System

Abstract

To provide a system.SOLUTION: A system includes: means for providing an explanation using a generative AI model that has learned curriculum guidelines; means for marking corrections to description questions; means for providing an explanation to a learner and performing a comprehension level check by asking questions to confirm a comprehension level after providing the explanation; means for acquiring a study log that is a record of the learner's learning activities, analyzing the results of the comprehension level check and the learner's past study log, and suggesting the next content to be studied and timing of studying; an emotion engine that recognizes the learner's emotions; means for reflecting the recognized emotions in the curriculum guidelines; means for inputting a question from the learner into the generative AI model and then generating an explanation for the question; means for providing the generated explanation to the learner; means for recognizing the learner's emotions; and means for providing additional explanations based on the emotions.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional learning support systems have the problem of being unable to provide sufficient explanations for the various questions that learners have, and also have the problem of making it difficult to immediately grade written questions or check students' understanding. [Means for solving the problem]

[0005] As a means for solving this problem, the system of the present invention includes: means for providing explanations using a generative AI model that has learned curriculum guidelines; means for grading corrections to written questions; means for providing explanations to learners and conducting comprehension checks by asking questions to confirm their level of comprehension after providing the explanations; means for acquiring a study log that is a record of the learning activities conducted by the learner, analyzing the results of the comprehension check and the learner's past study logs, and suggesting the next content to study and the timing of studying; an emotion engine that recognizes the learner's emotions; means for reflecting the recognized emotions in learning guidance; means for generating an explanation for a question from the learner by inputting the question from the learner into the generative AI model; means for providing the generated explanation to the learner; means for recognizing the learner's emotions; and means for providing additional explanations based on the emotions. [Brief explanation of the drawings]

[0006] [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. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] 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.

[0008] First, the terms used in the following description will be explained.

[0009] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] 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.

[0011] 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.

[0012] 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.

[0013] 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."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] The system of the present invention uses generative AI that has learned the curriculum guidelines to provide detailed and extensive explanations to questions from learners. Specifically, when a learner asks a question about a math problem, the generative AI generates a detailed explanation based on the curriculum guidelines and provides it to the learner.

[0029] "Example 2"

[0030] Furthermore, the system of the present invention has a function of instantly scoring essay questions submitted by learners. Specifically, when a learner submits an English composition, the system scores the composition and provides immediate feedback.

[0031] "Example 3"

[0032] Furthermore, the system of the present invention has the function of confirming the learner's level of understanding by combining explanations and comprehension checks. Specifically, the system poses questions to confirm the learner's level of understanding for the explanations provided by the generative AI. The learner's level of understanding is confirmed by answering these questions.

[0033] "Example 4"

[0034] Furthermore, the system of the present invention has the function of acquiring a learner's study log and scheduling the study by referring to the results of the comprehension check. Specifically, the learner records the amount of time and content of study for each day as a log, and the next study schedule is automatically generated based on the log and the results of the comprehension check.

[0035] The processing flow of each embodiment will be described below.

[0036] "Example 1"

[0037] Step 1: The learner types in a question about a math problem.

[0038] Step 2: The system uses generative AI that has learned the curriculum guidelines to generate detailed explanations.

[0039] Step 3: The generated explanation is provided to the learner, who then refers to it to further their learning.

[0040] "Example 2"

[0041] Step 1: Learners submit their English compositions to the system.

[0042] Step 2: The system grades the submitted essay and generates feedback along with the grade.

[0043] Step 3: The generated feedback is provided to the learner, who then refers to it to further their learning.

[0044] "Example 3"

[0045] Step 1: The system asks questions to confirm the level of understanding of the explanation provided by the generative AI.

[0046] Step 2: Learners answer the questions posed.

[0047] Step 3: The system evaluates the learner's answers to verify their understanding.

[0048] "Example 4"

[0049] Step 1: Learners log their daily study time and learning content into the system.

[0050] Step 2: The system automatically generates the next learning schedule based on the learner's log and the results of the comprehension check.

[0051] Step 3: The generated learning schedule is provided to the learner, who then follows the schedule.

[0052] Example 1

[0053] Next, a description will be given of Example 1 of Form 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."

[0054] In conventional learning support systems, learners had to refer to multiple learning materials to obtain detailed explanations on a specific field, making efficient learning difficult. Furthermore, correction of essay questions, comprehension checks, and learning progress management were often done manually, placing a heavy burden on learners. Furthermore, when learners had questions, it was difficult to obtain detailed explanations immediately, which led to a decline in the quality of their learning.

[0055] 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.

[0056] In this invention, the server includes means for providing detailed and extensive explanations by a generative AI that has studied the curriculum guidelines, means for instantly marking corrections to written questions, means for providing explanations and comprehension checks, means for acquiring study logs and scheduling by referring to comprehension checks, means for receiving questions from users and generating and inputting prompt sentences to the generative AI model, means for receiving explanations from the generative AI model and providing them to users, and means for sending questions from the user's terminal and receiving and displaying explanations. This allows learners to efficiently obtain detailed explanations, automates corrections of written questions, comprehension checks, and learning progress management, and improves the quality of learning.

[0057] "Course of Study" is an official guideline that defines the educational content and learning objectives provided by educational institutions.

[0058] "Generative AI" is artificial intelligence that uses natural language processing technology to generate new text based on input text.

[0059] "Detailed and extensive explanation" means providing in-depth explanations of a particular topic and a wide range of related information.

[0060] "Written question correction" is the process of evaluating the answers written by learners and indicating whether they are correct or incorrect and what areas need improvement.

[0061] "Instant grading" means evaluating answers submitted by learners in real time and returning results quickly.

[0062] "Explanation and comprehension check" means providing learners with an explanation and conducting tests and questions to check their understanding of the content.

[0063] "Study logging" means recording a learner's learning activities and progress.

[0064] "Scheduling" means creating a study plan for learners and managing their time to progress efficiently.

[0065] "Receiving a question from a user" means receiving a question posed to the system by a learner.

[0066] "Generating and inputting a prompt sentence to a generative AI model" means creating an input sentence for the generative AI to generate an explanation based on the received question and passing it to the AI.

[0067] "Receiving commentary from a generative AI model" means receiving commentary generated by a generative AI.

[0068] "Providing to the user" means displaying the received commentary to the learner and making it available for use.

[0069] "Sending a question from the user's terminal" means sending a question to the system from the device used by the learner.

[0070] "Receiving and displaying explanations" means displaying the explanations returned from the system on the learner's device.

[0071] This invention is a system that uses generative AI that has learned curriculum guidelines to provide detailed and extensive explanations in response to questions from learners. Specific embodiments of this system are described below.

[0072] Server Roles

[0073] The server hosts a generative AI model that has learned the curriculum guidelines. This generative AI model is, for example, a model with advanced natural language processing technology. The server receives a question from a user and generates a prompt sentence to input the question into the generative AI model. The generative AI model generates a detailed explanation based on the prompt sentence and returns the explanation to the server. The server provides the generated explanation to the user.

[0074] Device Role

[0075] The terminal is a device used by the learner, such as a PC or smartphone. The learner uses the terminal to input questions about the learning content. The terminal sends the questions to the server, receives and displays the explanations returned from the server, and allows the learner to view detailed explanations and advance their learning.

[0076] User Roles

[0077] The user is a learner, such as a high school or university student. The user uses a terminal to input questions about the content they are studying. The questions input by the user are sent to the server via the terminal. The server returns an explanation to the user, which the user can use to help with their studies.

[0078] Specific examples

[0079] Example 1

[0080] If a user asks, "What are the basic concepts of differentiation?", the following prompt sentence is input to the generative AI model:

[0081] Example prompt sentence:

[0082] "Please teach me the basic concepts of differentiation."

[0083] The server inputs this prompt into a generative AI model, which generates an explanation like this:

[0084] An example of a generated commentary:

[0085] "Differentiation is a mathematical technique for determining the rate of change of a function. Specifically, it shows how the output value of a function changes when the input value changes slightly. For example, the derivative of a function f(x) is expressed as f'(x), which shows the slope of f(x)."

[0086] Example 2

[0087] If a user asks, "What are some applications of integrals?", the following prompt sentence is input to the generative AI model:

[0088] Example prompt sentence:

[0089] "Please give me some examples of applications of integrals."

[0090] The server inputs this prompt into a generative AI model, which generates an explanation like this:

[0091] An example of a generated commentary:

[0092] "Integrals are widely used to calculate areas and volumes. For example, integrals are used to calculate the area under a curve or the volume of a solid of revolution. For example, integrals are used to calculate the area of ​​the region enclosed by the curve y = x^2 and the x-axis."

[0093] In this way, the system of the present invention supports learning by providing detailed and extensive explanations in response to questions from learners.

[0094] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0095] Step 1:

[0096] The user uses the terminal to input questions about the learning content.

[0097] Specific operation: The user enters a question into the input form on the terminal and clicks the send button.

[0098] Input: A question typed in by the user (e.g., "What are the basic concepts of differentiation?")

[0099] Output: The HTTP request generated by the device

[0100] Step 2:

[0101] The terminal sends the user's question to the server.

[0102] Specific operation: The terminal creates an HTTP request and sends it to the server.

[0103] Input: The question entered by the user

[0104] Output: HTTP request sent to the server

[0105] Step 3:

[0106] The server receives the user's question sent from the terminal.

[0107] Specific operation: The server receives the HTTP request and analyzes the question.

[0108] Input: HTTP request sent from the terminal

[0109] Output: Parsed question

[0110] Step 4:

[0111] Based on the received question, the server generates a prompt sentence to be input into the generative AI model.

[0112] Specific operation: The server converts the question content into an appropriate format and passes it to the generative AI model.

[0113] Input: Parsed question content

[0114] Output: Generated prompt sentence (e.g., "Please teach me the basic concepts of differentiation")

[0115] Step 5:

[0116] The server inputs the generated prompt sentence into the generative AI model.

[0117] Specific operation: The server sends a prompt to the generative AI model via the API.

[0118] Input: Generated prompt text

[0119] Output: Input to a generative AI model

[0120] Step 6:

[0121] The generative AI model generates detailed explanations based on the prompt.

[0122] Specific operation: The generative AI model uses internal learning data and algorithms to generate an explanation and send it back to the server.

[0123] Input: Input to the generative AI model (prompt sentence)

[0124] Output: Generated commentary

[0125] Step 7:

[0126] The server receives the generated commentary and sends it to the terminal.

[0127] Specific operation: The server returns the explanation to the terminal as an HTTP response.

[0128] Input: Generated commentary

[0129] Output: HTTP response sent to the device

[0130] Step 8:

[0131] The terminal receives the commentary returned from the server.

[0132] Specific operation: The terminal receives the HTTP response and analyzes the explanatory content.

[0133] Input: HTTP response sent from the server

[0134] Output: Parsed commentary

[0135] Step 9:

[0136] The terminal displays the received explanation to the user.

[0137] Specific behavior: Updates the view to display the description in the device UI.

[0138] Input: Parsed commentary

[0139] Output: A description that is displayed to the user

[0140] Step 10:

[0141] The user can understand the received explanation and use it to help with their studies.

[0142] Specific actions: The user reads the explanation and takes notes as needed to progress through the learning process.

[0143] Input: The description displayed to the user

[0144] Output: User understanding and learning progression

[0145] (Application example 1)

[0146] Next, a description will be given of Application Example 1 of Embodiment 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."

[0147] With conventional learning systems, it was difficult for learners to receive detailed and comprehensive explanations immediately when they asked questions, and they often did not provide appropriate feedback or scheduling based on the learner's level of understanding. This led to problems such as reduced learning efficiency and a loss of motivation to learn. Furthermore, even in brick-and-mortar cram schools and educational facilities, it was difficult to provide prompt and accurate explanations to individual questions.

[0148] 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.

[0149] In this invention, the server includes a means for providing detailed and extensive explanations by a generative AI that has studied the curriculum guidelines, a means for instantly marking corrections to written questions, a means for providing explanations and checking comprehension, a means for acquiring study logs and scheduling by referring to comprehension checks, a means for inputting questions from learners, a means for generating explanations using a generative AI model, and a means for displaying the generated explanations to the learner. This allows learners to instantly receive detailed and extensive explanations when they ask questions, and enables appropriate feedback and scheduling according to the learner's level of understanding.

[0150] The "Course of Study" is a set of teaching standards that systematically compile the knowledge and skills that learners should acquire at educational institutions.

[0151] "Generative AI" is artificial intelligence that generates new information or commentary based on given data or prompts.

[0152] A "detailed and wide-ranging explanation" is an explanation that provides a deep and multifaceted view of a specific question.

[0153] "Written question correction" is the process of evaluating the answers written by learners and indicating whether they are correct or incorrect and what areas need improvement.

[0154] A "comprehension check" is a test or question that assesses how well a learner has understood the content.

[0155] "Scheduling" refers to the process of creating a learner's study plan and managing time to progress efficiently.

[0156] "Means for inputting questions from learners" refers to an interface that allows learners to input doubts or queries into the system.

[0157] "Means for generating explanations using a generative AI model" refers to a process of automatically creating explanations for learners' questions using generative AI.

[0158] "Means for displaying the generated explanation to the learner" refers to an interface for visually providing the learner with the explanation created by the generative AI.

[0159] The system for implementing this invention uses generative AI that has learned the curriculum guidelines to provide detailed and extensive explanations to questions from learners. The system consists of a server and a terminal, and operates as follows.

[0160] Hardware and software used

[0161] Hardware: Servers, smartphones, tablets, smart glasses

[0162] Software: Python, OpenAI® API

[0163] Data processing and calculation

[0164] Server Processing

[0165] The server receives questions from learners and generates explanations using a generative AI model. Specifically, the process is as follows:

[0166] 1. Entering a question: The learner enters a question using a device (smartphone, tablet, smart glasses).

[0167] 2. Prompt generation: The server generates a prompt based on the input question. The prompt is an instruction for the generative AI model to generate an explanation.

[0168] 3. Calling the generative AI model: The server uses the OpenAI API to send a prompt to the generative AI model (e.g., GPT-3 (registered trademark)) to generate an explanation.

[0169] 4. Acquisition and display of explanation: The server acquires the generated explanation and sends it to the terminal, which visually displays the explanation to the learner.

[0170] Specific examples

[0171] If a learner asks, "What is the formula for solving a quadratic equation?", the server generates the following prompt:

[0172] Based on the curriculum guidelines, please provide a detailed explanation for the following mathematics problem.

[0173] Question: What is the formula for solving a quadratic equation?

[0174] Description:

[0175] Based on this prompt, the generative AI model generates a detailed explanation, which the server sends to the learner's device, where the learner can view the explanation on their device screen.

[0176] summary

[0177] This system allows learners to instantly receive detailed and comprehensive explanations when they ask questions. It also enables appropriate feedback and scheduling based on the learner's level of understanding. This is expected to improve learning efficiency and maintain motivation to learn.

[0178] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0179] Step 1:

[0180] The user uses the terminal to enter a question.

[0181] Input: A question that the user types into the terminal (e.g., "What is the formula for solving a quadratic equation?")

[0182] Output: Question data entered on the terminal

[0183] How it works: A user uses a smartphone, tablet, or smart glasses to enter a question in text format. The device receives this input and prepares it to be sent to the server.

[0184] Step 2:

[0185] The terminal transmits the question data to the server.

[0186] Input: Question data entered into the terminal

[0187] Output: Question data sent to the server

[0188] Specific operation: The device sends the question data entered by the user to the server. HTTP or HTTPS is used as the communication protocol.

[0189] Step 3:

[0190] The server receives the question data and generates a prompt.

[0191] Input: Question data sent to the server

[0192] Output: Generated prompt statement

[0193] Specific operation: The server analyzes the received question data and creates a prompt to allow the generative AI model to generate an explanation. For example, it generates a prompt in the format "Please provide a detailed explanation for the following math problem based on the curriculum guidelines. Problem: Please tell me the formula for solving a quadratic equation. Explanation:"

[0194] Step 4:

[0195] The server generates commentary using a generative AI model.

[0196] Input: Generated prompt statement

[0197] Output: Generated commentary data

[0198] How it works: The server uses the OpenAI API to send a prompt to a generative AI model (e.g., GPT-3). The generative AI model generates a detailed explanation based on the prompt and returns the result to the server.

[0199] Step 5:

[0200] The server transmits the generated commentary data to the terminal.

[0201] Input: Generated commentary data

[0202] Output: Commentary data sent to the terminal

[0203] Specific operation: The server receives the generated commentary data and sends it to the user's device. HTTP or HTTPS is used as the communication protocol.

[0204] Step 6:

[0205] The terminal receives the commentary data and displays it to the user.

[0206] Input: Commentary data sent to the terminal

[0207] Output: Explanation displayed on the terminal

[0208] Specific operation: The device analyzes the commentary data received from the server and visually displays it to the user, who can then check the commentary on the device screen.

[0209] Example 2

[0210] Next, a description will be given of Example 2 of Form 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."

[0211] Conventional learning systems have the problem that it takes time to grade essay questions submitted by learners, making it difficult to receive immediate feedback. Furthermore, learners cannot quickly check the evaluation results of their own writing and areas for improvement, which reduces learning efficiency. Furthermore, there is a lack of effective means for providing explanations and checking comprehension, making it difficult to accurately grasp learners' levels of comprehension.

[0212] 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.

[0213] In this invention, the server includes means for a user to submit an English composition from a terminal, means for the terminal to send composition data to the server, means for the server to receive the composition data and perform preprocessing, means for the server to send a prompt to the generative AI model and request evaluation of the composition, means for the generative AI model to evaluate the composition and generate a score and feedback, means for the server to receive the generated feedback and send it to the terminal, and means for the terminal to display the feedback to the user. This makes it possible to instantly score written questions submitted by learners and provide rapid feedback.

[0214] "Course of Study" is an official guideline that defines the educational content and learning objectives provided by educational institutions.

[0215] "Generative AI" is a system that generates text and data using artificial intelligence technology.

[0216] "Explanation" is a detailed and easy-to-understand explanation of a particular topic or issue.

[0217] A "comprehension check" is a test or question that assesses how well a learner understands a particular piece of content.

[0218] "Scheduling" refers to the process of creating a learner's study plan and managing time to progress efficiently.

[0219] A "terminal" is a device used by a user to access the system.

[0220] A "server" is a computer system that processes data and provides services to other devices over a network.

[0221] "Preprocessing" is the initial stage of processing to convert data into a format that is easier to analyze and process.

[0222] A "generative AI model" is an algorithm or system that uses artificial intelligence techniques to generate text or data.

[0223] A "prompt" is an instruction entered into a generative AI model to make it perform a specific task.

[0224] "Feedback" refers to the evaluation and improvement information provided to learners regarding their submitted content.

[0225] This invention is a system that instantly grades and provides feedback on English essays submitted by learners. The system allows users to submit English essays using their terminals, and the server processes and evaluates the essays. Specifically, the system uses the following hardware and software:

[0226] Hardware and software used

[0227] Device: The device on which a user enters and submits their essay. Examples include a computer, tablet, or smartphone.

[0228] Server: A computer system that receives and processes essay data. A server with a high-performance processor and sufficient memory is preferable.

[0229] Natural language processing library: Software for preprocessing text. Specifically, we use spaCy.

[0230] Generative AI model: An artificial intelligence model for evaluating essays. Specifically, we use OpenAI's GPT-3.

[0231] Program processing

[0232] A user submits an English essay to the system using a terminal. The terminal sends the essay data to the server through a web browser. The server first preprocesses the received essay data. This preprocessing includes text tokenization, part-of-speech tagging, and dependency analysis using spaCy.

[0233] The server then sends prompts to the generative AI model GPT-3 to evaluate the essay. The prompts include evaluation criteria and examples of expected answers. GPT-3 then evaluates the essay and generates a score and feedback.

[0234] The generated feedback is sent from the server to the terminal and displayed immediately to the user, allowing the user to immediately check the evaluation results of their essay and areas for improvement.

[0235] Specific examples

[0236] For example, suppose a user submits the following English composition:

[0237] I went to the park yesterday. It was very fun and I played with my friends.

[0238] The server receives this composition, preprocesses it using spaCy, and then sends the following prompt to GPT-3:

[0239] Evaluate the following English composition based on grammar, coherence, and vocabulary. Provide a score out of 10 and give constructive feedback:

[0240] "I went to the park yesterday. It was very fun and I played with my friends."

[0241] GPT-3 evaluates your writing and generates feedback such as:

[0242] Score: 8 / 10

[0243] Feedback: The composition is generally well-written with good grammar and coherence. However, "very fun" could be improved to "a lot of fun" for better expression. Additionally, consider adding more details about what activities you did with your friends.

[0244] This feedback is sent from the server to the terminal and displayed to the user, who can use it to improve their writing.

[0245] In this way, it is possible to instantly mark the essay questions submitted by the learner and provide quick feedback.

[0246] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0247] Step 1:

[0248] A user submits an English composition from a terminal.

[0249] A user accesses the system interface using a web browser, enters an English composition in the text box on the interface, and clicks the "Submit" button. The input is the composition text entered by the user, and the output is the composition data sent to the terminal.

[0250] Step 2:

[0251] The terminal transmits the composition data to the server.

[0252] The terminal converts the composition data entered by the user into JSON format and sends it to the server using an HTTP POST request. The input is the composition text entered by the user, and the output is the JSON-formatted composition data sent to the server.

[0253] Step 3:

[0254] The server receives the composition data and performs preprocessing.

[0255] The server parses the received essay data and performs text tokenization, part-of-speech tagging, and dependency analysis using a natural language processing library (e.g., spaCy). The input is the JSON-formatted essay data sent to the server, and the output is the preprocessed text data.

[0256] Step 4:

[0257] The server sends a prompt to the generative AI model, asking it to evaluate the essay.

[0258] The server generates a prompt to be sent to the generative AI model (e.g., GPT-3) based on the preprocessed text. The prompt includes evaluation criteria and examples of expected answers. The server sends this prompt to the generative AI model's API via an HTTP request. The input is the preprocessed text data and the prompt, and the output is the prompt sent to the generative AI model.

[0259] Step 5:

[0260] A generative AI model evaluates the essay and generates a score and feedback.

[0261] The generative AI model evaluates the essay based on the received prompt and generates a score and feedback, for example, evaluating it in terms of grammar, vocabulary, structure, etc. The input is the prompt sent to the generative AI model, and the output is the generated score and feedback.

[0262] Step 6:

[0263] The server receives the generated feedback and transmits it to the terminal.

[0264] The server receives the scores and feedback returned from the generative AI model, converts them into JSON format, and sends them to the device. The input is the scores and feedback returned from the generative AI model, and the output is the JSON-formatted feedback data sent to the device.

[0265] Step 7:

[0266] The device displays the feedback to the user.

[0267] The device analyzes the received feedback and displays it in a user-friendly format, allowing the user to instantly check the evaluation results and areas for improvement of their essay. The input is the JSON-formatted feedback data sent to the device, and the output is the feedback information displayed to the user.

[0268] (Application example 2)

[0269] Next, a description will be given of Application Example 2 of Form 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."

[0270] Conventional learning systems have the problem that learners do not receive immediate feedback on the essay questions they submit, which reduces learning efficiency. Also, because it takes time to grade essays, it is difficult for learners to quickly identify their weaknesses. Furthermore, because explanations and comprehension checks are not provided sufficiently, it is difficult to accurately evaluate a learner's level of comprehension.

[0271] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0272] In this invention, the server includes: a means for providing detailed and extensive explanations by a generative AI that has studied the curriculum guidelines; a means for instantly grading essay corrections; a means for providing explanations and comprehension checks; a means for recording study logs and scheduling by referencing comprehension checks; and a means for generating prompt sentences based on essays entered or uploaded by learners and providing instant grading results and feedback using a generative AI model. This allows for instant feedback on essay questions submitted by learners, improving learning efficiency. Furthermore, because essays are quickly graded, learners can quickly identify their weaknesses. Furthermore, because explanations and comprehension checks are performed thoroughly, it is possible to accurately evaluate a learner's level of comprehension.

[0273] "Course of Study" is an official guideline that defines the educational content and learning objectives provided by educational institutions.

[0274] "Generative AI" is a type of artificial intelligence that generates natural language, images, etc. from specific input.

[0275] "Explanation" is a detailed and easy-to-understand explanation of a particular topic or issue.

[0276] A "comprehension check" is a test or question that assesses how well a learner understands a particular piece of content.

[0277] "Study logging" refers to collecting records of the learning activities performed by learners.

[0278] "Scheduling" is the process of planning and executing specific tasks or activities at the appropriate time.

[0279] A "prompt sentence" is an input sentence that causes a generative AI to generate a specific output.

[0280] A "generative AI model" is an artificial intelligence model that generates natural language, images, etc. from specific input.

[0281] "Feedback" refers to evaluation and improvement information provided to learners regarding their activities and submissions.

[0282] The following system configuration and processing procedure will be described as an embodiment of the present invention.

[0283] System Configuration

[0284] The system includes a server, learner devices (smartphones, tablets, PCs, etc.), and a generative AI model. The server has the functions of providing detailed and extensive explanations using a generative AI that has studied the curriculum guidelines, instantly marking essay corrections, providing explanations and comprehension checks, recording study logs and scheduling by referencing comprehension checks, generating prompt sentences based on compositions entered or uploaded by learners, and instantly providing marking results and feedback using the generative AI model.

[0285] Hardware and Software

[0286] Hardware: Server, learner's device (smartphone, tablet, PC)

[0287] Software: Python, OpenAI API, database management system (e.g., MySQL (registered trademark))

[0288] Data processing and calculation

[0289] 1. Data entry: Learners use the terminal to enter or upload their English compositions.

[0290] 2. Prompt generation: The server generates prompts based on the input essay, requesting grading and feedback.

[0291] 3. Invoke the generative AI model: The server uses OpenAI's GPT-3 model to input the prompt and generate a score and feedback for the essay.

[0292] 4. Providing feedback: The generated feedback is immediately displayed on the learner's device.

[0293] 5. Log acquisition and scheduling: The server acquires the learner's learning log and proposes the next learning schedule based on the results of the comprehension check.

[0294] Specific examples

[0295] Suppose a learner inputs the following composition:

[0296] This is an example essay written by a student. It contains several grammatical errors and lacks coherence.

[0297] The server generates the following prompt based on this composition:

[0298] Please grade and provide feedback on the following English essays:

[0299] This is an example essay written by a student. It contains several grammatical errors and lacks coherence.

[0300] Scoring and feedback:

[0301] By inputting this prompt into the generative AI model, students can instantly receive scoring results and feedback, which is displayed on their devices, allowing them to instantly see the evaluation of their writing and areas for improvement.

[0302] In this way, the learner can study efficiently and improve his / her understanding.

[0303] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0304] Step 1:

[0305] A user uses a terminal to type or upload an English composition.

[0306] Input: English composition text entered by the user.

[0307] Output: Essay data sent from the device to the server.

[0308] Specific operation: The user opens the application on their device and enters an English composition or uploads an existing composition file. The entered composition data is sent to the server.

[0309] Step 2:

[0310] The server generates a prompt sentence based on the composition data received.

[0311] Input: Essay data received by the server.

[0312] Output: The generated prompt statement.

[0313] Specific operation: The server analyzes the received composition data and generates a prompt sentence like the following:

[0314] Please grade and provide feedback on the following English essays:

[0315] [Composition data]

[0316] Scoring and feedback:

[0317] Step 3:

[0318] The server uses a generative AI model to input prompts and generate scores and feedback for the essay.

[0319] Input: The generated prompt statement.

[0320] Output: Scoring and feedback from the generative AI model.

[0321] Specific operation: The server sends a prompt to OpenAI's GPT-3 model and receives the generated score and feedback.

[0322] Step 4:

[0323] The server transmits the generated feedback to the learner's terminal.

[0324] Input: Scoring and feedback from the generative AI model.

[0325] Output: Feedback displayed on the learner's device.

[0326] Specific operation: The server sends the generated feedback to the learner's device, which displays it. The learner can immediately check the evaluation of their composition and areas for improvement.

[0327] Step 5:

[0328] The server acquires the learner's learning log and suggests the next learning schedule based on the results of the comprehension check.

[0329] Input: Learner's learning log and comprehension check results.

[0330] Output: Next study schedule.

[0331] Specific operation: The server analyzes the learner's past learning log and the results of comprehension checks, and suggests the next learning content and timing. The next learning schedule is displayed on the learner's device.

[0332] Example 3

[0333] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0334] Conventional learning systems have difficulty accurately grasping a learner's level of comprehension and providing an appropriate learning schedule based on that. They also lack efficient learning support that combines explanations and comprehension checks. Furthermore, they lack the functionality to automatically generate the next learning plan using the learner's study log.

[0335] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0336] In this invention, the server includes a means for generating explanations for the learner using a generative AI model, a means for creating questions for a comprehension check based on the generated explanations, a means for evaluating the learner's answers, a means for acquiring the learner's study log and automatically generating a study schedule based on the results of the comprehension check, and a means for conducting the explanations and comprehension check. This makes it possible to accurately grasp the learner's level of comprehension and provide an appropriate study schedule based on that.

[0337] A "generative AI model" is an algorithm that uses artificial intelligence technology to generate and interpret natural language.

[0338] An "explanation" is a piece of writing or content that provides detailed explanations of a particular topic or concept so that it is easy for learners to understand.

[0339] A "comprehension check" is a question or test that assesses how well a learner has understood the content of the explanation.

[0340] A "means for generating questions" is a method or device for generating questions or tasks for assessing comprehension based on an explanation.

[0341] A "means for evaluating answers" is a method or device for determining and evaluating the accuracy and appropriateness of answers submitted by learners.

[0342] A "study log" is a record of a learner's learning activities, including data such as study time and content.

[0343] A "study schedule" is a planned schedule of study time and content for learners to study efficiently.

[0344] "Automatic generating means" refers to a method or device that uses a specific algorithm or program to automatically generate results without manual intervention.

[0345] The "means for providing explanations and checking comprehension" is a method or device for providing explanations and then asking questions to assess comprehension.

[0346] This invention is a system that uses a generative AI model to generate explanations for a learner, creates questions to check comprehension based on the explanations, evaluates the learner's answers, acquires the learner's study log, and automatically generates the learner's next study schedule. A specific embodiment of this system is described below.

[0347] Hardware and software used

[0348] server

[0349] The server provides the computational resources to run the generative AI model, specifically using the following hardware and software:

[0350] Hardware: A server machine with a powerful CPU, GPU, and sufficient memory

[0351] Software: Generative AI models (e.g., OpenAI's GPT-4 (registered trademark)), database management systems, web server software

[0352] Terminal

[0353] The terminal is a device that allows learners to read explanations and answer comprehension check questions. Specifically, the following hardware and software are used:

[0354] Hardware: PCs, tablets, smartphones

[0355] Software: Web browser, dedicated application

[0356] Data processing and calculation

[0357] Explanation Generation

[0358] The server uses the generative AI model to generate explanations for the learner. Specifically, it inputs the following prompt sentences into the generative AI model:

[0359] Example prompt: "Please explain the basic concept of differentiation in high school mathematics."

[0360] The generative AI model generates an explanation based on the prompt and returns it to the server. An example of the generated explanation is as follows:

[0361] Example text: "Differentiation is a method for finding the rate of change of a function. For example, suppose we have a function y = x^2. To find the rate of change of this function with respect to x, we get dy / dx = 2x."

[0362] Creating comprehension check questions

[0363] The server creates questions for checking comprehension based on the generated explanatory text. Specifically, it creates the following questions:

[0364] Example of a comprehension check question: "Find the derivative of the following function: y = 3x^3"

[0365] Submit explanations and questions

[0366] The server sends the generated explanatory text and comprehension check questions to the terminal, which then displays them to the learner.

[0367] Evaluating answers

[0368] When a learner answers a comprehension check question through their device, the device sends the answer to the server. The server receives the learner's answer and evaluates its accuracy. For example, if the learner's answer is "dy / dx = 9x^2," it will be evaluated as correct.

[0369] Acquiring learning logs and generating schedules

[0370] The server collects the learner's study log, which records the amount of time spent studying each day and the content of the study. Based on this log and the results of the comprehension check, the server automatically generates the next study schedule. For example, if the result of the comprehension check is 80%, the server will suggest "spend one hour reviewing differentiation and the remaining hour studying the basic concepts of integration."

[0371] The above is a specific embodiment for carrying out the present invention. This system makes it possible to accurately grasp the learner's level of understanding and provide an appropriate study schedule based on that understanding. The flow of the specification process in the third embodiment will be described with reference to FIG.

[0372] Step 1:

[0373] The server uses a generative AI model to generate explanations for the learner.

[0374] Input: Prompt sentence (e.g., "Please explain the basic concept of differentiation in high school mathematics.")

[0375] Data processing: The generative AI model analyzes the prompt and generates an appropriate explanation.

[0376] Output: Explanation (e.g., "Differentiation is a method for finding the rate of change of a function. For example, suppose there is a function y = x^2. To find the rate of change of this function with respect to x, we get dy / dx = 2x.")

[0377] Step 2:

[0378] The server creates questions for checking the level of understanding based on the generated commentary.

[0379] Input: Description

[0380] Data processing: Analyze the content of the explanatory text and generate questions to assess comprehension.

[0381] Output: Comprehension check question (e.g., "Find the derivative of the following function: y = 3x^3")

[0382] Step 3:

[0383] The server sends the generated explanatory text and comprehension check questions to the terminal.

[0384] Input: explanatory text, comprehension check questions

[0385] Data processing: The explanatory text and questions are packaged and converted into a data format for transmission to the terminal.

[0386] Output: Data sent to the terminal

[0387] Step 4:

[0388] The terminal displays the explanatory text and comprehension check questions sent from the server to the learner.

[0389] Input: Data sent from the server

[0390] Data processing: Convert the received data into a display format and display it on the screen.

[0391] Output: Explanations and questions that students can view

[0392] Step 5:

[0393] The user answers the comprehension check questions displayed on the terminal.

[0394] Input: Comprehension check question

[0395] Data processing: Solve the problems and enter the answers.

[0396] Output: Response data

[0397] Step 6:

[0398] The terminal transmits the user's answer to the server.

[0399] Input: User response data

[0400] Data processing: Convert the response data into a data format for sending to the server.

[0401] Output: Answer data sent to the server

[0402] Step 7:

[0403] The server receives the user's answers and evaluates their accuracy.

[0404] Input: User response data

[0405] Data processing: Analyze the response data and evaluate it by comparing it with the correct answer.

[0406] Output: Evaluation result (e.g. correct answer, incorrect answer, score, etc.)

[0407] Step 8:

[0408] The server acquires the learner's study log and automatically generates a study schedule based on the results of the comprehension check.

[0409] Input: Learner's study log, comprehension check results

[0410] Data processing: Analyze the study log and comprehension check results to generate the next study schedule.

[0411] Output: Study schedule (e.g., "1 hour review of differentiation, 1 hour learning basic concepts of integration")

[0412] The above are the specific processing steps of the program of this system.

[0413] (Application example 3)

[0414] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0415] Conventional learning support systems lack the functionality to check a learner's level of understanding in real time and automatically generate the next learning schedule based on that information. Furthermore, they do not adequately provide an interface that allows learners to easily progress through their studies using their smartphones. This leads to issues such as reduced learning efficiency and difficulty in effective learning.

[0416] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0417] In this invention, the server includes a means for providing detailed and wide-ranging explanations by generative AI that has studied the curriculum guidelines, a means for instantly marking corrections to written questions, a means for providing explanations and checking comprehension, a means for scheduling by acquiring a study log and referring to the comprehension check, a means for providing explanations to learners and checking comprehension via an application installed on a smartphone, and a means for recording the learner's study log and automatically generating the next study schedule. This makes it possible to check the learner's level of comprehension in real time and automatically generate the next study schedule based on that.

[0418] A "course of study" is an official guideline that defines the content and goals that learners should learn at an educational institution.

[0419] "Generative AI" is a system that uses artificial intelligence technology to generate new information and content.

[0420] A "detailed and extensive explanation" is one that provides a deep and comprehensive explanation of a particular topic.

[0421] "Written question correction" is the process of evaluating the answers written by learners and indicating whether they are correct or incorrect and what areas need improvement.

[0422] A "comprehension check" is a test or question that assesses how much a learner understands about a particular topic.

[0423] "Study logging" refers to collecting records of the learning activities performed by learners.

[0424] "Scheduling" means planning learners' learning activities and creating timetables and plans to carry them out efficiently.

[0425] "Applications installed on smartphones" refers to software that is downloaded to a mobile phone terminal and used.

[0426] A "learner's learning log" is a detailed record of the learning activities undertaken by a learner.

[0427] "Automatically generating the next learning schedule" means automatically planning the next learning content and time based on the learner's past learning data and level of understanding.

[0428] The system for implementing this invention mainly uses a server, a smartphone, and a generative AI model. The server includes a means for providing detailed and extensive explanations by a generative AI that has studied the curriculum guidelines, a means for instantly marking essay corrections, a means for providing explanations and checking comprehension, and a means for recording study logs and scheduling by referencing comprehension checks. An application for providing explanations to learners and checking comprehension is installed on the smartphone.

[0429] The server uses a generative AI model (e.g., OpenAI GPT-3) to provide explanations on specific topics to learners. For example, to provide explanations on basic concepts in mathematics, the server inputs the following prompt sentence into the generative AI model: "Please explain the basic concepts of mathematics."

[0430] The application installed on a smartphone displays explanations provided by the generative AI model to the learner, then asks questions to check their comprehension, which the learner answers. The answers are sent to a server and instantly scored.

[0431] The server records the learner's learning log and automatically generates the next study schedule based on the results of the comprehension check. For example, if a learner studies a mathematics topic for 60 minutes and receives a high score on the comprehension check, the server can suggest physics as the next study topic.

[0432] This system allows learners to easily progress through their studies using their smartphones, check their level of understanding in real time, and automatically generate their next study schedule based on that.

[0433] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0434] Step 1:

[0435] The server receives as input the topic the learner wants to learn. For example, the learner may input that they want to learn about "basic concepts of mathematics." Based on this input, the server generates and sends a prompt to the generative AI model: "Please explain the basic concepts of mathematics."

[0436] Step 2:

[0437] The generative AI model generates an explanation based on the prompt received from the server. The generated explanation is sent back to the server. For example, the generated explanation might be, "Mathematics is the study of numbers, quantities, structures, space, etc."

[0438] Step 3:

[0439] The server sends the explanations returned by the generative AI model to an application installed on the smartphone, which then displays the explanations to the learner. The learner reads the explanations and deepens their understanding.

[0440] Step 4:

[0441] After displaying the explanation, the server generates a question to check the learner's comprehension. For example, it generates a question such as, "What are the basic concepts of mathematics?" This question is sent to the learner's smartphone and displayed to them.

[0442] Step 5:

[0443] Learners answer comprehension check questions via their smartphones. The answers are sent from the smartphone to the server. For example, a learner might answer, "Mathematics is the study of numbers, quantities, structures, and spaces."

[0444] Step 6:

[0445] The server receives the learner's answers and immediately scores them. The results are used to evaluate the learner's level of understanding. For example, a learner who answers correctly will receive a higher score.

[0446] Step 7:

[0447] The server records the learner's learning log, which includes the learning topic, study time, and comprehension check results. For example, a log may be recorded stating, "I studied basic concepts of mathematics for 60 minutes and scored 90 points on the comprehension check."

[0448] Step 8:

[0449] The server automatically generates the next learning schedule based on the learning log and the results of the comprehension check. For example, it may suggest "Fundamental Laws of Physics" as the next learning topic. This schedule is sent to the learner's smartphone and displayed to them.

[0450] Step 9:

[0451] Learners can proceed with their studies by following the next study schedule displayed on their smartphone, which allows them to study efficiently.

[0452] 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.

[0453] "Example 1"

[0454] One embodiment of the present invention is a learning support system incorporating an emotion engine. This system recognizes the learner's emotions and reflects the results in learning instruction. Specifically, if a learner feels that they are struggling with their studies, the emotion engine captures this information and adjusts the instruction method for the learner.

[0455] For example, when a learner is facing a difficult problem, the emotion engine detects the stress and the system responds by providing more detailed explanations or additional learning materials.

[0456] "Example 2"

[0457] The emotion engine is also used to adjust the learning schedule. The system optimizes the learning schedule according to the learner's emotional state. For example, if the learner feels tired, the system will shorten the learning time that day and increase the time for relaxation and rest. This reduces the learner's stress and improves learning efficiency.

[0458] "Example 3"

[0459] Furthermore, the emotion engine can also be used to increase learner motivation. For example, when a learner achieves a certain goal, the emotion engine detects their joy and the system provides feedback praising their achievement, thereby enhancing the learner's sense of accomplishment and maintaining their motivation to learn.

[0460] "Example 4"

[0461] In this way, the system of the present invention, which incorporates an emotion engine, can properly understand the learner's emotions and provide optimal learning support accordingly, allowing the learner to study more efficiently and enjoyably.

[0462] The processing flow of each embodiment will be described below.

[0463] "Example 1"

[0464] Step 1: Learners engage in the learning task.

[0465] Step 2: The emotion engine monitors the learner's emotions in real time and evaluates their emotional state.

[0466] Step 3: If the emotion engine determines that the learner is struggling, it communicates this information to the learning support system.

[0467] Step 4: The learning support system adjusts the teaching method for the learner based on the information from the emotion engine.

[0468] "Example 2"

[0469] Step 1: Learners follow a study schedule.

[0470] Step 2: The emotion engine monitors the learner's emotions in real time and evaluates their emotional state.

[0471] Step 3: If the emotion engine determines that the learner is fatigued, it communicates this information to the learning support system.

[0472] Step 4: The learning support system adjusts the learning schedule based on the information from the emotion engine.

[0473] "Example 3"

[0474] Step 1: Learners engage in the learning task.

[0475] Step 2: When a learner achieves a specific goal, the emotion engine detects their joy. Step 3: The emotion engine communicates the information it has detected about the learner's joy to the learning support system. Step 4: The learning support system provides feedback to the learner based on the information from the emotion engine.

[0476] "Example 4"

[0477] Step 1: Learners engage in the learning task.

[0478] Step 2: The emotion engine monitors the learner's emotions in real time and evaluates their emotional state.

[0479] Step 3: Based on the information from the emotion engine, the learning support system provides optimal learning support.

[0480] Example 1

[0481] Next, a description will be given of Example 1 of Form 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."

[0482] Conventional learning support systems often provide insufficient explanations for learners' questions and do not take into account the learner's feelings when providing instruction. Furthermore, because corrections of written questions and comprehension checks are performed manually, they lack immediacy. Furthermore, scheduling to effectively manage learners' progress is difficult.

[0483] 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.

[0484] In this invention, the server includes a means for providing detailed and extensive explanations by a generative AI that has learned the curriculum guidelines, a means for instantly marking corrections to written questions, a means for providing explanations and comprehension checks, a means for recording study logs and scheduling by referring to comprehension checks, a means for recognizing the user's emotions and reflecting the results in learning instruction, a means for inputting questions into a generative AI model and generating explanations, a means for providing the generated explanations to the user, and a means for providing additional explanations and materials based on emotional data. This allows for the provision of detailed and extensive explanations to learners' questions, enabling instruction that takes learners' emotions into consideration, and automating the instant marking of written questions and comprehension checks, thereby improving the effectiveness of learning.

[0485] "Course of Study" is an official guideline that defines the educational content and learning objectives provided by educational institutions.

[0486] "Generative AI" is a type of artificial intelligence, a system that has the ability to generate new information and explanations based on input data.

[0487] A "detailed and broad explanation" is one that provides in-depth explanations of specific questions and covers a wide range of related knowledge.

[0488] "Written question correction" is the process of evaluating the answers written by learners and pointing out correct and incorrect answers and areas for improvement.

[0489] "Instant grading" means evaluating answers submitted by learners in real time and returning the results immediately.

[0490] "Explanation and comprehension check" is a process in which an explanation is provided to learners and then questions are asked to check their comprehension.

[0491] "Study logging" means recording a learner's learning activities and saving that data.

[0492] "Scheduling based on comprehension checks" means planning the next learning content and timing based on the learner's level of comprehension.

[0493] "Recognizing the user's emotions" means judging the learner's emotional state by analyzing their facial expressions, tone of voice, etc.

[0494] "Reflecting on learning instruction" means adjusting the instruction method for the learner based on the recognized emotional data.

[0495] "Inputting a question into a generative AI model" refers to the process of inputting a learner's question into a generative AI and generating an explanation.

[0496] "Providing the generated explanation to the user" means displaying the explanation generated by the generative AI to the learner.

[0497] "Providing additional explanations and materials based on emotional data" means providing additional explanations and learning materials as needed, taking into account the learner's emotional state.

[0498] This invention is a system that uses generative AI that has learned the curriculum guidelines to provide detailed and extensive explanations to questions from learners. Specifically, the system works in cooperation with the server, terminal, and user elements.

[0499] Hardware and software used

[0500] The server is a high-performance computer that provides an environment for running a generative AI model. Specifically, OpenAI's GPT-4 is used as the generative AI model. The server also includes software for running an emotion engine (e.g., Affectiva or Microsoft® Azure®'s Emotion API).

[0501] The terminal is a device used by the user, such as a PC or smartphone, that communicates with the server through a web browser or mobile application. The terminal provides an interface for the user to enter questions and receive answers.

[0502] Data processing and calculation

[0503] When a user inputs a question using a device, the question is sent from the device to a server. The server inputs the received question into a generative AI model and generates a detailed explanation. The generated explanation is sent from the server to the device and displayed to the user.

[0504] Furthermore, the emotion engine recognizes the user's emotions and sends the data to the server, which then requests additional explanations and learning materials from the generative AI model based on the emotion data, and provides them to the user.

[0505] Specific examples

[0506] For example, consider the case where a user asks, "Please tell me how to solve a quadratic equation." The user opens a web browser on their device and enters the question. The device then sends this question to the server. The server then inputs the received question into a generative AI model (GPT-4) and generates a detailed explanation. The generated explanation is then sent from the server to the device and displayed to the user.

[0507] Example prompt sentence:

[0508] "Please tell me how to solve quadratic equations."

[0509] The emotion engine analyzes the user's facial expressions and tone of voice, and if the user is having difficulty, the server requests additional explanations and learning materials from the generative AI model and provides them to the user. For example, if the user is having difficulty, the server will provide "additional example problems and step-by-step explanations on how to solve quadratic equations."

[0510] In this way, detailed and extensive explanations of learners' questions are provided, and instruction can be given taking into account the learners' feelings.

[0511] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0512] Step 1:

[0513] The user enters a question.

[0514] A user opens a web browser or mobile application on their device and enters a question. For example, they might enter, "Please tell me how to solve a quadratic equation." The input data is the user's question text.

[0515] Step 2:

[0516] The terminal sends a question to the server.

[0517] The terminal sends the user-entered question to the server using the HTTPS protocol. The input data is the user's question text, and the output data is the question text sent to the server.

[0518] Step 3:

[0519] The server inputs the question into a generative AI model.

[0520] The server inputs the received question text into a generative AI model. Specifically, GPT-4 is used as the generative AI model. The input data is the question text sent to the server, and the output data is the question text input into the generative AI model.

[0521] Step 4:

[0522] A generative AI model generates commentary.

[0523] The generative AI model generates detailed explanations based on the input question text. For example, it generates an explanation on "how to solve quadratic equations." The input data is the question text entered into the generative AI model, and the output data is the generated explanation text.

[0524] Step 5:

[0525] The server receives the generated description.

[0526] The server receives the commentary text returned from the generative AI model. The input data is the commentary text returned from the generative AI model, and the output data is the commentary text received by the server.

[0527] Step 6:

[0528] The server sends the description to the terminal.

[0529] The server transmits the generated commentary text to the terminal using the HTTPS protocol. The input data is the commentary text received by the server, and the output data is the commentary text transmitted to the terminal.

[0530] Step 7:

[0531] The terminal displays the explanation to the user.

[0532] The device displays the explanatory text received from the server in a web browser or mobile application. The input data is the explanatory text sent to the device, and the output data is the explanatory text displayed to the user.

[0533] Step 8:

[0534] The emotion engine recognizes the user's emotions.

[0535] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and tone of voice and generate emotion data. The input data is the user's facial expressions and tone of voice, and the output data is the generated emotion data.

[0536] Step 9:

[0537] The server provides additional commentary and materials based on the emotional data.

[0538] The server requests the generative AI model to generate additional explanations and learning materials based on the emotion data obtained from the emotion engine. For example, if the user is having difficulty, the server requests "additional example problems and step-by-step explanations on how to solve quadratic equations" from the generative AI model and provides the generated explanations and materials to the user. The input data is the emotion data obtained from the emotion engine, and the output data is the additional explanations and learning materials.

[0539] (Application example 1)

[0540] Next, a description will be given of Application Example 1 of Embodiment 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."

[0541] Conventional learning support systems and factory support systems have difficulty providing detailed explanations to questions from learners and workers, and are unable to recognize the emotions of learners and workers and provide appropriate support. As a result, learners and workers are unable to receive appropriate support when they face difficult problems, which leads to issues such as reduced learning and work efficiency.

[0542] 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.

[0543] In this invention, the server includes means for providing detailed and extensive explanations by generative AI that has learned the curriculum guidelines, means for instantly marking corrections to written questions, means for providing explanations and checking comprehension, means for recording study logs and scheduling by referring to comprehension checks, means for recognizing learners' emotions using an emotion engine and reflecting the results in learning guidance, means for providing detailed explanations in response to questions from workers in a factory, and means for recognizing workers' emotions using the emotion engine and providing appropriate support. This enables learners and workers to receive detailed explanations and appropriate support when they face difficult problems.

[0544] The "Course of Study" is a set of teaching standards that systematically compile the knowledge and skills that learners should acquire in educational institutions.

[0545] "Generative AI" is an artificial intelligence technology that generates new information and answers based on given data and instructions.

[0546] "Detailed and wide-ranging explanation" refers to providing an in-depth and multifaceted explanation of a specific question or issue.

[0547] "Written question correction" is the process of evaluating the answers written by learners and indicating whether they are correct or incorrect and what areas need improvement.

[0548] "Comprehension checks" refer to tests or questions that are used to assess how well a learner has understood the content.

[0549] "Study logging" refers to collecting records of the learning activities performed by learners.

[0550] "Scheduling" refers to creating a study plan for learners and managing their time to progress efficiently.

[0551] An "emotion engine" is a technology that recognizes the emotional state of learners and workers and responds appropriately based on that.

[0552] A "learner" refers to a person who engages in learning activities in order to acquire specific knowledge or skills.

[0553] "Worker" refers to a person who performs a specific task or work.

[0554] "Questions from workers in the factory" refers to doubts or problems that workers in the factory have related to their work.

[0555] "Appropriate support" refers to providing optimal solutions and assistance to the problems and difficulties that learners and workers face.

[0556] The system for implementing this invention includes a generative AI that has learned the curriculum guidelines, an emotion engine, and a function for providing explanations to questions from workers in a factory. Specific embodiments are described below.

[0557] System Configuration

[0558] The system consists of the following main components:

[0559] 1. Server: Runs the generative AI model and emotion engine.

[0560] 2. Devices: Tablets and smartphones used by learners and workers.

[0561] 3. Users: Learners and factory workers.

[0562] Hardware and software used

[0563] Server: A server with high-performance computing power that runs generative AI models (e.g., OpenAI's GPT-3) and emotion engines (e.g., EmotionEngine).

[0564] Devices: Tablets and smartphones used by learners and workers. These devices communicate with the server to send questions and receive explanations and support.

[0565] Software: Generative AI model, emotion engine, question explanation function, comprehension check function, scheduling function.

[0566] Data processing and calculation

[0567] 1. Entering a question: The user enters a question using a terminal.

[0568] 2. Emotion Recognition: The emotion engine recognizes the user's emotions, for example, determining whether the user is feeling stressed.

[0569] 3. Explanation Generation: The generative AI model generates a detailed explanation for the question. It uses the prompt text to provide an appropriate explanation.

[0570] 4. Providing support: Based on the results of the emotion engine, provide appropriate support. For example, if the user is feeling stressed, provide more detailed explanation or additional support.

[0571] Specific examples

[0572] Learner Examples

[0573] When a learner asks, "Please tell me how to solve this math problem," the emotion engine recognizes the learner's emotions and the generative AI model provides detailed explanations. For example, if the learner is feeling stressed, the system will provide more detailed step-by-step explanations.

[0574] Worker example

[0575] When a factory worker asks, "What is the maintenance procedure for this machine?", the emotion engine recognizes the worker's emotions and the generative AI model provides detailed explanations. For example, if the worker is confused, the system provides simple step-by-step instructions.

[0576] Prompt Sentence Examples

[0577] Factory work question: What are the maintenance procedures for this machine?

[0578] Please provide a detailed explanation.

[0579] In this way, the system can provide detailed explanations and appropriate support for problems faced by learners and workers.

[0580] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0581] Step 1:

[0582] The user uses the terminal to enter a question.

[0583] Input: The user types the question in text format into the terminal.

[0584] Output: The device sends the entered question to the server.

[0585] Specific operation: The user types "Please tell me the maintenance procedure for this machine" into the terminal and presses the send button.

[0586] Step 2:

[0587] The server receives the question and uses an emotion engine to recognize the user's emotion.

[0588] Input: Questions sent from the device and user emotion data.

[0589] Output: The user's emotional state (e.g., stressed, confused, etc.).

[0590] Specific operation: The server analyzes the question, and the emotion engine analyzes the user's voice and facial expression data to recognize "stress."

[0591] Step 3:

[0592] The server uses a generative AI model to generate detailed explanations for the questions.

[0593] Input: User question and emotional state.

[0594] Output: A detailed explanation of the question.

[0595] Specific operation: The server inputs the prompt sentence "Question about factory work: What is the maintenance procedure for this machine? Please provide a detailed explanation" into the generative AI model, and the AI ​​generates a detailed explanation.

[0596] Step 4:

[0597] The server provides appropriate support based on the emotional state.

[0598] Input: Generated commentary and the user's emotional state.

[0599] Output: Tailored commentary and additional support.

[0600] Specific Action: The server recognizes that the user is stressed and adds detailed step-by-step instructions to the generated explanation.

[0601] Step 5:

[0602] The server sends the generated explanations and support content to the device.

[0603] Input: Coordinated commentary and additional support.

[0604] Output: Explanations and supporting content sent to the device.

[0605] Specific operation: The server sends the generated explanation and additional support content to the terminal, allowing the user to view it on the terminal.

[0606] Step 6:

[0607] The user checks the explanations and support content on the device and asks additional questions as needed.

[0608] Input: Explanations and support displayed on the terminal.

[0609] Output: User understanding and follow-up questions.

[0610] Specific operation: The user reads the explanation on the terminal, and if there is any part they do not understand, they enter the question again.

[0611] Example 2

[0612] Next, a description will be given of Example 2 of Form 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."

[0613] Conventional learning systems take time to grade and provide feedback on written questions submitted by learners, resulting in a lack of immediacy. Furthermore, they do not optimize learning schedules to take into account the learner's emotional state, which can lead to reduced learning efficiency. Furthermore, when learners need to refer to other textbooks, explanations are often insufficient. To address these issues, a system is needed that provides instant grading and feedback and optimizes learning schedules according to the learner's emotional state.

[0614] 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.

[0615] In this invention, the server includes means for providing detailed and extensive explanations by a generative artificial intelligence that has studied the curriculum guidelines, means for instantly marking corrections to written questions, means for providing explanations and checking comprehension, means for recording study logs and scheduling by referring to the comprehension checks, means for analyzing essays using natural language processing technology, means for inputting prompt sentences to a generative artificial intelligence model and generating marks and feedback, and means for analyzing the emotional state of the learner using an emotion engine and optimizing the study schedule. This makes it possible to instantly mark written questions submitted by the learner, provide feedback, and optimize the study schedule according to the learner's emotional state.

[0616] "Course of Study" is an official guideline that defines the educational content and learning objectives provided by educational institutions.

[0617] "Generative AI" is AI that has the ability to generate text and data using natural language processing and machine learning techniques.

[0618] "Written question correction" is the process of evaluating free-form responses submitted by learners and pointing out errors and areas for improvement.

[0619] "Explanation" is a detailed and easy-to-understand explanation of a particular topic or issue.

[0620] A "comprehension check" is a test or question that assesses how well a learner understands a particular piece of content.

[0621] "Study logging" is the process of recording learners' learning activities and progress.

[0622] "Scheduling" means creating timetables and plans to efficiently plan and manage learners' learning activities.

[0623] "Natural language processing technology" is a technology that allows computers to understand, interpret, and generate human language.

[0624] A "generative artificial intelligence model" is an artificial intelligence model that has the ability to generate new text or data based on input data.

[0625] A "prompt sentence" is an input sentence that causes a generative artificial intelligence to perform a specific task.

[0626] An "emotion engine" is a technology that analyzes a user's emotional state and responds appropriately based on the results.

[0627] A "study schedule" is a timetable or plan designed to help learners study efficiently.

[0628] This invention is a system that instantly grades essay questions submitted by learners and provides feedback. It also includes a function to optimize the learning schedule according to the learner's emotional state. A specific embodiment of this system is described below.

[0629] The server receives English essays submitted by learners via their devices. The received essays are analyzed using natural language processing technology. Specifically, the Google® Cloud Natural Language API is used to evaluate the essay's grammar, vocabulary, structure, etc. The evaluation results are input into a generative AI model (e.g., OpenAI's GPT-4), which scores the essay and generates feedback.

[0630] Next, an emotion engine evaluates the learner's emotional state. The emotion engine analyzes the learner's input data (e.g., self-reports and biometric sensor data) to determine whether the learner is fatigued. The emotion engine uses IBM Watson® Tone Analyzer. Based on the learner's emotional state, the server adjusts the learning schedule. For example, if the server determines that the learner is fatigued, the server will reduce the learning time for that day and increase the time for relaxation and rest.

[0631] As a concrete example, suppose a learner submits the following English composition:

[0632] I have a dog. He name is Max. He is very playful and likes to run in the park.

[0633] The server receives this essay and evaluates its grammar and vocabulary using the Google Cloud Natural Language API. Based on the evaluation results, it inputs the following prompt sentence to the generative AI model (GPT-4):

[0634] Please grade the following English composition and provide feedback:

[0635] "I have a dog. He name is Max. He is very playful and likes to run in the park."

[0636] The generative AI model grades the essay and provides feedback such as:

[0637] Grade: C

[0638] Feedback: The sentence "I have a dog" should be "I have a dog". Also, "He name is Max" should be "His name is Max". Overall, the composition is understandable but contains several grammatical errors.

[0639] Next, if a learner self-reports, "I'm tired today," the emotion engine (IBM Watson Tone Analyzer) analyzes this information and determines that the learner is tired. The server then shortens the study schedule for that day and adjusts it to increase relaxation time.

[0640] In this way, the system can instantly grade a learner's writing, provide feedback, and optimize the learning schedule according to the learner's emotional state.

[0641] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0642] Step 1:

[0643] A user submits an English composition.

[0644] The user uses a terminal to access the system interface and input an English composition. When input is complete, the user clicks the submit button. The input data is the composition text entered by the user. The output is the composition data sent to the server.

[0645] Step 2:

[0646] The server receives the composition.

[0647] The server receives the essay data sent by the user. The received data is temporarily stored in a database. The input data is the essay text submitted by the user. The output is the stored essay data.

[0648] Step 3:

[0649] The server analyzes the essay using natural language processing (NLP) technology.

[0650] The server uses the Google Cloud Natural Language API to analyze the grammar, vocabulary, structure, etc. of the received essay. Specifically, it sends the essay data to the API and receives the analysis results. The input data is the saved essay data. The output is the analysis results.

[0651] Step 4:

[0652] The server inputs prompt sentences into the generative AI model and generates scores and feedback.

[0653] Based on the analysis results, the server inputs a prompt to the generative AI model (e.g., OpenAI's GPT-4). Examples of prompts include:

[0654] Please grade the following English composition and provide feedback:

[0655] "I have a dog. He name is Max. He is very playful and likes to run in the park."

[0656] The generative AI model receives a prompt and generates a score and feedback for the essay. The input data is the analysis result and the prompt. The output is the generated score and feedback.

[0657] Step 5:

[0658] The server provides feedback to the user.

[0659] The server sends the generated feedback to the user's terminal, and the user can check the feedback on the interface. The input data is the generated feedback. The output is the feedback provided to the user.

[0660] Step 6:

[0661] The user inputs an emotional state.

[0662] A user uses a terminal to input their emotional state into the system. For example, they self-report, "I feel tired today." The input data is the emotional state input by the user. The output is the emotional data sent to the server.

[0663] Step 7:

[0664] The server analyzes the emotional state using an emotion engine.

[0665] The server uses IBM Watson's Tone Analyzer to analyze the user's emotional state. It sends the input emotional data to the API and receives the analysis results. The input data is the emotional state entered by the user. The output is the analysis results.

[0666] Step 8:

[0667] The server optimizes the learning schedule.

[0668] The server optimizes the study schedule based on the analysis results. For example, if the server determines that the user is fatigued, it adjusts the schedule to shorten the study time that day and increase the time for relaxation and rest. The input data is the analysis result of the emotional state. The output is the optimized study schedule.

[0669] (Application example 2)

[0670] Next, a description will be given of Application Example 2 of Form 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."

[0671] Conventional learning systems and systems for optimizing the work efficiency of factory robots have the problem of lacking immediate feedback and schedule adjustments according to the state of the learner or worker. In particular, optimal responses according to the learner's level of understanding and emotional state, and the operating state and energy level of the factory robot are required, but there is no effective means to achieve this.

[0672] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0673] In this invention, the server includes a means for providing detailed and extensive explanations by generative AI that has learned the curriculum guidelines, a means for instantly marking written questions, a means for providing explanations and checking comprehension, a means for recording study logs and scheduling by referring to comprehension checks, a means for evaluating work progress in real time and providing instant feedback, and a means for analyzing operating conditions and energy levels and automatically adjusting optimal work schedules. This enables instant feedback and optimal schedule adjustments according to the status of learners and factory robots.

[0674] A "Course of Study" is a teaching plan that systematically summarizes the knowledge and skills that learners should acquire at an educational institution.

[0675] "Generative AI" is a type of artificial intelligence, a system that has the ability to generate new information and answers based on given data and information.

[0676] "Detailed and wide-ranging commentary" means providing in-depth explanations of specific themes or topics and providing a wide range of related knowledge.

[0677] "Written question correction" is the process of determining whether written questions submitted by learners are correct or incorrect and pointing out areas for improvement.

[0678] "Instant grading" means evaluating answers submitted by learners in real time and providing instant results.

[0679] "Explanation and comprehension check" involves providing an explanation to learners, followed by tests and questions to check their level of understanding of the content.

[0680] "Study logging" refers to collecting records of the learning activities performed by learners.

[0681] "Scheduling based on comprehension checks" means creating an optimal learning schedule based on the learner's level of comprehension.

[0682] "Real-time evaluation of work progress" means monitoring and evaluating in real time how far the work has progressed.

[0683] "Providing immediate feedback" means providing evaluation results and areas for improvement instantly.

[0684] "Analyzing operating status and energy levels" means analyzing the current operating status and remaining energy of a robot or system.

[0685] "Automatically adjusting the optimal work schedule" means automatically setting the most efficient work schedule based on the analysis results.

[0686] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The following explains how each element functions.

[0687] server

[0688] The server is equipped with a generative AI that has studied the curriculum guidelines and provides detailed and extensive explanations. The server instantly grades the written questions submitted by the learner, provides explanations and checks the learner's level of understanding, and also keeps a study log and optimizes the learning schedule by referring to the results of the comprehension checks. It also has the function of evaluating the progress of factory robots' work in real time and providing immediate feedback. The server analyzes the robots' operating status and energy levels and automatically adjusts the optimal work schedule.

[0689] Terminal

[0690] The terminal is a device used by the user, and can include smartphones, tablets, and PCs. The terminal displays explanations and feedback provided by the server and provides an interface for the user to submit written questions. The terminal also records the user's learning log and sends it to the server. In the case of a factory robot, the terminal monitors the robot's operating status and energy level and receives feedback from the server.

[0691] User

[0692] Users are learners and factory robot operators. Learners submit written questions via their terminals and receive explanations and feedback from the server. Learners progress through their studies according to the optimal study schedule provided by the server. Factory robot operators monitor the robot's operating status and energy levels and adjust their work based on feedback from the server.

[0693] Specific examples

[0694] For example, when a learner submits an English essay, the server instantly grades it and provides feedback. If the emotion engine determines that the learner is fatigued, the server adjusts the schedule to shorten the study time that day and increase the time for relaxation and rest.

[0695] In the case of a factory robot, when the robot is "assembling parts," the server analyzes the robot's energy level and recommends rest if the energy level is low, or continues normal work if the energy level is high.

[0696] Prompt Sentence Examples

[0697] "If your robot's energy level is low, tell it to stop working and take a rest."

[0698] In this way, immediate feedback and optimal schedule adjustments based on the status of learners and factory robots are possible.

[0699] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0700] Step 1:

[0701] A user submits a written question using a terminal. As input, text data written by the user is entered into the terminal. The terminal sends this text data to the server. As output, the text data is sent to the server.

[0702] Step 2:

[0703] The server inputs the received text data into the generative AI model and scores it immediately. The text data of the user's written questions is input into the generative AI model as input. The generative AI model analyzes the text data and generates a scoring result. The scoring result is generated as output.

[0704] Step 3:

[0705] The server feeds back the generated scoring results to the user. As input, the scoring results from the generative AI model are input to the server. The server sends the scoring results to the device. As output, the scoring results are sent to the device.

[0706] Step 4:

[0707] The terminal displays the scoring results received from the server to the user. As input, the scoring results from the server are input to the terminal. The terminal visually displays the results to the user. As output, the user confirms the scoring results.

[0708] Step 5:

[0709] The server acquires the user's learning log and optimizes the learning schedule by referring to the results of the comprehension check. The user's learning log and the results of the comprehension check are input to the server. The server analyzes this data and generates an optimal learning schedule. The optimized learning schedule is generated as output.

[0710] Step 6:

[0711] The server evaluates the progress of the factory robot's work in real time and provides immediate feedback. The robot's work progress data is entered into the server as input. The server analyzes this data and generates feedback. The feedback is generated as output.

[0712] Step 7:

[0713] The server analyzes the robot's operating status and energy level, and automatically adjusts the optimal work schedule. The robot's operating status data and energy level data are input to the server. The server analyzes this data and generates the optimal work schedule. The optimized work schedule is generated as output.

[0714] Step 8:

[0715] The server sends the generated optimal work schedule to the robot. As input, the optimized work schedule is input to the server. The server sends this schedule to the robot. As output, the optimized work schedule is sent to the robot.

[0716] Step 9:

[0717] The robot performs work according to the optimal work schedule received from the server. The optimized work schedule is input to the robot as input. The robot performs work based on this schedule. The output is the execution of work.

[0718] Example 3

[0719] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0720] Conventional learning support systems have difficulty accurately grasping a learner's level of understanding and providing appropriate feedback. Furthermore, they lack learning support that takes into account the learner's emotions and motivation, resulting in problems such as reduced learning efficiency and continuity. Furthermore, automatic generation of learning schedules is inadequate, making it difficult to provide an optimal learning plan that matches each learner's progress and level of understanding.

[0721] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0722] In this invention, the server includes a means for providing detailed and extensive explanations using generative artificial intelligence, a means for instantly scoring written questions, a means for providing explanations and comprehension checks, a means for acquiring a learner's study log and automatically generating a study schedule by referring to the results of the comprehension checks, and a means for analyzing the learner's emotions and providing feedback according to the learner's emotions. This makes it possible to accurately grasp the learner's level of comprehension and provide appropriate feedback. Furthermore, learning support that takes into account the learner's emotions and motivation is realized, improving the efficiency and continuity of learning. Furthermore, it becomes possible to provide an optimal study plan according to each learner's progress and level of comprehension.

[0723] "Generative AI" refers to AI that generates text using natural language processing technology.

[0724] A "detailed and comprehensive explanation" is a piece of content that provides an in-depth and multifaceted explanation of a particular topic.

[0725] An "essay question" is a question in which learners write their answers in free form.

[0726] "Instant grading" refers to the ability to evaluate answers and provide results immediately after a learner submits them.

[0727] "Explanation and comprehension check" is the process of providing learners with an explanation and then asking them questions to check their comprehension.

[0728] A "study log" is a record of the learning activities that a learner has performed.

[0729] "Comprehension check results" refers to an evaluation that indicates how accurately the learner was able to answer the comprehension check questions.

[0730] "Means for automatically generating a learning schedule" refers to a function that automatically creates the next learning plan based on the learner's log and the results of the comprehension check.

[0731] "Means for analyzing emotions" refers to the function of detecting the learner's emotional state and analyzing that information.

[0732] "Means for providing feedback" refers to the function of providing appropriate responses and advice based on the learner's behavior and emotions.

[0733] The present invention relates to a learning support system for improving a learner's level of understanding. A specific embodiment of this system will be described below.

[0734] Providing explanations and checking comprehension

[0735] The server uses generative artificial intelligence (e.g., a model using natural language processing technology) to generate detailed and extensive explanations for the learner. Specifically, the server inputs the prompt sentence into the generative AI model and obtains the explanation. For example, the following prompt sentence is used:

[0736] Explain the main causes of World War II.

[0737] The generative AI model returns the explanatory statement, "The main causes of World War II were economic hardship, political instability, and military expansionism."

[0738] The server sends the generated explanation to the device, which then displays it to the learner.The server then generates comprehension check questions based on the explanation, again using the generative AI model to create the questions.For example, use the following prompt:

[0739] "What is one of the main causes of World War II?"

[0740] The generative AI model returns the question, "What is one of the major causes of World War II?"

[0741] The server sends the generated questions to the terminal, which displays the questions to the learner and receives the answers. The user answers the questions, and the terminal sends the answers to the server. The server evaluates the answers and confirms the learner's level of understanding.

[0742] Learning log acquisition and scheduling

[0743] The user inputs the amount of time spent studying and the content of their studies into the device. For example, the following log is recorded:

[0744] "Today's study time: 2 hours, Study content: Calculus"

[0745] The device records these logs and sends them to the server. The server then references the learning log and the results of the comprehension check and automatically generates the next learning schedule. For example, if a learner's comprehension level is low on a particular topic, the next schedule will include more learning content related to that topic. The next learning schedule will look like this:

[0746] "Tomorrow's lesson: Calculus review, Study time: 2 hours"

[0747] Motivation boosted by emotional engine

[0748] The device collects data to detect the learner's emotions (e.g., facial expression recognition, voice analysis). The collected data is sent to the server, which then uses an emotion engine to analyze the learner's emotions. For example, when a learner achieves a specific goal, the server detects their joy and generates feedback such as:

[0749] "Congratulations! You've solved all the basic calculus problems! That's an amazing achievement!"

[0750] The terminal displays this feedback to the learner.

[0751] In this way, by combining the provision of explanations, checking the level of understanding, acquiring and scheduling learning logs, and improving motivation using an emotion engine, a system is realized that supports learners in efficient and enjoyable learning. The flow of the specific processing in the third embodiment will be described with reference to FIG.

[0752] Step 1:

[0753] The server generates the explanation using generative AI. Specifically, the server inputs the prompt sentence into a generative AI model and obtains the explanation.

[0754] Input: Prompt: "Explain the main causes of World War II."

[0755] Data processing: The generative AI model analyzes the prompt and generates an explanatory text.

[0756] Output: Explanation: "The main causes of World War II were economic hardship, political instability, and military expansionism."

[0757] Step 2:

[0758] The server transmits the generated explanation to the terminal, which displays the explanation to the learner.

[0759] Input:Explanatory text: "The main causes of World War II were economic hardship, political instability, and military expansionism."

[0760] Data processing: Send explanatory text to the terminal.

[0761] Output: Explanation displayed on the terminal

[0762] Step 3:

[0763] The server generates comprehension check questions based on the explanation. Specifically, the server inputs prompt sentences into a generative AI model to create questions.

[0764] Input: Prompt "Name one of the main causes of World War II."

[0765] Data processing: The generative AI model analyzes the prompt and generates a question.

[0766] Output: Question: "What is one of the main causes of World War II?"

[0767] Step 4:

[0768] The server sends the generated questions to the terminal, which displays the questions to the learner and receives the answers, and the user answers the questions.

[0769] Input: Question: "Name one of the main causes of World War II."

[0770] Data processing: Send the question to the terminal and receive the learner's answer.

[0771] Output: Learner's answer "Financial difficulties"

[0772] Step 5:

[0773] The terminal sends the learner's answers to the server, which evaluates the answers and checks the learner's level of understanding.

[0774] Input: Learner's answer "Financial difficulties"

[0775] Data processing: Evaluate the answers and determine whether they are correct.

[0776] Output: Evaluation result "Correct"

[0777] Step 6:

[0778] The user inputs the amount of time spent studying and the content of their studies into the terminal, which then records this information and sends it to the server.

[0779] Input: Learning log "Today's study time: 2 hours, Study content: Calculus"

[0780] Data processing: Record the learning log and send it to the server.

[0781] Output: Training log sent to the server

[0782] Step 7:

[0783] The server refers to the learning log and the results of the comprehension check and automatically generates the next learning schedule.

[0784] Input: Learning log and comprehension check results

[0785] Data processing: Generate the next learning schedule based on the learning log and the results of the comprehension check.

[0786] Output: Next study schedule "Tomorrow's study content: Calculus review, Study time: 2 hours"

[0787] Step 8:

[0788] The terminal collects data for detecting the learner's emotions and transmits the collected data to the server, which then analyzes the learner's emotions using an emotion engine.

[0789] Input: Learner's facial expression data

[0790] Data processing: The emotion engine analyzes facial expression data and detects emotions.

[0791] Output: Emotion analysis result "Joy"

[0792] Step 9:

[0793] The server generates feedback according to the learner's emotions and transmits it to the terminal, which then displays the feedback to the learner.

[0794] Input: Emotion analysis result "joy"

[0795] Data processing: Generate feedback based on the results of sentiment analysis.

[0796] Output: Feedback "Congratulations! You've solved all the basic calculus problems. That's a great achievement!"

[0797] (Application example 3)

[0798] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0799] Conventional learning systems lack the means to check a learner's level of understanding or the means to automatically schedule learning. They also lack sufficient feedback functions to increase learner motivation. Furthermore, there are no training systems in place to enable factory robots to efficiently learn new work procedures or machine operation methods. To solve these issues, a system is needed that integrates explanations and comprehension checks using generative AI, feedback using an emotion engine, and factory robot training.

[0800] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0801] In this invention, the server includes: means for providing detailed and extensive explanations by a generative AI that has studied the curriculum guidelines; means for instantly grading corrections to written questions; means for providing explanations and checking comprehension; means for recording study logs and scheduling by referring to comprehension checks; means for providing feedback to increase learner motivation using an emotion engine; means for training a factory robot to learn new work procedures or machine operation methods; means for the generative AI to explain work procedures and for the robot to perform those procedures; means for evaluating the robot's work as a comprehension check; means for automatically generating the next training schedule; and means for praising the robot's performance and providing feedback to increase motivation. This enables the learner's level of understanding to be confirmed, an efficient learning schedule to be provided, and efficient training and increased motivation for factory robots.

[0802] The "Course of Study" is a set of guidelines that systematically summarize the knowledge and skills that learners should acquire at educational institutions.

[0803] "Generative AI" is a type of artificial intelligence that generates new information and explanations based on given data and instructions.

[0804] An "explanation" is a detailed and easy-to-understand explanation of a particular theme or content.

[0805] A "comprehension check" is a means of assessing how well a learner has understood the explanations and information provided.

[0806] A "study log" is a record of the learning activities that a learner has performed, including the time spent studying and the content of the study.

[0807] "Scheduling" means the planned allocation of learning content and time in order to efficiently advance learners' learning activities.

[0808] An "emotion engine" is a technology that detects a learner's emotional state and provides feedback accordingly.

[0809] "Feedback" means providing evaluations and comments on learners' behavior and achievements.

[0810] A "factory robot" is a mechanical device used to automate work in a factory.

[0811] "Training" refers to training to learn new work procedures and how to operate machinery.

[0812] A "work procedure" is a set of steps or methods for performing a specific task efficiently and accurately.

[0813] "Evaluation" is the judging of the results of work or actions based on specific criteria.

[0814] "Performance" refers to the outcome or efficiency of a particular task or activity.

[0815] A system for implementing this invention includes means for providing detailed and extensive explanations by a generative AI that has studied curriculum guidelines, means for instantly grading corrections to written questions, means for providing explanations and checking comprehension, means for recording study logs and scheduling by referring to comprehension checks, means for providing feedback to motivate learners using an emotion engine, means for training a factory robot to learn new work procedures or machine operation methods, means for a generative AI to explain work procedures and for the robot to perform those procedures, means for evaluating the robot's work as a comprehension check, means for automatically generating the next training schedule, and means for praising the robot's performance and providing feedback to motivate it.

[0816] The server uses a generative AI model to generate detailed explanations based on the curriculum guidelines and provides them to the user. After the user receives the explanation, questions are posed to check their level of understanding, and their answers are immediately scored. This allows the user's level of understanding to be evaluated.

[0817] The server also acquires the user's study log and automatically generates the next study schedule based on the results of the comprehension check, allowing the user to study efficiently. Furthermore, an emotion engine is used to detect the user's emotional state and provide feedback according to the learning results. For example, if the user achieves a specific goal, the emotion engine detects their joy, and the server provides praising feedback.

[0818] For factory robots, generative AI explains new work procedures and machine operation methods, and the robots execute those procedures. After execution, the server evaluates the robot's work and checks its understanding. Based on the evaluation results, the next training schedule is automatically generated. If the robot performs well, an emotion engine provides praise feedback.

[0819] As a concrete example, consider a robot learning a new welding procedure. The generative AI explains the welding procedure, and the robot performs it. After execution, the server evaluates the quality of the weld and checks the robot's understanding. Based on the evaluation results, the next training schedule is automatically generated, and praise feedback is provided if the robot is successful.

[0820] Examples of prompts for generative AI models include:

[0821] "Please provide instructions for learning a new welding procedure. The steps are: 1. Setting up the welding machine; 2. Preparing the components for welding; 3. Performing the weld; 4. Checking the quality of the weld."

[0822] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0823] Step 1:

[0824] The server uses a generative AI model to generate detailed explanations based on the curriculum guidelines.

[0825] Input: Curriculum data, user learning history

[0826] Data processing: A generative AI model analyzes the input data and generates appropriate explanations.

[0827] Output: Detailed explanatory text

[0828] Specific operation: The server references the user's learning history and sends prompts to the generative AI model to generate explanations based on the curriculum guidelines. The generative AI model then generates explanatory text and returns it to the server.

[0829] Step 2:

[0830] The server provides the generated explanatory text to the user.

[0831] Input: Generated description text

[0832] Data processing: Present explanatory text in a format appropriate for the user.

[0833] Output: Descriptive text that is displayed on the user's terminal

[0834] Specific operation: The server sends the generated explanatory text to the user's terminal and displays it on the user's screen.

[0835] Step 3:

[0836] After reading the explanation, the user answers the questions to check their understanding.

[0837] Input: User's answer

[0838] Data processing: Send the user's answers to the server.

[0839] Output: User response data sent to the server

[0840] Specific operation: After reading the explanation, the user answers the questions displayed as a comprehension check and sends the answers to the server.

[0841] Step 4:

[0842] The server instantly scores the user's answers.

[0843] Input: User response data

[0844] Data processing: Analyze the response data and determine whether it is correct or incorrect.

[0845] Output:Scoring results

[0846] Specific operation: The server analyzes the user's answer data, determines whether the answer is correct or incorrect, and generates a score.

[0847] Step 5:

[0848] The server acquires the user's study log and automatically generates the next study schedule by referring to the results of the comprehension check.

[0849] Input: User's study log, comprehension check results

[0850] Data processing: Analyze the study log and comprehension check results to generate the next study schedule.

[0851] Output: Next study schedule

[0852] Specific operation: The server refers to the user's study log and the results of the comprehension check, and automatically generates the next study schedule.

[0853] Step 6:

[0854] The server uses an emotion engine to detect the user's emotional state and provides feedback according to the learning outcome.

[0855] Input: User emotion data, learning outcomes

[0856] Data processing: Analyze emotional data and learning outcomes to generate appropriate feedback.

[0857] Output: Feedback message

[0858] Specific operation: The server analyzes the user's emotional data and learning results, and uses the emotion engine to generate appropriate feedback messages and provide them to the user.

[0859] Step 7:

[0860] The server uses generative AI to explain new work procedures and machine operation methods to factory robots.

[0861] Input: Work procedure data, machine operation method data

[0862] Data processing: A generative AI model analyzes the input data and generates appropriate explanations.

[0863] Output:Descriptive text

[0864] Specific operation: The server sends work procedure data and machine operation method data to the generative AI model and generates explanatory text.

[0865] Step 8:

[0866] The factory robot executes the work procedure based on the generated explanation.

[0867] Input:Descriptive text

[0868] Data processing: Performing work procedures based on explanatory text.

[0869] Output: Work results

[0870] Specific operation: The factory robot executes the work procedure based on the generated explanatory text and sends the results to the server.

[0871] Step 9:

[0872] The server evaluates the work of the factory robot and checks the level of understanding.

[0873] Input: Work result data

[0874] Data processing: Analyze and evaluate the work result data.

[0875] Output: Evaluation results

[0876] Specific operation: The server analyzes the work result data of the factory robot and generates an evaluation result.

[0877] Step 10:

[0878] The server automatically generates the next training schedule based on the evaluation results.

[0879] Input: Evaluation result

[0880] Data processing: Analyze the evaluation results and generate the next training schedule.

[0881] Output: Next training schedule

[0882] Specific operation: The server refers to the evaluation results and automatically generates the next training schedule.

[0883] Step 11:

[0884] The server praises the robot's performance and provides motivational feedback.

[0885] Input: Evaluation results, emotion data

[0886] Data processing: Analyze the evaluation results and emotion data to generate appropriate feedback.

[0887] Output: Feedback message

[0888] Specific operation: The server analyzes the evaluation results and emotion data, uses the emotion engine to generate appropriate feedback messages, and provides them to the robot.

[0889] 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.

[0890] 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> ) 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.

[0891] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[0892] 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.

[0893] [Second embodiment]

[0894] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0895] 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.

[0896] 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).

[0897] 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.

[0898] 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.

[0899] 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).

[0900] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[0901] 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.

[0902] 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.

[0903] 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.

[0904] 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.

[0905] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0906] "Example 1"

[0907] The system of the present invention uses a generative AI that has learned the curriculum guidelines to provide detailed and extensive explanations to questions from learners. Specifically, when a learner asks a question about a math problem, the generative AI generates a detailed explanation based on the curriculum guidelines and provides it to the learner.

[0908] "Example 2"

[0909] Furthermore, the system of the present invention has a function of instantly scoring essay questions submitted by learners. Specifically, when a learner submits an English composition, the system scores the composition and provides immediate feedback.

[0910] "Example 3"

[0911] Furthermore, the system of the present invention has the function of confirming the learner's level of understanding by combining explanations and comprehension checks. Specifically, the system poses questions to confirm the learner's level of understanding for the explanations provided by the generative AI. The learner's level of understanding is confirmed by answering these questions.

[0912] "Example 4"

[0913] Furthermore, the system of the present invention has the function of acquiring a learner's study log and scheduling the study by referring to the results of the comprehension check. Specifically, the learner records the amount of time and content of study for each day as a log, and the next study schedule is automatically generated based on the log and the results of the comprehension check.

[0914] The processing flow of each embodiment will be described below.

[0915] "Example 1"

[0916] Step 1: The learner types in a question about a math problem.

[0917] Step 2: The system uses generative AI that has learned the curriculum guidelines to generate detailed explanations.

[0918] Step 3: The generated explanation is provided to the learner, who then refers to it to further their learning.

[0919] "Example 2"

[0920] Step 1: Learners submit their English compositions to the system.

[0921] Step 2: The system grades the submitted essay and generates feedback along with the grade.

[0922] Step 3: The generated feedback is provided to the learner, who then refers to it to further their learning.

[0923] "Example 3"

[0924] Step 1: The system asks questions to confirm the level of understanding of the explanation provided by the generative AI.

[0925] Step 2: Learners answer the questions posed.

[0926] Step 3: The system evaluates the learner's answers to verify their understanding.

[0927] "Example 4"

[0928] Step 1: Learners log their daily study time and learning content into the system.

[0929] Step 2: The system automatically generates the next learning schedule based on the learner's log and the results of the comprehension check.

[0930] Step 3: The generated learning schedule is provided to the learner, who then follows the schedule.

[0931] Example 1

[0932] Next, a description will be given of Example 1 of Form 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."

[0933] In conventional learning support systems, learners had to refer to multiple learning materials to obtain detailed explanations on a specific field, making efficient learning difficult. Furthermore, correction of essay questions, comprehension checks, and learning progress management were often done manually, placing a heavy burden on learners. Furthermore, when learners had questions, it was difficult to obtain detailed explanations immediately, which led to a decline in the quality of their learning.

[0934] 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.

[0935] In this invention, the server includes means for providing detailed and extensive explanations by a generative AI that has studied the curriculum guidelines, means for instantly marking corrections to written questions, means for providing explanations and comprehension checks, means for acquiring study logs and scheduling by referring to comprehension checks, means for receiving questions from users and generating and inputting prompt sentences to the generative AI model, means for receiving explanations from the generative AI model and providing them to users, and means for sending questions from the user's terminal and receiving and displaying explanations. This allows learners to efficiently obtain detailed explanations, automates corrections of written questions, comprehension checks, and learning progress management, and improves the quality of learning.

[0936] "Course of Study" is an official guideline that defines the educational content and learning objectives provided by educational institutions.

[0937] "Generative AI" is artificial intelligence that uses natural language processing technology to generate new text based on input text.

[0938] "Detailed and extensive explanation" means providing in-depth explanations of a particular topic and a wide range of related information.

[0939] "Written question correction" is the process of evaluating the answers written by learners and indicating whether they are correct or incorrect and what areas need improvement.

[0940] "Instant grading" means evaluating answers submitted by learners in real time and returning results quickly.

[0941] "Explanation and comprehension check" means providing learners with an explanation and conducting tests and questions to check their understanding of the content.

[0942] "Study logging" means recording a learner's learning activities and progress.

[0943] "Scheduling" means creating a study plan for learners and managing their time to progress efficiently.

[0944] "Receiving a question from a user" means receiving a question posed to the system by a learner.

[0945] "Generating and inputting a prompt sentence to a generative AI model" means creating an input sentence for the generative AI to generate an explanation based on the received question and passing it to the AI.

[0946] "Receiving commentary from a generative AI model" means receiving commentary generated by a generative AI.

[0947] "Providing to the user" means displaying the received commentary to the learner and making it available for use.

[0948] "Sending a question from the user's terminal" means sending a question to the system from the device used by the learner.

[0949] "Receiving and displaying explanations" means displaying the explanations returned from the system on the learner's device.

[0950] This invention is a system that uses generative AI that has learned curriculum guidelines to provide detailed and extensive explanations in response to questions from learners. Specific embodiments of this system are described below.

[0951] Server Roles

[0952] The server hosts a generative AI model that has learned the curriculum guidelines. This generative AI model is, for example, a model with advanced natural language processing technology. The server receives a question from a user and generates a prompt sentence to input the question into the generative AI model. The generative AI model generates a detailed explanation based on the prompt sentence and returns the explanation to the server. The server provides the generated explanation to the user.

[0953] Device Role

[0954] The terminal is a device used by the learner, such as a PC or smartphone. The learner uses the terminal to input questions about the learning content. The terminal sends the questions to the server, receives and displays the explanations returned from the server, and allows the learner to view detailed explanations and advance their learning.

[0955] User Roles

[0956] The user is a learner, such as a high school or university student. The user uses a terminal to input questions related to the content of their study. The questions input by the user are sent to the server via the terminal. The explanations returned from the server are then received by the user on the terminal and used to help with their studies.

[0957] Specific examples

[0958] Example 1

[0959] If a user asks, "What are the basic concepts of differentiation?", the following prompt sentence is input to the generative AI model:

[0960] Example prompt sentence:

[0961] "Please teach me the basic concepts of differentiation."

[0962] The server inputs this prompt into a generative AI model, which generates an explanation like this:

[0963] An example of a generated commentary:

[0964] "Differentiation is a mathematical technique for determining the rate of change of a function. Specifically, it shows how the output value of a function changes when the input value changes slightly. For example, the derivative of a function f(x) is expressed as f'(x), which shows the slope of f(x)."

[0965] Example 2

[0966] If a user asks, "What are some applications of integrals?", the following prompt sentence is input to the generative AI model:

[0967] Example prompt sentence:

[0968] "Please give me some examples of applications of integrals."

[0969] The server inputs this prompt into a generative AI model, which generates an explanation like this:

[0970] An example of a generated commentary:

[0971] "Integrals are widely used to calculate areas and volumes. For example, integrals are used to calculate the area under a curve or the volume of a solid of revolution. For example, integrals are used to calculate the area of ​​the region enclosed by the curve y = x^2 and the x-axis."

[0972] In this way, the system of the present invention supports learning by providing detailed and extensive explanations in response to questions from learners.

[0973] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0974] Step 1:

[0975] The user uses the terminal to input questions about the learning content.

[0976] Specific operation: The user enters a question into the input form on the terminal and clicks the send button.

[0977] Input: A user-entered question (e.g., "What are the basic concepts of differentiation?")

[0978] Output: The HTTP request generated by the device

[0979] Step 2:

[0980] The terminal sends the user's question to the server.

[0981] Specific operation: The terminal creates an HTTP request and sends it to the server.

[0982] Input: The question entered by the user

[0983] Output: HTTP request sent to the server

[0984] Step 3:

[0985] The server receives the user's question sent from the terminal.

[0986] Specific operation: The server receives the HTTP request and analyzes the question.

[0987] Input: HTTP request sent from the terminal

[0988] Output: Parsed question

[0989] Step 4:

[0990] Based on the received question, the server generates a prompt sentence to be input into the generative AI model.

[0991] Specific operation: The server converts the question content into an appropriate format and passes it to the generative AI model.

[0992] Input: Parsed question content

[0993] Output: Generated prompt sentence (e.g., "Please teach me the basic concepts of differentiation")

[0994] Step 5:

[0995] The server inputs the generated prompt sentence into the generative AI model.

[0996] Specific operation: The server sends a prompt to the generative AI model via the API.

[0997] Input: Generated prompt text

[0998] Output: Input to a generative AI model

[0999] Step 6:

[1000] The generative AI model generates detailed explanations based on the prompt.

[1001] Specific operation: The generative AI model uses internal learning data and algorithms to generate an explanation and send it back to the server.

[1002] Input: Input to the generative AI model (prompt sentence)

[1003] Output: Generated commentary

[1004] Step 7:

[1005] The server receives the generated commentary and sends it to the terminal.

[1006] Specific operation: The server returns the explanation to the terminal as an HTTP response.

[1007] Input: Generated commentary

[1008] Output: HTTP response sent to the device

[1009] Step 8:

[1010] The terminal receives the commentary returned from the server.

[1011] Specific operation: The terminal receives the HTTP response and analyzes the explanatory content.

[1012] Input: HTTP response sent from the server

[1013] Output: Parsed commentary

[1014] Step 9:

[1015] The terminal displays the received explanation to the user.

[1016] Specific behavior: Updates the view to display the description in the device UI.

[1017] Input: Parsed commentary

[1018] Output: A description that is displayed to the user

[1019] Step 10:

[1020] The user can understand the received explanation and use it to help with their studies.

[1021] Specific actions: The user reads the explanation and takes notes as needed to progress through the learning process.

[1022] Input: The description displayed to the user

[1023] Output: User understanding and learning progression

[1024] (Application example 1)

[1025] Next, a description will be given of Application Example 1 of Form 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."

[1026] With conventional learning systems, it was difficult for learners to receive detailed and comprehensive explanations immediately when they asked questions, and they often did not provide appropriate feedback or scheduling based on the learner's level of understanding. This led to problems such as reduced learning efficiency and a loss of motivation to learn. Furthermore, even in brick-and-mortar cram schools and educational facilities, it was difficult to provide prompt and accurate explanations to individual questions.

[1027] 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.

[1028] In this invention, the server includes a means for providing detailed and extensive explanations by a generative AI that has studied the curriculum guidelines, a means for instantly marking corrections to written questions, a means for providing explanations and checking comprehension, a means for acquiring study logs and scheduling by referring to comprehension checks, a means for inputting questions from learners, a means for generating explanations using a generative AI model, and a means for displaying the generated explanations to the learner. This allows learners to instantly receive detailed and extensive explanations when they ask questions, and enables appropriate feedback and scheduling according to the learner's level of understanding.

[1029] The "Course of Study" is a set of teaching standards that systematically compile the knowledge and skills that learners should acquire at educational institutions.

[1030] "Generative AI" is artificial intelligence that generates new information or commentary based on given data or prompts.

[1031] A "detailed and wide-ranging explanation" is an explanation that provides a deep and multifaceted view of a specific question.

[1032] "Written question correction" is the process of evaluating the answers written by learners and indicating whether they are correct or incorrect and what areas need improvement.

[1033] A "comprehension check" is a test or question that assesses how well a learner has understood the content.

[1034] "Scheduling" refers to the process of creating a learner's study plan and managing time to progress efficiently.

[1035] "Means for inputting questions from learners" refers to an interface that allows learners to input doubts or queries into the system.

[1036] "Means for generating explanations using a generative AI model" refers to a process of automatically creating explanations for learners' questions using generative AI.

[1037] "Means for displaying the generated explanation to the learner" refers to an interface for visually providing the learner with the explanation created by the generative AI.

[1038] The system for implementing this invention uses generative AI that has learned the curriculum guidelines to provide detailed and extensive explanations to questions from learners. The system consists of a server and a terminal, and operates as follows.

[1039] Hardware and software used

[1040] Hardware: Servers, smartphones, tablets, smart glasses

[1041] Software: Python, OpenAI API

[1042] Data processing and calculation

[1043] Server Processing

[1044] The server receives questions from learners and generates explanations using a generative AI model. Specifically, the process is as follows:

[1045] 1. Entering a question: The learner enters a question using a device (smartphone, tablet, smart glasses).

[1046] 2. Prompt generation: The server generates a prompt based on the input question. The prompt is an instruction for the generative AI model to generate an explanation.

[1047] 3. Calling the generative AI model: The server uses the OpenAI API to send a prompt to the generative AI model (e.g., GPT-3) to generate an explanation.

[1048] 4. Acquisition and display of explanation: The server acquires the generated explanation and sends it to the terminal, which visually displays the explanation to the learner.

[1049] Specific examples

[1050] If a learner asks, "What is the formula for solving a quadratic equation?", the server generates the following prompt:

[1051] Based on the curriculum guidelines, please provide a detailed explanation for the following mathematics problem.

[1052] Question: What is the formula for solving a quadratic equation?

[1053] Description:

[1054] Based on this prompt, the generative AI model generates a detailed explanation, which the server sends to the learner's device, where the learner can view the explanation on their device screen.

[1055] summary

[1056] This system allows learners to instantly receive detailed and comprehensive explanations when they ask questions. It also enables appropriate feedback and scheduling based on the learner's level of understanding. This is expected to improve learning efficiency and maintain motivation to learn.

[1057] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1058] Step 1:

[1059] The user uses the terminal to enter a question.

[1060] Input: A question that the user types into the terminal (e.g., "What is the formula for solving a quadratic equation?")

[1061] Output: Question data entered on the terminal

[1062] How it works: A user uses a smartphone, tablet, or smart glasses to enter a question in text format. The device receives this input and prepares it to be sent to the server.

[1063] Step 2:

[1064] The terminal transmits the question data to the server.

[1065] Input: Question data entered into the terminal

[1066] Output: Question data sent to the server

[1067] Specific operation: The device sends the question data entered by the user to the server. HTTP or HTTPS is used as the communication protocol.

[1068] Step 3:

[1069] The server receives the question data and generates a prompt.

[1070] Input: Question data sent to the server

[1071] Output: Generated prompt statement

[1072] Specific operation: The server analyzes the received question data and creates a prompt to allow the generative AI model to generate an explanation. For example, it generates a prompt in the format "Please provide a detailed explanation for the following math problem based on the curriculum guidelines. Problem: Please tell me the formula for solving a quadratic equation. Explanation:"

[1073] Step 4:

[1074] The server generates commentary using a generative AI model.

[1075] Input: Generated prompt statement

[1076] Output: Generated commentary data

[1077] How it works: The server uses the OpenAI API to send a prompt to a generative AI model (e.g., GPT-3). The generative AI model generates a detailed explanation based on the prompt and returns the result to the server.

[1078] Step 5:

[1079] The server transmits the generated commentary data to the terminal.

[1080] Input: Generated commentary data

[1081] Output: Commentary data sent to the terminal

[1082] Specific operation: The server receives the generated commentary data and sends it to the user's device. HTTP or HTTPS is used as the communication protocol.

[1083] Step 6:

[1084] The terminal receives the commentary data and displays it to the user.

[1085] Input: Commentary data sent to the terminal

[1086] Output: Explanation displayed on the terminal

[1087] Specific operation: The device analyzes the commentary data received from the server and visually displays it to the user, who can then check the commentary on the device screen.

[1088] Example 2

[1089] Next, a description will be given of Example 2 of Form 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."

[1090] Conventional learning systems have the problem that it takes time to grade essay questions submitted by learners, making it difficult to receive immediate feedback. Furthermore, learners cannot quickly check the evaluation results of their own writing and areas for improvement, which reduces learning efficiency. Furthermore, there is a lack of effective means for providing explanations and checking comprehension, making it difficult to accurately grasp learners' levels of comprehension.

[1091] 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.

[1092] In this invention, the server includes means for a user to submit an English composition from a terminal, means for the terminal to send composition data to the server, means for the server to receive the composition data and perform preprocessing, means for the server to send a prompt to the generative AI model and request evaluation of the composition, means for the generative AI model to evaluate the composition and generate a score and feedback, means for the server to receive the generated feedback and send it to the terminal, and means for the terminal to display the feedback to the user. This makes it possible to instantly score written questions submitted by learners and provide rapid feedback.

[1093] "Course of Study" is an official guideline that defines the educational content and learning objectives provided by educational institutions.

[1094] "Generative AI" is a system that generates text and data using artificial intelligence technology.

[1095] "Explanation" is a detailed and easy-to-understand explanation of a particular topic or issue.

[1096] A "comprehension check" is a test or question that assesses how well a learner understands a particular piece of content.

[1097] "Scheduling" refers to the process of creating a learner's study plan and managing time to progress efficiently.

[1098] A "terminal" is a device used by a user to access the system.

[1099] A "server" is a computer system that processes data and provides services to other devices over a network.

[1100] "Preprocessing" is the initial stage of processing to convert data into a format that is easier to analyze and process.

[1101] A "generative AI model" is an algorithm or system that uses artificial intelligence techniques to generate text or data.

[1102] A "prompt" is an instruction entered into a generative AI model to make it perform a specific task.

[1103] "Feedback" refers to the evaluation and improvement information provided to learners regarding their submitted content.

[1104] This invention is a system that instantly grades and provides feedback on English essays submitted by learners. The system allows users to submit English essays using their terminals, and the server processes and evaluates the essays. Specifically, the system uses the following hardware and software:

[1105] Hardware and software used

[1106] Device: The device on which a user enters and submits their essay. Examples include a computer, tablet, or smartphone.

[1107] Server: A computer system that receives and processes essay data. A server with a high-performance processor and sufficient memory is preferable.

[1108] Natural language processing library: Software for preprocessing text. Specifically, we use spaCy.

[1109] Generative AI model: An artificial intelligence model for evaluating essays. Specifically, we use OpenAI's GPT-3.

[1110] Program processing

[1111] A user submits an English essay to the system using a terminal. The terminal sends the essay data to the server through a web browser. The server first preprocesses the received essay data. This preprocessing includes text tokenization, part-of-speech tagging, and dependency analysis using spaCy.

[1112] The server then sends prompts to the generative AI model GPT-3 to evaluate the essay. The prompts include evaluation criteria and examples of expected answers. GPT-3 then evaluates the essay and generates a score and feedback.

[1113] The generated feedback is sent from the server to the terminal and displayed immediately to the user, allowing the user to immediately check the evaluation results of their essay and areas for improvement.

[1114] Specific examples

[1115] For example, suppose a user submits the following English composition:

[1116] I went to the park yesterday. It was very fun and I played with my friends.

[1117] The server receives this composition, preprocesses it using spaCy, and then sends the following prompt to GPT-3:

[1118] Evaluate the following English composition based on grammar, coherence, and vocabulary. Provide a score out of 10 and give constructive feedback:

[1119] "I went to the park yesterday. It was very fun and I played with my friends."

[1120] GPT-3 evaluates your writing and generates feedback such as:

[1121] Score: 8 / 10

[1122] Feedback: The composition is generally well-written with good grammar and coherence. However, "very fun" could be improved to "a lot of fun" for better expression. Additionally, consider adding more details about what activities you did with your friends.

[1123] This feedback is sent from the server to the terminal and displayed to the user, who can use it to improve their writing.

[1124] In this way, it is possible to instantly mark the essay questions submitted by the learner and provide quick feedback.

[1125] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1126] Step 1:

[1127] A user submits an English composition from a terminal.

[1128] A user accesses the system interface using a web browser, enters an English composition in the text box on the interface, and clicks the "Submit" button. The input is the composition text entered by the user, and the output is the composition data sent to the terminal.

[1129] Step 2:

[1130] The terminal transmits the composition data to the server.

[1131] The terminal converts the composition data entered by the user into JSON format and sends it to the server using an HTTP POST request. The input is the composition text entered by the user, and the output is the JSON-formatted composition data sent to the server.

[1132] Step 3:

[1133] The server receives the composition data and performs preprocessing.

[1134] The server parses the received essay data and performs text tokenization, part-of-speech tagging, and dependency analysis using a natural language processing library (e.g., spaCy). The input is the JSON-formatted essay data sent to the server, and the output is the preprocessed text data.

[1135] Step 4:

[1136] The server sends a prompt to the generative AI model, asking it to evaluate the essay.

[1137] The server generates a prompt to be sent to the generative AI model (e.g., GPT-3) based on the preprocessed text. The prompt includes evaluation criteria and examples of expected answers. The server sends this prompt to the generative AI model's API via an HTTP request. The input is the preprocessed text data and the prompt, and the output is the prompt sent to the generative AI model.

[1138] Step 5:

[1139] A generative AI model evaluates the essay and generates a score and feedback.

[1140] The generative AI model evaluates the essay based on the received prompt and generates a score and feedback, for example, evaluating it in terms of grammar, vocabulary, structure, etc. The input is the prompt sent to the generative AI model, and the output is the generated score and feedback.

[1141] Step 6:

[1142] The server receives the generated feedback and transmits it to the terminal.

[1143] The server receives the scores and feedback returned from the generative AI model, converts them into JSON format, and sends them to the device. The input is the scores and feedback returned from the generative AI model, and the output is the JSON-formatted feedback data sent to the device.

[1144] Step 7:

[1145] The device displays the feedback to the user.

[1146] The device analyzes the received feedback and displays it in a user-friendly format, allowing the user to instantly check the evaluation results and areas for improvement of their essay. The input is the JSON-formatted feedback data sent to the device, and the output is the feedback information displayed to the user.

[1147] (Application example 2)

[1148] Next, a description will be given of Application Example 2 of Form 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."

[1149] Conventional learning systems have the problem that learners do not receive immediate feedback on the essay questions they submit, which reduces learning efficiency. Also, because it takes time to grade essays, it is difficult for learners to quickly identify their weaknesses. Furthermore, because explanations and comprehension checks are not provided sufficiently, it is difficult to accurately evaluate a learner's level of comprehension.

[1150] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1151] In this invention, the server includes: a means for providing detailed and extensive explanations by a generative AI that has studied the curriculum guidelines; a means for instantly grading essay corrections; a means for providing explanations and comprehension checks; a means for recording study logs and scheduling by referencing comprehension checks; and a means for generating prompt sentences based on essays entered or uploaded by learners and providing instant grading results and feedback using a generative AI model. This allows for instant feedback on essay questions submitted by learners, improving learning efficiency. Furthermore, because essays are quickly graded, learners can quickly identify their weaknesses. Furthermore, because explanations and comprehension checks are performed thoroughly, it is possible to accurately evaluate a learner's level of comprehension.

[1152] "Course of Study" is an official guideline that defines the educational content and learning objectives provided by educational institutions.

[1153] "Generative AI" is a type of artificial intelligence that generates natural language, images, etc. from specific input.

[1154] "Explanation" is a detailed and easy-to-understand explanation of a particular topic or issue.

[1155] A "comprehension check" is a test or question that assesses how well a learner understands a particular piece of content.

[1156] "Study logging" refers to collecting records of the learning activities performed by learners.

[1157] "Scheduling" is the process of planning and executing specific tasks or activities at the appropriate time.

[1158] A "prompt sentence" is an input sentence that causes a generative AI to generate a specific output.

[1159] A "generative AI model" is an artificial intelligence model that generates natural language, images, etc. from specific input.

[1160] "Feedback" refers to evaluation and improvement information provided to learners regarding their activities and submissions.

[1161] The following system configuration and processing procedure will be described as an embodiment of the present invention.

[1162] System Configuration

[1163] The system includes a server, learner devices (smartphones, tablets, PCs, etc.), and a generative AI model. The server has the functions of providing detailed and extensive explanations using a generative AI that has studied the curriculum guidelines, instantly marking essay corrections, providing explanations and comprehension checks, recording study logs and scheduling by referencing comprehension checks, generating prompt sentences based on compositions entered or uploaded by learners, and instantly providing marking results and feedback using the generative AI model.

[1164] Hardware and Software

[1165] Hardware: Server, learner's device (smartphone, tablet, PC)

[1166] Software: Python, OpenAI API, database management system (e.g., MySQL)

[1167] Data processing and calculation

[1168] 1. Data entry: Learners use the terminal to enter or upload their English compositions.

[1169] 2. Prompt generation: The server generates prompts based on the input essay, requesting grading and feedback.

[1170] 3. Invoke the generative AI model: The server uses OpenAI's GPT-3 model to input the prompt and generate a score and feedback for the essay.

[1171] 4. Providing feedback: The generated feedback is immediately displayed on the learner's device.

[1172] 5. Log acquisition and scheduling: The server acquires the learner's learning log and proposes the next learning schedule based on the results of the comprehension check.

[1173] Specific examples

[1174] Suppose a learner inputs the following composition:

[1175] This is an example essay written by a student. It contains several grammatical errors and lacks coherence.

[1176] The server generates the following prompt based on this composition:

[1177] Please grade and provide feedback on the following English essays:

[1178] This is an example essay written by a student. It contains several grammatical errors and lacks coherence.

[1179] Scoring and feedback:

[1180] By inputting this prompt into the generative AI model, students can instantly receive scoring results and feedback, which is displayed on their devices, allowing them to instantly see the evaluation of their writing and areas for improvement.

[1181] In this way, the learner can study efficiently and improve his / her understanding.

[1182] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1183] Step 1:

[1184] A user uses a terminal to type or upload an English composition.

[1185] Input: English composition text entered by the user.

[1186] Output: Essay data sent from the device to the server.

[1187] Specific operation: The user opens the application on their device and enters an English composition or uploads an existing composition file. The entered composition data is sent to the server.

[1188] Step 2:

[1189] The server generates a prompt sentence based on the composition data received.

[1190] Input: Essay data received by the server.

[1191] Output: The generated prompt statement.

[1192] Specific operation: The server analyzes the received composition data and generates a prompt sentence like the following:

[1193] Please grade and provide feedback on the following English essays:

[1194] [Composition data]

[1195] Scoring and feedback:

[1196] Step 3:

[1197] The server uses a generative AI model to input prompts and generate scores and feedback for the essay.

[1198] Input: The generated prompt statement.

[1199] Output: Scoring and feedback from the generative AI model.

[1200] Specific operation: The server sends a prompt to OpenAI's GPT-3 model and receives the generated score and feedback.

[1201] Step 4:

[1202] The server transmits the generated feedback to the learner's terminal.

[1203] Input: Scoring and feedback from the generative AI model.

[1204] Output: Feedback displayed on the learner's device.

[1205] Specific operation: The server sends the generated feedback to the learner's device, which displays it. The learner can immediately check the evaluation of their composition and areas for improvement.

[1206] Step 5:

[1207] The server acquires the learner's learning log and suggests the next learning schedule based on the results of the comprehension check.

[1208] Input: Learner's learning log and comprehension check results.

[1209] Output: Next study schedule.

[1210] Specific operation: The server analyzes the learner's past learning log and the results of comprehension checks, and suggests the next learning content and timing. The next learning schedule is displayed on the learner's device.

[1211] Example 3

[1212] Next, a description will be given of Example 3 of Form Example 3. 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."

[1213] Conventional learning systems have difficulty accurately grasping a learner's level of comprehension and providing an appropriate learning schedule based on that. They also lack efficient learning support that combines explanations and comprehension checks. Furthermore, they lack the functionality to automatically generate the next learning plan using the learner's study log.

[1214] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1215] In this invention, the server includes means for generating explanations for the learner using a generative AI model, means for creating questions for a comprehension check based on the generated explanations, means for evaluating the learner's answers, means for acquiring the learner's study log and automatically generating a study schedule based on the results of the comprehension check, and means for conducting the explanations and comprehension check. This makes it possible to accurately grasp the learner's level of comprehension and provide an appropriate study schedule based on that.

[1216] A "generative AI model" is an algorithm that uses artificial intelligence technology to generate and interpret natural language.

[1217] An "explanation" is a piece of writing or content that provides detailed explanations of a particular topic or concept so that it is easy for learners to understand.

[1218] A "comprehension check" is a question or test that assesses how well a learner has understood the content of the explanation.

[1219] A "means for creating questions" is a method or device for generating questions or tasks for assessing comprehension based on an explanation.

[1220] A "means for evaluating answers" is a method or device for determining and evaluating the accuracy and appropriateness of answers submitted by learners.

[1221] A "study log" is a record of a learner's learning activities, including data such as study time and content.

[1222] A "study schedule" is a planned schedule of study time and content for learners to study efficiently.

[1223] "Automatic generating means" refers to a method or device that uses a specific algorithm or program to automatically generate a result without manual intervention.

[1224] The "means for providing explanations and checking comprehension" is a method or device for providing explanations and then asking questions to assess comprehension.

[1225] This invention is a system that uses a generative AI model to generate explanations for a learner, creates questions to check comprehension based on the explanations, evaluates the learner's answers, acquires the learner's study log, and automatically generates the learner's next study schedule. A specific embodiment of this system is described below.

[1226] Hardware and software used

[1227] server

[1228] The server provides the computational resources to run the generative AI model, specifically using the following hardware and software:

[1229] Hardware: A server machine with a powerful CPU, GPU, and sufficient memory

[1230] Software: Generative AI models (e.g., OpenAI's GPT-4), database management systems, web server software

[1231] Terminal

[1232] The terminal is a device that allows learners to read explanations and answer comprehension check questions. Specifically, the following hardware and software are used:

[1233] Hardware: PCs, tablets, smartphones

[1234] Software: Web browser, dedicated application

[1235] Data processing and calculation

[1236] Explanation Generation

[1237] The server uses the generative AI model to generate explanations for the learner. Specifically, it inputs the following prompt sentences into the generative AI model:

[1238] Example prompt: "Please explain the basic concept of differentiation in high school mathematics."

[1239] The generative AI model generates an explanation based on the prompt and returns it to the server. An example of the generated explanation is as follows:

[1240] Example text: "Differentiation is a method for finding the rate of change of a function. For example, suppose we have a function y = x^2. To find the rate of change of this function with respect to x, we get dy / dx = 2x."

[1241] Creating comprehension check questions

[1242] The server creates questions for checking comprehension based on the generated explanatory text. Specifically, it creates the following questions:

[1243] Example of a comprehension check question: "Find the derivative of the following function: y = 3x^3"

[1244] Submit explanations and questions

[1245] The server sends the generated explanatory text and comprehension check questions to the terminal, which then displays them to the learner.

[1246] Evaluating answers

[1247] When a learner answers a comprehension check question through their device, the device sends the answer to the server. The server receives the learner's answer and evaluates its accuracy. For example, if the learner's answer is "dy / dx = 9x^2," it will be evaluated as correct.

[1248] Acquiring learning logs and generating schedules

[1249] The server collects the learner's study log, which records the amount of time spent studying each day and the content of the study. Based on this log and the results of the comprehension check, the server automatically generates the next study schedule. For example, if the result of the comprehension check is 80%, the server will suggest "spend one hour reviewing differentiation and the remaining hour studying the basic concepts of integration."

[1250] The above is a specific embodiment for carrying out the present invention. This system makes it possible to accurately grasp the learner's level of understanding and provide an appropriate study schedule based on that understanding. The flow of the specification process in the third embodiment will be described with reference to FIG.

[1251] Step 1:

[1252] The server uses a generative AI model to generate explanations for the learner.

[1253] Input: Prompt sentence (e.g., "Please explain the basic concept of differentiation in high school mathematics.")

[1254] Data processing: The generative AI model analyzes the prompt and generates an appropriate explanation.

[1255] Output: Explanation (e.g., "Differentiation is a method for finding the rate of change of a function. For example, suppose there is a function y = x^2. The rate of change of this function with respect to x is found to be dy / dx = 2x.")

[1256] Step 2:

[1257] The server creates questions for checking the level of understanding based on the generated commentary.

[1258] Input: Description

[1259] Data processing: Analyze the content of the explanatory text and generate questions to assess comprehension.

[1260] Output: Comprehension check question (e.g., "Find the derivative of the following function: y = 3x^3")

[1261] Step 3:

[1262] The server sends the generated explanatory text and comprehension check questions to the terminal.

[1263] Input: explanatory text, comprehension check questions

[1264] Data processing: The explanatory text and questions are packaged and converted into a data format for transmission to the terminal.

[1265] Output: Data sent to the terminal

[1266] Step 4:

[1267] The terminal displays the explanatory text and comprehension check questions sent from the server to the learner.

[1268] Input: Data sent from the server

[1269] Data processing: Convert the received data into a display format and display it on the screen.

[1270] Output: Explanations and questions that students can view

[1271] Step 5:

[1272] The user answers the comprehension check questions displayed on the terminal.

[1273] Input: Comprehension check question

[1274] Data processing: Solve the problems and enter the answers.

[1275] Output: Response data

[1276] Step 6:

[1277] The terminal transmits the user's answer to the server.

[1278] Input: User response data

[1279] Data processing: Convert the response data into a data format for sending to the server.

[1280] Output: Answer data sent to the server

[1281] Step 7:

[1282] The server receives the user's answers and evaluates their accuracy.

[1283] Input: User response data

[1284] Data processing: Analyze the response data and evaluate it by comparing it with the correct answer.

[1285] Output: Evaluation result (e.g. correct answer, incorrect answer, score, etc.)

[1286] Step 8:

[1287] The server acquires the learner's study log and automatically generates a study schedule based on the results of the comprehension check.

[1288] Input: Learner's study log, comprehension check results

[1289] Data processing: Analyze the study log and comprehension check results to generate the next study schedule.

[1290] Output: Study schedule (e.g., "1 hour review of differentiation, 1 hour learning basic concepts of integration")

[1291] The above are the specific processing steps of the program of this system.

[1292] (Application example 3)

[1293] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1294] Conventional learning support systems lack the functionality to check a learner's level of understanding in real time and automatically generate the next learning schedule based on that information. Furthermore, they do not adequately provide an interface that allows learners to easily progress through their studies using their smartphones. This leads to issues such as reduced learning efficiency and difficulty in effective learning.

[1295] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1296] In this invention, the server includes a means for providing detailed and wide-ranging explanations by generative AI that has studied the curriculum guidelines, a means for instantly marking corrections to written questions, a means for providing explanations and checking comprehension, a means for scheduling by acquiring a study log and referring to the comprehension check, a means for providing explanations to learners and checking comprehension via an application installed on a smartphone, and a means for recording the learner's study log and automatically generating the next study schedule. This makes it possible to check the learner's level of comprehension in real time and automatically generate the next study schedule based on that.

[1297] A "course of study" is an official guideline that defines the content and goals that learners should learn at an educational institution.

[1298] "Generative AI" is a system that uses artificial intelligence technology to generate new information and content.

[1299] A "detailed and extensive explanation" is one that provides a deep and comprehensive explanation of a particular topic.

[1300] "Written question correction" is the process of evaluating the answers written by learners and indicating whether they are correct or incorrect and what areas need improvement.

[1301] A "comprehension check" is a test or question that assesses how much a learner understands about a particular topic.

[1302] "Study logging" refers to collecting records of the learning activities performed by learners.

[1303] "Scheduling" means planning learners' learning activities and creating timetables and plans to carry them out efficiently.

[1304] "Applications installed on smartphones" refers to software that is downloaded to a mobile phone terminal and used.

[1305] A "learner's learning log" is a detailed record of the learning activities undertaken by a learner.

[1306] "Automatically generating the next learning schedule" means automatically planning the next learning content and time based on the learner's past learning data and level of understanding.

[1307] The system for implementing this invention mainly uses a server, a smartphone, and a generative AI model. The server includes a means for providing detailed and extensive explanations by a generative AI that has studied the curriculum guidelines, a means for instantly marking essay corrections, a means for providing explanations and checking comprehension, and a means for recording study logs and scheduling by referencing comprehension checks. An application for providing explanations to learners and checking comprehension is installed on the smartphone.

[1308] The server uses a generative AI model (e.g., OpenAI GPT-3) to provide explanations on specific topics to learners. For example, to provide explanations on basic concepts in mathematics, the server inputs the following prompt sentence into the generative AI model: "Please explain the basic concepts of mathematics."

[1309] The application installed on a smartphone displays explanations provided by the generative AI model to the learner, then asks questions to check their comprehension, which the learner answers. The answers are sent to a server and instantly scored.

[1310] The server records the learner's learning log and automatically generates the next study schedule based on the results of the comprehension check. For example, if a learner studies a mathematics topic for 60 minutes and receives a high score on the comprehension check, the server can suggest physics as the next study topic.

[1311] This system allows learners to easily progress through their studies using their smartphones, check their level of understanding in real time, and automatically generate their next study schedule based on that.

[1312] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1313] Step 1:

[1314] The server receives as input the topic the learner wants to learn. For example, the learner may input that they want to learn about "basic concepts of mathematics." Based on this input, the server generates and sends a prompt to the generative AI model: "Please explain the basic concepts of mathematics."

[1315] Step 2:

[1316] The generative AI model generates an explanation based on the prompt received from the server. The generated explanation is sent back to the server. For example, the generated explanation might be, "Mathematics is the study of numbers, quantities, structures, space, etc."

[1317] Step 3:

[1318] The server sends the explanations returned by the generative AI model to an application installed on the smartphone, which then displays the explanations to the learner. The learner reads the explanations and deepens their understanding.

[1319] Step 4:

[1320] After displaying the explanation, the server generates a question to check the learner's comprehension. For example, it generates a question such as, "What are the basic concepts of mathematics?" This question is sent to the learner's smartphone and displayed to them.

[1321] Step 5:

[1322] Learners answer comprehension check questions via their smartphones. The answers are sent from the smartphone to the server. For example, a learner might answer, "Mathematics is the study of numbers, quantities, structures, and spaces."

[1323] Step 6:

[1324] The server receives the learner's answers and immediately scores them. The scoring results are used to evaluate the learner's level of understanding. For example, a learner who answers correctly will receive a high score.

[1325] Step 7:

[1326] The server records the learner's learning log, which includes the learning topic, study time, and comprehension check results. For example, a log may be recorded stating, "I studied basic concepts of mathematics for 60 minutes and scored 90 points on the comprehension check."

[1327] Step 8:

[1328] The server automatically generates the next learning schedule based on the learning log and the results of the comprehension check. For example, it may suggest "Fundamental Laws of Physics" as the next learning topic. This schedule is sent to the learner's smartphone and displayed to them.

[1329] Step 9:

[1330] Learners can proceed with their studies by following the next study schedule displayed on their smartphone, which allows them to study efficiently.

[1331] 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.

[1332] "Example 1"

[1333] One embodiment of the present invention is a learning support system incorporating an emotion engine. This system recognizes a learner's emotions and reflects the results in learning instruction. Specifically, if a learner feels that they are struggling with a lesson, the emotion engine captures this information and adjusts the instructional method for the learner. For example, when a learner is facing a difficult problem, the emotion engine detects their stress and the system responds by providing more detailed explanations or additional learning materials.

[1334] "Example 2"

[1335] The emotion engine is also used to adjust the learning schedule. The system optimizes the learning schedule according to the learner's emotional state. For example, if the learner feels tired, the system will shorten the learning time that day and increase the time for relaxation and rest. This reduces the learner's stress and improves learning efficiency.

[1336] "Example 3"

[1337] Furthermore, the emotion engine can also be used to increase learner motivation. For example, when a learner achieves a certain goal, the emotion engine detects their joy and the system provides feedback praising their achievement, thereby enhancing the learner's sense of accomplishment and maintaining their motivation to learn.

[1338] "Example 4"

[1339] In this way, the system of the present invention, which incorporates an emotion engine, can properly understand the learner's emotions and provide optimal learning support accordingly, allowing the learner to study more efficiently and enjoyably.

[1340] The processing flow of each embodiment will be described below.

[1341] "Example 1"

[1342] Step 1: Learners engage in the learning task.

[1343] Step 2: The emotion engine monitors the learner's emotions in real time and evaluates their emotional state.

[1344] Step 3: If the emotion engine determines that the learner is struggling, it communicates this information to the learning support system.

[1345] Step 4: The learning support system adjusts the teaching method for the learner based on the information from the emotion engine.

[1346] "Example 2"

[1347] Step 1: Learners follow a study schedule.

[1348] Step 2: The emotion engine monitors the learner's emotions in real time and evaluates their emotional state.

[1349] Step 3: If the emotion engine determines that the learner is fatigued, it communicates this information to the learning support system.

[1350] Step 4: The learning support system adjusts the learning schedule based on the information from the emotion engine.

[1351] "Example 3"

[1352] Step 1: Learners engage in the learning task.

[1353] Step 2: When a learner achieves a specific goal, the emotion engine detects their joy. Step 3: The emotion engine communicates the information it has detected about the learner's joy to the learning support system. Step 4: The learning support system provides feedback to the learner based on the information from the emotion engine.

[1354] "Example 4"

[1355] Step 1: Learners engage in the learning task.

[1356] Step 2: The emotion engine monitors the learner's emotions in real time and evaluates their emotional state.

[1357] Step 3: Based on the information from the emotion engine, the learning support system provides optimal learning support.

[1358] Example 1

[1359] Next, a description will be given of Example 1 of Form 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."

[1360] Conventional learning support systems often provide insufficient explanations for learners' questions and do not take into account the learner's feelings when providing instruction. Furthermore, because corrections of written questions and comprehension checks are performed manually, they lack immediacy. Furthermore, scheduling to effectively manage learners' progress is difficult.

[1361] 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.

[1362] In this invention, the server includes a means for providing detailed and extensive explanations by a generative AI that has learned the curriculum guidelines, a means for instantly marking corrections to written questions, a means for providing explanations and comprehension checks, a means for recording study logs and scheduling by referring to comprehension checks, a means for recognizing the user's emotions and reflecting the results in learning instruction, a means for inputting questions into a generative AI model and generating explanations, a means for providing the generated explanations to the user, and a means for providing additional explanations and materials based on emotional data. This allows for the provision of detailed and extensive explanations to learners' questions, enabling instruction that takes learners' emotions into consideration, and automating the instant marking of written questions and comprehension checks, thereby improving the effectiveness of learning.

[1363] "Course of Study" is an official guideline that defines the educational content and learning objectives provided by educational institutions.

[1364] "Generative AI" is a type of artificial intelligence, a system that has the ability to generate new information and explanations based on input data.

[1365] A "detailed and broad explanation" is one that provides in-depth explanations of specific questions and covers a wide range of related knowledge.

[1366] "Written question correction" is the process of evaluating the answers written by learners and pointing out correct and incorrect answers and areas for improvement.

[1367] "Instant grading" means evaluating answers submitted by learners in real time and returning the results immediately.

[1368] "Explanation and comprehension check" is a process in which an explanation is provided to learners and then questions are asked to check their comprehension.

[1369] "Study logging" means recording a learner's learning activities and saving that data.

[1370] "Scheduling based on comprehension checks" means planning the next learning content and timing based on the learner's level of comprehension.

[1371] "Recognizing the user's emotions" means judging the learner's emotional state by analyzing their facial expressions, tone of voice, etc.

[1372] "Reflecting on learning instruction" means adjusting the instruction method for the learner based on the recognized emotional data.

[1373] "Inputting a question into a generative AI model" refers to the process of inputting a learner's question into a generative AI and generating an explanation.

[1374] "Providing the generated explanation to the user" means displaying the explanation generated by the generative AI to the learner.

[1375] "Providing additional explanations and materials based on emotional data" means providing additional explanations and learning materials as needed, taking into account the learner's emotional state.

[1376] This invention is a system that uses generative AI that has learned the curriculum guidelines to provide detailed and extensive explanations to questions from learners. Specifically, the system works in cooperation with the server, terminal, and user elements.

[1377] Hardware and software used

[1378] The server is a high-performance computer that provides an environment for running generative AI models. Specifically, OpenAI's GPT-4 is used as the generative AI model. The server also includes software for running emotion engines (e.g., Affectiva or Microsoft Azure's Emotion API).

[1379] The terminal is a device used by the user, such as a PC or smartphone, that communicates with the server through a web browser or mobile application. The terminal provides an interface for the user to enter questions and receive answers.

[1380] Data processing and calculation

[1381] When a user inputs a question using a device, the question is sent from the device to a server. The server inputs the received question into a generative AI model and generates a detailed explanation. The generated explanation is sent from the server to the device and displayed to the user.

[1382] Furthermore, the emotion engine recognizes the user's emotions and sends the data to the server, which then requests additional explanations and learning materials from the generative AI model based on the emotion data, and provides them to the user.

[1383] Specific examples

[1384] For example, consider the case where a user asks, "Please tell me how to solve a quadratic equation." The user opens a web browser on their device and enters the question. The device then sends this question to the server. The server then inputs the received question into a generative AI model (GPT-4) and generates a detailed explanation. The generated explanation is then sent from the server to the device and displayed to the user.

[1385] Example prompt sentence:

[1386] "Please tell me how to solve quadratic equations."

[1387] The emotion engine analyzes the user's facial expressions and tone of voice, and if the user is having difficulty, the server requests additional explanations and learning materials from the generative AI model and provides them to the user. For example, if the user is having difficulty, the server will provide "additional example problems and step-by-step explanations on how to solve quadratic equations."

[1388] In this way, detailed and extensive explanations of learners' questions are provided, and instruction can be given taking into account the learners' feelings.

[1389] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1390] Step 1:

[1391] The user enters a question.

[1392] A user opens a web browser or mobile application on their device and enters a question. For example, they might enter, "Please tell me how to solve a quadratic equation." The input data is the user's question text.

[1393] Step 2:

[1394] The terminal sends a question to the server.

[1395] The terminal sends the user-entered question to the server using the HTTPS protocol. The input data is the user's question text, and the output data is the question text sent to the server.

[1396] Step 3:

[1397] The server inputs the question into a generative AI model.

[1398] The server inputs the received question text into a generative AI model. Specifically, GPT-4 is used as the generative AI model. The input data is the question text sent to the server, and the output data is the question text input into the generative AI model.

[1399] Step 4:

[1400] A generative AI model generates commentary.

[1401] The generative AI model generates detailed explanations based on the input question text. For example, it generates an explanation on "how to solve quadratic equations." The input data is the question text entered into the generative AI model, and the output data is the generated explanation text.

[1402] Step 5:

[1403] The server receives the generated description.

[1404] The server receives the commentary text returned from the generative AI model. The input data is the commentary text returned from the generative AI model, and the output data is the commentary text received by the server.

[1405] Step 6:

[1406] The server sends the description to the terminal.

[1407] The server transmits the generated commentary text to the terminal using the HTTPS protocol. The input data is the commentary text received by the server, and the output data is the commentary text transmitted to the terminal.

[1408] Step 7:

[1409] The terminal displays the explanation to the user.

[1410] The device displays the explanatory text received from the server in a web browser or mobile application. The input data is the explanatory text sent to the device, and the output data is the explanatory text displayed to the user.

[1411] Step 8:

[1412] The emotion engine recognizes the user's emotions.

[1413] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and tone of voice and generate emotion data. The input data is the user's facial expressions and tone of voice, and the output data is the generated emotion data.

[1414] Step 9:

[1415] The server provides additional commentary and materials based on the emotional data.

[1416] The server requests the generative AI model to generate additional explanations and learning materials based on the emotion data obtained from the emotion engine. For example, if the user is having difficulty, the server requests "additional example problems and step-by-step explanations on how to solve quadratic equations" from the generative AI model and provides the generated explanations and materials to the user. The input data is the emotion data obtained from the emotion engine, and the output data is the additional explanations and learning materials.

[1417] (Application example 1)

[1418] Next, a description will be given of Application Example 1 of Form 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."

[1419] Conventional learning support systems and factory support systems have difficulty providing detailed explanations to questions from learners and workers, and are unable to recognize the emotions of learners and workers and provide appropriate support. As a result, learners and workers are unable to receive appropriate support when they face difficult problems, which leads to issues such as reduced learning and work efficiency.

[1420] 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.

[1421] In this invention, the server includes means for providing detailed and extensive explanations by generative AI that has learned the curriculum guidelines, means for instantly marking corrections to written questions, means for providing explanations and checking comprehension, means for recording study logs and scheduling by referring to comprehension checks, means for recognizing learners' emotions using an emotion engine and reflecting the results in learning guidance, means for providing detailed explanations in response to questions from workers in a factory, and means for recognizing workers' emotions using the emotion engine and providing appropriate support. This enables learners and workers to receive detailed explanations and appropriate support when they face difficult problems.

[1422] The "Course of Study" is a set of teaching standards that systematically compile the knowledge and skills that learners should acquire in educational institutions.

[1423] "Generative AI" is an artificial intelligence technology that generates new information and answers based on given data and instructions.

[1424] "Detailed and wide-ranging explanation" refers to providing an in-depth and multifaceted explanation of a specific question or issue.

[1425] "Written question correction" is the process of evaluating the answers written by learners and indicating whether they are correct or incorrect and what areas need improvement.

[1426] "Comprehension checks" refer to tests or questions that are used to assess how well a learner has understood the content.

[1427] "Study logging" refers to collecting records of the learning activities performed by learners.

[1428] "Scheduling" refers to creating a study plan for learners and managing their time to progress efficiently.

[1429] An "emotion engine" is a technology that recognizes the emotional state of learners and workers and responds appropriately based on that.

[1430] A "learner" refers to a person who engages in learning activities in order to acquire specific knowledge or skills.

[1431] "Worker" refers to a person who performs a specific task or work.

[1432] "Questions from workers in the factory" refers to doubts or problems that workers in the factory have related to their work.

[1433] "Appropriate support" refers to providing optimal solutions and assistance to the problems and difficulties that learners and workers face.

[1434] The system for implementing this invention includes a generative AI that has learned the curriculum guidelines, an emotion engine, and a function for providing explanations to questions from workers in a factory. Specific embodiments are described below.

[1435] System Configuration

[1436] The system consists of the following main components:

[1437] 1. Server: Runs the generative AI model and emotion engine.

[1438] 2. Devices: Tablets and smartphones used by learners and workers.

[1439] 3. Users: Learners and factory workers.

[1440] Hardware and software used

[1441] Server: A server with high-performance computing power that runs generative AI models (e.g., OpenAI's GPT-3) and emotion engines (e.g., EmotionEngine).

[1442] Devices: Tablets and smartphones used by learners and workers. These devices communicate with the server to send questions and receive explanations and support.

[1443] Software: Generative AI model, emotion engine, question explanation function, comprehension check function, scheduling function.

[1444] Data processing and calculation

[1445] 1. Entering a question: The user enters a question using a terminal.

[1446] 2. Emotion Recognition: The emotion engine recognizes the user's emotions, for example, determining whether the user is feeling stressed.

[1447] 3. Explanation Generation: The generative AI model generates a detailed explanation for the question. It uses the prompt text to provide an appropriate explanation.

[1448] 4. Providing support: Based on the results of the emotion engine, provide appropriate support. For example, if the user is feeling stressed, provide more detailed explanation or additional support.

[1449] Specific examples

[1450] Learner Examples

[1451] When a learner asks, "Please tell me how to solve this math problem," the emotion engine recognizes the learner's emotions and the generative AI model provides detailed explanations. For example, if the learner is feeling stressed, the system will provide more detailed step-by-step explanations.

[1452] Worker example

[1453] When a factory worker asks, "What is the maintenance procedure for this machine?", the emotion engine recognizes the worker's emotions and the generative AI model provides detailed explanations. For example, if the worker is confused, the system provides simple step-by-step instructions.

[1454] Prompt Sentence Examples

[1455] Factory work question: What are the maintenance procedures for this machine?

[1456] Please provide a detailed explanation.

[1457] In this way, the system can provide detailed explanations and appropriate support for problems faced by learners and workers.

[1458] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1459] Step 1:

[1460] The user uses the terminal to enter a question.

[1461] Input: The user types the question in text format into the terminal.

[1462] Output: The device sends the entered question to the server.

[1463] Specific operation: The user types "Please tell me the maintenance procedure for this machine" into the terminal and presses the send button.

[1464] Step 2:

[1465] The server receives the question and uses an emotion engine to recognize the user's emotion.

[1466] Input: Questions sent from the device and user emotion data.

[1467] Output: The user's emotional state (e.g., stressed, confused, etc.).

[1468] Specific operation: The server analyzes the question, and the emotion engine analyzes the user's voice and facial expression data to recognize "stress."

[1469] Step 3:

[1470] The server uses a generative AI model to generate detailed explanations for the questions.

[1471] Input: User question and emotional state.

[1472] Output: A detailed explanation of the question.

[1473] Specific operation: The server inputs the prompt sentence "Question about factory work: What is the maintenance procedure for this machine? Please provide a detailed explanation" into the generative AI model, and the AI ​​generates a detailed explanation.

[1474] Step 4:

[1475] The server provides appropriate support based on the emotional state.

[1476] Input: Generated commentary and the user's emotional state.

[1477] Output: Tailored commentary and additional support.

[1478] Specific Action: The server recognizes that the user is stressed and adds detailed step-by-step instructions to the generated explanation.

[1479] Step 5:

[1480] The server sends the generated explanations and support content to the device.

[1481] Input: Coordinated commentary and additional support.

[1482] Output: Explanations and supporting content sent to the device.

[1483] Specific operation: The server sends the generated explanation and additional support content to the terminal, allowing the user to view it on the terminal.

[1484] Step 6:

[1485] The user checks the explanations and support content on the device and asks additional questions as needed.

[1486] Input: Explanations and support displayed on the terminal.

[1487] Output: User understanding and follow-up questions.

[1488] Specific operation: The user reads the explanation on the terminal, and if there is any part they do not understand, they enter the question again.

[1489] Example 2

[1490] Next, a description will be given of Example 2 of Form 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."

[1491] Conventional learning systems take time to grade and provide feedback on written questions submitted by learners, resulting in a lack of immediacy. Furthermore, they do not optimize learning schedules to take into account the learner's emotional state, which can lead to reduced learning efficiency. Furthermore, when learners need to refer to other textbooks, explanations are often insufficient. To address these issues, a system is needed that provides instant grading and feedback and optimizes learning schedules according to the learner's emotional state.

[1492] 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.

[1493] In this invention, the server includes means for providing detailed and extensive explanations by a generative artificial intelligence that has studied the curriculum guidelines, means for instantly marking corrections to written questions, means for providing explanations and checking comprehension, means for recording study logs and scheduling by referring to the comprehension checks, means for analyzing essays using natural language processing technology, means for inputting prompt sentences to a generative artificial intelligence model and generating marks and feedback, and means for analyzing the emotional state of the learner using an emotion engine and optimizing the study schedule. This makes it possible to instantly mark written questions submitted by the learner, provide feedback, and optimize the study schedule according to the learner's emotional state.

[1494] "Course of Study" is an official guideline that defines the educational content and learning objectives provided by educational institutions.

[1495] "Generative AI" is AI that has the ability to generate text and data using natural language processing and machine learning techniques.

[1496] "Written question correction" is the process of evaluating free-form responses submitted by learners and pointing out errors and areas for improvement.

[1497] "Explanation" is a detailed and easy-to-understand explanation of a particular topic or issue.

[1498] A "comprehension check" is a test or question that assesses how well a learner understands a particular piece of content.

[1499] "Study logging" is the process of recording learners' learning activities and progress.

[1500] "Scheduling" means creating timetables and plans to efficiently plan and manage learners' learning activities.

[1501] "Natural language processing technology" is a technology that allows computers to understand, interpret, and generate human language.

[1502] A "generative artificial intelligence model" is an artificial intelligence model that has the ability to generate new text or data based on input data.

[1503] A "prompt sentence" is an input sentence that causes a generative artificial intelligence to perform a specific task.

[1504] An "emotion engine" is a technology that analyzes a user's emotional state and responds appropriately based on the results.

[1505] A "study schedule" is a timetable or plan designed to help learners study efficiently.

[1506] This invention is a system that instantly grades essay questions submitted by learners and provides feedback. It also includes a function to optimize the learning schedule according to the learner's emotional state. A specific embodiment of this system is described below.

[1507] The server receives English essays submitted by learners via their devices. The received essays are analyzed using natural language processing technology. Specifically, the Google Cloud Natural Language API is used to evaluate the essay's grammar, vocabulary, structure, etc. The evaluation results are input into a generative AI model (e.g., OpenAI's GPT-4), which scores the essay and generates feedback.

[1508] Next, an emotion engine evaluates the learner's emotional state. The emotion engine analyzes the learner's input data (e.g., self-reports and biometric sensor data) and determines whether the learner is fatigued. The emotion engine uses IBM Watson's Tone Analyzer. Based on the learner's emotional state, the server adjusts the learning schedule. For example, if the server determines that the learner is fatigued, the server will reduce the learning time for that day and increase the time for relaxation and rest.

[1509] As a concrete example, suppose a learner submits the following English composition:

[1510] I have a dog. He name is Max. He is very playful and likes to run in the park.

[1511] The server receives this essay and evaluates its grammar and vocabulary using the Google Cloud Natural Language API. Based on the evaluation results, it inputs the following prompt sentence to the generative AI model (GPT-4):

[1512] Please grade the following English composition and provide feedback:

[1513] "I have a dog. He name is Max. He is very playful and likes to run in the park."

[1514] The generative AI model grades the essay and provides feedback such as:

[1515] Grade: C

[1516] Feedback: The sentence "I have a dog" should be "I have a dog". Also, "He name is Max" should be "His name is Max". Overall, the composition is understandable but contains several grammatical errors.

[1517] Next, if a learner self-reports, "I'm tired today," the emotion engine (IBM Watson Tone Analyzer) analyzes this information and determines that the learner is tired. The server then shortens the study schedule for that day and adjusts it to increase relaxation time.

[1518] In this way, the system can instantly grade a learner's writing, provide feedback, and optimize the learning schedule according to the learner's emotional state.

[1519] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1520] Step 1:

[1521] A user submits an English composition.

[1522] The user uses a terminal to access the system interface and input an English composition. When input is complete, the user clicks the submit button. The input data is the composition text entered by the user. The output is the composition data sent to the server.

[1523] Step 2:

[1524] The server receives the composition.

[1525] The server receives the essay data sent by the user. The received data is temporarily stored in a database. The input data is the essay text submitted by the user. The output is the stored essay data.

[1526] Step 3:

[1527] The server analyzes the essay using natural language processing (NLP) technology.

[1528] The server uses the Google Cloud Natural Language API to analyze the grammar, vocabulary, structure, etc. of the received essay. Specifically, it sends the essay data to the API and receives the analysis results. The input data is the saved essay data. The output is the analysis results.

[1529] Step 4:

[1530] The server inputs prompt sentences into the generative AI model and generates scores and feedback.

[1531] Based on the analysis results, the server inputs a prompt to the generative AI model (e.g., OpenAI's GPT-4). Examples of prompts include:

[1532] Please grade the following English composition and provide feedback:

[1533] "I have a dog. He name is Max. He is very playful and likes to run in the park."

[1534] The generative AI model receives a prompt and generates a score and feedback for the essay. The input data is the analysis result and the prompt. The output is the generated score and feedback.

[1535] Step 5:

[1536] The server provides feedback to the user.

[1537] The server sends the generated feedback to the user's terminal, and the user can check the feedback on the interface. The input data is the generated feedback. The output is the feedback provided to the user.

[1538] Step 6:

[1539] The user inputs an emotional state.

[1540] A user uses a terminal to input their emotional state into the system. For example, they self-report, "I feel tired today." The input data is the emotional state input by the user. The output is the emotional data sent to the server.

[1541] Step 7:

[1542] The server analyzes the emotional state using an emotion engine.

[1543] The server uses IBM Watson's Tone Analyzer to analyze the user's emotional state. It sends the input emotional data to the API and receives the analysis results. The input data is the emotional state entered by the user. The output is the analysis results.

[1544] Step 8:

[1545] The server optimizes the learning schedule.

[1546] The server optimizes the study schedule based on the analysis results. For example, if the server determines that the user is fatigued, it adjusts the schedule to shorten the study time that day and increase the time for relaxation and rest. The input data is the analysis result of the emotional state. The output is the optimized study schedule.

[1547] (Application example 2)

[1548] Next, a description will be given of Application Example 2 of Form 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."

[1549] Conventional learning systems and systems for optimizing the work efficiency of factory robots lack immediate feedback and schedule adjustments based on the state of the learner or worker. In particular, optimal responses based on the learner's level of understanding and emotional state, and the operating state and energy level of the factory robot are required, but no effective means exist for achieving this.

[1550] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1551] In this invention, the server includes a means for providing detailed and extensive explanations by generative AI that has learned the curriculum guidelines, a means for instantly marking written questions, a means for providing explanations and checking comprehension, a means for recording study logs and scheduling by referring to comprehension checks, a means for evaluating work progress in real time and providing instant feedback, and a means for analyzing operating conditions and energy levels and automatically adjusting optimal work schedules. This enables instant feedback and optimal schedule adjustments according to the status of learners and factory robots.

[1552] A "Course of Study" is a teaching plan that systematically summarizes the knowledge and skills that learners should acquire at an educational institution.

[1553] "Generative AI" is a type of artificial intelligence, a system that has the ability to generate new information and answers based on given data and information.

[1554] "Detailed and wide-ranging commentary" means providing in-depth explanations of specific themes or topics and providing a wide range of related knowledge.

[1555] "Written question correction" is the process of determining whether written questions submitted by learners are correct or incorrect and pointing out areas for improvement.

[1556] "Instant grading" means evaluating answers submitted by learners in real time and providing instant results.

[1557] "Explanation and comprehension check" involves providing an explanation to learners, followed by tests and questions to check their level of understanding of the content.

[1558] "Study logging" refers to collecting records of the learning activities performed by learners.

[1559] "Scheduling based on comprehension checks" means creating an optimal learning schedule based on the learner's level of comprehension.

[1560] "Real-time evaluation of work progress" means monitoring and evaluating in real time how far the work has progressed.

[1561] "Providing immediate feedback" means providing evaluation results and areas for improvement instantly.

[1562] "Analyzing operating status and energy levels" means analyzing the current operating status and remaining energy of a robot or system.

[1563] "Automatically adjusting the optimal work schedule" means automatically setting the most efficient work schedule based on the analysis results.

[1564] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The following explains how each element functions.

[1565] server

[1566] The server is equipped with a generative AI that has studied the curriculum guidelines and provides detailed and extensive explanations. The server instantly grades the written questions submitted by the learner, provides explanations and checks the learner's level of understanding, and also keeps a study log and optimizes the learning schedule by referring to the results of the comprehension checks. It also has the function of evaluating the progress of factory robots' work in real time and providing immediate feedback. The server analyzes the robots' operating status and energy levels and automatically adjusts the optimal work schedule.

[1567] Terminal

[1568] The terminal is a device used by the user, and can include smartphones, tablets, and PCs. The terminal displays explanations and feedback provided by the server and provides an interface for the user to submit written questions. The terminal also records the user's learning log and sends it to the server. In the case of a factory robot, the terminal monitors the robot's operating status and energy level and receives feedback from the server.

[1569] User

[1570] Users are learners and factory robot operators. Learners submit written questions via their terminals and receive explanations and feedback from the server. Learners progress through their studies according to the optimal study schedule provided by the server. Factory robot operators monitor the robot's operating status and energy levels and adjust their work based on feedback from the server.

[1571] Specific examples

[1572] For example, when a learner submits an English essay, the server instantly grades it and provides feedback. If the emotion engine determines that the learner is fatigued, the server adjusts the schedule to shorten the study time that day and increase the time for relaxation and rest.

[1573] In the case of a factory robot, when the robot is "assembling parts," the server analyzes the robot's energy level and recommends rest if the energy level is low, or continues normal work if the energy level is high.

[1574] Prompt Sentence Examples

[1575] "If your robot's energy level is low, tell it to stop working and take a rest."

[1576] In this way, immediate feedback and optimal schedule adjustments based on the status of learners and factory robots are possible.

[1577] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1578] Step 1:

[1579] A user submits a written question using a terminal. As input, text data written by the user is entered into the terminal. The terminal sends this text data to the server. As output, the text data is sent to the server.

[1580] Step 2:

[1581] The server inputs the received text data into the generative AI model and scores it immediately. The text data of the user's written questions is input into the generative AI model as input. The generative AI model analyzes the text data and generates a scoring result. The scoring result is generated as output.

[1582] Step 3:

[1583] The server feeds back the generated scoring results to the user. As input, the scoring results from the generative AI model are input to the server. The server sends the scoring results to the device. As output, the scoring results are sent to the device.

[1584] Step 4:

[1585] The terminal displays the scoring results received from the server to the user. As input, the scoring results from the server are input to the terminal. The terminal visually displays the results to the user. As output, the user confirms the scoring results.

[1586] Step 5:

[1587] The server acquires the user's learning log and optimizes the learning schedule by referring to the results of the comprehension check. The user's learning log and the results of the comprehension check are input to the server. The server analyzes this data and generates an optimal learning schedule. The optimized learning schedule is generated as output.

[1588] Step 6:

[1589] The server evaluates the progress of the factory robot's work in real time and provides immediate feedback. The robot's work progress data is entered into the server as input. The server analyzes this data and generates feedback. The feedback is generated as output.

[1590] Step 7:

[1591] The server analyzes the robot's operating status and energy level, and automatically adjusts the optimal work schedule. The robot's operating status data and energy level data are input to the server. The server analyzes this data and generates the optimal work schedule. The optimized work schedule is generated as output.

[1592] Step 8:

[1593] The server sends the generated optimal work schedule to the robot. As input, the optimized work schedule is input to the server. The server sends this schedule to the robot. As output, the optimized work schedule is sent to the robot.

[1594] Step 9:

[1595] The robot performs work according to the optimal work schedule received from the server. The optimized work schedule is input to the robot as input. The robot performs work based on this schedule. The output is the execution of work.

[1596] Example 3

[1597] Next, a description will be given of Example 3 of Form Example 3. 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."

[1598] Conventional learning support systems have difficulty accurately grasping a learner's level of understanding and providing appropriate feedback. Furthermore, they lack learning support that takes into account the learner's emotions and motivation, resulting in problems such as reduced learning efficiency and continuity. Furthermore, automatic generation of learning schedules is inadequate, making it difficult to provide an optimal learning plan that matches each learner's progress and level of understanding.

[1599] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1600] In this invention, the server includes a means for providing detailed and extensive explanations using generative artificial intelligence, a means for instantly scoring written questions, a means for providing explanations and comprehension checks, a means for acquiring a learner's study log and automatically generating a study schedule by referring to the results of the comprehension checks, and a means for analyzing the learner's emotions and providing feedback according to the learner's emotions. This makes it possible to accurately grasp the learner's level of comprehension and provide appropriate feedback. Furthermore, learning support that takes into account the learner's emotions and motivation is realized, improving the efficiency and continuity of learning. Furthermore, it becomes possible to provide an optimal study plan according to each learner's progress and level of comprehension.

[1601] "Generative AI" refers to AI that generates text using natural language processing technology.

[1602] A "detailed and comprehensive explanation" is a piece of content that provides an in-depth and multifaceted explanation of a particular topic.

[1603] An "essay question" is a question in which learners write their answers in free form.

[1604] "Instant grading" refers to the ability to evaluate answers and provide results immediately after a learner submits them.

[1605] "Explanation and comprehension check" is the process of providing learners with an explanation and then asking them questions to check their comprehension.

[1606] A "study log" is a record of the learning activities that a learner has performed.

[1607] "Comprehension check results" refers to an evaluation that indicates how accurately the learner was able to answer the comprehension check questions.

[1608] "Means for automatically generating a learning schedule" refers to a function that automatically creates the next learning plan based on the learner's log and the results of the comprehension check.

[1609] "Means for analyzing emotions" refers to the function of detecting the learner's emotional state and analyzing that information.

[1610] "Means for providing feedback" refers to the function of providing appropriate responses and advice based on the learner's behavior and emotions.

[1611] The present invention relates to a learning support system for improving a learner's level of understanding. A specific embodiment of this system will be described below.

[1612] Providing explanations and checking comprehension

[1613] The server uses generative artificial intelligence (e.g., a model using natural language processing technology) to generate detailed and extensive explanations for the learner. Specifically, the server inputs the prompt sentence into the generative AI model and obtains the explanation. For example, the following prompt sentence is used:

[1614] Explain the main causes of World War II.

[1615] The generative AI model returns the explanatory statement, "The main causes of World War II were economic hardship, political instability, and military expansionism."

[1616] The server sends the generated explanation to the device, which then displays it to the learner.The server then generates comprehension check questions based on the explanation, again using the generative AI model to create the questions.For example, use the following prompt:

[1617] "What is one of the main causes of World War II?"

[1618] The generative AI model returns the question, "What is one of the major causes of World War II?"

[1619] The server sends the generated questions to the terminal, which displays the questions to the learner and receives the answers. The user answers the questions, and the terminal sends the answers to the server. The server evaluates the answers and confirms the learner's level of understanding.

[1620] Learning log acquisition and scheduling

[1621] The user inputs the amount of time spent studying and the content of their studies into the device. For example, the following log is recorded:

[1622] "Today's study time: 2 hours, Study content: Calculus"

[1623] The device records these logs and sends them to the server. The server then references the learning log and the results of the comprehension check and automatically generates the next learning schedule. For example, if a learner's comprehension level is low on a particular topic, the next schedule will include more learning content related to that topic. The next learning schedule will look like this:

[1624] "Tomorrow's lesson: Calculus review, Study time: 2 hours"

[1625] Motivation boosted by emotional engine

[1626] The device collects data to detect the learner's emotions (e.g., facial expression recognition, voice analysis). The collected data is sent to the server, which then uses an emotion engine to analyze the learner's emotions. For example, when a learner achieves a specific goal, the server detects their joy and generates feedback such as:

[1627] "Congratulations! You've solved all the basic calculus problems! That's an amazing achievement!"

[1628] The terminal displays this feedback to the learner.

[1629] In this way, by combining the provision of explanations, checking the level of understanding, acquiring and scheduling learning logs, and improving motivation using an emotion engine, a system is realized that supports learners in efficient and enjoyable learning. The flow of the specific processing in the third embodiment will be described with reference to FIG.

[1630] Step 1:

[1631] The server generates the explanation using generative AI. Specifically, the server inputs the prompt sentence into a generative AI model and obtains the explanation.

[1632] Input: Prompt: "Explain the main causes of World War II."

[1633] Data processing: The generative AI model analyzes the prompt and generates an explanatory text.

[1634] Output: Explanation: "The main causes of World War II were economic hardship, political instability, and military expansionism."

[1635] Step 2:

[1636] The server transmits the generated explanation to the terminal, which displays the explanation to the learner.

[1637] Input:Explanatory text: "The main causes of World War II were economic hardship, political instability, and military expansionism."

[1638] Data processing: Send explanatory text to the terminal.

[1639] Output: Explanation displayed on the terminal

[1640] Step 3:

[1641] The server generates comprehension check questions based on the explanation. Specifically, the server inputs prompt sentences into a generative AI model to create questions.

[1642] Input: Prompt "Name one of the main causes of World War II."

[1643] Data processing: The generative AI model analyzes the prompt and generates a question.

[1644] Output: Question: "What is one of the main causes of World War II?"

[1645] Step 4:

[1646] The server sends the generated questions to the terminal, which displays the questions to the learner and receives the answers, and the user answers the questions.

[1647] Input: Question: "Name one of the main causes of World War II."

[1648] Data processing: Send the question to the terminal and receive the learner's answer.

[1649] Output: Learner's answer "Financial difficulties"

[1650] Step 5:

[1651] The terminal sends the learner's answers to the server, which evaluates the answers and checks the learner's level of understanding.

[1652] Input: Learner's answer "Financial difficulties"

[1653] Data processing: Evaluate the answers and determine whether they are correct.

[1654] Output: Evaluation result "Correct"

[1655] Step 6:

[1656] The user inputs the amount of time spent studying and the content of their studies into the terminal, which then records this information and sends it to the server.

[1657] Input: Learning log "Today's study time: 2 hours, Study content: Calculus"

[1658] Data processing: Record the learning log and send it to the server.

[1659] Output: Training log sent to the server

[1660] Step 7:

[1661] The server refers to the learning log and the results of the comprehension check and automatically generates the next learning schedule.

[1662] Input: Learning log and comprehension check results

[1663] Data processing: Generate the next learning schedule based on the learning log and the results of the comprehension check.

[1664] Output: Next study schedule "Tomorrow's study content: Calculus review, Study time: 2 hours"

[1665] Step 8:

[1666] The terminal collects data for detecting the learner's emotions and transmits the collected data to the server, which then analyzes the learner's emotions using an emotion engine.

[1667] Input: Learner's facial expression data

[1668] Data processing: The emotion engine analyzes facial expression data and detects emotions.

[1669] Output: Emotion analysis result "Joy"

[1670] Step 9:

[1671] The server generates feedback according to the learner's emotions and transmits it to the terminal, which then displays the feedback to the learner.

[1672] Input: Emotion analysis result "joy"

[1673] Data processing: Generate feedback based on the results of sentiment analysis.

[1674] Output: Feedback "Congratulations! You've solved all the basic calculus problems. That's a great achievement!"

[1675] (Application example 3)

[1676] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1677] Conventional learning systems lack the means to check a learner's level of understanding or the means to automatically schedule learning. They also lack sufficient feedback functions to increase learner motivation. Furthermore, there are no training systems in place to enable factory robots to efficiently learn new work procedures or machine operation methods. To solve these issues, a system is needed that integrates explanations and comprehension checks using generative AI, feedback using an emotion engine, and factory robot training.

[1678] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1679] In this invention, the server includes: means for providing detailed and extensive explanations by a generative AI that has studied the curriculum guidelines; means for instantly grading written question corrections; means for providing explanations and checking comprehension; means for recording study logs and scheduling by referring to comprehension checks; means for providing feedback to increase learner motivation using an emotion engine; means for training a factory robot to learn new work procedures or machine operation methods; means for the generative AI to explain work procedures and for the robot to perform those procedures; means for evaluating the robot's work as a comprehension check; means for automatically generating the next training schedule; and means for praising the robot's performance and providing feedback to increase motivation. This enables the learner's level of understanding to be confirmed, an efficient learning schedule to be provided, and efficient training and increased motivation for factory robots.

[1680] The "Course of Study" is a set of guidelines that systematically summarize the knowledge and skills that learners should acquire at educational institutions.

[1681] "Generative AI" is a type of artificial intelligence that generates new information and explanations based on given data and instructions.

[1682] An "explanation" is a detailed and easy-to-understand explanation of a particular theme or content.

[1683] A "comprehension check" is a means of assessing how well a learner has understood the explanations and information provided.

[1684] A "study log" is a record of the learning activities that a learner has performed, including the time spent studying and the content of the study.

[1685] "Scheduling" means the planned allocation of learning content and time in order to efficiently advance learners' learning activities.

[1686] An "emotion engine" is a technology that detects a learner's emotional state and provides feedback accordingly.

[1687] "Feedback" means providing evaluations and comments on learners' behavior and achievements.

[1688] A "factory robot" is a mechanical device used to automate work in a factory.

[1689] "Training" refers to training to learn new work procedures and how to operate machinery.

[1690] A "work procedure" is a set of steps or methods for performing a specific task efficiently and accurately.

[1691] "Evaluation" is the judging of the results of work or actions based on specific criteria.

[1692] "Performance" refers to the outcome or efficiency of a particular task or activity.

[1693] A system for implementing this invention includes: means for providing detailed and extensive explanations by a generative AI that has studied curriculum guidelines; means for instantly grading corrections to written questions; means for providing explanations and checking comprehension; means for recording study logs and scheduling by referring to comprehension checks; means for providing feedback to increase learners' motivation using an emotion engine; means for training a factory robot to learn new work procedures or machine operation methods; means for a generative AI to explain work procedures and for the robot to perform those procedures; means for evaluating the robot's work as a comprehension check; means for automatically generating the next training schedule; and means for praising the robot's performance and providing feedback to increase motivation.

[1694] The server uses a generative AI model to generate detailed explanations based on the curriculum guidelines and provides them to the user. After the user receives the explanation, questions are posed to check their level of understanding, and their answers are immediately scored. This allows the user's level of understanding to be evaluated.

[1695] The server also acquires the user's study log and automatically generates the next study schedule based on the results of the comprehension check, allowing the user to study efficiently. Furthermore, an emotion engine is used to detect the user's emotional state and provide feedback according to the learning results. For example, if the user achieves a specific goal, the emotion engine detects their joy, and the server provides praising feedback.

[1696] For factory robots, generative AI explains new work procedures and machine operation methods, and the robots execute those procedures. After execution, the server evaluates the robot's work and checks its understanding. Based on the evaluation results, the next training schedule is automatically generated. If the robot performs well, an emotion engine provides praise feedback.

[1697] As a concrete example, consider a robot learning a new welding procedure. The generative AI explains the welding procedure, and the robot performs it. After execution, the server evaluates the quality of the weld and checks the robot's understanding. Based on the evaluation results, the next training schedule is automatically generated, and praise feedback is provided if the robot is successful.

[1698] Examples of prompts for generative AI models include:

[1699] "Please provide instructions for learning a new welding procedure. The steps are: 1. Setting up the welding machine; 2. Preparing the components for welding; 3. Performing the weld; 4. Checking the quality of the weld."

[1700] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1701] Step 1:

[1702] The server uses a generative AI model to generate detailed explanations based on the curriculum guidelines.

[1703] Input: Curriculum data, user learning history

[1704] Data processing: A generative AI model analyzes the input data and generates appropriate explanations.

[1705] Output: Detailed explanatory text

[1706] Specific operation: The server references the user's learning history and sends prompts to the generative AI model to generate explanations based on the curriculum guidelines. The generative AI model then generates explanatory text and returns it to the server.

[1707] Step 2:

[1708] The server provides the generated explanatory text to the user.

[1709] Input: Generated description text

[1710] Data processing: Present explanatory text in a format appropriate for the user.

[1711] Output: Descriptive text that is displayed on the user's terminal

[1712] Specific operation: The server sends the generated explanatory text to the user's terminal and displays it on the user's screen.

[1713] Step 3:

[1714] After reading the explanation, the user answers the questions to check their understanding.

[1715] Input: User's answer

[1716] Data processing: Send the user's answers to the server.

[1717] Output: User response data sent to the server

[1718] Specific operation: After reading the explanation, the user answers the questions displayed as a comprehension check and sends the answers to the server.

[1719] Step 4:

[1720] The server instantly scores the user's answers.

[1721] Input: User response data

[1722] Data processing: Analyze the response data and determine whether it is correct or incorrect.

[1723] Output:Scoring results

[1724] Specific operation: The server analyzes the user's answer data, determines whether the answer is correct or incorrect, and generates a score.

[1725] Step 5:

[1726] The server acquires the user's study log and automatically generates the next study schedule by referring to the results of the comprehension check.

[1727] Input: User's study log, comprehension check results

[1728] Data processing: Analyze the study log and comprehension check results to generate the next study schedule.

[1729] Output: Next study schedule

[1730] Specific operation: The server refers to the user's study log and the results of the comprehension check, and automatically generates the next study schedule.

[1731] Step 6:

[1732] The server uses an emotion engine to detect the user's emotional state and provides feedback according to the learning outcome.

[1733] Input: User emotion data, learning outcomes

[1734] Data processing: Analyze emotional data and learning outcomes to generate appropriate feedback.

[1735] Output: Feedback message

[1736] Specific operation: The server analyzes the user's emotional data and learning results, and uses the emotion engine to generate appropriate feedback messages and provide them to the user.

[1737] Step 7:

[1738] The server uses generative AI to explain new work procedures and machine operation methods to factory robots.

[1739] Input: Work procedure data, machine operation method data

[1740] Data processing: A generative AI model analyzes the input data and generates appropriate explanations.

[1741] Output:Descriptive text

[1742] Specific operation: The server sends work procedure data and machine operation method data to the generative AI model and generates explanatory text.

[1743] Step 8:

[1744] The factory robot executes the work procedure based on the generated explanation.

[1745] Input:Descriptive text

[1746] Data processing: Performing work procedures based on explanatory text.

[1747] Output: Work results

[1748] Specific operation: The factory robot executes the work procedure based on the generated explanatory text and sends the results to the server.

[1749] Step 9:

[1750] The server evaluates the work of the factory robot and checks the level of understanding.

[1751] Input: Work result data

[1752] Data processing: Analyze and evaluate the work result data.

[1753] Output: Evaluation results

[1754] Specific operation: The server analyzes the work result data of the factory robot and generates an evaluation result.

[1755] Step 10:

[1756] The server automatically generates the next training schedule based on the evaluation results.

[1757] Input: Evaluation result

[1758] Data processing: Analyze the evaluation results and generate the next training schedule.

[1759] Output: Next training schedule

[1760] Specific operation: The server refers to the evaluation results and automatically generates the next training schedule.

[1761] Step 11:

[1762] The server praises the robot's performance and provides motivational feedback.

[1763] Input: Evaluation results, emotion data

[1764] Data processing: Analyze the evaluation results and emotion data to generate appropriate feedback.

[1765] Output: Feedback message

[1766] Specific operation: The server analyzes the evaluation results and emotion data, uses the emotion engine to generate appropriate feedback messages, and provides them to the robot.

[1767] 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.

[1768] 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> ) 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.

[1769] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[1770] 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.

[1771] [Third embodiment]

[1772] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1773] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1774] 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).

[1775] 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.

[1776] 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.

[1777] 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).

[1778] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[1779] 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.

[1780] 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.

[1781] 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.

[1782] 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.

[1783] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1784] "Example 1"

[1785] The system of the present invention uses generative AI that has learned the curriculum guidelines to provide detailed and extensive explanations to questions from learners. Specifically, when a learner asks a question about a math problem, the generative AI generates a detailed explanation based on the curriculum guidelines and provides it to the learner.

[1786] "Example 2"

[1787] Furthermore, the system of the present invention has a function of instantly scoring essay questions submitted by learners. Specifically, when a learner submits an English composition, the system scores the composition and provides immediate feedback.

[1788] "Example 3"

[1789] Furthermore, the system of the present invention has the function of confirming the learner's level of understanding by combining explanations and comprehension checks. Specifically, the system poses questions to confirm the learner's level of understanding for the explanations provided by the generative AI. The learner's level of understanding is confirmed by answering these questions.

[1790] "Example 4"

[1791] Furthermore, the system of the present invention has the function of acquiring a learner's study log and scheduling the study by referring to the results of the comprehension check. Specifically, the learner records the amount of time and content of study for each day as a log, and the next study schedule is automatically generated based on the log and the results of the comprehension check.

[1792] The processing flow of each embodiment will be described below.

[1793] "Example 1"

[1794] Step 1: The learner types in a question about a math problem.

[1795] Step 2: The system uses generative AI that has learned the curriculum guidelines to generate detailed explanations.

[1796] Step 3: The generated explanation is provided to the learner, who then refers to it to further their learning.

[1797] "Example 2"

[1798] Step 1: Learners submit their English compositions to the system.

[1799] Step 2: The system grades the submitted essay and generates feedback along with the grade.

[1800] Step 3: The generated feedback is provided to the learner, who then refers to it to further their learning.

[1801] "Example 3"

[1802] Step 1: The system asks questions to confirm the level of understanding of the explanation provided by the generative AI.

[1803] Step 2: Learners answer the questions posed.

[1804] Step 3: The system evaluates the learner's answers to verify their understanding.

[1805] "Example 4"

[1806] Step 1: Learners log their daily study time and learning content into the system.

[1807] Step 2: The system automatically generates the next learning schedule based on the learner's log and the results of the comprehension check.

[1808] Step 3: The generated learning schedule is provided to the learner, who then follows the schedule.

[1809] Example 1

[1810] Next, a description will be given of Example 1 of Form 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."

[1811] In conventional learning support systems, learners had to refer to multiple learning materials to obtain detailed explanations on a specific field, making efficient learning difficult. Furthermore, correction of essay questions, comprehension checks, and learning progress management were often done manually, placing a heavy burden on learners. Furthermore, when learners had questions, it was difficult to obtain detailed explanations immediately, which led to a decline in the quality of their learning.

[1812] 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.

[1813] In this invention, the server includes means for providing detailed and extensive explanations by a generative AI that has studied the curriculum guidelines, means for instantly marking corrections to written questions, means for providing explanations and comprehension checks, means for acquiring study logs and scheduling by referring to comprehension checks, means for receiving questions from users and generating and inputting prompt sentences to the generative AI model, means for receiving explanations from the generative AI model and providing them to users, and means for sending questions from the user's terminal and receiving and displaying explanations. This allows learners to efficiently obtain detailed explanations, automates corrections of written questions, comprehension checks, and learning progress management, and improves the quality of learning.

[1814] "Course of Study" is an official guideline that defines the educational content and learning objectives provided by educational institutions.

[1815] "Generative AI" is artificial intelligence that uses natural language processing technology to generate new text based on input text.

[1816] "Detailed and extensive explanation" means providing in-depth explanations of a particular topic and a wide range of related information.

[1817] "Written question correction" is the process of evaluating the answers written by learners and indicating whether they are correct or incorrect and what areas need improvement.

[1818] "Instant grading" means evaluating answers submitted by learners in real time and returning results quickly.

[1819] "Explanation and comprehension check" means providing learners with an explanation and conducting tests and questions to check their understanding of the content.

[1820] "Study logging" means recording a learner's learning activities and progress.

[1821] "Scheduling" means creating a study plan for learners and managing their time to progress efficiently.

[1822] "Receiving a question from a user" means receiving a question posed to the system by a learner.

[1823] "Generating and inputting a prompt sentence to a generative AI model" means creating an input sentence for the generative AI to generate an explanation based on the received question and passing it to the AI.

[1824] "Receiving commentary from a generative AI model" means receiving commentary generated by a generative AI.

[1825] "Providing to the user" means displaying the received commentary to the learner and making it available for use.

[1826] "Sending a question from the user's terminal" means sending a question to the system from the device used by the learner.

[1827] "Receiving and displaying explanations" means displaying the explanations returned from the system on the learner's device.

[1828] This invention is a system that uses generative AI that has learned curriculum guidelines to provide detailed and extensive explanations in response to questions from learners. Specific embodiments of this system are described below.

[1829] Server Roles

[1830] The server hosts a generative AI model that has learned the curriculum guidelines. This generative AI model is, for example, a model with advanced natural language processing technology. The server receives a question from a user and generates a prompt sentence to input the question into the generative AI model. The generative AI model generates a detailed explanation based on the prompt sentence and returns the explanation to the server. The server provides the generated explanation to the user.

[1831] Device Role

[1832] The terminal is a device used by the learner, such as a PC or smartphone. The learner uses the terminal to input questions about the learning content. The terminal sends the questions to the server, receives and displays the explanations returned from the server, and allows the learner to view detailed explanations and advance their learning.

[1833] User Roles

[1834] The user is a learner, such as a high school or university student. The user uses a terminal to input questions about the content they are studying. The questions input by the user are sent to the server via the terminal. The server returns an explanation to the user, which the user can use to help with their studies.

[1835] Specific examples

[1836] Example 1

[1837] If a user asks, "What are the basic concepts of differentiation?", the following prompt sentence is input to the generative AI model:

[1838] Example prompt sentence:

[1839] "Please teach me the basic concepts of differentiation."

[1840] The server inputs this prompt into a generative AI model, which generates an explanation like this:

[1841] An example of a generated commentary:

[1842] "Differentiation is a mathematical technique for determining the rate of change of a function. Specifically, it shows how the output value of a function changes when the input value changes slightly. For example, the derivative of a function f(x) is expressed as f'(x), which shows the slope of f(x)."

[1843] Example 2

[1844] If a user asks, "What are some applications of integrals?", the following prompt sentence is input to the generative AI model:

[1845] Example prompt sentence:

[1846] "Please give me some examples of applications of integrals."

[1847] The server inputs this prompt into a generative AI model, which generates an explanation like this:

[1848] An example of a generated commentary:

[1849] "Integrals are widely used to calculate areas and volumes. For example, integrals are used to calculate the area under a curve or the volume of a solid of revolution. For example, integrals are used to calculate the area of ​​the region enclosed by the curve y = x^2 and the x-axis."

[1850] In this way, the system of the present invention supports learning by providing detailed and extensive explanations in response to questions from learners.

[1851] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1852] Step 1:

[1853] The user uses the terminal to input questions about the learning content.

[1854] Specific operation: The user enters a question into the input form on the terminal and clicks the send button.

[1855] Input: A user-entered question (e.g., "What are the basic concepts of differentiation?")

[1856] Output: The HTTP request generated by the device

[1857] Step 2:

[1858] The terminal sends the user's question to the server.

[1859] Specific operation: The terminal creates an HTTP request and sends it to the server.

[1860] Input: The question entered by the user

[1861] Output: HTTP request sent to the server

[1862] Step 3:

[1863] The server receives the user's question sent from the terminal.

[1864] Specific operation: The server receives the HTTP request and analyzes the question.

[1865] Input: HTTP request sent from the terminal

[1866] Output: Parsed question

[1867] Step 4:

[1868] Based on the received question, the server generates a prompt sentence to be input into the generative AI model.

[1869] Specific operation: The server converts the question content into an appropriate format and passes it to the generative AI model.

[1870] Input: Parsed question content

[1871] Output: Generated prompt sentence (e.g., "Please teach me the basic concepts of differentiation")

[1872] Step 5:

[1873] The server inputs the generated prompt sentence into the generative AI model.

[1874] Specific operation: The server sends a prompt to the generative AI model via the API.

[1875] Input: Generated prompt text

[1876] Output: Input to a generative AI model

[1877] Step 6:

[1878] The generative AI model generates detailed explanations based on the prompt.

[1879] Specific operation: The generative AI model uses internal learning data and algorithms to generate an explanation and send it back to the server.

[1880] Input: Input to the generative AI model (prompt sentence)

[1881] Output: Generated commentary

[1882] Step 7:

[1883] The server receives the generated commentary and sends it to the terminal.

[1884] Specific operation: The server returns the explanation to the terminal as an HTTP response.

[1885] Input: Generated commentary

[1886] Output: HTTP response sent to the device

[1887] Step 8:

[1888] The terminal receives the commentary returned from the server.

[1889] Specific operation: The terminal receives the HTTP response and analyzes the explanatory content.

[1890] Input: HTTP response sent from the server

[1891] Output: Parsed commentary

[1892] Step 9:

[1893] The terminal displays the received explanation to the user.

[1894] Specific behavior: Updates the view to display the description in the device UI.

[1895] Input: Parsed commentary

[1896] Output: A description that is displayed to the user

[1897] Step 10:

[1898] The user can understand the received explanation and use it to help with their studies.

[1899] Specific actions: The user reads the explanation and takes notes as needed to progress through the learning process.

[1900] Input: The description displayed to the user

[1901] Output: User understanding and learning progression

[1902] (Application example 1)

[1903] Next, a description will be given of Application Example 1 of Form 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."

[1904] With conventional learning systems, it was difficult for learners to receive detailed and comprehensive explanations immediately when they asked questions, and they often did not provide appropriate feedback or scheduling based on the learner's level of understanding. This led to problems such as reduced learning efficiency and a loss of motivation to learn. Furthermore, even in brick-and-mortar cram schools and educational facilities, it was difficult to provide prompt and accurate explanations to individual questions.

[1905] 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.

[1906] In this invention, the server includes a means for providing detailed and extensive explanations by a generative AI that has studied the curriculum guidelines, a means for instantly marking corrections to written questions, a means for providing explanations and checking comprehension, a means for acquiring study logs and scheduling by referring to comprehension checks, a means for inputting questions from learners, a means for generating explanations using a generative AI model, and a means for displaying the generated explanations to the learner. This allows learners to instantly receive detailed and extensive explanations when they ask questions, and enables appropriate feedback and scheduling according to the learner's level of understanding.

[1907] The "Course of Study" is a set of teaching standards that systematically compile the knowledge and skills that learners should acquire at educational institutions.

[1908] "Generative AI" is artificial intelligence that generates new information or commentary based on given data or prompts.

[1909] A "detailed and wide-ranging explanation" is an explanation that provides a deep and multifaceted view of a specific question.

[1910] "Written question correction" is the process of evaluating the answers written by learners and indicating whether they are correct or incorrect and what areas need improvement.

[1911] A "comprehension check" is a test or question that assesses how well a learner has understood the content.

[1912] "Scheduling" refers to the process of creating a learner's study plan and managing time to progress efficiently.

[1913] "Means for inputting questions from learners" refers to an interface that allows learners to input doubts or queries into the system.

[1914] "Means for generating explanations using a generative AI model" refers to a process of automatically creating explanations for learners' questions using generative AI.

[1915] "Means for displaying the generated explanation to the learner" refers to an interface for visually providing the learner with the explanation created by the generative AI.

[1916] The system for implementing this invention uses generative AI that has learned the curriculum guidelines to provide detailed and extensive explanations to questions from learners. The system consists of a server and a terminal, and operates as follows.

[1917] Hardware and software used

[1918] Hardware: Servers, smartphones, tablets, smart glasses

[1919] Software: Python, OpenAI API

[1920] Data processing and calculation

[1921] Server Processing

[1922] The server receives questions from learners and generates explanations using a generative AI model. Specifically, the process is as follows:

[1923] 1. Entering a question: The learner enters a question using a device (smartphone, tablet, smart glasses).

[1924] 2. Prompt generation: The server generates a prompt based on the input question. The prompt is an instruction for the generative AI model to generate an explanation.

[1925] 3. Calling the generative AI model: The server uses the OpenAI API to send a prompt to the generative AI model (e.g., GPT-3) to generate an explanation.

[1926] 4. Acquisition and display of explanation: The server acquires the generated explanation and sends it to the terminal, which visually displays the explanation to the learner.

[1927] Specific examples

[1928] If a learner asks, "What is the formula for solving a quadratic equation?", the server generates the following prompt:

[1929] Based on the curriculum guidelines, please provide a detailed explanation for the following mathematics problem.

[1930] Question: What is the formula for solving a quadratic equation?

[1931] Description:

[1932] Based on this prompt, the generative AI model generates a detailed explanation, which the server sends to the learner's device, where the learner can view the explanation on their device screen.

[1933] summary

[1934] This system allows learners to instantly receive detailed and comprehensive explanations when they ask questions. It also enables appropriate feedback and scheduling based on the learner's level of understanding. This is expected to improve learning efficiency and maintain motivation to learn.

[1935] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1936] Step 1:

[1937] The user uses the terminal to enter a question.

[1938] Input: A question that the user types into the terminal (e.g., "What is the formula for solving a quadratic equation?")

[1939] Output: Question data entered on the terminal

[1940] How it works: A user uses a smartphone, tablet, or smart glasses to enter a question in text format. The device receives this input and prepares it to be sent to the server.

[1941] Step 2:

[1942] The terminal transmits the question data to the server.

[1943] Input: Question data entered into the terminal

[1944] Output: Question data sent to the server

[1945] Specific operation: The device sends the question data entered by the user to the server. HTTP or HTTPS is used as the communication protocol.

[1946] Step 3:

[1947] The server receives the question data and generates a prompt.

[1948] Input: Question data sent to the server

[1949] Output: Generated prompt statement

[1950] Specific operation: The server analyzes the received question data and creates a prompt to allow the generative AI model to generate an explanation. For example, it generates a prompt in the format "Please provide a detailed explanation for the following math problem based on the curriculum guidelines. Problem: Please tell me the formula for solving a quadratic equation. Explanation:"

[1951] Step 4:

[1952] The server generates commentary using a generative AI model.

[1953] Input: Generated prompt statement

[1954] Output: Generated commentary data

[1955] How it works: The server uses the OpenAI API to send a prompt to a generative AI model (e.g., GPT-3). The generative AI model generates a detailed explanation based on the prompt and returns the result to the server.

[1956] Step 5:

[1957] The server transmits the generated commentary data to the terminal.

[1958] Input: Generated commentary data

[1959] Output: Commentary data sent to the terminal

[1960] Specific operation: The server receives the generated commentary data and sends it to the user's device. HTTP or HTTPS is used as the communication protocol.

[1961] Step 6:

[1962] The terminal receives the commentary data and displays it to the user.

[1963] Input: Commentary data sent to the terminal

[1964] Output: Explanation displayed on the terminal

[1965] Specific operation: The device analyzes the commentary data received from the server and visually displays it to the user, who can then check the commentary on the device screen.

[1966] Example 2

[1967] Next, a description will be given of Example 2 of Form 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."

[1968] Conventional learning systems have the problem that it takes time to grade essay questions submitted by learners, making it difficult to receive immediate feedback. Furthermore, learners cannot quickly check the evaluation results of their own writing and areas for improvement, which reduces learning efficiency. Furthermore, there is a lack of effective means for providing explanations and checking comprehension, making it difficult to accurately grasp learners' levels of comprehension.

[1969] 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.

[1970] In this invention, the server includes means for a user to submit an English composition from a terminal, means for the terminal to send composition data to the server, means for the server to receive the composition data and perform preprocessing, means for the server to send a prompt to the generative AI model and request evaluation of the composition, means for the generative AI model to evaluate the composition and generate a score and feedback, means for the server to receive the generated feedback and send it to the terminal, and means for the terminal to display the feedback to the user. This makes it possible to instantly score written questions submitted by learners and provide rapid feedback.

[1971] "Course of Study" is an official guideline that defines the educational content and learning objectives provided by educational institutions.

[1972] "Generative AI" is a system that generates text and data using artificial intelligence technology.

[1973] "Explanation" is a detailed and easy-to-understand explanation of a particular topic or issue.

[1974] A "comprehension check" is a test or question that assesses how well a learner understands a particular piece of content.

[1975] "Scheduling" refers to the process of creating a learner's study plan and managing time to progress efficiently.

[1976] A "terminal" is a device used by a user to access the system.

[1977] A "server" is a computer system that processes data and provides services to other devices over a network.

[1978] "Preprocessing" is the initial stage of processing to convert data into a format that is easier to analyze and process.

[1979] A "generative AI model" is an algorithm or system that uses artificial intelligence techniques to generate text or data.

[1980] A "prompt" is an instruction entered into a generative AI model to make it perform a specific task.

[1981] "Feedback" refers to the evaluation and improvement information provided to learners regarding their submitted content.

[1982] This invention is a system that instantly grades and provides feedback on English essays submitted by learners. The system allows users to submit English essays using their terminals, and the server processes and evaluates the essays. Specifically, the system uses the following hardware and software:

[1983] Hardware and software used

[1984] Device: The device on which a user enters and submits their essay. Examples include a computer, tablet, or smartphone.

[1985] Server: A computer system that receives and processes essay data. A server with a high-performance processor and sufficient memory is preferable.

[1986] Natural language processing library: Software for preprocessing text. Specifically, we use spaCy.

[1987] Generative AI model: An artificial intelligence model for evaluating essays. Specifically, we use OpenAI's GPT-3.

[1988] Program processing

[1989] A user submits an English essay to the system using a terminal. The terminal sends the essay data to the server through a web browser. The server first preprocesses the received essay data. This preprocessing includes text tokenization, part-of-speech tagging, and dependency analysis using spaCy.

[1990] The server then sends prompts to the generative AI model GPT-3 to evaluate the essay. The prompts include evaluation criteria and examples of expected answers. GPT-3 then evaluates the essay and generates a score and feedback.

[1991] The generated feedback is sent from the server to the terminal and displayed immediately to the user, allowing the user to immediately check the evaluation results of their essay and areas for improvement.

[1992] Specific examples

[1993] For example, suppose a user submits the following English composition:

[1994] I went to the park yesterday. It was very fun and I played with my friends.

[1995] The server receives this composition, preprocesses it using spaCy, and then sends the following prompt to GPT-3:

[1996] Evaluate the following English composition based on grammar, coherence, and vocabulary. Provide a score out of 10 and give constructive feedback:

[1997] "I went to the park yesterday. It was very fun and I played with my friends."

[1998] GPT-3 evaluates your writing and generates feedback such as:

[1999] Score: 8 / 10

[2000] Feedback: The composition is generally well-written with good grammar and coherence. However, "very fun" could be improved to "a lot of fun" for better expression. Additionally, consider adding more details about what activities you did with your friends.

[2001] This feedback is sent from the server to the terminal and displayed to the user, who can use it to improve their writing.

[2002] In this way, it is possible to instantly mark the essay questions submitted by the learner and provide quick feedback.

[2003] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2004] Step 1:

[2005] A user submits an English composition from a terminal.

[2006] A user accesses the system interface using a web browser, enters an English composition in the text box on the interface, and clicks the "Submit" button. The input is the composition text entered by the user, and the output is the composition data sent to the terminal.

[2007] Step 2:

[2008] The terminal transmits the composition data to the server.

[2009] The terminal converts the composition data entered by the user into JSON format and sends it to the server using an HTTP POST request. The input is the composition text entered by the user, and the output is the JSON-formatted composition data sent to the server.

[2010] Step 3:

[2011] The server receives the composition data and performs preprocessing.

[2012] The server parses the received essay data and performs text tokenization, part-of-speech tagging, and dependency analysis using a natural language processing library (e.g., spaCy). The input is the JSON-formatted essay data sent to the server, and the output is the preprocessed text data.

[2013] Step 4:

[2014] The server sends a prompt to the generative AI model, asking it to evaluate the essay.

[2015] The server generates a prompt to be sent to the generative AI model (e.g., GPT-3) based on the preprocessed text. The prompt includes evaluation criteria and examples of expected answers. The server sends this prompt to the generative AI model's API via an HTTP request. The input is the preprocessed text data and the prompt, and the output is the prompt sent to the generative AI model.

[2016] Step 5:

[2017] A generative AI model evaluates the essay and generates a score and feedback.

[2018] The generative AI model evaluates the essay based on the received prompt and generates a score and feedback, for example, evaluating it in terms of grammar, vocabulary, structure, etc. The input is the prompt sent to the generative AI model, and the output is the generated score and feedback.

[2019] Step 6:

[2020] The server receives the generated feedback and transmits it to the device.

[2021] The server receives the scores and feedback returned from the generative AI model, converts them into JSON format, and sends them to the device. The input is the scores and feedback returned from the generative AI model, and the output is the JSON-formatted feedback data sent to the device.

[2022] Step 7:

[2023] The device displays the feedback to the user.

[2024] The device analyzes the received feedback and displays it in a user-friendly format, allowing the user to instantly check the evaluation results and areas for improvement of their essay. The input is the JSON-formatted feedback data sent to the device, and the output is the feedback information displayed to the user.

[2025] (Application example 2)

[2026] Next, a description will be given of Application Example 2 of Form 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."

[2027] Conventional learning systems have the problem that learners do not receive immediate feedback on the essay questions they submit, which reduces learning efficiency. Also, because it takes time to grade essays, it is difficult for learners to quickly identify their weaknesses. Furthermore, because explanations and comprehension checks are not provided sufficiently, it is difficult to accurately evaluate a learner's level of comprehension.

[2028] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2029] In this invention, the server includes: a means for providing detailed and extensive explanations by a generative AI that has studied the curriculum guidelines; a means for instantly grading essay corrections; a means for providing explanations and comprehension checks; a means for recording study logs and scheduling by referencing comprehension checks; and a means for generating prompt sentences based on essays entered or uploaded by learners and providing instant grading results and feedback using a generative AI model. This allows for instant feedback on essay questions submitted by learners, improving learning efficiency. Furthermore, because essays are quickly graded, learners can quickly identify their weaknesses. Furthermore, because explanations and comprehension checks are performed thoroughly, it is possible to accurately evaluate a learner's level of comprehension.

[2030] "Course of Study" is an official guideline that defines the educational content and learning objectives provided by educational institutions.

[2031] "Generative AI" is a type of artificial intelligence that generates natural language, images, etc. from specific input.

[2032] "Explanation" is a detailed and easy-to-understand explanation of a particular topic or issue.

[2033] A "comprehension check" is a test or question that assesses how well a learner understands a particular piece of content.

[2034] "Study logging" refers to collecting records of the learning activities performed by learners.

[2035] "Scheduling" is the process of planning and executing specific tasks or activities at the appropriate time.

[2036] A "prompt sentence" is an input sentence that causes a generative AI to generate a specific output.

[2037] A "generative AI model" is an artificial intelligence model that generates natural language, images, etc. from specific input.

[2038] "Feedback" refers to evaluation and improvement information provided to learners regarding their activities and submissions.

[2039] The following system configuration and processing procedure will be described as an embodiment of the present invention.

[2040] System Configuration

[2041] The system includes a server, learner devices (smartphones, tablets, PCs, etc.), and a generative AI model. The server has the functions of providing detailed and extensive explanations using a generative AI that has studied the curriculum guidelines, instantly marking essay corrections, providing explanations and comprehension checks, recording study logs and scheduling by referencing comprehension checks, generating prompt sentences based on compositions entered or uploaded by learners, and instantly providing marking results and feedback using the generative AI model.

[2042] Hardware and Software

[2043] Hardware: Server, learner's device (smartphone, tablet, PC)

[2044] Software: Python, OpenAI API, database management system (e.g., MySQL)

[2045] Data processing and calculation

[2046] 1. Data entry: Learners use the terminal to enter or upload their English compositions.

[2047] 2. Prompt generation: The server generates prompts based on the input essay, requesting grading and feedback.

[2048] 3. Invoke the generative AI model: The server uses OpenAI's GPT-3 model to input the prompt and generate a score and feedback for the essay.

[2049] 4. Providing feedback: The generated feedback is immediately displayed on the learner's device.

[2050] 5. Log acquisition and scheduling: The server acquires the learner's learning log and proposes the next learning schedule based on the results of the comprehension check.

[2051] Specific examples

[2052] Suppose a learner inputs the following composition:

[2053] This is an example essay written by a student. It contains several grammatical errors and lacks coherence.

[2054] The server generates the following prompt based on this composition:

[2055] Please grade and provide feedback on the following English essays:

[2056] This is an example essay written by a student. It contains several ...

Claims

1. A means for providing explanations using a generative AI model that has learned a curriculum guideline; A means of marking essay corrections, A means for providing an explanation to a learner and performing a comprehension check by asking the learner questions to confirm the learner's comprehension after providing the explanation; A means for acquiring a study log which is a record of the learning activities performed by the learner, analyzing the results of the comprehension check and the past study log of the learner, and proposing the next content to be studied and the timing of studying; an emotion engine that recognizes the emotion of the learner; A means to reflect the recognized emotions in learning instruction, A means for generating an explanation for a question by inputting a question from the learner to the generating AI model; A means for providing the generated commentary to the learner; A means for recognizing emotions of the learner; means for providing additional commentary based on said sentiment; A system including:

2. When the learner submits an English composition, a prompt sentence is input to the generative AI model to request evaluation of the composition; a means for providing said assessment by said learner; The system of claim 1 , comprising:

3. 2. The system according to claim 1, wherein the explanation and the comprehension check include providing an explanation for a question and then asking a confirmation question to test the comprehension.

Images