system

Abstract

Provide a system. [Solution] means for receiving a request for learning material input by a user; means for obtaining user profile information based on the request; means for transmitting data including the obtained profile information to an artificial intelligence model; means for receiving learning materials generated by the artificial intelligence model; means for displaying the received learning material to a user; A system including:

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] Conventional learning materials are uniform in content and are not customized based on the individual learner's comprehension ability, interests, or learning history. This often leads to reduced learning efficiency and learners losing interest in the materials. Furthermore, selecting and creating learning materials to meet the individual needs of each learner requires time and effort, placing a significant burden on educators and parents. The present invention aims to solve these problems and provide a system that efficiently provides optimal learning materials to each learner. [Means for solving the problem]

[0005] The present invention solves the problem by a system including a means for receiving a request for learning materials input by a user, a means for acquiring user profile information based on the request, a means for transmitting data including the acquired profile information to an AI model, a means for receiving learning materials generated by the AI ​​model, and a means for displaying the received learning materials to the user. This makes it possible to generate and provide learning materials optimized for each user in real time. The user's profile information includes learning history, comprehension ability, personality, etc., and the AI ​​model generates appropriate learning materials based on this information, thereby realizing the provision of learning materials tailored to each individual learner.

[0006] "User" refers to a human being or an entity acting on behalf of a human being who uses the system.

[0007] "Learning materials" refers to content such as documents and workbooks for educational purposes.

[0008] A "request" refers to data representing a request or wish that a user sends to the system via a terminal.

[0009] "Profile information" refers to information about a user's personal information, such as their learning history, comprehension, and personality.

[0010] An "AI model" is an algorithm or system that uses artificial intelligence, and refers to software that analyzes data and performs specific tasks.

[0011] A "database" is a system that stores and manages data in an organized manner and allows specific data to be searched for quickly and efficiently.

[0012] "Receiving" refers to the operation or action of a system or device receiving transmitted data or information.

[0013] "Transmission" refers to the operation or action of a system or device sending data or information to a specific party or entity.

[0014] "Display" refers to the operations and functions that a terminal uses to visually convey information to the user.

[0015] "System" is a general term for a mechanism in which multiple elements work together to provide specific functions or services. [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] To specifically implement the present invention, it is conceivable to build the following system. This system generates and displays optimal learning materials in real time based on user input, and is useful in many educational situations.

[0038] In this system, a user first inputs a request for learning materials using a device. For example, an elementary school child might use their parent's smartphone to request "fifth grade math practice problems." The device then sends this request to the server.

[0039] When the server receives the request, it retrieves profile information from the database based on the user's ID. This profile information includes the user's learning history, comprehension ability, personality, etc. For example, information such as "This child is good at arithmetic problems, but has difficulty with word problems" may be retrieved from the database.

[0040] The server then sends the acquired profile information to an AI model. This AI model analyzes the user information and generates learning materials based on it. Specifically, the AI ​​model considers the user's comprehension ability and learning history to select appropriate questions. In this case, the learning materials generated will include calculation problems, with an emphasis on written questions.

[0041] The server receives the generated learning materials and then sends them to the device. The device displays the received learning materials to the user. The parent's smartphone displays "5th grade math practice problems," allowing the user to start learning.

[0042] As a concrete example, consider the following scenario: Child A, an elementary school student, inputs a request from his / her parent's smartphone saying, "I want word problems for fifth-grade math." The device sends this request to the server. The server retrieves Child A's learning history from a database and sends profile information based on his / her comprehension ability and personality to the AI ​​model. Based on the profile information, the AI ​​model generates learning materials that include many medium-difficulty word problems. The server sends the generated learning materials to the device, which displays them to the user. Child A can use these learning materials to efficiently progress through his / her studies.

[0043] In this way, the present invention provides optimal learning materials to individual users in real time, thereby improving learning efficiency.

[0044] The processing flow will be explained below.

[0045] Step 1:

[0046] The terminal accepts a user's request for learning materials.

[0047] The user opens a dedicated app on their device and enters a request for learning materials, such as "5th grade math practice problems."

[0048] Step 2:

[0049] The device sends a request to the server.

[0050] The device sends the user's request to the server as an HTTP POST request.

[0051] Step 3:

[0052] The server receives the request and retrieves the user information from the database.

[0053] The server receives a request from the terminal and retrieves the user's profile information (learning history, comprehension, personality, etc.) from the database based on the user ID.

[0054] Step 4:

[0055] The server sends the acquired user information to the AI ​​model.

[0056] The server constructs an API request containing the user information and sends the request to the AI ​​model.

[0057] Step 5:

[0058] The AI ​​model analyzes user information and generates optimal learning materials.

[0059] The AI ​​model analyzes the user information it receives and generates customized learning materials taking into account the user's comprehension ability and areas of weakness.

[0060] Step 6:

[0061] The server receives the generated learning materials and transmits them to the terminal.

[0062] The server receives the teaching materials generated from the AI ​​model and sends them to the terminal as an HTTP response.

[0063] Step 7:

[0064] The terminal receives the learning material and displays it to the user.

[0065] The device receives the response from the server and displays the learning materials on the app's UI. The user can then begin learning using the displayed materials.

[0066] Example 1

[0067] 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."

[0068] In conventional educational systems, it has been difficult to provide optimal learning materials that take into account each user's learning history, comprehension ability, and strong and weak subjects. This can lead to a decrease in the user's learning efficiency and a loss of motivation to learn. Therefore, there is a need for the development of a system that can provide each user with learning materials that meet their individual needs in real time.

[0069] 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.

[0070] In this invention, the server includes means for receiving a request for learning materials input by a user, means for acquiring user profile information, means for transmitting data including the acquired profile information to the generative AI model, means for receiving learning materials generated by the AI ​​model, and means for displaying the received learning materials to the user, thereby enabling the provision of optimal learning materials to individual users in real time.

[0071] A "user" is an individual or entity who utilizes the system to request learning materials and study using the provided materials.

[0072] A "request" is information or a request entered by a user when requesting specific study materials.

[0073] "Profile information" is information that indicates attribute data such as the user's learning history, comprehension ability, strong subjects, and weak subjects.

[0074] A "generative AI model" is an artificial intelligence algorithm that analyzes input profile information and generates optimal learning materials based on that information.

[0075] "Learning materials" are questions and learning materials for users to study, including content customized by a generative AI model.

[0076] A "terminal" is an electronic device used by a user to input requests and view learning materials, including a smartphone, tablet, or computer.

[0077] A "server" is a computer system that receives user requests, retrieves profile information, and invokes generative AI models to generate learning materials.

[0078] A "database" is an information system for storing and managing user profile information and learning history.

[0079] The present invention relates to a system for generating and displaying optimal learning materials in real time based on user input. This system operates when a user inputs a request for learning materials using a terminal and transmits the request to a server. A specific embodiment of the present invention will be described below.

[0080] First, a user uses a device (e.g., a smartphone, tablet, or computer) to input a request for learning materials. The device has a request input interface, allowing the user to specify the subject and type of problem they want to study. For example, an elementary school child might use their parent's smartphone to input, "I want practice problems for fifth-grade math."

[0081] Next, the terminal sends the request entered by the user to the server. At this time, the request data includes the user ID and the request content. The server receives this and retrieves the user's profile information from the database. The profile information includes the user's learning history, comprehension ability, strong subjects, weak subjects, etc. For example, the information might be "User ID: 12345, strong points: calculation problems, weak points: written problems."

[0082] The acquired profile information is sent by the server to the generative AI model. The generative AI model is built using machine learning libraries such as TENSORFLOW (registered trademark) and PyTorch, and analyzes the user's profile information and generates optimal learning materials based on it. In this process, the AI ​​model takes into account the user's strong and weak subjects and selects problems to maximize learning effectiveness. For example, it generates "practice problems that include many word problems for fifth-grade math."

[0083] The generated learning materials are then sent back to the device by the server. The device then displays the received learning materials to the user. As a specific example of how this works, "5th grade math practice problems" are displayed on the parent's smartphone. The user can use this to advance their studies.

[0084] As a concrete example, the following prompt sentence can be input to a generative AI model:

[0085] A user has the following request: "I want word problems for 5th grade math." Information obtained from the database: "I'm good at math problems, but I'm not good at word problems." Please generate optimal learning materials based on this information.

[0086] This allows the user to be provided with the most suitable learning materials in real time, thereby improving the user's learning efficiency.

[0087] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0088] Step 1:

[0089] The user inputs a request for learning materials on the device. The user inputs a request such as "I want some math practice problems for fifth graders" via a smartphone or tablet. The input request is stored on the device as text data.

[0090] Step 2:

[0091] The terminal sends a request to the server. The request data includes the user ID and the request content, and is sent to the server as an HTTP request. The input is "User ID: 12345, Request: 5th grade math practice problems," and the server receives this data.

[0092] Step 3:

[0093] The server receives the request and retrieves the user's profile information from the database. Using the received user ID, the server queries the database to retrieve the corresponding user's profile information. Specific profile information includes the user's learning history, comprehension ability, strong subjects, and weak subjects. For example, the data retrieved is "User ID: 12345, strong points: calculation problems, weak points: written problems."

[0094] Step 4:

[0095] The server sends the profile information to the generative AI model. The acquired profile information is converted to JSON format and sent to the generative AI model as an API request. The input is the profile information, which becomes the data to be analyzed by the AI ​​model.

[0096] Step 5:

[0097] The generative AI model analyzes the profile information and generates optimal learning materials. Based on the received profile information, the AI ​​model analyzes the user's comprehension ability and strong and weak subjects, and generates optimal learning materials. Specifically, based on the profile information, it selects and generates a "problem set that includes many fifth-grade math word problems." The output is the generated learning materials.

[0098] Step 6:

[0099] The server sends the generated learning materials to the device. The server then sends the learning materials received from the AI ​​model to the user's device. This is also sent as an HTTP response, and the learning materials are included in JSON format. The output is response data containing the learning materials requested by the user.

[0100] Step 7:

[0101] The device displays the learning materials to the user. The device parses the received learning materials and displays them on the screen in a user-friendly format. Specifically, "5th grade math practice problems" are displayed on the parent's smartphone, and the user can use them to advance their learning. The output is the content of the learning materials displayed on the device.

[0102] (Application example 1)

[0103] 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."

[0104] Existing learning systems face challenges in providing optimal learning materials to individual users in real time, resulting in reduced learning efficiency. Furthermore, there is a lack of customization based on individual users' learning history and comprehension, which means learning outcomes are not maximized. Furthermore, there is a lack of interactive access to learning materials in virtual environments, which limits the educational effectiveness.

[0105] 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.

[0106] In this invention, the server includes: means for receiving a request for learning materials input by a user; means for acquiring user profile information based on the request; means for transmitting data including the acquired profile information to a generative AI model; means for receiving learning materials generated by the generative AI model; means for displaying the received learning materials to the user; means for making the learning materials interactively accessible in a virtual environment; and means for allowing the user to access the learning materials using a smartphone or a head-mounted display. This enables learning materials optimized for each individual user to be provided in real time, improving learning efficiency. Furthermore, interactive access in a virtual environment enables more effective learning.

[0107] The "means for receiving a request for learning materials input by a user" is an interface for receiving request information for learning materials designated by a user on the server side.

[0108] "Means for obtaining user profile information based on a request" is a function for extracting information such as the user's learning history, comprehension ability, and personality from a database based on a received request.

[0109] "Means for sending data including the acquired profile information to the generative AI model" is a function for sending the extracted profile information to the generative AI model as input data.

[0110] "Means for receiving learning materials generated by a generative AI model" refers to a mechanism for receiving learning materials sent from a generative AI model on the server side.

[0111] The "means for displaying the received learning materials to the user" is an interface for displaying the received learning materials on the terminal used by the user.

[0112] "Means for making learning materials interactively accessible within a virtual environment" refers to functionality that allows a user to manipulate or interact with the learning materials within the virtual environment.

[0113] "Means for users to access learning materials using smartphones or head-mounted displays" refers to a function that allows users to access learning materials using devices such as smartphones or head-mounted displays.

[0114] To implement this invention, the following system may be constructed. This system receives a request for learning materials input by a user, generates optimal learning materials using a generative AI model based on the user's profile information, and displays them in real time. Furthermore, this system enables interactive access within a virtual environment, allowing users to access the learning materials using a smartphone or head-mounted display.

[0115] Hardware and software used

[0116] Hardware: Servers, smartphones, head-mounted displays

[0117] Software: Flask (Python framework), TensorFlow (AI model), SQLite (database)

[0118] Program processing explanation

[0119] First, the user's device is provided with an interface that allows them to input requests for learning materials. Once the user inputs the request, the information is sent to the server. The server then uses a database to obtain the user's profile information and extracts information such as their learning history, comprehension ability, and personality.

[0120] The server then sends the profile information to a generative AI model (using TensorFlow), which generates optimal learning materials based on the information provided. These learning materials are then sent to the server and displayed on the user's device.

[0121] Furthermore, to enable interactive access within the virtual environment, the learning materials are designed to allow users to manipulate and interact with them. Users can access the learning materials using smartphones or head-mounted displays and carry out real learning activities.

[0122] Specific examples

[0123] As a concrete example, consider the case where a parent accesses a virtual store for their child and requests "5th grade word problems." In this case, the server retrieves the child's learning history and comprehension from a database and sends the information to a generative AI model based on that. The model then generates optimal learning materials and displays them on the parent's smartphone via the server. Because the learning materials can be accessed interactively within the virtual environment, the child can effectively practice word problems using, for example, a head-mounted display.

[0124] Prompt Sentence Examples

[0125] For example, a possible prompt for a generative AI model might be:

[0126] "Mathematics, 5th grade, good at calculation problems, bad at word problems, introverted"

[0127] In this way, by implementing the present invention, it is possible to provide optimal learning materials to individual users in real time, thereby improving learning efficiency. Furthermore, interactive access in a virtual environment makes learning more effective.

[0128] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0129] Step 1:

[0130] A user inputs a request for learning materials.

[0131] Input: A learning task specified by the user on the device (e.g., a 5th grade math word problem)

[0132] How it works: A user uses a smartphone or head-mounted display interface to input a request for learning materials.

[0133] Output: Request information is sent from the terminal to the server

[0134] Step 2:

[0135] The server retrieves the user's profile information.

[0136] Input: User request information, user ID

[0137] How it works: The server connects to the database and retrieves profile information such as the user's learning history, comprehension, and personality.

[0138] Output: User profile information is retrieved.

[0139] Step 3:

[0140] The server sends the profile information to the generative AI model.

[0141] Input: Retrieved profile information

[0142] How it works: The server sends the acquired profile information to the generative AI model as input data. Specifically, it converts the profile information into an appropriate format (e.g., vector or text format) and inputs it into the model.

[0143] Output: where the input data to the model is sent

[0144] Step 4:

[0145] A generative AI model generates optimal learning materials.

[0146] Input: Input data based on profile information

[0147] How it works: The generative AI model (powered by TensorFlow) performs calculations to generate optimal learning materials based on the user's learning history, comprehension, and personality information. This calculation includes using a neural network to predict the next task.

[0148] Output: The optimal learning material is generated and sent to the server.

[0149] Step 5:

[0150] The server receives the generated learning materials and transmits them to the user's terminal.

[0151] Input: Learning material data from a generative AI model

[0152] How it works: The server receives the generated learning materials and sends them to the user's device, where they are converted into an appropriate format and rendered.

[0153] Output: The learning material data is sent to the user's device.

[0154] Step 6:

[0155] The terminal displays the learning material to the user.

[0156] Input: Learning material data sent from the server

[0157] How it works: The user's device displays the received learning materials on the screen. In the case of a smartphone, the learning materials are displayed on the touchscreen, and in the case of a head-mounted display, the learning materials are projected within the user's field of view.

[0158] Output: Users can view and manipulate learning materials.

[0159] Step 7:

[0160] Users interactively access learning materials within a virtual environment.

[0161] Input: User actions and interactions

[0162] Action: The user manipulates and interacts with the learning material in the virtual environment, for example, solving problems or entering answers. These actions are reflected in the system in real time.

[0163] Output: User operation results are recorded and reflected in the system in real time.

[0164] 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.

[0165] This invention provides a system that generates and provides customized learning materials in real time, incorporating user emotional information. In addition to conventional learning material generation systems, this system uses an emotion engine to recognize the user's emotions and provides more optimal learning materials based on that information.

[0166] Specifically, a user uses a device to input a request for learning materials. For example, an elementary school child uses a parent's smartphone to request "5th grade math practice problems." The device then sends this request to the server.

[0167] When the server receives the request, it retrieves profile information from the database based on the user's ID. This profile information includes the user's learning history, comprehension ability, personality, etc. For example, information such as "This child is good at arithmetic problems, but has difficulty with word problems" may be retrieved from the database.

[0168] The server then sends the acquired profile information to an AI model, which analyzes the user information and generates learning materials based on it. An emotion engine then joins this process. The emotion engine analyzes the user's facial expressions, voice, body temperature, heart rate, and other biometric information to assess the user's emotional state. For example, it determines whether the user is stressed, relaxed, or focused while studying.

[0169] Emotional information obtained by the emotion engine is also sent to the AI ​​model. The AI ​​model integrates and analyzes the profile information and emotional information to evaluate the user's learning interest and concentration. Based on this, it generates further optimized learning materials. For example, if the user feels stressed by written questions, it generates learning materials that will increase motivation to study by adding simple calculation problems.

[0170] The server receives the generated learning materials and then sends them to the device, which then displays them to the user. This results in the parent's smartphone displaying "5th grade math practice problems," allowing the user to begin learning.

[0171] Consider the following scenario as a concrete example. Elementary school student Child A inputs a request on his / her parent's smartphone saying, "I want word problems for fifth-grade math," and the device sends this request to a server. The server retrieves Child A's learning history from a database and sends profile information based on his / her comprehension ability and personality to an AI model. At the same time, the device's built-in camera and microphone transmit Child A's facial expressions and voice to an emotion engine, which analyzes them. The AI ​​model integrates the profile information and emotional information to generate learning materials that include word problems of optimal difficulty as well as problems with a relaxing effect. The server receives the generated learning materials and sends them to the device, which then displays them to Child A. Child A can use these learning materials to study efficiently and without stress.

[0172] In this way, the present invention provides learning materials that take into account the user's individual profile information and real-time emotional state, maximizing learning efficiency and encouraging the user to learn.

[0173] The processing flow will be explained below.

[0174] Step 1:

[0175] A user inputs a learning material request through a terminal.

[0176] A user uses a dedicated app on their device to input a request for learning materials, for example, "I want some 5th grade math practice problems."

[0177] Step 2:

[0178] The device sends a request to the server.

[0179] The device sends the user's request to the server as an HTTP POST request.

[0180] Step 3:

[0181] The server receives and parses the request.

[0182] The server receives the request from the device and analyzes the request content (e.g., "5th grade math practice problems").

[0183] Step 4:

[0184] The server retrieves the user information from the database.

[0185] Based on the request, the server retrieves the user's profile information from the database using the user ID, which includes the user's learning history, comprehension ability, personality, etc.

[0186] Step 5:

[0187] The server instructs the emotion engine to acquire biometric information of the user.

[0188] The server instructs the emotion engine to acquire biometric information such as the user's facial expression, voice, body temperature, and heart rate from sensors such as a camera and microphone built into the device.

[0189] Step 6:

[0190] The emotion engine analyzes the user's biometric information and evaluates their emotional state.

[0191] The emotion engine analyzes the acquired biometric information and evaluates the user's emotional state (e.g., stress, relaxation, concentration).

[0192] Step 7:

[0193] The server sends the acquired profile information and emotional information to the AI ​​model.

[0194] The server sends data including profile information and emotion information to the AI ​​model.

[0195] Step 8:

[0196] The AI ​​model analyzes the information and generates optimal learning materials.

[0197] The AI ​​model analyzes the user's profile information and emotional information to generate learning materials that are best suited to the user's learning. If the user is feeling stressed, the difficulty level can be adjusted or questions with a relaxing effect can be included.

[0198] Step 9:

[0199] The server receives the generated learning materials and transmits them to the terminal.

[0200] The server receives the learning materials generated from the AI ​​model and sends them to the device.

[0201] Step 10:

[0202] The terminal receives the learning material and displays it to the user.

[0203] The device receives the response from the server and displays the learning materials on the app screen. The user can then begin learning using the displayed materials.

[0204] As a result, the present invention makes it possible to provide learning materials optimized for individual users in real time based on their profile information and emotional information, thereby maximizing the user's learning efficiency and encouraging them to learn.

[0205] Example 2

[0206] 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."

[0207] Conventional learning material generation systems provide learning materials based on the user's learning history and level of understanding, but they are unable to generate learning materials that take the user's emotional state into consideration. As a result, if the user is feeling stressed or has low concentration, the system is unable to provide learning materials that are adapted to that state, which can lead to a decrease in learning efficiency and a decrease in motivation to learn.

[0208] 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.

[0209] In this invention, the server includes means for receiving a request for learning materials input by a user, means for acquiring user profile information, means for collecting biometric information such as the user's facial expression, voice, body temperature, and heart rate, means for transmitting the acquired profile information and biometric information to an emotion engine for analysis, means for transmitting data integrating the analyzed emotional information to an artificial intelligence model, means for receiving learning materials generated by the artificial intelligence model, and means for displaying the received learning materials to the user. This makes it possible to provide customized learning materials that take into account the user's learning history, level of understanding, and real-time emotional state.

[0210] "User" means a person who uses the System to request and use learning materials.

[0211] "Learning materials" refers to educational content such as workbooks and textbooks that users use for studying.

[0212] A "request" is a request sent by a user to a server through a terminal for learning materials.

[0213] "Profile information" refers to information about a user's personal information, such as their learning history, comprehension, and personality.

[0214] "Biometric information" refers to information about the user's body, such as facial expression, voice, body temperature, and heart rate.

[0215] An "emotion engine" is an algorithm or system that analyzes a user's biometric information and infers their emotional state as a result.

[0216] An "artificial intelligence model" is a system that analyzes profile information and emotional information and generates optimized learning materials based on that information.

[0217] A "server" is a computer system that receives requests from users, retrieves the necessary profile information, uses AI models to generate learning materials, and sends them to the device.

[0218] A "terminal" is a device used by a user to input requests and display learning materials.

[0219] This invention provides a system that incorporates user emotional information and generates and provides customized learning materials in real time. This system operates using the following hardware and software.

[0220] First, a user inputs a request using a device (e.g., a smartphone or tablet). For example, the user inputs a request such as "I want math practice questions for fifth graders" by voice or text. The device then sends this request to the server. Data is transmitted over a network to send the request.

[0221] When the server receives the request, it retrieves the user's profile information from the database. This profile information includes the user's learning history, comprehension, and personality. For example, information such as "User A is good at calculation problems, but has difficulty with written problems" can be retrieved from the database. An RDBMS (e.g., MySQL (registered trademark), PostgreSQL) can be used as the database.

[0222] Next, the device uses its built-in camera and microphone to collect biometric information such as the user's facial expressions, voice, body temperature, and heart rate. The device transmits this data to a server in real time. Emotion analysis is performed using an emotion engine (e.g., Microsoft® Azure® Emotion API, IBM Watson® Tone Analyzer).

[0223] The server sends the biometric information to the emotion engine, which analyzes the emotional information. For example, it determines whether the user is feeling stressed, relaxed, or focused. The analysis results of the emotion engine are sent to the server, where the profile information and emotional information are integrated.

[0224] Based on the profile information and emotion information, the server sends the data to an AI model (e.g., TensorFlow, PyTorch) to generate learning materials optimized for the user. This AI model uses natural language processing (NLP) and machine learning (ML) techniques to create learning materials that best fit the user's learning needs. For example, if a user feels stressed by word problems, it can generate learning materials that include many calculation problems.

[0225] The generated learning materials are sent from the server to the terminal, which then displays them to the user, allowing the user to utilize customized learning materials that are adapted to their emotional state in real time.

[0226] As a concrete example, if elementary school student A inputs a request from his / her parent's smartphone saying, "I want some 5th grade math word problems," the following prompt is sent to the generative AI model:

[0227] Child A, an elementary school student, has requested "5th grade math word problems" from his parent's smartphone. Child A is good at calculation problems but not so good at word problems. Furthermore, Child A is feeling a bit stressed about his current learning situation. Based on this, please generate learning materials suitable for Child A.

[0228] As a result, the present invention provides learning materials that take into account the user's individual profile information and real-time emotional state, maximizing learning efficiency and encouraging the user's motivation to learn.

[0229] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0230] System program processing flow

[0231] Step 1: Fill out and submit your request

[0232] Subject: User

[0233] Actions: A user uses a terminal to input a request for learning materials, for example, "I want some 5th grade math practice problems."

[0234] Input: Learning material request (voice or text)

[0235] Output: Request data packet

[0236] Subject: Terminal

[0237] Operation: The terminal receives an input request, converts it into a data packet, and sends it to the server.

[0238] Input: User request

[0239] Output: Sending a request data packet

[0240] Step 2: Get profile information

[0241] Subject: Server

[0242] Operation: The server extracts the user ID from the received request data packet and retrieves the user's profile information from the database.

[0243] Input: Request data packet

[0244] Data processing: Extraction of user ID, database query

[0245] Output: User profile information

[0246] Example: For example, information such as "User A is good at calculation problems but has difficulty with written problems" is acquired.

[0247] Step 3: Collect and send emotion data

[0248] Subject: Terminal

[0249] How it works: The device's built-in camera and microphone collect the user's biometric information (facial expressions, voice, body temperature, heart rate, etc.).

[0250] Input: User's biometric information

[0251] Output: Biometric data packet

[0252] Example: A camera captures your facial expressions and a microphone records your voice.

[0253] Subject: Terminal

[0254] Operation: Collected biometric data is sent to a server in real time.

[0255] Input: Biometric data packet

[0256] Output: Sending biometric data

[0257] Step 4: Emotional Analysis

[0258] Subject: Server

[0259] How it works: The server sends biometric data to the emotion engine, which analyzes the emotional state.

[0260] Input: Biometric data

[0261] Data processing: Analysis using emotion engine

[0262] Output: Emotional information

[0263] Example: Assessing whether the user is stressed or relaxed.

[0264] Subject: Emotion Engine

[0265] How it works: The emotion engine analyzes the data it receives and quantifies or categorizes the user's emotional state.

[0266] Input: Biometric data

[0267] Data Computing: Applying Sentiment Analysis Algorithms

[0268] Output: Analyzed emotion information (e.g., "The user is feeling stressed")

[0269] Step 5: Sending data to the AI ​​model and generating teaching materials

[0270] Subject: Server

[0271] How it works: The profile information and analyzed emotional information are combined and sent to the AI ​​model.

[0272] Input: Profile information, emotion information

[0273] Data processing: information integration, data packet generation

[0274] Output: Integrated information data packet

[0275] Subject: AI model

[0276] Operation: Based on the integrated information, the most suitable learning materials are generated for the user.

[0277] Input: Integrated information data packet

[0278] Data calculation: Applying algorithms to generate optimal learning materials for users

[0279] Output: Generated learning materials

[0280] Step 6: Distributing the materials

[0281] Subject: Server

[0282] How it works: Receives learning materials generated by an AI model and sends them to the device.

[0283] Input: Generated learning materials

[0284] Output: Sending learning material data

[0285] Step 7: Displaying the materials

[0286] Subject: Terminal

[0287] Operation: Displays the received learning materials to the user.

[0288] Input: Learning material data

[0289] Output: Displayed learning material

[0290] Example: "Fifth grade math practice problems" are displayed on the device screen, allowing the user to begin studying.

[0291] Through these steps, users will receive customized learning materials that adapt to their emotional state in real time.

[0292] (Application example 2)

[0293] 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."

[0294] Conventional learning material provision systems provide learning materials based on a user's learning history, comprehension, and personality, but are unable to take into account the user's real-time emotional information. As a result, when a user is in a situation where they are prone to stress, their motivation and efficiency in learning may decrease. The objective of this invention is to improve motivation and achieve efficient learning by providing more optimal learning materials based on the user's emotional state.

[0295] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a request for learning materials input by a user, means for acquiring user profile information based on the request, means for transmitting data including the acquired profile information to an AI model, means for receiving learning materials generated by the AI ​​model, means for acquiring and analyzing user emotional information, means for transmitting the analyzed emotional information to the AI ​​model and generating further customized learning materials based on the analysis results, and means for displaying the received learning materials to the user. This makes it possible to integrate and analyze profile information based on the user's learning history and personality with real-time emotional information, thereby providing optimal learning materials and improving the user's motivation and efficiency in learning.

[0296] "A request for learning materials input by a user" is information that a user inputs into the system via a terminal as a request for learning materials.

[0297] "User profile information" refers to individual information about a user, such as the user's learning history, comprehension, personality, and emotional state.

[0298] An "artificial intelligence model" is a computational model that analyzes a user's profile information and emotional information and generates optimal learning materials.

[0299] "Emotion information" is information that indicates the user's real-time emotional state, obtained from facial expressions, voice, heart rate, body temperature, etc.

[0300] "Customized learning materials" are materials that are personalized based on a user's profile information and affective information.

[0301] The "display means" refers to a device or system that allows a user to visually confirm the generated learning materials.

[0302] The "means for obtaining profile information based on a request" is a system that has the function of receiving a request from a user and retrieving the user's profile information from a database in response to the request.

[0303] This invention is a system for generating and providing customized learning materials in real time that incorporates a user's emotional information. This system includes a terminal used by the user, a server that processes information, an emotion engine that analyzes emotional information, and a device for displaying the generated learning materials.

[0304] System configuration

[0305] 1. User Device:

[0306] The user device is equipped with a camera, microphone, heart rate monitor, temperature sensor, etc. This allows biometric information such as the user's facial expression, voice, heart rate, and body temperature to be acquired.

[0307] The terminal provides an interface for the user to input requests for study materials.

[0308] 2. Server:

[0309] The server receives the request sent from the user terminal and retrieves the profile information from the database.

[0310] This profile information includes the user's learning history, comprehension, personality, and emotional state.

[0311] The profile information obtained is sent to an artificial intelligence model (e.g., GPT-4 (registered trademark)).

[0312] The emotion engine uses machine learning frameworks such as TensorFlow to analyze the user's facial expressions and voice.

[0313] The server sends the analysis results from the emotion engine to the artificial intelligence model to generate optimal learning materials.

[0314] The generated learning materials are transmitted from the server to the user terminal.

[0315] 3. Emotion Engine:

[0316] The emotion engine is responsible for analyzing emotional information from the user's facial expressions, voice, etc.

[0317] Libraries such as TensorFlow and OpenCV are used for facial recognition and voice analysis.

[0318] 4. Generating and displaying learning materials:

[0319] Artificial intelligence models (e.g., GPT-4) generate optimal learning materials based on profile information and emotional information.

[0320] The generated learning materials are displayed on the user's terminal in real time, allowing the user to study efficiently.

[0321] Specific examples

[0322] For example, in the case of using a tablet installed in a bookstore or educational supply store, the following process takes place: When a user inputs a request such as "I want word problems for fifth-grade math," the tablet sends this information to a server. At the same time, the tablet uses a camera and microphone to transmit the user's face and voice to an emotion engine. The emotion engine uses TensorFlow to analyze the real-time emotion information and sends the results to a server-side AI model. The AI ​​model (e.g., GPT-4) combines the profile information and emotion information to generate customized learning materials. These materials are then sent from the server to the tablet and displayed to the user.

[0323] Example prompt sentence:

[0324] On a Friday night, User A enters a request into a tablet at an educational supply store: "I want word problems for 5th grade math." User A's past learning history indicates that he has difficulty with word problems. The emotion engine analyzes that User A is in a relaxed state.

[0325] In this way, the present invention can integrate user profile information and emotional information to provide optimized learning materials in real time, thereby improving the user's motivation and efficiency in learning.

[0326] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0327] Step 1:

[0328] The user uses a device to input a request for learning materials. Specifically, the user inputs a request such as "I want word problems for 5th grade math" using a tablet or smartphone. This request information is sent from the device to the server.

[0329] Input: User enters request for learning material.

[0330] Output: The request information is sent to the server.

[0331] Step 2:

[0332] When the server receives the request, it retrieves profile information from the database based on the user's ID. Specifically, the profile data includes information on the user's learning history, comprehension, and personality.

[0333] Input: Request information and user ID.

[0334] Output: A dataset containing profile information.

[0335] Step 3:

[0336] To obtain emotional information, the device's camera and microphone collect biometric information such as the user's facial expression, voice, heart rate, and body temperature. This biometric information is then sent to the emotion engine in real time.

[0337] Input: User's facial expression, voice, heart rate, and temperature.

[0338] Output: Biometric data is sent to the emotion engine.

[0339] Step 4:

[0340] The emotion engine analyzes biometric information to assess the user's current emotional state, using facial recognition, voice analysis, and analysis of heart rate and body temperature fluctuations to determine whether the user is relaxed, stressed, or focused.

[0341] Input: Biometric data.

[0342] Output: Parsed emotion information.

[0343] Step 5:

[0344] The server sends the acquired profile information and emotional information to an AI model (e.g., GPT-4), which then integrates this information and generates optimal learning materials based on the user's current emotional state and profile.

[0345] Input: Profile information and sentiment information.

[0346] Output: Generated customized learning materials.

[0347] Step 6:

[0348] The server receives the generated learning materials and transmits them to the user terminal.

[0349] Input: Generated customized learning materials.

[0350] Output: The learning materials are sent from the server to the device.

[0351] Step 7:

[0352] The terminal displays the learning materials received from the server to the user, allowing the user to progress with their studies using individually customized learning materials.

[0353] Input: Generated learning materials.

[0354] Output: The customized learning material displayed to the user.

[0355] 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.

[0356] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0357] 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.

[0358] [Second embodiment]

[0359] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0360] 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.

[0361] 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).

[0362] 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.

[0363] 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.

[0364] 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).

[0365] 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.

[0366] 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.

[0367] 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.

[0368] 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.

[0369] In the smart glasses 214, the 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.

[0370] 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."

[0371] To specifically implement the present invention, it is conceivable to build the following system. This system generates and displays optimal learning materials in real time based on user input, and is useful in many educational situations.

[0372] In this system, a user first inputs a request for learning materials using a device. For example, an elementary school child might use their parent's smartphone to request "fifth grade math practice problems." The device then sends this request to the server.

[0373] When the server receives the request, it retrieves profile information from the database based on the user's ID. This profile information includes the user's learning history, comprehension ability, personality, etc. For example, information such as "This child is good at arithmetic problems, but has difficulty with word problems" may be retrieved from the database.

[0374] The server then sends the acquired profile information to an AI model. This AI model analyzes the user information and generates learning materials based on it. Specifically, the AI ​​model considers the user's comprehension ability and learning history to select appropriate questions. In this case, the learning materials generated will include calculation problems, with an emphasis on written questions.

[0375] The server receives the generated learning materials and then sends them to the device. The device displays the received learning materials to the user. The parent's smartphone displays "5th grade math practice problems," allowing the user to start learning.

[0376] As a concrete example, consider the following scenario: Child A, an elementary school student, inputs a request from his / her parent's smartphone saying, "I want word problems for fifth-grade math." The device sends this request to the server. The server retrieves Child A's learning history from a database and sends profile information based on his / her comprehension ability and personality to the AI ​​model. Based on the profile information, the AI ​​model generates learning materials that include many medium-difficulty word problems. The server sends the generated learning materials to the device, which displays them to the user. Child A can use these learning materials to efficiently progress through his / her studies.

[0377] In this way, the present invention provides optimal learning materials to individual users in real time, thereby improving learning efficiency.

[0378] The processing flow will be explained below.

[0379] Step 1:

[0380] The terminal accepts a user's request for learning materials.

[0381] The user opens a dedicated app on their device and enters a request for learning materials, such as "5th grade math practice problems."

[0382] Step 2:

[0383] The device sends a request to the server.

[0384] The device sends the user's request to the server as an HTTP POST request.

[0385] Step 3:

[0386] The server receives the request and retrieves the user information from the database.

[0387] The server receives a request from the terminal and retrieves the user's profile information (learning history, comprehension, personality, etc.) from the database based on the user ID.

[0388] Step 4:

[0389] The server sends the acquired user information to the AI ​​model.

[0390] The server constructs an API request containing the user information and sends the request to the AI ​​model.

[0391] Step 5:

[0392] The AI ​​model analyzes user information and generates optimal learning materials.

[0393] The AI ​​model analyzes the user information it receives and generates customized learning materials taking into account the user's comprehension ability and areas of weakness.

[0394] Step 6:

[0395] The server receives the generated learning materials and transmits them to the terminal.

[0396] The server receives the teaching materials generated from the AI ​​model and sends them to the terminal as an HTTP response.

[0397] Step 7:

[0398] The terminal receives the learning material and displays it to the user.

[0399] The device receives the response from the server and displays the learning materials on the app's UI. The user can then begin learning using the displayed materials.

[0400] Example 1

[0401] 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."

[0402] In conventional educational systems, it has been difficult to provide optimal learning materials that take into account each user's learning history, comprehension ability, and strong and weak subjects. This can lead to a decrease in the user's learning efficiency and a loss of motivation to learn. Therefore, there is a need for the development of a system that can provide each user with learning materials that meet their individual needs in real time.

[0403] 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.

[0404] In this invention, the server includes means for receiving a request for learning materials input by a user, means for acquiring user profile information, means for transmitting data including the acquired profile information to the generative AI model, means for receiving learning materials generated by the AI ​​model, and means for displaying the received learning materials to the user, thereby enabling the provision of optimal learning materials to individual users in real time.

[0405] A "user" is an individual or entity who utilizes the system to request learning materials and study using the provided materials.

[0406] A "request" is information or a request entered by a user when requesting specific study materials.

[0407] "Profile information" is information that indicates attribute data such as the user's learning history, comprehension ability, strong subjects, and weak subjects.

[0408] A "generative AI model" is an artificial intelligence algorithm that analyzes input profile information and generates optimal learning materials based on that information.

[0409] "Learning materials" are questions and learning materials for users to study, including content customized by a generative AI model.

[0410] A "terminal" is an electronic device used by a user to input requests and view learning materials, including a smartphone, tablet, or computer.

[0411] A "server" is a computer system that receives user requests, retrieves profile information, and invokes generative AI models to generate learning materials.

[0412] A "database" is an information system for storing and managing user profile information and learning history.

[0413] The present invention relates to a system for generating and displaying optimal learning materials in real time based on user input. This system operates when a user inputs a request for learning materials using a terminal and transmits the request to a server. A specific embodiment of the present invention will be described below.

[0414] First, a user uses a device (e.g., a smartphone, tablet, or computer) to input a request for learning materials. The device has a request input interface, allowing the user to specify the subject and type of problem they want to study. For example, an elementary school child might use their parent's smartphone to input, "I want practice problems for fifth-grade math."

[0415] Next, the terminal sends the request entered by the user to the server. At this time, the request data includes the user ID and the request content. The server receives this and retrieves the user's profile information from the database. The profile information includes the user's learning history, comprehension ability, strong subjects, weak subjects, etc. For example, the information might be "User ID: 12345, strong points: calculation problems, weak points: written problems."

[0416] The server then sends the acquired profile information to a generative AI model. The generative AI model is built using machine learning libraries such as TensorFlow and PyTorch to analyze the user's profile information and generate optimal learning materials based on it. In this process, the AI ​​model considers the user's strong and weak subjects and selects problems to maximize learning effectiveness. For example, it generates "practice problems that include many word problems for fifth-grade math."

[0417] The generated learning materials are then sent back to the device by the server. The device then displays the received learning materials to the user. As a specific example of how this works, "5th grade math practice problems" are displayed on the parent's smartphone. The user can use this to advance their studies.

[0418] As a concrete example, the following prompt sentence can be input to a generative AI model:

[0419] A user has the following request: "I want word problems for 5th grade math." Information obtained from the database: "I'm good at math problems, but I'm not good at word problems." Please generate optimal learning materials based on this information.

[0420] This allows the user to be provided with the most suitable learning materials in real time, thereby improving the user's learning efficiency.

[0421] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0422] Step 1:

[0423] The user inputs a request for learning materials on the device. The user inputs a request such as "I want some math practice problems for fifth graders" via a smartphone or tablet. The input request is stored on the device as text data.

[0424] Step 2:

[0425] The terminal sends a request to the server. The request data includes the user ID and the request content, and is sent to the server as an HTTP request. The input is "User ID: 12345, Request: 5th grade math practice problems," and the server receives this data.

[0426] Step 3:

[0427] The server receives the request and retrieves the user's profile information from the database. Using the received user ID, the server queries the database to retrieve the corresponding user's profile information. Specific profile information includes the user's learning history, comprehension ability, strong subjects, and weak subjects. For example, the data retrieved is "User ID: 12345, strong points: calculation problems, weak points: written problems."

[0428] Step 4:

[0429] The server sends the profile information to the generative AI model. The acquired profile information is converted to JSON format and sent to the generative AI model as an API request. The input is the profile information, which becomes the data to be analyzed by the AI ​​model.

[0430] Step 5:

[0431] The generative AI model analyzes the profile information and generates optimal learning materials. Based on the received profile information, the AI ​​model analyzes the user's comprehension ability and strong and weak subjects, and generates optimal learning materials. Specifically, based on the profile information, it selects and generates a "problem set that includes many fifth-grade math word problems." The output is the generated learning materials.

[0432] Step 6:

[0433] The server sends the generated learning materials to the device. The server then sends the learning materials received from the AI ​​model to the user's device. This is also sent as an HTTP response, and the learning materials are included in JSON format. The output is response data containing the learning materials requested by the user.

[0434] Step 7:

[0435] The device displays the learning materials to the user. The device parses the received learning materials and displays them on the screen in a user-friendly format. Specifically, "5th grade math practice problems" are displayed on the parent's smartphone, and the user can use them to advance their learning. The output is the content of the learning materials displayed on the device.

[0436] (Application example 1)

[0437] 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."

[0438] Existing learning systems face challenges in providing optimal learning materials to individual users in real time, resulting in reduced learning efficiency. Furthermore, there is a lack of customization based on individual users' learning history and comprehension, which means learning outcomes are not maximized. Furthermore, there is a lack of interactive access to learning materials in virtual environments, which limits the educational effectiveness.

[0439] 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.

[0440] In this invention, the server includes: means for receiving a request for learning materials input by a user; means for acquiring user profile information based on the request; means for transmitting data including the acquired profile information to a generative AI model; means for receiving learning materials generated by the generative AI model; means for displaying the received learning materials to the user; means for making the learning materials interactively accessible in a virtual environment; and means for allowing the user to access the learning materials using a smartphone or a head-mounted display. This enables learning materials optimized for each individual user to be provided in real time, improving learning efficiency. Furthermore, interactive access in a virtual environment enables more effective learning.

[0441] The "means for receiving a request for learning materials input by a user" is an interface for receiving request information for learning materials designated by a user on the server side.

[0442] "Means for obtaining user profile information based on a request" is a function for extracting information such as the user's learning history, comprehension ability, and personality from a database based on a received request.

[0443] "Means for sending data including the acquired profile information to the generative AI model" is a function for sending the extracted profile information to the generative AI model as input data.

[0444] "Means for receiving learning materials generated by a generative AI model" refers to a mechanism for receiving learning materials sent from a generative AI model on the server side.

[0445] The "means for displaying the received learning materials to the user" is an interface for displaying the received learning materials on the terminal used by the user.

[0446] "Means for making learning materials interactively accessible within a virtual environment" refers to functionality that allows a user to manipulate or interact with the learning materials within the virtual environment.

[0447] "Means for users to access learning materials using smartphones or head-mounted displays" refers to a function that allows users to access learning materials using devices such as smartphones or head-mounted displays.

[0448] To implement this invention, the following system may be constructed. This system receives a request for learning materials input by a user, generates optimal learning materials using a generative AI model based on the user's profile information, and displays them in real time. Furthermore, this system enables interactive access within a virtual environment, allowing users to access the learning materials using a smartphone or head-mounted display.

[0449] Hardware and software used

[0450] Hardware: Servers, smartphones, head-mounted displays

[0451] Software: Flask (Python framework), TensorFlow (AI model), SQLite (database)

[0452] Program processing explanation

[0453] First, the user's device is provided with an interface that allows them to input requests for learning materials. Once the user inputs the request, the information is sent to the server. The server then uses a database to obtain the user's profile information and extracts information such as their learning history, comprehension ability, and personality.

[0454] The server then sends the profile information to a generative AI model (using TensorFlow), which generates optimal learning materials based on the information provided. These learning materials are then sent to the server and displayed on the user's device.

[0455] Furthermore, to enable interactive access within the virtual environment, the learning materials are designed to allow users to manipulate and interact with them. Users can access the learning materials using smartphones or head-mounted displays and carry out real learning activities.

[0456] Specific examples

[0457] As a concrete example, consider the case where a parent accesses a virtual store for their child and requests "5th grade word problems." In this case, the server retrieves the child's learning history and comprehension from a database and sends the information to a generative AI model based on that. The model then generates optimal learning materials and displays them on the parent's smartphone via the server. Because the learning materials can be accessed interactively within the virtual environment, the child can effectively practice word problems using, for example, a head-mounted display.

[0458] Prompt Sentence Examples

[0459] For example, a possible prompt for a generative AI model might be:

[0460] "Mathematics, 5th grade, good at calculation problems, bad at word problems, introverted"

[0461] In this way, by implementing the present invention, it is possible to provide optimal learning materials to individual users in real time, thereby improving learning efficiency. Furthermore, interactive access in a virtual environment makes learning more effective.

[0462] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0463] Step 1:

[0464] A user inputs a request for learning materials.

[0465] Input: A learning task specified by the user on the device (e.g., a 5th grade math word problem)

[0466] How it works: A user uses a smartphone or head-mounted display interface to input a request for learning materials.

[0467] Output: Request information is sent from the terminal to the server

[0468] Step 2:

[0469] The server retrieves the user's profile information.

[0470] Input: User request information, user ID

[0471] How it works: The server connects to the database and retrieves profile information such as the user's learning history, comprehension, and personality.

[0472] Output: User profile information is retrieved.

[0473] Step 3:

[0474] The server sends the profile information to the generative AI model.

[0475] Input: Retrieved profile information

[0476] How it works: The server sends the acquired profile information to the generative AI model as input data. Specifically, it converts the profile information into an appropriate format (e.g., vector or text format) and inputs it into the model.

[0477] Output: where the input data to the model is sent

[0478] Step 4:

[0479] A generative AI model generates optimal learning materials.

[0480] Input: Input data based on profile information

[0481] How it works: The generative AI model (powered by TensorFlow) performs calculations to generate optimal learning materials based on the user's learning history, comprehension, and personality information. This calculation includes using a neural network to predict the next task.

[0482] Output: The optimal learning material is generated and sent to the server.

[0483] Step 5:

[0484] The server receives the generated learning materials and transmits them to the user's terminal.

[0485] Input: Learning material data from a generative AI model

[0486] How it works: The server receives the generated learning materials and sends them to the user's device, where they are converted into an appropriate format and rendered.

[0487] Output: The learning material data is sent to the user's device.

[0488] Step 6:

[0489] The terminal displays the learning material to the user.

[0490] Input: Learning material data sent from the server

[0491] How it works: The user's device displays the received learning materials on the screen. In the case of a smartphone, the learning materials are displayed on the touchscreen, and in the case of a head-mounted display, the learning materials are projected within the user's field of view.

[0492] Output: Users can view and manipulate learning materials.

[0493] Step 7:

[0494] Users interactively access learning materials within a virtual environment.

[0495] Input: User actions and interactions

[0496] Action: The user manipulates and interacts with the learning material in the virtual environment, for example, solving problems or entering answers. These actions are reflected in the system in real time.

[0497] Output: User operation results are recorded and reflected in the system in real time.

[0498] 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.

[0499] This invention provides a system that generates and provides customized learning materials in real time, incorporating user emotional information. In addition to conventional learning material generation systems, this system uses an emotion engine to recognize the user's emotions and provides more optimal learning materials based on that information.

[0500] Specifically, a user uses a device to input a request for learning materials. For example, an elementary school child uses a parent's smartphone to request "5th grade math practice problems." The device then sends this request to the server.

[0501] When the server receives the request, it retrieves profile information from the database based on the user's ID. This profile information includes the user's learning history, comprehension ability, personality, etc. For example, information such as "This child is good at arithmetic problems, but has difficulty with word problems" may be retrieved from the database.

[0502] The server then sends the acquired profile information to an AI model, which analyzes the user information and generates learning materials based on it. An emotion engine then joins this process. The emotion engine analyzes the user's facial expressions, voice, body temperature, heart rate, and other biometric information to assess the user's emotional state. For example, it determines whether the user is stressed, relaxed, or focused while studying.

[0503] Emotional information obtained by the emotion engine is also sent to the AI ​​model. The AI ​​model integrates and analyzes the profile information and emotional information to evaluate the user's learning interest and concentration. Based on this, it generates further optimized learning materials. For example, if the user feels stressed by written questions, it generates learning materials that will increase motivation to study by adding simple calculation problems.

[0504] The server receives the generated learning materials and then sends them to the device, which then displays them to the user. This results in the parent's smartphone displaying "5th grade math practice problems," allowing the user to begin learning.

[0505] Consider the following scenario as a concrete example. Elementary school student Child A inputs a request on his / her parent's smartphone saying, "I want word problems for fifth-grade math," and the device sends this request to a server. The server retrieves Child A's learning history from a database and sends profile information based on his / her comprehension ability and personality to an AI model. At the same time, the device's built-in camera and microphone transmit Child A's facial expressions and voice to an emotion engine, which analyzes them. The AI ​​model integrates the profile information and emotional information to generate learning materials that include word problems of optimal difficulty as well as problems with a relaxing effect. The server receives the generated learning materials and sends them to the device, which then displays them to Child A. Child A can use these learning materials to study efficiently and without stress.

[0506] In this way, the present invention provides learning materials that take into account the user's individual profile information and real-time emotional state, maximizing learning efficiency and encouraging the user to learn.

[0507] The processing flow will be explained below.

[0508] Step 1:

[0509] A user inputs a learning material request through a terminal.

[0510] A user uses a dedicated app on their device to input a request for learning materials, for example, "I want some 5th grade math practice problems."

[0511] Step 2:

[0512] The device sends a request to the server.

[0513] The device sends the user's request to the server as an HTTP POST request.

[0514] Step 3:

[0515] The server receives and parses the request.

[0516] The server receives the request from the device and analyzes the request content (e.g., "5th grade math practice problems").

[0517] Step 4:

[0518] The server retrieves the user information from the database.

[0519] Based on the request, the server retrieves the user's profile information from the database using the user ID, which includes the user's learning history, comprehension ability, personality, etc.

[0520] Step 5:

[0521] The server instructs the emotion engine to acquire biometric information of the user.

[0522] The server instructs the emotion engine to acquire biometric information such as the user's facial expression, voice, body temperature, and heart rate from sensors such as a camera and microphone built into the device.

[0523] Step 6:

[0524] The emotion engine analyzes the user's biometric information and evaluates their emotional state.

[0525] The emotion engine analyzes the acquired biometric information and evaluates the user's emotional state (e.g., stress, relaxation, concentration).

[0526] Step 7:

[0527] The server sends the acquired profile information and emotional information to the AI ​​model.

[0528] The server sends data including profile information and emotion information to the AI ​​model.

[0529] Step 8:

[0530] The AI ​​model analyzes the information and generates optimal learning materials.

[0531] The AI ​​model analyzes the user's profile information and emotional information to generate learning materials that are best suited to the user's learning. If the user is feeling stressed, the difficulty level can be adjusted or questions with a relaxing effect can be included.

[0532] Step 9:

[0533] The server receives the generated learning materials and transmits them to the terminal.

[0534] The server receives the learning materials generated from the AI ​​model and sends them to the device.

[0535] Step 10:

[0536] The terminal receives the learning material and displays it to the user.

[0537] The device receives the response from the server and displays the learning materials on the app screen. The user can then begin learning using the displayed materials.

[0538] As a result, the present invention makes it possible to provide learning materials optimized for individual users in real time based on their profile information and emotional information, thereby maximizing the user's learning efficiency and encouraging them to learn.

[0539] Example 2

[0540] 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."

[0541] Conventional learning material generation systems provide learning materials based on the user's learning history and level of understanding, but they are unable to generate learning materials that take the user's emotional state into consideration. As a result, if the user is feeling stressed or has low concentration, the system is unable to provide learning materials that are adapted to that state, which can lead to a decrease in learning efficiency and a decrease in motivation to learn.

[0542] 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.

[0543] In this invention, the server includes means for receiving a request for learning materials input by a user, means for acquiring user profile information, means for collecting biometric information such as the user's facial expression, voice, body temperature, and heart rate, means for transmitting the acquired profile information and biometric information to an emotion engine for analysis, means for transmitting data integrating the analyzed emotional information to an artificial intelligence model, means for receiving learning materials generated by the artificial intelligence model, and means for displaying the received learning materials to the user. This makes it possible to provide customized learning materials that take into account the user's learning history, level of understanding, and real-time emotional state.

[0544] "User" means a person who uses the System to request and use learning materials.

[0545] "Learning materials" refers to educational content such as workbooks and textbooks that users use for studying.

[0546] A "request" is a request sent by a user to a server through a terminal for learning materials.

[0547] "Profile information" refers to information about a user's personal information, such as their learning history, comprehension, and personality.

[0548] "Biometric information" refers to information about the user's body, such as facial expression, voice, body temperature, and heart rate.

[0549] An "emotion engine" is an algorithm or system that analyzes a user's biometric information and infers their emotional state as a result.

[0550] An "artificial intelligence model" is a system that analyzes profile information and emotional information and generates optimized learning materials based on that information.

[0551] A "server" is a computer system that receives requests from users, retrieves the necessary profile information, uses AI models to generate learning materials, and sends them to the device.

[0552] A "terminal" is a device used by a user to input requests and display learning materials.

[0553] This invention provides a system that incorporates user emotional information and generates and provides customized learning materials in real time. This system operates using the following hardware and software.

[0554] First, a user inputs a request using a device (e.g., a smartphone or tablet). For example, the user inputs a request such as "I want math practice questions for fifth graders" by voice or text. The device then sends this request to the server. Data is transmitted over a network to send the request.

[0555] When the server receives a request, it retrieves the user's profile information from the database. This profile information includes the user's learning history, comprehension, and personality. For example, it retrieves information from the database that "User A is good at calculation problems, but has difficulty with written problems." An RDBMS (e.g., MySQL, PostgreSQL) can be used as the database.

[0556] Next, the device uses the built-in camera and microphone to collect biometric information such as the user's facial expressions, voice, body temperature, and heart rate. The device sends this data to a server in real time, and an emotion engine (e.g., Microsoft Azure Emotion API, IBM Watson Tone Analyzer) is used for emotion analysis.

[0557] The server sends the biometric information to the emotion engine, which analyzes the emotional information. For example, it determines whether the user is feeling stressed, relaxed, or focused. The analysis results of the emotion engine are sent to the server, where the profile information and emotional information are integrated.

[0558] Based on the profile information and emotion information, the server sends the data to an AI model (e.g., TensorFlow, PyTorch) to generate learning materials optimized for the user. This AI model uses natural language processing (NLP) and machine learning (ML) techniques to create learning materials that best fit the user's learning needs. For example, if a user feels stressed by word problems, it can generate learning materials that include many calculation problems.

[0559] The generated learning materials are sent from the server to the terminal, which then displays them to the user, allowing the user to utilize customized learning materials that are adapted to their emotional state in real time.

[0560] As a concrete example, if elementary school student A inputs a request from his / her parent's smartphone saying, "I want some 5th grade math word problems," the following prompt is sent to the generative AI model:

[0561] Child A, an elementary school student, has requested "5th grade math word problems" from his parent's smartphone. Child A is good at calculation problems but not so good at word problems. Furthermore, Child A is feeling a bit stressed about his current learning situation. Based on this, please generate learning materials suitable for Child A.

[0562] As a result, the present invention provides learning materials that take into account the user's individual profile information and real-time emotional state, maximizing learning efficiency and encouraging the user's motivation to learn.

[0563] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0564] System program processing flow

[0565] Step 1: Fill out and submit your request

[0566] Subject: User

[0567] Actions: A user uses a terminal to input a request for learning materials, for example, "I want some 5th grade math practice problems."

[0568] Input: Learning material request (voice or text)

[0569] Output: Request data packet

[0570] Subject: Terminal

[0571] Operation: The terminal receives an input request, converts it into a data packet, and sends it to the server.

[0572] Input: User request

[0573] Output: Sending a request data packet

[0574] Step 2: Get profile information

[0575] Subject: Server

[0576] Operation: The server extracts the user ID from the received request data packet and retrieves the user's profile information from the database.

[0577] Input: Request data packet

[0578] Data processing: Extraction of user ID, database query

[0579] Output: User profile information

[0580] Example: For example, information such as "User A is good at calculation problems but has difficulty with written problems" is acquired.

[0581] Step 3: Collect and send emotion data

[0582] Subject: Terminal

[0583] How it works: The device's built-in camera and microphone collect the user's biometric information (facial expressions, voice, body temperature, heart rate, etc.).

[0584] Input: User's biometric information

[0585] Output: Biometric data packet

[0586] Example: A camera captures your facial expressions and a microphone records your voice.

[0587] Subject: Terminal

[0588] Operation: Collected biometric data is sent to a server in real time.

[0589] Input: Biometric data packet

[0590] Output: Sending biometric data

[0591] Step 4: Emotional Analysis

[0592] Subject: Server

[0593] How it works: The server sends biometric data to the emotion engine, which analyzes the emotional state.

[0594] Input: Biometric data

[0595] Data processing: Analysis using emotion engine

[0596] Output: Emotional information

[0597] Example: Assessing whether the user is stressed or relaxed.

[0598] Subject: Emotion Engine

[0599] How it works: The emotion engine analyzes the data it receives and quantifies or categorizes the user's emotional state.

[0600] Input: Biometric data

[0601] Data Computing: Applying Sentiment Analysis Algorithms

[0602] Output: Analyzed emotion information (e.g., "The user is feeling stressed")

[0603] Step 5: Sending data to the AI ​​model and generating teaching materials

[0604] Subject: Server

[0605] How it works: The profile information and analyzed emotional information are combined and sent to the AI ​​model.

[0606] Input: Profile information, emotion information

[0607] Data processing: information integration, data packet generation

[0608] Output: Integrated information data packet

[0609] Subject: AI model

[0610] Operation: Based on the integrated information, the most suitable learning materials are generated for the user.

[0611] Input: Integrated information data packet

[0612] Data calculation: Applying algorithms to generate optimal learning materials for users

[0613] Output: Generated learning materials

[0614] Step 6: Distributing the materials

[0615] Subject: Server

[0616] How it works: Receives learning materials generated by an AI model and sends them to the device.

[0617] Input: Generated learning materials

[0618] Output: Sending learning material data

[0619] Step 7: Displaying the materials

[0620] Subject: Terminal

[0621] Operation: Displays the received learning materials to the user.

[0622] Input: Learning material data

[0623] Output: Displayed learning material

[0624] Example: "Fifth grade math practice problems" are displayed on the device screen, allowing the user to begin studying.

[0625] Through these steps, users will receive customized learning materials that adapt to their emotional state in real time.

[0626] (Application example 2)

[0627] 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."

[0628] Conventional learning material provision systems provide learning materials based on a user's learning history, comprehension, and personality, but are unable to take into account the user's real-time emotional information. As a result, when a user is in a situation where they are prone to stress, their motivation and efficiency in learning may decrease. The objective of this invention is to improve motivation and achieve efficient learning by providing more optimal learning materials based on the user's emotional state.

[0629] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a request for learning materials input by a user, means for acquiring user profile information based on the request, means for transmitting data including the acquired profile information to an AI model, means for receiving learning materials generated by the AI ​​model, means for acquiring and analyzing user emotional information, means for transmitting the analyzed emotional information to the AI ​​model and generating further customized learning materials based on the analysis results, and means for displaying the received learning materials to the user. This makes it possible to integrate and analyze profile information based on the user's learning history and personality with real-time emotional information, thereby providing optimal learning materials and improving the user's motivation and efficiency in learning.

[0630] "A request for learning materials input by a user" is information that a user inputs into the system via a terminal as a request for learning materials.

[0631] "User profile information" refers to individual information about a user, such as the user's learning history, comprehension, personality, and emotional state.

[0632] An "artificial intelligence model" is a computational model that analyzes a user's profile information and emotional information and generates optimal learning materials.

[0633] "Emotion information" is information that indicates the user's real-time emotional state, obtained from facial expressions, voice, heart rate, body temperature, etc.

[0634] "Customized learning materials" are materials that are personalized based on a user's profile information and affective information.

[0635] The "display means" refers to a device or system that allows a user to visually confirm the generated learning materials.

[0636] The "means for obtaining profile information based on a request" is a system that has the function of receiving a request from a user and retrieving the user's profile information from a database in response to the request.

[0637] This invention is a system for generating and providing customized learning materials in real time that incorporates a user's emotional information. This system includes a terminal used by the user, a server that processes information, an emotion engine that analyzes emotional information, and a device for displaying the generated learning materials.

[0638] System configuration

[0639] 1. User Device:

[0640] The user device is equipped with a camera, microphone, heart rate monitor, temperature sensor, etc. This allows biometric information such as the user's facial expression, voice, heart rate, and body temperature to be acquired.

[0641] The terminal provides an interface for the user to input requests for study materials.

[0642] 2. Server:

[0643] The server receives the request sent from the user terminal and retrieves the profile information from the database.

[0644] This profile information includes the user's learning history, comprehension, personality, and emotional state.

[0645] The profile information obtained is sent to an artificial intelligence model (e.g., GPT-4).

[0646] The emotion engine uses machine learning frameworks such as TensorFlow to analyze the user's facial expressions and voice.

[0647] The server sends the analysis results from the emotion engine to the artificial intelligence model to generate optimal learning materials.

[0648] The generated learning materials are transmitted from the server to the user terminal.

[0649] 3. Emotion Engine:

[0650] The emotion engine is responsible for analyzing emotional information from the user's facial expressions, voice, etc.

[0651] Libraries such as TensorFlow and OpenCV are used for facial recognition and voice analysis.

[0652] 4. Generating and displaying learning materials:

[0653] Artificial intelligence models (e.g., GPT-4) generate optimal learning materials based on profile information and emotional information.

[0654] The generated learning materials are displayed on the user's terminal in real time, allowing the user to study efficiently.

[0655] Specific examples

[0656] For example, in the case of using a tablet installed in a bookstore or educational supply store, the following process takes place: When a user inputs a request such as "I want word problems for fifth-grade math," the tablet sends this information to a server. At the same time, the tablet uses a camera and microphone to transmit the user's face and voice to an emotion engine. The emotion engine uses TensorFlow to analyze the real-time emotion information and sends the results to a server-side AI model. The AI ​​model (e.g., GPT-4) combines the profile information and emotion information to generate customized learning materials. These materials are then sent from the server to the tablet and displayed to the user.

[0657] Example prompt sentence:

[0658] On a Friday night, User A enters a request into a tablet at an educational supply store: "I want word problems for 5th grade math." User A's past learning history indicates that he has difficulty with word problems. The emotion engine analyzes that User A is in a relaxed state.

[0659] In this way, the present invention can integrate user profile information and emotional information to provide optimized learning materials in real time, thereby improving the user's motivation and efficiency in learning.

[0660] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0661] Step 1:

[0662] The user uses a device to input a request for learning materials. Specifically, the user inputs a request such as "I want word problems for 5th grade math" using a tablet or smartphone. This request information is sent from the device to the server.

[0663] Input: User enters request for learning material.

[0664] Output: The request information is sent to the server.

[0665] Step 2:

[0666] When the server receives the request, it retrieves profile information from the database based on the user's ID. Specifically, the profile data includes information on the user's learning history, comprehension, and personality.

[0667] Input: Request information and user ID.

[0668] Output: A dataset containing profile information.

[0669] Step 3:

[0670] To obtain emotional information, the device's camera and microphone collect biometric information such as the user's facial expression, voice, heart rate, and body temperature. This biometric information is then sent to the emotion engine in real time.

[0671] Input: User's facial expression, voice, heart rate, and temperature.

[0672] Output: Biometric data is sent to the emotion engine.

[0673] Step 4:

[0674] The emotion engine analyzes biometric information to assess the user's current emotional state, using facial recognition, voice analysis, and analysis of heart rate and body temperature fluctuations to determine whether the user is relaxed, stressed, or focused.

[0675] Input: Biometric data.

[0676] Output: Parsed emotion information.

[0677] Step 5:

[0678] The server sends the acquired profile information and emotional information to an AI model (e.g., GPT-4), which then integrates this information and generates optimal learning materials based on the user's current emotional state and profile.

[0679] Input: Profile information and sentiment information.

[0680] Output: Generated customized learning materials.

[0681] Step 6:

[0682] The server receives the generated learning materials and transmits them to the user terminal.

[0683] Input: Generated customized learning materials.

[0684] Output: The learning materials are sent from the server to the device.

[0685] Step 7:

[0686] The terminal displays the learning materials received from the server to the user, allowing the user to progress with their studies using individually customized learning materials.

[0687] Input: Generated learning materials.

[0688] Output: The customized learning material displayed to the user.

[0689] 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.

[0690] 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.

[0691] 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.

[0692] [Third embodiment]

[0693] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0694] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0695] 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).

[0696] 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.

[0697] 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.

[0698] 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).

[0699] 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.

[0700] 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.

[0701] 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.

[0702] 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.

[0703] 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.

[0704] 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."

[0705] To specifically implement the present invention, it is conceivable to build the following system. This system generates and displays optimal learning materials in real time based on user input, and is useful in many educational situations.

[0706] In this system, a user first inputs a request for learning materials using a device. For example, an elementary school child might use their parent's smartphone to request "fifth grade math practice problems." The device then sends this request to the server.

[0707] When the server receives the request, it retrieves profile information from the database based on the user's ID. This profile information includes the user's learning history, comprehension ability, personality, etc. For example, information such as "This child is good at arithmetic problems, but has difficulty with word problems" may be retrieved from the database.

[0708] The server then sends the acquired profile information to an AI model. This AI model analyzes the user information and generates learning materials based on it. Specifically, the AI ​​model considers the user's comprehension ability and learning history to select appropriate questions. In this case, the learning materials generated will include calculation problems, with an emphasis on written questions.

[0709] The server receives the generated learning materials and then sends them to the device. The device displays the received learning materials to the user. The parent's smartphone displays "5th grade math practice problems," allowing the user to start learning.

[0710] As a concrete example, consider the following scenario: Child A, an elementary school student, inputs a request from his / her parent's smartphone saying, "I want word problems for fifth-grade math." The device sends this request to the server. The server retrieves Child A's learning history from a database and sends profile information based on his / her comprehension ability and personality to the AI ​​model. Based on the profile information, the AI ​​model generates learning materials that include many medium-difficulty word problems. The server sends the generated learning materials to the device, which displays them to the user. Child A can use these learning materials to efficiently progress through his / her studies.

[0711] In this way, the present invention provides optimal learning materials to individual users in real time, thereby improving learning efficiency.

[0712] The processing flow will be explained below.

[0713] Step 1:

[0714] The terminal accepts a user's request for learning materials.

[0715] The user opens a dedicated app on their device and enters a request for learning materials, such as "5th grade math practice problems."

[0716] Step 2:

[0717] The device sends a request to the server.

[0718] The device sends the user's request to the server as an HTTP POST request.

[0719] Step 3:

[0720] The server receives the request and retrieves the user information from the database.

[0721] The server receives a request from the terminal and retrieves the user's profile information (learning history, comprehension, personality, etc.) from the database based on the user ID.

[0722] Step 4:

[0723] The server sends the acquired user information to the AI ​​model.

[0724] The server constructs an API request containing the user information and sends the request to the AI ​​model.

[0725] Step 5:

[0726] The AI ​​model analyzes user information and generates optimal learning materials.

[0727] The AI ​​model analyzes the user information it receives and generates customized learning materials taking into account the user's comprehension ability and areas of weakness.

[0728] Step 6:

[0729] The server receives the generated learning materials and transmits them to the terminal.

[0730] The server receives the teaching materials generated from the AI ​​model and sends them to the terminal as an HTTP response.

[0731] Step 7:

[0732] The terminal receives the learning material and displays it to the user.

[0733] The device receives the response from the server and displays the learning materials on the app's UI. The user can then begin learning using the displayed materials.

[0734] Example 1

[0735] 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."

[0736] In conventional educational systems, it has been difficult to provide optimal learning materials that take into account each user's learning history, comprehension ability, and strong and weak subjects. This can lead to a decrease in the user's learning efficiency and a loss of motivation to learn. Therefore, there is a need for the development of a system that can provide each user with learning materials that meet their individual needs in real time.

[0737] 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.

[0738] In this invention, the server includes means for receiving a request for learning materials input by a user, means for acquiring user profile information, means for transmitting data including the acquired profile information to the generative AI model, means for receiving learning materials generated by the AI ​​model, and means for displaying the received learning materials to the user, thereby enabling the provision of optimal learning materials to individual users in real time.

[0739] A "user" is an individual or entity who utilizes the system to request learning materials and study using the provided materials.

[0740] A "request" is information or a request entered by a user when requesting specific study materials.

[0741] "Profile information" is information that indicates attribute data such as the user's learning history, comprehension ability, strong subjects, and weak subjects.

[0742] A "generative AI model" is an artificial intelligence algorithm that analyzes input profile information and generates optimal learning materials based on that information.

[0743] "Learning materials" are questions and learning materials for users to study, including content customized by a generative AI model.

[0744] A "terminal" is an electronic device used by a user to input requests and view learning materials, including a smartphone, tablet, or computer.

[0745] A "server" is a computer system that receives user requests, retrieves profile information, and invokes generative AI models to generate learning materials.

[0746] A "database" is an information system for storing and managing user profile information and learning history.

[0747] The present invention relates to a system for generating and displaying optimal learning materials in real time based on user input. This system operates when a user inputs a request for learning materials using a terminal and transmits the request to a server. A specific embodiment of the present invention will be described below.

[0748] First, a user uses a device (e.g., a smartphone, tablet, or computer) to input a request for learning materials. The device has a request input interface, allowing the user to specify the subject and type of problem they want to study. For example, an elementary school child might use their parent's smartphone to input, "I want practice problems for fifth-grade math."

[0749] Next, the terminal sends the request entered by the user to the server. At this time, the request data includes the user ID and the request content. The server receives this and retrieves the user's profile information from the database. The profile information includes the user's learning history, comprehension ability, strong subjects, weak subjects, etc. For example, the information might be "User ID: 12345, strong points: calculation problems, weak points: written problems."

[0750] The server then sends the acquired profile information to a generative AI model. The generative AI model is built using machine learning libraries such as TensorFlow and PyTorch to analyze the user's profile information and generate optimal learning materials based on it. In this process, the AI ​​model considers the user's strong and weak subjects and selects problems to maximize learning effectiveness. For example, it generates "practice problems that include many word problems for fifth-grade math."

[0751] The generated learning materials are then sent back to the device by the server. The device then displays the received learning materials to the user. As a specific example of how this works, "5th grade math practice problems" are displayed on the parent's smartphone. The user can use this to advance their studies.

[0752] As a concrete example, the following prompt sentence can be input to a generative AI model:

[0753] A user has the following request: "I want word problems for 5th grade math." Information obtained from the database: "I'm good at math problems, but I'm not good at word problems." Please generate optimal learning materials based on this information.

[0754] This allows the user to be provided with the most suitable learning materials in real time, thereby improving the user's learning efficiency.

[0755] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0756] Step 1:

[0757] The user inputs a request for learning materials on the device. The user inputs a request such as "I want some math practice problems for fifth graders" via a smartphone or tablet. The input request is stored on the device as text data.

[0758] Step 2:

[0759] The terminal sends a request to the server. The request data includes the user ID and the request content, and is sent to the server as an HTTP request. The input is "User ID: 12345, Request: 5th grade math practice problems," and the server receives this data.

[0760] Step 3:

[0761] The server receives the request and retrieves the user's profile information from the database. Using the received user ID, the server queries the database to retrieve the corresponding user's profile information. Specific profile information includes the user's learning history, comprehension ability, strong subjects, and weak subjects. For example, the data retrieved is "User ID: 12345, strong points: calculation problems, weak points: written problems."

[0762] Step 4:

[0763] The server sends the profile information to the generative AI model. The acquired profile information is converted to JSON format and sent to the generative AI model as an API request. The input is the profile information, which becomes the data to be analyzed by the AI ​​model.

[0764] Step 5:

[0765] The generative AI model analyzes the profile information and generates optimal learning materials. Based on the received profile information, the AI ​​model analyzes the user's comprehension ability and strong and weak subjects, and generates optimal learning materials. Specifically, based on the profile information, it selects and generates a "problem set that includes many fifth-grade math word problems." The output is the generated learning materials.

[0766] Step 6:

[0767] The server sends the generated learning materials to the device. The server then sends the learning materials received from the AI ​​model to the user's device. This is also sent as an HTTP response, and the learning materials are included in JSON format. The output is response data containing the learning materials requested by the user.

[0768] Step 7:

[0769] The device displays the learning materials to the user. The device parses the received learning materials and displays them on the screen in a user-friendly format. Specifically, "5th grade math practice problems" are displayed on the parent's smartphone, and the user can use them to advance their learning. The output is the content of the learning materials displayed on the device.

[0770] (Application example 1)

[0771] 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."

[0772] Existing learning systems face challenges in providing optimal learning materials to individual users in real time, resulting in reduced learning efficiency. Furthermore, there is a lack of customization based on individual users' learning history and comprehension, which means learning outcomes are not maximized. Furthermore, there is a lack of interactive access to learning materials in virtual environments, which limits the educational effectiveness.

[0773] 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.

[0774] In this invention, the server includes: means for receiving a request for learning materials input by a user; means for acquiring user profile information based on the request; means for transmitting data including the acquired profile information to a generative AI model; means for receiving learning materials generated by the generative AI model; means for displaying the received learning materials to the user; means for making the learning materials interactively accessible in a virtual environment; and means for allowing the user to access the learning materials using a smartphone or a head-mounted display. This enables learning materials optimized for each individual user to be provided in real time, improving learning efficiency. Furthermore, interactive access in a virtual environment enables more effective learning.

[0775] The "means for receiving a request for learning materials input by a user" is an interface for receiving request information for learning materials designated by a user on the server side.

[0776] "Means for obtaining user profile information based on a request" is a function for extracting information such as the user's learning history, comprehension ability, and personality from a database based on a received request.

[0777] "Means for sending data including the acquired profile information to the generative AI model" is a function for sending the extracted profile information to the generative AI model as input data.

[0778] "Means for receiving learning materials generated by a generative AI model" refers to a mechanism for receiving learning materials sent from a generative AI model on the server side.

[0779] The "means for displaying the received learning materials to the user" is an interface for displaying the received learning materials on the terminal used by the user.

[0780] "Means for making learning materials interactively accessible within a virtual environment" refers to functionality that allows a user to manipulate or interact with the learning materials within the virtual environment.

[0781] "Means for users to access learning materials using smartphones or head-mounted displays" refers to a function that allows users to access learning materials using devices such as smartphones or head-mounted displays.

[0782] To implement this invention, the following system may be constructed. This system receives a request for learning materials input by a user, generates optimal learning materials using a generative AI model based on the user's profile information, and displays them in real time. Furthermore, this system enables interactive access within a virtual environment, allowing users to access the learning materials using a smartphone or head-mounted display.

[0783] Hardware and software used

[0784] Hardware: Servers, smartphones, head-mounted displays

[0785] Software: Flask (Python framework), TensorFlow (AI model), SQLite (database)

[0786] Program processing explanation

[0787] First, the user's device is provided with an interface that allows them to input requests for learning materials. Once the user inputs the request, the information is sent to the server. The server then uses a database to obtain the user's profile information and extracts information such as their learning history, comprehension ability, and personality.

[0788] The server then sends the profile information to a generative AI model (using TensorFlow), which generates optimal learning materials based on the information provided. These learning materials are then sent to the server and displayed on the user's device.

[0789] Furthermore, to enable interactive access within the virtual environment, the learning materials are designed to allow users to manipulate and interact with them. Users can access the learning materials using smartphones or head-mounted displays and carry out real learning activities.

[0790] Specific examples

[0791] As a concrete example, consider the case where a parent accesses a virtual store for their child and requests "5th grade word problems." In this case, the server retrieves the child's learning history and comprehension from a database and sends the information to a generative AI model based on that. The model then generates optimal learning materials and displays them on the parent's smartphone via the server. Because the learning materials can be accessed interactively within the virtual environment, the child can effectively practice word problems using, for example, a head-mounted display.

[0792] Prompt Sentence Examples

[0793] For example, a possible prompt for a generative AI model might be:

[0794] "Mathematics, 5th grade, good at calculation problems, bad at word problems, introverted"

[0795] In this way, by implementing the present invention, it is possible to provide optimal learning materials to individual users in real time, thereby improving learning efficiency. Furthermore, interactive access in a virtual environment makes learning more effective.

[0796] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0797] Step 1:

[0798] A user inputs a request for learning materials.

[0799] Input: A learning task specified by the user on the device (e.g., a 5th grade math word problem)

[0800] How it works: A user uses a smartphone or head-mounted display interface to input a request for learning materials.

[0801] Output: Request information is sent from the terminal to the server

[0802] Step 2:

[0803] The server retrieves the user's profile information.

[0804] Input: User request information, user ID

[0805] How it works: The server connects to the database and retrieves profile information such as the user's learning history, comprehension, and personality.

[0806] Output: User profile information is retrieved.

[0807] Step 3:

[0808] The server sends the profile information to the generative AI model.

[0809] Input: Retrieved profile information

[0810] How it works: The server sends the acquired profile information to the generative AI model as input data. Specifically, it converts the profile information into an appropriate format (e.g., vector or text format) and inputs it into the model.

[0811] Output: where the input data to the model is sent

[0812] Step 4:

[0813] A generative AI model generates optimal learning materials.

[0814] Input: Input data based on profile information

[0815] How it works: The generative AI model (powered by TensorFlow) performs calculations to generate optimal learning materials based on the user's learning history, comprehension, and personality information. This calculation includes using a neural network to predict the next task.

[0816] Output: The optimal learning material is generated and sent to the server.

[0817] Step 5:

[0818] The server receives the generated learning materials and transmits them to the user's terminal.

[0819] Input: Learning material data from a generative AI model

[0820] How it works: The server receives the generated learning materials and sends them to the user's device, where they are converted into an appropriate format and rendered.

[0821] Output: The learning material data is sent to the user's device.

[0822] Step 6:

[0823] The terminal displays the learning material to the user.

[0824] Input: Learning material data sent from the server

[0825] How it works: The user's device displays the received learning materials on the screen. In the case of a smartphone, the learning materials are displayed on the touchscreen, and in the case of a head-mounted display, the learning materials are projected within the user's field of view.

[0826] Output: Users can view and manipulate learning materials.

[0827] Step 7:

[0828] Users interactively access learning materials within a virtual environment.

[0829] Input: User actions and interactions

[0830] Action: The user manipulates and interacts with the learning material in the virtual environment, for example, solving problems or entering answers. These actions are reflected in the system in real time.

[0831] Output: User operation results are recorded and reflected in the system in real time.

[0832] 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.

[0833] This invention provides a system that generates and provides customized learning materials in real time, incorporating user emotional information. In addition to conventional learning material generation systems, this system uses an emotion engine to recognize the user's emotions and provides more optimal learning materials based on that information.

[0834] Specifically, a user uses a device to input a request for learning materials. For example, an elementary school child uses a parent's smartphone to request "5th grade math practice problems." The device then sends this request to the server.

[0835] When the server receives the request, it retrieves profile information from the database based on the user's ID. This profile information includes the user's learning history, comprehension ability, personality, etc. For example, information such as "This child is good at arithmetic problems, but has difficulty with word problems" may be retrieved from the database.

[0836] The server then sends the acquired profile information to an AI model, which analyzes the user information and generates learning materials based on it. An emotion engine then joins this process. The emotion engine analyzes the user's facial expressions, voice, body temperature, heart rate, and other biometric information to assess the user's emotional state. For example, it determines whether the user is stressed, relaxed, or focused while studying.

[0837] Emotional information obtained by the emotion engine is also sent to the AI ​​model. The AI ​​model integrates and analyzes the profile information and emotional information to evaluate the user's learning interest and concentration. Based on this, it generates further optimized learning materials. For example, if the user feels stressed by written questions, it generates learning materials that will increase motivation to study by adding simple calculation problems.

[0838] The server receives the generated learning materials and then sends them to the device, which then displays them to the user. This results in the parent's smartphone displaying "5th grade math practice problems," allowing the user to begin learning.

[0839] Consider the following scenario as a concrete example. Elementary school student Child A inputs a request on his / her parent's smartphone saying, "I want word problems for fifth-grade math," and the device sends this request to a server. The server retrieves Child A's learning history from a database and sends profile information based on his / her comprehension ability and personality to an AI model. At the same time, the device's built-in camera and microphone transmit Child A's facial expressions and voice to an emotion engine, which analyzes them. The AI ​​model integrates the profile information and emotional information to generate learning materials that include word problems of optimal difficulty as well as problems with a relaxing effect. The server receives the generated learning materials and sends them to the device, which then displays them to Child A. Child A can use these learning materials to study efficiently and without stress.

[0840] In this way, the present invention provides learning materials that take into account the user's individual profile information and real-time emotional state, maximizing learning efficiency and encouraging the user to learn.

[0841] The processing flow will be explained below.

[0842] Step 1:

[0843] A user inputs a learning material request through a terminal.

[0844] A user uses a dedicated app on their device to input a request for learning materials, for example, "I want some 5th grade math practice problems."

[0845] Step 2:

[0846] The device sends a request to the server.

[0847] The device sends the user's request to the server as an HTTP POST request.

[0848] Step 3:

[0849] The server receives and parses the request.

[0850] The server receives the request from the device and analyzes the request content (e.g., "5th grade math practice problems").

[0851] Step 4:

[0852] The server retrieves the user information from the database.

[0853] Based on the request, the server retrieves the user's profile information from the database using the user ID, which includes the user's learning history, comprehension ability, personality, etc.

[0854] Step 5:

[0855] The server instructs the emotion engine to acquire biometric information of the user.

[0856] The server instructs the emotion engine to acquire biometric information such as the user's facial expression, voice, body temperature, and heart rate from sensors such as a camera and microphone built into the device.

[0857] Step 6:

[0858] The emotion engine analyzes the user's biometric information and evaluates their emotional state.

[0859] The emotion engine analyzes the acquired biometric information and evaluates the user's emotional state (e.g., stress, relaxation, concentration).

[0860] Step 7:

[0861] The server sends the acquired profile information and emotional information to the AI ​​model.

[0862] The server sends data including profile information and emotion information to the AI ​​model.

[0863] Step 8:

[0864] The AI ​​model analyzes the information and generates optimal learning materials.

[0865] The AI ​​model analyzes the user's profile information and emotional information to generate learning materials that are best suited to the user's learning. If the user is feeling stressed, the difficulty level can be adjusted or questions with a relaxing effect can be included.

[0866] Step 9:

[0867] The server receives the generated learning materials and transmits them to the terminal.

[0868] The server receives the learning materials generated from the AI ​​model and sends them to the device.

[0869] Step 10:

[0870] The terminal receives the learning material and displays it to the user.

[0871] The device receives the response from the server and displays the learning materials on the app screen. The user can then begin learning using the displayed materials.

[0872] As a result, the present invention makes it possible to provide learning materials optimized for individual users in real time based on their profile information and emotional information, thereby maximizing the user's learning efficiency and encouraging them to learn.

[0873] Example 2

[0874] 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."

[0875] Conventional learning material generation systems provide learning materials based on the user's learning history and level of understanding, but they are unable to generate learning materials that take the user's emotional state into consideration. As a result, if the user is feeling stressed or has low concentration, the system is unable to provide learning materials that are adapted to that state, which can lead to a decrease in learning efficiency and a decrease in motivation to learn.

[0876] 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.

[0877] In this invention, the server includes means for receiving a request for learning materials input by a user, means for acquiring user profile information, means for collecting biometric information such as the user's facial expression, voice, body temperature, and heart rate, means for transmitting the acquired profile information and biometric information to an emotion engine for analysis, means for transmitting data integrating the analyzed emotional information to an artificial intelligence model, means for receiving learning materials generated by the artificial intelligence model, and means for displaying the received learning materials to the user. This makes it possible to provide customized learning materials that take into account the user's learning history, level of understanding, and real-time emotional state.

[0878] "User" means a person who uses the System to request and use learning materials.

[0879] "Learning materials" refers to educational content such as workbooks and textbooks that users use for studying.

[0880] A "request" is a request sent by a user to a server through a terminal for learning materials.

[0881] "Profile information" refers to information about a user's personal information, such as their learning history, comprehension, and personality.

[0882] "Biometric information" refers to information about the user's body, such as facial expression, voice, body temperature, and heart rate.

[0883] An "emotion engine" is an algorithm or system that analyzes a user's biometric information and infers their emotional state as a result.

[0884] An "artificial intelligence model" is a system that analyzes profile information and emotional information and generates optimized learning materials based on that information.

[0885] A "server" is a computer system that receives requests from users, retrieves the necessary profile information, uses AI models to generate learning materials, and sends them to the device.

[0886] A "terminal" is a device used by a user to input requests and display learning materials.

[0887] This invention provides a system that incorporates user emotional information and generates and provides customized learning materials in real time. This system operates using the following hardware and software.

[0888] First, a user inputs a request using a device (e.g., a smartphone or tablet). For example, the user inputs a request such as "I want math practice questions for fifth graders" by voice or text. The device then sends this request to the server. Data is transmitted over a network to send the request.

[0889] When the server receives a request, it retrieves the user's profile information from the database. This profile information includes the user's learning history, comprehension, and personality. For example, it retrieves information from the database that "User A is good at calculation problems, but has difficulty with written problems." An RDBMS (e.g., MySQL, PostgreSQL) can be used as the database.

[0890] Next, the device uses the built-in camera and microphone to collect biometric information such as the user's facial expressions, voice, body temperature, and heart rate. The device sends this data to a server in real time, and an emotion engine (e.g., Microsoft Azure Emotion API, IBM Watson Tone Analyzer) is used for emotion analysis.

[0891] The server sends the biometric information to the emotion engine, which analyzes the emotional information. For example, it determines whether the user is feeling stressed, relaxed, or focused. The analysis results of the emotion engine are sent to the server, where the profile information and emotional information are integrated.

[0892] Based on the profile information and emotion information, the server sends the data to an AI model (e.g., TensorFlow, PyTorch) to generate learning materials optimized for the user. This AI model uses natural language processing (NLP) and machine learning (ML) techniques to create learning materials that best fit the user's learning needs. For example, if a user feels stressed by word problems, it can generate learning materials that include many calculation problems.

[0893] The generated learning materials are sent from the server to the terminal, which then displays them to the user, allowing the user to utilize customized learning materials that are adapted to their emotional state in real time.

[0894] As a concrete example, if elementary school student A inputs a request from his / her parent's smartphone saying, "I want some 5th grade math word problems," the following prompt is sent to the generative AI model:

[0895] Child A, an elementary school student, has requested "5th grade math word problems" from his parent's smartphone. Child A is good at calculation problems but not so good at word problems. Furthermore, Child A is feeling a bit stressed about his current learning situation. Based on this, please generate learning materials suitable for Child A.

[0896] As a result, the present invention provides learning materials that take into account the user's individual profile information and real-time emotional state, maximizing learning efficiency and encouraging the user's motivation to learn.

[0897] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0898] System program processing flow

[0899] Step 1: Fill out and submit your request

[0900] Subject: User

[0901] Actions: A user uses a terminal to input a request for learning materials, for example, "I want some 5th grade math practice problems."

[0902] Input: Learning material request (voice or text)

[0903] Output: Request data packet

[0904] Subject: Terminal

[0905] Operation: The terminal receives an input request, converts it into a data packet, and sends it to the server.

[0906] Input: User request

[0907] Output: Sending a request data packet

[0908] Step 2: Get profile information

[0909] Subject: Server

[0910] Operation: The server extracts the user ID from the received request data packet and retrieves the user's profile information from the database.

[0911] Input: Request data packet

[0912] Data processing: Extraction of user ID, database query

[0913] Output: User profile information

[0914] Example: For example, information such as "User A is good at calculation problems but has difficulty with written problems" is acquired.

[0915] Step 3: Collect and send emotion data

[0916] Subject: Terminal

[0917] How it works: The device's built-in camera and microphone collect the user's biometric information (facial expressions, voice, body temperature, heart rate, etc.).

[0918] Input: User's biometric information

[0919] Output: Biometric data packet

[0920] Example: A camera captures your facial expressions and a microphone records your voice.

[0921] Subject: Terminal

[0922] Operation: Collected biometric data is sent to a server in real time.

[0923] Input: Biometric data packet

[0924] Output: Sending biometric data

[0925] Step 4: Emotional Analysis

[0926] Subject: Server

[0927] How it works: The server sends biometric data to the emotion engine, which analyzes the emotional state.

[0928] Input: Biometric data

[0929] Data processing: Analysis using emotion engine

[0930] Output: Emotional information

[0931] Example: Assessing whether the user is stressed or relaxed.

[0932] Subject: Emotion Engine

[0933] How it works: The emotion engine analyzes the data it receives and quantifies or categorizes the user's emotional state.

[0934] Input: Biometric data

[0935] Data Computing: Applying Sentiment Analysis Algorithms

[0936] Output: Analyzed emotion information (e.g., "The user is feeling stressed")

[0937] Step 5: Sending data to the AI ​​model and generating teaching materials

[0938] Subject: Server

[0939] How it works: The profile information and analyzed emotional information are combined and sent to the AI ​​model.

[0940] Input: Profile information, emotion information

[0941] Data processing: information integration, data packet generation

[0942] Output: Integrated information data packet

[0943] Subject: AI model

[0944] Operation: Based on the integrated information, the most suitable learning materials are generated for the user.

[0945] Input: Integrated information data packet

[0946] Data calculation: Applying algorithms to generate optimal learning materials for users

[0947] Output: Generated learning materials

[0948] Step 6: Distributing the materials

[0949] Subject: Server

[0950] How it works: Receives learning materials generated by an AI model and sends them to the device.

[0951] Input: Generated learning materials

[0952] Output: Sending learning material data

[0953] Step 7: Displaying the materials

[0954] Subject: Terminal

[0955] Operation: Displays the received learning materials to the user.

[0956] Input: Learning material data

[0957] Output: Displayed learning material

[0958] Example: "Fifth grade math practice problems" are displayed on the device screen, allowing the user to begin studying.

[0959] Through these steps, users will receive customized learning materials that adapt to their emotional state in real time.

[0960] (Application example 2)

[0961] 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."

[0962] Conventional learning material provision systems provide learning materials based on a user's learning history, comprehension, and personality, but are unable to take into account the user's real-time emotional information. As a result, when a user is in a situation where they are prone to stress, their motivation and efficiency in learning may decrease. The objective of this invention is to improve motivation and achieve efficient learning by providing more optimal learning materials based on the user's emotional state.

[0963] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a request for learning materials input by a user, means for acquiring user profile information based on the request, means for transmitting data including the acquired profile information to an AI model, means for receiving learning materials generated by the AI ​​model, means for acquiring and analyzing user emotional information, means for transmitting the analyzed emotional information to the AI ​​model and generating further customized learning materials based on the analysis results, and means for displaying the received learning materials to the user. This makes it possible to integrate and analyze profile information based on the user's learning history and personality with real-time emotional information, thereby providing optimal learning materials and improving the user's motivation and efficiency in learning.

[0964] "A request for learning materials input by a user" is information that a user inputs into the system via a terminal as a request for learning materials.

[0965] "User profile information" refers to individual information about a user, such as the user's learning history, comprehension, personality, and emotional state.

[0966] An "artificial intelligence model" is a computational model that analyzes a user's profile information and emotional information and generates optimal learning materials.

[0967] "Emotion information" is information that indicates the user's real-time emotional state, obtained from facial expressions, voice, heart rate, body temperature, etc.

[0968] "Customized learning materials" are materials that are personalized based on a user's profile information and affective information.

[0969] The "display means" refers to a device or system that allows a user to visually confirm the generated learning materials.

[0970] The "means for obtaining profile information based on a request" is a system that has the function of receiving a request from a user and retrieving the user's profile information from a database in response to the request.

[0971] This invention is a system for generating and providing customized learning materials in real time that incorporates a user's emotional information. This system includes a terminal used by the user, a server that processes information, an emotion engine that analyzes emotional information, and a device for displaying the generated learning materials.

[0972] System configuration

[0973] 1. User Device:

[0974] The user device is equipped with a camera, microphone, heart rate monitor, temperature sensor, etc. This allows biometric information such as the user's facial expression, voice, heart rate, and body temperature to be acquired.

[0975] The terminal provides an interface for the user to input requests for study materials.

[0976] 2. Server:

[0977] The server receives the request sent from the user terminal and retrieves the profile information from the database.

[0978] This profile information includes the user's learning history, comprehension, personality, and emotional state.

[0979] The profile information obtained is sent to an artificial intelligence model (e.g., GPT-4).

[0980] The emotion engine uses machine learning frameworks such as TensorFlow to analyze the user's facial expressions and voice.

[0981] The server sends the analysis results from the emotion engine to the artificial intelligence model to generate optimal learning materials.

[0982] The generated learning materials are transmitted from the server to the user terminal.

[0983] 3. Emotion Engine:

[0984] The emotion engine is responsible for analyzing emotional information from the user's facial expressions, voice, etc.

[0985] Libraries such as TensorFlow and OpenCV are used for facial recognition and voice analysis.

[0986] 4. Generating and displaying learning materials:

[0987] Artificial intelligence models (e.g., GPT-4) generate optimal learning materials based on profile information and emotional information.

[0988] The generated learning materials are displayed on the user's terminal in real time, allowing the user to study efficiently.

[0989] Specific examples

[0990] For example, in the case of using a tablet installed in a bookstore or educational supply store, the following process takes place: When a user inputs a request such as "I want word problems for fifth-grade math," the tablet sends this information to a server. At the same time, the tablet uses a camera and microphone to transmit the user's face and voice to an emotion engine. The emotion engine uses TensorFlow to analyze the real-time emotion information and sends the results to a server-side AI model. The AI ​​model (e.g., GPT-4) combines the profile information and emotion information to generate customized learning materials. These materials are then sent from the server to the tablet and displayed to the user.

[0991] Example prompt sentence:

[0992] On a Friday night, User A enters a request into a tablet at an educational supply store: "I want word problems for 5th grade math." User A's past learning history indicates that he has difficulty with word problems. The emotion engine analyzes that User A is in a relaxed state.

[0993] In this way, the present invention can integrate user profile information and emotional information to provide optimized learning materials in real time, thereby improving the user's motivation and efficiency in learning.

[0994] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0995] Step 1:

[0996] The user uses a device to input a request for learning materials. Specifically, the user inputs a request such as "I want word problems for 5th grade math" using a tablet or smartphone. This request information is sent from the device to the server.

[0997] Input: User enters request for learning material.

[0998] Output: The request information is sent to the server.

[0999] Step 2:

[1000] When the server receives the request, it retrieves profile information from the database based on the user's ID. Specifically, the profile data includes information on the user's learning history, comprehension, and personality.

[1001] Input: Request information and user ID.

[1002] Output: A dataset containing profile information.

[1003] Step 3:

[1004] To obtain emotional information, the device's camera and microphone collect biometric information such as the user's facial expression, voice, heart rate, and body temperature. This biometric information is then sent to the emotion engine in real time.

[1005] Input: User's facial expression, voice, heart rate, and temperature.

[1006] Output: Biometric data is sent to the emotion engine.

[1007] Step 4:

[1008] The emotion engine analyzes biometric information to assess the user's current emotional state, using facial recognition, voice analysis, and analysis of heart rate and body temperature fluctuations to determine whether the user is relaxed, stressed, or focused.

[1009] Input: Biometric data.

[1010] Output: Parsed emotion information.

[1011] Step 5:

[1012] The server sends the acquired profile information and emotional information to an AI model (e.g., GPT-4), which then integrates this information and generates optimal learning materials based on the user's current emotional state and profile.

[1013] Input: Profile information and sentiment information.

[1014] Output: Generated customized learning materials.

[1015] Step 6:

[1016] The server receives the generated learning materials and transmits them to the user terminal.

[1017] Input: Generated customized learning materials.

[1018] Output: The learning materials are sent from the server to the device.

[1019] Step 7:

[1020] The terminal displays the learning materials received from the server to the user, allowing the user to progress with their studies using individually customized learning materials.

[1021] Input: Generated learning materials.

[1022] Output: The customized learning material displayed to the user.

[1023] 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.

[1024] 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.

[1025] 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.

[1026] [Fourth embodiment]

[1027] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1028] 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.

[1029] 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).

[1030] 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.

[1031] 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.

[1032] 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).

[1033] 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.

[1034] 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.

[1035] 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.

[1036] 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.

[1037] 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.

[1038] 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.

[1039] 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."

[1040] To specifically implement the present invention, it is conceivable to build the following system. This system generates and displays optimal learning materials in real time based on user input, and is useful in many educational situations.

[1041] In this system, a user first inputs a request for learning materials using a device. For example, an elementary school child might use their parent's smartphone to request "fifth grade math practice problems." The device then sends this request to the server.

[1042] When the server receives the request, it retrieves profile information from the database based on the user's ID. This profile information includes the user's learning history, comprehension ability, personality, etc. For example, information such as "This child is good at arithmetic problems, but has difficulty with word problems" may be retrieved from the database.

[1043] The server then sends the acquired profile information to an AI model. This AI model analyzes the user information and generates learning materials based on it. Specifically, the AI ​​model considers the user's comprehension ability and learning history to select appropriate questions. In this case, the learning materials generated will include calculation problems, with an emphasis on written questions.

[1044] The server receives the generated learning materials and then sends them to the device. The device displays the received learning materials to the user. The parent's smartphone displays "5th grade math practice problems," allowing the user to start learning.

[1045] As a concrete example, consider the following scenario: Child A, an elementary school student, inputs a request from his / her parent's smartphone saying, "I want word problems for fifth-grade math." The device sends this request to the server. The server retrieves Child A's learning history from a database and sends profile information based on his / her comprehension ability and personality to the AI ​​model. Based on the profile information, the AI ​​model generates learning materials that include many medium-difficulty word problems. The server sends the generated learning materials to the device, which displays them to the user. Child A can use these learning materials to efficiently progress through his / her studies.

[1046] In this way, the present invention provides optimal learning materials to individual users in real time, thereby improving learning efficiency.

[1047] The processing flow will be explained below.

[1048] Step 1:

[1049] The terminal accepts a user's request for learning materials.

[1050] The user opens a dedicated app on their device and enters a request for learning materials, such as "5th grade math practice problems."

[1051] Step 2:

[1052] The device sends a request to the server.

[1053] The device sends the user's request to the server as an HTTP POST request.

[1054] Step 3:

[1055] The server receives the request and retrieves the user information from the database.

[1056] The server receives a request from the terminal and retrieves the user's profile information (learning history, comprehension, personality, etc.) from the database based on the user ID.

[1057] Step 4:

[1058] The server sends the acquired user information to the AI ​​model.

[1059] The server constructs an API request containing the user information and sends the request to the AI ​​model.

[1060] Step 5:

[1061] The AI ​​model analyzes user information and generates optimal learning materials.

[1062] The AI ​​model analyzes the user information it receives and generates customized learning materials taking into account the user's comprehension ability and areas of weakness.

[1063] Step 6:

[1064] The server receives the generated learning materials and transmits them to the terminal.

[1065] The server receives the teaching materials generated from the AI ​​model and sends them to the terminal as an HTTP response.

[1066] Step 7:

[1067] The terminal receives the learning material and displays it to the user.

[1068] The device receives the response from the server and displays the learning materials on the app's UI. The user can then begin learning using the displayed materials.

[1069] Example 1

[1070] 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."

[1071] In conventional educational systems, it has been difficult to provide optimal learning materials that take into account each user's learning history, comprehension ability, and strong and weak subjects. This can lead to a decrease in the user's learning efficiency and a loss of motivation to learn. Therefore, there is a need for the development of a system that can provide each user with learning materials that meet their individual needs in real time.

[1072] 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.

[1073] In this invention, the server includes means for receiving a request for learning materials input by a user, means for acquiring user profile information, means for transmitting data including the acquired profile information to the generative AI model, means for receiving learning materials generated by the AI ​​model, and means for displaying the received learning materials to the user, thereby enabling the provision of optimal learning materials to individual users in real time.

[1074] A "user" is an individual or entity who utilizes the system to request learning materials and study using the provided materials.

[1075] A "request" is information or a request entered by a user when requesting specific study materials.

[1076] "Profile information" is information that indicates attribute data such as the user's learning history, comprehension ability, strong subjects, and weak subjects.

[1077] A "generative AI model" is an artificial intelligence algorithm that analyzes input profile information and generates optimal learning materials based on that information.

[1078] "Learning materials" are questions and learning materials for users to study, including content customized by a generative AI model.

[1079] A "terminal" is an electronic device used by a user to input requests and view learning materials, including a smartphone, tablet, or computer.

[1080] A "server" is a computer system that receives user requests, retrieves profile information, and invokes generative AI models to generate learning materials.

[1081] A "database" is an information system for storing and managing user profile information and learning history.

[1082] The present invention relates to a system for generating and displaying optimal learning materials in real time based on user input. This system operates when a user inputs a request for learning materials using a terminal and transmits the request to a server. A specific embodiment of the present invention will be described below.

[1083] First, a user uses a device (e.g., a smartphone, tablet, or computer) to input a request for learning materials. The device has a request input interface, allowing the user to specify the subject and type of problem they want to study. For example, an elementary school child might use their parent's smartphone to input, "I want practice problems for fifth-grade math."

[1084] Next, the terminal sends the request entered by the user to the server. At this time, the request data includes the user ID and the request content. The server receives this and retrieves the user's profile information from the database. The profile information includes the user's learning history, comprehension ability, strong subjects, weak subjects, etc. For example, the information might be "User ID: 12345, strong points: calculation problems, weak points: written problems."

[1085] The server then sends the acquired profile information to a generative AI model. The generative AI model is built using machine learning libraries such as TensorFlow and PyTorch to analyze the user's profile information and generate optimal learning materials based on it. In this process, the AI ​​model considers the user's strong and weak subjects and selects problems to maximize learning effectiveness. For example, it generates "practice problems that include many word problems for fifth-grade math."

[1086] The generated learning materials are then sent back to the device by the server. The device then displays the received learning materials to the user. As a specific example of how this works, "5th grade math practice problems" are displayed on the parent's smartphone. The user can use this to advance their studies.

[1087] As a concrete example, the following prompt sentence can be input to a generative AI model:

[1088] A user has the following request: "I want word problems for 5th grade math." Information obtained from the database: "I'm good at math problems, but I'm not good at word problems." Please generate optimal learning materials based on this information.

[1089] This allows the user to be provided with the most suitable learning materials in real time, thereby improving the user's learning efficiency.

[1090] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1091] Step 1:

[1092] The user inputs a request for learning materials on the device. The user inputs a request such as "I want some math practice problems for fifth graders" via a smartphone or tablet. The input request is stored on the device as text data.

[1093] Step 2:

[1094] The terminal sends a request to the server. The request data includes the user ID and the request content, and is sent to the server as an HTTP request. The input is "User ID: 12345, Request: 5th grade math practice problems," and the server receives this data.

[1095] Step 3:

[1096] The server receives the request and retrieves the user's profile information from the database. Using the received user ID, the server queries the database to retrieve the corresponding user's profile information. Specific profile information includes the user's learning history, comprehension ability, strong subjects, and weak subjects. For example, the data retrieved is "User ID: 12345, strong points: calculation problems, weak points: written problems."

[1097] Step 4:

[1098] The server sends the profile information to the generative AI model. The acquired profile information is converted to JSON format and sent to the generative AI model as an API request. The input is the profile information, which becomes the data to be analyzed by the AI ​​model.

[1099] Step 5:

[1100] The generative AI model analyzes the profile information and generates optimal learning materials. Based on the received profile information, the AI ​​model analyzes the user's comprehension ability and strong and weak subjects, and generates optimal learning materials. Specifically, based on the profile information, it selects and generates a "problem set that includes many fifth-grade math word problems." The output is the generated learning materials.

[1101] Step 6:

[1102] The server sends the generated learning materials to the device. The server then sends the learning materials received from the AI ​​model to the user's device. This is also sent as an HTTP response, and the learning materials are included in JSON format. The output is response data containing the learning materials requested by the user.

[1103] Step 7:

[1104] The device displays the learning materials to the user. The device parses the received learning materials and displays them on the screen in a user-friendly format. Specifically, "5th grade math practice problems" are displayed on the parent's smartphone, and the user can use them to advance their learning. The output is the content of the learning materials displayed on the device.

[1105] (Application example 1)

[1106] 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."

[1107] Existing learning systems face challenges in providing optimal learning materials to individual users in real time, resulting in reduced learning efficiency. Furthermore, there is a lack of customization based on individual users' learning history and comprehension, which means learning outcomes are not maximized. Furthermore, there is a lack of interactive access to learning materials in virtual environments, which limits the educational effectiveness.

[1108] 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.

[1109] In this invention, the server includes: means for receiving a request for learning materials input by a user; means for acquiring user profile information based on the request; means for transmitting data including the acquired profile information to a generative AI model; means for receiving learning materials generated by the generative AI model; means for displaying the received learning materials to the user; means for making the learning materials interactively accessible in a virtual environment; and means for allowing the user to access the learning materials using a smartphone or a head-mounted display. This enables learning materials optimized for each individual user to be provided in real time, improving learning efficiency. Furthermore, interactive access in a virtual environment enables more effective learning.

[1110] The "means for receiving a request for learning materials input by a user" is an interface for receiving request information for learning materials designated by a user on the server side.

[1111] "Means for obtaining user profile information based on a request" is a function for extracting information such as the user's learning history, comprehension ability, and personality from a database based on a received request.

[1112] "Means for sending data including the acquired profile information to the generative AI model" is a function for sending the extracted profile information to the generative AI model as input data.

[1113] "Means for receiving learning materials generated by a generative AI model" refers to a mechanism for receiving learning materials sent from a generative AI model on the server side.

[1114] The "means for displaying the received learning materials to the user" is an interface for displaying the received learning materials on the terminal used by the user.

[1115] "Means for making learning materials interactively accessible within a virtual environment" refers to functionality that allows a user to manipulate or interact with the learning materials within the virtual environment.

[1116] "Means for users to access learning materials using smartphones or head-mounted displays" refers to a function that allows users to access learning materials using devices such as smartphones or head-mounted displays.

[1117] To implement this invention, the following system may be constructed. This system receives a request for learning materials input by a user, generates optimal learning materials using a generative AI model based on the user's profile information, and displays them in real time. Furthermore, this system enables interactive access within a virtual environment, allowing users to access the learning materials using a smartphone or head-mounted display.

[1118] Hardware and software used

[1119] Hardware: Servers, smartphones, head-mounted displays

[1120] Software: Flask (Python framework), TensorFlow (AI model), SQLite (database)

[1121] Program processing explanation

[1122] First, the user's device is provided with an interface that allows them to input requests for learning materials. Once the user inputs the request, the information is sent to the server. The server then uses a database to obtain the user's profile information and extracts information such as their learning history, comprehension ability, and personality.

[1123] The server then sends the profile information to a generative AI model (using TensorFlow), which generates optimal learning materials based on the information provided. These learning materials are then sent to the server and displayed on the user's device.

[1124] Furthermore, to enable interactive access within the virtual environment, the learning materials are designed to allow users to manipulate and interact with them. Users can access the learning materials using smartphones or head-mounted displays and carry out real learning activities.

[1125] Specific examples

[1126] As a concrete example, consider the case where a parent accesses a virtual store for their child and requests "5th grade word problems." In this case, the server retrieves the child's learning history and comprehension from a database and sends the information to a generative AI model based on that. The model then generates optimal learning materials and displays them on the parent's smartphone via the server. Because the learning materials can be accessed interactively within the virtual environment, the child can effectively practice word problems using, for example, a head-mounted display.

[1127] Prompt Sentence Examples

[1128] For example, a possible prompt for a generative AI model might be:

[1129] "Mathematics, 5th grade, good at calculation problems, bad at word problems, introverted"

[1130] In this way, by implementing the present invention, it is possible to provide optimal learning materials to individual users in real time, thereby improving learning efficiency. Furthermore, interactive access in a virtual environment makes learning more effective.

[1131] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1132] Step 1:

[1133] A user inputs a request for learning materials.

[1134] Input: A learning task specified by the user on the device (e.g., a 5th grade math word problem)

[1135] How it works: A user uses a smartphone or head-mounted display interface to input a request for learning materials.

[1136] Output: Request information is sent from the terminal to the server

[1137] Step 2:

[1138] The server retrieves the user's profile information.

[1139] Input: User request information, user ID

[1140] How it works: The server connects to the database and retrieves profile information such as the user's learning history, comprehension, and personality.

[1141] Output: User profile information is retrieved.

[1142] Step 3:

[1143] The server sends the profile information to the generative AI model.

[1144] Input: Retrieved profile information

[1145] How it works: The server sends the acquired profile information to the generative AI model as input data. Specifically, it converts the profile information into an appropriate format (e.g., vector or text format) and inputs it into the model.

[1146] Output: where the input data to the model is sent

[1147] Step 4:

[1148] A generative AI model generates optimal learning materials.

[1149] Input: Input data based on profile information

[1150] How it works: The generative AI model (powered by TensorFlow) performs calculations to generate optimal learning materials based on the user's learning history, comprehension, and personality information. This calculation includes using a neural network to predict the next task.

[1151] Output: The optimal learning material is generated and sent to the server.

[1152] Step 5:

[1153] The server receives the generated learning materials and transmits them to the user's terminal.

[1154] Input: Learning material data from a generative AI model

[1155] How it works: The server receives the generated learning materials and sends them to the user's device, where they are converted into an appropriate format and rendered.

[1156] Output: The learning material data is sent to the user's device.

[1157] Step 6:

[1158] The terminal displays the learning material to the user.

[1159] Input: Learning material data sent from the server

[1160] How it works: The user's device displays the received learning materials on the screen. In the case of a smartphone, the learning materials are displayed on the touchscreen, and in the case of a head-mounted display, the learning materials are projected within the user's field of view.

[1161] Output: Users can view and manipulate learning materials.

[1162] Step 7:

[1163] Users interactively access learning materials within a virtual environment.

[1164] Input: User actions and interactions

[1165] Action: The user manipulates and interacts with the learning material in the virtual environment, for example, solving problems or entering answers. These actions are reflected in the system in real time.

[1166] Output: User operation results are recorded and reflected in the system in real time.

[1167] 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.

[1168] This invention provides a system that generates and provides customized learning materials in real time, incorporating user emotional information. In addition to conventional learning material generation systems, this system uses an emotion engine to recognize the user's emotions and provides more optimal learning materials based on that information.

[1169] Specifically, a user uses a device to input a request for learning materials. For example, an elementary school child uses a parent's smartphone to request "5th grade math practice problems." The device then sends this request to the server.

[1170] When the server receives the request, it retrieves profile information from the database based on the user's ID. This profile information includes the user's learning history, comprehension ability, personality, etc. For example, information such as "This child is good at arithmetic problems, but has difficulty with word problems" may be retrieved from the database.

[1171] The server then sends the acquired profile information to an AI model, which analyzes the user information and generates learning materials based on it. An emotion engine then joins this process. The emotion engine analyzes the user's facial expressions, voice, body temperature, heart rate, and other biometric information to assess the user's emotional state. For example, it determines whether the user is stressed, relaxed, or focused while studying.

[1172] Emotional information obtained by the emotion engine is also sent to the AI ​​model. The AI ​​model integrates and analyzes the profile information and emotional information to evaluate the user's learning interest and concentration. Based on this, it generates further optimized learning materials. For example, if the user feels stressed by written questions, it generates learning materials that will increase motivation to study by adding simple calculation problems.

[1173] The server receives the generated learning materials and then sends them to the device, which then displays them to the user. This results in the parent's smartphone displaying "5th grade math practice problems," allowing the user to begin learning.

[1174] Consider the following scenario as a concrete example. Elementary school student Child A inputs a request on his / her parent's smartphone saying, "I want word problems for fifth-grade math," and the device sends this request to a server. The server retrieves Child A's learning history from a database and sends profile information based on his / her comprehension ability and personality to an AI model. At the same time, the device's built-in camera and microphone transmit Child A's facial expressions and voice to an emotion engine, which analyzes them. The AI ​​model integrates the profile information and emotional information to generate learning materials that include word problems of optimal difficulty as well as problems with a relaxing effect. The server receives the generated learning materials and sends them to the device, which then displays them to Child A. Child A can use these learning materials to study efficiently and without stress.

[1175] In this way, the present invention provides learning materials that take into account the user's individual profile information and real-time emotional state, maximizing learning efficiency and encouraging the user to learn.

[1176] The processing flow will be explained below.

[1177] Step 1:

[1178] A user inputs a learning material request through a terminal.

[1179] A user uses a dedicated app on their device to input a request for learning materials, for example, "I want some 5th grade math practice problems."

[1180] Step 2:

[1181] The device sends a request to the server.

[1182] The device sends the user's request to the server as an HTTP POST request.

[1183] Step 3:

[1184] The server receives and parses the request.

[1185] The server receives the request from the device and analyzes the request content (e.g., "5th grade math practice problems").

[1186] Step 4:

[1187] The server retrieves the user information from the database.

[1188] Based on the request, the server retrieves the user's profile information from the database using the user ID, which includes the user's learning history, comprehension ability, personality, etc.

[1189] Step 5:

[1190] The server instructs the emotion engine to acquire biometric information of the user.

[1191] The server instructs the emotion engine to acquire biometric information such as the user's facial expression, voice, body temperature, and heart rate from sensors such as a camera and microphone built into the device.

[1192] Step 6:

[1193] The emotion engine analyzes the user's biometric information and evaluates their emotional state.

[1194] The emotion engine analyzes the acquired biometric information and evaluates the user's emotional state (e.g., stress, relaxation, concentration).

[1195] Step 7:

[1196] The server sends the acquired profile information and emotional information to the AI ​​model.

[1197] The server sends data including profile information and emotion information to the AI ​​model.

[1198] Step 8:

[1199] The AI ​​model analyzes the information and generates optimal learning materials.

[1200] The AI ​​model analyzes the user's profile information and emotional information to generate learning materials that are best suited to the user's learning. If the user is feeling stressed, the difficulty level can be adjusted or questions with a relaxing effect can be included.

[1201] Step 9:

[1202] The server receives the generated learning materials and transmits them to the terminal.

[1203] The server receives the learning materials generated from the AI ​​model and sends them to the device.

[1204] Step 10:

[1205] The terminal receives the learning material and displays it to the user.

[1206] The device receives the response from the server and displays the learning materials on the app screen. The user can then begin learning using the displayed materials.

[1207] As a result, the present invention makes it possible to provide learning materials optimized for individual users in real time based on their profile information and emotional information, thereby maximizing the user's learning efficiency and encouraging them to learn.

[1208] Example 2

[1209] 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."

[1210] Conventional learning material generation systems provide learning materials based on the user's learning history and level of understanding, but they are unable to generate learning materials that take the user's emotional state into consideration. As a result, if the user is feeling stressed or has low concentration, the system is unable to provide learning materials that are adapted to that state, which can lead to a decrease in learning efficiency and a decrease in motivation to learn.

[1211] 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.

[1212] In this invention, the server includes means for receiving a request for learning materials input by a user, means for acquiring user profile information, means for collecting biometric information such as the user's facial expression, voice, body temperature, and heart rate, means for transmitting the acquired profile information and biometric information to an emotion engine for analysis, means for transmitting data integrating the analyzed emotional information to an artificial intelligence model, means for receiving learning materials generated by the artificial intelligence model, and means for displaying the received learning materials to the user. This makes it possible to provide customized learning materials that take into account the user's learning history, level of understanding, and real-time emotional state.

[1213] "User" means a person who uses the System to request and use learning materials.

[1214] "Learning materials" refers to educational content such as workbooks and textbooks that users use for studying.

[1215] A "request" is a request sent by a user to a server through a terminal for learning materials.

[1216] "Profile information" refers to information about a user's personal information, such as their learning history, comprehension, and personality.

[1217] "Biometric information" refers to information about the user's body, such as facial expression, voice, body temperature, and heart rate.

[1218] An "emotion engine" is an algorithm or system that analyzes a user's biometric information and infers their emotional state as a result.

[1219] An "artificial intelligence model" is a system that analyzes profile information and emotional information and generates optimized learning materials based on that information.

[1220] A "server" is a computer system that receives requests from users, retrieves the necessary profile information, uses AI models to generate learning materials, and sends them to the device.

[1221] A "terminal" is a device used by a user to input requests and display learning materials.

[1222] This invention provides a system that incorporates user emotional information and generates and provides customized learning materials in real time. This system operates using the following hardware and software.

[1223] First, a user inputs a request using a device (e.g., a smartphone or tablet). For example, the user inputs a request such as "I want math practice questions for fifth graders" by voice or text. The device then sends this request to the server. Data is transmitted over a network to send the request.

[1224] When the server receives a request, it retrieves the user's profile information from the database. This profile information includes the user's learning history, comprehension, and personality. For example, it retrieves information from the database that "User A is good at calculation problems, but has difficulty with written problems." An RDBMS (e.g., MySQL, PostgreSQL) can be used as the database.

[1225] Next, the device uses the built-in camera and microphone to collect biometric information such as the user's facial expressions, voice, body temperature, and heart rate. The device sends this data to a server in real time, and an emotion engine (e.g., Microsoft Azure Emotion API, IBM Watson Tone Analyzer) is used for emotion analysis.

[1226] The server sends the biometric information to the emotion engine, which analyzes the emotional information. For example, it determines whether the user is feeling stressed, relaxed, or focused. The analysis results of the emotion engine are sent to the server, where the profile information and emotional information are integrated.

[1227] Based on the profile information and emotion information, the server sends the data to an AI model (e.g., TensorFlow, PyTorch) to generate learning materials optimized for the user. This AI model uses natural language processing (NLP) and machine learning (ML) techniques to create learning materials that best fit the user's learning needs. For example, if a user feels stressed by word problems, it can generate learning materials that include many calculation problems.

[1228] The generated learning materials are sent from the server to the terminal, which then displays them to the user, allowing the user to utilize customized learning materials that are adapted to their emotional state in real time.

[1229] As a concrete example, if elementary school student A inputs a request from his / her parent's smartphone saying, "I want some 5th grade math word problems," the following prompt is sent to the generative AI model:

[1230] Child A, an elementary school student, has requested "5th grade math word problems" from his parent's smartphone. Child A is good at calculation problems but not so good at word problems. Furthermore, Child A is feeling a bit stressed about his current learning situation. Based on this, please generate learning materials suitable for Child A.

[1231] As a result, the present invention provides learning materials that take into account the user's individual profile information and real-time emotional state, maximizing learning efficiency and encouraging the user's motivation to learn.

[1232] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1233] System program processing flow

[1234] Step 1: Fill out and submit your request

[1235] Subject: User

[1236] Actions: A user uses a terminal to input a request for learning materials, for example, "I want some 5th grade math practice problems."

[1237] Input: Learning material request (voice or text)

[1238] Output: Request data packet

[1239] Subject: Terminal

[1240] Operation: The terminal receives an input request, converts it into a data packet, and sends it to the server.

[1241] Input: User request

[1242] Output: Sending a request data packet

[1243] Step 2: Get profile information

[1244] Subject: Server

[1245] Operation: The server extracts the user ID from the received request data packet and retrieves the user's profile information from the database.

[1246] Input: Request data packet

[1247] Data processing: Extraction of user ID, database query

[1248] Output: User profile information

[1249] Example: For example, information such as "User A is good at calculation problems but has difficulty with written problems" is acquired.

[1250] Step 3: Collect and send emotion data

[1251] Subject: Terminal

[1252] How it works: The device's built-in camera and microphone collect the user's biometric information (facial expressions, voice, body temperature, heart rate, etc.).

[1253] Input: User's biometric information

[1254] Output: Biometric data packet

[1255] Example: A camera captures your facial expressions and a microphone records your voice.

[1256] Subject: Terminal

[1257] Operation: Collected biometric data is sent to a server in real time.

[1258] Input: Biometric data packet

[1259] Output: Sending biometric data

[1260] Step 4: Emotional Analysis

[1261] Subject: Server

[1262] How it works: The server sends biometric data to the emotion engine, which analyzes the emotional state.

[1263] Input: Biometric data

[1264] Data processing: Analysis using emotion engine

[1265] Output: Emotional information

[1266] Example: Assessing whether the user is stressed or relaxed.

[1267] Subject: Emotion Engine

[1268] How it works: The emotion engine analyzes the data it receives and quantifies or categorizes the user's emotional state.

[1269] Input: Biometric data

[1270] Data Computing: Applying Sentiment Analysis Algorithms

[1271] Output: Analyzed emotion information (e.g., "The user is feeling stressed")

[1272] Step 5: Sending data to the AI ​​model and generating teaching materials

[1273] Subject: Server

[1274] How it works: The profile information and analyzed emotional information are combined and sent to the AI ​​model.

[1275] Input: Profile information, emotion information

[1276] Data processing: information integration, data packet generation

[1277] Output: Integrated information data packet

[1278] Subject: AI model

[1279] Operation: Based on the integrated information, the most suitable learning materials are generated for the user.

[1280] Input: Integrated information data packet

[1281] Data calculation: Applying algorithms to generate optimal learning materials for users

[1282] Output: Generated learning materials

[1283] Step 6: Distributing the materials

[1284] Subject: Server

[1285] How it works: Receives learning materials generated by an AI model and sends them to the device.

[1286] Input: Generated learning materials

[1287] Output: Sending learning material data

[1288] Step 7: Displaying the materials

[1289] Subject: Terminal

[1290] Operation: Displays the received learning materials to the user.

[1291] Input: Learning material data

[1292] Output: Displayed learning material

[1293] Example: "Fifth grade math practice problems" are displayed on the device screen, allowing the user to begin studying.

[1294] Through these steps, users will receive customized learning materials that adapt to their emotional state in real time.

[1295] (Application example 2)

[1296] 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."

[1297] Conventional learning material provision systems provide learning materials based on a user's learning history, comprehension, and personality, but are unable to take into account the user's real-time emotional information. As a result, when a user is in a situation where they are prone to stress, their motivation and efficiency in learning may decrease. The objective of this invention is to improve motivation and achieve efficient learning by providing more optimal learning materials based on the user's emotional state.

[1298] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a request for learning materials input by a user, means for acquiring user profile information based on the request, means for transmitting data including the acquired profile information to an AI model, means for receiving learning materials generated by the AI ​​model, means for acquiring and analyzing user emotional information, means for transmitting the analyzed emotional information to the AI ​​model and generating further customized learning materials based on the analysis results, and means for displaying the received learning materials to the user. This makes it possible to integrate and analyze profile information based on the user's learning history and personality with real-time emotional information, thereby providing optimal learning materials and improving the user's motivation and efficiency in learning.

[1299] "A request for learning materials input by a user" is information that a user inputs into the system via a terminal as a request for learning materials.

[1300] "User profile information" refers to individual information about a user, such as the user's learning history, comprehension, personality, and emotional state.

[1301] An "artificial intelligence model" is a computational model that analyzes a user's profile information and emotional information and generates optimal learning materials.

[1302] "Emotion information" is information that indicates the user's real-time emotional state, obtained from facial expressions, voice, heart rate, body temperature, etc.

[1303] "Customized learning materials" are materials that are personalized based on a user's profile information and affective information.

[1304] The "display means" refers to a device or system that allows a user to visually confirm the generated learning materials.

[1305] The "means for obtaining profile information based on a request" is a system that has the function of receiving a request from a user and retrieving the user's profile information from a database in response to the request.

[1306] This invention is a system for generating and providing customized learning materials in real time that incorporates a user's emotional information. This system includes a terminal used by the user, a server that processes information, an emotion engine that analyzes emotional information, and a device for displaying the generated learning materials.

[1307] System configuration

[1308] 1. User Device:

[1309] The user device is equipped with a camera, microphone, heart rate monitor, temperature sensor, etc. This allows biometric information such as the user's facial expression, voice, heart rate, and body temperature to be acquired.

[1310] The terminal provides an interface for the user to input requests for study materials.

[1311] 2. Server:

[1312] The server receives the request sent from the user terminal and retrieves the profile information from the database.

[1313] This profile information includes the user's learning history, comprehension, personality, and emotional state.

[1314] The profile information obtained is sent to an artificial intelligence model (e.g., GPT-4).

[1315] The emotion engine uses machine learning frameworks such as TensorFlow to analyze the user's facial expressions and voice.

[1316] The server sends the analysis results from the emotion engine to the artificial intelligence model to generate optimal learning materials.

[1317] The generated learning materials are transmitted from the server to the user terminal.

[1318] 3. Emotion Engine:

[1319] The emotion engine is responsible for analyzing emotional information from the user's facial expressions, voice, etc.

[1320] Libraries such as TensorFlow and OpenCV are used for facial recognition and voice analysis.

[1321] 4. Generating and displaying learning materials:

[1322] Artificial intelligence models (e.g., GPT-4) generate optimal learning materials based on profile information and emotional information.

[1323] The generated learning materials are displayed on the user's terminal in real time, allowing the user to study efficiently.

[1324] Specific examples

[1325] For example, in the case of using a tablet installed in a bookstore or educational supply store, the following process takes place: When a user inputs a request such as "I want word problems for fifth-grade math," the tablet sends this information to a server. At the same time, the tablet uses a camera and microphone to transmit the user's face and voice to an emotion engine. The emotion engine uses TensorFlow to analyze the real-time emotion information and sends the results to a server-side AI model. The AI ​​model (e.g., GPT-4) combines the profile information and emotion information to generate customized learning materials. These materials are then sent from the server to the tablet and displayed to the user.

[1326] Example prompt sentence:

[1327] On a Friday night, User A enters a request into a tablet at an educational supply store: "I want word problems for 5th grade math." User A's past learning history indicates that he has difficulty with word problems. The emotion engine analyzes that User A is in a relaxed state.

[1328] In this way, the present invention can integrate user profile information and emotional information to provide optimized learning materials in real time, thereby improving the user's motivation and efficiency in learning.

[1329] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1330] Step 1:

[1331] The user uses a device to input a request for learning materials. Specifically, the user inputs a request such as "I want word problems for 5th grade math" using a tablet or smartphone. This request information is sent from the device to the server.

[1332] Input: User enters request for learning material.

[1333] Output: The request information is sent to the server.

[1334] Step 2:

[1335] When the server receives the request, it retrieves profile information from the database based on the user's ID. Specifically, the profile data includes information on the user's learning history, comprehension, and personality.

[1336] Input: Request information and user ID.

[1337] Output: A dataset containing profile information.

[1338] Step 3:

[1339] To obtain emotional information, the device's camera and microphone collect biometric information such as the user's facial expression, voice, heart rate, and body temperature. This biometric information is then sent to the emotion engine in real time.

[1340] Input: User's facial expression, voice, heart rate, and temperature.

[1341] Output: Biometric data is sent to the emotion engine.

[1342] Step 4:

[1343] The emotion engine analyzes biometric information to assess the user's current emotional state, using facial recognition, voice analysis, and analysis of heart rate and body temperature fluctuations to determine whether the user is relaxed, stressed, or focused.

[1344] Input: Biometric data.

[1345] Output: Parsed emotion information.

[1346] Step 5:

[1347] The server sends the acquired profile information and emotional information to an AI model (e.g., GPT-4), which then integrates this information and generates optimal learning materials based on the user's current emotional state and profile.

[1348] Input: Profile information and sentiment information.

[1349] Output: Generated customized learning materials.

[1350] Step 6:

[1351] The server receives the generated learning materials and transmits them to the user terminal.

[1352] Input: Generated customized learning materials.

[1353] Output: The learning materials are sent from the server to the device.

[1354] Step 7:

[1355] The terminal displays the learning materials received from the server to the user, allowing the user to progress with their studies using individually customized learning materials.

[1356] Input: Generated learning materials.

[1357] Output: The customized learning material displayed to the user.

[1358] 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.

[1359] 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.

[1360] 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 robot 414.

[1361] 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.

[1362] 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.

[1363] 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.

[1364] 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).

[1365] 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.

[1366] 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."

[1367] 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.

[1368] 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).

[1369] 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.

[1370] 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.

[1371] 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.

[1372] 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.

[1373] 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.

[1374] 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.

[1375] 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.

[1376] 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.

[1377] 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.

[1378] 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.

[1379] The following is further disclosed regarding the above embodiment.

[1380] (Claim 1)

[1381] means for receiving a request for learning material input by a user;

[1382] means for obtaining user profile information based on the request;

[1383] means for transmitting data including the obtained profile information to an artificial intelligence model;

[1384] means for receiving learning materials generated by the artificial intelligence model;

[1385] means for displaying the received learning material to a user;

[1386] A system including:

[1387] (Claim 2)

[1388] 2. The system according to claim 1, wherein the user profile information includes the user's learning history, comprehension ability, personality, etc.

[1389] (Claim 3)

[1390] 2. The system according to claim 1, wherein the artificial intelligence model analyzes user information and generates optimal learning materials based on the analysis results.

[1391] "Example 1"

[1392] (Claim 1)

[1393] means for receiving a request for learning material input by a user;

[1394] means for obtaining user profile information based on the request;

[1395] means for transmitting data including the obtained profile information to a generative AI model;

[1396] means for receiving learning materials generated by the generative AI model;

[1397] means for displaying the received learning material to a user;

[1398] A system including:

[1399] (Claim 2)

[1400] 2. The system according to claim 1, wherein the user profile information includes the user's learning history, comprehension ability, strong subjects, weak subjects, etc.

[1401] (Claim 3)

[1402] The system according to claim 1, characterized in that the generative AI model analyzes user information and generates optimal learning materials based on the analysis results.

[1403] "Application Example 1"

[1404] (Claim 1)

[1405] means for receiving a request for learning material input by a user;

[1406] means for obtaining user profile information based on the request;

[1407] means for transmitting data including the obtained profile information to a generative AI model;

[1408] means for receiving learning materials generated by the generative AI model;

[1409] means for displaying the received learning material to a user;

[1410] means for making said learning materials interactively accessible within a virtual environment;

[1411] A means for a user to access the learning materials using a smartphone or a head-mounted display;

[1412] A system including:

[1413] (Claim 2)

[1414] 2. The system according to claim 1, wherein the user profile information includes the user's learning history, comprehension ability, personality, etc.

[1415] (Claim 3)

[1416] The system according to claim 1, characterized in that the generative AI model analyzes user information and generates optimal learning materials based on the analysis results.

[1417] "Example 2: Combining Emotion Engines"

[1418] (Claim 1)

[1419] means for receiving a request for learning material input by a user;

[1420] means for obtaining user profile information based on the request;

[1421] A means for collecting biometric information such as the user's facial expression, voice, body temperature, and heart rate;

[1422] means for transmitting the acquired profile information and biological information to an emotion engine for analysis;

[1423] means for transmitting data integrating the analyzed emotion information to an artificial intelligence model;

[1424] means for receiving learning materials generated by the artificial intelligence model;

[1425] means for displaying the received learning material to a user;

[1426] A system including:

[1427] (Claim 2)

[1428] 2. The system of claim 1, wherein the user profile information includes the user's learning history, comprehension, and personality.

[1429] (Claim 3)

[1430] 2. The system according to claim 1, wherein the artificial intelligence model analyzes user information and emotional information and generates optimal learning materials based on the analysis results.

[1431] "Application example 2 when combining emotion engines"

[1432] (Claim 1)

[1433] means for receiving a request for learning material input by a user;

[1434] means for obtaining user profile information based on the request;

[1435] means for transmitting data including the obtained profile information to an artificial intelligence model;

[1436] means for receiving learning materials generated by the artificial intelligence model;

[1437] A means for acquiring and analyzing user emotion information;

[1438] means for transmitting the analyzed emotion information to the artificial intelligence model and generating further customized learning materials based on the analysis results;

[1439] means for displaying the received learning material to a user;

[1440] A system including:

[1441] (Claim 2)

[1442] 2. The system of claim 1, wherein the user profile information includes the user's learning history, comprehension, personality, and emotional state.

[1443] (Claim 3)

[1444] 2. The system according to claim 1, wherein the artificial intelligence model analyzes user information and emotional information and generates optimal learning materials based on the analysis results. [Explanation of symbols]

[1445] 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 receiving a request for learning material input by a user; means for obtaining user profile information based on the request; means for transmitting data including the obtained profile information to an artificial intelligence model; means for receiving learning materials generated by the artificial intelligence model; means for displaying the received learning material to a user; A system including:

2. 2. The system according to claim 1, wherein the user profile information includes the user's learning history, comprehension ability, personality, etc.

3. 2. The system according to claim 1, wherein the artificial intelligence model analyzes user information and generates optimal learning materials based on the analysis results.

Images