invention is implemented as a system that provides adaptive educational content for each learner. This system mainly consists of server, terminal, and user interaction, and its specific embodiments are described below.

[0235] The server first stores the learner's user information, obtained via the terminal, in a database. This user information includes the learner's age, past learning history, and test results. The server analyzes this information to evaluate the learner's abilities. Natural language processing techniques and machine learning algorithms can be used for ability evaluation.

[0236] Next, the server automatically generates educational content optimized for the learner based on the evaluation results. This educational content is presented in various media formats, including text, images, and videos, to accommodate different learning styles. The generated materials are then delivered to the learner via their device.

[0237] Users can learn at their own pace using their devices. During learning, users can input questions into their devices. The devices send the questions to the server, which uses AI to generate appropriate answers. The generated answers, along with supplementary materials as needed, are returned to the devices and presented to the user.

[0238] Furthermore, the server constantly monitors the learner's progress and develops an optimal review schedule based on factors such as Ebbinghaus's forgetting curve. The terminal notifies the user of this schedule, thereby supporting long-term retention of the learned material.

[0239] As a concrete example, consider a scenario where a user studies history on their device. The server prepares appropriate reading materials and video resources related to history based on information obtained from the user's past learning history. In response to questions posed by the user, the AI ​​provides real-time explanations of the historical background and related events, promoting a deeper understanding.

[0240] Thus, the present invention enables efficient learning tailored to individual learning needs and helps learners retain their knowledge.

[0241] The following describes the processing flow.

[0242] Step 1:

[0243] The user starts up the device and logs into the learning application. The device sends the user's login information to the server and requests authentication.

[0244] Step 2:

[0245] The server compares the received login information with the database to authenticate the user. If authentication is successful, it retrieves the user's user information and sends the authentication result back to the terminal.

[0246] Step 3:

[0247] The user selects the subjects or topics they want to learn through their device. The device then sends the selection information to the server.

[0248] Step 4:

[0249] The server analyzes the learner's abilities based on user information and selection information, and generates adaptive educational content. The generated content is available in various media formats, including text, images, and videos.

[0250] Step 5:

[0251] The server generates educational content and sends it to the terminal. The terminal visually displays the received content to the user and initiates learning.

[0252] Step 6:

[0253] As the user progresses through the learning process, they can input any questions or doubts into their device. The device then sends the question to the server.

[0254] Step 7:

[0255] The server receives questions from users and uses generative AI to generate appropriate answers. The answers include additional information as needed.

[0256] Step 8:

[0257] The server sends the generated answer to the terminal. The terminal displays the received answer to the user, resolving their question.

[0258] Step 9:

[0259] The server monitors the user's learning progress and creates a review schedule based on Ebbinghaus's forgetting curve. The created schedule is then sent to the user's device.

[0260] Step 10:

[0261] The terminal notifies the user of the review schedule received from the server. The user then reviews according to this schedule.

[0262] (Example 1)

[0263] 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."

[0264] In the education industry, providing educational content tailored to each individual learner is crucial, but a fixed curriculum faces the challenge of failing to address individual learning needs. Furthermore, it is difficult to respond quickly and accurately to learners' questions and to appropriately present review plans that match their learning progress. There is also a need to provide diverse media formats that suit the preferences and learning styles of individual learners.

[0265] 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.

[0266] In this invention, the server includes means for evaluating learners' abilities based on user information, means for generating adaptive educational resources based on the learners' ability evaluation, and means for generating responses to learners' inquiries based on the generated educational resources. This makes it possible to provide customized educational content that meets the individual needs of each learner, thereby realizing more effective learning support.

[0267] "User information" refers to information related to each individual learner, such as their age, learning history, and test results.

[0268] "Competency assessment" is the process of analyzing and evaluating the skill and knowledge levels of learners, either quantitatively or qualitatively.

[0269] "Educational resources" refer to the educational content provided to learners, and include various formats such as text, still images, and videos.

[0270] "Inquiries" refer to questions or doubts that arise during the learning process, and their purpose is to deepen the learner's understanding of the material.

[0271] A "review plan" is a schedule outlining the timing and content of reviews, designed to help learners retain previously learned material in their long-term memory.

[0272] Artificial intelligence is a type of technology in which computers imitate human intellectual activity, using data and algorithms to learn and reason.

[0273] "Media format" refers to the form in which information is presented visually or audibly, and includes text, still images, and moving images.

[0274] This system is built around server, terminal, and user interaction to provide adaptive educational resources tailored to each learner. The server retrieves learner user information via the terminal and stores it in a database. The stored information is analyzed using the Python library scikit-learn to assess the learner's abilities.

[0275] The server generates adaptive educational resources based on the evaluation results. In this process, it utilizes a generative AI model to automatically generate content optimized for the learner using prompts. For example, the prompt "Generate the most suitable educational content on history based on the user's learning history" is input to the AI ​​model, providing customized educational content.

[0276] Educational resources are provided in diverse media formats, including text, still images, and videos, accommodating different learning styles. The generated resources are delivered to learners via their devices, allowing users to learn at their own pace.

[0277] Furthermore, when a user enters a question during learning, the device sends it to the server. The server uses artificial intelligence technology to generate an appropriate response to the question and returns it to the device. This allows the user to progress through the learning process while resolving their questions.

[0278] Furthermore, the server monitors the learner's progress and creates an optimal review plan based on Ebbinghaus's forgetting curve and other factors. The terminal notifies the user of this plan, thereby supporting long-term retention of the learned material.

[0279] As a concrete example, when a user is learning history, the server prepares appropriate resources related to history based on user information and provides the user with information in real time. In this way, the present invention realizes effective learning tailored to the needs of each learner.

[0280] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0281] Step 1:

[0282] The server obtains user information from learners via the terminal. This information includes the learner's age, past learning history, and test results. The server stores this data in a database. The input at this stage is the learner's personal information, and the output is database storage. Specifically, the user enters information into an input form on the terminal, and the terminal sends this information to the server.

[0283] Step 2:

[0284] The server analyzes the saved user information and evaluates the learner's capabilities. Here, the Python scikit-learn library is used to process the data and identify the learner's strong and weak areas. The input is the user information saved in the database, and the output is the evaluation result. As a specific operation, the server executes a process of analyzing the data by applying a specific algorithm.

[0285] Step 3:

[0286] Based on the evaluation result, the server generates adaptive educational resources. In this process, a generative AI model is utilized to generate appropriate educational content using prompt texts. The input is the evaluation result, and the output is the generated educational resources. As a specific operation, the server sends a prompt such as "Please generate the optimal educational content regarding history" to the AI model and obtains the generated text and materials.

[0287] Step 4:

[0288] The server distributes the generated educational resources to the terminal. The terminal receives this, and the user proceeds with learning using the terminal. The input is the generated educational resources, and the output is the data distribution to the terminal. In a specific operation, the terminal downloads the educational content, and the user browses it on the screen.

[0289] Step 5:

[0290] When the user inputs a question during learning, the terminal sends this to the server. The server uses artificial intelligence technology to generate an appropriate response to the question and returns it to the terminal. The input is the question from the user, and the output is the generated response. As a specific operation, the terminal sends the question data to the server, and the server analyzes it and then returns a text response.

[0291] Step 6:

[0292] The server monitors the learner's progress and creates an optimal review plan based on Ebbinghaus's forgetting curve. The terminal notifies the user of this plan. The input is learning history data, and the output is the review plan. Specifically, the server analyzes progress data, calculates the optimal review timing, and sends a notification to the terminal.

[0293] (Application Example 1)

[0294] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0295] Traditional education systems struggle to provide personalized feedback to each learner, particularly lacking real-time feedback on pronunciation and physical expression. This results in insufficient learning efficiency and challenges in retaining learners' skills and knowledge.

[0296] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0297] In this invention, the server includes means for analyzing the learner's abilities based on user information, means for generating adaptive educational content, means for generating an appropriate review schedule based on the learner's learning progress, and means for detecting the learner's pronunciation via a voice control member and providing real-time feedback. This makes it possible to provide individually customized educational content to learners and promote skill improvement through real-time voice feedback.

[0298] "User information" refers to data about learners, such as age, past learning history, and test results, and is basic information for analyzing an individual's learning ability and characteristics.

[0299] "Learner ability analysis" is a process of evaluating a learner's learning ability and characteristics based on their learning history and user information.

[0300] "Adaptive educational content" refers to teaching materials and learning programs that are optimized based on the results of an analysis of each learner's abilities, and are provided in a variety of media formats.

[0301] A "review schedule" is a plan designed to manage the time and frequency of review sessions, optimized for learners' memory retention.

[0302] A "voice control component" is hardware or software that has the function of detecting and analyzing the learner's voice and providing real-time feedback based on that analysis.

[0303] "Real-time feedback" refers to the ability to respond immediately to a learner's pronunciation and behavior, and to provide immediate feedback and evaluations on areas for improvement.

[0304] The system implementing this invention consists of a server, a terminal, and user interaction. The server is the main data processing center and analyzes the learner's abilities based on user information. The database stores the learner's age, past learning history, test results, etc., and uses natural language processing technology and machine learning algorithms to evaluate abilities based on this data.

[0305] Subsequently, the server generates educational content in adaptive and diverse media formats based on the evaluation results and provides it to learners through their devices. The devices receive the educational content, allowing users to learn at their own pace. During learning, when a user enters a question into the device, the server uses a generative AI model to generate an appropriate answer, and returns supplementary materials to the device as needed.

[0306] Furthermore, the server constantly monitors the learner's progress and develops a schedule that takes review into account to optimize memory retention. This schedule is notified to the user via their device, supporting the long-term retention of the learned material.

[0307] The voice control member in this system detects the user's pronunciation in real time and provides immediate feedback. As a result, the user can improve their pronunciation and accuracy. As a specific example, when a learner asks "What is the French Revolution?", the prompt sentence "The user wants to know about the background and impact of the French Revolution. Please provide a brief explanation about this historical theme." is used, and the AI provides a detailed historical explanation.

[0308] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0309] Step 1:

[0310] The server collects user information via the terminal. The inputs are the learner's age, past learning history, test results, etc., and these are saved in the database. As data processing, the information is organized as structured data and optimized for future analysis.

[0311] Step 2:

[0312] The server analyzes the learner's ability using the collected information. Using the learner information saved in the database as input and applying natural language processing technology and machine learning algorithms, an ability evaluation result is generated as output.

[0313] Step 3:

[0314] Based on the evaluation result, the server generates adaptive educational content. The input is the ability evaluation result, which is converted into the output in the form of plain text, images, and videos of educational content. In data calculation, a personalized content generation algorithm is used.

[0315] Step 4:

[0316] The terminal receives educational content sent from the server and presents it to the user. The input is educational content from the server, and the output is provided to the user as visual and audio information on the screen. The operation involves displaying the learning content in an appropriate media format.

[0317] Step 5:

[0318] When a user enters a question into the terminal, that question is sent to the server. The input is a text question from the user, and preprocessing is performed to pass the prompt text to the AI ​​model, which then sends its output to the server.

[0319] Step 6:

[0320] The server uses a generation AI model to generate answers to questions. The input is the user's question, and a prompt based on that question is sent to the generation AI model, which then outputs a specific answer.

[0321] Step 7:

[0322] The device that receives the response will present the answer to the user, along with supplementary materials as needed. The input is the response from the server, and the output provides the response in visual and audio formats.

[0323] Step 8:

[0324] The server monitors the learner's learning progress. It receives learning history information sent from the terminal as input, calculates an optimal review schedule based on Ebbinghaus's forgetting curve, and generates the schedule as output.

[0325] Step 9:

[0326] The terminal notifies the user of the generated review schedule. The input is the schedule provided by the server, and the output is a notification message displayed to the user.

[0327] Step 10:

[0328] The voice control component detects the user's pronunciation in real time and provides immediate feedback based on that data. The input is voice data, and the feedback is output based on voice analysis.

[0329] 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.

[0330] This invention provides a system that offers learners an individualized learning experience, aiming to more appropriately adjust educational content using emotion recognition. This system mainly consists of a server, terminals, an emotion engine, and user interaction.

[0331] The server analyzes learners' abilities based on user information obtained through their terminals. This user information includes not only learning history and test results, but also sentiment data acquired in real time. The server analyzes this information to generate personalized educational content.

[0332] The emotion engine analyzes the user's visual or auditory data to recognize their emotional state in real time. This allows the server to determine how learners are feeling about the learning materials and adjust the educational content as needed. For example, if a user is feeling frustrated with difficult content, the system can sense this and provide simpler explanations or additional hints.

[0333] As users progress through their learning using their devices, the emotion engine continuously monitors their emotions and detects any changes. Based on this, the server readjusts the educational content and delivers new content to the device. Furthermore, the review schedule is flexibly adjusted according to the learner's emotions, maximizing learning efficiency.

[0334] As a concrete example, consider a scenario where a user is tackling a difficult mathematical problem. The device uses the user's camera and microphone to record their facial expressions and tone of voice, and an emotion engine identifies the user's anxiety or confusion. As a result, the server generates new educational content in the form of step-by-step explanations of the problem or similar problems, and provides it in an easy-to-understand format for the learner.

[0335] Thus, by using emotion recognition technology, the present invention provides adaptive educational services that take into account the learner's psychological state, thereby deepening the learner's understanding and creating an environment where learning can proceed smoothly.

[0336] The following describes the processing flow.

[0337] Step 1:

[0338] The user starts up the device and logs into the learning application. The device receives the user's authentication information as input and sends it to the server.

[0339] Step 2:

[0340] The server verifies the login information against the database to authenticate the user. If authentication is successful, it retrieves the user information and past learning history and sends them to the terminal.

[0341] Step 3:

[0342] The user selects the subjects or topics they wish to study through their device. The device then sends this selection information to the server, communicating the user's preferences.

[0343] Step 4:

[0344] The server analyzes the learner's abilities based on user information and topic selection. Based on the analysis results, the server generates educational content in text, image, and video formats.

[0345] Step 5:

[0346] The device's built-in emotion engine uses the built-in camera and microphone to record the user's facial expressions and voice tone in real time.

[0347] Step 6:

[0348] The emotion engine analyzes the collected data to recognize the user's current emotional state. The recognized emotional data is then sent to the server.

[0349] Step 7:

[0350] The server receives emotional data and adjusts the educational content based on the user's psychological state. For example, if it determines that the user is confused, it generates educational content that includes more detailed explanations and hints.

[0351] Step 8:

[0352] The server sends the adjusted educational content to the device. The device displays the updated content to the user, supporting their learning.

[0353] Step 9:

[0354] If a user's understanding or emotional state does not improve as they progress through the learning process, the emotion engine continues to monitor the user's state and sends new emotional data to the server.

[0355] Step 10:

[0356] The server continues to adjust the educational content based on sentiment data and changes the review schedule as needed. The terminal notifies the user of these changes and provides an optimal learning environment.

[0357] (Example 2)

[0358] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0359] Traditional education systems have struggled to provide appropriate educational content tailored to learners' abilities and emotional states, sometimes leading to decreased learning efficiency. Furthermore, insufficient optimization of review schedules to consider learners' emotions resulted in underutilized learning outcomes.

[0360] 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.

[0361] In this invention, the server includes means for analyzing a learner's abilities based on user information, means for generating personalized educational content based on the learner's ability analysis and emotional data, and an emotion analysis device for recognizing the learner's emotional state in real time. This enables the provision of educational content adapted to each learner's abilities and emotional state, thereby improving learning efficiency and maximizing results.

[0362] "User information" is a general term for data that includes learners' learning history, test results, and real-time sentiment data.

[0363] "Learner's competence" refers to the level of knowledge and skills a learner possesses, and it is the fundamental information upon which adaptive educational content is generated.

[0364] "Emotional data" refers to information that indicates a learner's emotional state, and is acquired through visual or auditory methods.

[0365] "Individualized educational content" refers to learning materials that are tailored based on learners' ability and emotional data, and are provided in a way that is optimized for each individual learner.

[0366] An "emotion analysis device" is a device that detects and analyzes changes in a learner's emotions in real time, based on their visual and auditory perceptions.

[0367] A "review schedule" is a flexible plan for reviewing learned material, generated based on the learner's learning progress and emotional information.

[0368] This invention is a system that adaptively provides educational content based on the learner's emotional state and personal abilities. The entire system consists of a server, terminals, an emotion analysis device, and user interaction.

[0369] The server aggregates information from users through terminals and analyzes learners' ability and emotional data. This includes data processing using generative AI models, which process learning history and real-time emotional data. Based on the analyzed information, the server generates personalized educational content and sends that content to the terminal.

[0370] The emotion analysis device receives visual or auditory data from the user as input and analyzes their emotional state in real time. This device uses data obtained from the user's camera and microphone to analyze facial expressions and voice tone, thereby evaluating the learner's psychological state.

[0371] Users use a device to receive personalized educational content provided by the server and proceed with their learning. The device continuously monitors the user's learning progress and emotional changes, and sends the collected data to the server. This server-side process dynamically adjusts the educational content and presents it in a way that is easy for the learner to understand.

[0372] As a concrete example, when a user is learning a new mathematical concept, if the device's emotion analysis device detects that the user's facial expression indicates confusion, it will use a generative AI model to generate additional hints or video tutorials about that concept and present them to the user.

[0373] An example of a prompt might be: "If a user indicates that they are having difficulty understanding a new mathematical concept, explain how you will generate personalized educational content based on their sentiment data and past learning history."

[0374] This system enables learners to progress through their studies more smoothly and deepen their understanding, providing an effective educational environment.

[0375] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0376] Step 1:

[0377] The user activates the device and starts a learning session. The device collects the user's learning history, current learning progress, and emotional data as input. It uses the camera and microphone to acquire real-time facial expression and voice tone data and sends it to the server. Specifically, it performs facial recognition and voice analysis of the user and formats it as digital data.

[0378] Step 2:

[0379] The server analyzes the input data received from the terminal. It integrates learning history, progress, and collected sentiment data, and analyzes this information using a generative AI model. Data processing includes evaluating past learning performance and detecting real-time changes in sentiment. The output is an assessment of the learner's abilities and emotional state.

[0380] Step 3:

[0381] The server generates personalized educational content based on the analysis results. Inputs include ability and emotion assessments. A generative AI model is used to select or generate adaptive learning materials. Specific actions include selecting relevant text, image, and video resources. The output is personalized educational content.

[0382] Step 4:

[0383] The terminal delivers educational content sent from the server to the user. During this process, the terminal continuously monitors the user's reactions and records new emotional states. This is done in real time using an emotion analysis device, leading to highly effective understanding enhancement. The output consists of new learner feedback and emotional data.

[0384] Step 5:

[0385] The server further refines the educational content based on feedback and sentiment data from the device. It utilizes the information received as input to improve the content again using a generative AI model, and updates it as needed. For example, if a learner finds a particular unit difficult to understand, it might add more detailed explanations or practice problems. The output is the updated educational content.

[0386] This processing flow provides learners with an adaptive and effective educational experience.

[0387] (Application Example 2)

[0388] 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."

[0389] To enhance the learning effectiveness of educators, it is necessary to consider the psychological state of each learner and provide appropriate teaching materials and environmental adjustments. However, the current education system sometimes fails to adequately consider the emotional state of learners, and the provision of fixed teaching materials can lead to decreased learning efficiency. Furthermore, there are cases where care tailored to the emotional needs of those receiving care is insufficient, and solutions to this problem are needed.

[0390] 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.

[0391] In this invention, the server includes means for analyzing the abilities of the person being educated based on user information, means for acquiring emotional data and recognizing the emotional state of the person being educated in real time, and means for generating adaptive and emotionally responsive educational content based on the analysis of the person being educated. This makes it possible to provide educational content that is tailored to the emotional state of each individual learner, and to realize appropriate care based on the psychological state of the person being cared for.

[0392] "User information" refers to all data concerning the student, and specifically includes learning history, test results, and sentiment data acquired in real time.

[0393] "The learner's ability" refers to the level of knowledge and skills possessed by the learner, and is analyzed based on user information.

[0394] "Adaptive educational content" refers to teaching materials and learning plans that are optimized according to the abilities and emotional state of the students.

[0395] "Emotional data" refers to information about the psychological state of the person being educated, analyzed based on visual or auditory information.

[0396] "Emotional state" refers to the psychological state of an educated person, obtained by analyzing emotional data, and includes emotions such as anxiety and happiness.

[0397] A "review schedule" is a plan for reviewing what has been learned at appropriate times, based on the learner's progress.

[0398] "Environmental settings" refer to the surrounding conditions that can be adjusted according to the emotional state of the person being educated, and specifically include elements such as music and lighting.

[0399] The system for realizing this invention mainly consists of a server, a terminal, and an emotion recognition engine. The server has the function of analyzing the learner's abilities based on user information and generating adaptive educational content. This ability analysis includes learning history, test results, and emotion data. Based on the analysis results, the server generates personalized educational content and delivers it to the terminal.

[0400] The device uses its camera and microphone to acquire visual and auditory information from the learner and transmits it to an emotion recognition engine. The emotion recognition engine analyzes this data and identifies the user's emotional state in real time. Based on this emotional state, the server readjusts the educational content and review schedule, providing the learner with the most effective educational content.

[0401] The emotion recognition engine can utilize software such as the Microsoft Emotion API, enabling advanced emotion recognition. By using hardware such as smart glasses, applications in the field of elderly care are also possible. For example, if a learner faces a difficult problem and experiences anxiety or stress, the emotion recognition engine can detect this, and the server can generate learning materials that include simpler explanations and additional support.

[0402] In addition, when a caregiver recognizes that the person being cared for is feeling restless, they adjust environmental settings such as music and lighting.

[0403] Example of a prompt:

[0404] "We're looking for ideas for a smart glasses app that uses emotion recognition technology to understand the emotions of the person receiving care in real time and suggest appropriate care methods."

[0405] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0406] Step 1:

[0407] The device uses a camera and microphone to acquire visual and auditory information from the student. Input is video and audio of the student's face, and output is data converted into an appropriate digital format for transmission to the server. Data acquisition and format conversion occur in real time.

[0408] Step 2:

[0409] The server receives visual and audio information transmitted from the terminal and inputs it into the emotion recognition engine. The input is digitized video and audio data, and the output is the analyzed emotional state. The emotion recognition engine uses image analysis and audio analysis algorithms to identify specific emotions (e.g., anxiety, concentration, excitement, etc.).

[0410] Step 3:

[0411] The server analyzes the learner's abilities by combining their emotional state with past learning history and test results, and generates adaptive educational content. Inputs are learning history, test results, and emotional states, and output is customized learning materials tailored to the learner's emotions and abilities. Data combination and computation are performed using database queries and machine learning algorithms.

[0412] Step 4:

[0413] The server delivers the generated educational content to the terminal, which then displays it to the learner. The input is customized learning materials, and the output is the educational content displayed on the terminal's screen. Data transmission and display are instantaneous, allowing learners to begin learning immediately.

[0414] Step 5:

[0415] The user (learner) progresses through the learning process via a terminal and inputs questions if necessary. The input is the learner's question, and the output is the answer generated by the server. The server extracts appropriate information from its accumulated knowledge database based on the question content and forms the answer.

[0416] Step 6:

[0417] The server continuously monitors the learner's emotional state and learning progress, and readjusts the review schedule as needed. Input is real-time emotional data and progress information, while output is an updated review schedule tailored to the learner's level of understanding. Data collection and schedule updates are performed through the progress management system.

[0418] 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.

[0419] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0420] 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.

[0421] [Third Embodiment]

[0422] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0423] 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.

[0424] 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).

[0425] 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.

[0426] 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.

[0427] 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).

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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.

[0432] 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.

[0433] 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".

[0434] The present invention is implemented as a system that provides adaptive educational content for each learner. This system mainly consists of server, terminal, and user interaction, and its specific embodiments are described below.

[0435] The server first stores the learner's user information, obtained via the terminal, in a database. This user information includes the learner's age, past learning history, and test results. The server analyzes this information to evaluate the learner's abilities. Natural language processing techniques and machine learning algorithms can be used for ability evaluation.

[0436] Next, the server automatically generates educational content optimized for the learner based on the evaluation results. This educational content is presented in various media formats, including text, images, and videos, to accommodate different learning styles. The generated materials are then delivered to the learner via their device.

[0437] Users can learn at their own pace using their devices. During learning, users can input questions into their devices. The devices send the questions to the server, which uses AI to generate appropriate answers. The generated answers, along with supplementary materials as needed, are returned to the devices and presented to the user.

[0438] Furthermore, the server constantly monitors the learner's progress and develops an optimal review schedule based on factors such as Ebbinghaus's forgetting curve. The terminal notifies the user of this schedule, thereby supporting long-term retention of the learned material.

[0439] As a concrete example, consider a scenario where a user studies history on their device. The server prepares appropriate reading materials and video resources related to history based on information obtained from the user's past learning history. In response to questions posed by the user, the AI ​​provides real-time explanations of the historical background and related events, promoting a deeper understanding.

[0440] Thus, the present invention enables efficient learning tailored to individual learning needs and helps learners retain their knowledge.

[0441] The following describes the processing flow.

[0442] Step 1:

[0443] The user starts up the device and logs into the learning application. The device sends the user's login information to the server and requests authentication.

[0444] Step 2:

[0445] The server compares the received login information with the database to authenticate the user. If authentication is successful, it retrieves the user's user information and sends the authentication result back to the terminal.

[0446] Step 3:

[0447] The user selects the subjects or topics they want to learn through their device. The device then sends the selection information to the server.

[0448] Step 4:

[0449] The server analyzes the learner's abilities based on user information and selection information, and generates adaptive educational content. The generated content is available in various media formats, including text, images, and videos.

[0450] Step 5:

[0451] The server generates educational content and sends it to the terminal. The terminal visually displays the received content to the user and initiates learning.

[0452] Step 6:

[0453] As the user progresses through the learning process, they can input any questions or doubts into their device. The device then sends the question to the server.

[0454] Step 7:

[0455] The server receives questions from users and uses generative AI to generate appropriate answers. The answers include additional information as needed.

[0456] Step 8:

[0457] The server sends the generated answer to the terminal. The terminal displays the received answer to the user, resolving their question.

[0458] Step 9:

[0459] The server monitors the user's learning progress and creates a review schedule based on Ebbinghaus's forgetting curve. The created schedule is then sent to the user's device.

[0460] Step 10:

[0461] The terminal notifies the user of the review schedule received from the server. The user then reviews according to this schedule.

[0462] (Example 1)

[0463] 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."

[0464] In the education industry, providing educational content tailored to each individual learner is crucial, but a fixed curriculum faces the challenge of failing to address individual learning needs. Furthermore, it is difficult to respond quickly and accurately to learners' questions and to appropriately present review plans that match their learning progress. There is also a need to provide diverse media formats that suit the preferences and learning styles of individual learners.

[0465] 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.

[0466] In this invention, the server includes means for evaluating learners' abilities based on user information, means for generating adaptive educational resources based on the learners' ability evaluation, and means for generating responses to learners' inquiries based on the generated educational resources. This makes it possible to provide customized educational content that meets the individual needs of each learner, thereby realizing more effective learning support.

[0467] "User information" refers to information related to each individual learner, such as their age, learning history, and test results.

[0468] "Competency assessment" is the process of analyzing and evaluating the skill and knowledge levels of learners, either quantitatively or qualitatively.

[0469] "Educational resources" refer to the educational content provided to learners, and include various formats such as text, still images, and videos.

[0470] "Inquiries" refer to questions or doubts that arise during the learning process, and their purpose is to deepen the learner's understanding of the material.

[0471] A "review plan" is a schedule outlining the timing and content of reviews, designed to help learners retain previously learned material in their long-term memory.

[0472] Artificial intelligence is a type of technology in which computers imitate human intellectual activity, using data and algorithms to learn and reason.

[0473] "Media format" refers to the form in which information is presented visually or audibly, and includes text, still images, and moving images.

[0474] This system is built around server, terminal, and user interaction to provide adaptive educational resources tailored to each learner. The server retrieves learner user information via the terminal and stores it in a database. The stored information is analyzed using the Python library scikit-learn to assess the learner's abilities.

[0475] The server generates adaptive educational resources based on the evaluation results. In this process, it utilizes a generative AI model to automatically generate content optimized for the learner using prompts. For example, the prompt "Generate the most suitable educational content on history based on the user's learning history" is input to the AI ​​model, providing customized educational content.

[0476] Educational resources are provided in diverse media formats, including text, still images, and videos, accommodating different learning styles. The generated resources are delivered to learners via their devices, allowing users to learn at their own pace.

[0477] Furthermore, when a user enters a question during learning, the device sends it to the server. The server uses artificial intelligence technology to generate an appropriate response to the question and returns it to the device. This allows the user to progress through the learning process while resolving their questions.

[0478] Furthermore, the server monitors the learner's progress and creates an optimal review plan based on Ebbinghaus's forgetting curve and other factors. The terminal notifies the user of this plan, thereby supporting long-term retention of the learned material.

[0479] As a concrete example, when a user is learning history, the server prepares appropriate resources related to history based on user information and provides the user with information in real time. In this way, the present invention realizes effective learning tailored to the needs of each learner.

[0480] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0481] Step 1:

[0482] The server obtains user information from learners via the terminal. This information includes the learner's age, past learning history, and test results. The server stores this data in a database. The input at this stage is the learner's personal information, and the output is database storage. Specifically, the user enters information into an input form on the terminal, and the terminal sends this information to the server.

[0483] Step 2:

[0484] The server analyzes stored user information and evaluates the learner's abilities. Here, the scikit-learn library in Python is used to process the data and identify the learner's strengths and weaknesses. The input is user information stored in the database, and the output is the evaluation result. Specifically, the server executes a process of analyzing the data by applying a particular algorithm.

[0485] Step 3:

[0486] The server generates adaptive educational resources based on the evaluation results. This process utilizes a generative AI model and uses prompts to generate appropriate educational content. The input is the evaluation results, and the output is the generated educational resources. Specifically, the server sends a prompt to the AI ​​model such as "Generate the best educational content on history," and retrieves the generated text and materials.

[0487] Step 4:

[0488] The server delivers the generated educational resources to the terminal. The terminal receives these resources, and the user uses the terminal to proceed with their learning. The input is the generated educational resources, and the output is the data delivery to the terminal. In specific operations, the terminal downloads the educational content, and the user views it on the screen.

[0489] Step 5:

[0490] When a user enters a question during training, the device sends it to the server. The server uses artificial intelligence technology to generate an appropriate response to the question and returns it to the device. The input is the question from the user, and the output is the generated response. Specifically, the device sends question data to the server, the server analyzes it, and then returns a response in text.

[0491] Step 6:

[0492] The server monitors the learner's progress and creates an optimal review plan based on Ebbinghaus's forgetting curve. The terminal notifies the user of this plan. The input is learning history data, and the output is the review plan. Specifically, the server analyzes progress data, calculates the optimal review timing, and sends a notification to the terminal.

[0493] (Application Example 1)

[0494] 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."

[0495] Traditional education systems struggle to provide personalized feedback to each learner, particularly lacking real-time feedback on pronunciation and physical expression. This results in insufficient learning efficiency and challenges in retaining learners' skills and knowledge.

[0496] 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.

[0497] In this invention, the server includes means for analyzing the learner's abilities based on user information, means for generating adaptive educational content, means for generating an appropriate review schedule based on the learner's learning progress, and means for detecting the learner's pronunciation via a voice control member and providing real-time feedback. This makes it possible to provide individually customized educational content to learners and promote skill improvement through real-time voice feedback.

[0498] "User information" refers to data about learners, such as age, past learning history, and test results, and is basic information for analyzing an individual's learning ability and characteristics.

[0499] "Learner ability analysis" is a process of evaluating a learner's learning ability and characteristics based on their learning history and user information.

[0500] "Adaptive educational content" refers to teaching materials and learning programs that are optimized based on the results of an analysis of each learner's abilities, and are provided in a variety of media formats.

[0501] A "review schedule" is a plan designed to manage the time and frequency of review sessions, optimized for learners' memory retention.

[0502] A "voice control component" is hardware or software that has the function of detecting and analyzing the learner's voice and providing real-time feedback based on that analysis.

[0503] "Real-time feedback" refers to the ability to respond immediately to a learner's pronunciation and behavior, and to provide immediate feedback and evaluations on areas for improvement.

[0504] The system implementing this invention consists of a server, a terminal, and user interaction. The server is the main data processing center and analyzes the learner's abilities based on user information. The database stores the learner's age, past learning history, test results, etc., and uses natural language processing technology and machine learning algorithms to evaluate abilities based on this data.

[0505] Subsequently, the server generates educational content in adaptive and diverse media formats based on the evaluation results and provides it to learners through their devices. The devices receive the educational content, allowing users to learn at their own pace. During learning, when a user enters a question into the device, the server uses a generative AI model to generate an appropriate answer, and returns supplementary materials to the device as needed.

[0506] Furthermore, the server constantly monitors the learner's progress and develops a schedule that takes review into account to optimize memory retention. This schedule is notified to the user via their device, supporting the long-term retention of the learned material.

[0507] The voice control component in this system detects the user's pronunciation in real time and provides immediate feedback. This allows the user to improve their pronunciation and accuracy. For example, when a learner asks "What is the French Revolution?", the prompt "The user wants to know about the background and impact of the French Revolution. Please provide a concise explanation of this historical topic." is used, and the AI ​​provides a detailed historical explanation.

[0508] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0509] Step 1:

[0510] The server collects user information via the terminal. Inputs include the learner's age, past learning history, and test results, which are then stored in a database. Data processing involves organizing the information as structured data and optimizing it for future analysis.

[0511] Step 2:

[0512] The server analyzes learners' abilities using the collected information. Using learner information stored in a database as input, and applying natural language processing techniques and machine learning algorithms, it generates ability assessment results as output.

[0513] Step 3:

[0514] The server generates adaptive educational content based on the assessment results. The input is the competency assessment results, which are converted into plain text, image, and video formats for output. Personalized content generation algorithms are used for data processing.

[0515] Step 4:

[0516] The terminal receives educational content sent from the server and presents it to the user. The input is educational content from the server, and the output is provided to the user as visual and audio information on the screen. The operation involves displaying the learning content in an appropriate media format.

[0517] Step 5:

[0518] When a user enters a question into the terminal, that question is sent to the server. The input is a text question from the user, and preprocessing is performed to pass the prompt text to the AI ​​model, which then sends its output to the server.

[0519] Step 6:

[0520] The server uses a generation AI model to generate answers to questions. The input is the user's question, and a prompt based on that question is sent to the generation AI model, which then outputs a specific answer.

[0521] Step 7:

[0522] The device that receives the response will present the answer to the user, along with supplementary materials as needed. The input is the response from the server, and the output provides the response in visual and audio formats.

[0523] Step 8:

[0524] The server monitors the learner's learning progress. It receives learning history information sent from the terminal as input, calculates an optimal review schedule based on Ebbinghaus's forgetting curve, and generates the schedule as output.

[0525] Step 9:

[0526] The terminal notifies the user of the generated review schedule. The input is the schedule provided by the server, and the output is a notification message displayed to the user.

[0527] Step 10:

[0528] The voice control component detects the user's pronunciation in real time and provides immediate feedback based on that data. The input is voice data, and the feedback is output based on voice analysis.

[0529] 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.

[0530] This invention provides a system that offers learners an individualized learning experience, aiming to more appropriately adjust educational content using emotion recognition. This system mainly consists of a server, terminals, an emotion engine, and user interaction.

[0531] The server analyzes learners' abilities based on user information obtained through their terminals. This user information includes not only learning history and test results, but also sentiment data acquired in real time. The server analyzes this information to generate personalized educational content.

[0532] The emotion engine analyzes the user's visual or auditory data to recognize their emotional state in real time. This allows the server to determine how learners are feeling about the learning materials and adjust the educational content as needed. For example, if a user is feeling frustrated with difficult content, the system can sense this and provide simpler explanations or additional hints.

[0533] As users progress through their learning using their devices, the emotion engine continuously monitors their emotions and detects any changes. Based on this, the server readjusts the educational content and delivers new content to the device. Furthermore, the review schedule is flexibly adjusted according to the learner's emotions, maximizing learning efficiency.

[0534] As a concrete example, consider a scenario where a user is tackling a difficult mathematical problem. The device uses the user's camera and microphone to record their facial expressions and tone of voice, and an emotion engine identifies the user's anxiety or confusion. As a result, the server generates new educational content in the form of step-by-step explanations of the problem or similar problems, and provides it in an easy-to-understand format for the learner.

[0535] Thus, by using emotion recognition technology, the present invention provides adaptive educational services that take into account the learner's psychological state, thereby deepening the learner's understanding and creating an environment where learning can proceed smoothly.

[0536] The following describes the processing flow.

[0537] Step 1:

[0538] The user starts up the device and logs into the learning application. The device receives the user's authentication information as input and sends it to the server.

[0539] Step 2:

[0540] The server verifies the login information against the database to authenticate the user. If authentication is successful, it retrieves the user information and past learning history and sends them to the terminal.

[0541] Step 3:

[0542] The user selects the subjects or topics they wish to study through their device. The device then sends this selection information to the server, communicating the user's preferences.

[0543] Step 4:

[0544] The server analyzes the learner's abilities based on user information and topic selection. Based on the analysis results, the server generates educational content in text, image, and video formats.

[0545] Step 5:

[0546] The device's built-in emotion engine uses the built-in camera and microphone to record the user's facial expressions and voice tone in real time.

[0547] Step 6:

[0548] The emotion engine analyzes the collected data to recognize the user's current emotional state. The recognized emotional data is then sent to the server.

[0549] Step 7:

[0550] The server receives emotional data and adjusts the educational content based on the user's psychological state. For example, if it determines that the user is confused, it generates educational content that includes more detailed explanations and hints.

[0551] Step 8:

[0552] The server sends the adjusted educational content to the device. The device displays the updated content to the user, supporting their learning.

[0553] Step 9:

[0554] If a user's understanding or emotional state does not improve as they progress through the learning process, the emotion engine continues to monitor the user's state and sends new emotional data to the server.

[0555] Step 10:

[0556] The server continues to adjust the educational content based on sentiment data and changes the review schedule as needed. The terminal notifies the user of these changes and provides an optimal learning environment.

[0557] (Example 2)

[0558] 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."

[0559] Traditional education systems have struggled to provide appropriate educational content tailored to learners' abilities and emotional states, sometimes leading to decreased learning efficiency. Furthermore, insufficient optimization of review schedules to consider learners' emotions resulted in underutilized learning outcomes.

[0560] 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.

[0561] In this invention, the server includes means for analyzing a learner's abilities based on user information, means for generating personalized educational content based on the learner's ability analysis and emotional data, and an emotion analysis device for recognizing the learner's emotional state in real time. This enables the provision of educational content adapted to each learner's abilities and emotional state, thereby improving learning efficiency and maximizing results.

[0562] "User information" is a general term for data that includes learners' learning history, test results, and real-time sentiment data.

[0563] "Learner's competence" refers to the level of knowledge and skills a learner possesses, and it is the fundamental information upon which adaptive educational content is generated.

[0564] "Emotional data" refers to information that indicates a learner's emotional state, and is acquired through visual or auditory methods.

[0565] "Individualized educational content" refers to learning materials that are tailored based on learners' ability and emotional data, and are provided in a way that is optimized for each individual learner.

[0566] An "emotion analysis device" is a device that detects and analyzes changes in a learner's emotions in real time, based on their visual and auditory perceptions.

[0567] A "review schedule" is a flexible plan for reviewing learned material, generated based on the learner's learning progress and emotional information.

[0568] This invention is a system that adaptively provides educational content based on the learner's emotional state and personal abilities. The entire system consists of a server, terminals, an emotion analysis device, and user interaction.

[0569] The server aggregates information from users through terminals and analyzes learners' ability and emotional data. This includes data processing using generative AI models, which process learning history and real-time emotional data. Based on the analyzed information, the server generates personalized educational content and sends that content to the terminal.

[0570] The emotion analysis device receives visual or auditory data from the user as input and analyzes their emotional state in real time. This device uses data obtained from the user's camera and microphone to analyze facial expressions and voice tone, thereby evaluating the learner's psychological state.

[0571] Users use a device to receive personalized educational content provided by the server and proceed with their learning. The device continuously monitors the user's learning progress and emotional changes, and sends the collected data to the server. This server-side process dynamically adjusts the educational content and presents it in a way that is easy for the learner to understand.

[0572] As a concrete example, when a user is learning a new mathematical concept, if the device's emotion analysis device detects that the user's facial expression indicates confusion, it will use a generative AI model to generate additional hints or video tutorials about that concept and present them to the user.

[0573] An example of a prompt might be: "If a user indicates that they are having difficulty understanding a new mathematical concept, explain how you will generate personalized educational content based on their sentiment data and past learning history."

[0574] This system enables learners to progress through their studies more smoothly and deepen their understanding, providing an effective educational environment.

[0575] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0576] Step 1:

[0577] The user activates the device and starts a learning session. The device collects the user's learning history, current learning progress, and emotional data as input. It uses the camera and microphone to acquire real-time facial expression and voice tone data and sends it to the server. Specifically, it performs facial recognition and voice analysis of the user and formats it as digital data.

[0578] Step 2:

[0579] The server analyzes the input data received from the terminal. It integrates learning history, progress, and collected sentiment data, and analyzes this information using a generative AI model. Data processing includes evaluating past learning performance and detecting real-time changes in sentiment. The output is an assessment of the learner's abilities and emotional state.

[0580] Step 3:

[0581] The server generates personalized educational content based on the analysis results. Inputs include ability and emotion assessments. A generative AI model is used to select or generate adaptive learning materials. Specific actions include selecting relevant text, image, and video resources. The output is personalized educational content.

[0582] Step 4:

[0583] The terminal delivers educational content sent from the server to the user. During this process, the terminal continuously monitors the user's reactions and records new emotional states. This is done in real time using an emotion analysis device, leading to highly effective understanding enhancement. The output consists of new learner feedback and emotional data.

[0584] Step 5:

[0585] The server further refines the educational content based on feedback and sentiment data from the device. It utilizes the information received as input to improve the content again using a generative AI model, and updates it as needed. For example, if a learner finds a particular unit difficult to understand, it might add more detailed explanations or practice problems. The output is the updated educational content.

[0586] This processing flow provides learners with an adaptive and effective educational experience.

[0587] (Application Example 2)

[0588] 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."

[0589] To enhance the learning effectiveness of educators, it is necessary to consider the psychological state of each learner and provide appropriate teaching materials and environmental adjustments. However, the current education system sometimes fails to adequately consider the emotional state of learners, and the provision of fixed teaching materials can lead to decreased learning efficiency. Furthermore, there are cases where care tailored to the emotional needs of those receiving care is insufficient, and solutions to this problem are needed.

[0590] 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.

[0591] In this invention, the server includes means for analyzing the abilities of the person being educated based on user information, means for acquiring emotional data and recognizing the emotional state of the person being educated in real time, and means for generating adaptive and emotionally responsive educational content based on the analysis of the person being educated. This makes it possible to provide educational content that is tailored to the emotional state of each individual learner, and to realize appropriate care based on the psychological state of the person being cared for.

[0592] "User information" refers to all data concerning the student, and specifically includes learning history, test results, and sentiment data acquired in real time.

[0593] "The learner's ability" refers to the level of knowledge and skills possessed by the learner, and is analyzed based on user information.

[0594] "Adaptive educational content" refers to teaching materials and learning plans that are optimized according to the abilities and emotional state of the students.

[0595] "Emotional data" refers to information about the psychological state of the person being educated, analyzed based on visual or auditory information.

[0596] "Emotional state" refers to the psychological state of an educated person, obtained by analyzing emotional data, and includes emotions such as anxiety and happiness.

[0597] A "review schedule" is a plan for reviewing what has been learned at appropriate times, based on the learner's progress.

[0598] "Environmental settings" refer to the surrounding conditions that can be adjusted according to the emotional state of the person being educated, and specifically include elements such as music and lighting.

[0599] The system for realizing this invention mainly consists of a server, a terminal, and an emotion recognition engine. The server has the function of analyzing the learner's abilities based on user information and generating adaptive educational content. This ability analysis includes learning history, test results, and emotion data. Based on the analysis results, the server generates personalized educational content and delivers it to the terminal.

[0600] The device uses its camera and microphone to acquire visual and auditory information from the learner and transmits it to an emotion recognition engine. The emotion recognition engine analyzes this data and identifies the user's emotional state in real time. Based on this emotional state, the server readjusts the educational content and review schedule, providing the learner with the most effective educational content.

[0601] The emotion recognition engine can utilize software such as the Microsoft Emotion API, enabling advanced emotion recognition. By using hardware such as smart glasses, applications in the field of elderly care are also possible. For example, if a learner faces a difficult problem and experiences anxiety or stress, the emotion recognition engine can detect this, and the server can generate learning materials that include simpler explanations and additional support.

[0602] In addition, when a caregiver recognizes that the person being cared for is feeling restless, they adjust environmental settings such as music and lighting.

[0603] Example of a prompt:

[0604] "We're looking for ideas for a smart glasses app that uses emotion recognition technology to understand the emotions of the person receiving care in real time and suggest appropriate care methods."

[0605] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0606] Step 1:

[0607] The device uses a camera and microphone to acquire visual and auditory information from the student. Input is video and audio of the student's face, and output is data converted into an appropriate digital format for transmission to the server. Data acquisition and format conversion occur in real time.

[0608] Step 2:

[0609] The server receives visual and audio information transmitted from the terminal and inputs it into the emotion recognition engine. The input is digitized video and audio data, and the output is the analyzed emotional state. The emotion recognition engine uses image analysis and audio analysis algorithms to identify specific emotions (e.g., anxiety, concentration, excitement, etc.).

[0610] Step 3:

[0611] The server analyzes the learner's abilities by combining their emotional state with past learning history and test results, and generates adaptive educational content. Inputs are learning history, test results, and emotional states, and output is customized learning materials tailored to the learner's emotions and abilities. Data combination and computation are performed using database queries and machine learning algorithms.

[0612] Step 4:

[0613] The server delivers the generated educational content to the terminal, which then displays it to the learner. The input is customized learning materials, and the output is the educational content displayed on the terminal's screen. Data transmission and display are instantaneous, allowing learners to begin learning immediately.

[0614] Step 5:

[0615] The user (learner) progresses through the learning process via a terminal and inputs questions if necessary. The input is the learner's question, and the output is the answer generated by the server. The server extracts appropriate information from its accumulated knowledge database based on the question content and forms the answer.

[0616] Step 6:

[0617] The server continuously monitors the learner's emotional state and learning progress, and readjusts the review schedule as needed. Input is real-time emotional data and progress information, while output is an updated review schedule tailored to the learner's level of understanding. Data collection and schedule updates are performed through the progress management system.

[0618] 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.

[0619] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0620] 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.

[0621] [Fourth Embodiment]

[0622] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0623] 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.

[0624] 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).

[0625] 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.

[0626] 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.

[0627] 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).

[0628] 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.

[0629] 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.

[0630] 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.

[0631] 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.

[0632] 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.

[0633] 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.

[0634] 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".

[0635] The present invention is implemented as a system that provides adaptive educational content for each learner. This system mainly consists of server, terminal, and user interaction, and its specific embodiments are described below.

[0636] The server first stores the learner's user information, obtained via the terminal, in a database. This user information includes the learner's age, past learning history, and test results. The server analyzes this information to evaluate the learner's abilities. Natural language processing techniques and machine learning algorithms can be used for ability evaluation.

[0637] Next, the server automatically generates educational content optimized for the learner based on the evaluation results. This educational content is presented in various media formats, including text, images, and videos, to accommodate different learning styles. The generated materials are then delivered to the learner via their device.

[0638] Users can learn at their own pace using their devices. During learning, users can input questions into their devices. The devices send the questions to the server, which uses AI to generate appropriate answers. The generated answers, along with supplementary materials as needed, are returned to the devices and presented to the user.

[0639] Furthermore, the server constantly monitors the learner's progress and develops an optimal review schedule based on factors such as Ebbinghaus's forgetting curve. The terminal notifies the user of this schedule, thereby supporting long-term retention of the learned material.

[0640] As a concrete example, consider a scenario where a user studies history on their device. The server prepares appropriate reading materials and video resources related to history based on information obtained from the user's past learning history. In response to questions posed by the user, the AI ​​provides real-time explanations of the historical background and related events, promoting a deeper understanding.

[0641] Thus, the present invention enables efficient learning tailored to individual learning needs and helps learners retain their knowledge.

[0642] The following describes the processing flow.

[0643] Step 1:

[0644] The user starts up the device and logs into the learning application. The device sends the user's login information to the server and requests authentication.

[0645] Step 2:

[0646] The server compares the received login information with the database to authenticate the user. If authentication is successful, it retrieves the user's user information and sends the authentication result back to the terminal.

[0647] Step 3:

[0648] The user selects the subjects or topics they want to learn through their device. The device then sends the selection information to the server.

[0649] Step 4:

[0650] The server analyzes the learner's abilities based on user information and selection information, and generates adaptive educational content. The generated content is available in various media formats, including text, images, and videos.

[0651] Step 5:

[0652] The server generates educational content and sends it to the terminal. The terminal visually displays the received content to the user and initiates learning.

[0653] Step 6:

[0654] As the user progresses through the learning process, they can input any questions or doubts into their device. The device then sends the question to the server.

[0655] Step 7:

[0656] The server receives questions from users and uses generative AI to generate appropriate answers. The answers include additional information as needed.

[0657] Step 8:

[0658] The server sends the generated answer to the terminal. The terminal displays the received answer to the user, resolving their question.

[0659] Step 9:

[0660] The server monitors the user's learning progress and creates a review schedule based on Ebbinghaus's forgetting curve. The created schedule is then sent to the user's device.

[0661] Step 10:

[0662] The terminal notifies the user of the review schedule received from the server. The user then reviews according to this schedule.

[0663] (Example 1)

[0664] 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".

[0665] In the education industry, providing educational content tailored to each individual learner is crucial, but a fixed curriculum faces the challenge of failing to address individual learning needs. Furthermore, it is difficult to respond quickly and accurately to learners' questions and to appropriately present review plans that match their learning progress. There is also a need to provide diverse media formats that suit the preferences and learning styles of individual learners.

[0666] 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.

[0667] In this invention, the server includes means for evaluating learners' abilities based on user information, means for generating adaptive educational resources based on the learners' ability evaluation, and means for generating responses to learners' inquiries based on the generated educational resources. This makes it possible to provide customized educational content that meets the individual needs of each learner, thereby realizing more effective learning support.

[0668] "User information" refers to information related to each individual learner, such as their age, learning history, and test results.

[0669] "Competency assessment" is the process of analyzing and evaluating the skill and knowledge levels of learners, either quantitatively or qualitatively.

[0670] "Educational resources" refer to the educational content provided to learners, and include various formats such as text, still images, and videos.

[0671] "Inquiries" refer to questions or doubts that arise during the learning process, and their purpose is to deepen the learner's understanding of the material.

[0672] A "review plan" is a schedule outlining the timing and content of reviews, designed to help learners retain previously learned material in their long-term memory.

[0673] Artificial intelligence is a type of technology in which computers imitate human intellectual activity, using data and algorithms to learn and reason.

[0674] "Media format" refers to the form in which information is presented visually or audibly, and includes text, still images, and moving images.

[0675] This system is built around server, terminal, and user interaction to provide adaptive educational resources tailored to each learner. The server retrieves learner user information via the terminal and stores it in a database. The stored information is analyzed using the Python library scikit-learn to assess the learner's abilities.

[0676] The server generates adaptive educational resources based on the evaluation results. In this process, it utilizes a generative AI model to automatically generate content optimized for the learner using prompts. For example, the prompt "Generate the most suitable educational content on history based on the user's learning history" is input to the AI ​​model, providing customized educational content.

[0677] Educational resources are provided in diverse media formats, including text, still images, and videos, accommodating different learning styles. The generated resources are delivered to learners via their devices, allowing users to learn at their own pace.

[0678] Furthermore, when a user enters a question during learning, the device sends it to the server. The server uses artificial intelligence technology to generate an appropriate response to the question and returns it to the device. This allows the user to progress through the learning process while resolving their questions.

[0679] Furthermore, the server monitors the learner's progress and creates an optimal review plan based on Ebbinghaus's forgetting curve and other factors. The terminal notifies the user of this plan, thereby supporting long-term retention of the learned material.

[0680] As a concrete example, when a user is learning history, the server prepares appropriate resources related to history based on user information and provides the user with information in real time. In this way, the present invention realizes effective learning tailored to the needs of each learner.

[0681] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0682] Step 1:

[0683] The server obtains user information from learners via the terminal. This information includes the learner's age, past learning history, and test results. The server stores this data in a database. The input at this stage is the learner's personal information, and the output is database storage. Specifically, the user enters information into an input form on the terminal, and the terminal sends this information to the server.

[0684] Step 2:

[0685] The server analyzes stored user information and evaluates the learner's abilities. Here, the scikit-learn library in Python is used to process the data and identify the learner's strengths and weaknesses. The input is user information stored in the database, and the output is the evaluation result. Specifically, the server executes a process of analyzing the data by applying a particular algorithm.

[0686] Step 3:

[0687] The server generates adaptive educational resources based on the evaluation results. This process utilizes a generative AI model and uses prompts to generate appropriate educational content. The input is the evaluation results, and the output is the generated educational resources. Specifically, the server sends a prompt to the AI ​​model such as "Generate the best educational content on history," and retrieves the generated text and materials.

[0688] Step 4:

[0689] The server delivers the generated educational resources to the terminal. The terminal receives these resources, and the user uses the terminal to proceed with their learning. The input is the generated educational resources, and the output is the data delivery to the terminal. In specific operations, the terminal downloads the educational content, and the user views it on the screen.

[0690] Step 5:

[0691] When a user enters a question during training, the device sends it to the server. The server uses artificial intelligence technology to generate an appropriate response to the question and returns it to the device. The input is the question from the user, and the output is the generated response. Specifically, the device sends question data to the server, the server analyzes it, and then returns a response in text.

[0692] Step 6:

[0693] The server monitors the learner's progress and creates an optimal review plan based on Ebbinghaus's forgetting curve. The terminal notifies the user of this plan. The input is learning history data, and the output is the review plan. Specifically, the server analyzes progress data, calculates the optimal review timing, and sends a notification to the terminal.

[0694] (Application Example 1)

[0695] 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".

[0696] Traditional education systems struggle to provide personalized feedback to each learner, particularly lacking real-time feedback on pronunciation and physical expression. This results in insufficient learning efficiency and challenges in retaining learners' skills and knowledge.

[0697] 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.

[0698] In this invention, the server includes means for analyzing the learner's abilities based on user information, means for generating adaptive educational content, means for generating an appropriate review schedule based on the learner's learning progress, and means for detecting the learner's pronunciation via a voice control member and providing real-time feedback. This makes it possible to provide individually customized educational content to learners and promote skill improvement through real-time voice feedback.

[0699] "User information" refers to data about learners, such as age, past learning history, and test results, and is basic information for analyzing an individual's learning ability and characteristics.

[0700] "Learner ability analysis" is a process of evaluating a learner's learning ability and characteristics based on their learning history and user information.

[0701] "Adaptive educational content" refers to teaching materials and learning programs that are optimized based on the results of an analysis of each learner's abilities, and are provided in a variety of media formats.

[0702] A "review schedule" is a plan designed to manage the time and frequency of review sessions, optimized for learners' memory retention.

[0703] A "voice control component" is hardware or software that has the function of detecting and analyzing the learner's voice and providing real-time feedback based on that analysis.

[0704] "Real-time feedback" refers to the ability to respond immediately to a learner's pronunciation and behavior, and to provide immediate feedback and evaluations on areas for improvement.

[0705] The system implementing this invention consists of a server, a terminal, and user interaction. The server is the main data processing center and analyzes the learner's abilities based on user information. The database stores the learner's age, past learning history, test results, etc., and uses natural language processing technology and machine learning algorithms to evaluate abilities based on this data.

[0706] Subsequently, the server generates educational content in adaptive and diverse media formats based on the evaluation results and provides it to learners through their devices. The devices receive the educational content, allowing users to learn at their own pace. During learning, when a user enters a question into the device, the server uses a generative AI model to generate an appropriate answer, and returns supplementary materials to the device as needed.

[0707] Furthermore, the server constantly monitors the learner's progress and develops a schedule that takes review into account to optimize memory retention. This schedule is notified to the user via their device, supporting the long-term retention of the learned material.

[0708] The voice control component in this system detects the user's pronunciation in real time and provides immediate feedback. This allows the user to improve their pronunciation and accuracy. For example, when a learner asks "What is the French Revolution?", the prompt "The user wants to know about the background and impact of the French Revolution. Please provide a concise explanation of this historical topic." is used, and the AI ​​provides a detailed historical explanation.

[0709] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0710] Step 1:

[0711] The server collects user information via the terminal. Inputs include the learner's age, past learning history, and test results, which are then stored in a database. Data processing involves organizing the information as structured data and optimizing it for future analysis.

[0712] Step 2:

[0713] The server analyzes learners' abilities using the collected information. Using learner information stored in a database as input, and applying natural language processing techniques and machine learning algorithms, it generates ability assessment results as output.

[0714] Step 3:

[0715] The server generates adaptive educational content based on the assessment results. The input is the competency assessment results, which are converted into plain text, image, and video formats for output. Personalized content generation algorithms are used for data processing.

[0716] Step 4:

[0717] The terminal receives educational content sent from the server and presents it to the user. The input is educational content from the server, and the output is provided to the user as visual and audio information on the screen. The operation involves displaying the learning content in an appropriate media format.

[0718] Step 5:

[0719] When a user enters a question into the terminal, that question is sent to the server. The input is a text question from the user, and preprocessing is performed to pass the prompt text to the AI ​​model, which then sends its output to the server.

[0720] Step 6:

[0721] The server uses a generation AI model to generate answers to questions. The input is the user's question, and a prompt based on that question is sent to the generation AI model, which then outputs a specific answer.

[0722] Step 7:

[0723] The device that receives the response will present the answer to the user, along with supplementary materials as needed. The input is the response from the server, and the output provides the response in visual and audio formats.

[0724] Step 8:

[0725] The server monitors the learner's learning progress. It receives learning history information sent from the terminal as input, calculates an optimal review schedule based on Ebbinghaus's forgetting curve, and generates the schedule as output.

[0726] Step 9:

[0727] The terminal notifies the user of the generated review schedule. The input is the schedule provided by the server, and the output is a notification message displayed to the user.

[0728] Step 10:

[0729] The voice control component detects the user's pronunciation in real time and provides immediate feedback based on that data. The input is voice data, and the feedback is output based on voice analysis.

[0730] 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.

[0731] This invention provides a system that offers learners an individualized learning experience, aiming to more appropriately adjust educational content using emotion recognition. This system mainly consists of a server, terminals, an emotion engine, and user interaction.

[0732] The server analyzes learners' abilities based on user information obtained through their terminals. This user information includes not only learning history and test results, but also sentiment data acquired in real time. The server analyzes this information to generate personalized educational content.

[0733] The emotion engine analyzes the user's visual or auditory data to recognize their emotional state in real time. This allows the server to determine how learners are feeling about the learning materials and adjust the educational content as needed. For example, if a user is feeling frustrated with difficult content, the system can sense this and provide simpler explanations or additional hints.

[0734] As users progress through their learning using their devices, the emotion engine continuously monitors their emotions and detects any changes. Based on this, the server readjusts the educational content and delivers new content to the device. Furthermore, the review schedule is flexibly adjusted according to the learner's emotions, maximizing learning efficiency.

[0735] As a concrete example, consider a scenario where a user is tackling a difficult mathematical problem. The device uses the user's camera and microphone to record their facial expressions and tone of voice, and an emotion engine identifies the user's anxiety or confusion. As a result, the server generates new educational content in the form of step-by-step explanations of the problem or similar problems, and provides it in an easy-to-understand format for the learner.

[0736] Thus, by using emotion recognition technology, the present invention provides adaptive educational services that take into account the learner's psychological state, thereby deepening the learner's understanding and creating an environment where learning can proceed smoothly.

[0737] The following describes the processing flow.

[0738] Step 1:

[0739] The user starts up the device and logs into the learning application. The device receives the user's authentication information as input and sends it to the server.

[0740] Step 2:

[0741] The server verifies the login information against the database to authenticate the user. If authentication is successful, it retrieves the user information and past learning history and sends them to the terminal.

[0742] Step 3:

[0743] The user selects the subjects or topics they wish to study through their device. The device then sends this selection information to the server, communicating the user's preferences.

[0744] Step 4:

[0745] The server analyzes the learner's abilities based on user information and topic selection. Based on the analysis results, the server generates educational content in text, image, and video formats.

[0746] Step 5:

[0747] The device's built-in emotion engine uses the built-in camera and microphone to record the user's facial expressions and voice tone in real time.

[0748] Step 6:

[0749] The emotion engine analyzes the collected data to recognize the user's current emotional state. The recognized emotional data is then sent to the server.

[0750] Step 7:

[0751] The server receives emotional data and adjusts the educational content based on the user's psychological state. For example, if it determines that the user is confused, it generates educational content that includes more detailed explanations and hints.

[0752] Step 8:

[0753] The server sends the adjusted educational content to the device. The device displays the updated content to the user, supporting their learning.

[0754] Step 9:

[0755] If a user's understanding or emotional state does not improve as they progress through the learning process, the emotion engine continues to monitor the user's state and sends new emotional data to the server.

[0756] Step 10:

[0757] The server continues to adjust the educational content based on sentiment data and changes the review schedule as needed. The terminal notifies the user of these changes and provides an optimal learning environment.

[0758] (Example 2)

[0759] 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".

[0760] Traditional education systems have struggled to provide appropriate educational content tailored to learners' abilities and emotional states, sometimes leading to decreased learning efficiency. Furthermore, insufficient optimization of review schedules to consider learners' emotions resulted in underutilized learning outcomes.

[0761] 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.

[0762] In this invention, the server includes means for analyzing a learner's abilities based on user information, means for generating personalized educational content based on the learner's ability analysis and emotional data, and an emotion analysis device for recognizing the learner's emotional state in real time. This enables the provision of educational content adapted to each learner's abilities and emotional state, thereby improving learning efficiency and maximizing results.

[0763] "User information" is a general term for data that includes learners' learning history, test results, and real-time sentiment data.

[0764] "Learner's competence" refers to the level of knowledge and skills a learner possesses, and it is the fundamental information upon which adaptive educational content is generated.

[0765] "Emotional data" refers to information that indicates a learner's emotional state, and is acquired through visual or auditory methods.

[0766] "Individualized educational content" refers to learning materials that are tailored based on learners' ability and emotional data, and are provided in a way that is optimized for each individual learner.

[0767] An "emotion analysis device" is a device that detects and analyzes changes in a learner's emotions in real time, based on their visual and auditory perceptions.

[0768] A "review schedule" is a flexible plan for reviewing learned material, generated based on the learner's learning progress and emotional information.

[0769] This invention is a system that adaptively provides educational content based on the learner's emotional state and personal abilities. The entire system consists of a server, terminals, an emotion analysis device, and user interaction.

[0770] The server aggregates information from users through terminals and analyzes learners' ability and emotional data. This includes data processing using generative AI models, which process learning history and real-time emotional data. Based on the analyzed information, the server generates personalized educational content and sends that content to the terminal.

[0771] The emotion analysis device receives visual or auditory data from the user as input and analyzes their emotional state in real time. This device uses data obtained from the user's camera and microphone to analyze facial expressions and voice tone, thereby evaluating the learner's psychological state.

[0772] Users use a device to receive personalized educational content provided by the server and proceed with their learning. The device continuously monitors the user's learning progress and emotional changes, and sends the collected data to the server. This server-side process dynamically adjusts the educational content and presents it in a way that is easy for the learner to understand.

[0773] As a concrete example, when a user is learning a new mathematical concept, if the device's emotion analysis device detects that the user's facial expression indicates confusion, it will use a generative AI model to generate additional hints or video tutorials about that concept and present them to the user.

[0774] An example of a prompt might be: "If a user indicates that they are having difficulty understanding a new mathematical concept, explain how you will generate personalized educational content based on their sentiment data and past learning history."

[0775] This system enables learners to progress through their studies more smoothly and deepen their understanding, providing an effective educational environment.

[0776] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0777] Step 1:

[0778] The user activates the device and starts a learning session. The device collects the user's learning history, current learning progress, and emotional data as input. It uses the camera and microphone to acquire real-time facial expression and voice tone data and sends it to the server. Specifically, it performs facial recognition and voice analysis of the user and formats it as digital data.

[0779] Step 2:

[0780] The server analyzes the input data received from the terminal. It integrates learning history, progress, and collected sentiment data, and analyzes this information using a generative AI model. Data processing includes evaluating past learning performance and detecting real-time changes in sentiment. The output is an assessment of the learner's abilities and emotional state.

[0781] Step 3:

[0782] The server generates personalized educational content based on the analysis results. Inputs include ability and emotion assessments. A generative AI model is used to select or generate adaptive learning materials. Specific actions include selecting relevant text, image, and video resources. The output is personalized educational content.

[0783] Step 4:

[0784] The terminal delivers educational content sent from the server to the user. During this process, the terminal continuously monitors the user's reactions and records new emotional states. This is done in real time using an emotion analysis device, leading to highly effective understanding enhancement. The output consists of new learner feedback and emotional data.

[0785] Step 5:

[0786] The server further refines the educational content based on feedback and sentiment data from the device. It utilizes the information received as input to improve the content again using a generative AI model, and updates it as needed. For example, if a learner finds a particular unit difficult to understand, it might add more detailed explanations or practice problems. The output is the updated educational content.

[0787] This processing flow provides learners with an adaptive and effective educational experience.

[0788] (Application Example 2)

[0789] 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".

[0790] To enhance the learning effectiveness of educators, it is necessary to consider the psychological state of each learner and provide appropriate teaching materials and environmental adjustments. However, the current education system sometimes fails to adequately consider the emotional state of learners, and the provision of fixed teaching materials can lead to decreased learning efficiency. Furthermore, there are cases where care tailored to the emotional needs of those receiving care is insufficient, and solutions to this problem are needed.

[0791] 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.

[0792] In this invention, the server includes means for analyzing the abilities of the person being educated based on user information, means for acquiring emotional data and recognizing the emotional state of the person being educated in real time, and means for generating adaptive and emotionally responsive educational content based on the analysis of the person being educated. This makes it possible to provide educational content that is tailored to the emotional state of each individual learner, and to realize appropriate care based on the psychological state of the person being cared for.

[0793] "User information" refers to all data concerning the student, and specifically includes learning history, test results, and sentiment data acquired in real time.

[0794] "The learner's ability" refers to the level of knowledge and skills possessed by the learner, and is analyzed based on user information.

[0795] "Adaptive educational content" refers to teaching materials and learning plans that are optimized according to the abilities and emotional state of the students.

[0796] "Emotional data" refers to information about the psychological state of the person being educated, analyzed based on visual or auditory information.

[0797] "Emotional state" refers to the psychological state of an educated person, obtained by analyzing emotional data, and includes emotions such as anxiety and happiness.

[0798] A "review schedule" is a plan for reviewing what has been learned at appropriate times, based on the learner's progress.

[0799] "Environmental settings" refer to the surrounding conditions that can be adjusted according to the emotional state of the person being educated, and specifically include elements such as music and lighting.

[0800] The system for realizing this invention mainly consists of a server, a terminal, and an emotion recognition engine. The server has the function of analyzing the learner's abilities based on user information and generating adaptive educational content. This ability analysis includes learning history, test results, and emotion data. Based on the analysis results, the server generates personalized educational content and delivers it to the terminal.

[0801] The device uses its camera and microphone to acquire visual and auditory information from the learner and transmits it to an emotion recognition engine. The emotion recognition engine analyzes this data and identifies the user's emotional state in real time. Based on this emotional state, the server readjusts the educational content and review schedule, providing the learner with the most effective educational content.

[0802] The emotion recognition engine can utilize software such as the Microsoft Emotion API, enabling advanced emotion recognition. By using hardware such as smart glasses, applications in the field of elderly care are also possible. For example, if a learner faces a difficult problem and experiences anxiety or stress, the emotion recognition engine can detect this, and the server can generate learning materials that include simpler explanations and additional support.

[0803] In addition, when a caregiver recognizes that the person being cared for is feeling restless, they adjust environmental settings such as music and lighting.

[0804] Example of a prompt:

[0805] "We're looking for ideas for a smart glasses app that uses emotion recognition technology to understand the emotions of the person receiving care in real time and suggest appropriate care methods."

[0806] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0807] Step 1:

[0808] The device uses a camera and microphone to acquire visual and auditory information from the student. Input is video and audio of the student's face, and output is data converted into an appropriate digital format for transmission to the server. Data acquisition and format conversion occur in real time.

[0809] Step 2:

[0810] The server receives visual and audio information transmitted from the terminal and inputs it into the emotion recognition engine. The input is digitized video and audio data, and the output is the analyzed emotional state. The emotion recognition engine uses image analysis and audio analysis algorithms to identify specific emotions (e.g., anxiety, concentration, excitement, etc.).

[0811] Step 3:

[0812] The server analyzes the learner's abilities by combining their emotional state with past learning history and test results, and generates adaptive educational content. Inputs are learning history, test results, and emotional states, and output is customized learning materials tailored to the learner's emotions and abilities. Data combination and computation are performed using database queries and machine learning algorithms.

[0813] Step 4:

[0814] The server delivers the generated educational content to the terminal, which then displays it to the learner. The input is customized learning materials, and the output is the educational content displayed on the terminal's screen. Data transmission and display are instantaneous, allowing learners to begin learning immediately.

[0815] Step 5:

[0816] The user (learner) progresses through the learning process via a terminal and inputs questions if necessary. The input is the learner's question, and the output is the answer generated by the server. The server extracts appropriate information from its accumulated knowledge database based on the question content and forms the answer.

[0817] Step 6:

[0818] The server continuously monitors the learner's emotional state and learning progress, and readjusts the review schedule as needed. Input is real-time emotional data and progress information, while output is an updated review schedule tailored to the learner's level of understanding. Data collection and schedule updates are performed through the progress management system.

[0819] 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.

[0820] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0821] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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."

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] The following is further disclosed regarding the embodiments described above.

[0841] (Claim 1)

[0842] A means of analyzing learners' abilities based on user information,

[0843] A means for generating adaptive educational content based on the aforementioned learner ability analysis,

[0844] A means for generating answers to questions from learners based on the aforementioned generated educational content,

[0845] A means for generating an appropriate review schedule based on the learner's learning progress,

[0846] A system that includes this.

[0847] (Claim 2)

[0848] The system according to claim 1, characterized in that the aforementioned educational content is generated in a variety of media formats, including text, images, and videos.

[0849] (Claim 3)

[0850] The system according to claim 1, characterized in that the review schedule is calculated based on a curve that optimizes memory retention.

[0851] "Example 1"

[0852] (Claim 1)

[0853] A means of evaluating learners' abilities based on user information,

[0854] A means for generating adaptive educational resources based on the assessment of the learners' abilities,

[0855] Based on the aforementioned generated educational resources, a means for generating responses to inquiries from learners,

[0856] A means for creating an appropriate review plan based on the learner's learning progress,

[0857] A means of using artificial intelligence to assist in responding to user questions,

[0858] A means of delivering educational resources in diverse media formats to suit the learning style of the learners,

[0859] A system that includes this.

[0860] (Claim 2)

[0861] The system according to claim 1, characterized in that the aforementioned educational resources are generated in a variety of media formats, including text, still images, and moving images.

[0862] (Claim 3)

[0863] The system according to claim 1, characterized in that the review plan is calculated based on a curve for optimizing memory retention.

[0864] "Application Example 1"

[0865] (Claim 1)

[0866] A means of analyzing learners' abilities based on user information,

[0867] A means for generating adaptive educational content based on the aforementioned learner ability analysis,

[0868] A means for generating answers to questions from learners based on the aforementioned generated educational content,

[0869] A means for generating an appropriate review schedule based on the learner's learning progress,

[0870] A means for detecting the learner's pronunciation via a voice control component and providing real-time feedback,

[0871] A system that includes this.

[0872] (Claim 2)

[0873] The system according to claim 1, characterized in that the aforementioned educational content is generated in a variety of media formats, including text, images, and videos.

[0874] (Claim 3)

[0875] The system according to claim 1, characterized in that the review schedule is calculated based on a curve that optimizes memory retention.

[0876] "Example 2 of combining an emotion engine"

[0877] (Claim 1)

[0878] A means of analyzing learners' abilities based on user information,

[0879] A means for generating individualized educational content based on the learner's ability analysis and emotional data,

[0880] Based on the aforementioned generated educational content, a means for generating responses to questions from learners,

[0881] An emotion analysis device that recognizes the learner's emotional state in real time,

[0882] A means of dynamically readjusting educational content based on emotion analysis results,

[0883] A means for generating an adaptive review schedule based on the learner's learning progress and emotional information,

[0884] A system that includes this.

[0885] (Claim 2)

[0886] The system according to claim 1, characterized in that the aforementioned educational content is generated in a variety of media formats, including text, images, and videos.

[0887] (Claim 3)

[0888] The system according to claim 1, characterized in that the review schedule is calculated based on a curve that optimizes memory retention and is further flexibly adjusted based on the emotional data.

[0889] "Application example 2 when combining with an emotional engine"

[0890] (Claim 1)

[0891] A means of analyzing the abilities of students based on user information,

[0892] A means for generating adaptive educational content based on the ability analysis of the aforementioned student,

[0893] A means of acquiring emotional data and recognizing the emotional state of the educated person in real time,

[0894] Means for readjusting educational content based on the aforementioned emotional state,

[0895] Based on the aforementioned revised educational content, a means for generating answers to questions from learners,

[0896] A means for generating an appropriate review schedule based on the learning progress of the aforementioned student,

[0897] A system that includes this.

[0898] (Claim 2)

[0899] The system according to claim 1, characterized in that the aforementioned educational content is generated in multiple media formats, and the environmental settings are adjusted according to the emotional state of the student.

[0900] (Claim 3)

[0901] The system according to claim 1, characterized in that the aforementioned review schedule is calculated based on an algorithm for optimizing memory retention and further refined by emotional data. [Explanation of Symbols]

[0902] 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 analyzing learners' abilities based on user information, A means for generating adaptive educational content based on the aforementioned learner ability analysis, A means for generating answers to questions from learners based on the aforementioned generated educational content, A means for generating an appropriate review schedule based on the learner's learning progress, A means for detecting the learner's pronunciation via a voice control component and providing real-time feedback, A system that includes this.

2. The system according to claim 1, characterized in that the aforementioned educational content is generated in a variety of media formats, including text, images, and videos.

3. The system according to claim 1, characterized in that the review schedule is calculated based on a curve that optimizes memory retention.

Images