system

Abstract

We provide the system. [Solution] A means equipped with an algorithm that evaluates the learner's level of comprehension and concentration in real time using facial expression information, posture information, gaze information, and voice information obtained from the learner, Based on the aforementioned evaluation, a means of selecting and providing the most suitable educational materials for learners, A means of suggesting a break or a change of pace when a learner's concentration level decreases, A means of providing individualized instruction feedback to teachers or parents based on the aforementioned evaluation results, 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, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a modern educational environment, in online classes and self-study scenarios, it is difficult to grasp the understanding and concentration of learners in real time, so there is a problem that individual guidance cannot be sufficiently carried out. As a result of this problem, there is a problem that the learning effect of learners cannot be maximized.

Means for Solving the Problems

[0005] To address this challenge, the present invention provides a system that acquires learner facial expressions, posture, gaze, and voice information in real time and analyzes this information using a specialized algorithm to evaluate the learner's level of understanding and concentration. Based on the evaluation results, this system provides optimal educational materials and suggests breaks or changes of pace when concentration levels decline. Furthermore, it includes a feedback mechanism that enables individualized instruction by delivering the learner's evaluation results to teachers or guardians.

[0006] "Facial expression information" refers to data obtained from the facial features and expressions of learners, and is used to estimate their emotions and level of comprehension.

[0007] "Postural information" refers to data about the position and angle of a learner's body, and is collected to evaluate their level of concentration and attention.

[0008] "Eye-gaze information" refers to data about the movement of a learner's eyeballs and their gaze points, and is used to evaluate their level of interest in the learning material and where their attention is directed.

[0009] "Auditory information" refers to data obtained from learners' speech and voice quality, and is used to estimate emotions, comprehension, and stress levels.

[0010] "Comprehension level" is an indicator that shows how accurately learners understand the material they have studied, and it is an important element for measuring educational effectiveness.

[0011] "Concentration level" is an indicator that shows how much attention learners are paying to learning activities, and is a factor used to evaluate the efficiency of learning.

[0012] An "algorithm" is a series of calculations or processes that define the steps for solving a specific problem, and in this invention, it is used as a means of data analysis.

[0013] "Educational materials" refer to teaching materials and content provided to learners, and are selected with the aim of improving learners' understanding.

[0014] "Feedback" refers to information provided to teachers and parents regarding evaluations of learners' comprehension and concentration levels, which can be used to improve individualized instruction. [Brief explanation of the drawing]

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

Modes for Carrying Out the Invention

[0016] 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.

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

[0018] 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.

[0019] 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.

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

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

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

[0023] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0036] The educational support system of the present invention collects learners' facial expressions, posture, gaze, and voice data via terminals equipped with numerous sensors, and performs real-time analysis on a server. In a specific embodiment, the system is constructed in the following manner.

[0037] First, the device is installed where the learner is located. The device is equipped with a camera and microphone and continuously records the learner's movements and voice. This recorded data is transmitted to the server in real time.

[0038] Next, the server analyzes the received data and uses multiple algorithms to evaluate the learner's comprehension and concentration levels. For example, it uses facial recognition technology to infer emotions from the learner's facial expressions and eye-tracking technology to evaluate which learning materials they are paying attention to. It also uses speech analysis to measure stress levels and comprehension based on the intonation and content of their speech.

[0039] Based on the evaluation results generated by the server, the system dynamically selects the most suitable educational materials for each learner and provides them through the terminal. For example, it suggests advanced materials to learners with a high level of understanding, and presents basic materials and visual content to those with a lower level of understanding. Furthermore, if it determines that a learner's concentration is declining, it can also suggest short breaks or ways to refresh their mind.

[0040] Teachers and parents, who are users of the system, regularly receive personalized feedback generated by the server that is helpful for instruction. This allows users to understand the learners' progress and provide more effective instruction.

[0041] As a concrete example, consider a student taking an online math lesson. In this case, the device detects when the student's gaze is fixed on a specific problem in the textbook and sends this information to the server. The server analyzes the data and determines that the student is struggling with that problem, then provides the device with a relevant video tutorial. At the same time, the teacher is notified of which problems the student is having difficulty with, which can be used to plan individualized instruction.

[0042] In this way, the present invention makes it possible to provide effective learning support that meets the individual needs of learners.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The device uses a camera and microphone positioned in front of the learner to collect facial expression data, posture data, gaze data, and voice data in real time. This data is preprocessed with noise reduction and basic formatting before being sent to the server.

[0046] Step 2:

[0047] The server applies a facial recognition algorithm to analyze the received data. This allows it to infer emotional states and comprehension levels from the learner's face. Specifically, it analyzes facial feature points and detects changes in microexpressions.

[0048] Step 3:

[0049] The server analyzes posture and eye-tracking data to assess the learner's level of concentration. Posture data is used to detect the angle of the learner's body and head to determine if they are concentrating. Eye-tracking technology is used to identify where the learner is focusing their attention.

[0050] Step 4:

[0051] The server converts the audio data into text and uses natural language processing techniques to analyze the content and emotional tone of the speech. This allows it to obtain information that further reinforces the learner's understanding and emotional state based on the content and tone of their speech.

[0052] Step 5:

[0053] The server synthesizes these analysis results and selects the most suitable educational materials based on the learner's level of understanding and concentration. It then sends these materials to the terminal and provides them to the learner.

[0054] Step 6:

[0055] If the server determines that a learner's comprehension or concentration level is declining, it will suggest a break or provide simple refreshment methods via the terminal.

[0056] Step 7:

[0057] The server organizes all evaluation results and generates feedback on learners' progress and understanding. This feedback is provided to users, such as teachers and parents, to help them plan individualized instruction.

[0058] (Example 1)

[0059] 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."

[0060] In today's educational environment, there is a need to provide individualized instruction tailored to each learner's level of understanding and concentration. However, traditional teaching methods have presented challenges in accurately understanding and responding to learners' situations. In particular, in online learning environments where real-time situational assessment is required, there is a lack of efficient means to grasp learners' situations and provide appropriate support based on that understanding.

[0061] 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.

[0062] In this invention, the server includes a calculation means for analyzing the learner's level of recognition and attention in real time using visual and auditory information acquired from the learner; a means for dynamically selecting and supplying educational materials suitable for the learner based on the analysis results; and a means for suggesting a break or a reminder when the learner's attention level decreases. This makes it possible to provide rapid and accurate educational support according to the individual state of the learner.

[0063] "Visual information" refers to data related to the learner's facial expressions, posture, and gaze.

[0064] "Auditory information" refers to data related to the learner's voice and the surrounding sound environment.

[0065] "Recognition level" refers to an indicator that shows how well learners understand educational materials.

[0066] "Attention level" refers to an indicator that shows how much a learner is concentrating on educational materials or tasks.

[0067] "Computational means" refers to processes and technologies for analyzing information obtained from learners and evaluating their level of recognition and attention.

[0068] "Educational materials" refer to content and teaching materials designed to support learners' learning.

[0069] "Dynamic selection" refers to the process of selecting and providing educational materials in real time based on analysis results.

[0070] "Breaks or attention-gathering" refer to means of refreshing learners to restore their attention or promoting concentration.

[0071] "Feedback" refers to information used by instructors and parents for individualized instruction, based on the learner's level of awareness and concentration.

[0072] This educational support system primarily consists of three elements: a terminal, a server, and a user. During implementation, the terminal is placed in front of the learner and is equipped with a high-resolution camera and a high-sensitivity microphone. This terminal is designed to acquire the learner's visual and auditory information in real time and immediately transmit this information to the server.

[0073] The server possesses powerful processing capabilities and analyzes received data using multiple analytical algorithms. Specifically, it estimates emotions from facial expressions using facial recognition technology and identifies points of gaze using eye-tracking technology. In addition, it evaluates prosody (sound accent and intonation) and speed through speech analysis, thereby quantifying the learner's level of recognition and attention. Based on these analysis results, the server dynamically selects educational materials suitable for the learner and provides them through the terminal. This selection includes content tailored to the learner's level of understanding.

[0074] Furthermore, users, such as teachers and parents, receive feedback from the server. This feedback includes detailed information about the learner's progress and necessary instruction, which can be used as a reference when developing individualized instruction plans. This allows users to support learners more effectively.

[0075] As a concrete example, consider a scenario where a student is struggling with a problem during an online math lesson. The device detects that the student is concentrating on a specific task and sends that data to the server. The server quickly analyzes this situation and determines that the student is having difficulty with the task. Based on this, the server delivers a video tutorial relevant to the device and simultaneously notifies the teacher which problem the student is having trouble with.

[0076] Utilizing a generative AI model, this system provides appropriate responses to prompts such as, "When a learner's attention is focused on a problem but they are unable to find a solution, provide appropriate learning materials and suggestions to maintain their focus."

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The device is placed in front of the learner and uses a camera and microphone to record visual information (facial expressions, posture, gaze) and auditory information (voice) in real time. The input data consists of video of the learner's face and audio of their speech. The device encrypts this data as digital data and transmits it to the server. Specifically, the camera focuses on the learner's face, and the eye-tracking sensor tracks their eye movements.

[0080] Step 2:

[0081] The server receives data sent from the terminal and performs facial expression analysis using a facial recognition algorithm. The input is visual data from the terminal, from which the server estimates the emotional state (joy, surprise, confusion, etc.). This analysis outputs results indicating the learner's recognition level and emotional state. Specifically, the server maps facial feature points and detects subtle changes in facial expression.

[0082] Step 3:

[0083] The server uses an eye-tracking algorithm to identify the learner's gaze points. The input is eye-tracking data, which generates output data indicating which learning materials the learner is paying attention to. Specifically, the server determines which part of the screen the learner's gaze is focused on based on the pattern of their eye movements.

[0084] Step 4:

[0085] The server uses a speech analysis algorithm to evaluate speech content and intonation. The input is audio data, from which it extracts and outputs information regarding stress levels and comprehension. Specifically, the server analyzes the audio waveform to evaluate speech speed and tone.

[0086] Step 5:

[0087] The server integrates these analysis results and selects educational materials suitable for the learner. The input is all the analysis results, and the output is the appropriate teaching materials and content. Specifically, the server uses a generated AI model to evaluate the relevance of the content based on the analysis data and dynamically select the materials.

[0088] Step 6:

[0089] The terminal provides learners with educational materials transmitted from the server. Input is selected materials from the server, and output is viewable or interactive educational content. Specifically, the terminal either displays the materials on its screen or provides voice instructions.

[0090] Step 7:

[0091] Teachers and parents, who are the users, are provided with feedback generated by the server. The input is the server's analysis and selection results, and the output is a detailed progress report. Specifically, the server converts the feedback into text format and distributes it to users via email or a portal.

[0092] (Application Example 1)

[0093] 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."

[0094] In today's educational environment, there is a challenge in that learning support is not adequately tailored to each learner's individual level of understanding and concentration. Furthermore, in the home learning environment, parents have limited means of monitoring their child's progress and understanding, making it difficult to provide appropriate support. Moreover, there is a lack of mechanisms to quickly identify a decline in concentration and take appropriate measures.

[0095] 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.

[0096] In this invention, the server includes processing means for evaluating comprehension and concentration levels in real time using biometric information acquired from the learner, processing means for selecting and providing optimal learning materials based on the evaluation, and processing means for suggesting a break or change of pace when concentration levels decline. This enables flexible learning support tailored to the learner's comprehension and concentration levels, thereby improving the quality of education in the home environment.

[0097] "Biometric information" is a general term for facial expressions, posture, gaze, and voice information obtained from learners, and is data used for real-time evaluation.

[0098] "Processing means" refers to devices or software that evaluate the learner's level of understanding and concentration, and based on that, provide optimal learning materials or suggest breaks and changes of pace.

[0099] The term "educator" is a general term encompassing teachers, parents, and other individuals who provide guidance to learners.

[0100] A "device" refers to a hardware device that monitors learning progress within the home and provides materials tailored to the student's level of understanding.

[0101] A "display device" refers to a screen or projector used to present dynamically selected learning materials to learners.

[0102] "Eye-tracking technology" is a technique that detects the direction of a learner's gaze and measures their level of attention to a specific object.

[0103] The system for implementing this invention monitors learners and provides learning support using devices installed in the home. The main components are a group of sensors that acquire biometric information, a central control unit (server), and a display device that presents information to learners.

[0104] The server receives biometric information from learners and evaluates their comprehension and concentration levels in real time. This utilizes technologies such as facial recognition and eye-tracking. Specifically, it analyzes emotions from facial expressions and vocalizations using cameras and microphones, and identifies points of focus from eye-tracking data. This allows the system to evaluate the learner's attention and comprehension levels and select the most appropriate learning materials.

[0105] The software used to execute the processing could include image processing libraries such as OpenCV and audio analysis tools. Leveraging these technologies, the server dynamically provides learning materials to learners, selecting and displaying materials according to their level of understanding.

[0106] When a learner's concentration level declines, the system automatically notifies the parent. This makes it easier for parents to monitor their child's learning progress and provide support as needed.

[0107] As a concrete example, consider a situation where an elementary school child is working on a specific math problem while studying at home. The server detects when the child's gaze shifts away from the problem and provides a math video tutorial to the display device. It then notifies the parent which problem the child was struggling with.

[0108] Examples of prompts to input into a generative AI model:

[0109] "The child's expression looks confused. Analyze the details of the material he is focusing on and display related supplementary tutorials."

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] The device acquires the learner's biometric information using a camera and microphone. It captures the learner's facial expressions, posture, gaze, and voice data as input and sends it to the server. The device collects this data and transfers it to the server in real time.

[0113] Step 2:

[0114] The server analyzes the received data. The input data includes the learner's facial expressions and voice information, which are used to evaluate their comprehension and concentration levels. Data processing involves facial recognition using an image processing library (e.g., OpenCV) and identifying the point of focus using eye-tracking technology. The output here is a numerical evaluation of the learner's current comprehension and concentration levels.

[0115] Step 3:

[0116] The server selects the most suitable learning materials for the learner based on the evaluation results. The comprehension evaluation results are used as input, and appropriate materials are searched and selected from the server's material database accordingly. The output is the content data of the selected learning materials.

[0117] Step 4:

[0118] The terminal provides selected learning materials to the learner via a display device. The input here is content data received from the server, and the output is the display of learning materials on the learner's screen. In this process, the learning materials are dynamically displayed using a display device.

[0119] Step 5:

[0120] When the server determines that a learner's concentration level has decreased, it sends a notification to the parent. The criteria for determining the decrease in concentration are used as input, and the output is a message sent to the parent through the notification system. This notification also includes information about which learning material caused the problem.

[0121] 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.

[0122] This invention relates to an educational support system that incorporates an emotion engine to recognize learners' emotions in real time and enhance learning effectiveness. This system is equipped with multiple sensors and analysis modules to acquire learners' facial expressions, posture, gaze, and voice in real time and detect changes in their emotions.

[0123] First, the camera and microphone installed on the device capture the learner's micro-expressions and vocal intonation. This data is then sent from the device to the server. The server uses the received data to activate the emotion engine. The emotion engine analyzes the subtle movements of facial muscles and specific tones of the voice to infer the learner's emotional state.

[0124] The server uses the results of the emotion engine to evaluate the learner's level of understanding and concentration in detail. In particular, it can capture emotional changes during learning and identify where the learner is feeling confused, stressed, or excited. The server aggregates this information, selects educational materials that correspond to the learner's specific emotional state, and sends them to the terminal.

[0125] The device directly provides learners with feedback based on evaluation results from the emotion engine and offers learning materials tailored to their situation. For example, if a learner feels anxious about a new concept, it will present additional materials to reinforce that learning content. It can also suggest short relaxation techniques in response to a decrease in concentration.

[0126] Teachers and parents, who are users of the system, receive feedback from the server regarding the learners' emotional state and progress. This allows teachers to understand how stressed learners are during their studies and to refine their individualized instruction.

[0127] For example, if the emotion engine detects an increase in stress levels while a learner is tackling a difficult physics problem, the server can provide guidance and visual explanations to change their approach to the problem. Furthermore, once the learner solves the problem, positive feedback can be provided based on their emotional changes, reinforcing their sense of accomplishment.

[0128] In this way, the present invention utilizes an emotion engine to realize flexible and effective educational support that responds to the learner's emotional state.

[0129] The following describes the processing flow.

[0130] Step 1:

[0131] The device uses a camera to capture the learner's face, tracking facial muscle movements and gaze direction in real time. Simultaneously, it uses a microphone to record the learner's voice. This data is preprocessed with noise reduction before being sent to the server.

[0132] Step 2:

[0133] The server inputs the received data into an emotion engine to analyze the learner's emotional state. Specifically, it analyzes micro-expressions using a facial recognition algorithm and evaluates vocal intonation through voice analysis. This allows it to estimate the emotions the learner is feeling, such as joy, anxiety, and their level of concentration.

[0134] Step 3:

[0135] Based on the analysis results, the server comprehensively evaluates the learner's emotional state, comprehension level, and concentration level. It identifies where the learner is finding the material difficult and determines the optimal countermeasures. For example, if it determines that the learner has a low level of understanding of a difficult concept, it selects supplementary materials or easy-to-understand explanatory videos.

[0136] Step 4:

[0137] The server sends selected educational materials and instructions to the terminal and presents them to the learner. The terminal displays the materials in a format that is easy for the user (learner) to view, and if necessary, suggests breaks or relaxation activities in a pop-up format.

[0138] Step 5:

[0139] The server continuously monitors the learner's emotional state and reports real-time feedback to teachers and parents. This allows teachers and parents to understand the learner's progress and emotional changes, and use this information to plan individualized instruction.

[0140] Step 6:

[0141] When a learner completes an assignment, the device summarizes their final emotional state and learning outcomes and sends them to the server. The server analyzes this data, generates a final report, and shares it with the user (teacher or parent). This facilitates the planning of the next learning step.

[0142] (Example 2)

[0143] 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".

[0144] Traditional educational support systems have struggled to grasp learners' emotional states and changes in comprehension in real time and to provide immediate, appropriate feedback and learning materials. Furthermore, they lacked the flexibility to adapt to learners' concentration levels, making it difficult to provide support tailored to individual learning progress and emotional needs. This resulted in challenges such as an inability to improve learning efficiency and provide instruction that meets the individual needs of learners.

[0145] 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.

[0146] In this invention, the server includes means equipped with an algorithm that analyzes the learner's emotional state and comprehension level in real time using facial expression data, posture data, gaze data, and voice data acquired from the learner; means for selecting and providing educational resources optimized for the learner based on the analysis results; and means having a function to suggest a way to take a break or a way to change the learner's mood when their concentration level decreases. This enables flexible and effective educational support tailored to the emotional state and concentration level of each individual learner.

[0147] "Facial expression data" refers to information about the learner's micro-expressions and facial muscle movements acquired through sensors such as cameras.

[0148] "Posture data" refers to information about the learner's body position, movement, and changes in posture, and this data is used to analyze the learner's condition.

[0149] "Eye-tracking data" refers to information about the direction of a learner's gaze and changes in their viewpoint, obtained using eye-tracking technology.

[0150] "Audio data" refers to information about the learner's voice, including tone, pitch, and rhythm, which enables the analysis of their emotional state.

[0151] "Emotional state" refers to the learner's emotional changes and current emotional responses, and is a mental state inferred from micro-expressions, tone of voice, and other factors.

[0152] "Understanding status" refers to information indicating the extent to which a learner understands the current learning material, and is estimated by an analysis algorithm.

[0153] "Educational resources" refer to teaching materials, learning activity-related information, and support tools provided to learners, and are selected according to the learners' needs and circumstances.

[0154] An "analysis algorithm" is a computational method used to analyze data and to analyze and infer the emotional state and comprehension level of learners.

[0155] "Break methods" refer to temporary activities or guidelines suggested to alleviate fatigue and stress during learning.

[0156] "Mood-changing techniques" refer to methods of interrupting activities or introducing new stimuli, which are proposed to help learners regain their concentration.

[0157] This system is an educational support technology that incorporates an emotion recognition engine to recognize learners' emotions in real time and enhance learning effectiveness. The terminals that make up the system use cameras and microphones to capture the learner's micro-expressions and vocal intonation. This data is transmitted to a server via the network.

[0158] The server uses emotion recognition algorithms to analyze the received data. Specifically, it employs face detection technology and facial muscle pattern analysis for facial expression recognition, and analyzes changes in voice tone and intonation for speech analysis. This allows for detailed inferences about the learner's emotional state and level of comprehension.

[0159] Based on the analysis results, the server evaluates the learner's level of understanding and concentration, and selects the most appropriate educational resources accordingly. These resources are then sent back to the terminal and provided to the learner. For example, if sentiment analysis indicates that the learner is having difficulty understanding a particular concept, the server selects supplementary materials to help them understand that concept more deeply and sends them to the terminal. Also, if a low level of concentration is detected, guidance suggesting a short break will be displayed on the terminal.

[0160] Teachers and parents, who are users of the system, receive feedback from the server regarding the learners' emotional state and learning progress. This allows teachers to provide individualized instruction based on the learners' condition.

[0161] As a concrete example of its use, when a learner is tackling a difficult mathematical problem, this system can be used to detect an increase in stress levels and provide a visual guide for problem-solving approaches to address that stress.

[0162] An example of a prompt statement is, "Provide appropriate materials when learners show an emotional response to a new concept."

[0163] In this way, this invention utilizes an emotion engine to realize a flexible and effective educational support environment that responds to the learner's emotional state.

[0164] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0165] Step 1:

[0166] The device collects the learner's real-time facial expressions and voice using a camera and microphone. As input, the learner's micro-expressions and voice tone are captured. This data is converted into a digital format. As output, digitized facial expression and voice data are generated. This provides raw data about the learner's emotional state.

[0167] Step 2:

[0168] The terminal sends the collected facial expression and audio data to the server. At this stage, encryption technology is used to ensure the security of the data. As a result, the server receives encrypted data packets. By transmitting the data, the server can obtain a dataset ready for analysis.

[0169] Step 3:

[0170] The server decodes the received data and executes an emotion analysis algorithm. Decoded facial expression data and voice data are used as input. The analysis evaluates patterns of facial muscle movement and changes in voice tone. The output provides estimated results of the learner's emotional state and comprehension level. This clarifies the learner's emotional tendencies.

[0171] Step 4:

[0172] The server evaluates the analysis results and selects the most suitable educational resources for the learner. This process is carried out by an algorithm that searches for and selects materials that fit the learner's emotional state based on the prediction results. A list of selected educational materials is generated as output. This allows the server to secure customized materials tailored to the learner.

[0173] Step 5:

[0174] The terminal receives educational resources provided by the server and presents them to the learner. The input is educational material sent from the server. The terminal displays the learning materials on its screen. The output is support materials that help the learner progress through their learning. This allows the learner to enjoy a learning experience that is appropriate to their emotional state.

[0175] Step 6:

[0176] Users receive feedback information from the server. This feedback includes the learner's emotional state and learning progress. Based on this information, users can adjust their individualized instruction strategies. As an output, specific instructional plans and strategies are formed. This allows teachers and parents to implement more effective instruction.

[0177] (Application Example 2)

[0178] 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".

[0179] In recent years, as individualized support has become increasingly important in education, it is crucial to provide flexible educational approaches that respond to learners' emotional states. However, traditional systems have struggled to accurately grasp learners' emotions and provide effective educational materials and support based on that understanding. Furthermore, learners often face the challenge of not receiving high-quality educational support even within their home environment.

[0180] 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.

[0181] This invention includes a server that uses facial expression information, posture information, gaze information, and voice information acquired from the learner to evaluate the learner's level of understanding and concentration in real time; a server that selects and provides the learner with the most appropriate educational materials based on the evaluation; and a home robot incorporating an emotion engine that analyzes the learner's emotions in real time and provides the optimal educational environment. This makes it possible for learners to receive appropriate educational support in a home environment, regardless of their emotional state.

[0182] "Facial expression information" refers to data extracted from the learner's facial expressions, including information about microexpressions and facial muscle movements.

[0183] "Postural information" refers to data that indicates the learner's body position, tilt, and movement state, including information about how they are sitting and their body movements.

[0184] "Eye-gaze information" refers to data about the learner's eye movements and points of fixation, including information indicating where they are looking.

[0185] "Auditory information" refers to data related to the learner's speech, intonation, and tone, and includes information about voice quality and speaking style.

[0186] "Evaluating in real time" means analyzing and evaluating data with virtually no delay from the moment it is acquired.

[0187] "Comprehension level" is a measure that indicates the degree to which a learner understands specific learning material.

[0188] "Concentration level" is a measure that indicates the degree to which a learner is paying attention to their studies.

[0189] "Optimal educational materials" are educational content selected to most effectively advance a learner's learning, based on their current learning situation and emotional state.

[0190] An "emotion engine" is software or an algorithm used to analyze acquired data and infer the emotional state of a learner.

[0191] A "household robot" is a device that incorporates a computer for use in a home environment and is equipped with various sensors for the purpose of educational support.

[0192] This invention provides an educational support system to maximize learners' learning effectiveness. The system is configured as follows:

[0193] The server uses facial expression, posture, gaze, and voice information acquired from the learner to run an algorithm that evaluates the learner's comprehension and concentration level in real time. This utilizes high-performance computer vision technology, with facial expression information acquired in real time via a camera and voice information captured via a microphone. The server analyzes this information and uses an emotion engine to estimate the learner's emotional state.

[0194] The terminal is responsible for selecting and providing the most suitable educational materials to the learner based on evaluation results from the server. These educational materials are retrieved in real time from a cloud-based database and displayed on the learner's device. If this device is a home robot, it can communicate interactively with the learner through its display and voice support functions.

[0195] Teachers and parents, who are users of the system, are provided with information on learners' progress and emotional state through feedback sent from the server. This helps to improve the quality of individualized instruction.

[0196] As a concrete example, if a learner feels unsure about a new concept, the educational system can provide simpler materials or animations to reinforce the learning content. Furthermore, if a learner loses focus, the robot can suggest short breaks or relaxation content to support sustained learning. An example of a prompt for a generative AI model used to make this robot assistance even more effective is: "Please come up with an encouraging message for an 8-year-old child who is struggling to understand math."

[0197] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0198] Step 1:

[0199] The server receives facial expression information, posture information, gaze information, and voice information from the learner transmitted from the terminal. This information is data captured in real time by the camera and microphone installed in the terminal. The information acquired as input is stored and prepared for analysis in the next processing step.

[0200] Step 2:

[0201] Based on the acquired information, the server uses an emotion engine to analyze the learner's emotional state in real time. It processes data related to subtle changes in facial expressions and vocal intonation using facial recognition and speech analysis technologies to generate output that evaluates comprehension and concentration levels. This output is evaluation data that indicates the learner's current state.

[0202] Step 3:

[0203] The server selects the most suitable educational materials from a cloud-based database based on evaluation data. It uses evaluation data as input and queries for appropriate learning content based on this data. The selected educational materials, which are best suited to the learner's situation, are sent to the terminal as output.

[0204] Step 4:

[0205] The terminal analyzes educational materials received from the server and presents them to the learner using the display and speakers of the home robot. The terminal receives educational materials as input and generates output that supports the learner's understanding by displaying or explaining them aloud through the user interface.

[0206] Step 5:

[0207] Teachers and parents, as users, receive feedback sent from the server to understand the learners' progress and emotional state. This feedback includes evaluation data and information on the availability of educational materials, which is used to obtain input information for adjusting individualized instruction plans. Based on this information, output is generated to determine specific instructional actions.

[0208] 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.

[0209] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0210] 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.

[0211] [Second Embodiment]

[0212] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0213] 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.

[0214] 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).

[0215] 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.

[0216] 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.

[0217] 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).

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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".

[0224] The educational support system of the present invention collects learners' facial expressions, posture, gaze, and voice data via terminals equipped with numerous sensors, and performs real-time analysis on a server. In a specific embodiment, the system is constructed in the following manner.

[0225] First, the device is installed where the learner is located. The device is equipped with a camera and microphone and continuously records the learner's movements and voice. This recorded data is transmitted to the server in real time.

[0226] Next, the server analyzes the received data and uses multiple algorithms to evaluate the learner's comprehension and concentration levels. For example, it uses facial recognition technology to infer emotions from the learner's facial expressions and eye-tracking technology to evaluate which learning materials they are paying attention to. It also uses speech analysis to measure stress levels and comprehension based on the intonation and content of their speech.

[0227] Based on the evaluation results generated by the server, the system dynamically selects the most suitable educational materials for each learner and provides them through the terminal. For example, it suggests advanced materials to learners with a high level of understanding, and presents basic materials and visual content to those with a lower level of understanding. Furthermore, if it determines that a learner's concentration is declining, it can also suggest short breaks or ways to refresh their mind.

[0228] Teachers and parents, who are users of the system, regularly receive personalized feedback generated by the server that is helpful for instruction. This allows users to understand the learners' progress and provide more effective instruction.

[0229] As a concrete example, consider a student taking an online math lesson. In this case, the device detects when the student's gaze is fixed on a specific problem in the textbook and sends this information to the server. The server analyzes the data and determines that the student is struggling with that problem, then provides the device with a relevant video tutorial. At the same time, the teacher is notified of which problems the student is having difficulty with, which can be used to plan individualized instruction.

[0230] In this way, the present invention makes it possible to provide effective learning support that meets the individual needs of learners.

[0231] The following describes the processing flow.

[0232] Step 1:

[0233] The device uses a camera and microphone positioned in front of the learner to collect facial expression data, posture data, gaze data, and voice data in real time. This data is preprocessed with noise reduction and basic formatting before being sent to the server.

[0234] Step 2:

[0235] The server applies a facial recognition algorithm to analyze the received data. This allows it to infer emotional states and comprehension levels from the learner's face. Specifically, it analyzes facial feature points and detects changes in microexpressions.

[0236] Step 3:

[0237] The server analyzes posture and eye-tracking data to assess the learner's level of concentration. Posture data is used to detect the angle of the learner's body and head to determine if they are concentrating. Eye-tracking technology is used to identify where the learner is focusing their attention.

[0238] Step 4:

[0239] The server converts the audio data into text and uses natural language processing techniques to analyze the content and emotional tone of the speech. This allows it to obtain information that further reinforces the learner's understanding and emotional state based on the content and tone of their speech.

[0240] Step 5:

[0241] The server synthesizes these analysis results and selects the most suitable educational materials based on the learner's level of understanding and concentration. It then sends these materials to the terminal and provides them to the learner.

[0242] Step 6:

[0243] If the server determines that a learner's comprehension or concentration level is declining, it will suggest a break or provide simple refreshment methods via the terminal.

[0244] Step 7:

[0245] The server organizes all evaluation results and generates feedback on learners' progress and understanding. This feedback is provided to users, such as teachers and parents, to help them plan individualized instruction.

[0246] (Example 1)

[0247] 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."

[0248] In today's educational environment, there is a need to provide individualized instruction tailored to each learner's level of understanding and concentration. However, traditional teaching methods have presented challenges in accurately understanding and responding to learners' situations. In particular, in online learning environments where real-time situational assessment is required, there is a lack of efficient means to grasp learners' situations and provide appropriate support based on that understanding.

[0249] 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.

[0250] In this invention, the server includes a calculation means for analyzing the learner's level of recognition and attention in real time using visual and auditory information acquired from the learner; a means for dynamically selecting and supplying educational materials suitable for the learner based on the analysis results; and a means for suggesting a break or a reminder when the learner's attention level decreases. This makes it possible to provide rapid and accurate educational support according to the individual state of the learner.

[0251] "Visual information" refers to data related to the learner's facial expressions, posture, and gaze.

[0252] "Auditory information" refers to data related to the learner's voice and the surrounding sound environment.

[0253] "Recognition level" refers to an indicator that shows how well learners understand educational materials.

[0254] "Attention level" refers to an indicator that shows how much a learner is concentrating on educational materials or tasks.

[0255] "Computational means" refers to processes and technologies for analyzing information obtained from learners and evaluating their level of recognition and attention.

[0256] "Educational materials" refer to content and teaching materials designed to support learners' learning.

[0257] "Dynamic selection" refers to the process of selecting and providing educational materials in real time based on analysis results.

[0258] "Breaks or attention-gathering" refer to means of refreshing learners to restore their attention or promoting concentration.

[0259] "Feedback" refers to information used by instructors and parents for individualized instruction, based on the learner's level of awareness and concentration.

[0260] This educational support system primarily consists of three elements: a terminal, a server, and a user. During implementation, the terminal is placed in front of the learner and is equipped with a high-resolution camera and a high-sensitivity microphone. This terminal is designed to acquire the learner's visual and auditory information in real time and immediately transmit this information to the server.

[0261] The server possesses powerful processing capabilities and analyzes received data using multiple analytical algorithms. Specifically, it estimates emotions from facial expressions using facial recognition technology and identifies points of gaze using eye-tracking technology. In addition, it evaluates prosody (sound accent and intonation) and speed through speech analysis, thereby quantifying the learner's level of recognition and attention. Based on these analysis results, the server dynamically selects educational materials suitable for the learner and provides them through the terminal. This selection includes content tailored to the learner's level of understanding.

[0262] Furthermore, users, such as teachers and parents, receive feedback from the server. This feedback includes detailed information about the learner's progress and necessary instruction, which can be used as a reference when developing individualized instruction plans. This allows users to support learners more effectively.

[0263] As a concrete example, consider a scenario where a student is struggling with a problem during an online math lesson. The device detects that the student is concentrating on a specific task and sends that data to the server. The server quickly analyzes this situation and determines that the student is having difficulty with the task. Based on this, the server delivers a video tutorial relevant to the device and simultaneously notifies the teacher which problem the student is having trouble with.

[0264] Utilizing a generative AI model, this system provides appropriate responses to prompts such as, "When a learner's attention is focused on a problem but they are unable to find a solution, provide appropriate learning materials and suggestions to maintain their focus."

[0265] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0266] Step 1:

[0267] The device is placed in front of the learner and uses a camera and microphone to record visual information (facial expressions, posture, gaze) and auditory information (voice) in real time. The input data consists of video of the learner's face and audio of their speech. The device encrypts this data as digital data and transmits it to the server. Specifically, the camera focuses on the learner's face, and the eye-tracking sensor tracks their eye movements.

[0268] Step 2:

[0269] The server receives data sent from the terminal and performs facial expression analysis using a facial recognition algorithm. The input is visual data from the terminal, from which the server estimates the emotional state (joy, surprise, confusion, etc.). This analysis outputs results indicating the learner's recognition level and emotional state. Specifically, the server maps facial feature points and detects subtle changes in facial expression.

[0270] Step 3:

[0271] The server uses an eye-tracking algorithm to identify the learner's gaze points. The input is eye-tracking data, which generates output data indicating which learning materials the learner is paying attention to. Specifically, the server determines which part of the screen the learner's gaze is focused on based on the pattern of their eye movements.

[0272] Step 4:

[0273] The server uses a speech analysis algorithm to evaluate speech content and intonation. The input is audio data, from which it extracts and outputs information regarding stress levels and comprehension. Specifically, the server analyzes the audio waveform to evaluate speech speed and tone.

[0274] Step 5:

[0275] The server integrates these analysis results and selects educational materials suitable for the learner. The input is all the analysis results, and the output is the appropriate teaching materials and content. Specifically, the server uses a generated AI model to evaluate the relevance of the content based on the analysis data and dynamically select the materials.

[0276] Step 6:

[0277] The terminal provides learners with educational materials transmitted from the server. Input is selected materials from the server, and output is viewable or interactive educational content. Specifically, the terminal either displays the materials on its screen or provides voice instructions.

[0278] Step 7:

[0279] Teachers and parents, who are the users, are provided with feedback generated by the server. The input is the server's analysis and selection results, and the output is a detailed progress report. Specifically, the server converts the feedback into text format and distributes it to users via email or a portal.

[0280] (Application Example 1)

[0281] 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."

[0282] In today's educational environment, there is a challenge in that learning support is not adequately tailored to each learner's individual level of understanding and concentration. Furthermore, in the home learning environment, parents have limited means of monitoring their child's progress and understanding, making it difficult to provide appropriate support. Moreover, there is a lack of mechanisms to quickly identify a decline in concentration and take appropriate measures.

[0283] 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.

[0284] In this invention, the server includes a processing means for evaluating the degree of understanding and concentration in real time using the biological information acquired from the learner, a processing means for selecting and providing optimal learning materials based on the evaluation, and a processing means for proposing a break or a mood change when the concentration decreases. As a result, flexible learning support according to the learner's degree of understanding and concentration becomes possible, and the quality of education in the home environment can be improved.

[0285] "Biological information" is a general term for facial expressions, postures, eye movements, and voice information acquired from the learner, and is data used for real-time evaluation.

[0286] "Processing means" is a device or software that evaluates the learner's degree of understanding and concentration, provides optimal learning materials based on this, and functions to propose breaks or mood changes.

[0287] "Educator" is a general term for teachers, guardians, etc. who give guidance to learners.

[0288] "Device" is a hardware device that monitors the progress of learning within the home and provides materials according to the degree of understanding.

[0289] "Display device" is a screen or projector used to present the learning materials dynamically selected for the learner.

[0290] "Eye tracking technology" is a technology for detecting the direction of the learner's gaze and measuring the degree of attention to a specific object.

[0291] The system for implementing this invention monitors the learner using a device installed in the home and provides learning support. The main components are a group of sensors for acquiring biological information, a central control device (server), and a display device for presenting information to the learner.

[0292] The server receives biometric information from learners and evaluates their comprehension and concentration levels in real time. This utilizes technologies such as facial recognition and eye-tracking. Specifically, it analyzes emotions from facial expressions and vocalizations using cameras and microphones, and identifies points of focus from eye-tracking data. This allows the system to evaluate the learner's attention and comprehension levels and select the most appropriate learning materials.

[0293] The software used to execute the processing could include image processing libraries such as OpenCV and audio analysis tools. Leveraging these technologies, the server dynamically provides learning materials to learners, selecting and displaying materials according to their level of understanding.

[0294] When a learner's concentration level declines, the system automatically notifies the parent. This makes it easier for parents to monitor their child's learning progress and provide support as needed.

[0295] As a concrete example, consider a situation where an elementary school child is working on a specific math problem while studying at home. The server detects when the child's gaze shifts away from the problem and provides a math video tutorial to the display device. It then notifies the parent which problem the child was struggling with.

[0296] Examples of prompts to input into a generative AI model:

[0297] "The child's expression looks confused. Analyze the details of the material he is focusing on and display related supplementary tutorials."

[0298] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0299] Step 1:

[0300] The terminal acquires the learner's biometric information using a camera and a microphone. It captures the learner's facial expressions, postures, eye gazes, and voice data as inputs and transmits them to the server. The terminal collects this data and performs real-time transfer to the server.

[0301] Step 2:

[0302] The server analyzes the received data. The input data includes the learner's facial expression information and voice information, and based on this, the understanding level and concentration level are evaluated. For data processing, facial expression recognition is performed using an image processing library (e.g., OpenCV), and the fixation point is identified using gaze tracking technology. The output here is the numerical evaluation of the learner's current understanding level and concentration level.

[0303] Step 3:

[0304] The server selects the most suitable learning materials for the learner based on the evaluation results. The previous understanding level evaluation is used as the input, and the appropriate teaching materials are searched and selected from the server's teaching material database accordingly. The output is the content data of the selected learning materials.

[0305] Step 4:

[0306] The terminal provides the selected learning materials to the learner through the display device. The input here is the content data received from the server, and the output is to display the teaching materials on the display screen for the learner. At this time, the teaching materials are dynamically displayed using the display device.

[0307] Step 5:

[0308] When the server determines that the learner's concentration level has decreased, it sends a countermeasure notice to the parent. The criteria for determining the decrease in concentration level are used as the input, and the output is the message sent to the parent through the notification system. This notice also describes what teaching materials the problem occurred with.

[0309] 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.

[0310] This invention relates to an educational support system that incorporates an emotion engine to recognize learners' emotions in real time and enhance learning effectiveness. This system is equipped with multiple sensors and analysis modules to acquire learners' facial expressions, posture, gaze, and voice in real time and detect changes in their emotions.

[0311] First, the camera and microphone installed on the device capture the learner's micro-expressions and vocal intonation. This data is then sent from the device to the server. The server uses the received data to activate the emotion engine. The emotion engine analyzes the subtle movements of facial muscles and specific tones of the voice to infer the learner's emotional state.

[0312] The server uses the results of the emotion engine to evaluate the learner's level of understanding and concentration in detail. In particular, it can capture emotional changes during learning and identify where the learner is feeling confused, stressed, or excited. The server aggregates this information, selects educational materials that correspond to the learner's specific emotional state, and sends them to the terminal.

[0313] The device directly provides learners with feedback based on evaluation results from the emotion engine and offers learning materials tailored to their situation. For example, if a learner feels anxious about a new concept, it will present additional materials to reinforce that learning content. It can also suggest short relaxation techniques in response to a decrease in concentration.

[0314] Teachers and parents, who are users of the system, receive feedback from the server regarding the learners' emotional state and progress. This allows teachers to understand how stressed learners are during their studies and to refine their individualized instruction.

[0315] For example, if the emotion engine detects an increase in stress levels while a learner is tackling a difficult physics problem, the server can provide guidance and visual explanations to change their approach to the problem. Furthermore, once the learner solves the problem, positive feedback can be provided based on their emotional changes, reinforcing their sense of accomplishment.

[0316] In this way, the present invention utilizes an emotion engine to realize flexible and effective educational support that responds to the learner's emotional state.

[0317] The following describes the processing flow.

[0318] Step 1:

[0319] The device uses a camera to capture the learner's face, tracking facial muscle movements and gaze direction in real time. Simultaneously, it uses a microphone to record the learner's voice. This data is preprocessed with noise reduction before being sent to the server.

[0320] Step 2:

[0321] The server inputs the received data into an emotion engine to analyze the learner's emotional state. Specifically, it analyzes micro-expressions using a facial recognition algorithm and evaluates vocal intonation through voice analysis. This allows it to estimate the emotions the learner is feeling, such as joy, anxiety, and their level of concentration.

[0322] Step 3:

[0323] Based on the analysis results, the server comprehensively evaluates the learner's emotional state, comprehension level, and concentration level. It identifies where the learner is finding the material difficult and determines the optimal countermeasures. For example, if it determines that the learner has a low level of understanding of a difficult concept, it selects supplementary materials or easy-to-understand explanatory videos.

[0324] Step 4:

[0325] The server sends selected educational materials and instructions to the terminal and presents them to the learner. The terminal displays the materials in a format that is easy for the user (learner) to view, and if necessary, suggests breaks or relaxation activities in a pop-up format.

[0326] Step 5:

[0327] The server continuously monitors the learner's emotional state and reports real-time feedback to teachers and parents. This allows teachers and parents to understand the learner's progress and emotional changes, and use this information to plan individualized instruction.

[0328] Step 6:

[0329] When a learner completes an assignment, the device summarizes their final emotional state and learning outcomes and sends them to the server. The server analyzes this data, generates a final report, and shares it with the user (teacher or parent). This facilitates the planning of the next learning step.

[0330] (Example 2)

[0331] 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".

[0332] Traditional educational support systems have struggled to grasp learners' emotional states and changes in comprehension in real time and to provide immediate, appropriate feedback and learning materials. Furthermore, they lacked the flexibility to adapt to learners' concentration levels, making it difficult to provide support tailored to individual learning progress and emotional needs. This resulted in challenges such as an inability to improve learning efficiency and provide instruction that meets the individual needs of learners.

[0333] 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.

[0334] In this invention, the server includes means equipped with an algorithm that analyzes the learner's emotional state and comprehension level in real time using facial expression data, posture data, gaze data, and voice data acquired from the learner; means for selecting and providing educational resources optimized for the learner based on the analysis results; and means having a function to suggest a way to take a break or a way to change the learner's mood when their concentration level decreases. This enables flexible and effective educational support tailored to the emotional state and concentration level of each individual learner.

[0335] "Facial expression data" refers to information about the learner's micro-expressions and facial muscle movements acquired through sensors such as cameras.

[0336] "Posture data" refers to information about the learner's body position, movement, and changes in posture, and this data is used to analyze the learner's condition.

[0337] "Eye-tracking data" refers to information about the direction of a learner's gaze and changes in their viewpoint, obtained using eye-tracking technology.

[0338] "Audio data" refers to information about the learner's voice, including tone, pitch, and rhythm, which enables the analysis of their emotional state.

[0339] "Emotional state" refers to the learner's emotional changes and current emotional responses, and is a mental state inferred from micro-expressions, tone of voice, and other factors.

[0340] "Understanding status" refers to information indicating the extent to which a learner understands the current learning material, and is estimated by an analysis algorithm.

[0341] "Educational resources" refer to teaching materials, learning activity-related information, and support tools provided to learners, and are selected according to the learners' needs and circumstances.

[0342] An "analysis algorithm" is a computational method used to analyze data and to analyze and infer the emotional state and comprehension level of learners.

[0343] "Break methods" refer to temporary activities or guidelines suggested to alleviate fatigue and stress during learning.

[0344] "Mood-changing techniques" refer to methods of interrupting activities or introducing new stimuli, which are proposed to help learners regain their concentration.

[0345] This system is an educational support technology that incorporates an emotion recognition engine to recognize learners' emotions in real time and enhance learning effectiveness. The terminals that make up the system use cameras and microphones to capture the learner's micro-expressions and vocal intonation. This data is transmitted to a server via the network.

[0346] The server uses emotion recognition algorithms to analyze the received data. Specifically, it employs face detection technology and facial muscle pattern analysis for facial expression recognition, and analyzes changes in voice tone and intonation for speech analysis. This allows for detailed inferences about the learner's emotional state and level of comprehension.

[0347] Based on the analysis results, the server evaluates the learner's level of understanding and concentration, and selects the most appropriate educational resources accordingly. These resources are then sent back to the terminal and provided to the learner. For example, if sentiment analysis indicates that the learner is having difficulty understanding a particular concept, the server selects supplementary materials to help them understand that concept more deeply and sends them to the terminal. Also, if a low level of concentration is detected, guidance suggesting a short break will be displayed on the terminal.

[0348] Teachers and parents, who are users of the system, receive feedback from the server regarding the learners' emotional state and learning progress. This allows teachers to provide individualized instruction based on the learners' condition.

[0349] As a concrete example of its use, when a learner is tackling a difficult mathematical problem, this system can be used to detect an increase in stress levels and provide a visual guide for problem-solving approaches to address that stress.

[0350] An example of a prompt statement is, "Provide appropriate materials when learners show an emotional response to a new concept."

[0351] In this way, this invention utilizes an emotion engine to realize a flexible and effective educational support environment that responds to the learner's emotional state.

[0352] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0353] Step 1:

[0354] The device collects the learner's real-time facial expressions and voice using a camera and microphone. As input, the learner's micro-expressions and voice tone are captured. This data is converted into a digital format. As output, digitized facial expression and voice data are generated. This provides raw data about the learner's emotional state.

[0355] Step 2:

[0356] The terminal sends the collected facial expression and audio data to the server. At this stage, encryption technology is used to ensure the security of the data. As a result, the server receives encrypted data packets. By transmitting the data, the server can obtain a dataset ready for analysis.

[0357] Step 3:

[0358] The server decodes the received data and executes an emotion analysis algorithm. Decoded facial expression data and voice data are used as input. The analysis evaluates patterns of facial muscle movement and changes in voice tone. The output provides estimated results of the learner's emotional state and comprehension level. This clarifies the learner's emotional tendencies.

[0359] Step 4:

[0360] The server evaluates the analysis results and selects the most suitable educational resources for the learner. This process is carried out by an algorithm that searches for and selects materials that fit the learner's emotional state based on the prediction results. A list of selected educational materials is generated as output. This allows the server to secure customized materials tailored to the learner.

[0361] Step 5:

[0362] The terminal receives educational resources provided by the server and presents them to the learner. The input is educational material sent from the server. The terminal displays the learning materials on its screen. The output is support materials that help the learner progress through their learning. This allows the learner to enjoy a learning experience that is appropriate to their emotional state.

[0363] Step 6:

[0364] Users receive feedback information from the server. This feedback includes the learner's emotional state and learning progress. Based on this information, users can adjust their individualized instruction strategies. As an output, specific instructional plans and strategies are formed. This allows teachers and parents to implement more effective instruction.

[0365] (Application Example 2)

[0366] 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."

[0367] In recent years, as individualized support has become increasingly important in education, it is crucial to provide flexible educational approaches that respond to learners' emotional states. However, traditional systems have struggled to accurately grasp learners' emotions and provide effective educational materials and support based on that understanding. Furthermore, learners often face the challenge of not receiving high-quality educational support even within their home environment.

[0368] 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.

[0369] This invention includes a server that uses facial expression information, posture information, gaze information, and voice information acquired from the learner to evaluate the learner's level of understanding and concentration in real time; a server that selects and provides the learner with the most appropriate educational materials based on the evaluation; and a home robot incorporating an emotion engine that analyzes the learner's emotions in real time and provides the optimal educational environment. This makes it possible for learners to receive appropriate educational support in a home environment, regardless of their emotional state.

[0370] "Facial expression information" refers to data extracted from the learner's facial expressions, including information about microexpressions and facial muscle movements.

[0371] "Postural information" refers to data that indicates the learner's body position, tilt, and movement state, including information about how they are sitting and their body movements.

[0372] "Eye-gaze information" refers to data about the learner's eye movements and points of fixation, including information indicating where they are looking.

[0373] "Auditory information" refers to data related to the learner's speech, intonation, and tone, and includes information about voice quality and speaking style.

[0374] "Evaluating in real time" means analyzing and evaluating data with virtually no delay from the moment it is acquired.

[0375] "Comprehension level" is a measure that indicates the degree to which a learner understands specific learning material.

[0376] "Concentration level" is a measure that indicates the degree to which a learner is paying attention to their studies.

[0377] "Optimal educational materials" are educational content selected to most effectively advance a learner's learning, based on their current learning situation and emotional state.

[0378] An "emotion engine" is software or an algorithm used to analyze acquired data and infer the emotional state of a learner.

[0379] A "household robot" is a device that incorporates a computer for use in a home environment and is equipped with various sensors for the purpose of educational support.

[0380] This invention provides an educational support system to maximize learners' learning effectiveness. The system is configured as follows:

[0381] The server uses facial expression, posture, gaze, and voice information acquired from the learner to run an algorithm that evaluates the learner's comprehension and concentration level in real time. This utilizes high-performance computer vision technology, with facial expression information acquired in real time via a camera and voice information captured via a microphone. The server analyzes this information and uses an emotion engine to estimate the learner's emotional state.

[0382] The terminal is responsible for selecting and providing the most suitable educational materials to the learner based on evaluation results from the server. These educational materials are retrieved in real time from a cloud-based database and displayed on the learner's device. If this device is a home robot, it can communicate interactively with the learner through its display and voice support functions.

[0383] Teachers and parents, who are users of the system, are provided with information on learners' progress and emotional state through feedback sent from the server. This helps to improve the quality of individualized instruction.

[0384] As a concrete example, if a learner feels unsure about a new concept, the educational system can provide simpler materials or animations to reinforce the learning content. Furthermore, if a learner loses focus, the robot can suggest short breaks or relaxation content to support sustained learning. An example of a prompt for a generative AI model used to make this robot assistance even more effective is: "Please come up with an encouraging message for an 8-year-old child who is struggling to understand math."

[0385] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0386] Step 1:

[0387] The server receives facial expression information, posture information, gaze information, and voice information from the learner transmitted from the terminal. This information is data captured in real time by the camera and microphone installed in the terminal. The information acquired as input is stored and prepared for analysis in the next processing step.

[0388] Step 2:

[0389] Based on the acquired information, the server uses an emotion engine to analyze the learner's emotional state in real time. It processes data related to subtle changes in facial expressions and vocal intonation using facial recognition and speech analysis technologies to generate output that evaluates comprehension and concentration levels. This output is evaluation data that indicates the learner's current state.

[0390] Step 3:

[0391] The server selects the most suitable educational materials from a cloud-based database based on evaluation data. It uses evaluation data as input and queries for appropriate learning content based on this data. The selected educational materials, which are best suited to the learner's situation, are sent to the terminal as output.

[0392] Step 4:

[0393] The terminal analyzes educational materials received from the server and presents them to the learner using the display and speakers of the home robot. The terminal receives educational materials as input and generates output that supports the learner's understanding by displaying or explaining them aloud through the user interface.

[0394] Step 5:

[0395] Teachers and parents, as users, receive feedback sent from the server to understand the learners' progress and emotional state. This feedback includes evaluation data and information on the availability of educational materials, which is used to obtain input information for adjusting individualized instruction plans. Based on this information, output is generated to determine specific instructional actions.

[0396] 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.

[0397] 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.

[0398] 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.

[0399] [Third Embodiment]

[0400] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0401] 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.

[0402] 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).

[0403] 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.

[0404] 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.

[0405] 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).

[0406] 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.

[0407] 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.

[0408] 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.

[0409] 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.

[0410] 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.

[0411] 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".

[0412] The educational support system of the present invention collects learners' facial expressions, posture, gaze, and voice data via terminals equipped with numerous sensors, and performs real-time analysis on a server. In a specific embodiment, the system is constructed in the following manner.

[0413] First, the device is installed where the learner is located. The device is equipped with a camera and microphone and continuously records the learner's movements and voice. This recorded data is transmitted to the server in real time.

[0414] Next, the server analyzes the received data and uses multiple algorithms to evaluate the learner's comprehension and concentration levels. For example, it uses facial recognition technology to infer emotions from the learner's facial expressions and eye-tracking technology to evaluate which learning materials they are paying attention to. It also uses speech analysis to measure stress levels and comprehension based on the intonation and content of their speech.

[0415] Based on the evaluation results generated by the server, the system dynamically selects the most suitable educational materials for each learner and provides them through the terminal. For example, it suggests advanced materials to learners with a high level of understanding, and presents basic materials and visual content to those with a lower level of understanding. Furthermore, if it determines that a learner's concentration is declining, it can also suggest short breaks or ways to refresh their mind.

[0416] Teachers and parents, who are users of the system, regularly receive personalized feedback generated by the server that is helpful for instruction. This allows users to understand the learners' progress and provide more effective instruction.

[0417] As a concrete example, consider a student taking an online math lesson. In this case, the device detects when the student's gaze is fixed on a specific problem in the textbook and sends this information to the server. The server analyzes the data and determines that the student is struggling with that problem, then provides the device with a relevant video tutorial. At the same time, the teacher is notified of which problems the student is having difficulty with, which can be used to plan individualized instruction.

[0418] In this way, the present invention makes it possible to provide effective learning support that meets the individual needs of learners.

[0419] The following describes the processing flow.

[0420] Step 1:

[0421] The device uses a camera and microphone positioned in front of the learner to collect facial expression data, posture data, gaze data, and voice data in real time. This data is preprocessed with noise reduction and basic formatting before being sent to the server.

[0422] Step 2:

[0423] The server applies a facial recognition algorithm to analyze the received data. This allows it to infer emotional states and comprehension levels from the learner's face. Specifically, it analyzes facial feature points and detects changes in microexpressions.

[0424] Step 3:

[0425] The server analyzes posture and eye-tracking data to assess the learner's level of concentration. Posture data is used to detect the angle of the learner's body and head to determine if they are concentrating. Eye-tracking technology is used to identify where the learner is focusing their attention.

[0426] Step 4:

[0427] The server converts the audio data into text and uses natural language processing techniques to analyze the content and emotional tone of the speech. This allows it to obtain information that further reinforces the learner's understanding and emotional state based on the content and tone of their speech.

[0428] Step 5:

[0429] The server synthesizes these analysis results and selects the most suitable educational materials based on the learner's level of understanding and concentration. It then sends these materials to the terminal and provides them to the learner.

[0430] Step 6:

[0431] If the server determines that a learner's comprehension or concentration level is declining, it will suggest a break or provide simple refreshment methods via the terminal.

[0432] Step 7:

[0433] The server organizes all evaluation results and generates feedback on learners' progress and understanding. This feedback is provided to users, such as teachers and parents, to help them plan individualized instruction.

[0434] (Example 1)

[0435] 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."

[0436] In today's educational environment, there is a need to provide individualized instruction tailored to each learner's level of understanding and concentration. However, traditional teaching methods have presented challenges in accurately understanding and responding to learners' situations. In particular, in online learning environments where real-time situational assessment is required, there is a lack of efficient means to grasp learners' situations and provide appropriate support based on that understanding.

[0437] 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.

[0438] In this invention, the server includes a calculation means for analyzing the learner's level of recognition and attention in real time using visual and auditory information acquired from the learner; a means for dynamically selecting and supplying educational materials suitable for the learner based on the analysis results; and a means for suggesting a break or a reminder when the learner's attention level decreases. This makes it possible to provide rapid and accurate educational support according to the individual state of the learner.

[0439] "Visual information" refers to data related to the learner's facial expressions, posture, and gaze.

[0440] "Auditory information" refers to data related to the learner's voice and the surrounding sound environment.

[0441] "Recognition level" refers to an indicator that shows how well learners understand educational materials.

[0442] "Attention level" refers to an indicator that shows how much a learner is concentrating on educational materials or tasks.

[0443] "Computational means" refers to processes and technologies for analyzing information obtained from learners and evaluating their level of recognition and attention.

[0444] "Educational materials" refer to content and teaching materials designed to support learners' learning.

[0445] "Dynamic selection" refers to the process of selecting and providing educational materials in real time based on analysis results.

[0446] "Breaks or attention-gathering" refer to means of refreshing learners to restore their attention or promoting concentration.

[0447] "Feedback" refers to information used by instructors and parents for individualized instruction, based on the learner's level of awareness and concentration.

[0448] This educational support system primarily consists of three elements: a terminal, a server, and a user. During implementation, the terminal is placed in front of the learner and is equipped with a high-resolution camera and a high-sensitivity microphone. This terminal is designed to acquire the learner's visual and auditory information in real time and immediately transmit this information to the server.

[0449] The server possesses powerful processing capabilities and analyzes received data using multiple analytical algorithms. Specifically, it estimates emotions from facial expressions using facial recognition technology and identifies points of gaze using eye-tracking technology. In addition, it evaluates prosody (sound accent and intonation) and speed through speech analysis, thereby quantifying the learner's level of recognition and attention. Based on these analysis results, the server dynamically selects educational materials suitable for the learner and provides them through the terminal. This selection includes content tailored to the learner's level of understanding.

[0450] Furthermore, users, such as teachers and parents, receive feedback from the server. This feedback includes detailed information about the learner's progress and necessary instruction, which can be used as a reference when developing individualized instruction plans. This allows users to support learners more effectively.

[0451] As a concrete example, consider a scenario where a student is struggling with a problem during an online math lesson. The device detects that the student is concentrating on a specific task and sends that data to the server. The server quickly analyzes this situation and determines that the student is having difficulty with the task. Based on this, the server delivers a video tutorial relevant to the device and simultaneously notifies the teacher which problem the student is having trouble with.

[0452] Utilizing a generative AI model, this system provides appropriate responses to prompts such as, "When a learner's attention is focused on a problem but they are unable to find a solution, provide appropriate learning materials and suggestions to maintain their focus."

[0453] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0454] Step 1:

[0455] The device is placed in front of the learner and uses a camera and microphone to record visual information (facial expressions, posture, gaze) and auditory information (voice) in real time. The input data consists of video of the learner's face and audio of their speech. The device encrypts this data as digital data and transmits it to the server. Specifically, the camera focuses on the learner's face, and the eye-tracking sensor tracks their eye movements.

[0456] Step 2:

[0457] The server receives data sent from the terminal and performs facial expression analysis using a facial recognition algorithm. The input is visual data from the terminal, from which the server estimates the emotional state (joy, surprise, confusion, etc.). This analysis outputs results indicating the learner's recognition level and emotional state. Specifically, the server maps facial feature points and detects subtle changes in facial expression.

[0458] Step 3:

[0459] The server uses an eye-tracking algorithm to identify the learner's gaze points. The input is eye-tracking data, which generates output data indicating which learning materials the learner is paying attention to. Specifically, the server determines which part of the screen the learner's gaze is focused on based on the pattern of their eye movements.

[0460] Step 4:

[0461] The server uses a speech analysis algorithm to evaluate speech content and intonation. The input is audio data, from which it extracts and outputs information regarding stress levels and comprehension. Specifically, the server analyzes the audio waveform to evaluate speech speed and tone.

[0462] Step 5:

[0463] The server integrates these analysis results and selects educational materials suitable for the learner. The input is all the analysis results, and the output is the appropriate teaching materials and content. Specifically, the server uses a generated AI model to evaluate the relevance of the content based on the analysis data and dynamically select the materials.

[0464] Step 6:

[0465] The terminal provides learners with educational materials transmitted from the server. Input is selected materials from the server, and output is viewable or interactive educational content. Specifically, the terminal either displays the materials on its screen or provides voice instructions.

[0466] Step 7:

[0467] Teachers and parents, who are the users, are provided with feedback generated by the server. The input is the server's analysis and selection results, and the output is a detailed progress report. Specifically, the server converts the feedback into text format and distributes it to users via email or a portal.

[0468] (Application Example 1)

[0469] 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."

[0470] In today's educational environment, there is a challenge in that learning support is not adequately tailored to each learner's individual level of understanding and concentration. Furthermore, in the home learning environment, parents have limited means of monitoring their child's progress and understanding, making it difficult to provide appropriate support. Moreover, there is a lack of mechanisms to quickly identify a decline in concentration and take appropriate measures.

[0471] 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.

[0472] In this invention, the server includes processing means for evaluating comprehension and concentration levels in real time using biometric information acquired from the learner, processing means for selecting and providing optimal learning materials based on the evaluation, and processing means for suggesting a break or change of pace when concentration levels decline. This enables flexible learning support tailored to the learner's comprehension and concentration levels, thereby improving the quality of education in the home environment.

[0473] "Biometric information" is a general term for facial expressions, posture, gaze, and voice information obtained from learners, and is data used for real-time evaluation.

[0474] "Processing means" refers to devices or software that evaluate the learner's level of understanding and concentration, and based on that, provide optimal learning materials or suggest breaks and changes of pace.

[0475] The term "educator" is a general term encompassing teachers, parents, and other individuals who provide guidance to learners.

[0476] A "device" refers to a hardware device that monitors learning progress within the home and provides materials tailored to the student's level of understanding.

[0477] A "display device" refers to a screen or projector used to present dynamically selected learning materials to learners.

[0478] "Eye-tracking technology" is a technique that detects the direction of a learner's gaze and measures their level of attention to a specific object.

[0479] The system for implementing this invention monitors learners and provides learning support using devices installed in the home. The main components are a group of sensors that acquire biometric information, a central control unit (server), and a display device that presents information to learners.

[0480] The server receives biometric information from learners and evaluates their comprehension and concentration levels in real time. This utilizes technologies such as facial recognition and eye-tracking. Specifically, it analyzes emotions from facial expressions and vocalizations using cameras and microphones, and identifies points of focus from eye-tracking data. This allows the system to evaluate the learner's attention and comprehension levels and select the most appropriate learning materials.

[0481] The software used to execute the processing could include image processing libraries such as OpenCV and audio analysis tools. Leveraging these technologies, the server dynamically provides learning materials to learners, selecting and displaying materials according to their level of understanding.

[0482] When a learner's concentration level declines, the system automatically notifies the parent. This makes it easier for parents to monitor their child's learning progress and provide support as needed.

[0483] As a concrete example, consider a situation where an elementary school child is working on a specific math problem while studying at home. The server detects when the child's gaze shifts away from the problem and provides a math video tutorial to the display device. It then notifies the parent which problem the child was struggling with.

[0484] Examples of prompts to input into a generative AI model:

[0485] "The child's expression looks confused. Analyze the details of the material he is focusing on and display related supplementary tutorials."

[0486] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0487] Step 1:

[0488] The device acquires the learner's biometric information using a camera and microphone. It captures the learner's facial expressions, posture, gaze, and voice data as input and sends it to the server. The device collects this data and transfers it to the server in real time.

[0489] Step 2:

[0490] The server analyzes the received data. The input data includes the learner's facial expressions and voice information, which are used to evaluate their comprehension and concentration levels. Data processing involves facial recognition using an image processing library (e.g., OpenCV) and identifying the point of focus using eye-tracking technology. The output here is a numerical evaluation of the learner's current comprehension and concentration levels.

[0491] Step 3:

[0492] The server selects the most suitable learning materials for the learner based on the evaluation results. The comprehension evaluation results are used as input, and appropriate materials are searched and selected from the server's material database accordingly. The output is the content data of the selected learning materials.

[0493] Step 4:

[0494] The terminal provides selected learning materials to the learner via a display device. The input here is content data received from the server, and the output is the display of learning materials on the learner's screen. In this process, the learning materials are dynamically displayed using a display device.

[0495] Step 5:

[0496] When the server determines that a learner's concentration level has decreased, it sends a notification to the parent. The criteria for determining the decrease in concentration are used as input, and the output is a message sent to the parent through the notification system. This notification also includes information about which learning material caused the problem.

[0497] 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.

[0498] This invention relates to an educational support system that incorporates an emotion engine to recognize learners' emotions in real time and enhance learning effectiveness. This system is equipped with multiple sensors and analysis modules to acquire learners' facial expressions, posture, gaze, and voice in real time and detect changes in their emotions.

[0499] First, the camera and microphone installed on the device capture the learner's micro-expressions and vocal intonation. This data is then sent from the device to the server. The server uses the received data to activate the emotion engine. The emotion engine analyzes the subtle movements of facial muscles and specific tones of the voice to infer the learner's emotional state.

[0500] The server uses the results of the emotion engine to evaluate the learner's level of understanding and concentration in detail. In particular, it can capture emotional changes during learning and identify where the learner is feeling confused, stressed, or excited. The server aggregates this information, selects educational materials that correspond to the learner's specific emotional state, and sends them to the terminal.

[0501] The device directly provides learners with feedback based on evaluation results from the emotion engine and offers learning materials tailored to their situation. For example, if a learner feels anxious about a new concept, it will present additional materials to reinforce that learning content. It can also suggest short relaxation techniques in response to a decrease in concentration.

[0502] Teachers and parents, who are users of the system, receive feedback from the server regarding the learners' emotional state and progress. This allows teachers to understand how stressed learners are during their studies and to refine their individualized instruction.

[0503] For example, if the emotion engine detects an increase in stress levels while a learner is tackling a difficult physics problem, the server can provide guidance and visual explanations to change their approach to the problem. Furthermore, once the learner solves the problem, positive feedback can be provided based on their emotional changes, reinforcing their sense of accomplishment.

[0504] In this way, the present invention utilizes an emotion engine to realize flexible and effective educational support that responds to the learner's emotional state.

[0505] The following describes the processing flow.

[0506] Step 1:

[0507] The device uses a camera to capture the learner's face, tracking facial muscle movements and gaze direction in real time. Simultaneously, it uses a microphone to record the learner's voice. This data is preprocessed with noise reduction before being sent to the server.

[0508] Step 2:

[0509] The server inputs the received data into an emotion engine to analyze the learner's emotional state. Specifically, it analyzes micro-expressions using a facial recognition algorithm and evaluates vocal intonation through voice analysis. This allows it to estimate the emotions the learner is feeling, such as joy, anxiety, and their level of concentration.

[0510] Step 3:

[0511] Based on the analysis results, the server comprehensively evaluates the learner's emotional state, comprehension level, and concentration level. It identifies where the learner is finding the material difficult and determines the optimal countermeasures. For example, if it determines that the learner has a low level of understanding of a difficult concept, it selects supplementary materials or easy-to-understand explanatory videos.

[0512] Step 4:

[0513] The server sends selected educational materials and instructions to the terminal and presents them to the learner. The terminal displays the materials in a format that is easy for the user (learner) to view, and if necessary, suggests breaks or relaxation activities in a pop-up format.

[0514] Step 5:

[0515] The server continuously monitors the learner's emotional state and reports real-time feedback to teachers and parents. This allows teachers and parents to understand the learner's progress and emotional changes, and use this information to plan individualized instruction.

[0516] Step 6:

[0517] When a learner completes an assignment, the device summarizes their final emotional state and learning outcomes and sends them to the server. The server analyzes this data, generates a final report, and shares it with the user (teacher or parent). This facilitates the planning of the next learning step.

[0518] (Example 2)

[0519] 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."

[0520] Traditional educational support systems have struggled to grasp learners' emotional states and changes in comprehension in real time and to provide immediate, appropriate feedback and learning materials. Furthermore, they lacked the flexibility to adapt to learners' concentration levels, making it difficult to provide support tailored to individual learning progress and emotional needs. This resulted in challenges such as an inability to improve learning efficiency and provide instruction that meets the individual needs of learners.

[0521] 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.

[0522] In this invention, the server includes means equipped with an algorithm that analyzes the learner's emotional state and comprehension level in real time using facial expression data, posture data, gaze data, and voice data acquired from the learner; means for selecting and providing educational resources optimized for the learner based on the analysis results; and means having a function to suggest a way to take a break or a way to change the learner's mood when their concentration level decreases. This enables flexible and effective educational support tailored to the emotional state and concentration level of each individual learner.

[0523] "Facial expression data" refers to information about the learner's micro-expressions and facial muscle movements acquired through sensors such as cameras.

[0524] "Posture data" refers to information about the learner's body position, movement, and changes in posture, and this data is used to analyze the learner's condition.

[0525] "Eye-tracking data" refers to information about the direction of a learner's gaze and changes in their viewpoint, obtained using eye-tracking technology.

[0526] "Audio data" refers to information about the learner's voice, including tone, pitch, and rhythm, which enables the analysis of their emotional state.

[0527] "Emotional state" refers to the learner's emotional changes and current emotional responses, and is a mental state inferred from micro-expressions, tone of voice, and other factors.

[0528] "Understanding status" refers to information indicating the extent to which a learner understands the current learning material, and is estimated by an analysis algorithm.

[0529] "Educational resources" refer to teaching materials, learning activity-related information, and support tools provided to learners, and are selected according to the learners' needs and circumstances.

[0530] An "analysis algorithm" is a computational method used to analyze data and to analyze and infer the emotional state and comprehension level of learners.

[0531] "Break methods" refer to temporary activities or guidelines suggested to alleviate fatigue and stress during learning.

[0532] "Mood-changing techniques" refer to methods of interrupting activities or introducing new stimuli, which are proposed to help learners regain their concentration.

[0533] This system is an educational support technology that incorporates an emotion recognition engine to recognize learners' emotions in real time and enhance learning effectiveness. The terminals that make up the system use cameras and microphones to capture the learner's micro-expressions and vocal intonation. This data is transmitted to a server via the network.

[0534] The server uses emotion recognition algorithms to analyze the received data. Specifically, it employs face detection technology and facial muscle pattern analysis for facial expression recognition, and analyzes changes in voice tone and intonation for speech analysis. This allows for detailed inferences about the learner's emotional state and level of comprehension.

[0535] Based on the analysis results, the server evaluates the learner's level of understanding and concentration, and selects the most appropriate educational resources accordingly. These resources are then sent back to the terminal and provided to the learner. For example, if sentiment analysis indicates that the learner is having difficulty understanding a particular concept, the server selects supplementary materials to help them understand that concept more deeply and sends them to the terminal. Also, if a low level of concentration is detected, guidance suggesting a short break will be displayed on the terminal.

[0536] Teachers and parents, who are users of the system, receive feedback from the server regarding the learners' emotional state and learning progress. This allows teachers to provide individualized instruction based on the learners' condition.

[0537] As a concrete example of its use, when a learner is tackling a difficult mathematical problem, this system can be used to detect an increase in stress levels and provide a visual guide for problem-solving approaches to address that stress.

[0538] An example of a prompt statement is, "Provide appropriate materials when learners show an emotional response to a new concept."

[0539] In this way, this invention utilizes an emotion engine to realize a flexible and effective educational support environment that responds to the learner's emotional state.

[0540] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0541] Step 1:

[0542] The device collects the learner's real-time facial expressions and voice using a camera and microphone. As input, the learner's micro-expressions and voice tone are captured. This data is converted into a digital format. As output, digitized facial expression and voice data are generated. This provides raw data about the learner's emotional state.

[0543] Step 2:

[0544] The terminal sends the collected facial expression and audio data to the server. At this stage, encryption technology is used to ensure the security of the data. As a result, the server receives encrypted data packets. By transmitting the data, the server can obtain a dataset ready for analysis.

[0545] Step 3:

[0546] The server decodes the received data and executes an emotion analysis algorithm. Decoded facial expression data and voice data are used as input. The analysis evaluates patterns of facial muscle movement and changes in voice tone. The output provides estimated results of the learner's emotional state and comprehension level. This clarifies the learner's emotional tendencies.

[0547] Step 4:

[0548] The server evaluates the analysis results and selects the most suitable educational resources for the learner. This process is carried out by an algorithm that searches for and selects materials that fit the learner's emotional state based on the prediction results. A list of selected educational materials is generated as output. This allows the server to secure customized materials tailored to the learner.

[0549] Step 5:

[0550] The terminal receives educational resources provided by the server and presents them to the learner. The input is educational material sent from the server. The terminal displays the learning materials on its screen. The output is support materials that help the learner progress through their learning. This allows the learner to enjoy a learning experience that is appropriate to their emotional state.

[0551] Step 6:

[0552] Users receive feedback information from the server. This feedback includes the learner's emotional state and learning progress. Based on this information, users can adjust their individualized instruction strategies. As an output, specific instructional plans and strategies are formed. This allows teachers and parents to implement more effective instruction.

[0553] (Application Example 2)

[0554] 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."

[0555] In recent years, as individualized support has become increasingly important in education, it is crucial to provide flexible educational approaches that respond to learners' emotional states. However, traditional systems have struggled to accurately grasp learners' emotions and provide effective educational materials and support based on that understanding. Furthermore, learners often face the challenge of not receiving high-quality educational support even within their home environment.

[0556] 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.

[0557] This invention includes a server that uses facial expression information, posture information, gaze information, and voice information acquired from the learner to evaluate the learner's level of understanding and concentration in real time; a server that selects and provides the learner with the most appropriate educational materials based on the evaluation; and a home robot incorporating an emotion engine that analyzes the learner's emotions in real time and provides the optimal educational environment. This makes it possible for learners to receive appropriate educational support in a home environment, regardless of their emotional state.

[0558] "Facial expression information" refers to data extracted from the learner's facial expressions, including information about microexpressions and facial muscle movements.

[0559] "Postural information" refers to data that indicates the learner's body position, tilt, and movement state, including information about how they are sitting and their body movements.

[0560] "Eye-gaze information" refers to data about the learner's eye movements and points of fixation, including information indicating where they are looking.

[0561] "Auditory information" refers to data related to the learner's speech, intonation, and tone, and includes information about voice quality and speaking style.

[0562] "Evaluating in real time" means analyzing and evaluating data with virtually no delay from the moment it is acquired.

[0563] "Comprehension level" is a measure that indicates the degree to which a learner understands specific learning material.

[0564] "Concentration level" is a measure that indicates the degree to which a learner is paying attention to their studies.

[0565] "Optimal educational materials" are educational content selected to most effectively advance a learner's learning, based on their current learning situation and emotional state.

[0566] An "emotion engine" is software or an algorithm used to analyze acquired data and infer the emotional state of a learner.

[0567] A "household robot" is a device that incorporates a computer for use in a home environment and is equipped with various sensors for the purpose of educational support.

[0568] This invention provides an educational support system to maximize learners' learning effectiveness. The system is configured as follows:

[0569] The server uses facial expression, posture, gaze, and voice information acquired from the learner to run an algorithm that evaluates the learner's comprehension and concentration level in real time. This utilizes high-performance computer vision technology, with facial expression information acquired in real time via a camera and voice information captured via a microphone. The server analyzes this information and uses an emotion engine to estimate the learner's emotional state.

[0570] The terminal is responsible for selecting and providing the most suitable educational materials to the learner based on evaluation results from the server. These educational materials are retrieved in real time from a cloud-based database and displayed on the learner's device. If this device is a home robot, it can communicate interactively with the learner through its display and voice support functions.

[0571] Teachers and parents, who are users of the system, are provided with information on learners' progress and emotional state through feedback sent from the server. This helps to improve the quality of individualized instruction.

[0572] As a concrete example, if a learner feels unsure about a new concept, the educational system can provide simpler materials or animations to reinforce the learning content. Furthermore, if a learner loses focus, the robot can suggest short breaks or relaxation content to support sustained learning. An example of a prompt for a generative AI model used to make this robot assistance even more effective is: "Please come up with an encouraging message for an 8-year-old child who is struggling to understand math."

[0573] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0574] Step 1:

[0575] The server receives facial expression information, posture information, gaze information, and voice information from the learner transmitted from the terminal. This information is data captured in real time by the camera and microphone installed in the terminal. The information acquired as input is stored and prepared for analysis in the next processing step.

[0576] Step 2:

[0577] Based on the acquired information, the server uses an emotion engine to analyze the learner's emotional state in real time. It processes data related to subtle changes in facial expressions and vocal intonation using facial recognition and speech analysis technologies to generate output that evaluates comprehension and concentration levels. This output is evaluation data that indicates the learner's current state.

[0578] Step 3:

[0579] The server selects the most suitable educational materials from a cloud-based database based on evaluation data. It uses evaluation data as input and queries for appropriate learning content based on this data. The selected educational materials, which are best suited to the learner's situation, are sent to the terminal as output.

[0580] Step 4:

[0581] The terminal analyzes educational materials received from the server and presents them to the learner using the display and speakers of the home robot. The terminal receives educational materials as input and generates output that supports the learner's understanding by displaying or explaining them aloud through the user interface.

[0582] Step 5:

[0583] Teachers and parents, as users, receive feedback sent from the server to understand the learners' progress and emotional state. This feedback includes evaluation data and information on the availability of educational materials, which is used to obtain input information for adjusting individualized instruction plans. Based on this information, output is generated to determine specific instructional actions.

[0584] 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.

[0585] 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.

[0586] 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.

[0587] [Fourth Embodiment]

[0588] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0589] 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.

[0590] 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).

[0591] 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.

[0592] 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.

[0593] 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).

[0594] 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.

[0595] 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.

[0596] 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.

[0597] 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.

[0598] 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.

[0599] 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.

[0600] 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".

[0601] The educational support system of the present invention collects learners' facial expressions, posture, gaze, and voice data via terminals equipped with numerous sensors, and performs real-time analysis on a server. In a specific embodiment, the system is constructed in the following manner.

[0602] First, the device is installed where the learner is located. The device is equipped with a camera and microphone and continuously records the learner's movements and voice. This recorded data is transmitted to the server in real time.

[0603] Next, the server analyzes the received data and uses multiple algorithms to evaluate the learner's comprehension and concentration levels. For example, it uses facial recognition technology to infer emotions from the learner's facial expressions and eye-tracking technology to evaluate which learning materials they are paying attention to. It also uses speech analysis to measure stress levels and comprehension based on the intonation and content of their speech.

[0604] Based on the evaluation results generated by the server, the system dynamically selects the most suitable educational materials for each learner and provides them through the terminal. For example, it suggests advanced materials to learners with a high level of understanding, and presents basic materials and visual content to those with a lower level of understanding. Furthermore, if it determines that a learner's concentration is declining, it can also suggest short breaks or ways to refresh their mind.

[0605] Teachers and parents, who are users of the system, regularly receive personalized feedback generated by the server that is helpful for instruction. This allows users to understand the learners' progress and provide more effective instruction.

[0606] As a concrete example, consider a student taking an online math lesson. In this case, the device detects when the student's gaze is fixed on a specific problem in the textbook and sends this information to the server. The server analyzes the data and determines that the student is struggling with that problem, then provides the device with a relevant video tutorial. At the same time, the teacher is notified of which problems the student is having difficulty with, which can be used to plan individualized instruction.

[0607] In this way, the present invention makes it possible to provide effective learning support that meets the individual needs of learners.

[0608] The following describes the processing flow.

[0609] Step 1:

[0610] The device uses a camera and microphone positioned in front of the learner to collect facial expression data, posture data, gaze data, and voice data in real time. This data is preprocessed with noise reduction and basic formatting before being sent to the server.

[0611] Step 2:

[0612] The server applies a facial recognition algorithm to analyze the received data. This allows it to infer emotional states and comprehension levels from the learner's face. Specifically, it analyzes facial feature points and detects changes in microexpressions.

[0613] Step 3:

[0614] The server analyzes posture and eye-tracking data to assess the learner's level of concentration. Posture data is used to detect the angle of the learner's body and head to determine if they are concentrating. Eye-tracking technology is used to identify where the learner is focusing their attention.

[0615] Step 4:

[0616] The server converts the audio data into text and uses natural language processing techniques to analyze the content and emotional tone of the speech. This allows it to obtain information that further reinforces the learner's understanding and emotional state based on the content and tone of their speech.

[0617] Step 5:

[0618] The server synthesizes these analysis results and selects the most suitable educational materials based on the learner's level of understanding and concentration. It then sends these materials to the terminal and provides them to the learner.

[0619] Step 6:

[0620] If the server determines that a learner's comprehension or concentration level is declining, it will suggest a break or provide simple refreshment methods via the terminal.

[0621] Step 7:

[0622] The server organizes all evaluation results and generates feedback on learners' progress and understanding. This feedback is provided to users, such as teachers and parents, to help them plan individualized instruction.

[0623] (Example 1)

[0624] 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".

[0625] In today's educational environment, there is a need to provide individualized instruction tailored to each learner's level of understanding and concentration. However, traditional teaching methods have presented challenges in accurately understanding and responding to learners' situations. In particular, in online learning environments where real-time situational assessment is required, there is a lack of efficient means to grasp learners' situations and provide appropriate support based on that understanding.

[0626] 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.

[0627] In this invention, the server includes a calculation means for analyzing the learner's level of recognition and attention in real time using visual and auditory information acquired from the learner; a means for dynamically selecting and supplying educational materials suitable for the learner based on the analysis results; and a means for suggesting a break or a reminder when the learner's attention level decreases. This makes it possible to provide rapid and accurate educational support according to the individual state of the learner.

[0628] "Visual information" refers to data related to the learner's facial expressions, posture, and gaze.

[0629] "Auditory information" refers to data related to the learner's voice and the surrounding sound environment.

[0630] "Recognition level" refers to an indicator that shows how well learners understand educational materials.

[0631] "Attention level" refers to an indicator that shows how much a learner is concentrating on educational materials or tasks.

[0632] "Computational means" refers to processes and technologies for analyzing information obtained from learners and evaluating their level of recognition and attention.

[0633] "Educational materials" refer to content and teaching materials designed to support learners' learning.

[0634] "Dynamic selection" refers to the process of selecting and providing educational materials in real time based on analysis results.

[0635] "Breaks or attention-gathering" refer to means of refreshing learners to restore their attention or promoting concentration.

[0636] "Feedback" refers to information used by instructors and parents for individualized instruction, based on the learner's level of awareness and concentration.

[0637] This educational support system primarily consists of three elements: a terminal, a server, and a user. During implementation, the terminal is placed in front of the learner and is equipped with a high-resolution camera and a high-sensitivity microphone. This terminal is designed to acquire the learner's visual and auditory information in real time and immediately transmit this information to the server.

[0638] The server possesses powerful processing capabilities and analyzes received data using multiple analytical algorithms. Specifically, it estimates emotions from facial expressions using facial recognition technology and identifies points of gaze using eye-tracking technology. In addition, it evaluates prosody (sound accent and intonation) and speed through speech analysis, thereby quantifying the learner's level of recognition and attention. Based on these analysis results, the server dynamically selects educational materials suitable for the learner and provides them through the terminal. This selection includes content tailored to the learner's level of understanding.

[0639] Furthermore, users, such as teachers and parents, receive feedback from the server. This feedback includes detailed information about the learner's progress and necessary instruction, which can be used as a reference when developing individualized instruction plans. This allows users to support learners more effectively.

[0640] As a concrete example, consider a scenario where a student is struggling with a problem during an online math lesson. The device detects that the student is concentrating on a specific task and sends that data to the server. The server quickly analyzes this situation and determines that the student is having difficulty with the task. Based on this, the server delivers a video tutorial relevant to the device and simultaneously notifies the teacher which problem the student is having trouble with.

[0641] Utilizing a generative AI model, this system provides appropriate responses to prompts such as, "When a learner's attention is focused on a problem but they are unable to find a solution, provide appropriate learning materials and suggestions to maintain their focus."

[0642] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0643] Step 1:

[0644] The device is placed in front of the learner and uses a camera and microphone to record visual information (facial expressions, posture, gaze) and auditory information (voice) in real time. The input data consists of video of the learner's face and audio of their speech. The device encrypts this data as digital data and transmits it to the server. Specifically, the camera focuses on the learner's face, and the eye-tracking sensor tracks their eye movements.

[0645] Step 2:

[0646] The server receives data sent from the terminal and performs facial expression analysis using a facial recognition algorithm. The input is visual data from the terminal, from which the server estimates the emotional state (joy, surprise, confusion, etc.). This analysis outputs results indicating the learner's recognition level and emotional state. Specifically, the server maps facial feature points and detects subtle changes in facial expression.

[0647] Step 3:

[0648] The server uses an eye-tracking algorithm to identify the learner's gaze points. The input is eye-tracking data, which generates output data indicating which learning materials the learner is paying attention to. Specifically, the server determines which part of the screen the learner's gaze is focused on based on the pattern of their eye movements.

[0649] Step 4:

[0650] The server uses a speech analysis algorithm to evaluate speech content and intonation. The input is audio data, from which it extracts and outputs information regarding stress levels and comprehension. Specifically, the server analyzes the audio waveform to evaluate speech speed and tone.

[0651] Step 5:

[0652] The server integrates these analysis results and selects educational materials suitable for the learner. The input is all the analysis results, and the output is the appropriate teaching materials and content. Specifically, the server uses a generated AI model to evaluate the relevance of the content based on the analysis data and dynamically select the materials.

[0653] Step 6:

[0654] The terminal provides learners with educational materials transmitted from the server. Input is selected materials from the server, and output is viewable or interactive educational content. Specifically, the terminal either displays the materials on its screen or provides voice instructions.

[0655] Step 7:

[0656] Teachers and parents, who are the users, are provided with feedback generated by the server. The input is the server's analysis and selection results, and the output is a detailed progress report. Specifically, the server converts the feedback into text format and distributes it to users via email or a portal.

[0657] (Application Example 1)

[0658] 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".

[0659] In today's educational environment, there is a challenge in that learning support is not adequately tailored to each learner's individual level of understanding and concentration. Furthermore, in the home learning environment, parents have limited means of monitoring their child's progress and understanding, making it difficult to provide appropriate support. Moreover, there is a lack of mechanisms to quickly identify a decline in concentration and take appropriate measures.

[0660] 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.

[0661] In this invention, the server includes processing means for evaluating comprehension and concentration levels in real time using biometric information acquired from the learner, processing means for selecting and providing optimal learning materials based on the evaluation, and processing means for suggesting a break or change of pace when concentration levels decline. This enables flexible learning support tailored to the learner's comprehension and concentration levels, thereby improving the quality of education in the home environment.

[0662] "Biometric information" is a general term for facial expressions, posture, gaze, and voice information obtained from learners, and is data used for real-time evaluation.

[0663] "Processing means" refers to devices or software that evaluate the learner's level of understanding and concentration, and based on that, provide optimal learning materials or suggest breaks and changes of pace.

[0664] The term "educator" is a general term encompassing teachers, parents, and other individuals who provide guidance to learners.

[0665] A "device" refers to a hardware device that monitors learning progress within the home and provides materials tailored to the student's level of understanding.

[0666] A "display device" refers to a screen or projector used to present dynamically selected learning materials to learners.

[0667] "Eye-tracking technology" is a technique that detects the direction of a learner's gaze and measures their level of attention to a specific object.

[0668] The system for implementing this invention monitors learners and provides learning support using devices installed in the home. The main components are a group of sensors that acquire biometric information, a central control unit (server), and a display device that presents information to learners.

[0669] The server receives biometric information from learners and evaluates their comprehension and concentration levels in real time. This utilizes technologies such as facial recognition and eye-tracking. Specifically, it analyzes emotions from facial expressions and vocalizations using cameras and microphones, and identifies points of focus from eye-tracking data. This allows the system to evaluate the learner's attention and comprehension levels and select the most appropriate learning materials.

[0670] The software used to execute the processing could include image processing libraries such as OpenCV and audio analysis tools. Leveraging these technologies, the server dynamically provides learning materials to learners, selecting and displaying materials according to their level of understanding.

[0671] When a learner's concentration level declines, the system automatically notifies the parent. This makes it easier for parents to monitor their child's learning progress and provide support as needed.

[0672] As a concrete example, consider a situation where an elementary school child is working on a specific math problem while studying at home. The server detects when the child's gaze shifts away from the problem and provides a math video tutorial to the display device. It then notifies the parent which problem the child was struggling with.

[0673] Examples of prompts to input into a generative AI model:

[0674] "The child's expression looks confused. Analyze the details of the material he is focusing on and display related supplementary tutorials."

[0675] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0676] Step 1:

[0677] The device acquires the learner's biometric information using a camera and microphone. It captures the learner's facial expressions, posture, gaze, and voice data as input and sends it to the server. The device collects this data and transfers it to the server in real time.

[0678] Step 2:

[0679] The server analyzes the received data. The input data includes the learner's facial expressions and voice information, which are used to evaluate their comprehension and concentration levels. Data processing involves facial recognition using an image processing library (e.g., OpenCV) and identifying the point of focus using eye-tracking technology. The output here is a numerical evaluation of the learner's current comprehension and concentration levels.

[0680] Step 3:

[0681] The server selects the most suitable learning materials for the learner based on the evaluation results. The comprehension evaluation results are used as input, and appropriate materials are searched and selected from the server's material database accordingly. The output is the content data of the selected learning materials.

[0682] Step 4:

[0683] The terminal provides selected learning materials to the learner via a display device. The input here is content data received from the server, and the output is the display of learning materials on the learner's screen. In this process, the learning materials are dynamically displayed using a display device.

[0684] Step 5:

[0685] When the server determines that a learner's concentration level has decreased, it sends a notification to the parent. The criteria for determining the decrease in concentration are used as input, and the output is a message sent to the parent through the notification system. This notification also includes information about which learning material caused the problem.

[0686] 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.

[0687] This invention relates to an educational support system that incorporates an emotion engine to recognize learners' emotions in real time and enhance learning effectiveness. This system is equipped with multiple sensors and analysis modules to acquire learners' facial expressions, posture, gaze, and voice in real time and detect changes in their emotions.

[0688] First, the camera and microphone installed on the device capture the learner's micro-expressions and vocal intonation. This data is then sent from the device to the server. The server uses the received data to activate the emotion engine. The emotion engine analyzes the subtle movements of facial muscles and specific tones of the voice to infer the learner's emotional state.

[0689] The server uses the results of the emotion engine to evaluate the learner's level of understanding and concentration in detail. In particular, it can capture emotional changes during learning and identify where the learner is feeling confused, stressed, or excited. The server aggregates this information, selects educational materials that correspond to the learner's specific emotional state, and sends them to the terminal.

[0690] The device directly provides learners with feedback based on evaluation results from the emotion engine and offers learning materials tailored to their situation. For example, if a learner feels anxious about a new concept, it will present additional materials to reinforce that learning content. It can also suggest short relaxation techniques in response to a decrease in concentration.

[0691] Teachers and parents, who are users of the system, receive feedback from the server regarding the learners' emotional state and progress. This allows teachers to understand how stressed learners are during their studies and to refine their individualized instruction.

[0692] For example, if the emotion engine detects an increase in stress levels while a learner is tackling a difficult physics problem, the server can provide guidance and visual explanations to change their approach to the problem. Furthermore, once the learner solves the problem, positive feedback can be provided based on their emotional changes, reinforcing their sense of accomplishment.

[0693] In this way, the present invention utilizes an emotion engine to realize flexible and effective educational support that responds to the learner's emotional state.

[0694] The following describes the processing flow.

[0695] Step 1:

[0696] The device uses a camera to capture the learner's face, tracking facial muscle movements and gaze direction in real time. Simultaneously, it uses a microphone to record the learner's voice. This data is preprocessed with noise reduction before being sent to the server.

[0697] Step 2:

[0698] The server inputs the received data into an emotion engine to analyze the learner's emotional state. Specifically, it analyzes micro-expressions using a facial recognition algorithm and evaluates vocal intonation through voice analysis. This allows it to estimate the emotions the learner is feeling, such as joy, anxiety, and their level of concentration.

[0699] Step 3:

[0700] Based on the analysis results, the server comprehensively evaluates the learner's emotional state, comprehension level, and concentration level. It identifies where the learner is finding the material difficult and determines the optimal countermeasures. For example, if it determines that the learner has a low level of understanding of a difficult concept, it selects supplementary materials or easy-to-understand explanatory videos.

[0701] Step 4:

[0702] The server sends selected educational materials and instructions to the terminal and presents them to the learner. The terminal displays the materials in a format that is easy for the user (learner) to view, and if necessary, suggests breaks or relaxation activities in a pop-up format.

[0703] Step 5:

[0704] The server continuously monitors the learner's emotional state and reports real-time feedback to teachers and parents. This allows teachers and parents to understand the learner's progress and emotional changes, and use this information to plan individualized instruction.

[0705] Step 6:

[0706] When a learner completes an assignment, the device summarizes their final emotional state and learning outcomes and sends them to the server. The server analyzes this data, generates a final report, and shares it with the user (teacher or parent). This facilitates the planning of the next learning step.

[0707] (Example 2)

[0708] 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".

[0709] Traditional educational support systems have struggled to grasp learners' emotional states and changes in comprehension in real time and to provide immediate, appropriate feedback and learning materials. Furthermore, they lacked the flexibility to adapt to learners' concentration levels, making it difficult to provide support tailored to individual learning progress and emotional needs. This resulted in challenges such as an inability to improve learning efficiency and provide instruction that meets the individual needs of learners.

[0710] 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.

[0711] In this invention, the server includes means equipped with an algorithm that analyzes the learner's emotional state and comprehension level in real time using facial expression data, posture data, gaze data, and voice data acquired from the learner; means for selecting and providing educational resources optimized for the learner based on the analysis results; and means having a function to suggest a way to take a break or a way to change the learner's mood when their concentration level decreases. This enables flexible and effective educational support tailored to the emotional state and concentration level of each individual learner.

[0712] "Facial expression data" refers to information about the learner's micro-expressions and facial muscle movements acquired through sensors such as cameras.

[0713] "Posture data" refers to information about the learner's body position, movement, and changes in posture, and this data is used to analyze the learner's condition.

[0714] "Eye-tracking data" refers to information about the direction of a learner's gaze and changes in their viewpoint, obtained using eye-tracking technology.

[0715] "Audio data" refers to information about the learner's voice, including tone, pitch, and rhythm, which enables the analysis of their emotional state.

[0716] "Emotional state" refers to the learner's emotional changes and current emotional responses, and is a mental state inferred from micro-expressions, tone of voice, and other factors.

[0717] "Understanding status" refers to information indicating the extent to which a learner understands the current learning material, and is estimated by an analysis algorithm.

[0718] "Educational resources" refer to teaching materials, learning activity-related information, and support tools provided to learners, and are selected according to the learners' needs and circumstances.

[0719] An "analysis algorithm" is a computational method used to analyze data and to analyze and infer the emotional state and comprehension level of learners.

[0720] "Break methods" refer to temporary activities or guidelines suggested to alleviate fatigue and stress during learning.

[0721] "Mood-changing techniques" refer to methods of interrupting activities or introducing new stimuli, which are proposed to help learners regain their concentration.

[0722] This system is an educational support technology that incorporates an emotion recognition engine to recognize learners' emotions in real time and enhance learning effectiveness. The terminals that make up the system use cameras and microphones to capture the learner's micro-expressions and vocal intonation. This data is transmitted to a server via the network.

[0723] The server uses emotion recognition algorithms to analyze the received data. Specifically, it employs face detection technology and facial muscle pattern analysis for facial expression recognition, and analyzes changes in voice tone and intonation for speech analysis. This allows for detailed inferences about the learner's emotional state and level of comprehension.

[0724] Based on the analysis results, the server evaluates the learner's level of understanding and concentration, and selects the most appropriate educational resources accordingly. These resources are then sent back to the terminal and provided to the learner. For example, if sentiment analysis indicates that the learner is having difficulty understanding a particular concept, the server selects supplementary materials to help them understand that concept more deeply and sends them to the terminal. Also, if a low level of concentration is detected, guidance suggesting a short break will be displayed on the terminal.

[0725] Teachers and parents, who are users of the system, receive feedback from the server regarding the learners' emotional state and learning progress. This allows teachers to provide individualized instruction based on the learners' condition.

[0726] As a concrete example of its use, when a learner is tackling a difficult mathematical problem, this system can be used to detect an increase in stress levels and provide a visual guide for problem-solving approaches to address that stress.

[0727] An example of a prompt statement is, "Provide appropriate materials when learners show an emotional response to a new concept."

[0728] In this way, this invention utilizes an emotion engine to realize a flexible and effective educational support environment that responds to the learner's emotional state.

[0729] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0730] Step 1:

[0731] The device collects the learner's real-time facial expressions and voice using a camera and microphone. As input, the learner's micro-expressions and voice tone are captured. This data is converted into a digital format. As output, digitized facial expression and voice data are generated. This provides raw data about the learner's emotional state.

[0732] Step 2:

[0733] The terminal sends the collected facial expression and audio data to the server. At this stage, encryption technology is used to ensure the security of the data. As a result, the server receives encrypted data packets. By transmitting the data, the server can obtain a dataset ready for analysis.

[0734] Step 3:

[0735] The server decodes the received data and executes an emotion analysis algorithm. Decoded facial expression data and voice data are used as input. The analysis evaluates patterns of facial muscle movement and changes in voice tone. The output provides estimated results of the learner's emotional state and comprehension level. This clarifies the learner's emotional tendencies.

[0736] Step 4:

[0737] The server evaluates the analysis results and selects the most suitable educational resources for the learner. This process is carried out by an algorithm that searches for and selects materials that fit the learner's emotional state based on the prediction results. A list of selected educational materials is generated as output. This allows the server to secure customized materials tailored to the learner.

[0738] Step 5:

[0739] The terminal receives educational resources provided by the server and presents them to the learner. The input is educational material sent from the server. The terminal displays the learning materials on its screen. The output is support materials that help the learner progress through their learning. This allows the learner to enjoy a learning experience that is appropriate to their emotional state.

[0740] Step 6:

[0741] Users receive feedback information from the server. This feedback includes the learner's emotional state and learning progress. Based on this information, users can adjust their individualized instruction strategies. As an output, specific instructional plans and strategies are formed. This allows teachers and parents to implement more effective instruction.

[0742] (Application Example 2)

[0743] 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".

[0744] In recent years, as individualized support has become increasingly important in education, it is crucial to provide flexible educational approaches that respond to learners' emotional states. However, traditional systems have struggled to accurately grasp learners' emotions and provide effective educational materials and support based on that understanding. Furthermore, learners often face the challenge of not receiving high-quality educational support even within their home environment.

[0745] 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.

[0746] This invention includes a server that uses facial expression information, posture information, gaze information, and voice information acquired from the learner to evaluate the learner's level of understanding and concentration in real time; a server that selects and provides the learner with the most appropriate educational materials based on the evaluation; and a home robot incorporating an emotion engine that analyzes the learner's emotions in real time and provides the optimal educational environment. This makes it possible for learners to receive appropriate educational support in a home environment, regardless of their emotional state.

[0747] "Facial expression information" refers to data extracted from the learner's facial expressions, including information about microexpressions and facial muscle movements.

[0748] "Postural information" refers to data that indicates the learner's body position, tilt, and movement state, including information about how they are sitting and their body movements.

[0749] "Eye-gaze information" refers to data about the learner's eye movements and points of fixation, including information indicating where they are looking.

[0750] "Auditory information" refers to data related to the learner's speech, intonation, and tone, and includes information about voice quality and speaking style.

[0751] "Evaluating in real time" means analyzing and evaluating data with virtually no delay from the moment it is acquired.

[0752] "Comprehension level" is a measure that indicates the degree to which a learner understands specific learning material.

[0753] "Concentration level" is a measure that indicates the degree to which a learner is paying attention to their studies.

[0754] "Optimal educational materials" are educational content selected to most effectively advance a learner's learning, based on their current learning situation and emotional state.

[0755] An "emotion engine" is software or an algorithm used to analyze acquired data and infer the emotional state of a learner.

[0756] A "household robot" is a device that incorporates a computer for use in a home environment and is equipped with various sensors for the purpose of educational support.

[0757] This invention provides an educational support system to maximize learners' learning effectiveness. The system is configured as follows:

[0758] The server uses facial expression, posture, gaze, and voice information acquired from the learner to run an algorithm that evaluates the learner's comprehension and concentration level in real time. This utilizes high-performance computer vision technology, with facial expression information acquired in real time via a camera and voice information captured via a microphone. The server analyzes this information and uses an emotion engine to estimate the learner's emotional state.

[0759] The terminal is responsible for selecting and providing the most suitable educational materials to the learner based on evaluation results from the server. These educational materials are retrieved in real time from a cloud-based database and displayed on the learner's device. If this device is a home robot, it can communicate interactively with the learner through its display and voice support functions.

[0760] Teachers and parents, who are users of the system, are provided with information on learners' progress and emotional state through feedback sent from the server. This helps to improve the quality of individualized instruction.

[0761] As a concrete example, if a learner feels unsure about a new concept, the educational system can provide simpler materials or animations to reinforce the learning content. Furthermore, if a learner loses focus, the robot can suggest short breaks or relaxation content to support sustained learning. An example of a prompt for a generative AI model used to make this robot assistance even more effective is: "Please come up with an encouraging message for an 8-year-old child who is struggling to understand math."

[0762] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0763] Step 1:

[0764] The server receives facial expression information, posture information, gaze information, and voice information from the learner transmitted from the terminal. This information is data captured in real time by the camera and microphone installed in the terminal. The information acquired as input is stored and prepared for analysis in the next processing step.

[0765] Step 2:

[0766] Based on the acquired information, the server uses an emotion engine to analyze the learner's emotional state in real time. It processes data related to subtle changes in facial expressions and vocal intonation using facial recognition and speech analysis technologies to generate output that evaluates comprehension and concentration levels. This output is evaluation data that indicates the learner's current state.

[0767] Step 3:

[0768] The server selects the most suitable educational materials from a cloud-based database based on evaluation data. It uses evaluation data as input and queries for appropriate learning content based on this data. The selected educational materials, which are best suited to the learner's situation, are sent to the terminal as output.

[0769] Step 4:

[0770] The terminal analyzes educational materials received from the server and presents them to the learner using the display and speakers of the home robot. The terminal receives educational materials as input and generates output that supports the learner's understanding by displaying or explaining them aloud through the user interface.

[0771] Step 5:

[0772] Teachers and parents, as users, receive feedback sent from the server to understand the learners' progress and emotional state. This feedback includes evaluation data and information on the availability of educational materials, which is used to obtain input information for adjusting individualized instruction plans. Based on this information, output is generated to determine specific instructional actions.

[0773] 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.

[0774] 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.

[0775] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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."

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] The following is further disclosed regarding the embodiments described above.

[0795] (Claim 1)

[0796] A means equipped with an algorithm that evaluates the learner's level of comprehension and concentration in real time using facial expression information, posture information, gaze information, and voice information obtained from the learner,

[0797] Based on the aforementioned evaluation, a means of selecting and providing the most suitable educational materials for learners,

[0798] A means of suggesting a break or a change of pace when a learner's concentration level decreases,

[0799] A means of providing individualized instruction feedback to teachers or parents based on the aforementioned evaluation results,

[0800] A system that includes this.

[0801] (Claim 2)

[0802] The system according to claim 1, comprising an algorithm for extracting micro-expression features from a learner's face and estimating their emotions and level of comprehension.

[0803] (Claim 3)

[0804] The system according to claim 1, comprising an algorithm that uses eye-tracking technology to identify a learner's gaze point and measure their level of interest in the screen.

[0805] "Example 1"

[0806] (Claim 1)

[0807] A computation means that analyzes the learner's level of recognition and attention concentration in real time using visual and auditory information acquired from the learner,

[0808] Based on the aforementioned analysis results, a means for dynamically selecting and supplying educational materials suitable for learners,

[0809] A means of suggesting a break or a reminder when a learner's level of attention decreases,

[0810] A means of providing individualized feedback to instructors or parents based on the aforementioned analysis results,

[0811] A system that includes this.

[0812] (Claim 2)

[0813] The system according to claim 1, comprising a computation means for extracting micro-expression features from a learner's face and estimating emotion and recognition level.

[0814] (Claim 3)

[0815] The system according to claim 1, comprising a calculation means for identifying the object of a learner's gaze using eye-tracking technology and measuring the degree of interest.

[0816] "Application Example 1"

[0817] (Claim 1)

[0818] A processing means that uses biometric information obtained from learners to evaluate the learners' level of understanding and concentration in real time,

[0819] Based on the aforementioned evaluation, a processing means is provided to select and provide the most suitable learning materials for the learner.

[0820] A processing mechanism that suggests a break or change of pace when the learner's concentration level decreases,

[0821] A processing means that provides feedback for individual instruction to educators or parents based on the aforementioned evaluation results,

[0822] A device for monitoring the learning progress of learners within the home,

[0823] A processing means that dynamically selects learning materials according to the learner's level of understanding and provides them through a display device,

[0824] A processing mechanism that detects a decrease in a learner's concentration and notifies the parent,

[0825] A system that includes this.

[0826] (Claim 2)

[0827] The system according to claim 1, comprising processing means for extracting subtle facial characteristics from a learner's face and estimating their emotions and level of comprehension.

[0828] (Claim 3)

[0829] The system according to claim 1, comprising processing means for identifying the direction of a learner's gaze using eye-tracking technology and measuring their level of interest in the screen.

[0830] "Example 2 of combining an emotion engine"

[0831] (Claim 1)

[0832] A means equipped with an algorithm that analyzes the learner's emotional state and comprehension state in real time using facial expression data, posture data, gaze data, and voice data acquired from the learner,

[0833] Based on the aforementioned analysis results, a means for selecting and providing educational resources optimized for learners,

[0834] A means having the function of suggesting a method for taking a break or a way to change one's mood when the learner's concentration level decreases,

[0835] A means for sending feedback for individualized instruction to educators or parents based on the aforementioned analysis results,

[0836] A system that includes this.

[0837] (Claim 2)

[0838] The system according to claim 1, comprising an analysis module that extracts micro-expression features from a learner's face and estimates their emotions and level of comprehension.

[0839] (Claim 3)

[0840] The system according to claim 1, comprising an analysis module that uses eye-tracking technology to identify a learner's gaze point and measure their level of interest in a display device.

[0841] "Application example 2 when combining with an emotional engine"

[0842] (Claim 1)

[0843] A means equipped with an algorithm that evaluates the learner's level of comprehension and concentration in real time using facial expression information, posture information, gaze information, and voice information obtained from the learner,

[0844] Based on the aforementioned evaluation, a means of selecting and providing the most suitable educational materials for learners,

[0845] A means of suggesting a break or a change of pace when a learner's concentration level decreases,

[0846] A means of providing individualized instruction feedback to teachers or parents based on the aforementioned evaluation results,

[0847] A home robot incorporating an emotion engine can analyze learners' emotions in real time and provide an optimal educational environment.

[0848] A system that includes this.

[0849] (Claim 2)

[0850] The system according to claim 1, comprising an algorithm for extracting micro-expression features from a learner's face and estimating their emotions and level of comprehension.

[0851] (Claim 3)

[0852] The system according to claim 1, comprising an algorithm that uses eye-tracking technology to identify a learner's gaze point and measure their level of interest in the screen. [Explanation of symbols]

[0853] 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 equipped with an algorithm that evaluates the learner's level of comprehension and concentration in real time using facial expression information, posture information, gaze information, and voice information obtained from the learner, Based on the aforementioned evaluation, a means of selecting and providing the most suitable educational materials for learners, A means of suggesting a break or a change of pace when a learner's concentration level decreases, A means of providing individualized instruction feedback to teachers or parents based on the aforementioned evaluation results, A system that includes this.

2. The system according to claim 1, comprising an algorithm for extracting micro-expression features from a learner's face and estimating their emotions and level of comprehension.

3. The system according to claim 1, comprising an algorithm that uses eye-tracking technology to identify a learner's gaze point and measure their level of interest in the screen.

Images