System

Abstract

A system is provided.SOLUTION: A system, comprising: means for detecting and analyzing facial expressions; means for detecting and analyzing actions; means for adjusting and providing learning materials based on the facial expressions and actions; and means for providing the analysis results as feedback to guardians and teachers.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In conventional education systems, it is difficult to grasp each child's learning progress and interests in real time, making it difficult to provide individually appropriate learning materials. There is also a problem of a lack of feedback for teachers and parents to accurately grasp a child's learning situation and provide appropriate guidance. This can hinder children's motivation to learn and their efficient growth. [Means for solving the problem]

[0005] To solve these problems, the present invention employs the following means. First, it provides a means for detecting and analyzing a user's facial expressions and a means for detecting and analyzing their behavior. Next, it provides a means for adjusting learning materials based on the facial expressions and behavior and providing them to the user. Finally, it constructs a system including a means for providing the analysis results as feedback to parents and teachers. This makes it possible to grasp each child's learning progress and interests in real time, provide appropriate learning materials, and support educators in providing appropriate instruction.

[0006] "Means for detecting and analyzing facial expressions" refers to machine learning models and hardware for detecting and analyzing a user's facial expressions to determine their emotional state.

[0007] "Means for detecting and analyzing behavior" refers to machine learning models and hardware for detecting and analyzing user movements and attitudes to determine the type of behavior.

[0008] "Means for adjusting and providing learning materials" refers to software and hardware for selecting optimal learning materials based on the analysis of the user's facial expressions and behavior and providing them to the user.

[0009] "Means for providing analysis results as feedback to parents and teachers" refers to software and communication means for providing parents and teachers with information about the learning situation and appropriate teaching methods based on the analysis results of the user's facial expressions and behavior.

[0010] A "machine learning model" refers to an artificial intelligence model that uses algorithms trained on large amounts of data to recognize specific patterns and features.

[0011] "User" refers to children and students who use this system to study.

[0012] "Guardian" refers to a parent or other adult at home who monitors the user's learning status and provides support.

[0013] "Teacher" refers to an educator or school staff member who provides educational guidance to the user.

[0014] "Feedback" refers to information and advice provided based on the analysis results, and refers to detailed reports on the user's learning progress and level of understanding.

[0015] "Hardware" refers to the physical devices and equipment used to operate the System. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a 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.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0030] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The system of the present invention is capable of analyzing the user's learning status in real time and providing optimal learning materials to each user based on the results. Specific embodiments for carrying out the present invention will now be described.

[0038] First, the server loads the facial expression and behavior recognition models, which are machine learning models used to analyze the user's facial expressions and behavior.

[0039] Next, the device activates the camera and captures the user's video in real time. The captured video frames are input into a facial expression recognition model, which classifies the user's facial expression as "happy," "neutral," "sad," etc. Based on the results of this facial expression analysis, the user's emotional state is understood.

[0040] In parallel, the device stores a certain number of frames in a buffer and inputs them into an activity recognition model. The activity recognition model classifies the user's behavior from these frames as "attentive," "distracted," "fidgeting," etc. In this way, the user's behavioral state is also understood.

[0041] Based on the analysis of these facial expressions and behaviors, the device selects and provides the most suitable learning materials to the user. Specifically, if the user is "happy" and "attentive," it provides advanced learning materials. On the other hand, if the user is "neutral" or "distracted," it provides standard learning materials, and if the user is "sad" or "fidgeting," it provides basic learning materials. This process maintains the user's motivation to learn and promotes effective learning progress.

[0042] Furthermore, the server generates detailed feedback based on the analysis results sent from the device. This feedback is provided to parents and teachers and includes information on the user's learning status and appropriate teaching methods. Based on this information, parents and teachers can take effective approaches to support the user's educational growth.

[0043] As a concrete example, imagine a user is solving math problems online. If the device analyzes the user's face and classifies it as "happy" and their behavior as "attentive," the device will offer the user advanced problems or additional assignments. Conversely, if the device classifies the user's facial expression as "sad" and their behavior as "distracted," the device will offer the user basic review questions or supplementary materials. In this way, the user's learning experience is personalized.

[0044] As described above, the system of the present invention uses a means for analyzing a user's facial expressions and behavior to adjust and provide learning materials in real time, providing an optimal educational environment that is adapted to individual learning needs. This system increases the user's motivation to learn and allows teachers and parents to provide appropriate support.

[0045] The processing flow will be explained below.

[0046] Step 1:

[0047] The server loads the facial expression and behavior recognition models, which prepares the system for rapid analysis.

[0048] Step 2:

[0049] The device activates the camera and captures the user's video in real time, and the captured video frames are used for subsequent analysis.

[0050] Step 3:

[0051] The device inputs the captured video frames into a facial expression recognition model to analyze the user's facial expression. As a result of the analysis, the user's facial expression is classified as "happy," "neutral," "sad," etc.

[0052] Step 4:

[0053] The device stores a certain number of frames in a buffer and inputs them into an activity recognition model, which uses these frames to classify the user's behavior as "attentive," "distracted," "fidgeting," etc.

[0054] Step 5:

[0055] The device selects the appropriate level of learning materials to provide to the user based on the analysis of their facial expressions and behavior. Specifically, if the user is "happy" and "attentive," advanced learning materials will be selected.

[0056] Step 6:

[0057] The device provides the user with learning materials selected based on the user's learning progress and level of understanding.

[0058] Step 7:

[0059] The device sends the results of facial and behavioral analysis to a server, which uses this information to generate feedback later.

[0060] Step 8:

[0061] Based on the analysis results received by the server, detailed feedback is generated for parents and teachers, including information about the user's learning status and appropriate teaching methods.

[0062] Step 9:

[0063] The server generates feedback and sends it to parents and teachers, allowing them to understand the user's learning status and provide appropriate support and guidance.

[0064] Through each step, the system personalizes the user's learning experience and enables parents and teachers to provide effective support.

[0065] Example 1

[0066] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0067] Conventional educational systems have the problem of being unable to grasp the learning status of individual users in real time and provide optimal learning materials accordingly. Furthermore, there are limited means of providing appropriate feedback on the user's educational progress and status to parents and teachers. This makes it difficult to maintain the user's motivation to learn and effective learning progress. Therefore, there is a need for a system that can analyze the user's facial expressions and behavior in real time, adjust and provide learning materials based on that information, and provide the analysis results as feedback to parents and teachers.

[0068] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0069] In this invention, the server includes means for using a machine learning model to detect and classify a user's facial expressions, means for using a machine learning model to detect and classify the user's behavior, means for capturing video of the user in real time, means for adjusting and providing learning materials based on the facial expressions and behavior, and means for providing the analysis results as feedback to parents and teachers. This makes it possible to analyze the user's facial expressions and behavior in real time, and to provide optimal learning materials based on the analysis results and provide appropriate feedback of the analysis results.

[0070] "Machine learning model for detecting and classifying user facial expressions" refers to the algorithm used to analyze video data of a user captured by a camera and classify it into emotional states such as "happy," "neutral," and "sad."

[0071] A "machine learning model for detecting and classifying user behavior" refers to an algorithm that analyzes video data consisting of multiple frames and classifies user behavior into categories such as "attentive," "distracted," and "fidgeting."

[0072] "Means for capturing a user's image in real time" refers to the process of using a camera built into or connected to a device to capture the user's movements and facial expressions in real time and obtain the video data.

[0073] "Means for adjusting and providing learning materials" refers to the process of selecting and providing the most suitable learning materials (advanced learning materials, standard learning materials, basic learning materials) to the user based on the analysis of the user's facial expressions and behavior.

[0074] "Means for providing analysis results as feedback to parents and teachers" refers to a process for generating and providing detailed feedback to parents and teachers based on the analysis results regarding the user's learning status.

[0075] A "machine learning model" refers to an artificial intelligence technique that trains algorithms based on large data sets to recognize patterns and make predictions about new data.

[0076] The system of the present invention utilizes a machine learning model to analyze a user's facial expressions and behavior in real time, provides optimal learning materials based on the analysis results, and also provides the analysis results as feedback to parents and teachers. Specific embodiments of the present invention are described below.

[0077] First, the server uses machine learning libraries such as TensorFlow and PyTorch to load pre-trained facial expression and behavior recognition models into memory, which enables the server to analyze the user's video data.

[0078] When a user starts learning, the device activates the built-in or connected camera and captures the user's video in real time. The video data is acquired frame by frame and used for analysis.

[0079] The device preprocesses the captured video frames and inputs them into a facial expression recognition model, which classifies the user's facial expression into "happy," "neutral," "sad," etc., and returns the result to the device, allowing the device to understand the user's emotional state.

[0080] In parallel, the device accumulates a certain number of frames in a buffer and inputs them into the behavior recognition model. The behavior recognition model classifies the user's behavior from these frames into categories such as "attentive," "distracted," and "fidgeting," and returns the results to the device. This allows the device to understand the user's behavioral state.

[0081] The device selects and provides the most suitable learning materials to the user based on the analysis results of facial expressions and behaviors obtained from the server. Specifically, if the user is "happy" and "attentive," advanced learning materials are provided, if the user is "neutral" or "distracted," standard learning materials are provided, and if the user is "sad" or "fidgeting," basic learning materials are provided.

[0082] Furthermore, the server generates detailed feedback based on the analysis results sent from the device. This feedback is provided to parents and teachers and includes information on the user's learning status and appropriate teaching methods, allowing parents and teachers to take effective approaches to support the user's educational growth.

[0083] As a concrete example, consider a user solving a math problem online. If the device analyzes the user's face and classifies it as "happy" and their behavior as "attentive," the device will provide the user with applied problems or additional assignments. On the other hand, if the device classifies the user's facial expression as "sad" and their behavior as "distracted," the device will provide the user with basic review questions or supplementary materials. In this way, the user's learning experience is personalized.

[0084] An example of a prompt is, "If a user is solving a math problem and their facial expression is classified as 'happy' and their behavior is classified as 'attentive,' please suggest what kind of learning material should be provided in the next step. Please also specify the machine learning model to be used and the role of the server / device."

[0085] The system of the present invention analyzes the user's learning status in real time and provides optimal learning materials based on that analysis, thereby realizing an educational environment that is adapted to individual learning needs. This increases the user's motivation to learn, promotes effective learning progress, and allows parents and teachers to provide appropriate support.

[0086] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0087] Step 1:

[0088] The server loads the facial expression recognition model and the behavior recognition model.

[0089] Input: The server receives a machine learning library (TensorFlow or PyTorch) and a pre-trained model file.

[0090] Specific operation: The server uses the TensorFlow and PyTorch libraries to load each machine learning model into memory, which prepares the server for face recognition and behavior recognition calculations.

[0091] Output: The loaded facial expression recognition model and behavior recognition model are prepared in memory.

[0092] Step 2:

[0093] The device activates the camera and captures the user's image.

[0094] Input: The user inputs an instruction to start learning into the terminal.

[0095] Specific operation: The device activates the built-in or connected camera and captures the user's video in real time. The video data is acquired frame by frame.

[0096] Output: A sequence of video frames is generated and made available in real time.

[0097] Step 3:

[0098] The device analyzes the user's facial expression using a facial expression recognition model.

[0099] Input: Captured video frames of the user

[0100] How it works: The device preprocesses video frames and sends them to the server's facial expression recognition model, which then classifies the user's facial expression into categories such as "happy," "neutral," or "sad." Preprocessing includes frame resizing and normalization.

[0101] Output: Classification result of the analyzed facial expression (e.g. "happy").

[0102] Step 4:

[0103] The device analyzes the user's behavior using a behavior recognition model

[0104] Input: A certain number of captured video frames

[0105] Specific operation: The device accumulates a certain number of frames in a buffer and sends the buffer to the server's activity recognition model. The activity recognition model classifies the user's behavior from these frames into categories such as "attentive," "distracted," and "fidgeting." Preprocessing includes configuring the buffer and resizing the frames.

[0106] Output: Classification result of the analyzed behavior (e.g. "attentive").

[0107] Step 5:

[0108] The device selects and provides learning materials based on the analysis results

[0109] Input: Analysis results of facial expressions and behavior obtained from the server

[0110] Specific behavior: Evaluate each data combination and select the most suitable learning material for the user. For example, if the user is "happy" and "attentive," select advanced learning materials. The selection process is based on predefined rules and conditions.

[0111] Output: The selected learning materials (e.g., advanced learning materials) are provided to the user via the terminal.

[0112] Step 6:

[0113] The server generates detailed feedback

[0114] Input: Analysis results of facial expressions and behavior sent from the device

[0115] Specific operation: The server generates detailed feedback based on the analysis results and provides it to parents and teachers. The feedback includes specific information about the user's learning progress, areas for improvement, and teaching methods.

[0116] Output: A detailed feedback document is generated and sent to parents and teachers.

[0117] The process of analyzing and selecting data based on input data in each processing step and obtaining each output has been described in detail above.

[0118] (Application example 1)

[0119] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0120] Conventional learning systems have difficulty analyzing users' facial expressions and behavior in real time to individually optimize learning materials. Furthermore, they lack the ability to propose customized products and services in virtual environments, making it impossible to provide a personalized experience tailored to users' interests and behavior. This makes it difficult to maintain motivation to learn and effectively promote purchases.

[0121] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0122] In this invention, the server includes means for detecting and analyzing facial expressions, means for detecting and analyzing behavior, means for adjusting and providing learning materials based on the facial expressions and behavior, means for providing the analysis results as feedback to parents and teachers, and means for analyzing the facial expressions and behavior of the user in the virtual environment and adjusting the products or services provided, thereby enabling the provision of personalized learning materials based on the user's facial expressions and behavior and optimizing the user experience in the virtual environment.

[0123] The "means for detecting and analyzing facial expressions" is a system that captures a user's facial expressions in real time and uses a machine learning model to classify and analyze the expressions.

[0124] The "means for detecting and analyzing behavior" is a system that uses a camera to capture video frames to analyze a user's movements and postures, and then uses a machine learning model to classify and analyze the behavior.

[0125] The "means for adjusting and providing learning materials" is a system that selects optimal learning materials based on the analyzed user's facial expressions and behavior and provides them to the user.

[0126] The "means for providing feedback" is a system that provides the results of an analysis of the user's learning situation as information to parents and teachers, and provides results and advice for educational support.

[0127] The "means for tailoring products or services in a virtual environment" is a system that analyzes the user's facial expressions and behavior in real time and, based on the results, customizes and proposes products and services to be offered in a virtual store.

[0128] The present invention is a system that analyzes a user's learning status and behavior in a virtual environment in real time, and based on the results, provides individually optimized learning materials, products, and services. Specific embodiments for implementing the present invention are described below.

[0129] First, the server loads the facial expression and behavior recognition models. These models are machine learning models used to analyze the user's facial expressions and behavior. The server then executes these models using machine learning libraries such as TensorFlow and Keras.

[0130] Next, the device activates the camera and captures the user's video in real time. The captured video frames are input into a facial expression recognition model, which classifies the user's facial expression as "happy," "neutral," "sad," etc. Based on the results of this facial expression analysis, the user's emotional state is understood.

[0131] In parallel, the device accumulates a certain number of frames in a buffer and inputs them into the behavior recognition model. The behavior recognition model classifies the user's behavior from these frames as "attentive," "distracted," "fidgeting," etc. In this way, the user's behavioral state is also understood.

[0132] Based on the analysis of these facial expressions and behaviors, the device selects and provides the most suitable learning materials to the user. Specifically, if the user is "happy" and "attentive," it provides advanced learning materials. On the other hand, if the user is "neutral" or "distracted," it provides standard learning materials, and if the user is "sad" or "fidgeting," it provides basic learning materials. This process maintains the user's motivation to learn and promotes effective learning progress.

[0133] The system of the present invention also analyzes a user's facial expressions and behavior in the virtual environment and adjusts the products and services provided based on the analysis. For example, during a shopping experience in a virtual store, if a user's facial expression is "happy" and their behavior is "attentive," the system will suggest related luxury products and special offers. On the other hand, if the user's facial expression is classified as "sad" or "distracted," the system will provide support suggestions and discount information. This will increase the user's purchasing motivation and create a more satisfying shopping experience.

[0134] Furthermore, the server generates detailed feedback based on the analysis results sent from the device. This feedback is provided to parents and teachers and includes information on the user's learning status and appropriate teaching methods. Based on this information, parents and teachers can take effective approaches to support the user's educational growth.

[0135] As a concrete example, imagine a user is solving math problems online. If the device analyzes the user's face and classifies it as "happy" and their behavior as "attentive," the device will offer the user advanced problems or additional assignments. Conversely, if the device classifies the user's facial expression as "sad" and their behavior as "distracted," the device will offer the user basic review questions or supplementary materials. In this way, the user's learning experience is personalized.

[0136] Additionally, as an example of a prompt sentence using a generative AI model, the following can be entered:

[0137] "As users browse products in a virtual store, facial expression and behavioral recognition models should analyze their emotions and behavior in real time. Based on the analysis results, analyze how to suggest products and services that may interest the user and generate optimal suggestions."

[0138] The system of the present invention uses a means for analyzing a user's facial expressions and behavior to provide learning materials that are tailored in real time to provide an optimal educational environment that is adapted to individual learning needs. In addition, in the virtual environment, a personalized experience based on the user's behavior is provided, improving user motivation and satisfaction.

[0139] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0140] Step 1:

[0141] The server loads the facial expression recognition model and the behavior recognition model.

[0142] Input: A file of a pre-trained machine learning model.

[0143] Output: Facial expression and action recognition models loaded in memory.

[0144] What it does: The server reads machine learning model files from a database or local storage and loads these models into memory using TensorFlow or Keras.

[0145] Step 2:

[0146] The device activates the camera and captures the user's video in real time.

[0147] Input: A camera device connected to the device.

[0148] Output: Real-time video frames.

[0149] Specific operation: The device initializes the camera device and continuously captures the user's video data. It then uses a library such as OpenCV to acquire video frames.

[0150] Step 3:

[0151] The captured video frames are input into a facial expression recognition model.

[0152] Input: Real-time video frames.

[0153] Output: User's facial expression class (e.g. happy, neutral, sad).

[0154] Specific operation: The device converts the captured video frame to grayscale, resizes and normalizes it to match the input format of the facial expression recognition model, and then inputs this processed video data into the facial expression recognition model to obtain analysis results.

[0155] Step 4:

[0156] The device stores a certain number of frames in a buffer and inputs them into the behavior recognition model.

[0157] Input: A buffer of real-time video frames.

[0158] Output: User behavior class (e.g., attentive, distracted, fidgeting).

[0159] Specific operation: The device stores real-time video frames in a buffer for a certain period of time and inputs this buffer into the behavior recognition model. The behavior recognition model analyzes this continuous frame data and classifies the user's specific behavior.

[0160] Step 5:

[0161] Based on the analysis of facial expressions and behavior, the device selects and provides the most suitable learning materials to the user.

[0162] Input: Analysis results of facial expression classes and behavior classes.

[0163] Output: Selected learning materials.

[0164] Specific operation: Based on the analysis of facial expressions and behavior, the device searches the database for the most appropriate learning materials and provides them to the user. For example, a user who is "happy" and "attentive" will receive advanced learning materials, while a user who is "sad" and "distracted" will receive basic supplementary learning materials.

[0165] Step 6:

[0166] The device sends the analysis results to a server, which generates detailed feedback.

[0167] Input: Facial expression and behavior analysis results.

[0168] Output: Feedback report.

[0169] Specific operation: The device sends the analysis results of facial expressions and behaviors to the server, which then generates a detailed feedback report based on the analysis results. This feedback is provided to parents and teachers.

[0170] Step 7:

[0171] In a virtual environment, the user's facial expressions and behavior are analyzed and the products or services provided are adjusted accordingly.

[0172] Input: Real-time facial and behavioral analysis results.

[0173] Output: A customized product or service proposal.

[0174] Specific operation: The system analyzes the user's facial expressions and behavior in real time within the virtual store, and then customizes and suggests relevant products and services based on the analysis results. For example, it offers luxury products and special offers to users who are "happy" and "attentive," and offers support or discount information to users who are "sad" or "distracted."

[0175] These are the specific steps for implementing the system, which makes it possible to provide a personalized experience based on the user's learning status and behavior in the virtual environment.

[0176] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0177] The present invention is a system that analyzes a user's learning status in real time and provides learning materials adapted to individual needs. The system also incorporates an emotion engine that recognizes the user's emotions, thereby further personalizing the learning experience. Specific embodiments for implementing the present invention will now be described.

[0178] First, the server loads the facial expression recognition model, behavior recognition model, and emotion engine, which are machine learning models used to analyze the user's facial expressions, behavior, and emotions.

[0179] Next, the device activates the camera and captures the user's video in real time. The captured video frames are input into a facial expression recognition model, which classifies the user's facial expressions as "happy," "neutral," "sad," etc. Based on the results of this facial expression analysis, the user's emotional state is further analyzed by the emotion engine. The emotion engine identifies multiple emotional states based on the user's facial expression data and behavioral data, and provides more detailed emotional information.

[0180] In parallel, the device stores a certain number of frames in a buffer and inputs them into an activity recognition model. The activity recognition model classifies the user's behavior from these frames as "attentive," "distracted," "fidgeting," etc. In this way, the user's behavioral state is also understood.

[0181] Based on the results of these facial and behavioral analyses, as well as the detailed emotional information provided by the emotion engine, the device selects the appropriate level of learning materials to provide to the user. Specifically, if the user is "happy" and "attentive" and the emotion engine classifies them as "excited," advanced learning materials will be selected. On the other hand, if the user is "neutral" or "distracted" and the emotion engine classifies them as "anxious," standard learning materials will be selected. Furthermore, if the user is "sad" or "fidgeting" and the emotion engine classifies them as "sad," basic learning materials will be selected.

[0182] As a concrete example, consider a user watching a video of a scientific experiment online. If the device analyzes the user's face and classifies it as "happy" and their behavior as "attentive," and the emotion engine then classifies it as "excited," the device will provide the user with detailed experimental procedures and applied experiments. On the other hand, if the device classifies the user's facial expression as "sad" and their behavior as "distracted," and the emotion engine then classifies them as "anxious," the device will provide the user with basic experimental procedures and supplementary materials. In this way, the user's learning experience is highly personalized.

[0183] Furthermore, the server generates detailed feedback based on the analysis results sent from the device and the emotion engine's analysis results. This feedback is provided to parents and teachers and includes information on the user's learning status and appropriate teaching methods. This allows parents and teachers to accurately understand the user's learning status and provide appropriate support and guidance.

[0184] As described above, the system of the present invention uses a means for analyzing a user's facial expressions, behavior, and emotions to adjust and provide learning materials in real time, providing an optimal educational environment adapted to individual learning needs. The introduction of an emotion engine allows for a detailed understanding of the user's emotional state, which is expected to further improve learning effectiveness.

[0185] The processing flow will be explained below.

[0186] Step 1:

[0187] The server loads the facial expression recognition model, the behavior recognition model, and the emotion engine, which prepares the system for rapid analysis processing.

[0188] Step 2:

[0189] The device activates the camera and captures the user's video in real time, and the captured video frames are used for subsequent analysis.

[0190] Step 3:

[0191] The device inputs the captured video frames into a facial expression recognition model to analyze the user's facial expression. As a result of the analysis, the user's facial expression is classified as "happy," "neutral," "sad," etc.

[0192] Step 4:

[0193] The device stores a certain number of frames in a buffer and inputs them into an activity recognition model, which uses these frames to classify the user's behavior as "attentive," "distracted," "fidgeting," etc.

[0194] Step 5:

[0195] The device inputs the analysis results of the facial expression and behavior recognition models into the emotion engine, which then analyzes the user's emotional state in more detail. Based on this data, the emotion engine classifies the user's emotions as "excitement," "anxiety," "sadness," etc.

[0196] Step 6:

[0197] The device analyzes facial expressions, behavior, and emotions to select the appropriate level of learning materials to provide to the user. For example, if the user is "happy," "attentive," and "excited," advanced learning materials will be selected.

[0198] Step 7:

[0199] The device provides the user with learning materials selected based on the user's learning progress and level of understanding.

[0200] Step 8:

[0201] The device sends the results of its facial expression, behavior, and emotional analysis to a server, which then uses this information to generate feedback.

[0202] Step 9:

[0203] Based on the analysis results received by the server, detailed feedback is generated for parents and teachers, including information on the user's learning status and appropriate teaching methods.

[0204] Step 10:

[0205] The server generates feedback and sends it to parents and teachers, allowing them to understand the user's learning status and provide appropriate guidance.

[0206] Through these steps, the system will be able to highly personalize the user's learning experience and provide effective support to parents and teachers.

[0207] Example 2

[0208] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0209] Conventional learning systems have difficulty providing optimal learning materials according to a user's learning situation. Furthermore, because learning materials are selected without taking the user's emotional state into consideration, the user's learning effectiveness is not maximized. Furthermore, there is a lack of a way to accurately communicate the user's learning situation to parents and teachers. This makes it difficult to provide education adapted to individual learning needs.

[0210] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0211] In this invention, the server includes means for detecting and analyzing facial expressions, means for detecting and analyzing behavior, means for analyzing a user's emotions based on the user's facial expressions and behavior, means for adjusting and providing learning materials based on the facial expressions, behavior, and emotions, and means for providing the analysis results as feedback to parents and teachers. This makes it possible to provide learning materials adapted to the user's individual learning needs in real time, maximizing the user's learning effectiveness. In addition, detailed feedback to parents and teachers allows them to accurately grasp the user's learning status and provide effective support and guidance.

[0212] "Facial expression detection and analysis means" is the machine learning model or software used to capture a user's facial expressions and analyze those expressions.

[0213] The "means for detecting and analyzing behavior" is a machine learning model or software that stores and analyzes a certain number of video frames to capture and analyze the user's movements.

[0214] The "means for analyzing a user's emotions based on the user's facial expressions and behavior" refers to an algorithm or engine that uses the user's facial expression data and behavior data as input and classifies and analyzes the user's emotional state in detail.

[0215] The "means for adjusting and providing learning materials based on the facial expressions, behavior, and emotions" refers to logic or software for selecting and providing learning materials appropriate to the user's learning needs based on the analyzed facial expressions, behavior, and emotional data.

[0216] "Means for providing the analysis results as feedback to parents and teachers" is a system function for notifying parents and teachers of the analysis results of the user's learning status, emotions, and behavior, and providing support information for effective instruction.

[0217] The present invention is a system that analyzes a user's learning status in real time and provides learning materials adapted to individual needs. The system also incorporates an emotion engine that recognizes the user's emotions, thereby further personalizing the learning experience. Specific embodiments for implementing the present invention will now be described.

[0218] First, the server loads facial expression and behavior recognition models using machine learning libraries such as TensorFlow and PyTorch. These models are pre-trained with large amounts of data and can classify the user's facial expressions and behavior with high accuracy. The server also uses emotion engines such as Microsoft's Azure Emotion API and Google's Cloud Vision API to perform detailed analysis of the user's emotions.

[0219] Next, the device captures the user's video in real time using a Logitech webcam or similar. The captured video frames are first input into a facial expression recognition model, which classifies the user's facial expression into "happy," "neutral," "sad," etc. The results of this facial expression analysis are sent to an emotion engine for further detailed emotional analysis.

[0220] In parallel, the device stores a certain number of frames in a buffer and inputs them into an activity recognition model. This model classifies the user's behavior into categories such as "attentive," "distracted," and "fidgeting." In this way, the user's behavioral state is also understood.

[0221] Next, based on these analysis results, the device selects the appropriate level of learning materials to provide to the user. Specifically, if the user is "happy" and "attentive" and the emotion engine classifies them as "excited," advanced learning materials are selected. On the other hand, if the user is "neutral" or "distracted" and the emotion engine classifies them as "anxious," standard learning materials are selected. And if the user is "sad" or "fidgeting" and the emotion engine classifies them as "sad," basic learning materials are selected.

[0222] As a concrete example, consider a user watching a video of a scientific experiment online. If the device analyzes the user's face and classifies it as "happy" and their behavior as "attentive," and the emotion engine then classifies it as "excited," the device will provide the user with detailed experimental procedures and applied experiments. On the other hand, if the device classifies the user's facial expression as "sad," their behavior as "distracted," and the emotion engine then classifies them as "anxious," the device will provide the user with basic experimental procedures and supplementary materials. In this way, the user's learning experience is highly personalized.

[0223] Furthermore, the server generates detailed feedback for parents and teachers based on the analysis results sent from the device and the emotion engine's analysis results. This feedback includes information on the user's learning status and appropriate teaching methods, helping parents and teachers accurately understand the user's learning status and provide appropriate support and guidance.

[0224] Examples of prompts include:

[0225] "Please analyze the user's facial expressions and behavior in real time while they are watching this video and provide them with the most appropriate learning materials."

[0226] "Categorize your users' emotions in detail and adjust the difficulty of your learning materials based on the results."

[0227] As described above, the system of the present invention provides an optimal educational environment that adapts to individual learning needs by adjusting and providing learning materials in real time. Furthermore, the introduction of an emotion engine allows for detailed understanding of the user's emotional state, which is expected to further improve learning effectiveness.

[0228] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0229] Step 1:

[0230] The server loads the machine learning model and emotion engine.

[0231] Input: The model file and API key to use when loading.

[0232] What it does: The server loads facial expression and behavior recognition models using TensorFlow and PyTorch libraries, and prepares to use the Azure Emotion API and Google Cloud Vision API for emotion analysis.

[0233] Output: Initialized facial expression recognition model, action recognition model and emotion engine.

[0234] Step 2:

[0235] The device activates the camera and captures the user's image.

[0236] Input: A camera device connected to the device.

[0237] Specific operation: When a user starts learning, the device activates the camera device and captures the user's image in real time using a common webcam such as a Logitech camera.

[0238] Output: Real-time captured video data.

[0239] Step 3:

[0240] The device analyzes the video frames using a facial expression recognition model.

[0241] Input: Captured video frames.

[0242] How it works: Captured video frames are fed into a facial expression recognition model on the device's CPU or GPU, which classifies the user's facial expression for each frame into categories such as "happy," "neutral," or "sad."

[0243] Output: Classified facial expression data.

[0244] Step 4:

[0245] The device sends facial expression data to the emotion engine, which analyzes the emotions.

[0246] Input: Classified facial expression data.

[0247] How it works: The device sends the results of the facial expression recognition model to the emotion engine, which uses this data to classify the user's emotional state into categories such as "excitement," "anxiety," or "sadness."

[0248] Output: Detailed emotion data.

[0249] Step 5:

[0250] The device stores video frames in a buffer and analyzes them using an action recognition model.

[0251] Input: Captured video frames.

[0252] How it works: A certain number of frames are stored in a buffer and then fed into an action recognition model, which classifies the user's behavior as "attentive," "distracted," "fidgeting," etc.

[0253] Output: Classified behavioral data.

[0254] Step 6:

[0255] The device selects the most appropriate learning materials based on the facial expressions, behavior, and emotional data it obtains.

[0256] Input: facial expression data, behavioral data, and emotion data.

[0257] Specific operation: The device integrates this data and selects the most suitable learning materials for the user. For example, if the user is "happy" and "attentive" and their emotion is classified as "excited," the device will display advanced learning materials.

[0258] Output: The learning material provided to the user.

[0259] Step 7:

[0260] The server receives the data from the terminal and generates feedback.

[0261] Input: Analysis results and emotion data sent from the device.

[0262] What it does: The server receives this data and generates detailed feedback for parents and teachers, including information about the user's learning progress, emotional state, and appropriate teaching methods.

[0263] Output: Feedback information for parents and teachers.

[0264] (Application example 2)

[0265] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0266] Conventional learning systems have difficulty adapting to a user's learning situation and emotional state in real time. As a result, they are unable to provide a personalized learning experience that meets the user's individual needs, resulting in reduced learning effectiveness. It is also difficult for parents and teachers to accurately grasp a user's learning situation and provide appropriate support. Furthermore, even with online educational content distribution services, it is difficult to provide content that responds to a user's real-time emotions and behavior, delaying learning optimization.

[0267] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0268] In this invention, the server includes means for detecting and analyzing facial expressions, means for detecting and analyzing behavior, means for adjusting and providing learning materials based on the facial expressions and behavior, means for adjusting and providing learning materials in real time based on the analysis results and detailed emotional information generated by the emotion engine, and means for providing the analysis results as feedback to parents and teachers. This makes it possible to personalize content using generated prompts based on the user's emotional state. This makes it possible to accurately grasp the user's learning situation and provide appropriate support, enabling a highly personalized learning experience.

[0269] "Means for detecting and analyzing facial expressions" refers to a device or method for recognizing facial expressions from an image of a user's face and analyzing their specific emotional state.

[0270] The "means for detecting and analyzing behavior" refers to a device or method for capturing a user's daily actions and behavior from video data and analyzing the behavioral patterns.

[0271] The "means for adjusting and providing learning materials" refers to a device or method for selecting learning materials of appropriate difficulty and type based on the analysis of the user's facial expressions and behavior, and providing them in real time.

[0272] An "emotion engine" is an advanced algorithm or model that analyzes a user's facial and behavioral data to identify more detailed emotional states.

[0273] "Detailed emotion information from the emotion engine" is information on the user's various emotional states and their changes, obtained as a result of analysis by the emotion engine.

[0274] The "means for providing feedback" is a device or method for providing parents and teachers with reports and advice generated based on the analysis results and emotional information.

[0275] A "generative AI model" is a machine learning model used to analyze a user's facial expressions and behavior and identify their detailed emotional state.

[0276] "Generative prompts" are instructions or guidelines used to optimize learning content or materials based on the user's emotional state.

[0277] The "means for adjusting and providing in real time" refers to a device or method for instantly changing and providing learning materials according to the user's current situation.

[0278] The present invention is a system that analyzes a user's learning status in real time and provides personalized learning materials based on the user's emotions and behavior. Specifically, this system is configured as follows.

[0279] First, the server loads the facial expression recognition model, behavioral recognition model, and emotion engine. These models are based on machine learning and are used to analyze the user's facial expressions, behavior, and emotions. Specifically, the facial expression recognition model classifies the user's facial expressions into categories such as "happy," "neutral," and "sad," while the behavioral recognition model classifies the user's behavior into categories such as "attentive," "distracted," and "fidgeting." The emotion engine also uses a generative AI model to identify detailed emotional states and provides more complex emotional information from the user's facial expression and behavioral data.

[0280] Next, the device used by the user activates the camera and captures the user's video in real time. The captured video frames are input into a facial expression recognition model, and the user's facial expressions are analyzed. At the same time, a certain number of frames are stored in a buffer and input into a behavior recognition model. This allows the user's behavior to be analyzed in real time.

[0281] Based on the analysis results, the device selects the appropriate level of learning materials to provide to the user. Specifically, if the user is "happy" and "attentive" and the emotion engine classifies them as "excited," advanced learning materials are selected. On the other hand, if the user is "neutral" or "distracted" and the emotion engine classifies them as "anxious," standard learning materials are selected. Also, if the user is "sad" or "fidgeting" and the emotion engine classifies them as "sad," basic learning materials are selected.

[0282] Furthermore, the server generates detailed feedback based on the analysis results sent from the device and the emotion engine's analysis results. This feedback is provided to parents and teachers and includes information on the user's learning status and appropriate teaching methods.

[0283] For example, if a user is watching an online video of a science experiment, and the device analyzes the user's face and classifies it as "happy" and their behavior as "attentive," and the emotion engine classifies it as "excited," the device will provide the user with detailed experimental procedures and applied experiments. On the other hand, if the device classifies the user's facial expression as "sad" and their behavior as "distracted," and the emotion engine classifies them as "anxious," the device will provide the user with basic experimental procedures and supplementary materials. In this way, the user's learning experience is highly personalized.

[0284] Example prompt sentence:

[0285] By setting prompts as follows, you can have the generative AI model perform detailed analysis.

[0286] prompt

[0287] The system inputs the user's facial expression and behavior data and analyzes it using facial expression and behavior recognition models. It then uses an emotion engine to estimate the user's detailed emotional state, and selects and provides appropriate learning materials based on that.

[0288] Input data

[0289] User's facial expression image (live video frame)

[0290] User behavior data (a certain number of frames)

[0291] output

[0292] Appropriate learning materials

[0293] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0294] Step 1:

[0295] The device used by the user activates the camera and captures the user's image in real time.

[0296] Input: Live video of the user's face

[0297] Output: Video frame

[0298] Specific operation: The device's camera detects the user's face and captures the image.

[0299] Step 2:

[0300] The captured video frames are input into a facial expression recognition model to analyze the user's facial expressions.

[0301] Input: Video frame

[0302] Output: User's facial expression data (e.g. "happy", "neutral", "sad")

[0303] Specific operation: The device passes video frames to the facial expression recognition model, which then classifies the facial expression.

[0304] Step 3:

[0305] A certain number of frames are stored in a buffer and input into the action recognition model.

[0306] Input: A certain number of video frames

[0307] Output: User behavior data (e.g., "attentive," "distracted," "fidgeting")

[0308] Specific operation: Continuous images captured by the camera are stored in a buffer, and the buffer is passed to the action recognition model for analysis.

[0309] Step 4:

[0310] The analysis results are input into an emotion engine to identify detailed emotional states.

[0311] Input: facial expression data, behavior data

[0312] Output: Detailed emotional information (e.g., "excitement," "anxiety," "sadness")

[0313] Specific behavior: The emotion engine analyzes facial expression and behavior data to estimate detailed emotional states.

[0314] Step 5:

[0315] Based on the analysis results and those of the emotion engine, the device selects appropriate learning materials.

[0316] Input: Detailed emotional information

[0317] Output: Selected learning material content

[0318] Specific operation: Based on the user's emotional state in real time, the device selects learning materials suitable for the user from the database.

[0319] Step 6:

[0320] Selected learning materials are provided to users.

[0321] Input: Content of selected learning materials

[0322] Output: Learning materials that can be viewed or used by the user

[0323] Specific operation: The terminal displays the selected learning materials to the user.

[0324] Step 7:

[0325] The server generates detailed feedback based on the analysis results sent from the device and the analysis results of the emotion engine.

[0326] Input: Analysis results, emotion engine analysis results

[0327] Output: Feedback to parents and teachers

[0328] Specific operation: The server aggregates the data and generates reports and teaching guidelines for parents and teachers.

[0329] Step 8:

[0330] Provide feedback to parents and teachers.

[0331] Input: Generated feedback

[0332] Output: Report on the user's learning progress

[0333] Specific operation: The server sends the feedback to the parent and teacher's devices and displays it.

[0334] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0335] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0336] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0337] [Second embodiment]

[0338] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0339] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0340] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0341] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0342] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0343] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0344] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0345] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0346] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0347] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0348] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0349] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0350] The system of the present invention is capable of analyzing the user's learning status in real time and providing optimal learning materials to each user based on the results. Specific embodiments for carrying out the present invention will now be described.

[0351] First, the server loads the facial expression and behavior recognition models, which are machine learning models used to analyze the user's facial expressions and behavior.

[0352] Next, the device activates the camera and captures the user's video in real time. The captured video frames are input into a facial expression recognition model, which classifies the user's facial expression as "happy," "neutral," "sad," etc. Based on the results of this facial expression analysis, the user's emotional state is understood.

[0353] In parallel, the device stores a certain number of frames in a buffer and inputs them into an activity recognition model. The activity recognition model classifies the user's behavior from these frames as "attentive," "distracted," "fidgeting," etc. In this way, the user's behavioral state is also understood.

[0354] Based on the analysis of these facial expressions and behaviors, the device selects and provides the most suitable learning materials to the user. Specifically, if the user is "happy" and "attentive," it provides advanced learning materials. On the other hand, if the user is "neutral" or "distracted," it provides standard learning materials, and if the user is "sad" or "fidgeting," it provides basic learning materials. This process maintains the user's motivation to learn and promotes effective learning progress.

[0355] Furthermore, the server generates detailed feedback based on the analysis results sent from the device. This feedback is provided to parents and teachers and includes information on the user's learning status and appropriate teaching methods. Based on this information, parents and teachers can take effective approaches to support the user's educational growth.

[0356] As a concrete example, imagine a user is solving math problems online. If the device analyzes the user's face and classifies it as "happy" and their behavior as "attentive," the device will offer the user advanced problems or additional assignments. Conversely, if the device classifies the user's facial expression as "sad" and their behavior as "distracted," the device will offer the user basic review questions or supplementary materials. In this way, the user's learning experience is personalized.

[0357] As described above, the system of the present invention uses a means for analyzing a user's facial expressions and behavior to adjust and provide learning materials in real time, providing an optimal educational environment that is adapted to individual learning needs. This system increases the user's motivation to learn and allows teachers and parents to provide appropriate support.

[0358] The processing flow will be explained below.

[0359] Step 1:

[0360] The server loads the facial expression and behavior recognition models, which prepares the system for rapid analysis.

[0361] Step 2:

[0362] The device activates the camera and captures the user's video in real time, and the captured video frames are used for subsequent analysis.

[0363] Step 3:

[0364] The device inputs the captured video frames into a facial expression recognition model to analyze the user's facial expression. As a result of the analysis, the user's facial expression is classified as "happy," "neutral," "sad," etc.

[0365] Step 4:

[0366] The device stores a certain number of frames in a buffer and inputs them into an activity recognition model, which uses these frames to classify the user's behavior as "attentive," "distracted," "fidgeting," etc.

[0367] Step 5:

[0368] The device selects the appropriate level of learning materials to provide to the user based on the analysis of their facial expressions and behavior. Specifically, if the user is "happy" and "attentive," advanced learning materials will be selected.

[0369] Step 6:

[0370] The device provides the user with learning materials selected based on the user's learning progress and level of understanding.

[0371] Step 7:

[0372] The device sends the results of facial and behavioral analysis to a server, which uses this information to generate feedback later.

[0373] Step 8:

[0374] Based on the analysis results received by the server, detailed feedback is generated for parents and teachers, including information about the user's learning status and appropriate teaching methods.

[0375] Step 9:

[0376] The server generates feedback and sends it to parents and teachers, allowing them to understand the user's learning status and provide appropriate support and guidance.

[0377] Through each step, the system personalizes the user's learning experience and enables parents and teachers to provide effective support.

[0378] Example 1

[0379] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0380] Conventional educational systems have the problem of being unable to grasp the learning status of individual users in real time and provide optimal learning materials accordingly. Furthermore, there are limited means of providing appropriate feedback on the user's educational progress and status to parents and teachers. This makes it difficult to maintain the user's motivation to learn and effective learning progress. Therefore, there is a need for a system that can analyze the user's facial expressions and behavior in real time, adjust and provide learning materials based on that information, and provide the analysis results as feedback to parents and teachers.

[0381] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0382] In this invention, the server includes means for using a machine learning model to detect and classify a user's facial expressions, means for using a machine learning model to detect and classify the user's behavior, means for capturing video of the user in real time, means for adjusting and providing learning materials based on the facial expressions and behavior, and means for providing the analysis results as feedback to parents and teachers. This makes it possible to analyze the user's facial expressions and behavior in real time, and to provide optimal learning materials based on the analysis results and provide appropriate feedback of the analysis results.

[0383] "Machine learning model for detecting and classifying user facial expressions" refers to the algorithm used to analyze video data of a user captured by a camera and classify it into emotional states such as "happy," "neutral," and "sad."

[0384] A "machine learning model for detecting and classifying user behavior" refers to an algorithm that analyzes video data consisting of multiple frames and classifies user behavior into categories such as "attentive," "distracted," and "fidgeting."

[0385] "Means for capturing a user's image in real time" refers to the process of using a camera built into or connected to a device to capture the user's movements and facial expressions in real time and obtain the video data.

[0386] "Means for adjusting and providing learning materials" refers to the process of selecting and providing the most suitable learning materials (advanced learning materials, standard learning materials, basic learning materials) to the user based on the analysis of the user's facial expressions and behavior.

[0387] "Means for providing analysis results as feedback to parents and teachers" refers to a process for generating and providing detailed feedback to parents and teachers based on the analysis results regarding the user's learning status.

[0388] A "machine learning model" refers to an artificial intelligence technique that trains algorithms based on large data sets to recognize patterns and make predictions about new data.

[0389] The system of the present invention utilizes a machine learning model to analyze a user's facial expressions and behavior in real time, provides optimal learning materials based on the analysis results, and also provides the analysis results as feedback to parents and teachers. Specific embodiments of the present invention are described below.

[0390] First, the server uses machine learning libraries such as TensorFlow and PyTorch to load pre-trained facial expression and behavior recognition models into memory, which enables the server to analyze the user's video data.

[0391] When a user starts learning, the device activates the built-in or connected camera and captures the user's video in real time. The video data is acquired frame by frame and used for analysis.

[0392] The device preprocesses the captured video frames and inputs them into a facial expression recognition model, which classifies the user's facial expression into "happy," "neutral," "sad," etc., and returns the result to the device, allowing the device to understand the user's emotional state.

[0393] In parallel, the device accumulates a certain number of frames in a buffer and inputs them into the behavior recognition model. The behavior recognition model classifies the user's behavior from these frames into categories such as "attentive," "distracted," and "fidgeting," and returns the results to the device. This allows the device to understand the user's behavioral state.

[0394] The device selects and provides the most suitable learning materials to the user based on the analysis results of facial expressions and behaviors obtained from the server. Specifically, if the user is "happy" and "attentive," advanced learning materials are provided, if the user is "neutral" or "distracted," standard learning materials are provided, and if the user is "sad" or "fidgeting," basic learning materials are provided.

[0395] Furthermore, the server generates detailed feedback based on the analysis results sent from the device. This feedback is provided to parents and teachers and includes information on the user's learning status and appropriate teaching methods, allowing parents and teachers to take effective approaches to support the user's educational growth.

[0396] As a concrete example, consider a user solving a math problem online. If the device analyzes the user's face and classifies it as "happy" and their behavior as "attentive," the device will provide the user with applied problems or additional assignments. On the other hand, if the device classifies the user's facial expression as "sad" and their behavior as "distracted," the device will provide the user with basic review questions or supplementary materials. In this way, the user's learning experience is personalized.

[0397] An example of a prompt is, "If a user is solving a math problem and their facial expression is classified as 'happy' and their behavior is classified as 'attentive,' please suggest what kind of learning material should be provided in the next step. Please also specify the machine learning model to be used and the role of the server / device."

[0398] The system of the present invention analyzes the user's learning status in real time and provides optimal learning materials based on that analysis, thereby realizing an educational environment that is adapted to individual learning needs. This increases the user's motivation to learn, promotes effective learning progress, and allows parents and teachers to provide appropriate support.

[0399] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0400] Step 1:

[0401] The server loads the facial expression recognition model and the behavior recognition model.

[0402] Input: The server receives a machine learning library (TensorFlow or PyTorch) and a pre-trained model file.

[0403] Specific operation: The server uses the TensorFlow and PyTorch libraries to load each machine learning model into memory, which prepares the server for face recognition and behavior recognition calculations.

[0404] Output: The loaded facial expression recognition model and behavior recognition model are prepared in memory.

[0405] Step 2:

[0406] The device activates the camera and captures the user's image.

[0407] Input: The user inputs an instruction to start learning into the terminal.

[0408] Specific operation: The device activates the built-in or connected camera and captures the user's video in real time. The video data is acquired frame by frame.

[0409] Output: A sequence of video frames is generated and made available in real time.

[0410] Step 3:

[0411] The device analyzes the user's facial expression using a facial expression recognition model.

[0412] Input: Captured video frames of the user

[0413] How it works: The device preprocesses video frames and sends them to the server's facial expression recognition model, which then classifies the user's facial expression into categories such as "happy," "neutral," or "sad." Preprocessing includes frame resizing and normalization.

[0414] Output: Classification result of the analyzed facial expression (e.g. "happy").

[0415] Step 4:

[0416] The device analyzes the user's behavior using a behavior recognition model

[0417] Input: A certain number of captured video frames

[0418] Specific operation: The device accumulates a certain number of frames in a buffer and sends the buffer to the server's activity recognition model. The activity recognition model classifies the user's behavior from these frames into categories such as "attentive," "distracted," and "fidgeting." Preprocessing includes configuring the buffer and resizing the frames.

[0419] Output: Classification result of the analyzed behavior (e.g. "attentive").

[0420] Step 5:

[0421] The device selects and provides learning materials based on the analysis results

[0422] Input: Analysis results of facial expressions and behavior obtained from the server

[0423] Specific behavior: Evaluate each data combination and select the most suitable learning material for the user. For example, if the user is "happy" and "attentive," select advanced learning materials. The selection process is based on predefined rules and conditions.

[0424] Output: The selected learning materials (e.g., advanced learning materials) are provided to the user via the terminal.

[0425] Step 6:

[0426] The server generates detailed feedback

[0427] Input: Analysis results of facial expressions and behavior sent from the device

[0428] Specific operation: The server generates detailed feedback based on the analysis results and provides it to parents and teachers. The feedback includes specific information about the user's learning progress, areas for improvement, and teaching methods.

[0429] Output: A detailed feedback document is generated and sent to parents and teachers.

[0430] The process of analyzing and selecting data based on input data in each processing step and obtaining each output has been described in detail above.

[0431] (Application example 1)

[0432] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0433] Conventional learning systems have difficulty analyzing users' facial expressions and behavior in real time to individually optimize learning materials. Furthermore, they lack the ability to propose customized products and services in virtual environments, making it impossible to provide a personalized experience tailored to users' interests and behavior. This makes it difficult to maintain motivation to learn and effectively promote purchases.

[0434] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0435] In this invention, the server includes means for detecting and analyzing facial expressions, means for detecting and analyzing behavior, means for adjusting and providing learning materials based on the facial expressions and behavior, means for providing the analysis results as feedback to parents and teachers, and means for analyzing the facial expressions and behavior of the user in the virtual environment and adjusting the products or services provided, thereby enabling the provision of personalized learning materials based on the user's facial expressions and behavior and optimizing the user experience in the virtual environment.

[0436] The "means for detecting and analyzing facial expressions" is a system that captures a user's facial expressions in real time and uses a machine learning model to classify and analyze the expressions.

[0437] The "means for detecting and analyzing behavior" is a system that uses a camera to capture video frames to analyze a user's movements and postures, and then uses a machine learning model to classify and analyze the behavior.

[0438] The "means for adjusting and providing learning materials" is a system that selects optimal learning materials based on the analyzed user's facial expressions and behavior and provides them to the user.

[0439] The "means for providing feedback" is a system that provides the results of an analysis of the user's learning situation as information to parents and teachers, and provides results and advice for educational support.

[0440] The "means for tailoring products or services in a virtual environment" is a system that analyzes the user's facial expressions and behavior in real time and, based on the results, customizes and proposes products and services to be offered in a virtual store.

[0441] The present invention is a system that analyzes a user's learning status and behavior in a virtual environment in real time, and based on the results, provides individually optimized learning materials, products, and services. Specific embodiments for implementing the present invention are described below.

[0442] First, the server loads the facial expression and behavior recognition models. These models are machine learning models used to analyze the user's facial expressions and behavior. The server then executes these models using machine learning libraries such as TensorFlow and Keras.

[0443] Next, the device activates the camera and captures the user's video in real time. The captured video frames are input into a facial expression recognition model, which classifies the user's facial expression as "happy," "neutral," "sad," etc. Based on the results of this facial expression analysis, the user's emotional state is understood.

[0444] In parallel, the device accumulates a certain number of frames in a buffer and inputs them into the behavior recognition model. The behavior recognition model classifies the user's behavior from these frames as "attentive," "distracted," "fidgeting," etc. In this way, the user's behavioral state is also understood.

[0445] Based on the analysis of these facial expressions and behaviors, the device selects and provides the most suitable learning materials to the user. Specifically, if the user is "happy" and "attentive," it provides advanced learning materials. On the other hand, if the user is "neutral" or "distracted," it provides standard learning materials, and if the user is "sad" or "fidgeting," it provides basic learning materials. This process maintains the user's motivation to learn and promotes effective learning progress.

[0446] The system of the present invention also analyzes a user's facial expressions and behavior in the virtual environment and adjusts the products and services provided based on the analysis. For example, during a shopping experience in a virtual store, if a user's facial expression is "happy" and their behavior is "attentive," the system will suggest related luxury products and special offers. On the other hand, if the user's facial expression is classified as "sad" or "distracted," the system will provide support suggestions and discount information. This will increase the user's purchasing motivation and create a more satisfying shopping experience.

[0447] Furthermore, the server generates detailed feedback based on the analysis results sent from the device. This feedback is provided to parents and teachers and includes information on the user's learning status and appropriate teaching methods. Based on this information, parents and teachers can take effective approaches to support the user's educational growth.

[0448] As a concrete example, imagine a user is solving math problems online. If the device analyzes the user's face and classifies it as "happy" and their behavior as "attentive," the device will offer the user advanced problems or additional assignments. Conversely, if the device classifies the user's facial expression as "sad" and their behavior as "distracted," the device will offer the user basic review questions or supplementary materials. In this way, the user's learning experience is personalized.

[0449] Additionally, as an example of a prompt sentence using a generative AI model, the following can be entered:

[0450] "As users browse products in a virtual store, facial expression and behavioral recognition models should analyze their emotions and behavior in real time. Based on the analysis results, analyze how to suggest products and services that may interest the user and generate optimal suggestions."

[0451] The system of the present invention uses a means for analyzing a user's facial expressions and behavior to provide learning materials that are tailored in real time to provide an optimal educational environment that is adapted to individual learning needs. In addition, in the virtual environment, a personalized experience based on the user's behavior is provided, improving user motivation and satisfaction.

[0452] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0453] Step 1:

[0454] The server loads the facial expression recognition model and the behavior recognition model.

[0455] Input: A file of a pre-trained machine learning model.

[0456] Output: Facial expression and action recognition models loaded in memory.

[0457] What it does: The server reads machine learning model files from a database or local storage and loads these models into memory using TensorFlow or Keras.

[0458] Step 2:

[0459] The device activates the camera and captures the user's video in real time.

[0460] Input: A camera device connected to the device.

[0461] Output: Real-time video frames.

[0462] Specific operation: The device initializes the camera device and continuously captures the user's video data. It then uses a library such as OpenCV to acquire video frames.

[0463] Step 3:

[0464] The captured video frames are input into a facial expression recognition model.

[0465] Input: Real-time video frames.

[0466] Output: User's facial expression class (e.g. happy, neutral, sad).

[0467] Specific operation: The device converts the captured video frame to grayscale, resizes and normalizes it to match the input format of the facial expression recognition model, and then inputs this processed video data into the facial expression recognition model to obtain analysis results.

[0468] Step 4:

[0469] The device stores a certain number of frames in a buffer and inputs them into the behavior recognition model.

[0470] Input: A buffer of real-time video frames.

[0471] Output: User behavior class (e.g., attentive, distracted, fidgeting).

[0472] Specific operation: The device stores real-time video frames in a buffer for a certain period of time and inputs this buffer into the behavior recognition model. The behavior recognition model analyzes this continuous frame data and classifies the user's specific behavior.

[0473] Step 5:

[0474] Based on the analysis of facial expressions and behavior, the device selects and provides the most suitable learning materials to the user.

[0475] Input: Analysis results of facial expression classes and behavior classes.

[0476] Output: Selected learning materials.

[0477] Specific operation: Based on the analysis of facial expressions and behavior, the device searches the database for the most appropriate learning materials and provides them to the user. For example, a user who is "happy" and "attentive" will receive advanced learning materials, while a user who is "sad" and "distracted" will receive basic supplementary learning materials.

[0478] Step 6:

[0479] The device sends the analysis results to a server, which generates detailed feedback.

[0480] Input: Facial expression and behavior analysis results.

[0481] Output: Feedback report.

[0482] Specific operation: The device sends the analysis results of facial expressions and behaviors to the server, which then generates a detailed feedback report based on the analysis results. This feedback is provided to parents and teachers.

[0483] Step 7:

[0484] In a virtual environment, the user's facial expressions and behavior are analyzed and the products or services provided are adjusted accordingly.

[0485] Input: Real-time facial and behavioral analysis results.

[0486] Output: A customized product or service proposal.

[0487] Specific operation: The system analyzes the user's facial expressions and behavior in real time within the virtual store, and then customizes and suggests relevant products and services based on the analysis results. For example, it offers luxury products and special offers to users who are "happy" and "attentive," and offers support or discount information to users who are "sad" or "distracted."

[0488] These are the specific steps for implementing the system, which makes it possible to provide a personalized experience based on the user's learning status and behavior in the virtual environment.

[0489] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0490] The present invention is a system that analyzes a user's learning status in real time and provides learning materials adapted to individual needs. The system also incorporates an emotion engine that recognizes the user's emotions, thereby further personalizing the learning experience. Specific embodiments for implementing the present invention will now be described.

[0491] First, the server loads the facial expression recognition model, behavior recognition model, and emotion engine, which are machine learning models used to analyze the user's facial expressions, behavior, and emotions.

[0492] Next, the device activates the camera and captures the user's video in real time. The captured video frames are input into a facial expression recognition model, which classifies the user's facial expressions as "happy," "neutral," "sad," etc. Based on the results of this facial expression analysis, the user's emotional state is further analyzed by the emotion engine. The emotion engine identifies multiple emotional states based on the user's facial expression data and behavioral data, and provides more detailed emotional information.

[0493] In parallel, the device stores a certain number of frames in a buffer and inputs them into an activity recognition model. The activity recognition model classifies the user's behavior from these frames as "attentive," "distracted," "fidgeting," etc. In this way, the user's behavioral state is also understood.

[0494] Based on the results of these facial and behavioral analyses, as well as the detailed emotional information provided by the emotion engine, the device selects the appropriate level of learning materials to provide to the user. Specifically, if the user is "happy" and "attentive" and the emotion engine classifies them as "excited," advanced learning materials will be selected. On the other hand, if the user is "neutral" or "distracted" and the emotion engine classifies them as "anxious," standard learning materials will be selected. Furthermore, if the user is "sad" or "fidgeting" and the emotion engine classifies them as "sad," basic learning materials will be selected.

[0495] As a concrete example, consider a user watching a video of a scientific experiment online. If the device analyzes the user's face and classifies it as "happy" and their behavior as "attentive," and the emotion engine then classifies it as "excited," the device will provide the user with detailed experimental procedures and applied experiments. On the other hand, if the device classifies the user's facial expression as "sad" and their behavior as "distracted," and the emotion engine then classifies them as "anxious," the device will provide the user with basic experimental procedures and supplementary materials. In this way, the user's learning experience is highly personalized.

[0496] Furthermore, the server generates detailed feedback based on the analysis results sent from the device and the emotion engine's analysis results. This feedback is provided to parents and teachers and includes information on the user's learning status and appropriate teaching methods. This allows parents and teachers to accurately understand the user's learning status and provide appropriate support and guidance.

[0497] As described above, the system of the present invention uses a means for analyzing a user's facial expressions, behavior, and emotions to adjust and provide learning materials in real time, providing an optimal educational environment adapted to individual learning needs. The introduction of an emotion engine allows for a detailed understanding of the user's emotional state, which is expected to further improve learning effectiveness.

[0498] The processing flow will be explained below.

[0499] Step 1:

[0500] The server loads the facial expression recognition model, the behavior recognition model, and the emotion engine, which prepares the system for rapid analysis processing.

[0501] Step 2:

[0502] The device activates the camera and captures the user's video in real time, and the captured video frames are used for subsequent analysis.

[0503] Step 3:

[0504] The device inputs the captured video frames into a facial expression recognition model to analyze the user's facial expression. As a result of the analysis, the user's facial expression is classified as "happy," "neutral," "sad," etc.

[0505] Step 4:

[0506] The device stores a certain number of frames in a buffer and inputs them into an activity recognition model, which uses these frames to classify the user's behavior as "attentive," "distracted," "fidgeting," etc.

[0507] Step 5:

[0508] The device inputs the analysis results of the facial expression and behavior recognition models into the emotion engine, which then analyzes the user's emotional state in more detail. Based on this data, the emotion engine classifies the user's emotions as "excitement," "anxiety," "sadness," etc.

[0509] Step 6:

[0510] The device analyzes facial expressions, behavior, and emotions to select the appropriate level of learning materials to provide to the user. For example, if the user is "happy," "attentive," and "excited," advanced learning materials will be selected.

[0511] Step 7:

[0512] The device provides the user with learning materials selected based on the user's learning progress and level of understanding.

[0513] Step 8:

[0514] The device sends the results of its facial expression, behavior, and emotional analysis to a server, which then uses this information to generate feedback.

[0515] Step 9:

[0516] Based on the analysis results received by the server, detailed feedback is generated for parents and teachers, including information on the user's learning status and appropriate teaching methods.

[0517] Step 10:

[0518] The server generates feedback and sends it to parents and teachers, allowing them to understand the user's learning status and provide appropriate guidance.

[0519] Through these steps, the system will be able to highly personalize the user's learning experience and provide effective support to parents and teachers.

[0520] Example 2

[0521] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0522] Conventional learning systems have difficulty providing optimal learning materials according to a user's learning situation. Furthermore, because learning materials are selected without taking the user's emotional state into consideration, the user's learning effectiveness is not maximized. Furthermore, there is a lack of a way to accurately communicate the user's learning situation to parents and teachers. This makes it difficult to provide education adapted to individual learning needs.

[0523] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0524] In this invention, the server includes means for detecting and analyzing facial expressions, means for detecting and analyzing behavior, means for analyzing a user's emotions based on the user's facial expressions and behavior, means for adjusting and providing learning materials based on the facial expressions, behavior, and emotions, and means for providing the analysis results as feedback to parents and teachers. This makes it possible to provide learning materials adapted to the user's individual learning needs in real time, maximizing the user's learning effectiveness. In addition, detailed feedback to parents and teachers allows them to accurately grasp the user's learning status and provide effective support and guidance.

[0525] "Facial expression detection and analysis means" is the machine learning model or software used to capture a user's facial expressions and analyze those expressions.

[0526] The "means for detecting and analyzing behavior" is a machine learning model or software that stores and analyzes a certain number of video frames to capture and analyze the user's movements.

[0527] The "means for analyzing a user's emotions based on the user's facial expressions and behavior" refers to an algorithm or engine that uses the user's facial expression data and behavior data as input and classifies and analyzes the user's emotional state in detail.

[0528] The "means for adjusting and providing learning materials based on the facial expressions, behavior, and emotions" refers to logic or software for selecting and providing learning materials appropriate to the user's learning needs based on the analyzed facial expressions, behavior, and emotional data.

[0529] "Means for providing the analysis results as feedback to parents and teachers" is a system function for notifying parents and teachers of the analysis results of the user's learning status, emotions, and behavior, and providing support information for effective instruction.

[0530] The present invention is a system that analyzes a user's learning status in real time and provides learning materials adapted to individual needs. The system also incorporates an emotion engine that recognizes the user's emotions, thereby further personalizing the learning experience. Specific embodiments for implementing the present invention will now be described.

[0531] First, the server loads facial expression and behavior recognition models using machine learning libraries such as TensorFlow and PyTorch. These models are pre-trained with large amounts of data and can classify the user's facial expressions and behavior with high accuracy. The server also uses emotion engines such as Microsoft's Azure Emotion API and Google's Cloud Vision API to perform detailed analysis of the user's emotions.

[0532] Next, the device captures the user's video in real time using a Logitech webcam or similar. The captured video frames are first input into a facial expression recognition model, which classifies the user's facial expression into "happy," "neutral," "sad," etc. The results of this facial expression analysis are sent to an emotion engine for further detailed emotional analysis.

[0533] In parallel, the device stores a certain number of frames in a buffer and inputs them into an activity recognition model. This model classifies the user's behavior into categories such as "attentive," "distracted," and "fidgeting." In this way, the user's behavioral state is also understood.

[0534] Next, based on these analysis results, the device selects the appropriate level of learning materials to provide to the user. Specifically, if the user is "happy" and "attentive" and the emotion engine classifies them as "excited," advanced learning materials are selected. On the other hand, if the user is "neutral" or "distracted" and the emotion engine classifies them as "anxious," standard learning materials are selected. And if the user is "sad" or "fidgeting" and the emotion engine classifies them as "sad," basic learning materials are selected.

[0535] As a concrete example, consider a user watching a video of a scientific experiment online. If the device analyzes the user's face and classifies it as "happy" and their behavior as "attentive," and the emotion engine then classifies it as "excited," the device will provide the user with detailed experimental procedures and applied experiments. On the other hand, if the device classifies the user's facial expression as "sad," their behavior as "distracted," and the emotion engine then classifies them as "anxious," the device will provide the user with basic experimental procedures and supplementary materials. In this way, the user's learning experience is highly personalized.

[0536] Furthermore, the server generates detailed feedback for parents and teachers based on the analysis results sent from the device and the emotion engine's analysis results. This feedback includes information on the user's learning status and appropriate teaching methods, helping parents and teachers accurately understand the user's learning status and provide appropriate support and guidance.

[0537] Examples of prompts include:

[0538] "Please analyze the user's facial expressions and behavior in real time while they are watching this video and provide them with the most appropriate learning materials."

[0539] "Categorize your users' emotions in detail and adjust the difficulty of your learning materials based on the results."

[0540] As described above, the system of the present invention provides an optimal educational environment that adapts to individual learning needs by adjusting and providing learning materials in real time. Furthermore, the introduction of an emotion engine allows for detailed understanding of the user's emotional state, which is expected to further improve learning effectiveness.

[0541] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0542] Step 1:

[0543] The server loads the machine learning model and emotion engine.

[0544] Input: The model file and API key to use when loading.

[0545] What it does: The server loads facial expression and behavior recognition models using TensorFlow and PyTorch libraries, and prepares to use the Azure Emotion API and Google Cloud Vision API for emotion analysis.

[0546] Output: Initialized facial expression recognition model, action recognition model and emotion engine.

[0547] Step 2:

[0548] The device activates the camera and captures the user's image.

[0549] Input: A camera device connected to the device.

[0550] Specific operation: When a user starts learning, the device activates the camera device and captures the user's image in real time using a common webcam such as a Logitech camera.

[0551] Output: Real-time captured video data.

[0552] Step 3:

[0553] The device analyzes the video frames using a facial expression recognition model.

[0554] Input: Captured video frames.

[0555] How it works: Captured video frames are fed into a facial expression recognition model on the device's CPU or GPU, which classifies the user's facial expression for each frame into categories such as "happy," "neutral," or "sad."

[0556] Output: Classified facial expression data.

[0557] Step 4:

[0558] The device sends facial expression data to the emotion engine, which analyzes the emotions.

[0559] Input: Classified facial expression data.

[0560] How it works: The device sends the results of the facial expression recognition model to the emotion engine, which uses this data to classify the user's emotional state into categories such as "excitement," "anxiety," or "sadness."

[0561] Output: Detailed emotion data.

[0562] Step 5:

[0563] The device stores video frames in a buffer and analyzes them using an action recognition model.

[0564] Input: Captured video frames.

[0565] How it works: A certain number of frames are stored in a buffer and then fed into an action recognition model, which classifies the user's behavior as "attentive," "distracted," "fidgeting," etc.

[0566] Output: Classified behavioral data.

[0567] Step 6:

[0568] The device selects the most appropriate learning materials based on the facial expressions, behavior, and emotional data it obtains.

[0569] Input: facial expression data, behavioral data, and emotion data.

[0570] Specific operation: The device integrates this data and selects the most suitable learning materials for the user. For example, if the user is "happy" and "attentive" and their emotion is classified as "excited," the device will display advanced learning materials.

[0571] Output: The learning material provided to the user.

[0572] Step 7:

[0573] The server receives the data from the terminal and generates feedback.

[0574] Input: Analysis results and emotion data sent from the device.

[0575] What it does: The server receives this data and generates detailed feedback for parents and teachers, including information about the user's learning progress, emotional state, and appropriate teaching methods.

[0576] Output: Feedback information for parents and teachers.

[0577] (Application example 2)

[0578] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0579] Conventional learning systems have difficulty adapting to a user's learning situation and emotional state in real time. As a result, they are unable to provide a personalized learning experience that meets the user's individual needs, resulting in reduced learning effectiveness. It is also difficult for parents and teachers to accurately grasp a user's learning situation and provide appropriate support. Furthermore, even with online educational content distribution services, it is difficult to provide content that responds to a user's real-time emotions and behavior, delaying learning optimization.

[0580] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0581] In this invention, the server includes means for detecting and analyzing facial expressions, means for detecting and analyzing behavior, means for adjusting and providing learning materials based on the facial expressions and behavior, means for adjusting and providing learning materials in real time based on the analysis results and detailed emotional information generated by the emotion engine, and means for providing the analysis results as feedback to parents and teachers. This makes it possible to personalize content using generated prompts based on the user's emotional state. This makes it possible to accurately grasp the user's learning situation and provide appropriate support, enabling a highly personalized learning experience.

[0582] "Means for detecting and analyzing facial expressions" refers to a device or method for recognizing facial expressions from an image of a user's face and analyzing their specific emotional state.

[0583] The "means for detecting and analyzing behavior" refers to a device or method for capturing a user's daily actions and behavior from video data and analyzing the behavioral patterns.

[0584] The "means for adjusting and providing learning materials" refers to a device or method for selecting learning materials of appropriate difficulty and type based on the analysis of the user's facial expressions and behavior, and providing them in real time.

[0585] An "emotion engine" is an advanced algorithm or model that analyzes a user's facial and behavioral data to identify more detailed emotional states.

[0586] "Detailed emotion information from the emotion engine" is information on the user's various emotional states and their changes, obtained as a result of analysis by the emotion engine.

[0587] The "means for providing feedback" is a device or method for providing parents and teachers with reports and advice generated based on the analysis results and emotional information.

[0588] A "generative AI model" is a machine learning model used to analyze a user's facial expressions and behavior and identify their detailed emotional state.

[0589] "Generative prompts" are instructions or guidelines used to optimize learning content or materials based on the user's emotional state.

[0590] The "means for adjusting and providing in real time" refers to a device or method for instantly changing and providing learning materials according to the user's current situation.

[0591] The present invention is a system that analyzes a user's learning status in real time and provides personalized learning materials based on the user's emotions and behavior. Specifically, this system is configured as follows.

[0592] First, the server loads the facial expression recognition model, behavioral recognition model, and emotion engine. These models are based on machine learning and are used to analyze the user's facial expressions, behavior, and emotions. Specifically, the facial expression recognition model classifies the user's facial expressions into categories such as "happy," "neutral," and "sad," while the behavioral recognition model classifies the user's behavior into categories such as "attentive," "distracted," and "fidgeting." The emotion engine also uses a generative AI model to identify detailed emotional states and provides more complex emotional information from the user's facial expression and behavioral data.

[0593] Next, the device used by the user activates the camera and captures the user's video in real time. The captured video frames are input into a facial expression recognition model, and the user's facial expressions are analyzed. At the same time, a certain number of frames are stored in a buffer and input into a behavior recognition model. This allows the user's behavior to be analyzed in real time.

[0594] Based on the analysis results, the device selects the appropriate level of learning materials to provide to the user. Specifically, if the user is "happy" and "attentive" and the emotion engine classifies them as "excited," advanced learning materials are selected. On the other hand, if the user is "neutral" or "distracted" and the emotion engine classifies them as "anxious," standard learning materials are selected. Also, if the user is "sad" or "fidgeting" and the emotion engine classifies them as "sad," basic learning materials are selected.

[0595] Furthermore, the server generates detailed feedback based on the analysis results sent from the device and the emotion engine's analysis results. This feedback is provided to parents and teachers and includes information on the user's learning status and appropriate teaching methods.

[0596] For example, if a user is watching an online video of a science experiment, and the device analyzes the user's face and classifies it as "happy" and their behavior as "attentive," and the emotion engine classifies it as "excited," the device will provide the user with detailed experimental procedures and applied experiments. On the other hand, if the device classifies the user's facial expression as "sad" and their behavior as "distracted," and the emotion engine classifies them as "anxious," the device will provide the user with basic experimental procedures and supplementary materials. In this way, the user's learning experience is highly personalized.

[0597] Example prompt sentence:

[0598] By setting prompts as follows, you can have the generative AI model perform detailed analysis.

[0599] prompt

[0600] The system inputs the user's facial expression and behavior data and analyzes it using facial expression and behavior recognition models. It then uses an emotion engine to estimate the user's detailed emotional state, and selects and provides appropriate learning materials based on that.

[0601] Input data

[0602] User's facial expression image (live video frame)

[0603] User behavior data (a certain number of frames)

[0604] output

[0605] Appropriate learning materials

[0606] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0607] Step 1:

[0608] The device used by the user activates the camera and captures the user's image in real time.

[0609] Input: Live video of the user's face

[0610] Output: Video frame

[0611] Specific operation: The device's camera detects the user's face and captures the image.

[0612] Step 2:

[0613] The captured video frames are input into a facial expression recognition model to analyze the user's facial expressions.

[0614] Input: Video frame

[0615] Output: User's facial expression data (e.g. "happy", "neutral", "sad")

[0616] Specific operation: The device passes video frames to the facial expression recognition model, which then classifies the facial expression.

[0617] Step 3:

[0618] A certain number of frames are stored in a buffer and input into the action recognition model.

[0619] Input: A certain number of video frames

[0620] Output: User behavior data (e.g., "attentive," "distracted," "fidgeting")

[0621] Specific operation: Continuous images captured by the camera are stored in a buffer, and the buffer is passed to the action recognition model for analysis.

[0622] Step 4:

[0623] The analysis results are input into an emotion engine to identify detailed emotional states.

[0624] Input: facial expression data, behavior data

[0625] Output: Detailed emotional information (e.g., "excitement," "anxiety," "sadness")

[0626] Specific behavior: The emotion engine analyzes facial expression and behavior data to estimate detailed emotional states.

[0627] Step 5:

[0628] Based on the analysis results and those of the emotion engine, the device selects appropriate learning materials.

[0629] Input: Detailed emotional information

[0630] Output: Selected learning material content

[0631] Specific operation: Based on the user's emotional state in real time, the device selects learning materials suitable for the user from the database.

[0632] Step 6:

[0633] Selected learning materials are provided to users.

[0634] Input: Content of selected learning materials

[0635] Output: Learning materials that can be viewed or used by the user

[0636] Specific operation: The terminal displays the selected learning materials to the user.

[0637] Step 7:

[0638] The server generates detailed feedback based on the analysis results sent from the device and the analysis results of the emotion engine.

[0639] Input: Analysis results, emotion engine analysis results

[0640] Output: Feedback to parents and teachers

[0641] Specific operation: The server aggregates the data and generates reports and teaching guidelines for parents and teachers.

[0642] Step 8:

[0643] Provide feedback to parents and teachers.

[0644] Input: Generated feedback

[0645] Output: Report on the user's learning progress

[0646] Specific operation: The server sends the feedback to the parent and teacher's devices and displays it.

[0647] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0648] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0649] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0650] [Third embodiment]

[0651] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0652] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0653] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0654] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0655] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0656] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0657] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0658] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0659] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0660] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0661] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0662] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0663] The system of the present invention is capable of analyzing the user's learning status in real time and providing optimal learning materials to each user based on the results. Specific embodiments for carrying out the present invention will now be described.

[0664] First, the server loads the facial expression and behavior recognition models, which are machine learning models used to analyze the user's facial expressions and behavior.

[0665] Next, the device activates the camera and captures the user's video in real time. The captured video frames are input into a facial expression recognition model, which classifies the user's facial expression as "happy," "neutral," "sad," etc. Based on the results of this facial expression analysis, the user's emotional state is understood.

[0666] In parallel, the device stores a certain number of frames in a buffer and inputs them into an activity recognition model. The activity recognition model classifies the user's behavior from these frames as "attentive," "distracted," "fidgeting," etc. In this way, the user's behavioral state is also understood.

[0667] Based on the analysis of these facial expressions and behaviors, the device selects and provides the most suitable learning materials to the user. Specifically, if the user is "happy" and "attentive," it provides advanced learning materials. On the other hand, if the user is "neutral" or "distracted," it provides standard learning materials, and if the user is "sad" or "fidgeting," it provides basic learning materials. This process maintains the user's motivation to learn and promotes effective learning progress.

[0668] Furthermore, the server generates detailed feedback based on the analysis results sent from the device. This feedback is provided to parents and teachers and includes information on the user's learning status and appropriate teaching methods. Based on this information, parents and teachers can take effective approaches to support the user's educational growth.

[0669] As a concrete example, imagine a user is solving math problems online. If the device analyzes the user's face and classifies it as "happy" and their behavior as "attentive," the device will offer the user advanced problems or additional assignments. Conversely, if the device classifies the user's facial expression as "sad" and their behavior as "distracted," the device will offer the user basic review questions or supplementary materials. In this way, the user's learning experience is personalized.

[0670] As described above, the system of the present invention uses a means for analyzing a user's facial expressions and behavior to adjust and provide learning materials in real time, providing an optimal educational environment that is adapted to individual learning needs. This system increases the user's motivation to learn and allows teachers and parents to provide appropriate support.

[0671] The processing flow will be explained below.

[0672] Step 1:

[0673] The server loads the facial expression and behavior recognition models, which prepares the system for rapid analysis.

[0674] Step 2:

[0675] The device activates the camera and captures the user's video in real time, and the captured video frames are used for subsequent analysis.

[0676] Step 3:

[0677] The device inputs the captured video frames into a facial expression recognition model to analyze the user's facial expression. As a result of the analysis, the user's facial expression is classified as "happy," "neutral," "sad," etc.

[0678] Step 4:

[0679] The device stores a certain number of frames in a buffer and inputs them into an activity recognition model, which uses these frames to classify the user's behavior as "attentive," "distracted," "fidgeting," etc.

[0680] Step 5:

[0681] The device selects the appropriate level of learning materials to provide to the user based on the analysis of their facial expressions and behavior. Specifically, if the user is "happy" and "attentive," advanced learning materials will be selected.

[0682] Step 6:

[0683] The device provides the user with learning materials selected based on the user's learning progress and level of understanding.

[0684] Step 7:

[0685] The device sends the results of facial and behavioral analysis to a server, which uses this information to generate feedback later.

[0686] Step 8:

[0687] Based on the analysis results received by the server, detailed feedback is generated for parents and teachers, including information about the user's learning status and appropriate teaching methods.

[0688] Step 9:

[0689] The server generates feedback and sends it to parents and teachers, allowing them to understand the user's learning status and provide appropriate support and guidance.

[0690] Through each step, the system personalizes the user's learning experience and enables parents and teachers to provide effective support.

[0691] Example 1

[0692] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0693] Conventional educational systems have the problem of being unable to grasp the learning status of individual users in real time and provide optimal learning materials accordingly. Furthermore, there are limited means of providing appropriate feedback on the user's educational progress and status to parents and teachers. This makes it difficult to maintain the user's motivation to learn and effective learning progress. Therefore, there is a need for a system that can analyze the user's facial expressions and behavior in real time, adjust and provide learning materials based on that information, and provide the analysis results as feedback to parents and teachers.

[0694] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0695] In this invention, the server includes means for using a machine learning model to detect and classify a user's facial expressions, means for using a machine learning model to detect and classify the user's behavior, means for capturing video of the user in real time, means for adjusting and providing learning materials based on the facial expressions and behavior, and means for providing the analysis results as feedback to parents and teachers. This makes it possible to analyze the user's facial expressions and behavior in real time, and to provide optimal learning materials based on the analysis results and provide appropriate feedback of the analysis results.

[0696] "Machine learning model for detecting and classifying user facial expressions" refers to the algorithm used to analyze video data of a user captured by a camera and classify it into emotional states such as "happy," "neutral," and "sad."

[0697] A "machine learning model for detecting and classifying user behavior" refers to an algorithm that analyzes video data consisting of multiple frames and classifies user behavior into categories such as "attentive," "distracted," and "fidgeting."

[0698] "Means for capturing a user's image in real time" refers to the process of using a camera built into or connected to a device to capture the user's movements and facial expressions in real time and obtain the video data.

[0699] "Means for adjusting and providing learning materials" refers to the process of selecting and providing the most suitable learning materials (advanced learning materials, standard learning materials, basic learning materials) to the user based on the analysis of the user's facial expressions and behavior.

[0700] "Means for providing analysis results as feedback to parents and teachers" refers to a process for generating and providing detailed feedback to parents and teachers based on the analysis results regarding the user's learning status.

[0701] A "machine learning model" refers to an artificial intelligence technique that trains algorithms based on large data sets to recognize patterns and make predictions about new data.

[0702] The system of the present invention utilizes a machine learning model to analyze a user's facial expressions and behavior in real time, provides optimal learning materials based on the analysis results, and also provides the analysis results as feedback to parents and teachers. Specific embodiments of the present invention are described below.

[0703] First, the server uses machine learning libraries such as TensorFlow and PyTorch to load pre-trained facial expression and behavior recognition models into memory, which enables the server to analyze the user's video data.

[0704] When a user starts learning, the device activates the built-in or connected camera and captures the user's video in real time. The video data is acquired frame by frame and used for analysis.

[0705] The device preprocesses the captured video frames and inputs them into a facial expression recognition model, which classifies the user's facial expression into "happy," "neutral," "sad," etc., and returns the result to the device, allowing the device to understand the user's emotional state.

[0706] In parallel, the device accumulates a certain number of frames in a buffer and inputs them into the behavior recognition model. The behavior recognition model classifies the user's behavior from these frames into categories such as "attentive," "distracted," and "fidgeting," and returns the results to the device. This allows the device to understand the user's behavioral state.

[0707] The device selects and provides the most suitable learning materials to the user based on the analysis results of facial expressions and behaviors obtained from the server. Specifically, if the user is "happy" and "attentive," advanced learning materials are provided, if the user is "neutral" or "distracted," standard learning materials are provided, and if the user is "sad" or "fidgeting," basic learning materials are provided.

[0708] Furthermore, the server generates detailed feedback based on the analysis results sent from the device. This feedback is provided to parents and teachers and includes information on the user's learning status and appropriate teaching methods, allowing parents and teachers to take effective approaches to support the user's educational growth.

[0709] As a concrete example, consider a user solving a math problem online. If the device analyzes the user's face and classifies it as "happy" and their behavior as "attentive," the device will provide the user with applied problems or additional assignments. On the other hand, if the device classifies the user's facial expression as "sad" and their behavior as "distracted," the device will provide the user with basic review questions or supplementary materials. In this way, the user's learning experience is personalized.

[0710] An example of a prompt is, "If a user is solving a math problem and their facial expression is classified as 'happy' and their behavior is classified as 'attentive,' please suggest what kind of learning material should be provided in the next step. Please also specify the machine learning model to be used and the role of the server / device."

[0711] The system of the present invention analyzes the user's learning status in real time and provides optimal learning materials based on that analysis, thereby realizing an educational environment that is adapted to individual learning needs. This increases the user's motivation to learn, promotes effective learning progress, and allows parents and teachers to provide appropriate support.

[0712] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0713] Step 1:

[0714] The server loads the facial expression recognition model and the behavior recognition model.

[0715] Input: The server receives a machine learning library (TensorFlow or PyTorch) and a pre-trained model file.

[0716] Specific operation: The server uses the TensorFlow and PyTorch libraries to load each machine learning model into memory, which prepares the server for face recognition and behavior recognition calculations.

[0717] Output: The loaded facial expression recognition model and behavior recognition model are prepared in memory.

[0718] Step 2:

[0719] The device activates the camera and captures the user's image.

[0720] Input: The user inputs an instruction to start learning into the terminal.

[0721] Specific operation: The device activates the built-in or connected camera and captures the user's video in real time. The video data is acquired frame by frame.

[0722] Output: A sequence of video frames is generated and made available in real time.

[0723] Step 3:

[0724] The device analyzes the user's facial expression using a facial expression recognition model.

[0725] Input: Captured video frames of the user

[0726] How it works: The device preprocesses video frames and sends them to the server's facial expression recognition model, which then classifies the user's facial expression into categories such as "happy," "neutral," or "sad." Preprocessing includes frame resizing and normalization.

[0727] Output: Classification result of the analyzed facial expression (e.g. "happy").

[0728] Step 4:

[0729] The device analyzes the user's behavior using a behavior recognition model

[0730] Input: A certain number of captured video frames

[0731] Specific operation: The device accumulates a certain number of frames in a buffer and sends the buffer to the server's activity recognition model. The activity recognition model classifies the user's behavior from these frames into categories such as "attentive," "distracted," and "fidgeting." Preprocessing includes configuring the buffer and resizing the frames.

[0732] Output: Classification result of the analyzed behavior (e.g. "attentive").

[0733] Step 5:

[0734] The device selects and provides learning materials based on the analysis results

[0735] Input: Analysis results of facial expressions and behavior obtained from the server

[0736] Specific behavior: Evaluate each data combination and select the most suitable learning material for the user. For example, if the user is "happy" and "attentive," select advanced learning materials. The selection process is based on predefined rules and conditions.

[0737] Output: The selected learning materials (e.g., advanced learning materials) are provided to the user via the terminal.

[0738] Step 6:

[0739] The server generates detailed feedback

[0740] Input: Analysis results of facial expressions and behavior sent from the device

[0741] Specific operation: The server generates detailed feedback based on the analysis results and provides it to parents and teachers. The feedback includes specific information about the user's learning progress, areas for improvement, and teaching methods.

[0742] Output: A detailed feedback document is generated and sent to parents and teachers.

[0743] The process of analyzing and selecting data based on input data in each processing step and obtaining each output has been described in detail above.

[0744] (Application example 1)

[0745] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0746] Conventional learning systems have difficulty analyzing users' facial expressions and behavior in real time to individually optimize learning materials. Furthermore, they lack the ability to propose customized products and services in virtual environments, making it impossible to provide a personalized experience tailored to users' interests and behavior. This makes it difficult to maintain motivation to learn and effectively promote purchases.

[0747] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0748] In this invention, the server includes means for detecting and analyzing facial expressions, means for detecting and analyzing behavior, means for adjusting and providing learning materials based on the facial expressions and behavior, means for providing the analysis results as feedback to parents and teachers, and means for analyzing the facial expressions and behavior of the user in the virtual environment and adjusting the products or services provided, thereby enabling the provision of personalized learning materials based on the user's facial expressions and behavior and optimizing the user experience in the virtual environment.

[0749] The "means for detecting and analyzing facial expressions" is a system that captures a user's facial expressions in real time and uses a machine learning model to classify and analyze the expressions.

[0750] The "means for detecting and analyzing behavior" is a system that uses a camera to capture video frames to analyze a user's movements and postures, and then uses a machine learning model to classify and analyze the behavior.

[0751] The "means for adjusting and providing learning materials" is a system that selects optimal learning materials based on the analyzed user's facial expressions and behavior and provides them to the user.

[0752] The "means for providing feedback" is a system that provides the results of an analysis of the user's learning situation as information to parents and teachers, and provides results and advice for educational support.

[0753] The "means for tailoring products or services in a virtual environment" is a system that analyzes the user's facial expressions and behavior in real time and, based on the results, customizes and proposes products and services to be offered in a virtual store.

[0754] The present invention is a system that analyzes a user's learning status and behavior in a virtual environment in real time, and based on the results, provides individually optimized learning materials, products, and services. Specific embodiments for implementing the present invention are described below.

[0755] First, the server loads the facial expression and behavior recognition models. These models are machine learning models used to analyze the user's facial expressions and behavior. The server then executes these models using machine learning libraries such as TensorFlow and Keras.

[0756] Next, the device activates the camera and captures the user's video in real time. The captured video frames are input into a facial expression recognition model, which classifies the user's facial expression as "happy," "neutral," "sad," etc. Based on the results of this facial expression analysis, the user's emotional state is understood.

[0757] In parallel, the device accumulates a certain number of frames in a buffer and inputs them into the behavior recognition model. The behavior recognition model classifies the user's behavior from these frames as "attentive," "distracted," "fidgeting," etc. In this way, the user's behavioral state is also understood.

[0758] Based on the analysis of these facial expressions and behaviors, the device selects and provides the most suitable learning materials to the user. Specifically, if the user is "happy" and "attentive," it provides advanced learning materials. On the other hand, if the user is "neutral" or "distracted," it provides standard learning materials, and if the user is "sad" or "fidgeting," it provides basic learning materials. This process maintains the user's motivation to learn and promotes effective learning progress.

[0759] The system of the present invention also analyzes a user's facial expressions and behavior in the virtual environment and adjusts the products and services provided based on the analysis. For example, during a shopping experience in a virtual store, if a user's facial expression is "happy" and their behavior is "attentive," the system will suggest related luxury products and special offers. On the other hand, if the user's facial expression is classified as "sad" or "distracted," the system will provide support suggestions and discount information. This will increase the user's purchasing motivation and create a more satisfying shopping experience.

[0760] Furthermore, the server generates detailed feedback based on the analysis results sent from the device. This feedback is provided to parents and teachers and includes information on the user's learning status and appropriate teaching methods. Based on this information, parents and teachers can take effective approaches to support the user's educational growth.

[0761] As a concrete example, imagine a user is solving math problems online. If the device analyzes the user's face and classifies it as "happy" and their behavior as "attentive," the device will offer the user advanced problems or additional assignments. Conversely, if the device classifies the user's facial expression as "sad" and their behavior as "distracted," the device will offer the user basic review questions or supplementary materials. In this way, the user's learning experience is personalized.

[0762] Additionally, as an example of a prompt sentence using a generative AI model, the following can be entered:

[0763] "As users browse products in a virtual store, facial expression and behavioral recognition models should analyze their emotions and behavior in real time. Based on the analysis results, analyze how to suggest products and services that may interest the user and generate optimal suggestions."

[0764] The system of the present invention uses a means for analyzing a user's facial expressions and behavior to provide learning materials that are tailored in real time to provide an optimal educational environment that is adapted to individual learning needs. In addition, in the virtual environment, a personalized experience based on the user's behavior is provided, improving user motivation and satisfaction.

[0765] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0766] Step 1:

[0767] The server loads the facial expression recognition model and the behavior recognition model.

[0768] Input: A file of a pre-trained machine learning model.

[0769] Output: Facial expression and action recognition models loaded in memory.

[0770] What it does: The server reads machine learning model files from a database or local storage and loads these models into memory using TensorFlow or Keras.

[0771] Step 2:

[0772] The device activates the camera and captures the user's video in real time.

[0773] Input: A camera device connected to the device.

[0774] Output: Real-time video frames.

[0775] Specific operation: The device initializes the camera device and continuously captures the user's video data. It then uses a library such as OpenCV to acquire video frames.

[0776] Step 3:

[0777] The captured video frames are input into a facial expression recognition model.

[0778] Input: Real-time video frames.

[0779] Output: User's facial expression class (e.g. happy, neutral, sad).

[0780] Specific operation: The device converts the captured video frame to grayscale, resizes and normalizes it to match the input format of the facial expression recognition model, and then inputs this processed video data into the facial expression recognition model to obtain analysis results.

[0781] Step 4:

[0782] The device stores a certain number of frames in a buffer and inputs them into the behavior recognition model.

[0783] Input: A buffer of real-time video frames.

[0784] Output: User behavior class (e.g., attentive, distracted, fidgeting).

[0785] Specific operation: The device stores real-time video frames in a buffer for a certain period of time and inputs this buffer into the behavior recognition model. The behavior recognition model analyzes this continuous frame data and classifies the user's specific behavior.

[0786] Step 5:

[0787] Based on the analysis of facial expressions and behavior, the device selects and provides the most suitable learning materials to the user.

[0788] Input: Analysis results of facial expression classes and behavior classes.

[0789] Output: Selected learning materials.

[0790] Specific operation: Based on the analysis of facial expressions and behavior, the device searches the database for the most appropriate learning materials and provides them to the user. For example, a user who is "happy" and "attentive" will receive advanced learning materials, while a user who is "sad" and "distracted" will receive basic supplementary learning materials.

[0791] Step 6:

[0792] The device sends the analysis results to a server, which generates detailed feedback.

[0793] Input: Facial expression and behavior analysis results.

[0794] Output: Feedback report.

[0795] Specific operation: The device sends the analysis results of facial expressions and behaviors to the server, which then generates a detailed feedback report based on the analysis results. This feedback is provided to parents and teachers.

[0796] Step 7:

[0797] In a virtual environment, the user's facial expressions and behavior are analyzed and the products or services provided are adjusted accordingly.

[0798] Input: Real-time facial and behavioral analysis results.

[0799] Output: A customized product or service proposal.

[0800] Specific operation: The system analyzes the user's facial expressions and behavior in real time within the virtual store, and then customizes and suggests relevant products and services based on the analysis results. For example, it offers luxury products and special offers to users who are "happy" and "attentive," and offers support or discount information to users who are "sad" or "distracted."

[0801] These are the specific steps for implementing the system, which makes it possible to provide a personalized experience based on the user's learning status and behavior in the virtual environment.

[0802] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0803] The present invention is a system that analyzes a user's learning status in real time and provides learning materials adapted to individual needs. The system also incorporates an emotion engine that recognizes the user's emotions, thereby further personalizing the learning experience. Specific embodiments for implementing the present invention will now be described.

[0804] First, the server loads the facial expression recognition model, behavior recognition model, and emotion engine, which are machine learning models used to analyze the user's facial expressions, behavior, and emotions.

[0805] Next, the device activates the camera and captures the user's video in real time. The captured video frames are input into a facial expression recognition model, which classifies the user's facial expressions as "happy," "neutral," "sad," etc. Based on the results of this facial expression analysis, the user's emotional state is further analyzed by the emotion engine. The emotion engine identifies multiple emotional states based on the user's facial expression data and behavioral data, and provides more detailed emotional information.

[0806] In parallel, the device stores a certain number of frames in a buffer and inputs them into an activity recognition model. The activity recognition model classifies the user's behavior from these frames as "attentive," "distracted," "fidgeting," etc. In this way, the user's behavioral state is also understood.

[0807] Based on the results of these facial and behavioral analyses, as well as the detailed emotional information provided by the emotion engine, the device selects the appropriate level of learning materials to provide to the user. Specifically, if the user is "happy" and "attentive" and the emotion engine classifies them as "excited," advanced learning materials will be selected. On the other hand, if the user is "neutral" or "distracted" and the emotion engine classifies them as "anxious," standard learning materials will be selected. Furthermore, if the user is "sad" or "fidgeting" and the emotion engine classifies them as "sad," basic learning materials will be selected.

[0808] As a concrete example, consider a user watching a video of a scientific experiment online. If the device analyzes the user's face and classifies it as "happy" and their behavior as "attentive," and the emotion engine then classifies it as "excited," the device will provide the user with detailed experimental procedures and applied experiments. On the other hand, if the device classifies the user's facial expression as "sad" and their behavior as "distracted," and the emotion engine then classifies them as "anxious," the device will provide the user with basic experimental procedures and supplementary materials. In this way, the user's learning experience is highly personalized.

[0809] Furthermore, the server generates detailed feedback based on the analysis results sent from the device and the emotion engine's analysis results. This feedback is provided to parents and teachers and includes information on the user's learning status and appropriate teaching methods. This allows parents and teachers to accurately understand the user's learning status and provide appropriate support and guidance.

[0810] As described above, the system of the present invention uses a means for analyzing a user's facial expressions, behavior, and emotions to adjust and provide learning materials in real time, providing an optimal educational environment adapted to individual learning needs. The introduction of an emotion engine allows for a detailed understanding of the user's emotional state, which is expected to further improve learning effectiveness.

[0811] The processing flow will be explained below.

[0812] Step 1:

[0813] The server loads the facial expression recognition model, the behavior recognition model, and the emotion engine, which prepares the system for rapid analysis processing.

[0814] Step 2:

[0815] The device activates the camera and captures the user's video in real time, and the captured video frames are used for subsequent analysis.

[0816] Step 3:

[0817] The device inputs the captured video frames into a facial expression recognition model to analyze the user's facial expression. As a result of the analysis, the user's facial expression is classified as "happy," "neutral," "sad," etc.

[0818] Step 4:

[0819] The device stores a certain number of frames in a buffer and inputs them into an activity recognition model, which uses these frames to classify the user's behavior as "attentive," "distracted," "fidgeting," etc.

[0820] Step 5:

[0821] The device inputs the analysis results of the facial expression and behavior recognition models into the emotion engine, which then analyzes the user's emotional state in more detail. Based on this data, the emotion engine classifies the user's emotions as "excitement," "anxiety," "sadness," etc.

[0822] Step 6:

[0823] The device analyzes facial expressions, behavior, and emotions to select the appropriate level of learning materials to provide to the user. For example, if the user is "happy," "attentive," and "excited," advanced learning materials will be selected.

[0824] Step 7:

[0825] The device provides the user with learning materials selected based on the user's learning progress and level of understanding.

[0826] Step 8:

[0827] The device sends the results of its facial expression, behavior, and emotional analysis to a server, which then uses this information to generate feedback.

[0828] Step 9:

[0829] Based on the analysis results received by the server, detailed feedback is generated for parents and teachers, including information on the user's learning status and appropriate teaching methods.

[0830] Step 10:

[0831] The server generates feedback and sends it to parents and teachers, allowing them to understand the user's learning status and provide appropriate guidance.

[0832] Through these steps, the system will be able to highly personalize the user's learning experience and provide effective support to parents and teachers.

[0833] Example 2

[0834] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0835] Conventional learning systems have difficulty providing optimal learning materials according to a user's learning situation. Furthermore, because learning materials are selected without taking the user's emotional state into consideration, the user's learning effectiveness is not maximized. Furthermore, there is a lack of a way to accurately communicate the user's learning situation to parents and teachers. This makes it difficult to provide education adapted to individual learning needs.

[0836] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0837] In this invention, the server includes means for detecting and analyzing facial expressions, means for detecting and analyzing behavior, means for analyzing a user's emotions based on the user's facial expressions and behavior, means for adjusting and providing learning materials based on the facial expressions, behavior, and emotions, and means for providing the analysis results as feedback to parents and teachers. This makes it possible to provide learning materials adapted to the user's individual learning needs in real time, maximizing the user's learning effectiveness. In addition, detailed feedback to parents and teachers allows them to accurately grasp the user's learning status and provide effective support and guidance.

[0838] "Facial expression detection and analysis means" is the machine learning model or software used to capture a user's facial expressions and analyze those expressions.

[0839] The "means for detecting and analyzing behavior" is a machine learning model or software that stores and analyzes a certain number of video frames to capture and analyze the user's movements.

[0840] The "means for analyzing a user's emotions based on the user's facial expressions and behavior" refers to an algorithm or engine that uses the user's facial expression data and behavior data as input and classifies and analyzes the user's emotional state in detail.

[0841] The "means for adjusting and providing learning materials based on the facial expressions, behavior, and emotions" refers to logic or software for selecting and providing learning materials appropriate to the user's learning needs based on the analyzed facial expressions, behavior, and emotional data.

[0842] "Means for providing the analysis results as feedback to parents and teachers" is a system function for notifying parents and teachers of the analysis results of the user's learning status, emotions, and behavior, and providing support information for effective instruction.

[0843] The present invention is a system that analyzes a user's learning status in real time and provides learning materials adapted to individual needs. The system also incorporates an emotion engine that recognizes the user's emotions, thereby further personalizing the learning experience. Specific embodiments for implementing the present invention will now be described.

[0844] First, the server loads facial expression and behavior recognition models using machine learning libraries such as TensorFlow and PyTorch. These models are pre-trained with large amounts of data and can classify the user's facial expressions and behavior with high accuracy. The server also uses emotion engines such as Microsoft's Azure Emotion API and Google's Cloud Vision API to perform detailed analysis of the user's emotions.

[0845] Next, the device captures the user's video in real time using a Logitech webcam or similar. The captured video frames are first input into a facial expression recognition model, which classifies the user's facial expression into "happy," "neutral," "sad," etc. The results of this facial expression analysis are sent to an emotion engine for further detailed emotional analysis.

[0846] In parallel, the device stores a certain number of frames in a buffer and inputs them into an activity recognition model. This model classifies the user's behavior into categories such as "attentive," "distracted," and "fidgeting." In this way, the user's behavioral state is also understood.

[0847] Next, based on these analysis results, the device selects the appropriate level of learning materials to provide to the user. Specifically, if the user is "happy" and "attentive" and the emotion engine classifies them as "excited," advanced learning materials are selected. On the other hand, if the user is "neutral" or "distracted" and the emotion engine classifies them as "anxious," standard learning materials are selected. And if the user is "sad" or "fidgeting" and the emotion engine classifies them as "sad," basic learning materials are selected.

[0848] As a concrete example, consider a user watching a video of a scientific experiment online. If the device analyzes the user's face and classifies it as "happy" and their behavior as "attentive," and the emotion engine then classifies it as "excited," the device will provide the user with detailed experimental procedures and applied experiments. On the other hand, if the device classifies the user's facial expression as "sad," their behavior as "distracted," and the emotion engine then classifies them as "anxious," the device will provide the user with basic experimental procedures and supplementary materials. In this way, the user's learning experience is highly personalized.

[0849] Furthermore, the server generates detailed feedback for parents and teachers based on the analysis results sent from the device and the emotion engine's analysis results. This feedback includes information on the user's learning status and appropriate teaching methods, helping parents and teachers accurately understand the user's learning status and provide appropriate support and guidance.

[0850] Examples of prompts include:

[0851] "Please analyze the user's facial expressions and behavior in real time while they are watching this video and provide them with the most appropriate learning materials."

[0852] "Categorize your users' emotions in detail and adjust the difficulty of your learning materials based on the results."

[0853] As described above, the system of the present invention provides an optimal educational environment that adapts to individual learning needs by adjusting and providing learning materials in real time. Furthermore, the introduction of an emotion engine allows for detailed understanding of the user's emotional state, which is expected to further improve learning effectiveness.

[0854] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0855] Step 1:

[0856] The server loads the machine learning model and emotion engine.

[0857] Input: The model file and API key to use when loading.

[0858] What it does: The server loads facial expression and behavior recognition models using TensorFlow and PyTorch libraries, and prepares to use the Azure Emotion API and Google Cloud Vision API for emotion analysis.

[0859] Output: Initialized facial expression recognition model, action recognition model and emotion engine.

[0860] Step 2:

[0861] The device activates the camera and captures the user's image.

[0862] Input: A camera device connected to the device.

[0863] Specific operation: When a user starts learning, the device activates the camera device and captures the user's image in real time using a common webcam such as a Logitech camera.

[0864] Output: Real-time captured video data.

[0865] Step 3:

[0866] The device analyzes the video frames using a facial expression recognition model.

[0867] Input: Captured video frames.

[0868] How it works: Captured video frames are fed into a facial expression recognition model on the device's CPU or GPU, which classifies the user's facial expression for each frame into categories such as "happy," "neutral," or "sad."

[0869] Output: Classified facial expression data.

[0870] Step 4:

[0871] The device sends facial expression data to the emotion engine, which analyzes the emotions.

[0872] Input: Classified facial expression data.

[0873] How it works: The device sends the results of the facial expression recognition model to the emotion engine, which uses this data to classify the user's emotional state into categories such as "excitement," "anxiety," or "sadness."

[0874] Output: Detailed emotion data.

[0875] Step 5:

[0876] The device stores video frames in a buffer and analyzes them using an action recognition model.

[0877] Input: Captured video frames.

[0878] How it works: A certain number of frames are stored in a buffer and then fed into an action recognition model, which classifies the user's behavior as "attentive," "distracted," "fidgeting," etc.

[0879] Output: Classified behavioral data.

[0880] Step 6:

[0881] The device selects the most appropriate learning materials based on the facial expressions, behavior, and emotional data it obtains.

[0882] Input: facial expression data, behavioral data, and emotion data.

[0883] Specific operation: The device integrates this data and selects the most suitable learning materials for the user. For example, if the user is "happy" and "attentive" and their emotion is classified as "excited," the device will display advanced learning materials.

[0884] Output: The learning material provided to the user.

[0885] Step 7:

[0886] The server receives the data from the terminal and generates feedback.

[0887] Input: Analysis results and emotion data sent from the device.

[0888] What it does: The server receives this data and generates detailed feedback for parents and teachers, including information about the user's learning progress, emotional state, and appropriate teaching methods.

[0889] Output: Feedback information for parents and teachers.

[0890] (Application example 2)

[0891] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0892] Conventional learning systems have difficulty adapting to a user's learning situation and emotional state in real time. As a result, they are unable to provide a personalized learning experience that meets the user's individual needs, resulting in reduced learning effectiveness. It is also difficult for parents and teachers to accurately grasp a user's learning situation and provide appropriate support. Furthermore, even with online educational content distribution services, it is difficult to provide content that responds to a user's real-time emotions and behavior, delaying learning optimization.

[0893] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0894] In this invention, the server includes means for detecting and analyzing facial expressions, means for detecting and analyzing behavior, means for adjusting and providing learning materials based on the facial expressions and behavior, means for adjusting and providing learning materials in real time based on the analysis results and detailed emotional information generated by the emotion engine, and means for providing the analysis results as feedback to parents and teachers. This makes it possible to personalize content using generated prompts based on the user's emotional state. This makes it possible to accurately grasp the user's learning situation and provide appropriate support, enabling a highly personalized learning experience.

[0895] "Means for detecting and analyzing facial expressions" refers to a device or method for recognizing facial expressions from an image of a user's face and analyzing their specific emotional state.

[0896] The "means for detecting and analyzing behavior" refers to a device or method for capturing a user's daily actions and behavior from video data and analyzing the behavioral patterns.

[0897] The "means for adjusting and providing learning materials" refers to a device or method for selecting learning materials of appropriate difficulty and type based on the analysis of the user's facial expressions and behavior, and providing them in real time.

[0898] An "emotion engine" is an advanced algorithm or model that analyzes a user's facial and behavioral data to identify more detailed emotional states.

[0899] "Detailed emotion information from the emotion engine" is information on the user's various emotional states and their changes, obtained as a result of analysis by the emotion engine.

[0900] The "means for providing feedback" is a device or method for providing parents and teachers with reports and advice generated based on the analysis results and emotional information.

[0901] A "generative AI model" is a machine learning model used to analyze a user's facial expressions and behavior and identify their detailed emotional state.

[0902] "Generative prompts" are instructions or guidelines used to optimize learning content or materials based on the user's emotional state.

[0903] The "means for adjusting and providing in real time" refers to a device or method for instantly changing and providing learning materials according to the user's current situation.

[0904] The present invention is a system that analyzes a user's learning status in real time and provides personalized learning materials based on the user's emotions and behavior. Specifically, this system is configured as follows.

[0905] First, the server loads the facial expression recognition model, behavioral recognition model, and emotion engine. These models are based on machine learning and are used to analyze the user's facial expressions, behavior, and emotions. Specifically, the facial expression recognition model classifies the user's facial expressions into categories such as "happy," "neutral," and "sad," while the behavioral recognition model classifies the user's behavior into categories such as "attentive," "distracted," and "fidgeting." The emotion engine also uses a generative AI model to identify detailed emotional states and provides more complex emotional information from the user's facial expression and behavioral data.

[0906] Next, the device used by the user activates the camera and captures the user's video in real time. The captured video frames are input into a facial expression recognition model, and the user's facial expressions are analyzed. At the same time, a certain number of frames are stored in a buffer and input into a behavior recognition model. This allows the user's behavior to be analyzed in real time.

[0907] Based on the analysis results, the device selects the appropriate level of learning materials to provide to the user. Specifically, if the user is "happy" and "attentive" and the emotion engine classifies them as "excited," advanced learning materials are selected. On the other hand, if the user is "neutral" or "distracted" and the emotion engine classifies them as "anxious," standard learning materials are selected. Also, if the user is "sad" or "fidgeting" and the emotion engine classifies them as "sad," basic learning materials are selected.

[0908] Furthermore, the server generates detailed feedback based on the analysis results sent from the device and the emotion engine's analysis results. This feedback is provided to parents and teachers and includes information on the user's learning status and appropriate teaching methods.

[0909] For example, if a user is watching an online video of a science experiment, and the device analyzes the user's face and classifies it as "happy" and their behavior as "attentive," and the emotion engine classifies it as "excited," the device will provide the user with detailed experimental procedures and applied experiments. On the other hand, if the device classifies the user's facial expression as "sad" and their behavior as "distracted," and the emotion engine classifies them as "anxious," the device will provide the user with basic experimental procedures and supplementary materials. In this way, the user's learning experience is highly personalized.

[0910] Example prompt sentence:

[0911] By setting prompts as follows, you can have the generative AI model perform detailed analysis.

[0912] prompt

[0913] The system inputs the user's facial expression and behavior data and analyzes it using facial expression and behavior recognition models. It then uses an emotion engine to estimate the user's detailed emotional state, and selects and provides appropriate learning materials based on that.

[0914] Input data

[0915] User's facial expression image (live video frame)

[0916] User behavior data (a certain number of frames)

[0917] output

[0918] Appropriate learning materials

[0919] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0920] Step 1:

[0921] The device used by the user activates the camera and captures the user's image in real time.

[0922] Input: Live video of the user's face

[0923] Output: Video frame

[0924] Specific operation: The device's camera detects the user's face and captures the image.

[0925] Step 2:

[0926] The captured video frames are input into a facial expression recognition model to analyze the user's facial expressions.

[0927] Input: Video frame

[0928] Output: User's facial expression data (e.g. "happy", "neutral", "sad")

[0929] Specific operation: The device passes video frames to the facial expression recognition model, which then classifies the facial expression.

[0930] Step 3:

[0931] A certain number of frames are stored in a buffer and input into the action recognition model.

[0932] Input: A certain number of video frames

[0933] Output: User behavior data (e.g., "attentive," "distracted," "fidgeting")

[0934] Specific operation: Continuous images captured by the camera are stored in a buffer, and the buffer is passed to the action recognition model for analysis.

[0935] Step 4:

[0936] The analysis results are input into an emotion engine to identify detailed emotional states.

[0937] Input: facial expression data, behavior data

[0938] Output: Detailed emotional information (e.g., "excitement," "anxiety," "sadness")

[0939] Specific behavior: The emotion engine analyzes facial expression and behavior data to estimate detailed emotional states.

[0940] Step 5:

[0941] Based on the analysis results and those of the emotion engine, the device selects appropriate learning materials.

[0942] Input: Detailed emotional information

[0943] Output: Selected learning material content

[0944] Specific operation: Based on the user's emotional state in real time, the device selects learning materials suitable for the user from the database.

[0945] Step 6:

[0946] Selected learning materials are provided to users.

[0947] Input: Content of selected learning materials

[0948] Output: Learning materials that can be viewed or used by the user

[0949] Specific operation: The terminal displays the selected learning materials to the user.

[0950] Step 7:

[0951] The server generates detailed feedback based on the analysis results sent from the device and the analysis results of the emotion engine.

[0952] Input: Analysis results, emotion engine analysis results

[0953] Output: Feedback to parents and teachers

[0954] Specific operation: The server aggregates the data and generates reports and teaching guidelines for parents and teachers.

[0955] Step 8:

[0956] Provide feedback to parents and teachers.

[0957] Input: Generated feedback

[0958] Output: Report on the user's learning progress

[0959] Specific operation: The server sends the feedback to the parent and teacher's devices and displays it.

[0960] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0961] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0962] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0963] [Fourth embodiment]

[0964] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0965] 7, a 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.

[0966] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0967] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0968] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0969] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0970] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0971] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0972] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0973] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0974] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0975] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0976] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0977] The system of the present invention is capable of analyzing the user's learning status in real time and providing optimal learning materials to each user based on the results. Specific embodiments for carrying out the present invention will now be described.

[0978] First, the server loads the facial expression and behavior recognition models, which are machine learning models used to analyze the user's facial expressions and behavior.

[0979] Next, the device activates the camera and captures the user's video in real time. The captured video frames are input into a facial expression recognition model, which classifies the user's facial expression as "happy," "neutral," "sad," etc. Based on the results of this facial expression analysis, the user's emotional state is understood.

[0980] In parallel, the device stores a certain number of frames in a buffer and inputs them into an activity recognition model. The activity recognition model classifies the user's behavior from these frames as "attentive," "distracted," "fidgeting," etc. In this way, the user's behavioral state is also understood.

[0981] Based on the analysis of these facial expressions and behaviors, the device selects and provides the most suitable learning materials to the user. Specifically, if the user is "happy" and "attentive," it provides advanced learning materials. On the other hand, if the user is "neutral" or "distracted," it provides standard learning materials, and if the user is "sad" or "fidgeting," it provides basic learning materials. This process maintains the user's motivation to learn and promotes effective learning progress.

[0982] Furthermore, the server generates detailed feedback based on the analysis results sent from the device. This feedback is provided to parents and teachers and includes information on the user's learning status and appropriate teaching methods. Based on this information, parents and teachers can take effective approaches to support the user's educational growth.

[0983] As a concrete example, imagine a user is solving math problems online. If the device analyzes the user's face and classifies it as "happy" and their behavior as "attentive," the device will offer the user advanced problems or additional assignments. Conversely, if the device classifies the user's facial expression as "sad" and their behavior as "distracted," the device will offer the user basic review questions or supplementary materials. In this way, the user's learning experience is personalized.

[0984] As described above, the system of the present invention uses a means for analyzing a user's facial expressions and behavior to adjust and provide learning materials in real time, providing an optimal educational environment that is adapted to individual learning needs. This system increases the user's motivation to learn and allows teachers and parents to provide appropriate support.

[0985] The processing flow will be explained below.

[0986] Step 1:

[0987] The server loads the facial expression and behavior recognition models, which prepares the system for rapid analysis.

[0988] Step 2:

[0989] The device activates the camera and captures the user's video in real time, and the captured video frames are used for subsequent analysis.

[0990] Step 3:

[0991] The device inputs the captured video frames into a facial expression recognition model to analyze the user's facial expression. As a result of the analysis, the user's facial expression is classified as "happy," "neutral," "sad," etc.

[0992] Step 4:

[0993] The device stores a certain number of frames in a buffer and inputs them into an activity recognition model, which uses these frames to classify the user's behavior as "attentive," "distracted," "fidgeting," etc.

[0994] Step 5:

[0995] The device selects the appropriate level of learning materials to provide to the user based on the analysis of their facial expressions and behavior. Specifically, if the user is "happy" and "attentive," advanced learning materials will be selected.

[0996] Step 6:

[0997] The device provides the user with learning materials selected based on the user's learning progress and level of understanding.

[0998] Step 7:

[0999] The device sends the results of facial and behavioral analysis to a server, which uses this information to generate feedback later.

[1000] Step 8:

[1001] Based on the analysis results received by the server, detailed feedback is generated for parents and teachers, including information about the user's learning status and appropriate teaching methods.

[1002] Step 9:

[1003] The server generates feedback and sends it to parents and teachers, allowing them to understand the user's learning status and provide appropriate support and guidance.

[1004] Through each step, the system personalizes the user's learning experience and enables parents and teachers to provide effective support.

[1005] Example 1

[1006] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1007] Conventional educational systems have the problem of being unable to grasp the learning status of individual users in real time and provide optimal learning materials accordingly. Furthermore, there are limited means of providing appropriate feedback on the user's educational progress and status to parents and teachers. This makes it difficult to maintain the user's motivation to learn and effective learning progress. Therefore, there is a need for a system that can analyze the user's facial expressions and behavior in real time, adjust and provide learning materials based on that information, and provide the analysis results as feedback to parents and teachers.

[1008] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1009] In this invention, the server includes means for using a machine learning model to detect and classify a user's facial expressions, means for using a machine learning model to detect and classify the user's behavior, means for capturing video of the user in real time, means for adjusting and providing learning materials based on the facial expressions and behavior, and means for providing the analysis results as feedback to parents and teachers. This makes it possible to analyze the user's facial expressions and behavior in real time, and to provide optimal learning materials based on the analysis results and provide appropriate feedback of the analysis results.

[1010] "Machine learning model for detecting and classifying user facial expressions" refers to the algorithm used to analyze video data of a user captured by a camera and classify it into emotional states such as "happy," "neutral," and "sad."

[1011] A "machine learning model for detecting and classifying user behavior" refers to an algorithm that analyzes video data consisting of multiple frames and classifies user behavior into categories such as "attentive," "distracted," and "fidgeting."

[1012] "Means for capturing a user's image in real time" refers to the process of using a camera built into or connected to a device to capture the user's movements and facial expressions in real time and obtain the video data.

[1013] "Means for adjusting and providing learning materials" refers to the process of selecting and providing the most suitable learning materials (advanced learning materials, standard learning materials, basic learning materials) to the user based on the analysis of the user's facial expressions and behavior.

[1014] "Means for providing analysis results as feedback to parents and teachers" refers to a process for generating and providing detailed feedback to parents and teachers based on the analysis results regarding the user's learning status.

[1015] A "machine learning model" refers to an artificial intelligence technique that trains algorithms based on large data sets to recognize patterns and make predictions about new data.

[1016] The system of the present invention utilizes a machine learning model to analyze a user's facial expressions and behavior in real time, provides optimal learning materials based on the analysis results, and also provides the analysis results as feedback to parents and teachers. Specific embodiments of the present invention are described below.

[1017] First, the server uses machine learning libraries such as TensorFlow and PyTorch to load pre-trained facial expression and behavior recognition models into memory, which enables the server to analyze the user's video data.

[1018] When a user starts learning, the device activates the built-in or connected camera and captures the user's video in real time. The video data is acquired frame by frame and used for analysis.

[1019] The device preprocesses the captured video frames and inputs them into a facial expression recognition model, which classifies the user's facial expression into "happy," "neutral," "sad," etc., and returns the result to the device, allowing the device to understand the user's emotional state.

[1020] In parallel, the device accumulates a certain number of frames in a buffer and inputs them into the behavior recognition model. The behavior recognition model classifies the user's behavior from these frames into categories such as "attentive," "distracted," and "fidgeting," and returns the results to the device. This allows the device to understand the user's behavioral state.

[1021] The device selects and provides the most suitable learning materials to the user based on the analysis results of facial expressions and behaviors obtained from the server. Specifically, if the user is "happy" and "attentive," advanced learning materials are provided, if the user is "neutral" or "distracted," standard learning materials are provided, and if the user is "sad" or "fidgeting," basic learning materials are provided.

[1022] Furthermore, the server generates detailed feedback based on the analysis results sent from the device. This feedback is provided to parents and teachers and includes information on the user's learning status and appropriate teaching methods, allowing parents and teachers to take effective approaches to support the user's educational growth.

[1023] As a concrete example, consider a user solving a math problem online. If the device analyzes the user's face and classifies it as "happy" and their behavior as "attentive," the device will provide the user with applied problems or additional assignments. On the other hand, if the device classifies the user's facial expression as "sad" and their behavior as "distracted," the device will provide the user with basic review questions or supplementary materials. In this way, the user's learning experience is personalized.

[1024] An example of a prompt is, "If a user is solving a math problem and their facial expression is classified as 'happy' and their behavior is classified as 'attentive,' please suggest what kind of learning material should be provided in the next step. Please also specify the machine learning model to be used and the role of the server / device."

[1025] The system of the present invention analyzes the user's learning status in real time and provides optimal learning materials based on that analysis, thereby realizing an educational environment that is adapted to individual learning needs. This increases the user's motivation to learn, promotes effective learning progress, and allows parents and teachers to provide appropriate support.

[1026] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1027] Step 1:

[1028] The server loads the facial expression recognition model and the behavior recognition model.

[1029] Input: The server receives a machine learning library (TensorFlow or PyTorch) and a pre-trained model file.

[1030] Specific operation: The server uses the TensorFlow and PyTorch libraries to load each machine learning model into memory, which prepares the server for face recognition and behavior recognition calculations.

[1031] Output: The loaded facial expression recognition model and behavior recognition model are prepared in memory.

[1032] Step 2:

[1033] The device activates the camera and captures the user's image.

[1034] Input: The user inputs an instruction to start learning into the terminal.

[1035] Specific operation: The device activates the built-in or connected camera and captures the user's video in real time. The video data is acquired frame by frame.

[1036] Output: A sequence of video frames is generated and made available in real time.

[1037] Step 3:

[1038] The device analyzes the user's facial expression using a facial expression recognition model.

[1039] Input: Captured video frames of the user

[1040] How it works: The device preprocesses video frames and sends them to the server's facial expression recognition model, which then classifies the user's facial expression into categories such as "happy," "neutral," or "sad." Preprocessing includes frame resizing and normalization.

[1041] Output: Classification result of the analyzed facial expression (e.g. "happy").

[1042] Step 4:

[1043] The device analyzes the user's behavior using a behavior recognition model

[1044] Input: A certain number of captured video frames

[1045] Specific operation: The device accumulates a certain number of frames in a buffer and sends the buffer to the server's activity recognition model. The activity recognition model classifies the user's behavior from these frames into categories such as "attentive," "distracted," and "fidgeting." Preprocessing includes configuring the buffer and resizing the frames.

[1046] Output: Classification result of the analyzed behavior (e.g. "attentive").

[1047] Step 5:

[1048] The device selects and provides learning materials based on the analysis results

[1049] Input: Analysis results of facial expressions and behavior obtained from the server

[1050] Specific behavior: Evaluate each data combination and select the most suitable learning material for the user. For example, if the user is "happy" and "attentive," select advanced learning materials. The selection process is based on predefined rules and conditions.

[1051] Output: The selected learning materials (e.g., advanced learning materials) are provided to the user via the terminal.

[1052] Step 6:

[1053] The server generates detailed feedback

[1054] Input: Analysis results of facial expressions and behavior sent from the device

[1055] Specific operation: The server generates detailed feedback based on the analysis results and provides it to parents and teachers. The feedback includes specific information about the user's learning progress, areas for improvement, and teaching methods.

[1056] Output: A detailed feedback document is generated and sent to parents and teachers.

[1057] The process of analyzing and selecting data based on input data in each processing step and obtaining each output has been described in detail above.

[1058] (Application example 1)

[1059] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1060] Conventional learning systems have difficulty analyzing users' facial expressions and behavior in real time to individually optimize learning materials. Furthermore, they lack the ability to propose customized products and services in virtual environments, making it impossible to provide a personalized experience tailored to users' interests and behavior. This makes it difficult to maintain motivation to learn and effectively promote purchases.

[1061] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1062] In this invention, the server includes means for detecting and analyzing facial expressions, means for detecting and analyzing behavior, means for adjusting and providing learning materials based on the facial expressions and behavior, means for providing the analysis results as feedback to parents and teachers, and means for analyzing the facial expressions and behavior of the user in the virtual environment and adjusting the products or services provided, thereby enabling the provision of personalized learning materials based on the user's facial expressions and behavior and optimizing the user experience in the virtual environment.

[1063] The "means for detecting and analyzing facial expressions" is a system that captures a user's facial expressions in real time and uses a machine learning model to classify and analyze the expressions.

[1064] The "means for detecting and analyzing behavior" is a system that uses a camera to capture video frames to analyze a user's movements and postures, and then uses a machine learning model to classify and analyze the behavior.

[1065] The "means for adjusting and providing learning materials" is a system that selects optimal learning materials based on the analyzed user's facial expressions and behavior and provides them to the user.

[1066] The "means for providing feedback" is a system that provides the results of an analysis of the user's learning situation as information to parents and teachers, and provides results and advice for educational support.

[1067] The "means for tailoring products or services in a virtual environment" is a system that analyzes the user's facial expressions and behavior in real time and, based on the results, customizes and proposes products and services to be offered in a virtual store.

[1068] The present invention is a system that analyzes a user's learning status and behavior in a virtual environment in real time, and based on the results, provides individually optimized learning materials, products, and services. Specific embodiments for implementing the present invention are described below.

[1069] First, the server loads the facial expression and behavior recognition models. These models are machine learning models used to analyze the user's facial expressions and behavior. The server then executes these models using machine learning libraries such as TensorFlow and Keras.

[1070] Next, the device activates the camera and captures the user's video in real time. The captured video frames are input into a facial expression recognition model, which classifies the user's facial expression as "happy," "neutral," "sad," etc. Based on the results of this facial expression analysis, the user's emotional state is understood.

[1071] In parallel, the device accumulates a certain number of frames in a buffer and inputs them into the behavior recognition model. The behavior recognition model classifies the user's behavior from these frames as "attentive," "distracted," "fidgeting," etc. In this way, the user's behavioral state is also understood.

[1072] Based on the analysis of these facial expressions and behaviors, the device selects and provides the most suitable learning materials to the user. Specifically, if the user is "happy" and "attentive," it provides advanced learning materials. On the other hand, if the user is "neutral" or "distracted," it provides standard learning materials, and if the user is "sad" or "fidgeting," it provides basic learning materials. This process maintains the user's motivation to learn and promotes effective learning progress.

[1073] The system of the present invention also analyzes a user's facial expressions and behavior in the virtual environment and adjusts the products and services provided based on the analysis. For example, during a shopping experience in a virtual store, if a user's facial expression is "happy" and their behavior is "attentive," the system will suggest related luxury products and special offers. On the other hand, if the user's facial expression is classified as "sad" or "distracted," the system will provide support suggestions and discount information. This will increase the user's purchasing motivation and create a more satisfying shopping experience.

[1074] Furthermore, the server generates detailed feedback based on the analysis results sent from the device. This feedback is provided to parents and teachers and includes information on the user's learning status and appropriate teaching methods. Based on this information, parents and teachers can take effective approaches to support the user's educational growth.

[1075] As a concrete example, imagine a user is solving math problems online. If the device analyzes the user's face and classifies it as "happy" and their behavior as "attentive," the device will offer the user advanced problems or additional assignments. Conversely, if the device classifies the user's facial expression as "sad" and their behavior as "distracted," the device will offer the user basic review questions or supplementary materials. In this way, the user's learning experience is personalized.

[1076] Additionally, as an example of a prompt sentence using a generative AI model, the following can be entered:

[1077] "As users browse products in a virtual store, facial expression and behavioral recognition models should analyze their emotions and behavior in real time. Based on the analysis results, analyze how to suggest products and services that may interest the user and generate optimal suggestions."

[1078] The system of the present invention uses a means for analyzing a user's facial expressions and behavior to provide learning materials that are tailored in real time to provide an optimal educational environment that is adapted to individual learning needs. In addition, in the virtual environment, a personalized experience based on the user's behavior is provided, improving user motivation and satisfaction.

[1079] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1080] Step 1:

[1081] The server loads the facial expression recognition model and the behavior recognition model.

[1082] Input: A file of a pre-trained machine learning model.

[1083] Output: Facial expression and action recognition models loaded in memory.

[1084] What it does: The server reads machine learning model files from a database or local storage and loads these models into memory using TensorFlow or Keras.

[1085] Step 2:

[1086] The device activates the camera and captures the user's video in real time.

[1087] Input: A camera device connected to the device.

[1088] Output: Real-time video frames.

[1089] Specific operation: The device initializes the camera device and continuously captures the user's video data. It then uses a library such as OpenCV to acquire video frames.

[1090] Step 3:

[1091] The captured video frames are input into a facial expression recognition model.

[1092] Input: Real-time video frames.

[1093] Output: User's facial expression class (e.g. happy, neutral, sad).

[1094] Specific operation: The device converts the captured video frame to grayscale, resizes and normalizes it to match the input format of the facial expression recognition model, and then inputs this processed video data into the facial expression recognition model to obtain analysis results.

[1095] Step 4:

[1096] The device stores a certain number of frames in a buffer and inputs them into the behavior recognition model.

[1097] Input: A buffer of real-time video frames.

[1098] Output: User behavior class (e.g., attentive, distracted, fidgeting).

[1099] Specific operation: The device stores real-time video frames in a buffer for a certain period of time and inputs this buffer into the behavior recognition model. The behavior recognition model analyzes this continuous frame data and classifies the user's specific behavior.

[1100] Step 5:

[1101] Based on the analysis of facial expressions and behavior, the device selects and provides the most suitable learning materials to the user.

[1102] Input: Analysis results of facial expression classes and behavior classes.

[1103] Output: Selected learning materials.

[1104] Specific operation: Based on the analysis of facial expressions and behavior, the device searches the database for the most appropriate learning materials and provides them to the user. For example, a user who is "happy" and "attentive" will receive advanced learning materials, while a user who is "sad" and "distracted" will receive basic supplementary learning materials.

[1105] Step 6:

[1106] The device sends the analysis results to a server, which generates detailed feedback.

[1107] Input: Facial expression and behavior analysis results.

[1108] Output: Feedback report.

[1109] Specific operation: The device sends the analysis results of facial expressions and behaviors to the server, which then generates a detailed feedback report based on the analysis results. This feedback is provided to parents and teachers.

[1110] Step 7:

[1111] In a virtual environment, the user's facial expressions and behavior are analyzed and the products or services provided are adjusted accordingly.

[1112] Input: Real-time facial and behavioral analysis results.

[1113] Output: A customized product or service proposal.

[1114] Specific operation: The system analyzes the user's facial expressions and behavior in real time within the virtual store, and then customizes and suggests relevant products and services based on the analysis results. For example, it offers luxury products and special offers to users who are "happy" and "attentive," and offers support or discount information to users who are "sad" or "distracted."

[1115] These are the specific steps for implementing the system, which makes it possible to provide a personalized experience based on the user's learning status and behavior in the virtual environment.

[1116] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1117] The present invention is a system that analyzes a user's learning status in real time and provides learning materials adapted to individual needs. The system also incorporates an emotion engine that recognizes the user's emotions, thereby further personalizing the learning experience. Specific embodiments for implementing the present invention will now be described.

[1118] First, the server loads the facial expression recognition model, behavior recognition model, and emotion engine, which are machine learning models used to analyze the user's facial expressions, behavior, and emotions.

[1119] Next, the device activates the camera and captures the user's video in real time. The captured video frames are input into a facial expression recognition model, which classifies the user's facial expressions as "happy," "neutral," "sad," etc. Based on the results of this facial expression analysis, the user's emotional state is further analyzed by the emotion engine. The emotion engine identifies multiple emotional states based on the user's facial expression data and behavioral data, and provides more detailed emotional information.

[1120] In parallel, the device stores a certain number of frames in a buffer and inputs them into an activity recognition model. The activity recognition model classifies the user's behavior from these frames as "attentive," "distracted," "fidgeting," etc. In this way, the user's behavioral state is also understood.

[1121] Based on the results of these facial and behavioral analyses, as well as the detailed emotional information provided by the emotion engine, the device selects the appropriate level of learning materials to provide to the user. Specifically, if the user is "happy" and "attentive" and the emotion engine classifies them as "excited," advanced learning materials will be selected. On the other hand, if the user is "neutral" or "distracted" and the emotion engine classifies them as "anxious," standard learning materials will be selected. Furthermore, if the user is "sad" or "fidgeting" and the emotion engine classifies them as "sad," basic learning materials will be selected.

[1122] As a concrete example, consider a user watching a video of a scientific experiment online. If the device analyzes the user's face and classifies it as "happy" and their behavior as "attentive," and the emotion engine then classifies it as "excited," the device will provide the user with detailed experimental procedures and applied experiments. On the other hand, if the device classifies the user's facial expression as "sad" and their behavior as "distracted," and the emotion engine then classifies them as "anxious," the device will provide the user with basic experimental procedures and supplementary materials. In this way, the user's learning experience is highly personalized.

[1123] Furthermore, the server generates detailed feedback based on the analysis results sent from the device and the emotion engine's analysis results. This feedback is provided to parents and teachers and includes information on the user's learning status and appropriate teaching methods. This allows parents and teachers to accurately understand the user's learning status and provide appropriate support and guidance.

[1124] As described above, the system of the present invention uses a means for analyzing a user's facial expressions, behavior, and emotions to adjust and provide learning materials in real time, providing an optimal educational environment adapted to individual learning needs. The introduction of an emotion engine allows for a detailed understanding of the user's emotional state, which is expected to further improve learning effectiveness.

[1125] The processing flow will be explained below.

[1126] Step 1:

[1127] The server loads the facial expression recognition model, the behavior recognition model, and the emotion engine, which prepares the system for rapid analysis processing.

[1128] Step 2:

[1129] The device activates the camera and captures the user's video in real time, and the captured video frames are used for subsequent analysis.

[1130] Step 3:

[1131] The device inputs the captured video frames into a facial expression recognition model to analyze the user's facial expression. As a result of the analysis, the user's facial expression is classified as "happy," "neutral," "sad," etc.

[1132] Step 4:

[1133] The device stores a certain number of frames in a buffer and inputs them into an activity recognition model, which uses these frames to classify the user's behavior as "attentive," "distracted," "fidgeting," etc.

[1134] Step 5:

[1135] The device inputs the analysis results of the facial expression and behavior recognition models into the emotion engine, which then analyzes the user's emotional state in more detail. Based on this data, the emotion engine classifies the user's emotions as "excitement," "anxiety," "sadness," etc.

[1136] Step 6:

[1137] The device analyzes facial expressions, behavior, and emotions to select the appropriate level of learning materials to provide to the user. For example, if the user is "happy," "attentive," and "excited," advanced learning materials will be selected.

[1138] Step 7:

[1139] The device provides the user with learning materials selected based on the user's learning progress and level of understanding.

[1140] Step 8:

[1141] The device sends the results of its facial expression, behavior, and emotional analysis to a server, which then uses this information to generate feedback.

[1142] Step 9:

[1143] Based on the analysis results received by the server, detailed feedback is generated for parents and teachers, including information on the user's learning status and appropriate teaching methods.

[1144] Step 10:

[1145] The server generates feedback and sends it to parents and teachers, allowing them to understand the user's learning status and provide appropriate guidance.

[1146] Through these steps, the system will be able to highly personalize the user's learning experience and provide effective support to parents and teachers.

[1147] Example 2

[1148] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1149] Conventional learning systems have difficulty providing optimal learning materials according to a user's learning situation. Furthermore, because learning materials are selected without taking the user's emotional state into consideration, the user's learning effectiveness is not maximized. Furthermore, there is a lack of a way to accurately communicate the user's learning situation to parents and teachers. This makes it difficult to provide education adapted to individual learning needs.

[1150] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1151] In this invention, the server includes means for detecting and analyzing facial expressions, means for detecting and analyzing behavior, means for analyzing a user's emotions based on the user's facial expressions and behavior, means for adjusting and providing learning materials based on the facial expressions, behavior, and emotions, and means for providing the analysis results as feedback to parents and teachers. This makes it possible to provide learning materials adapted to the user's individual learning needs in real time, maximizing the user's learning effectiveness. In addition, detailed feedback to parents and teachers allows them to accurately grasp the user's learning status and provide effective support and guidance.

[1152] "Facial expression detection and analysis means" is the machine learning model or software used to capture a user's facial expressions and analyze those expressions.

[1153] The "means for detecting and analyzing behavior" is a machine learning model or software that stores and analyzes a certain number of video frames to capture and analyze the user's movements.

[1154] The "means for analyzing a user's emotions based on the user's facial expressions and behavior" refers to an algorithm or engine that uses the user's facial expression data and behavior data as input and classifies and analyzes the user's emotional state in detail.

[1155] The "means for adjusting and providing learning materials based on the facial expressions, behavior, and emotions" refers to logic or software for selecting and providing learning materials appropriate to the user's learning needs based on the analyzed facial expressions, behavior, and emotional data.

[1156] "Means for providing the analysis results as feedback to parents and teachers" is a system function for notifying parents and teachers of the analysis results of the user's learning status, emotions, and behavior, and providing support information for effective instruction.

[1157] The present invention is a system that analyzes a user's learning status in real time and provides learning materials adapted to individual needs. The system also incorporates an emotion engine that recognizes the user's emotions, thereby further personalizing the learning experience. Specific embodiments for implementing the present invention will now be described.

[1158] First, the server loads facial expression and behavior recognition models using machine learning libraries such as TensorFlow and PyTorch. These models are pre-trained with large amounts of data and can classify the user's facial expressions and behavior with high accuracy. The server also uses emotion engines such as Microsoft's Azure Emotion API and Google's Cloud Vision API to perform detailed analysis of the user's emotions.

[1159] Next, the device captures the user's video in real time using a Logitech webcam or similar. The captured video frames are first input into a facial expression recognition model, which classifies the user's facial expression into "happy," "neutral," "sad," etc. The results of this facial expression analysis are sent to an emotion engine for further detailed emotional analysis.

[1160] In parallel, the device stores a certain number of frames in a buffer and inputs them into an activity recognition model. This model classifies the user's behavior into categories such as "attentive," "distracted," and "fidgeting." In this way, the user's behavioral state is also understood.

[1161] Next, based on these analysis results, the device selects the appropriate level of learning materials to provide to the user. Specifically, if the user is "happy" and "attentive" and the emotion engine classifies them as "excited," advanced learning materials are selected. On the other hand, if the user is "neutral" or "distracted" and the emotion engine classifies them as "anxious," standard learning materials are selected. And if the user is "sad" or "fidgeting" and the emotion engine classifies them as "sad," basic learning materials are selected.

[1162] As a concrete example, consider a user watching a video of a scientific experiment online. If the device analyzes the user's face and classifies it as "happy" and their behavior as "attentive," and the emotion engine then classifies it as "excited," the device will provide the user with detailed experimental procedures and applied experiments. On the other hand, if the device classifies the user's facial expression as "sad," their behavior as "distracted," and the emotion engine then classifies them as "anxious," the device will provide the user with basic experimental procedures and supplementary materials. In this way, the user's learning experience is highly personalized.

[1163] Furthermore, the server generates detailed feedback for parents and teachers based on the analysis results sent from the device and the emotion engine's analysis results. This feedback includes information on the user's learning status and appropriate teaching methods, helping parents and teachers accurately understand the user's learning status and provide appropriate support and guidance.

[1164] Examples of prompts include:

[1165] "Please analyze the user's facial expressions and behavior in real time while they are watching this video and provide them with the most appropriate learning materials."

[1166] "Categorize your users' emotions in detail and adjust the difficulty of your learning materials based on the results."

[1167] As described above, the system of the present invention provides an optimal educational environment that adapts to individual learning needs by adjusting and providing learning materials in real time. Furthermore, the introduction of an emotion engine allows for detailed understanding of the user's emotional state, which is expected to further improve learning effectiveness.

[1168] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1169] Step 1:

[1170] The server loads the machine learning model and emotion engine.

[1171] Input: The model file and API key to use when loading.

[1172] What it does: The server loads facial expression and behavior recognition models using TensorFlow and PyTorch libraries, and prepares to use the Azure Emotion API and Google Cloud Vision API for emotion analysis.

[1173] Output: Initialized facial expression recognition model, action recognition model and emotion engine.

[1174] Step 2:

[1175] The device activates the camera and captures the user's image.

[1176] Input: A camera device connected to the device.

[1177] Specific operation: When a user starts learning, the device activates the camera device and captures the user's image in real time using a common webcam such as a Logitech camera.

[1178] Output: Real-time captured video data.

[1179] Step 3:

[1180] The device analyzes the video frames using a facial expression recognition model.

[1181] Input: Captured video frames.

[1182] How it works: Captured video frames are fed into a facial expression recognition model on the device's CPU or GPU, which classifies the user's facial expression for each frame into categories such as "happy," "neutral," or "sad."

[1183] Output: Classified facial expression data.

[1184] Step 4:

[1185] The device sends facial expression data to the emotion engine, which analyzes the emotions.

[1186] Input: Classified facial expression data.

[1187] How it works: The device sends the results of the facial expression recognition model to the emotion engine, which uses this data to classify the user's emotional state into categories such as "excitement," "anxiety," or "sadness."

[1188] Output: Detailed emotion data.

[1189] Step 5:

[1190] The device stores video frames in a buffer and analyzes them using an action recognition model.

[1191] Input: Captured video frames.

[1192] How it works: A certain number of frames are stored in a buffer and then fed into an action recognition model, which classifies the user's behavior as "attentive," "distracted," "fidgeting," etc.

[1193] Output: Classified behavioral data.

[1194] Step 6:

[1195] The device selects the most appropriate learning materials based on the facial expressions, behavior, and emotional data it obtains.

[1196] Input: facial expression data, behavioral data, and emotion data.

[1197] Specific operation: The device integrates this data and selects the most suitable learning materials for the user. For example, if the user is "happy" and "attentive" and their emotion is classified as "excited," the device will display advanced learning materials.

[1198] Output: The learning material provided to the user.

[1199] Step 7:

[1200] The server receives the data from the terminal and generates feedback.

[1201] Input: Analysis results and emotion data sent from the device.

[1202] What it does: The server receives this data and generates detailed feedback for parents and teachers, including information about the user's learning progress, emotional state, and appropriate teaching methods.

[1203] Output: Feedback information for parents and teachers.

[1204] (Application example 2)

[1205] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1206] Conventional learning systems have difficulty adapting to a user's learning situation and emotional state in real time. As a result, they are unable to provide a personalized learning experience that meets the user's individual needs, resulting in reduced learning effectiveness. It is also difficult for parents and teachers to accurately grasp a user's learning situation and provide appropriate support. Furthermore, even with online educational content distribution services, it is difficult to provide content that responds to a user's real-time emotions and behavior, delaying learning optimization.

[1207] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1208] In this invention, the server includes means for detecting and analyzing facial expressions, means for detecting and analyzing behavior, means for adjusting and providing learning materials based on the facial expressions and behavior, means for adjusting and providing learning materials in real time based on the analysis results and detailed emotional information generated by the emotion engine, and means for providing the analysis results as feedback to parents and teachers. This makes it possible to personalize content using generated prompts based on the user's emotional state. This makes it possible to accurately grasp the user's learning situation and provide appropriate support, enabling a highly personalized learning experience.

[1209] "Means for detecting and analyzing facial expressions" refers to a device or method for recognizing facial expressions from an image of a user's face and analyzing their specific emotional state.

[1210] The "means for detecting and analyzing behavior" refers to a device or method for capturing a user's daily actions and behavior from video data and analyzing the behavioral patterns.

[1211] The "means for adjusting and providing learning materials" refers to a device or method for selecting learning materials of appropriate difficulty and type based on the analysis of the user's facial expressions and behavior, and providing them in real time.

[1212] An "emotion engine" is an advanced algorithm or model that analyzes a user's facial and behavioral data to identify more detailed emotional states.

[1213] "Detailed emotion information from the emotion engine" is information on the user's various emotional states and their changes, obtained as a result of analysis by the emotion engine.

[1214] The "means for providing feedback" is a device or method for providing parents and teachers with reports and advice generated based on the analysis results and emotional information.

[1215] A "generative AI model" is a machine learning model used to analyze a user's facial expressions and behavior and identify their detailed emotional state.

[1216] "Generative prompts" are instructions or guidelines used to optimize learning content or materials based on the user's emotional state.

[1217] The "means for adjusting and providing in real time" refers to a device or method for instantly changing and providing learning materials according to the user's current situation.

[1218] The present invention is a system that analyzes a user's learning status in real time and provides personalized learning materials based on the user's emotions and behavior. Specifically, this system is configured as follows.

[1219] First, the server loads the facial expression recognition model, behavioral recognition model, and emotion engine. These models are based on machine learning and are used to analyze the user's facial expressions, behavior, and emotions. Specifically, the facial expression recognition model classifies the user's facial expressions into categories such as "happy," "neutral," and "sad," while the behavioral recognition model classifies the user's behavior into categories such as "attentive," "distracted," and "fidgeting." The emotion engine also uses a generative AI model to identify detailed emotional states and provides more complex emotional information from the user's facial expression and behavioral data.

[1220] Next, the device used by the user activates the camera and captures the user's video in real time. The captured video frames are input into a facial expression recognition model, and the user's facial expressions are analyzed. At the same time, a certain number of frames are stored in a buffer and input into a behavior recognition model. This allows the user's behavior to be analyzed in real time.

[1221] Based on the analysis results, the device selects the appropriate level of learning materials to provide to the user. Specifically, if the user is "happy" and "attentive" and the emotion engine classifies them as "excited," advanced learning materials are selected. On the other hand, if the user is "neutral" or "distracted" and the emotion engine classifies them as "anxious," standard learning materials are selected. Also, if the user is "sad" or "fidgeting" and the emotion engine classifies them as "sad," basic learning materials are selected.

[1222] Furthermore, the server generates detailed feedback based on the analysis results sent from the device and the emotion engine's analysis results. This feedback is provided to parents and teachers and includes information on the user's learning status and appropriate teaching methods.

[1223] For example, if a user is watching an online video of a science experiment, and the device analyzes the user's face and classifies it as "happy" and their behavior as "attentive," and the emotion engine classifies it as "excited," the device will provide the user with detailed experimental procedures and applied experiments. On the other hand, if the device classifies the user's facial expression as "sad" and their behavior as "distracted," and the emotion engine classifies them as "anxious," the device will provide the user with basic experimental procedures and supplementary materials. In this way, the user's learning experience is highly personalized.

[1224] Example prompt sentence:

[1225] By setting prompts as follows, you can have the generative AI model perform detailed analysis.

[1226] prompt

[1227] The system inputs the user's facial expression and behavior data and analyzes it using facial expression and behavior recognition models. It then uses an emotion engine to estimate the user's detailed emotional state, and selects and provides appropriate learning materials based on that.

[1228] Input data

[1229] User's facial expression image (live video frame)

[1230] User behavior data (a certain number of frames)

[1231] output

[1232] Appropriate learning materials

[1233] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1234] Step 1:

[1235] The device used by the user activates the camera and captures the user's image in real time.

[1236] Input: Live video of the user's face

[1237] Output: Video frame

[1238] Specific operation: The device's camera detects the user's face and captures the image.

[1239] Step 2:

[1240] The captured video frames are input into a facial expression recognition model to analyze the user's facial expressions.

[1241] Input: Video frame

[1242] Output: User's facial expression data (e.g. "happy", "neutral", "sad")

[1243] Specific operation: The device passes video frames to the facial expression recognition model, which then classifies the facial expression.

[1244] Step 3:

[1245] A certain number of frames are stored in a buffer and input into the action recognition model.

[1246] Input: A certain number of video frames

[1247] Output: User behavior data (e.g., "attentive," "distracted," "fidgeting")

[1248] Specific operation: Continuous images captured by the camera are stored in a buffer, and the buffer is passed to the action recognition model for analysis.

[1249] Step 4:

[1250] The analysis results are input into an emotion engine to identify detailed emotional states.

[1251] Input: facial expression data, behavior data

[1252] Output: Detailed emotional information (e.g., "excitement," "anxiety," "sadness")

[1253] Specific behavior: The emotion engine analyzes facial expression and behavior data to estimate detailed emotional states.

[1254] Step 5:

[1255] Based on the analysis results and those of the emotion engine, the device selects appropriate learning materials.

[1256] Input: Detailed emotional information

[1257] Output: Selected learning material content

[1258] Specific operation: Based on the user's emotional state in real time, the device selects learning materials suitable for the user from the database.

[1259] Step 6:

[1260] Selected learning materials are provided to users.

[1261] Input: Content of selected learning materials

[1262] Output: Learning materials that can be viewed or used by the user

[1263] Specific operation: The terminal displays the selected learning materials to the user.

[1264] Step 7:

[1265] The server generates detailed feedback based on the analysis results sent from the device and the analysis results of the emotion engine.

[1266] Input: Analysis results, emotion engine analysis results

[1267] Output: Feedback to parents and teachers

[1268] Specific operation: The server aggregates the data and generates reports and teaching guidelines for parents and teachers.

[1269] Step 8:

[1270] Provide feedback to parents and teachers.

[1271] Input: Generated feedback

[1272] Output: Report on the user's learning progress

[1273] Specific operation: The server sends the feedback to the parent and teacher's devices and displays it.

[1274] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1275] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1276] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1277] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1278] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1279] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1280] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1281] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1282] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1283] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1284] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1285] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1286] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1287] 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.

[1288] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1289] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1290] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1291] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1292] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1293] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1294] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1295] The following is further disclosed regarding the above embodiment.

[1296] (Claim 1)

[1297] means for detecting and analyzing facial expressions;

[1298] a means for detecting and analyzing behavior;

[1299] means for adjusting and providing learning materials based on said facial expressions and behaviors;

[1300] means for providing the analysis results as feedback to parents and teachers;

[1301] A system including:

[1302] (Claim 2)

[1303] 10. The system of claim 1, wherein the means for detecting and analyzing facial expressions uses a machine learning model to classify the user's facial expressions.

[1304] (Claim 3)

[1305] 10. The system of claim 1, wherein the means for detecting and analyzing behavior uses a machine learning model to analyze multiple frames and classify user behavior.

[1306] "Example 1"

[1307] (Claim 1)

[1308] a means for using a machine learning model to detect and classify a user's facial expression;

[1309] a means for using a machine learning model to detect and classify user behavior;

[1310] means for capturing video of a user in real time;

[1311] means for adjusting and providing learning materials based on said facial expressions and behaviors;

[1312] a means for providing the analysis results as feedback to parents and teachers;

[1313] A system including:

[1314] (Claim 2)

[1315] 10. The system of claim 1, wherein the means for capturing and processing video of the user uses a camera to capture video of the user in real time.

[1316] (Claim 3)

[1317] The system of claim 1, characterized in that the machine learning model for classifying the user's facial expressions classifies the user's facial expressions into "happy," "neutral," "sad," etc.

[1318] (Claim 4)

[1319] The system described in claim 1, characterized in that the machine learning model for classifying the user's behavior analyzes multiple frames and classifies the user's behavior into ``attentive,'' ``distracted,'' ``fidgeting,'' etc.

[1320] (Claim 5)

[1321] 2. The system according to claim 1, wherein the means for adjusting and providing the learning materials selects advanced learning materials, standard learning materials, and basic learning materials based on the results of analyzing the user's facial expressions and behavior.

[1322] (Claim 6)

[1323] 2. The system according to claim 1, wherein the means for providing feedback provides parents and teachers with information about the user's learning situation and appropriate teaching methods based on the analysis results.

[1324] "Application Example 1"

[1325] (Claim 1)

[1326] means for detecting and analyzing facial expressions;

[1327] a means for detecting and analyzing behavior;

[1328] means for adjusting and providing learning materials based on said facial expressions and behaviors;

[1329] means for providing the analysis results as feedback to parents and teachers;

[1330] means for analyzing the user's facial expressions and behavior in the virtual environment and adjusting the products or services provided;

[1331] A system including:

[1332] (Claim 2)

[1333] 10. The system of claim 1, wherein the means for detecting and analyzing facial expressions uses a machine learning model to classify the user's facial expressions.

[1334] (Claim 3)

[1335] 10. The system of claim 1, wherein the means for detecting and analyzing behavior uses a machine learning model to analyze multiple frames and classify user behavior.

[1336] "Example 2: Combining Emotion Engines"

[1337] (Claim 1)

[1338] means for detecting and analyzing facial expressions;

[1339] a means for detecting and analyzing behavior;

[1340] A means for analyzing a user's emotions based on the user's facial expressions and actions;

[1341] means for adjusting and providing learning materials based on said facial expressions, actions, and emotions;

[1342] means for providing the analysis results as feedback to parents and teachers;

[1343] A system including:

[1344] (Claim 2)

[1345] 10. The system of claim 1, wherein the means for detecting and analyzing facial expressions uses a machine learning model to classify the user's facial expressions.

[1346] (Claim 3)

[1347] 10. The system of claim 1, wherein the means for detecting and analyzing behavior accumulates and analyzes a certain number of video frames and uses a machine learning model to classify user behavior.

[1348] "Application example 2 when combining emotion engines"

[1349] (Claim 1)

[1350] means for detecting and analyzing facial expressions;

[1351] a means for detecting and analyzing behavior;

[1352] means for adjusting and providing learning materials based on said facial expressions and behaviors;

[1353] a means for adjusting and providing learning materials in real time based on the analysis results and detailed emotional information from the emotional engine;

[1354] means for providing the analysis results as feedback to parents and teachers;

[1355] A system including:

[1356] (Claim 2)

[1357] 10. The system of claim 1, wherein the means for detecting and analyzing facial expressions uses a machine learning model to classify the user's facial expressions.

[1358] (Claim 3)

[1359] 10. The system of claim 1, wherein the means for detecting and analyzing behavior uses a machine learning model to analyze multiple frames and classify user behavior.

[1360] (Claim 4)

[1361] 10. The system of claim 1, wherein the emotion engine uses a generative AI model to identify detailed emotional states based on a user's facial and behavioral data.

[1362] (Claim 5)

[1363] 10. The system of claim 1, wherein the means for tailoring and providing learning materials utilizes generated prompts to personalize content in response to a user's emotional state. [Explanation of symbols]

[1364] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for detecting and analyzing facial expressions; a means for detecting and analyzing behavior; means for adjusting and providing learning materials based on said facial expressions and behaviors; means for providing the analysis results as feedback to parents and teachers; A system including:

2. 10. The system of claim 1, wherein the means for detecting and analyzing facial expressions uses a machine learning model to classify the user's facial expressions.

3. 10. The system of claim 1, wherein the means for detecting and analyzing behavior uses a machine learning model to analyze multiple frames and classify user behavior.

Images