system

Abstract

Provide a system. A system for generating learning questions for children and adjusting the difficulty level based on the user's answers, comprising: A means for generating study questions corresponding to the current level of difficulty; means for displaying the study questions; means for accepting a user's answer to the study question; means for determining whether the user's answer is correct or incorrect; means for adjusting the difficulty level of the study questions based on the determination result; means for displaying feedback regarding the determination result and difficulty level adjustment to a user; A system including:

Description

[Technical Field]

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

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

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

[0004] Conventional learning support systems have the problem of not maximizing learning effectiveness because it is difficult to appropriately adjust the difficulty of questions according to a child's level of understanding and progress. Furthermore, the lack of real-time feedback makes it difficult to maintain a child's motivation. Furthermore, there are few systems that support multiple subjects, such as mathematics and Japanese, which means that consistent learning support is not provided. The present invention aims to solve these problems. [Means for solving the problem]

[0005] The present invention is a system for generating study questions for children and adjusting their difficulty level based on a user's answers, and includes the following means: First, a means for generating study questions corresponding to the current level of difficulty. Second, a means for displaying the generated study questions to the user is provided. Furthermore, a means for accepting a user's answer and determining whether the answer is correct or incorrect is provided. A means for adjusting the difficulty level of the study questions based on the determination result is provided. Also, a means for displaying feedback regarding the determination result and the difficulty level adjustment to the user is included. This allows the difficulty level of the questions to be appropriately adjusted according to the user's level of understanding, maximizing learning effectiveness through real-time feedback. Furthermore, by including a means for generating study questions for mathematics and Japanese, it is possible to provide consistent learning support for multiple subjects.

[0006] A "learning problem" is a task that a child must solve in order to acquire knowledge or skills through the answer.

[0007] "Difficulty" is an indicator of the ease and complexity of a learning problem.

[0008] A "system" is a combination of devices and programs that operate in cooperation with multiple means to provide specific functions and services to users.

[0009] "Generate" means to create something new, and in this case refers to automatically creating learning questions.

[0010] "User" refers to those who use this system to answer study questions, specifically children.

[0011] "Answer" means the answer given by the user to the study question.

[0012] "Judgment" refers to assessing whether an answer is correct or incorrect.

[0013] "Feedback" refers to conveying information about the results of the assessment and difficulty level adjustments to the user.

[0014] "Adjust" means to adaptively change the difficulty, such as by increasing or decreasing it. [Brief explanation of the drawings]

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

[0016] 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.

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

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

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

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0030] 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.

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

[0032] 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.

[0033] 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.

[0034] 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.

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

[0036] The present invention is a system for automatically generating learning questions for children and adjusting the difficulty of the questions based on the answers of a user. Specific embodiments of the system are described below.

[0037] This system mainly consists of a server and a terminal. The server generates study questions, evaluates users' answers, and adjusts the difficulty level. The terminal displays study questions to users, collects their answers, and displays feedback received from the server.

[0038] Server Operation

[0039] The server first generates study questions using a problem generation class. The problem generation class stores the current difficulty level and creates appropriate study questions based on that level. For example, in arithmetic, a low level of difficulty generates addition problems within the range of 1 to 10, while a high level of difficulty generates addition problems within the range of 1 to 20. In Japanese language questions, reading and writing tasks are presented according to the level of difficulty.

[0040] The generated study questions are sent to the device and displayed to the user. The user's answers are then sent to the server via the device. The server compares the received answers with the correct answers, increasing the difficulty if they are correct, and decreasing the difficulty if they are incorrect. This provides an appropriate learning environment according to the user's level of understanding and progress.

[0041] Device behavior

[0042] The device displays the learning questions received from the server to the user. When the user enters an answer to a question, the answer is sent to the server. The server then receives feedback on the assessment result and difficulty level adjustment, which is then displayed to the user. For example, if the user answers correctly, the device displays "You got it right! The difficulty level will be increased," and if the answer is incorrect, the device displays "You got it wrong. The difficulty level will be lowered."

[0043] User Actions

[0044] The user answers the learning problems displayed on the device. For example, if the math problem is "5 + 3," the user enters "8" as the answer. The device then sends this answer to the server, which returns the result. The user can then move on to the next problem based on the result.

[0045] Specific examples

[0046] In the first learning cycle, the problem generated by the server is "5 + 3." If the user answers "8," the server determines this is the correct answer and increases the difficulty of the next problem. The device then displays feedback to the user saying, "You got it right! The difficulty will increase."

[0047] In the second learning cycle, the server generates a more difficult question, for example, "15 + 7." If the user answers "20," the server determines this is an incorrect answer and lowers the difficulty of the next question. The device displays feedback saying, "That's wrong. We'll lower the difficulty."

[0048] In this way, the system can adjust the difficulty level in real time based on the user's answers, providing an appropriate learning environment. This continuous feedback and adjustment effectively supports the user's academic improvement.

[0049] This system can also handle Japanese language learning problems, not just math problems. By automatically generating appropriate learning problems according to difficulty level, it helps users to study each subject in a balanced way.

[0050] As described above, the present invention is extremely effective as a learning support system for children, and can maximize the learning effect.

[0051] The processing flow will be explained below.

[0052] Step 1:

[0053] The server obtains the current difficulty level using an instance of the problem generator class. Specifically, it checks the initial difficulty level by referencing the property self.problem_generator.difficulty .

[0054] Step 2:

[0055] The server generates practice questions based on the acquired difficulty level. For example, if the difficulty level is 1, it generates addition problems using random numbers in the range of 1 to 10. The problems are stored in string format.

[0056] Step 3:

[0057] The server sends the generated learning questions to the device. Specifically, data including the question content (e.g., "5 + 3") is transferred to the device.

[0058] Step 4:

[0059] The terminal displays the transmitted study questions to the user, and displays the question text on the screen so that the user can visually recognize the question content.

[0060] Step 5:

[0061] The user answers the displayed study question. For example, the user answers "8" to the question "5 + 3."

[0062] Step 6:

[0063] The terminal collects the user's answers. Specifically, it stores the answers entered by the user as numerical values ​​and prepares to send them to the server.

[0064] Step 7:

[0065] The terminal sends the collected answers of the user to the server, and the user's input data is passed to the server.

[0066] Step 8:

[0067] The server determines whether the received user answer is correct or incorrect by evaluating the question text and comparing the correct answer with the user answer.

[0068] Step 9:

[0069] The server adjusts the difficulty of the study questions based on the answers, increasing the difficulty if the user answers correctly and decreasing it if the user answers incorrectly.

[0070] Step 10:

[0071] The server generates feedback regarding the judgment result and difficulty adjustment, and sends it to the terminal. It creates a feedback message (for example, "You got it right! The difficulty level will increase.").

[0072] Step 11:

[0073] The terminal displays the feedback received from the server to the user, who can obtain information about his / her answer results and future study strategies.

[0074] Step 12:

[0075] The user checks the displayed feedback and moves on to the next problem, and this cycle is repeated to maximize the user's learning effect.

[0076] Example 1

[0077] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0078] Conventional learning systems for children often do not adjust the difficulty of questions in real time according to the individual user's learning progress, resulting in a decrease in learning efficiency. Furthermore, many systems only support a single subject, making it difficult to provide balanced, comprehensive learning support. Given these points, there is a demand for a learning support system that can appropriately adjust the difficulty level based on the user's answers and can support multiple subjects.

[0079] 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.

[0080] In this invention, the server includes means for generating study questions for children using a study question generation program, means for transmitting the study questions to a terminal and displaying them, means for accepting a user's answer to the study questions, means for transmitting the user's answer to the server, means for determining whether the answer is correct or incorrect and adjusting the difficulty of the study questions based on the result, and means for generating and displaying feedback on the determination result and the difficulty adjustment to the user. This allows the difficulty of the questions to be adjusted in real time based on the user's answer, enabling balanced learning support for multiple subjects.

[0081] A "program for generating study questions" is software that automatically creates study questions for subjects such as arithmetic and Japanese language based on the user's study data and level of difficulty.

[0082] A "server" is a computer system that performs processes such as generating study questions, receiving and judging user answers, adjusting difficulty, and generating feedback.

[0083] A "terminal" is a device operated by a user, and is a device for displaying study questions, inputting user answers, and displaying feedback.

[0084] "User's answer" refers to the answer data that the user inputs to the study question.

[0085] The "means for transmitting the answer to the server" is a communication means for sending the user's answer from the terminal to the server.

[0086] The "means for determining" refers to an algorithm and program that the server uses to check the user's answer against the correct answer and determine whether it is correct or incorrect.

[0087] The "means for adjusting the difficulty level" refers to an algorithm and program for appropriately changing the difficulty level of the next study question based on the evaluation result of the user's answer.

[0088] The "means for generating feedback" is a program for creating a message to be displayed to the user based on the user's answer results and information regarding difficulty level adjustment.

[0089] The "means for transmitting study questions to the terminal" refers to a communication means for transmitting the generated study questions from the server to the terminal.

[0090] The "means for displaying study questions" refers to software and hardware for displaying study questions received by the terminal on a user interface.

[0091] The present invention is a system that automatically generates learning questions for children and adjusts the difficulty of the questions based on the user's answers. This system is mainly composed of a server and a terminal.

[0092] Server Operation

[0093] The server generates study questions using a "program for generating study questions" that uses a "generative AI model." This problem generation program automatically creates appropriate study questions, taking into account the current level of difficulty. The server sends the generated questions in JSON format to the device and waits for the user to enter their answers. The user's answers are then sent to the server via the device, and the server compares them with the correct answers. Based on the evaluation results, the server adjusts the difficulty of the next question. It then generates feedback regarding the difficulty adjustment and the evaluation results and sends this to the device. The server is responsible for generating questions, evaluating answers, adjusting the difficulty, and generating feedback.

[0094] Device behavior

[0095] The device displays the learning questions received from the server on a user interface. A form is displayed for the user to enter their answers to the questions. When the user enters their answers, the device converts the data into JSON format and sends it to the server. When feedback is received from the server, the device analyzes it and displays it on the user interface. For example, if the user answers correctly, it displays "You're correct! The difficulty level will increase," and if the answer is incorrect, it displays "You're wrong. The difficulty level will be lowered." The device is responsible for displaying learning questions, sending answers, and displaying feedback.

[0096] User Actions

[0097] The user answers the study questions displayed on the device. For example, if the math question displayed is "5 + 3," the user enters "8" as the answer. The device then sends this answer to the server, which returns a judgment result. The user can then move on to the next question based on the result. The user enters the answer to the study question and checks the feedback from the server.

[0098] Specific examples

[0099] In the first learning cycle, the problem generated by the server is "5 + 3." If the user answers "8," the server determines this is the correct answer and increases the difficulty of the next problem. The device then displays feedback to the user saying, "You got it right! The difficulty will increase."

[0100] In the second learning cycle, the server generates a more difficult question, for example, "15 + 7." If the user answers "20," the server determines this is an incorrect answer and lowers the difficulty of the next question. The device displays feedback saying, "That's wrong. We'll lower the difficulty."

[0101] Through this series of processes, the system can provide appropriate questions according to the user's learning progress, thereby providing efficient learning support.

[0102] Example prompt

[0103] Here are some example prompts to enter into a generative AI model:

[0104] "The server of this system first generates learning questions using a question generation class. Depending on the current level of difficulty, arithmetic questions or Japanese language questions are selected. The generated questions are then sent to the terminal, and when the user enters the answer, the answer is sent to the server. The server evaluates the answer and increases the difficulty if it is correct, or decreases it if it is incorrect. Please explain this process with a concrete example."

[0105] From the above explanation, the detailed operation and effects of the present invention can be understood.

[0106] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0107] Program processing flow

[0108] Step 1:

[0109] Start the program to generate questions

[0110] The server launches a "program for generating learning questions" using the "generative AI model."

[0111] Input: Current difficulty information, user learning history data.

[0112] Specific operation: The server obtains the current difficulty information and the user's learning history from the internal database and inputs them into the generative AI model.

[0113] Output: A new training problem is generated.

[0114] Step 2:

[0115] Send and display study questions on your device

[0116] The server converts the generated learning questions into JSON format and sends them to the terminal.

[0117] Input: The newly generated training problem.

[0118] Specific operation: The server formats the training problem as a JSON object and sends it to the device using a communication protocol (e.g., HTTP, WebSocket).

[0119] Output: The training problem sent to the device.

[0120] Step 3:

[0121] Displaying study questions to users

[0122] The terminal analyzes the received study questions and displays them on the user interface.

[0123] Input: Training question data from the server (JSON format).

[0124] Specific operation: The device parses the JSON data and displays the learning questions on the user's screen.

[0125] Output: The training question displayed in the user interface.

[0126] Step 4:

[0127] Enter the user's answer

[0128] The user inputs answers to the study questions displayed on the terminal.

[0129] Input: The study question displayed in the user interface.

[0130] Specific operation: The user enters the answer into the input form and clicks the submit button.

[0131] Output: The answer entered by the user.

[0132] Step 5:

[0133] Send the user's answer to the server

[0134] The device converts the user's answer into JSON format and sends it to the server.

[0135] Input: The answer entered by the user.

[0136] Specific operation: The device formats the answer data as a JSON object and sends it to the server using a communication protocol.

[0137] Output: The answer data sent to the server.

[0138] Step 6:

[0139] Judge the answer and adjust the difficulty level

[0140] The server receives the user's answer and determines whether it is correct or incorrect.

[0141] Input: User answer data, correct answer data for the learning questions.

[0142] Specific operation: The server compares the answer data with the correct answers to the learning questions and determines whether they are correct or not. Based on the result of the judgment, it determines the difficulty level of the next question.

[0143] Output: Judgment result and difficulty information for the next question.

[0144] Step 7:

[0145] Generate a feedback message

[0146] The server generates a feedback message for the user based on the determination result.

[0147] Input: Answer judgment result, difficulty information.

[0148] Specific operation: The server generates a feedback message in text format based on the judgment result and difficulty information.

[0149] Output: The generated feedback message.

[0150] Step 8:

[0151] Send and display feedback on the device

[0152] The server sends the generated feedback message to the terminal.

[0153] Input: Feedback message.

[0154] Specific operation: The server formats the feedback message as a JSON object and sends it to the device using a communication protocol.

[0155] Output: Feedback sent to the device.

[0156] Step 9:

[0157] Displaying feedback to the user

[0158] The terminal displays the received feedback message on a user interface.

[0159] Input: Feedback message from the server (JSON format).

[0160] Specific behavior: The device parses the JSON data and displays a feedback message on the user's screen, for example, "Correct! The difficulty level will increase."

[0161] Output: The feedback message displayed in the user interface.

[0162] (Application example 1)

[0163] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0164] Currently, most learning support systems for children are used at home or at school, making it difficult to make effective use of travel time. Furthermore, conventional systems only allow for the display of learning problems and the input of answers in limited environments, making it impossible to provide effective learning support in mobile devices such as self-driving vehicles. Furthermore, it is important to provide real-time feedback and appropriate difficulty adjustments to maintain learning motivation. Therefore, there is a need for a system that maximizes children's learning efficiency by providing learning problems while on the move, adjusting the difficulty level, and providing feedback in real time.

[0165] 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.

[0166] In this invention, the server includes means for generating study questions corresponding to the current level of difficulty, means for displaying the study questions, means for displaying the study questions on a mobile object, means for accepting a user's answer to the study questions by voice or touch operation, means for determining whether the user's answer is correct or incorrect, means for adjusting the difficulty of the study questions based on the determination result, and means for displaying feedback regarding the determination result and the difficulty level adjustment to the user. This enables learning activities even while on the move, and by providing effective feedback and difficulty level adjustment in real time, children's learning efficiency can be improved.

[0167] "Study Problems" are educational tasks or questions that children must complete and are automatically generated by the server.

[0168] A "user answer" is an answer provided by a user to a study question, and is input through voice or touch operation.

[0169] "Current difficulty" refers to the difficulty level of the study questions that is set based on the user's level of understanding and progress.

[0170] "Mobile object" refers to something in motion, such as an autonomous vehicle, and specifically refers to the in-car environment, including the infotainment system or tablet.

[0171] "Display means" refers to a device or function for visually or audibly presenting information such as study questions and feedback to the user.

[0172] "Voice input" refers to an input method in which a user provides answers to study questions using voice.

[0173] "Touch operation" refers to the user entering answers using the touchscreen of a tablet or infotainment system.

[0174] The "judging means" is a function that evaluates whether the user's answer is correct or incorrect and adjusts the difficulty level based on the result.

[0175] "Feedback" provides the user with information indicating the evaluation of their answer and next steps.

[0176] The present invention provides a system for automatically generating learning questions for children and adjusting the difficulty of the questions based on the user's answers. This system can be installed in an autonomous vehicle, enabling learning activities while traveling in the vehicle. A specific embodiment of the system is described below.

[0177] System Structure

[0178] This system mainly consists of a server and a terminal. The server generates learning questions, evaluates the user's answers, and provides the function to adjust the difficulty level. The terminal, especially the infotainment system or tablet in the autonomous vehicle, displays the learning questions to the user, collects the user's answers, and displays the feedback received from the server.

[0179] Server Operation

[0180] The server first generates learning questions using a question generation class. The generated learning questions are sent to the terminal and displayed to the user. The user's answers are then sent to the server via the terminal. The server compares the received answers with the correct answers, increasing the difficulty if they are correct and decreasing the difficulty if they are incorrect. This provides an appropriate learning environment according to the user's level of understanding and progress.

[0181] Device behavior

[0182] The device is an infotainment system or tablet installed in the autonomous vehicle, which displays the learning questions and accepts the user's answers. The user inputs their answers through touch or voice input. The answers are sent to a server, and the results and feedback on difficulty adjustments are displayed on the device. This allows users to continue learning without interruption even while on the move.

[0183] User Actions

[0184] The user, or child, works on learning problems while in the car. For example, when a math problem such as "15 + 7" appears, the user inputs the answer "22" using touch or voice input. The device sends the answer to the server, which evaluates the result and returns feedback. The user then works on the next problem based on the result.

[0185] Specific examples

[0186] In the first learning cycle, the problem generated by the server is "15 + 7." If the user answers "22," the server determines this is an incorrect answer and lowers the difficulty of the next problem. The device then displays feedback to the user saying, "This is incorrect. Proceed to the next problem."

[0187] In the second learning cycle, the server generates a question with a lower level of difficulty, such as "8 + 4." If the user answers "12," the server recognizes this as the correct answer and increases the difficulty of the next question. The device displays feedback saying, "Correct! The difficulty will increase."

[0188] Prompt Sentence Examples

[0189] Examples of prompts for generative AI models include:

[0190] "Current difficulty level is 2. Generate math problems for children."

[0191] "Please create a Japanese language question that corresponds to level 3."

[0192] This allows learning activities to be carried out while on the move, and by providing effective feedback and difficulty adjustments in real time, children's learning efficiency can be improved.

[0193] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0194] Step 1:

[0195] The server generates the training questions (input: current difficulty level, output: generated training questions)

[0196] The server generates learning problems based on the current level of difficulty. For example, it uses a generative AI model to input a prompt such as "Please generate a math problem of level 1" and outputs appropriate learning problems based on that. The server stores the generated learning problems and prepares them to be sent to the device.

[0197] Step 2:

[0198] The device displays the study questions (input: study questions received from the server, output: displayed study questions)

[0199] The device displays the learning questions received from the server to the user. During this process, the question is displayed on the screen or the user is informed of the question by voice output. For example, the question "15 + 7" is displayed on the screen.

[0200] Step 3:

[0201] User enters answer (input: study question, output: user answer)

[0202] The user inputs answers to the displayed study questions. The input method can be touch operation or voice input. For example, the user can provide the answer "22" by voice input.

[0203] Step 4:

[0204] The device receives the user's answer and sends it to the server (input: user's answer, output: sending the answer to the server)

[0205] The terminal receives the answer entered by the user and sends it to the server. The data includes the question ID along with the answer content.

[0206] Step 5:

[0207] The server judges the answer and adjusts the difficulty level (input: user's answer, output: judgement result and new difficulty level)

[0208] The server compares the received user answer with the correct answer data, and based on the results, increases the difficulty level if the answer is correct, or decreases it if the answer is incorrect. For example, if the answer "22" is incorrect, the difficulty level of the next question is lowered.

[0209] Step 6:

[0210] The server generates feedback and sends it to the device (input: judgment result and new difficulty level, output: feedback message).

[0211] The server generates a feedback message for the user based on the result of the judgment and the new difficulty level. For example, it generates a message such as "This is a mistake. Proceed to the next question." and sends it to the terminal.

[0212] Step 7:

[0213] The device displays the feedback (input: feedback message received from the server, output: displayed feedback)

[0214] The terminal displays the feedback message received from the server to the user. Feedback is provided by visual display or audio, allowing the user to confirm the results of their answers.

[0215] Step 8:

[0216] The device requests a new learning problem (input: new difficulty level, output: next learning problem)

[0217] After providing feedback to the server, the device requests the server to generate new learning questions corresponding to the new level of difficulty for the next learning cycle, thereby maintaining continuity of learning.

[0218] 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.

[0219] The present invention provides a learning support system for children that incorporates an emotion engine that recognizes the emotions of a user. Specific embodiments of the system will be described below.

[0220] This system mainly consists of a server, a terminal, and an emotion engine. The server generates learning questions, evaluates users' answers, and adjusts the difficulty level. The terminal displays learning questions to users, collects their answers, and displays feedback received from the server. The emotion engine recognizes users' emotions and adjusts the difficulty and type of learning questions based on those emotions.

[0221] Server Operation

[0222] The server first generates study questions using a problem generation class. The problem generation class stores the current difficulty level and creates appropriate study questions based on that level. For example, for math problems, a low level generates addition problems using random numbers in the range of 1 to 10, while a high level generates addition problems in the range of 1 to 20. For Japanese language problems, reading and writing tasks are presented according to the level of difficulty.

[0223] The generated learning questions are sent to the device and displayed to the user. The user's answers are then sent to the server via the device. The server compares the received answers with the correct answers, increasing the difficulty if they are correct and decreasing the difficulty if they are incorrect. Furthermore, the difficulty and type of learning questions are adjusted based on the user's emotions recognized by the emotion engine.

[0224] Device behavior

[0225] The device displays the study questions received from the server to the user. The question text is displayed on the screen so that the user can see the question content. When the user enters the answer to the study question, the answer is sent to the server. The device receives feedback from the server regarding the assessment result and difficulty level adjustment, and displays this to the user. For example, if the user answers correctly, it displays "You got it right! The difficulty level will be increased," and if the answer is incorrect, it displays "You got it wrong. The difficulty level will be lowered."

[0226] Emotion Engine Operation

[0227] The emotion engine measures data such as the user's facial expressions, voice, and input speed to recognize the user's emotions. For example, if it recognizes that the user is feeling stressed, it temporarily lowers the difficulty of the study questions to reduce the user's burden. On the other hand, if the user is feeling relaxed, it adjusts the difficulty level appropriately to maintain or increase it.

[0228] User Actions

[0229] The user answers the learning problems displayed on the device. For example, if the math problem is "5 + 3," the user enters "8" as the answer. The device then sends the answer to the server, which returns a judgment and feedback. The user can then move on to the next problem based on the result. The emotion engine also monitors the user's emotional state and adjusts the learning experience more appropriately, allowing the user to continue studying without stress.

[0230] Specific examples

[0231] In the first learning cycle, the problem generated by the server is "5 + 3." If the user answers "8," the server determines this is the correct answer and increases the difficulty of the next problem. The device then displays feedback to the user saying, "You got it right! The difficulty will increase." Also, if the emotion engine recognizes a relaxed state from the user's facial expressions and voice, the difficulty of the next problem will increase appropriately.

[0232] In the second learning cycle, the server generates a more difficult question, for example, "15 + 7." If the user answers "20," the server determines this is an incorrect answer and lowers the difficulty of the next question. Also, if the emotion engine recognizes that the user is feeling stressed, it appropriately lowers the difficulty of the next question to reduce the user's burden. The device displays feedback saying, "That's a mistake. We'll lower the difficulty."

[0233] In this way, the system can provide an appropriate learning environment by adjusting the difficulty and type of questions in real time based on the user's answers and emotional state. This continuous feedback and adjustment effectively supports the user's academic improvement.

[0234] Furthermore, this system can handle multiple subjects, such as math and Japanese. By automatically generating appropriate study questions according to difficulty level, it can help users study each subject in a balanced way.

[0235] As described above, the present invention is extremely effective as a learning support system for children, and can maximize the learning effect.

[0236] The processing flow will be explained below.

[0237] Step 1:

[0238] The server obtains the current difficulty level using an instance of the problem generator class. Specifically, it checks the initial difficulty level by referencing the property self.problem_generator.difficulty .

[0239] Step 2:

[0240] The server generates learning questions based on the acquired difficulty level. For example, if the difficulty level is 1, it generates addition questions using random numbers in the range of 1 to 10. The generated questions are stored in string format.

[0241] Step 3:

[0242] The server sends the generated learning questions to the device. Specifically, it transfers data including the question content (e.g., "5 + 3") to the device.

[0243] Step 4:

[0244] The terminal displays the transmitted study questions to the user, and displays the question text on the screen so that the user can visually recognize the question content.

[0245] Step 5:

[0246] The user answers the displayed study question. For example, the user answers "8" to the question "5 + 3."

[0247] Step 6:

[0248] The terminal collects the user's answers. Specifically, it stores the answers entered by the user as numerical values ​​and prepares to send the answer data to the server.

[0249] Step 7:

[0250] The terminal sends the collected answers of the user to the server, and the user's input data is passed to the server.

[0251] Step 8:

[0252] The server determines whether the received user answer is correct or incorrect. The server evaluates the question text and compares the correct answer with the user's answer. For example, the correct answer to "5 + 3" is "8," and if the user's answer is "8," it is determined to be correct.

[0253] Step 9:

[0254] The server adjusts the difficulty of the study questions based on the answers. If the user answers correctly, the difficulty level is increased, and if the user answers incorrectly, the difficulty level is decreased. For example, the difficulty level may be increased from 1 to 2, or decreased from 2 to 1.

[0255] Step 10:

[0256] The emotion engine analyzes the user's facial expressions, voice, typing speed, etc. to recognize the user's emotions, thereby determining whether the user is stressed or relaxed.

[0257] Step 11:

[0258] An emotion engine adjusts the difficulty or type of study questions based on the perceived user emotion, for example, if the user is stressed, the next study question will be less difficult.

[0259] Step 12:

[0260] The server generates feedback regarding the result of the judgment and the difficulty adjustment, and sends it to the device. It creates a feedback message (e.g., "You got it right! The difficulty will be increased." or "You got it wrong. The difficulty will be decreased.").

[0261] Step 13:

[0262] The terminal displays the feedback received from the server to the user, who can obtain information about his / her answer results and future study strategies.

[0263] Step 14:

[0264] The user checks the displayed feedback and moves on to the next problem. For example, if the emotion engine determines that the user is feeling stressed, the difficulty level of the next problem is set low. This cycle is repeated to maximize the user's learning effect.

[0265] Example 2

[0266] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0267] Conventional learning support systems adjust the difficulty of study questions based on the user's answers, but lack a mechanism for adjusting the learning experience based on the user's emotional state. As a result, if the user is stressed or overly relaxed, the difficulty level may not be adjusted appropriately, potentially reducing the learning effect. The present invention aims to recognize the user's emotions and adjust the difficulty and type of study questions based on that, allowing the user to continue learning in an optimal state.

[0268] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for generating study questions corresponding to the current level of difficulty, means for displaying the study questions, means for accepting a user's answers to the study questions, means for determining whether the user's answers are correct or incorrect, means for adjusting the difficulty of the study questions based on the determination result, means for collecting emotional data and recognizing the user's emotions, means for adjusting the difficulty or type of the study questions based on the emotion recognition, and means for displaying feedback regarding the determination result and the difficulty adjustment to the user. This makes it possible to comprehensively determine the user's answering status and emotional state and provide an appropriate learning environment in real time.

[0269] The following are definitions of important terms contained in the claims.

[0270] A "study question" is a math or language related challenge provided for the user to answer.

[0271] "Difficulty" is an indicator of the complexity of the study questions and the difficulty of solving them.

[0272] A "server" is a computer system that generates study questions, judges user answers, adjusts difficulty, and provides feedback.

[0273] A "terminal" is a device that displays study questions to a user, collects the user's answers, and displays feedback from the server.

[0274] "Emotion data" is information collected from the user's facial expression, voice, input speed, etc., and is data that indicates the user's emotional state.

[0275] An "emotion engine" is a software or hardware system for analyzing emotion data and recognizing a user's emotion.

[0276] "Feedback" is information that provides the user with the evaluation results of the user's answers, as well as study instructions and comments based on the evaluation results.

[0277] "Determination" is the process of determining whether the answer given by the user is correct or incorrect.

[0278] "Tuning" is the process of changing the difficulty and type of study questions based on the user's answers and emotional state.

[0279] "Display" refers to the act of visually presenting information on the screen of a terminal, such as showing study questions and feedback to the user.

[0280] The present invention is a learning support system for children that combines an emotion engine that recognizes the user's emotions. This system is mainly composed of a server, a terminal, and an emotion engine. Specific embodiments of the system are described below.

[0281] System Configuration

[0282] The system includes the following means:

[0283] 1. Server

[0284] 2. Terminal

[0285] 3. Emotion Engine

[0286] Server Operation

[0287] The server first generates learning problems using a problem generation class. The problem generation class stores the current difficulty level and creates appropriate learning problems based on that level. For example, in arithmetic, a low level of difficulty generates a simple addition problem like "5 + 3," while a high level of difficulty generates a more complex addition problem like "15 + 7." The generated learning problems are then sent to the device and displayed to the user. After the user's answer is sent to the server via the device, the server compares the answer with the correct answer and makes a judgment. If the answer is correct, the difficulty level is increased; if the answer is incorrect, the difficulty level is decreased. The difficulty and type of learning problems are further adjusted based on the user's emotional data recognized by the emotion engine.

[0288] Examples:

[0289] Example prompt: "The server generates a '5 + 3' problem and sends it to the terminal, then waits for the user's answer. After the user enters the answer, write a program that judges the answer and returns appropriate feedback. Also, add a function to adjust the difficulty of the problem using the user's emotional data."

[0290] Device behavior

[0291] The device displays the learning questions received from the server to the user. For example, the problem "5 + 3" is displayed on the screen, and the user inputs the answer to the problem. This answer is sent to the server, and the user checks the feedback from the server. The feedback from the server is displayed to the user as a message such as "That's correct! The difficulty will increase" or "That's incorrect. The difficulty will be lowered."

[0292] Emotion Engine Operation

[0293] The emotion engine uses emotion sensors to measure data such as the user's facial expressions, voice, and input speed. It then analyzes the collected data using an AI model to recognize the user's emotions. For example, it can determine whether the user is feeling stressed or relaxed based on data from the camera, microphone, and keyboard input speed. The recognized emotion data is sent to the server, which uses it as reference information to adjust the difficulty and type of the next learning problem.

[0294] User Actions

[0295] The user answers the study questions displayed on the device. For example, they enter "8" for the "5 + 3" question. After answering, the device sends the answer to the server and receives and displays feedback. This allows the user to prepare for the next question. The user can also see that their learning progress is optimized in real time according to the emotion recognition by the emotion engine.

[0296] This system comprehensively assesses the user's response status and emotional state, and adjusts the difficulty and type of study questions appropriately to provide an effective learning environment, which is expected to improve the user's academic ability.

[0297] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0298] The processing flow of the program of this system will be explained in detail below, divided into processing steps.

[0299] Step 1: Generate training questions

[0300] The server uses the problem generation class to generate problems based on the current difficulty level. For example, if the current difficulty level is low, the server generates a simple addition problem such as "5 + 3." The input for this problem generation is the current difficulty level data, and the output is the generated problem.

[0301] Step 2: Submit and view the exercises

[0302] The server sends the generated study questions to the terminal. The input is the generated study question data, and the output is a notification that the sending process is complete. The terminal then displays the received study questions on the screen. For example, a "5 + 3" problem is displayed on the screen. The input here is the study question data received from the server, and the output is the problem displayed on the screen in a format that the user can see.

[0303] Step 3: User answers

[0304] The user inputs answers to the study questions displayed on the terminal. For example, the user inputs "8" using the keyboard. The input is the data the user answered, and the output is the answer data stored inside the terminal.

[0305] Step 4: Submitting user answers

[0306] The terminal sends the user's answer to the server. The input is the user's answer data, and the output is a transmission completion notification to the server.

[0307] Step 5: Determine the answer

[0308] The server compares the received user answer with the correct answer and makes a judgment. For example, if the received answer is "8" and the question is the addition "5 + 3", it judges whether the answer is correct. The input is the user's answer data and the correct answer data, and the output is the judgment result data.

[0309] Step 6: Collect and recognize emotion data

[0310] The emotion engine collects data such as the user's facial expressions, voice, and input speed, and uses this data to recognize the user's emotions. For example, it acquires the user's facial expression data through a camera and analyzes it with an AI model to determine whether the user is relaxed or stressed. The input is emotion data, and the output is the user's emotion recognition result data.

[0311] Step 7: Adjusting the difficulty

[0312] The server adjusts the difficulty of the learning questions based on the answer judgment results and emotion recognition results. For example, if the user answers correctly and the emotion engine recognizes that the user is relaxed, the server increases the difficulty of the next question. The input is the judgment result data and emotion recognition result data, and the output is the adjusted difficulty data.

[0313] Step 8: Submit and view feedback

[0314] The server sends the judgment result and the difficulty adjustment result to the terminal, and the terminal displays them to the user. For example, a feedback message such as "Correct! The difficulty will increase." The input is the feedback data from the server, and the output is the feedback message displayed to the user.

[0315] Through the above specific processing steps, the system can comprehensively judge the user's answering situation and emotional state, and provide an appropriate learning environment in real time.

[0316] (Application example 2)

[0317] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0318] Conventional learning support systems and work support systems set the difficulty level unilaterally without considering the user's emotional state, which often led to stress and fatigue for the user. Furthermore, because the difficulty level was set uniformly, the user's learning effect and work efficiency were often reduced. In this modern age, where flexible responses according to the user's state are required, systems incorporating emotion recognition are becoming increasingly important.

[0319] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for generating study questions corresponding to the current level of difficulty, means for displaying study questions, means for accepting a user's answers to the study questions, means for determining whether the user's answers are correct or incorrect, means for adjusting the difficulty of the study questions based on the determination result, means for displaying feedback to the user regarding the determination result and the difficulty adjustment, means for recognizing the user's emotions, means for adjusting the difficulty and type of study questions based on the emotions, and means for feeding back the emotion recognition results to the work environment and adjusting the work difficulty appropriately. This provides an appropriate learning environment and work environment according to the user's emotional state, allowing the user to study and work efficiently without stress.

[0320] A "system" is a collection of multiple elements, each of which works together to achieve a specific function.

[0321] The "means for generating study questions" is a component within the system that has the function of creating questions that correspond to the user's study content.

[0322] The "means for displaying study questions" is a component that has the function of visually presenting study questions to the user.

[0323] The "means for accepting user answers" is a component that has the function of allowing the system to receive answers entered by the user to the study questions.

[0324] The "means for determining whether the answer is correct or incorrect" is a component that has the function of determining whether the user's answer is correct or not.

[0325] The "means for adjusting difficulty" is a component that has the function of automatically changing the difficulty of the next study question to be presented based on the user's answer.

[0326] The "means for displaying feedback to the user" is a component that has the function of conveying information about the answer result and difficulty level adjustment to the user.

[0327] The "means for recognizing user's emotions" is a component having a function for analyzing the user's emotional state (for example, stress, relaxation, motivation, etc.).

[0328] The "means for adjusting the difficulty and type of study questions based on emotions" is a component that has the function of appropriately changing the difficulty and type of study questions for the user based on the results of emotion recognition.

[0329] The "means for feeding back emotion recognition results to the work environment and adjusting the difficulty of the work appropriately" is a component that has the function of adjusting the work content and difficulty based on the user's emotion recognition results, thereby reducing the burden on the user.

[0330] The present invention is a learning and work support system that combines an emotion engine that recognizes the user's emotions. This system is composed of a server, a terminal, and an emotion engine.

[0331] The server first generates study questions using a problem generation class. The problem generation class stores the current difficulty level and creates appropriate study questions based on that level. For example, for arithmetic questions, a basic addition problem is generated if the difficulty level is low, and a more complex addition problem is generated if the difficulty level is high. For Japanese language questions, reading and writing tasks are presented according to the respective level of difficulty. The generated study questions are sent to the device and displayed to the user. The user's answers are then sent to the server via the device. The server compares the received answers with the correct answers and increases the difficulty level if they are correct, or decreases the difficulty level if they are incorrect. The server also adjusts the difficulty level and type of study questions based on the user's emotions recognized by the emotion engine.

[0332] The device displays the study questions received from the server to the user. The question text is displayed on the screen so that the user can see the question content. When the user enters the answer to the study question, the answer is sent to the server. The device receives feedback from the server regarding the assessment result and difficulty level adjustment, and displays this to the user. For example, if the user answers correctly, it displays "You got it right! The difficulty level will be increased," and if the answer is incorrect, it displays "You got it wrong. The difficulty level will be lowered."

[0333] The emotion engine measures data such as the user's facial expressions, voice, and input speed to recognize the user's emotions. For example, if it recognizes that the user is feeling stressed, it temporarily lowers the difficulty of the study questions to reduce the user's burden. On the other hand, if the user is feeling relaxed, it adjusts the difficulty level appropriately to maintain or increase it.

[0334] Furthermore, this invention can also be applied to assisting factory robots in their work. This system involves installing an emotion engine in a factory robot, recognizing the emotional state of a worker in real time, and adjusting the difficulty of the work based on the results. For example, if the emotion engine recognizes that a worker is under stress, it can assign the worker an easy task or suggest a temporary break. If the emotion engine recognizes that the worker is highly motivated, it can assign a difficult task.

[0335] To illustrate, consider the following scenario:

[0336] Example 1:

[0337] If the emotion engine recognizes that Worker A is under stress, it assigns him / her an easy task (e.g., sorting parts), thereby reducing the workload.

[0338] Example 2:

[0339] If Worker B is perceived as highly motivated, he or she will be assigned a more difficult task (e.g., assembling a complex machine), which will improve work efficiency.

[0340] Example prompt sentence:

[0341] "Recognize the facial expressions of the workers from the images and use an emotion engine to estimate their emotions. Assuming the emotion is stress, relaxation, or motivation, suggest an appropriate level of task difficulty depending on the emotion."

[0342] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0343] Step 1:

[0344] The server generates learning questions according to the current level of difficulty using a question generation class. At this time, the current level of difficulty is given as input, and learning content according to that level of difficulty (for example, addition problems in arithmetic or reading and writing problems in Japanese) is output.

[0345] Step 2:

[0346] The server sends the generated training questions to the terminal, where the input is the generated training questions and the output is the training question data sent to the terminal.

[0347] Step 3:

[0348] The terminal displays the exercises received from the server to the user, with the input being the exercises received from the server and the output being the text of the exercises displayed to the user.

[0349] Step 4:

[0350] The user inputs answers to the displayed study questions. The input is the study question and the user's answer, and the output is the user's answer data input to the terminal.

[0351] Step 5:

[0352] The terminal sends the user's answer to the server. The input is the user's answer data, and the output is the answer data sent to the server.

[0353] Step 6:

[0354] The server determines whether the user's answer is correct or incorrect. The input is the user's answer and the correct answer data, and the output is the judgment result (correct or incorrect).

[0355] Step 7:

[0356] The server adjusts the difficulty of the next study question based on the judgment result. The input is the judgment result, and the output is the difficulty data for the next study question.

[0357] Step 8:

[0358] The server generates feedback regarding the judgment result and the difficulty level adjustment and sends it to the terminal. The input is the judgment result and the adjusted difficulty level, and the output is a feedback message.

[0359] Step 9:

[0360] The terminal displays the feedback received from the server to the user. The input is the feedback message and the output is the feedback text displayed to the user.

[0361] Step 10:

[0362] The emotion engine measures and analyzes data such as the user's facial expressions, voice, and input speed to recognize the user's emotions. The input is the user's raw data (facial expressions, voice data, input speed data), and the output is the user's emotional state (stress, relaxation, motivation, etc.).

[0363] Step 11:

[0364] The server adjusts the difficulty and type of training questions based on the emotion recognition results. The input is the emotion recognition results, and the output is the adjusted difficulty and type of questions.

[0365] Step 12:

[0366] The server feeds back the emotion recognition results to the work environment and adjusts the task difficulty. The input is the emotion recognition results and the current task content, and the output is the adjusted task.

[0367] Step 13:

[0368] The terminal displays the adjusted work task to the user or the work robot or issues instructions to the user or the work robot. The input is the adjusted work task data, and the output is instructions to the user or the work robot.

[0369] 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.

[0370] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0371] 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.

[0372] [Second embodiment]

[0373] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0374] 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.

[0375] 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).

[0376] 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.

[0377] 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.

[0378] 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).

[0379] 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.

[0380] 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.

[0381] 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.

[0382] 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.

[0383] 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.

[0384] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0385] The present invention is a system for automatically generating learning questions for children and adjusting the difficulty of the questions based on the answers of a user. Specific embodiments of the system are described below.

[0386] This system mainly consists of a server and a terminal. The server generates study questions, evaluates users' answers, and adjusts the difficulty level. The terminal displays study questions to users, collects their answers, and displays feedback received from the server.

[0387] Server Operation

[0388] The server first generates study questions using a problem generation class. The problem generation class stores the current difficulty level and creates appropriate study questions based on that level. For example, in arithmetic, a low level of difficulty generates addition problems within the range of 1 to 10, while a high level of difficulty generates addition problems within the range of 1 to 20. In Japanese language questions, reading and writing tasks are presented according to the level of difficulty.

[0389] The generated study questions are sent to the device and displayed to the user. The user's answers are then sent to the server via the device. The server compares the received answers with the correct answers, increasing the difficulty if they are correct, and decreasing the difficulty if they are incorrect. This provides an appropriate learning environment according to the user's level of understanding and progress.

[0390] Device behavior

[0391] The device displays the learning questions received from the server to the user. When the user enters an answer to a question, the answer is sent to the server. The server then receives feedback on the assessment result and difficulty level adjustment, which is then displayed to the user. For example, if the user answers correctly, the device displays "You got it right! The difficulty level will be increased," and if the answer is incorrect, the device displays "You got it wrong. The difficulty level will be lowered."

[0392] User Actions

[0393] The user answers the learning problems displayed on the device. For example, if the math problem is "5 + 3," the user enters "8" as the answer. The device then sends this answer to the server, which returns the result. The user can then move on to the next problem based on the result.

[0394] Specific examples

[0395] In the first learning cycle, the problem generated by the server is "5 + 3." If the user answers "8," the server determines this is the correct answer and increases the difficulty of the next problem. The device then displays feedback to the user saying, "You got it right! The difficulty will increase."

[0396] In the second learning cycle, the server generates a more difficult question, for example, "15 + 7." If the user answers "20," the server determines this is an incorrect answer and lowers the difficulty of the next question. The device displays feedback saying, "That's wrong. We'll lower the difficulty."

[0397] In this way, the system can adjust the difficulty level in real time based on the user's answers, providing an appropriate learning environment. This continuous feedback and adjustment effectively supports the user's academic improvement.

[0398] This system can also handle Japanese language learning problems, not just math problems. By automatically generating appropriate learning problems according to difficulty level, it helps users to study each subject in a balanced way.

[0399] As described above, the present invention is extremely effective as a learning support system for children, and can maximize the learning effect.

[0400] The processing flow will be explained below.

[0401] Step 1:

[0402] The server obtains the current difficulty level using an instance of the problem generator class. Specifically, it checks the initial difficulty level by referencing the property self.problem_generator.difficulty .

[0403] Step 2:

[0404] The server generates practice questions based on the acquired difficulty level. For example, if the difficulty level is 1, it generates addition problems using random numbers in the range of 1 to 10. The problems are stored in string format.

[0405] Step 3:

[0406] The server sends the generated learning questions to the device. Specifically, data including the question content (e.g., "5 + 3") is transferred to the device.

[0407] Step 4:

[0408] The terminal displays the transmitted study questions to the user, and displays the question text on the screen so that the user can visually recognize the question content.

[0409] Step 5:

[0410] The user answers the displayed study question. For example, the user answers "8" to the question "5 + 3."

[0411] Step 6:

[0412] The terminal collects the user's answers. Specifically, it stores the answers entered by the user as numerical values ​​and prepares to send them to the server.

[0413] Step 7:

[0414] The terminal sends the collected answers of the user to the server, and the user's input data is passed to the server.

[0415] Step 8:

[0416] The server determines whether the received user answer is correct or incorrect by evaluating the question text and comparing the correct answer with the user answer.

[0417] Step 9:

[0418] The server adjusts the difficulty of the study questions based on the answers, increasing the difficulty if the user answers correctly and decreasing it if the user answers incorrectly.

[0419] Step 10:

[0420] The server generates feedback regarding the judgment result and difficulty adjustment, and sends it to the terminal. It creates a feedback message (for example, "You got it right! The difficulty level will increase.").

[0421] Step 11:

[0422] The terminal displays the feedback received from the server to the user, who can obtain information about his / her answer results and future study strategies.

[0423] Step 12:

[0424] The user checks the displayed feedback and moves on to the next problem, and this cycle is repeated to maximize the user's learning effect.

[0425] Example 1

[0426] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0427] Conventional learning systems for children often do not adjust the difficulty of questions in real time according to the individual user's learning progress, resulting in a decrease in learning efficiency. Furthermore, many systems only support a single subject, making it difficult to provide balanced, comprehensive learning support. Given these points, there is a demand for a learning support system that can appropriately adjust the difficulty level based on the user's answers and can support multiple subjects.

[0428] 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.

[0429] In this invention, the server includes means for generating study questions for children using a study question generation program, means for transmitting the study questions to a terminal and displaying them, means for accepting a user's answer to the study questions, means for transmitting the user's answer to the server, means for determining whether the answer is correct or incorrect and adjusting the difficulty of the study questions based on the result, and means for generating and displaying feedback on the determination result and the difficulty adjustment to the user. This allows the difficulty of the questions to be adjusted in real time based on the user's answer, enabling balanced learning support for multiple subjects.

[0430] A "program for generating study questions" is software that automatically creates study questions for subjects such as arithmetic and Japanese language based on the user's study data and level of difficulty.

[0431] A "server" is a computer system that performs processes such as generating study questions, receiving and judging user answers, adjusting difficulty, and generating feedback.

[0432] A "terminal" is a device operated by a user, and is a device for displaying study questions, inputting user answers, and displaying feedback.

[0433] "User's answer" refers to the answer data that the user inputs to the study question.

[0434] The "means for transmitting the answer to the server" is a communication means for sending the user's answer from the terminal to the server.

[0435] The "means for determining" refers to an algorithm and program that the server uses to check the user's answer against the correct answer and determine whether it is correct or incorrect.

[0436] The "means for adjusting the difficulty level" refers to an algorithm and program for appropriately changing the difficulty level of the next study question based on the evaluation result of the user's answer.

[0437] The "means for generating feedback" is a program for creating a message to be displayed to the user based on the user's answer results and information regarding difficulty level adjustment.

[0438] The "means for transmitting study questions to the terminal" refers to a communication means for transmitting the generated study questions from the server to the terminal.

[0439] The "means for displaying study questions" refers to software and hardware for displaying study questions received by the terminal on a user interface.

[0440] The present invention is a system that automatically generates learning questions for children and adjusts the difficulty of the questions based on the user's answers. This system is mainly composed of a server and a terminal.

[0441] Server Operation

[0442] The server generates study questions using a "program for generating study questions" that uses a "generative AI model." This problem generation program automatically creates appropriate study questions, taking into account the current level of difficulty. The server sends the generated questions in JSON format to the device and waits for the user to enter their answers. The user's answers are then sent to the server via the device, and the server compares them with the correct answers. Based on the evaluation results, the server adjusts the difficulty of the next question. It then generates feedback regarding the difficulty adjustment and the evaluation results and sends this to the device. The server is responsible for generating questions, evaluating answers, adjusting the difficulty, and generating feedback.

[0443] Device behavior

[0444] The device displays the learning questions received from the server on a user interface. A form is displayed for the user to enter their answers to the questions. When the user enters their answers, the device converts the data into JSON format and sends it to the server. When feedback is received from the server, the device analyzes it and displays it on the user interface. For example, if the user answers correctly, it displays "You're correct! The difficulty level will increase," and if the answer is incorrect, it displays "You're wrong. The difficulty level will be lowered." The device is responsible for displaying learning questions, sending answers, and displaying feedback.

[0445] User Actions

[0446] The user answers the study questions displayed on the device. For example, if the math question displayed is "5 + 3," the user enters "8" as the answer. The device then sends this answer to the server, which returns a judgment result. The user can then move on to the next question based on the result. The user enters the answer to the study question and checks the feedback from the server.

[0447] Specific examples

[0448] In the first learning cycle, the problem generated by the server is "5 + 3." If the user answers "8," the server determines this is the correct answer and increases the difficulty of the next problem. The device then displays feedback to the user saying, "You got it right! The difficulty will increase."

[0449] In the second learning cycle, the server generates a more difficult question, for example, "15 + 7." If the user answers "20," the server determines this is an incorrect answer and lowers the difficulty of the next question. The device displays feedback saying, "That's wrong. We'll lower the difficulty."

[0450] Through this series of processes, the system can provide appropriate questions according to the user's learning progress, thereby providing efficient learning support.

[0451] Example prompt

[0452] Here are some example prompts to enter into a generative AI model:

[0453] "The server of this system first generates learning questions using a question generation class. Depending on the current level of difficulty, arithmetic questions or Japanese language questions are selected. The generated questions are then sent to the terminal, and when the user enters the answer, the answer is sent to the server. The server evaluates the answer and increases the difficulty if it is correct, or decreases it if it is incorrect. Please explain this process with a concrete example."

[0454] From the above explanation, the detailed operation and effects of the present invention can be understood.

[0455] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0456] Program processing flow

[0457] Step 1:

[0458] Start the program to generate questions

[0459] The server launches a "program for generating learning questions" using the "generative AI model."

[0460] Input: Current difficulty information, user learning history data.

[0461] Specific operation: The server obtains the current difficulty information and the user's learning history from the internal database and inputs them into the generative AI model.

[0462] Output: A new training problem is generated.

[0463] Step 2:

[0464] Send and display study questions on your device

[0465] The server converts the generated learning questions into JSON format and sends them to the terminal.

[0466] Input: The newly generated training problem.

[0467] Specific operation: The server formats the training problem as a JSON object and sends it to the device using a communication protocol (e.g., HTTP, WebSocket).

[0468] Output: The training problem sent to the device.

[0469] Step 3:

[0470] Displaying study questions to users

[0471] The terminal analyzes the received study questions and displays them on the user interface.

[0472] Input: Training question data from the server (JSON format).

[0473] Specific operation: The device parses the JSON data and displays the learning questions on the user's screen.

[0474] Output: The training question displayed in the user interface.

[0475] Step 4:

[0476] Enter the user's answer

[0477] The user inputs answers to the study questions displayed on the terminal.

[0478] Input: The study question displayed in the user interface.

[0479] Specific operation: The user enters the answer into the input form and clicks the submit button.

[0480] Output: The answer entered by the user.

[0481] Step 5:

[0482] Send the user's answer to the server

[0483] The device converts the user's answer into JSON format and sends it to the server.

[0484] Input: The answer entered by the user.

[0485] Specific operation: The device formats the answer data as a JSON object and sends it to the server using a communication protocol.

[0486] Output: The answer data sent to the server.

[0487] Step 6:

[0488] Judge the answer and adjust the difficulty level

[0489] The server receives the user's answer and determines whether it is correct or incorrect.

[0490] Input: User answer data, correct answer data for the learning questions.

[0491] Specific operation: The server compares the answer data with the correct answers to the learning questions and determines whether they are correct or not. Based on the result of the judgment, it determines the difficulty level of the next question.

[0492] Output: Judgment result and difficulty information for the next question.

[0493] Step 7:

[0494] Generate a feedback message

[0495] The server generates a feedback message for the user based on the determination result.

[0496] Input: Answer judgment result, difficulty information.

[0497] Specific operation: The server generates a feedback message in text format based on the judgment result and difficulty information.

[0498] Output: The generated feedback message.

[0499] Step 8:

[0500] Send and display feedback on the device

[0501] The server sends the generated feedback message to the terminal.

[0502] Input: Feedback message.

[0503] Specific operation: The server formats the feedback message as a JSON object and sends it to the device using a communication protocol.

[0504] Output: Feedback sent to the device.

[0505] Step 9:

[0506] Displaying feedback to the user

[0507] The terminal displays the received feedback message on a user interface.

[0508] Input: Feedback message from the server (JSON format).

[0509] Specific behavior: The device parses the JSON data and displays a feedback message on the user's screen, for example, "Correct! The difficulty level will increase."

[0510] Output: The feedback message displayed in the user interface.

[0511] (Application example 1)

[0512] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0513] Currently, most learning support systems for children are used at home or at school, making it difficult to make effective use of travel time. Furthermore, conventional systems only allow for the display of learning problems and the input of answers in limited environments, making it impossible to provide effective learning support in mobile devices such as self-driving vehicles. Furthermore, it is important to provide real-time feedback and appropriate difficulty adjustments to maintain learning motivation. Therefore, there is a need for a system that maximizes children's learning efficiency by providing learning problems while on the move, adjusting the difficulty level, and providing feedback in real time.

[0514] 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.

[0515] In this invention, the server includes means for generating study questions corresponding to the current level of difficulty, means for displaying the study questions, means for displaying the study questions on a mobile object, means for accepting a user's answer to the study questions by voice or touch operation, means for determining whether the user's answer is correct or incorrect, means for adjusting the difficulty of the study questions based on the determination result, and means for displaying feedback regarding the determination result and the difficulty level adjustment to the user. This enables learning activities even while on the move, and by providing effective feedback and difficulty level adjustment in real time, children's learning efficiency can be improved.

[0516] "Study Problems" are educational tasks or questions that children must complete and are automatically generated by the server.

[0517] A "user answer" is an answer provided by a user to a study question, and is input through voice or touch operation.

[0518] "Current difficulty" refers to the difficulty level of the study questions that is set based on the user's level of understanding and progress.

[0519] "Mobile object" refers to something in motion, such as an autonomous vehicle, and specifically refers to the in-car environment, including the infotainment system or tablet.

[0520] "Display means" refers to a device or function for visually or audibly presenting information such as study questions and feedback to the user.

[0521] "Voice input" refers to an input method in which a user provides answers to study questions using voice.

[0522] "Touch operation" refers to the user entering answers using the touchscreen of a tablet or infotainment system.

[0523] The "judging means" is a function that evaluates whether the user's answer is correct or incorrect and adjusts the difficulty level based on the result.

[0524] "Feedback" provides the user with information indicating the evaluation of their answer and next steps.

[0525] The present invention provides a system for automatically generating learning questions for children and adjusting the difficulty of the questions based on the user's answers. This system can be installed in an autonomous vehicle, enabling learning activities while traveling in the vehicle. A specific embodiment of the system is described below.

[0526] System Structure

[0527] This system mainly consists of a server and a terminal. The server generates learning questions, evaluates the user's answers, and provides the function to adjust the difficulty level. The terminal, especially the infotainment system or tablet in the autonomous vehicle, displays the learning questions to the user, collects the user's answers, and displays the feedback received from the server.

[0528] Server Operation

[0529] The server first generates learning questions using a question generation class. The generated learning questions are sent to the terminal and displayed to the user. The user's answers are then sent to the server via the terminal. The server compares the received answers with the correct answers, increasing the difficulty if they are correct and decreasing the difficulty if they are incorrect. This provides an appropriate learning environment according to the user's level of understanding and progress.

[0530] Device behavior

[0531] The device is an infotainment system or tablet installed in the autonomous vehicle, which displays the learning questions and accepts the user's answers. The user inputs their answers through touch or voice input. The answers are sent to a server, and the results and feedback on difficulty adjustments are displayed on the device. This allows users to continue learning without interruption even while on the move.

[0532] User Actions

[0533] The user, or child, works on learning problems while in the car. For example, when a math problem such as "15 + 7" appears, the user inputs the answer "22" using touch or voice input. The device sends the answer to the server, which evaluates the result and returns feedback. The user then works on the next problem based on the result.

[0534] Specific examples

[0535] In the first learning cycle, the problem generated by the server is "15 + 7." If the user answers "22," the server determines this is an incorrect answer and lowers the difficulty of the next problem. The device then displays feedback to the user saying, "This is incorrect. Proceed to the next problem."

[0536] In the second learning cycle, the server generates a question with a lower level of difficulty, such as "8 + 4." If the user answers "12," the server recognizes this as the correct answer and increases the difficulty of the next question. The device displays feedback saying, "Correct! The difficulty will increase."

[0537] Prompt Sentence Examples

[0538] Examples of prompts for generative AI models include:

[0539] "Current difficulty level is 2. Generate math problems for children."

[0540] "Please create a Japanese language question that corresponds to level 3."

[0541] This allows learning activities to be carried out while on the move, and by providing effective feedback and difficulty adjustments in real time, children's learning efficiency can be improved.

[0542] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0543] Step 1:

[0544] The server generates the training questions (input: current difficulty level, output: generated training questions)

[0545] The server generates learning problems based on the current level of difficulty. For example, it uses a generative AI model to input a prompt such as "Please generate a math problem of level 1" and outputs appropriate learning problems based on that. The server stores the generated learning problems and prepares them to be sent to the device.

[0546] Step 2:

[0547] The device displays the study questions (input: study questions received from the server, output: displayed study questions)

[0548] The device displays the learning questions received from the server to the user. During this process, the question is displayed on the screen or the user is informed of the question by voice output. For example, the question "15 + 7" is displayed on the screen.

[0549] Step 3:

[0550] User enters answer (input: study question, output: user answer)

[0551] The user inputs answers to the displayed study questions. The input method can be touch operation or voice input. For example, the user can provide the answer "22" by voice input.

[0552] Step 4:

[0553] The device receives the user's answer and sends it to the server (input: user's answer, output: sending the answer to the server)

[0554] The terminal receives the answer entered by the user and sends it to the server. The data includes the question ID along with the answer content.

[0555] Step 5:

[0556] The server judges the answer and adjusts the difficulty level (input: user's answer, output: judgement result and new difficulty level)

[0557] The server compares the received user answer with the correct answer data, and based on the results, increases the difficulty level if the answer is correct, or decreases it if the answer is incorrect. For example, if the answer "22" is incorrect, the difficulty level of the next question is lowered.

[0558] Step 6:

[0559] The server generates feedback and sends it to the device (input: judgment result and new difficulty level, output: feedback message).

[0560] The server generates a feedback message for the user based on the result of the judgment and the new difficulty level. For example, it generates a message such as "This is a mistake. Proceed to the next question." and sends it to the terminal.

[0561] Step 7:

[0562] The device displays the feedback (input: feedback message received from the server, output: displayed feedback)

[0563] The terminal displays the feedback message received from the server to the user. Feedback is provided by visual display or audio, allowing the user to confirm the results of their answers.

[0564] Step 8:

[0565] The device requests a new learning problem (input: new difficulty level, output: next learning problem)

[0566] After providing feedback to the server, the device requests the server to generate new learning questions corresponding to the new level of difficulty for the next learning cycle, thereby maintaining continuity of learning.

[0567] 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.

[0568] The present invention provides a learning support system for children that incorporates an emotion engine that recognizes the emotions of a user. Specific embodiments of the system will be described below.

[0569] This system mainly consists of a server, a terminal, and an emotion engine. The server generates learning questions, evaluates users' answers, and adjusts the difficulty level. The terminal displays learning questions to users, collects their answers, and displays feedback received from the server. The emotion engine recognizes users' emotions and adjusts the difficulty and type of learning questions based on those emotions.

[0570] Server Operation

[0571] The server first generates study questions using a problem generation class. The problem generation class stores the current difficulty level and creates appropriate study questions based on that level. For example, for math problems, a low level generates addition problems using random numbers in the range of 1 to 10, while a high level generates addition problems in the range of 1 to 20. For Japanese language problems, reading and writing tasks are presented according to the level of difficulty.

[0572] The generated learning questions are sent to the device and displayed to the user. The user's answers are then sent to the server via the device. The server compares the received answers with the correct answers, increasing the difficulty if they are correct and decreasing the difficulty if they are incorrect. Furthermore, the difficulty and type of learning questions are adjusted based on the user's emotions recognized by the emotion engine.

[0573] Device behavior

[0574] The device displays the study questions received from the server to the user. The question text is displayed on the screen so that the user can see the question content. When the user enters the answer to the study question, the answer is sent to the server. The device receives feedback from the server regarding the assessment result and difficulty level adjustment, and displays this to the user. For example, if the user answers correctly, it displays "You got it right! The difficulty level will be increased," and if the answer is incorrect, it displays "You got it wrong. The difficulty level will be lowered."

[0575] Emotion Engine Operation

[0576] The emotion engine measures data such as the user's facial expressions, voice, and input speed to recognize the user's emotions. For example, if it recognizes that the user is feeling stressed, it temporarily lowers the difficulty of the study questions to reduce the user's burden. On the other hand, if the user is feeling relaxed, it adjusts the difficulty level appropriately to maintain or increase it.

[0577] User Actions

[0578] The user answers the learning problems displayed on the device. For example, if the math problem is "5 + 3," the user enters "8" as the answer. The device then sends the answer to the server, which returns a judgment and feedback. The user can then move on to the next problem based on the result. The emotion engine also monitors the user's emotional state and adjusts the learning experience more appropriately, allowing the user to continue studying without stress.

[0579] Specific examples

[0580] In the first learning cycle, the problem generated by the server is "5 + 3." If the user answers "8," the server determines this is the correct answer and increases the difficulty of the next problem. The device then displays feedback to the user saying, "You got it right! The difficulty will increase." Also, if the emotion engine recognizes a relaxed state from the user's facial expressions and voice, the difficulty of the next problem will increase appropriately.

[0581] In the second learning cycle, the server generates a more difficult question, for example, "15 + 7." If the user answers "20," the server determines this is an incorrect answer and lowers the difficulty of the next question. Also, if the emotion engine recognizes that the user is feeling stressed, it appropriately lowers the difficulty of the next question to reduce the user's burden. The device displays feedback saying, "That's a mistake. We'll lower the difficulty."

[0582] In this way, the system can provide an appropriate learning environment by adjusting the difficulty and type of questions in real time based on the user's answers and emotional state. This continuous feedback and adjustment effectively supports the user's academic improvement.

[0583] Furthermore, this system can handle multiple subjects, such as math and Japanese. By automatically generating appropriate study questions according to difficulty level, it can help users study each subject in a balanced way.

[0584] As described above, the present invention is extremely effective as a learning support system for children, and can maximize the learning effect.

[0585] The processing flow will be explained below.

[0586] Step 1:

[0587] The server obtains the current difficulty level using an instance of the problem generator class. Specifically, it checks the initial difficulty level by referencing the property self.problem_generator.difficulty .

[0588] Step 2:

[0589] The server generates learning questions based on the acquired difficulty level. For example, if the difficulty level is 1, it generates addition questions using random numbers in the range of 1 to 10. The generated questions are stored in string format.

[0590] Step 3:

[0591] The server sends the generated learning questions to the device. Specifically, it transfers data including the question content (e.g., "5 + 3") to the device.

[0592] Step 4:

[0593] The terminal displays the transmitted study questions to the user, and displays the question text on the screen so that the user can visually recognize the question content.

[0594] Step 5:

[0595] The user answers the displayed study question. For example, the user answers "8" to the question "5 + 3."

[0596] Step 6:

[0597] The terminal collects the user's answers. Specifically, it stores the answers entered by the user as numerical values ​​and prepares to send the answer data to the server.

[0598] Step 7:

[0599] The terminal sends the collected answers of the user to the server, and the user's input data is passed to the server.

[0600] Step 8:

[0601] The server determines whether the received user answer is correct or incorrect. The server evaluates the question text and compares the correct answer with the user's answer. For example, the correct answer to "5 + 3" is "8," and if the user's answer is "8," it is determined to be correct.

[0602] Step 9:

[0603] The server adjusts the difficulty of the study questions based on the answers. If the user answers correctly, the difficulty level is increased, and if the user answers incorrectly, the difficulty level is decreased. For example, the difficulty level may be increased from 1 to 2, or decreased from 2 to 1.

[0604] Step 10:

[0605] The emotion engine analyzes the user's facial expressions, voice, typing speed, etc. to recognize the user's emotions, thereby determining whether the user is stressed or relaxed.

[0606] Step 11:

[0607] An emotion engine adjusts the difficulty or type of study questions based on the perceived user emotion, for example, if the user is stressed, the next study question will be less difficult.

[0608] Step 12:

[0609] The server generates feedback regarding the result of the judgment and the difficulty adjustment, and sends it to the device. It creates a feedback message (e.g., "You got it right! The difficulty will be increased." or "You got it wrong. The difficulty will be decreased.").

[0610] Step 13:

[0611] The terminal displays the feedback received from the server to the user, who can obtain information about his / her answer results and future study strategies.

[0612] Step 14:

[0613] The user checks the displayed feedback and moves on to the next problem. For example, if the emotion engine determines that the user is feeling stressed, the difficulty level of the next problem is set low. This cycle is repeated to maximize the user's learning effect.

[0614] Example 2

[0615] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0616] Conventional learning support systems adjust the difficulty of study questions based on the user's answers, but lack a mechanism for adjusting the learning experience based on the user's emotional state. As a result, if the user is stressed or overly relaxed, the difficulty level may not be adjusted appropriately, potentially reducing the learning effect. The present invention aims to recognize the user's emotions and adjust the difficulty and type of study questions based on that, allowing the user to continue learning in an optimal state.

[0617] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for generating study questions corresponding to the current level of difficulty, means for displaying the study questions, means for accepting a user's answers to the study questions, means for determining whether the user's answers are correct or incorrect, means for adjusting the difficulty of the study questions based on the determination result, means for collecting emotional data and recognizing the user's emotions, means for adjusting the difficulty or type of the study questions based on the emotion recognition, and means for displaying feedback regarding the determination result and the difficulty adjustment to the user. This makes it possible to comprehensively determine the user's answering status and emotional state and provide an appropriate learning environment in real time.

[0618] The following are definitions of important terms contained in the claims.

[0619] A "study question" is a math or language related challenge provided for the user to answer.

[0620] "Difficulty" is an indicator of the complexity of the study questions and the difficulty of solving them.

[0621] A "server" is a computer system that generates study questions, judges user answers, adjusts difficulty, and provides feedback.

[0622] A "terminal" is a device that displays study questions to a user, collects the user's answers, and displays feedback from the server.

[0623] "Emotion data" is information collected from the user's facial expression, voice, input speed, etc., and is data that indicates the user's emotional state.

[0624] An "emotion engine" is a software or hardware system for analyzing emotion data and recognizing a user's emotion.

[0625] "Feedback" is information that provides the user with the evaluation results of the user's answers, as well as study instructions and comments based on the evaluation results.

[0626] "Determination" is the process of determining whether the answer given by the user is correct or incorrect.

[0627] "Tuning" is the process of changing the difficulty and type of study questions based on the user's answers and emotional state.

[0628] "Display" refers to the act of visually presenting information on the screen of a terminal, such as showing study questions and feedback to the user.

[0629] The present invention is a learning support system for children that combines an emotion engine that recognizes the user's emotions. This system is mainly composed of a server, a terminal, and an emotion engine. Specific embodiments of the system are described below.

[0630] System Configuration

[0631] The system includes the following means:

[0632] 1. Server

[0633] 2. Terminal

[0634] 3. Emotion Engine

[0635] Server Operation

[0636] The server first generates learning problems using a problem generation class. The problem generation class stores the current difficulty level and creates appropriate learning problems based on that level. For example, in arithmetic, a low level of difficulty generates a simple addition problem like "5 + 3," while a high level of difficulty generates a more complex addition problem like "15 + 7." The generated learning problems are then sent to the device and displayed to the user. After the user's answer is sent to the server via the device, the server compares the answer with the correct answer and makes a judgment. If the answer is correct, the difficulty level is increased; if the answer is incorrect, the difficulty level is decreased. The difficulty and type of learning problems are further adjusted based on the user's emotional data recognized by the emotion engine.

[0637] Examples:

[0638] Example prompt: "The server generates a '5 + 3' problem and sends it to the terminal, then waits for the user's answer. After the user enters the answer, write a program that judges the answer and returns appropriate feedback. Also, add a function to adjust the difficulty of the problem using the user's emotional data."

[0639] Device behavior

[0640] The device displays the learning questions received from the server to the user. For example, the problem "5 + 3" is displayed on the screen, and the user inputs the answer to the problem. This answer is sent to the server, and the user checks the feedback from the server. The feedback from the server is displayed to the user as a message such as "That's correct! The difficulty will increase" or "That's incorrect. The difficulty will be lowered."

[0641] Emotion Engine Operation

[0642] The emotion engine uses emotion sensors to measure data such as the user's facial expressions, voice, and input speed. It then analyzes the collected data using an AI model to recognize the user's emotions. For example, it can determine whether the user is feeling stressed or relaxed based on data from the camera, microphone, and keyboard input speed. The recognized emotion data is sent to the server, which uses it as reference information to adjust the difficulty and type of the next learning problem.

[0643] User Actions

[0644] The user answers the study questions displayed on the device. For example, they enter "8" for the "5 + 3" question. After answering, the device sends the answer to the server and receives and displays feedback. This allows the user to prepare for the next question. The user can also see that their learning progress is optimized in real time according to the emotion recognition by the emotion engine.

[0645] This system comprehensively assesses the user's response status and emotional state, and adjusts the difficulty and type of study questions appropriately to provide an effective learning environment, which is expected to improve the user's academic ability.

[0646] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0647] The processing flow of the program of this system will be explained in detail below, divided into processing steps.

[0648] Step 1: Generate training questions

[0649] The server uses the problem generation class to generate problems based on the current difficulty level. For example, if the current difficulty level is low, the server generates a simple addition problem such as "5 + 3." The input for this problem generation is the current difficulty level data, and the output is the generated problem.

[0650] Step 2: Submit and view the exercises

[0651] The server sends the generated study questions to the terminal. The input is the generated study question data, and the output is a notification that the sending process is complete. The terminal then displays the received study questions on the screen. For example, a "5 + 3" problem is displayed on the screen. The input here is the study question data received from the server, and the output is the problem displayed on the screen in a format that the user can see.

[0652] Step 3: User answers

[0653] The user inputs answers to the study questions displayed on the terminal. For example, the user inputs "8" using the keyboard. The input is the data the user answered, and the output is the answer data stored inside the terminal.

[0654] Step 4: Submitting user answers

[0655] The terminal sends the user's answer to the server. The input is the user's answer data, and the output is a transmission completion notification to the server.

[0656] Step 5: Determine the answer

[0657] The server compares the received user answer with the correct answer and makes a judgment. For example, if the received answer is "8" and the question is the addition "5 + 3", it judges whether the answer is correct. The input is the user's answer data and the correct answer data, and the output is the judgment result data.

[0658] Step 6: Collect and recognize emotion data

[0659] The emotion engine collects data such as the user's facial expressions, voice, and input speed, and uses this data to recognize the user's emotions. For example, it acquires the user's facial expression data through a camera and analyzes it with an AI model to determine whether the user is relaxed or stressed. The input is emotion data, and the output is the user's emotion recognition result data.

[0660] Step 7: Adjusting the difficulty

[0661] The server adjusts the difficulty of the learning questions based on the answer judgment results and emotion recognition results. For example, if the user answers correctly and the emotion engine recognizes that the user is relaxed, the server increases the difficulty of the next question. The input is the judgment result data and emotion recognition result data, and the output is the adjusted difficulty data.

[0662] Step 8: Submit and view feedback

[0663] The server sends the judgment result and the difficulty adjustment result to the terminal, and the terminal displays them to the user. For example, a feedback message such as "Correct! The difficulty will increase." The input is the feedback data from the server, and the output is the feedback message displayed to the user.

[0664] Through the above specific processing steps, the system can comprehensively judge the user's answering situation and emotional state, and provide an appropriate learning environment in real time.

[0665] (Application example 2)

[0666] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0667] Conventional learning support systems and work support systems set the difficulty level unilaterally without considering the user's emotional state, which often led to stress and fatigue for the user. Furthermore, because the difficulty level was set uniformly, the user's learning effect and work efficiency were often reduced. In this modern age, where flexible responses according to the user's state are required, systems incorporating emotion recognition are becoming increasingly important.

[0668] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for generating study questions corresponding to the current level of difficulty, means for displaying study questions, means for accepting a user's answers to the study questions, means for determining whether the user's answers are correct or incorrect, means for adjusting the difficulty of the study questions based on the determination result, means for displaying feedback to the user regarding the determination result and the difficulty adjustment, means for recognizing the user's emotions, means for adjusting the difficulty and type of study questions based on the emotions, and means for feeding back the emotion recognition results to the work environment and adjusting the work difficulty appropriately. This provides an appropriate learning environment and work environment according to the user's emotional state, allowing the user to study and work efficiently without stress.

[0669] A "system" is a collection of multiple elements, each of which works together to achieve a specific function.

[0670] The "means for generating study questions" is a component within the system that has the function of creating questions that correspond to the user's study content.

[0671] The "means for displaying study questions" is a component that has the function of visually presenting study questions to the user.

[0672] The "means for accepting user answers" is a component that has the function of allowing the system to receive answers entered by the user to the study questions.

[0673] The "means for determining whether the answer is correct or incorrect" is a component that has the function of determining whether the user's answer is correct or not.

[0674] The "means for adjusting difficulty" is a component that has the function of automatically changing the difficulty of the next study question to be presented based on the user's answer.

[0675] The "means for displaying feedback to the user" is a component that has the function of conveying information about the answer result and difficulty level adjustment to the user.

[0676] The "means for recognizing user's emotions" is a component having a function for analyzing the user's emotional state (for example, stress, relaxation, motivation, etc.).

[0677] The "means for adjusting the difficulty and type of study questions based on emotions" is a component that has the function of appropriately changing the difficulty and type of study questions for the user based on the results of emotion recognition.

[0678] The "means for feeding back emotion recognition results to the work environment and adjusting the difficulty of the work appropriately" is a component that has the function of adjusting the work content and difficulty based on the user's emotion recognition results, thereby reducing the burden on the user.

[0679] The present invention is a learning and work support system that combines an emotion engine that recognizes the user's emotions. This system is composed of a server, a terminal, and an emotion engine.

[0680] The server first generates study questions using a problem generation class. The problem generation class stores the current difficulty level and creates appropriate study questions based on that level. For example, for arithmetic questions, a basic addition problem is generated if the difficulty level is low, and a more complex addition problem is generated if the difficulty level is high. For Japanese language questions, reading and writing tasks are presented according to the respective level of difficulty. The generated study questions are sent to the device and displayed to the user. The user's answers are then sent to the server via the device. The server compares the received answers with the correct answers and increases the difficulty level if they are correct, or decreases the difficulty level if they are incorrect. The server also adjusts the difficulty level and type of study questions based on the user's emotions recognized by the emotion engine.

[0681] The device displays the study questions received from the server to the user. The question text is displayed on the screen so that the user can see the question content. When the user enters the answer to the study question, the answer is sent to the server. The device receives feedback from the server regarding the assessment result and difficulty level adjustment, and displays this to the user. For example, if the user answers correctly, it displays "You got it right! The difficulty level will be increased," and if the answer is incorrect, it displays "You got it wrong. The difficulty level will be lowered."

[0682] The emotion engine measures data such as the user's facial expressions, voice, and input speed to recognize the user's emotions. For example, if it recognizes that the user is feeling stressed, it temporarily lowers the difficulty of the study questions to reduce the user's burden. On the other hand, if the user is feeling relaxed, it adjusts the difficulty level appropriately to maintain or increase it.

[0683] Furthermore, this invention can also be applied to assisting factory robots in their work. This system involves installing an emotion engine in a factory robot, recognizing the emotional state of a worker in real time, and adjusting the difficulty of the work based on the results. For example, if the emotion engine recognizes that a worker is under stress, it can assign the worker an easy task or suggest a temporary break. If the emotion engine recognizes that the worker is highly motivated, it can assign a difficult task.

[0684] To illustrate, consider the following scenario:

[0685] Example 1:

[0686] If the emotion engine recognizes that Worker A is under stress, it assigns him / her an easy task (e.g., sorting parts), thereby reducing the workload.

[0687] Example 2:

[0688] If Worker B is perceived as highly motivated, he or she will be assigned a more difficult task (e.g., assembling a complex machine), which will improve work efficiency.

[0689] Example prompt sentence:

[0690] "Recognize the facial expressions of the workers from the images and use an emotion engine to estimate their emotions. Assuming the emotion is stress, relaxation, or motivation, suggest an appropriate level of task difficulty depending on the emotion."

[0691] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0692] Step 1:

[0693] The server generates learning questions according to the current level of difficulty using a question generation class. At this time, the current level of difficulty is given as input, and learning content according to that level of difficulty (for example, addition problems in arithmetic or reading and writing problems in Japanese) is output.

[0694] Step 2:

[0695] The server sends the generated training questions to the terminal, where the input is the generated training questions and the output is the training question data sent to the terminal.

[0696] Step 3:

[0697] The terminal displays the exercises received from the server to the user, with the input being the exercises received from the server and the output being the text of the exercises displayed to the user.

[0698] Step 4:

[0699] The user inputs answers to the displayed study questions. The input is the study question and the user's answer, and the output is the user's answer data input to the terminal.

[0700] Step 5:

[0701] The terminal sends the user's answer to the server. The input is the user's answer data, and the output is the answer data sent to the server.

[0702] Step 6:

[0703] The server determines whether the user's answer is correct or incorrect. The input is the user's answer and the correct answer data, and the output is the judgment result (correct or incorrect).

[0704] Step 7:

[0705] The server adjusts the difficulty of the next study question based on the judgment result. The input is the judgment result, and the output is the difficulty data for the next study question.

[0706] Step 8:

[0707] The server generates feedback regarding the judgment result and the difficulty level adjustment and sends it to the terminal. The input is the judgment result and the adjusted difficulty level, and the output is a feedback message.

[0708] Step 9:

[0709] The terminal displays the feedback received from the server to the user. The input is the feedback message and the output is the feedback text displayed to the user.

[0710] Step 10:

[0711] The emotion engine measures and analyzes data such as the user's facial expressions, voice, and input speed to recognize the user's emotions. The input is the user's raw data (facial expressions, voice data, input speed data), and the output is the user's emotional state (stress, relaxation, motivation, etc.).

[0712] Step 11:

[0713] The server adjusts the difficulty and type of training questions based on the emotion recognition results. The input is the emotion recognition results, and the output is the adjusted difficulty and type of questions.

[0714] Step 12:

[0715] The server feeds back the emotion recognition results to the work environment and adjusts the task difficulty. The input is the emotion recognition results and the current task content, and the output is the adjusted task.

[0716] Step 13:

[0717] The terminal displays the adjusted work task to the user or the work robot or issues instructions to the user or the work robot. The input is the adjusted work task data, and the output is instructions to the user or the work robot.

[0718] 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.

[0719] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0720] 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.

[0721] [Third embodiment]

[0722] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0723] 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.

[0724] 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).

[0725] 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.

[0726] 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.

[0727] 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).

[0728] 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.

[0729] 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.

[0730] 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.

[0731] 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.

[0732] 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.

[0733] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0734] The present invention is a system for automatically generating learning questions for children and adjusting the difficulty of the questions based on the answers of a user. Specific embodiments of the system are described below.

[0735] This system mainly consists of a server and a terminal. The server generates study questions, evaluates users' answers, and adjusts the difficulty level. The terminal displays study questions to users, collects their answers, and displays feedback received from the server.

[0736] Server Operation

[0737] The server first generates study questions using a problem generation class. The problem generation class stores the current difficulty level and creates appropriate study questions based on that level. For example, in arithmetic, a low level of difficulty generates addition problems within the range of 1 to 10, while a high level of difficulty generates addition problems within the range of 1 to 20. In Japanese language questions, reading and writing tasks are presented according to the level of difficulty.

[0738] The generated study questions are sent to the device and displayed to the user. The user's answers are then sent to the server via the device. The server compares the received answers with the correct answers, increasing the difficulty if they are correct, and decreasing the difficulty if they are incorrect. This provides an appropriate learning environment according to the user's level of understanding and progress.

[0739] Device behavior

[0740] The device displays the learning questions received from the server to the user. When the user enters an answer to a question, the answer is sent to the server. The server then receives feedback on the assessment result and difficulty level adjustment, which is then displayed to the user. For example, if the user answers correctly, the device displays "You got it right! The difficulty level will be increased," and if the answer is incorrect, the device displays "You got it wrong. The difficulty level will be lowered."

[0741] User Actions

[0742] The user answers the learning problems displayed on the device. For example, if the math problem is "5 + 3," the user enters "8" as the answer. The device then sends this answer to the server, which returns the result. The user can then move on to the next problem based on the result.

[0743] Specific examples

[0744] In the first learning cycle, the problem generated by the server is "5 + 3." If the user answers "8," the server determines this is the correct answer and increases the difficulty of the next problem. The device then displays feedback to the user saying, "You got it right! The difficulty will increase."

[0745] In the second learning cycle, the server generates a more difficult question, for example, "15 + 7." If the user answers "20," the server determines this is an incorrect answer and lowers the difficulty of the next question. The device displays feedback saying, "That's wrong. We'll lower the difficulty."

[0746] In this way, the system can adjust the difficulty level in real time based on the user's answers, providing an appropriate learning environment. This continuous feedback and adjustment effectively supports the user's academic improvement.

[0747] This system can also handle Japanese language learning problems, not just math problems. By automatically generating appropriate learning problems according to difficulty level, it helps users to study each subject in a balanced way.

[0748] As described above, the present invention is extremely effective as a learning support system for children, and can maximize the learning effect.

[0749] The processing flow will be explained below.

[0750] Step 1:

[0751] The server obtains the current difficulty level using an instance of the problem generator class. Specifically, it checks the initial difficulty level by referencing the property self.problem_generator.difficulty .

[0752] Step 2:

[0753] The server generates practice questions based on the acquired difficulty level. For example, if the difficulty level is 1, it generates addition problems using random numbers in the range of 1 to 10. The problems are stored in string format.

[0754] Step 3:

[0755] The server sends the generated learning questions to the device. Specifically, data including the question content (e.g., "5 + 3") is transferred to the device.

[0756] Step 4:

[0757] The terminal displays the transmitted study questions to the user, and displays the question text on the screen so that the user can visually recognize the question content.

[0758] Step 5:

[0759] The user answers the displayed study question. For example, the user answers "8" to the question "5 + 3."

[0760] Step 6:

[0761] The terminal collects the user's answers. Specifically, it stores the answers entered by the user as numerical values ​​and prepares to send them to the server.

[0762] Step 7:

[0763] The terminal sends the collected answers of the user to the server, and the user's input data is passed to the server.

[0764] Step 8:

[0765] The server determines whether the received user answer is correct or incorrect by evaluating the question text and comparing the correct answer with the user answer.

[0766] Step 9:

[0767] The server adjusts the difficulty of the study questions based on the answers, increasing the difficulty if the user answers correctly and decreasing it if the user answers incorrectly.

[0768] Step 10:

[0769] The server generates feedback regarding the judgment result and difficulty adjustment, and sends it to the terminal. It creates a feedback message (for example, "You got it right! The difficulty level will increase.").

[0770] Step 11:

[0771] The terminal displays the feedback received from the server to the user, who can obtain information about his / her answer results and future study strategies.

[0772] Step 12:

[0773] The user checks the displayed feedback and moves on to the next problem, and this cycle is repeated to maximize the user's learning effect.

[0774] Example 1

[0775] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0776] Conventional learning systems for children often do not adjust the difficulty of questions in real time according to the individual user's learning progress, resulting in a decrease in learning efficiency. Furthermore, many systems only support a single subject, making it difficult to provide balanced, comprehensive learning support. Given these points, there is a demand for a learning support system that can appropriately adjust the difficulty level based on the user's answers and can support multiple subjects.

[0777] 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.

[0778] In this invention, the server includes means for generating study questions for children using a study question generation program, means for transmitting the study questions to a terminal and displaying them, means for accepting a user's answer to the study questions, means for transmitting the user's answer to the server, means for determining whether the answer is correct or incorrect and adjusting the difficulty of the study questions based on the result, and means for generating and displaying feedback on the determination result and the difficulty adjustment to the user. This allows the difficulty of the questions to be adjusted in real time based on the user's answer, enabling balanced learning support for multiple subjects.

[0779] A "program for generating study questions" is software that automatically creates study questions for subjects such as arithmetic and Japanese language based on the user's study data and level of difficulty.

[0780] A "server" is a computer system that performs processes such as generating study questions, receiving and judging user answers, adjusting difficulty, and generating feedback.

[0781] A "terminal" is a device operated by a user, and is a device for displaying study questions, inputting user answers, and displaying feedback.

[0782] "User's answer" refers to the answer data that the user inputs to the study question.

[0783] The "means for transmitting the answer to the server" is a communication means for sending the user's answer from the terminal to the server.

[0784] The "means for determining" refers to an algorithm and program that the server uses to check the user's answer against the correct answer and determine whether it is correct or incorrect.

[0785] The "means for adjusting the difficulty level" refers to an algorithm and program for appropriately changing the difficulty level of the next study question based on the evaluation result of the user's answer.

[0786] The "means for generating feedback" is a program for creating a message to be displayed to the user based on the user's answer results and information regarding difficulty level adjustment.

[0787] The "means for transmitting study questions to the terminal" refers to a communication means for transmitting the generated study questions from the server to the terminal.

[0788] The "means for displaying study questions" refers to software and hardware for displaying study questions received by the terminal on a user interface.

[0789] The present invention is a system that automatically generates learning questions for children and adjusts the difficulty of the questions based on the user's answers. This system is mainly composed of a server and a terminal.

[0790] Server Operation

[0791] The server generates study questions using a "program for generating study questions" that uses a "generative AI model." This problem generation program automatically creates appropriate study questions, taking into account the current level of difficulty. The server sends the generated questions in JSON format to the device and waits for the user to enter their answers. The user's answers are then sent to the server via the device, and the server compares them with the correct answers. Based on the evaluation results, the server adjusts the difficulty of the next question. It then generates feedback regarding the difficulty adjustment and the evaluation results and sends this to the device. The server is responsible for generating questions, evaluating answers, adjusting the difficulty, and generating feedback.

[0792] Device behavior

[0793] The device displays the learning questions received from the server on a user interface. A form is displayed for the user to enter their answers to the questions. When the user enters their answers, the device converts the data into JSON format and sends it to the server. When feedback is received from the server, the device analyzes it and displays it on the user interface. For example, if the user answers correctly, it displays "You're correct! The difficulty level will increase," and if the answer is incorrect, it displays "You're wrong. The difficulty level will be lowered." The device is responsible for displaying learning questions, sending answers, and displaying feedback.

[0794] User Actions

[0795] The user answers the study questions displayed on the device. For example, if the math question displayed is "5 + 3," the user enters "8" as the answer. The device then sends this answer to the server, which returns a judgment result. The user can then move on to the next question based on the result. The user enters the answer to the study question and checks the feedback from the server.

[0796] Specific examples

[0797] In the first learning cycle, the problem generated by the server is "5 + 3." If the user answers "8," the server determines this is the correct answer and increases the difficulty of the next problem. The device then displays feedback to the user saying, "You got it right! The difficulty will increase."

[0798] In the second learning cycle, the server generates a more difficult question, for example, "15 + 7." If the user answers "20," the server determines this is an incorrect answer and lowers the difficulty of the next question. The device displays feedback saying, "That's wrong. We'll lower the difficulty."

[0799] Through this series of processes, the system can provide appropriate questions according to the user's learning progress, thereby providing efficient learning support.

[0800] Example prompt

[0801] Here are some example prompts to enter into a generative AI model:

[0802] "The server of this system first generates learning questions using a question generation class. Depending on the current level of difficulty, arithmetic questions or Japanese language questions are selected. The generated questions are then sent to the terminal, and when the user enters the answer, the answer is sent to the server. The server evaluates the answer and increases the difficulty if it is correct, or decreases it if it is incorrect. Please explain this process with a concrete example."

[0803] From the above explanation, the detailed operation and effects of the present invention can be understood.

[0804] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0805] Program processing flow

[0806] Step 1:

[0807] Start the program to generate questions

[0808] The server launches a "program for generating learning questions" using the "generative AI model."

[0809] Input: Current difficulty information, user learning history data.

[0810] Specific operation: The server obtains the current difficulty information and the user's learning history from the internal database and inputs them into the generative AI model.

[0811] Output: A new training problem is generated.

[0812] Step 2:

[0813] Send and display study questions on your device

[0814] The server converts the generated learning questions into JSON format and sends them to the terminal.

[0815] Input: The newly generated training problem.

[0816] Specific operation: The server formats the training problem as a JSON object and sends it to the device using a communication protocol (e.g., HTTP, WebSocket).

[0817] Output: The training problem sent to the device.

[0818] Step 3:

[0819] Displaying study questions to users

[0820] The terminal analyzes the received study questions and displays them on the user interface.

[0821] Input: Training question data from the server (JSON format).

[0822] Specific operation: The device parses the JSON data and displays the learning questions on the user's screen.

[0823] Output: The training question displayed in the user interface.

[0824] Step 4:

[0825] Enter the user's answer

[0826] The user inputs answers to the study questions displayed on the terminal.

[0827] Input: The study question displayed in the user interface.

[0828] Specific operation: The user enters the answer into the input form and clicks the submit button.

[0829] Output: The answer entered by the user.

[0830] Step 5:

[0831] Send the user's answer to the server

[0832] The device converts the user's answer into JSON format and sends it to the server.

[0833] Input: The answer entered by the user.

[0834] Specific operation: The device formats the answer data as a JSON object and sends it to the server using a communication protocol.

[0835] Output: The answer data sent to the server.

[0836] Step 6:

[0837] Judge the answer and adjust the difficulty level

[0838] The server receives the user's answer and determines whether it is correct or incorrect.

[0839] Input: User answer data, correct answer data for the learning questions.

[0840] Specific operation: The server compares the answer data with the correct answers to the learning questions and determines whether they are correct or not. Based on the result of the judgment, it determines the difficulty level of the next question.

[0841] Output: Judgment result and difficulty information for the next question.

[0842] Step 7:

[0843] Generate a feedback message

[0844] The server generates a feedback message for the user based on the determination result.

[0845] Input: Answer judgment result, difficulty information.

[0846] Specific operation: The server generates a feedback message in text format based on the judgment result and difficulty information.

[0847] Output: The generated feedback message.

[0848] Step 8:

[0849] Send and display feedback on the device

[0850] The server sends the generated feedback message to the terminal.

[0851] Input: Feedback message.

[0852] Specific operation: The server formats the feedback message as a JSON object and sends it to the device using a communication protocol.

[0853] Output: Feedback sent to the device.

[0854] Step 9:

[0855] Displaying feedback to the user

[0856] The terminal displays the received feedback message on a user interface.

[0857] Input: Feedback message from the server (JSON format).

[0858] Specific behavior: The device parses the JSON data and displays a feedback message on the user's screen, for example, "Correct! The difficulty level will increase."

[0859] Output: The feedback message displayed in the user interface.

[0860] (Application example 1)

[0861] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0862] Currently, most learning support systems for children are used at home or at school, making it difficult to make effective use of travel time. Furthermore, conventional systems only allow for the display of learning problems and the input of answers in limited environments, making it impossible to provide effective learning support in mobile devices such as self-driving vehicles. Furthermore, it is important to provide real-time feedback and appropriate difficulty adjustments to maintain learning motivation. Therefore, there is a need for a system that maximizes children's learning efficiency by providing learning problems while on the move, adjusting the difficulty level, and providing feedback in real time.

[0863] 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.

[0864] In this invention, the server includes means for generating study questions corresponding to the current level of difficulty, means for displaying the study questions, means for displaying the study questions on a mobile object, means for accepting a user's answer to the study questions by voice or touch operation, means for determining whether the user's answer is correct or incorrect, means for adjusting the difficulty of the study questions based on the determination result, and means for displaying feedback regarding the determination result and the difficulty level adjustment to the user. This enables learning activities even while on the move, and by providing effective feedback and difficulty level adjustment in real time, children's learning efficiency can be improved.

[0865] "Study Problems" are educational tasks or questions that children must complete and are automatically generated by the server.

[0866] A "user answer" is an answer provided by a user to a study question, and is input through voice or touch operation.

[0867] "Current difficulty" refers to the difficulty level of the study questions that is set based on the user's level of understanding and progress.

[0868] "Mobile object" refers to something in motion, such as an autonomous vehicle, and specifically refers to the in-car environment, including the infotainment system or tablet.

[0869] "Display means" refers to a device or function for visually or audibly presenting information such as study questions and feedback to the user.

[0870] "Voice input" refers to an input method in which a user provides answers to study questions using voice.

[0871] "Touch operation" refers to the user entering answers using the touchscreen of a tablet or infotainment system.

[0872] The "judging means" is a function that evaluates whether the user's answer is correct or incorrect and adjusts the difficulty level based on the result.

[0873] "Feedback" provides the user with information indicating the evaluation of their answer and next steps.

[0874] The present invention provides a system for automatically generating learning questions for children and adjusting the difficulty of the questions based on the user's answers. This system can be installed in an autonomous vehicle, enabling learning activities while traveling in the vehicle. A specific embodiment of the system is described below.

[0875] System Structure

[0876] This system mainly consists of a server and a terminal. The server generates learning questions, evaluates the user's answers, and provides the function to adjust the difficulty level. The terminal, especially the infotainment system or tablet in the autonomous vehicle, displays the learning questions to the user, collects the user's answers, and displays the feedback received from the server.

[0877] Server Operation

[0878] The server first generates learning questions using a question generation class. The generated learning questions are sent to the terminal and displayed to the user. The user's answers are then sent to the server via the terminal. The server compares the received answers with the correct answers, increasing the difficulty if they are correct and decreasing the difficulty if they are incorrect. This provides an appropriate learning environment according to the user's level of understanding and progress.

[0879] Device behavior

[0880] The device is an infotainment system or tablet installed in the autonomous vehicle, which displays the learning questions and accepts the user's answers. The user inputs their answers through touch or voice input. The answers are sent to a server, and the results and feedback on difficulty adjustments are displayed on the device. This allows users to continue learning without interruption even while on the move.

[0881] User Actions

[0882] The user, or child, works on learning problems while in the car. For example, when a math problem such as "15 + 7" appears, the user inputs the answer "22" using touch or voice input. The device sends the answer to the server, which evaluates the result and returns feedback. The user then works on the next problem based on the result.

[0883] Specific examples

[0884] In the first learning cycle, the problem generated by the server is "15 + 7." If the user answers "22," the server determines this is an incorrect answer and lowers the difficulty of the next problem. The device then displays feedback to the user saying, "This is incorrect. Proceed to the next problem."

[0885] In the second learning cycle, the server generates a question with a lower level of difficulty, such as "8 + 4." If the user answers "12," the server recognizes this as the correct answer and increases the difficulty of the next question. The device displays feedback saying, "Correct! The difficulty will increase."

[0886] Prompt Sentence Examples

[0887] Examples of prompts for generative AI models include:

[0888] "Current difficulty level is 2. Generate math problems for children."

[0889] "Please create a Japanese language question that corresponds to level 3."

[0890] This allows learning activities to be carried out while on the move, and by providing effective feedback and difficulty adjustments in real time, children's learning efficiency can be improved.

[0891] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0892] Step 1:

[0893] The server generates the training questions (input: current difficulty level, output: generated training questions)

[0894] The server generates learning problems based on the current level of difficulty. For example, it uses a generative AI model to input a prompt such as "Please generate a math problem of level 1" and outputs appropriate learning problems based on that. The server stores the generated learning problems and prepares them to be sent to the device.

[0895] Step 2:

[0896] The device displays the study questions (input: study questions received from the server, output: displayed study questions)

[0897] The device displays the learning questions received from the server to the user. During this process, the question is displayed on the screen or the user is informed of the question by voice output. For example, the question "15 + 7" is displayed on the screen.

[0898] Step 3:

[0899] User enters answer (input: study question, output: user answer)

[0900] The user inputs answers to the displayed study questions. The input method can be touch operation or voice input. For example, the user can provide the answer "22" by voice input.

[0901] Step 4:

[0902] The device receives the user's answer and sends it to the server (input: user's answer, output: sending the answer to the server)

[0903] The terminal receives the answer entered by the user and sends it to the server. The data includes the question ID along with the answer content.

[0904] Step 5:

[0905] The server judges the answer and adjusts the difficulty level (input: user's answer, output: judgement result and new difficulty level)

[0906] The server compares the received user answer with the correct answer data, and based on the results, increases the difficulty level if the answer is correct, or decreases it if the answer is incorrect. For example, if the answer "22" is incorrect, the difficulty level of the next question is lowered.

[0907] Step 6:

[0908] The server generates feedback and sends it to the device (input: judgment result and new difficulty level, output: feedback message).

[0909] The server generates a feedback message for the user based on the result of the judgment and the new difficulty level. For example, it generates a message such as "This is a mistake. Proceed to the next question." and sends it to the terminal.

[0910] Step 7:

[0911] The device displays the feedback (input: feedback message received from the server, output: displayed feedback)

[0912] The terminal displays the feedback message received from the server to the user. Feedback is provided by visual display or audio, allowing the user to confirm the results of their answers.

[0913] Step 8:

[0914] The device requests a new learning problem (input: new difficulty level, output: next learning problem)

[0915] After providing feedback to the server, the device requests the server to generate new learning questions corresponding to the new level of difficulty for the next learning cycle, thereby maintaining continuity of learning.

[0916] 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.

[0917] The present invention provides a learning support system for children that incorporates an emotion engine that recognizes the emotions of a user. Specific embodiments of the system will be described below.

[0918] This system mainly consists of a server, a terminal, and an emotion engine. The server generates learning questions, evaluates users' answers, and adjusts the difficulty level. The terminal displays learning questions to users, collects their answers, and displays feedback received from the server. The emotion engine recognizes users' emotions and adjusts the difficulty and type of learning questions based on those emotions.

[0919] Server Operation

[0920] The server first generates study questions using a problem generation class. The problem generation class stores the current difficulty level and creates appropriate study questions based on that level. For example, for math problems, a low level generates addition problems using random numbers in the range of 1 to 10, while a high level generates addition problems in the range of 1 to 20. For Japanese language problems, reading and writing tasks are presented according to the level of difficulty.

[0921] The generated learning questions are sent to the device and displayed to the user. The user's answers are then sent to the server via the device. The server compares the received answers with the correct answers, increasing the difficulty if they are correct and decreasing the difficulty if they are incorrect. Furthermore, the difficulty and type of learning questions are adjusted based on the user's emotions recognized by the emotion engine.

[0922] Device behavior

[0923] The device displays the study questions received from the server to the user. The question text is displayed on the screen so that the user can see the question content. When the user enters the answer to the study question, the answer is sent to the server. The device receives feedback from the server regarding the assessment result and difficulty level adjustment, and displays this to the user. For example, if the user answers correctly, it displays "You got it right! The difficulty level will be increased," and if the answer is incorrect, it displays "You got it wrong. The difficulty level will be lowered."

[0924] Emotion Engine Operation

[0925] The emotion engine measures data such as the user's facial expressions, voice, and input speed to recognize the user's emotions. For example, if it recognizes that the user is feeling stressed, it temporarily lowers the difficulty of the study questions to reduce the user's burden. On the other hand, if the user is feeling relaxed, it adjusts the difficulty level appropriately to maintain or increase it.

[0926] User Actions

[0927] The user answers the learning problems displayed on the device. For example, if the math problem is "5 + 3," the user enters "8" as the answer. The device then sends the answer to the server, which returns a judgment and feedback. The user can then move on to the next problem based on the result. The emotion engine also monitors the user's emotional state and adjusts the learning experience more appropriately, allowing the user to continue studying without stress.

[0928] Specific examples

[0929] In the first learning cycle, the problem generated by the server is "5 + 3." If the user answers "8," the server determines this is the correct answer and increases the difficulty of the next problem. The device then displays feedback to the user saying, "You got it right! The difficulty will increase." Also, if the emotion engine recognizes a relaxed state from the user's facial expressions and voice, the difficulty of the next problem will increase appropriately.

[0930] In the second learning cycle, the server generates a more difficult question, for example, "15 + 7." If the user answers "20," the server determines this is an incorrect answer and lowers the difficulty of the next question. Also, if the emotion engine recognizes that the user is feeling stressed, it appropriately lowers the difficulty of the next question to reduce the user's burden. The device displays feedback saying, "That's a mistake. We'll lower the difficulty."

[0931] In this way, the system can provide an appropriate learning environment by adjusting the difficulty and type of questions in real time based on the user's answers and emotional state. This continuous feedback and adjustment effectively supports the user's academic improvement.

[0932] Furthermore, this system can handle multiple subjects, such as math and Japanese. By automatically generating appropriate study questions according to difficulty level, it can help users study each subject in a balanced way.

[0933] As described above, the present invention is extremely effective as a learning support system for children, and can maximize the learning effect.

[0934] The processing flow will be explained below.

[0935] Step 1:

[0936] The server obtains the current difficulty level using an instance of the problem generator class. Specifically, it checks the initial difficulty level by referencing the property self.problem_generator.difficulty .

[0937] Step 2:

[0938] The server generates learning questions based on the acquired difficulty level. For example, if the difficulty level is 1, it generates addition questions using random numbers in the range of 1 to 10. The generated questions are stored in string format.

[0939] Step 3:

[0940] The server sends the generated learning questions to the device. Specifically, it transfers data including the question content (e.g., "5 + 3") to the device.

[0941] Step 4:

[0942] The terminal displays the transmitted study questions to the user, and displays the question text on the screen so that the user can visually recognize the question content.

[0943] Step 5:

[0944] The user answers the displayed study question. For example, the user answers "8" to the question "5 + 3."

[0945] Step 6:

[0946] The terminal collects the user's answers. Specifically, it stores the answers entered by the user as numerical values ​​and prepares to send the answer data to the server.

[0947] Step 7:

[0948] The terminal sends the collected answers of the user to the server, and the user's input data is passed to the server.

[0949] Step 8:

[0950] The server determines whether the received user answer is correct or incorrect. The server evaluates the question text and compares the correct answer with the user's answer. For example, the correct answer to "5 + 3" is "8," and if the user's answer is "8," it is determined to be correct.

[0951] Step 9:

[0952] The server adjusts the difficulty of the study questions based on the answers. If the user answers correctly, the difficulty level is increased, and if the user answers incorrectly, the difficulty level is decreased. For example, the difficulty level may be increased from 1 to 2, or decreased from 2 to 1.

[0953] Step 10:

[0954] The emotion engine analyzes the user's facial expressions, voice, typing speed, etc. to recognize the user's emotions, thereby determining whether the user is stressed or relaxed.

[0955] Step 11:

[0956] An emotion engine adjusts the difficulty or type of study questions based on the perceived user emotion, for example, if the user is stressed, the next study question will be less difficult.

[0957] Step 12:

[0958] The server generates feedback regarding the result of the judgment and the difficulty adjustment, and sends it to the device. It creates a feedback message (e.g., "You got it right! The difficulty will be increased." or "You got it wrong. The difficulty will be decreased.").

[0959] Step 13:

[0960] The terminal displays the feedback received from the server to the user, who can obtain information about his / her answer results and future study strategies.

[0961] Step 14:

[0962] The user checks the displayed feedback and moves on to the next problem. For example, if the emotion engine determines that the user is feeling stressed, the difficulty level of the next problem is set low. This cycle is repeated to maximize the user's learning effect.

[0963] Example 2

[0964] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0965] Conventional learning support systems adjust the difficulty of study questions based on the user's answers, but lack a mechanism for adjusting the learning experience based on the user's emotional state. As a result, if the user is stressed or overly relaxed, the difficulty level may not be adjusted appropriately, potentially reducing the learning effect. The present invention aims to recognize the user's emotions and adjust the difficulty and type of study questions based on that, allowing the user to continue learning in an optimal state.

[0966] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for generating study questions corresponding to the current level of difficulty, means for displaying the study questions, means for accepting a user's answers to the study questions, means for determining whether the user's answers are correct or incorrect, means for adjusting the difficulty of the study questions based on the determination result, means for collecting emotional data and recognizing the user's emotions, means for adjusting the difficulty or type of the study questions based on the emotion recognition, and means for displaying feedback regarding the determination result and the difficulty adjustment to the user. This makes it possible to comprehensively determine the user's answering status and emotional state and provide an appropriate learning environment in real time.

[0967] The following are definitions of important terms contained in the claims.

[0968] A "study question" is a math or language related challenge provided for the user to answer.

[0969] "Difficulty" is an indicator of the complexity of the study questions and the difficulty of solving them.

[0970] A "server" is a computer system that generates study questions, judges user answers, adjusts difficulty, and provides feedback.

[0971] A "terminal" is a device that displays study questions to a user, collects the user's answers, and displays feedback from the server.

[0972] "Emotion data" is information collected from the user's facial expression, voice, input speed, etc., and is data that indicates the user's emotional state.

[0973] An "emotion engine" is a software or hardware system for analyzing emotion data and recognizing a user's emotion.

[0974] "Feedback" is information that provides the user with the evaluation results of the user's answers, as well as study instructions and comments based on the evaluation results.

[0975] "Determination" is the process of determining whether the answer given by the user is correct or incorrect.

[0976] "Tuning" is the process of changing the difficulty and type of study questions based on the user's answers and emotional state.

[0977] "Display" refers to the act of visually presenting information on the screen of a terminal, such as showing study questions and feedback to the user.

[0978] The present invention is a learning support system for children that combines an emotion engine that recognizes the user's emotions. This system is mainly composed of a server, a terminal, and an emotion engine. Specific embodiments of the system are described below.

[0979] System Configuration

[0980] The system includes the following means:

[0981] 1. Server

[0982] 2. Terminal

[0983] 3. Emotion Engine

[0984] Server Operation

[0985] The server first generates learning problems using a problem generation class. The problem generation class stores the current difficulty level and creates appropriate learning problems based on that level. For example, in arithmetic, a low level of difficulty generates a simple addition problem like "5 + 3," while a high level of difficulty generates a more complex addition problem like "15 + 7." The generated learning problems are then sent to the device and displayed to the user. After the user's answer is sent to the server via the device, the server compares the answer with the correct answer and makes a judgment. If the answer is correct, the difficulty level is increased; if the answer is incorrect, the difficulty level is decreased. The difficulty and type of learning problems are further adjusted based on the user's emotional data recognized by the emotion engine.

[0986] Examples:

[0987] Example prompt: "The server generates a '5 + 3' problem and sends it to the terminal, then waits for the user's answer. After the user enters the answer, write a program that judges the answer and returns appropriate feedback. Also, add a function to adjust the difficulty of the problem using the user's emotional data."

[0988] Device behavior

[0989] The device displays the learning questions received from the server to the user. For example, the problem "5 + 3" is displayed on the screen, and the user inputs the answer to the problem. This answer is sent to the server, and the user checks the feedback from the server. The feedback from the server is displayed to the user as a message such as "That's correct! The difficulty will increase" or "That's incorrect. The difficulty will be lowered."

[0990] Emotion Engine Operation

[0991] The emotion engine uses emotion sensors to measure data such as the user's facial expressions, voice, and input speed. It then analyzes the collected data using an AI model to recognize the user's emotions. For example, it can determine whether the user is feeling stressed or relaxed based on data from the camera, microphone, and keyboard input speed. The recognized emotion data is sent to the server, which uses it as reference information to adjust the difficulty and type of the next learning problem.

[0992] User Actions

[0993] The user answers the study questions displayed on the device. For example, they enter "8" for the "5 + 3" question. After answering, the device sends the answer to the server and receives and displays feedback. This allows the user to prepare for the next question. The user can also see that their learning progress is optimized in real time according to the emotion recognition by the emotion engine.

[0994] This system comprehensively assesses the user's response status and emotional state, and adjusts the difficulty and type of study questions appropriately to provide an effective learning environment, which is expected to improve the user's academic ability.

[0995] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0996] The processing flow of the program of this system will be explained in detail below, divided into processing steps.

[0997] Step 1: Generate training questions

[0998] The server uses the problem generation class to generate problems based on the current difficulty level. For example, if the current difficulty level is low, the server generates a simple addition problem such as "5 + 3." The input for this problem generation is the current difficulty level data, and the output is the generated problem.

[0999] Step 2: Submit and view the exercises

[1000] The server sends the generated study questions to the terminal. The input is the generated study question data, and the output is a notification that the sending process is complete. The terminal then displays the received study questions on the screen. For example, a "5 + 3" problem is displayed on the screen. The input here is the study question data received from the server, and the output is the problem displayed on the screen in a format that the user can see.

[1001] Step 3: User answers

[1002] The user inputs answers to the study questions displayed on the terminal. For example, the user inputs "8" using the keyboard. The input is the data the user answered, and the output is the answer data stored inside the terminal.

[1003] Step 4: Submitting user answers

[1004] The terminal sends the user's answer to the server. The input is the user's answer data, and the output is a transmission completion notification to the server.

[1005] Step 5: Determine the answer

[1006] The server compares the received user answer with the correct answer and makes a judgment. For example, if the received answer is "8" and the question is the addition "5 + 3", it judges whether the answer is correct. The input is the user's answer data and the correct answer data, and the output is the judgment result data.

[1007] Step 6: Collect and recognize emotion data

[1008] The emotion engine collects data such as the user's facial expressions, voice, and input speed, and uses this data to recognize the user's emotions. For example, it acquires the user's facial expression data through a camera and analyzes it with an AI model to determine whether the user is relaxed or stressed. The input is emotion data, and the output is the user's emotion recognition result data.

[1009] Step 7: Adjusting the difficulty

[1010] The server adjusts the difficulty of the learning questions based on the answer judgment results and emotion recognition results. For example, if the user answers correctly and the emotion engine recognizes that the user is relaxed, the server increases the difficulty of the next question. The input is the judgment result data and emotion recognition result data, and the output is the adjusted difficulty data.

[1011] Step 8: Submit and view feedback

[1012] The server sends the judgment result and the difficulty adjustment result to the terminal, and the terminal displays them to the user. For example, a feedback message such as "Correct! The difficulty will increase." The input is the feedback data from the server, and the output is the feedback message displayed to the user.

[1013] Through the above specific processing steps, the system can comprehensively judge the user's answering situation and emotional state, and provide an appropriate learning environment in real time.

[1014] (Application example 2)

[1015] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1016] Conventional learning support systems and work support systems set the difficulty level unilaterally without considering the user's emotional state, which often led to stress and fatigue for the user. Furthermore, because the difficulty level was set uniformly, the user's learning effect and work efficiency were often reduced. In this modern age, where flexible responses according to the user's state are required, systems incorporating emotion recognition are becoming increasingly important.

[1017] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for generating study questions corresponding to the current level of difficulty, means for displaying study questions, means for accepting a user's answers to the study questions, means for determining whether the user's answers are correct or incorrect, means for adjusting the difficulty of the study questions based on the determination result, means for displaying feedback to the user regarding the determination result and the difficulty adjustment, means for recognizing the user's emotions, means for adjusting the difficulty and type of study questions based on the emotions, and means for feeding back the emotion recognition results to the work environment and adjusting the work difficulty appropriately. This provides an appropriate learning environment and work environment according to the user's emotional state, allowing the user to study and work efficiently without stress.

[1018] A "system" is a collection of multiple elements, each of which works together to achieve a specific function.

[1019] The "means for generating study questions" is a component within the system that has the function of creating questions that correspond to the user's study content.

[1020] The "means for displaying study questions" is a component that has the function of visually presenting study questions to the user.

[1021] The "means for accepting user answers" is a component that has the function of allowing the system to receive answers entered by the user to the study questions.

[1022] The "means for determining whether the answer is correct or incorrect" is a component that has the function of determining whether the user's answer is correct or not.

[1023] The "means for adjusting difficulty" is a component that has the function of automatically changing the difficulty of the next study question to be presented based on the user's answer.

[1024] The "means for displaying feedback to the user" is a component that has the function of conveying information about the answer result and difficulty level adjustment to the user.

[1025] The "means for recognizing user's emotions" is a component having a function for analyzing the user's emotional state (for example, stress, relaxation, motivation, etc.).

[1026] The "means for adjusting the difficulty and type of study questions based on emotions" is a component that has the function of appropriately changing the difficulty and type of study questions for the user based on the results of emotion recognition.

[1027] The "means for feeding back emotion recognition results to the work environment and adjusting the difficulty of the work appropriately" is a component that has the function of adjusting the work content and difficulty based on the user's emotion recognition results, thereby reducing the burden on the user.

[1028] The present invention is a learning and work support system that combines an emotion engine that recognizes the user's emotions. This system is composed of a server, a terminal, and an emotion engine.

[1029] The server first generates study questions using a problem generation class. The problem generation class stores the current difficulty level and creates appropriate study questions based on that level. For example, for arithmetic questions, a basic addition problem is generated if the difficulty level is low, and a more complex addition problem is generated if the difficulty level is high. For Japanese language questions, reading and writing tasks are presented according to the respective level of difficulty. The generated study questions are sent to the device and displayed to the user. The user's answers are then sent to the server via the device. The server compares the received answers with the correct answers and increases the difficulty level if they are correct, or decreases the difficulty level if they are incorrect. The server also adjusts the difficulty level and type of study questions based on the user's emotions recognized by the emotion engine.

[1030] The device displays the study questions received from the server to the user. The question text is displayed on the screen so that the user can see the question content. When the user enters the answer to the study question, the answer is sent to the server. The device receives feedback from the server regarding the assessment result and difficulty level adjustment, and displays this to the user. For example, if the user answers correctly, it displays "You got it right! The difficulty level will be increased," and if the answer is incorrect, it displays "You got it wrong. The difficulty level will be lowered."

[1031] The emotion engine measures data such as the user's facial expressions, voice, and input speed to recognize the user's emotions. For example, if it recognizes that the user is feeling stressed, it temporarily lowers the difficulty of the study questions to reduce the user's burden. On the other hand, if the user is feeling relaxed, it adjusts the difficulty level appropriately to maintain or increase it.

[1032] Furthermore, this invention can also be applied to assisting factory robots in their work. This system involves installing an emotion engine in a factory robot, recognizing the emotional state of a worker in real time, and adjusting the difficulty of the work based on the results. For example, if the emotion engine recognizes that a worker is under stress, it can assign the worker an easy task or suggest a temporary break. If the emotion engine recognizes that the worker is highly motivated, it can assign a difficult task.

[1033] To illustrate, consider the following scenario:

[1034] Example 1:

[1035] If the emotion engine recognizes that Worker A is under stress, it assigns him / her an easy task (e.g., sorting parts), thereby reducing the workload.

[1036] Example 2:

[1037] If Worker B is perceived as highly motivated, he or she will be assigned a more difficult task (e.g., assembling a complex machine), which will improve work efficiency.

[1038] Example prompt sentence:

[1039] "Recognize the facial expressions of the workers from the images and use an emotion engine to estimate their emotions. Assuming the emotion is stress, relaxation, or motivation, suggest an appropriate level of task difficulty depending on the emotion."

[1040] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1041] Step 1:

[1042] The server generates learning questions according to the current level of difficulty using a question generation class. At this time, the current level of difficulty is given as input, and learning content according to that level of difficulty (for example, addition problems in arithmetic or reading and writing problems in Japanese) is output.

[1043] Step 2:

[1044] The server sends the generated training questions to the terminal, where the input is the generated training questions and the output is the training question data sent to the terminal.

[1045] Step 3:

[1046] The terminal displays the exercises received from the server to the user, with the input being the exercises received from the server and the output being the text of the exercises displayed to the user.

[1047] Step 4:

[1048] The user inputs answers to the displayed study questions. The input is the study question and the user's answer, and the output is the user's answer data input to the terminal.

[1049] Step 5:

[1050] The terminal sends the user's answer to the server. The input is the user's answer data, and the output is the answer data sent to the server.

[1051] Step 6:

[1052] The server determines whether the user's answer is correct or incorrect. The input is the user's answer and the correct answer data, and the output is the judgment result (correct or incorrect).

[1053] Step 7:

[1054] The server adjusts the difficulty of the next study question based on the judgment result. The input is the judgment result, and the output is the difficulty data for the next study question.

[1055] Step 8:

[1056] The server generates feedback regarding the judgment result and the difficulty level adjustment and sends it to the terminal. The input is the judgment result and the adjusted difficulty level, and the output is a feedback message.

[1057] Step 9:

[1058] The terminal displays the feedback received from the server to the user. The input is the feedback message and the output is the feedback text displayed to the user.

[1059] Step 10:

[1060] The emotion engine measures and analyzes data such as the user's facial expressions, voice, and input speed to recognize the user's emotions. The input is the user's raw data (facial expressions, voice data, input speed data), and the output is the user's emotional state (stress, relaxation, motivation, etc.).

[1061] Step 11:

[1062] The server adjusts the difficulty and type of training questions based on the emotion recognition results. The input is the emotion recognition results, and the output is the adjusted difficulty and type of questions.

[1063] Step 12:

[1064] The server feeds back the emotion recognition results to the work environment and adjusts the task difficulty. The input is the emotion recognition results and the current task content, and the output is the adjusted task.

[1065] Step 13:

[1066] The terminal displays the adjusted work task to the user or the work robot or issues instructions to the user or the work robot. The input is the adjusted work task data, and the output is instructions to the user or the work robot.

[1067] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1068] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1069] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1070] [Fourth embodiment]

[1071] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1072] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1073] 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).

[1074] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1075] 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.

[1076] 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).

[1077] 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.

[1078] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1079] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1080] 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.

[1081] 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.

[1082] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1083] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1084] The present invention is a system for automatically generating learning questions for children and adjusting the difficulty of the questions based on the answers of a user. Specific embodiments of the system are described below.

[1085] This system mainly consists of a server and a terminal. The server generates study questions, evaluates users' answers, and adjusts the difficulty level. The terminal displays study questions to users, collects their answers, and displays feedback received from the server.

[1086] Server Operation

[1087] The server first generates study questions using a problem generation class. The problem generation class stores the current difficulty level and creates appropriate study questions based on that level. For example, in arithmetic, a low level of difficulty generates addition problems within the range of 1 to 10, while a high level of difficulty generates addition problems within the range of 1 to 20. In Japanese language questions, reading and writing tasks are presented according to the level of difficulty.

[1088] The generated study questions are sent to the device and displayed to the user. The user's answers are then sent to the server via the device. The server compares the received answers with the correct answers, increasing the difficulty if they are correct, and decreasing the difficulty if they are incorrect. This provides an appropriate learning environment according to the user's level of understanding and progress.

[1089] Device behavior

[1090] The device displays the learning questions received from the server to the user. When the user enters an answer to a question, the answer is sent to the server. The server then receives feedback on the assessment result and difficulty level adjustment, which is then displayed to the user. For example, if the user answers correctly, the device displays "You got it right! The difficulty level will be increased," and if the answer is incorrect, the device displays "You got it wrong. The difficulty level will be lowered."

[1091] User Actions

[1092] The user answers the learning problems displayed on the device. For example, if the math problem is "5 + 3," the user enters "8" as the answer. The device then sends this answer to the server, which returns the result. The user can then move on to the next problem based on the result.

[1093] Specific examples

[1094] In the first learning cycle, the problem generated by the server is "5 + 3." If the user answers "8," the server determines this is the correct answer and increases the difficulty of the next problem. The device then displays feedback to the user saying, "You got it right! The difficulty will increase."

[1095] In the second learning cycle, the server generates a more difficult question, for example, "15 + 7." If the user answers "20," the server determines this is an incorrect answer and lowers the difficulty of the next question. The device displays feedback saying, "That's wrong. We'll lower the difficulty."

[1096] In this way, the system can adjust the difficulty level in real time based on the user's answers, providing an appropriate learning environment. This continuous feedback and adjustment effectively supports the user's academic improvement.

[1097] This system can also handle Japanese language learning problems, not just math problems. By automatically generating appropriate learning problems according to difficulty level, it helps users to study each subject in a balanced way.

[1098] As described above, the present invention is extremely effective as a learning support system for children, and can maximize the learning effect.

[1099] The processing flow will be explained below.

[1100] Step 1:

[1101] The server obtains the current difficulty level using an instance of the problem generator class. Specifically, it checks the initial difficulty level by referencing the property self.problem_generator.difficulty .

[1102] Step 2:

[1103] The server generates practice questions based on the acquired difficulty level. For example, if the difficulty level is 1, it generates addition problems using random numbers in the range of 1 to 10. The problems are stored in string format.

[1104] Step 3:

[1105] The server sends the generated learning questions to the device. Specifically, data including the question content (e.g., "5 + 3") is transferred to the device.

[1106] Step 4:

[1107] The terminal displays the transmitted study questions to the user, and displays the question text on the screen so that the user can visually recognize the question content.

[1108] Step 5:

[1109] The user answers the displayed study question. For example, the user answers "8" to the question "5 + 3."

[1110] Step 6:

[1111] The terminal collects the user's answers. Specifically, it stores the answers entered by the user as numerical values ​​and prepares to send them to the server.

[1112] Step 7:

[1113] The terminal sends the collected answers of the user to the server, and the user's input data is passed to the server.

[1114] Step 8:

[1115] The server determines whether the received user answer is correct or incorrect by evaluating the question text and comparing the correct answer with the user answer.

[1116] Step 9:

[1117] The server adjusts the difficulty of the study questions based on the answers, increasing the difficulty if the user answers correctly and decreasing it if the user answers incorrectly.

[1118] Step 10:

[1119] The server generates feedback regarding the judgment result and difficulty adjustment, and sends it to the terminal. It creates a feedback message (for example, "You got it right! The difficulty level will increase.").

[1120] Step 11:

[1121] The terminal displays the feedback received from the server to the user, who can obtain information about his / her answer results and future study strategies.

[1122] Step 12:

[1123] The user checks the displayed feedback and moves on to the next problem, and this cycle is repeated to maximize the user's learning effect.

[1124] Example 1

[1125] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1126] Conventional learning systems for children often do not adjust the difficulty of questions in real time according to the individual user's learning progress, resulting in a decrease in learning efficiency. Furthermore, many systems only support a single subject, making it difficult to provide balanced, comprehensive learning support. Given these points, there is a demand for a learning support system that can appropriately adjust the difficulty level based on the user's answers and can support multiple subjects.

[1127] 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.

[1128] In this invention, the server includes means for generating study questions for children using a study question generation program, means for transmitting the study questions to a terminal and displaying them, means for accepting a user's answer to the study questions, means for transmitting the user's answer to the server, means for determining whether the answer is correct or incorrect and adjusting the difficulty of the study questions based on the result, and means for generating and displaying feedback on the determination result and the difficulty adjustment to the user. This allows the difficulty of the questions to be adjusted in real time based on the user's answer, enabling balanced learning support for multiple subjects.

[1129] A "program for generating study questions" is software that automatically creates study questions for subjects such as arithmetic and Japanese language based on the user's study data and level of difficulty.

[1130] A "server" is a computer system that performs processes such as generating study questions, receiving and judging user answers, adjusting difficulty, and generating feedback.

[1131] A "terminal" is a device operated by a user, and is a device for displaying study questions, inputting user answers, and displaying feedback.

[1132] "User's answer" refers to the answer data that the user inputs to the study question.

[1133] The "means for transmitting the answer to the server" is a communication means for sending the user's answer from the terminal to the server.

[1134] The "means for determining" refers to an algorithm and program that the server uses to check the user's answer against the correct answer and determine whether it is correct or incorrect.

[1135] The "means for adjusting the difficulty level" refers to an algorithm and program for appropriately changing the difficulty level of the next study question based on the evaluation result of the user's answer.

[1136] The "means for generating feedback" is a program for creating a message to be displayed to the user based on the user's answer results and information regarding difficulty level adjustment.

[1137] The "means for transmitting study questions to the terminal" refers to a communication means for transmitting the generated study questions from the server to the terminal.

[1138] The "means for displaying study questions" refers to software and hardware for displaying study questions received by the terminal on a user interface.

[1139] The present invention is a system that automatically generates learning questions for children and adjusts the difficulty of the questions based on the user's answers. This system is mainly composed of a server and a terminal.

[1140] Server Operation

[1141] The server generates study questions using a "program for generating study questions" that uses a "generative AI model." This problem generation program automatically creates appropriate study questions, taking into account the current level of difficulty. The server sends the generated questions in JSON format to the device and waits for the user to enter their answers. The user's answers are then sent to the server via the device, and the server compares them with the correct answers. Based on the evaluation results, the server adjusts the difficulty of the next question. It then generates feedback regarding the difficulty adjustment and the evaluation results and sends this to the device. The server is responsible for generating questions, evaluating answers, adjusting the difficulty, and generating feedback.

[1142] Device behavior

[1143] The device displays the learning questions received from the server on a user interface. A form is displayed for the user to enter their answers to the questions. When the user enters their answers, the device converts the data into JSON format and sends it to the server. When feedback is received from the server, the device analyzes it and displays it on the user interface. For example, if the user answers correctly, it displays "You're correct! The difficulty level will increase," and if the answer is incorrect, it displays "You're wrong. The difficulty level will be lowered." The device is responsible for displaying learning questions, sending answers, and displaying feedback.

[1144] User Actions

[1145] The user answers the study questions displayed on the device. For example, if the math question displayed is "5 + 3," the user enters "8" as the answer. The device then sends this answer to the server, which returns a judgment result. The user can then move on to the next question based on the result. The user enters the answer to the study question and checks the feedback from the server.

[1146] Specific examples

[1147] In the first learning cycle, the problem generated by the server is "5 + 3." If the user answers "8," the server determines this is the correct answer and increases the difficulty of the next problem. The device then displays feedback to the user saying, "You got it right! The difficulty will increase."

[1148] In the second learning cycle, the server generates a more difficult question, for example, "15 + 7." If the user answers "20," the server determines this is an incorrect answer and lowers the difficulty of the next question. The device displays feedback saying, "That's wrong. We'll lower the difficulty."

[1149] Through this series of processes, the system can provide appropriate questions according to the user's learning progress, thereby providing efficient learning support.

[1150] Example prompt

[1151] Here are some example prompts to enter into a generative AI model:

[1152] "The server of this system first generates learning questions using a question generation class. Depending on the current level of difficulty, arithmetic questions or Japanese language questions are selected. The generated questions are then sent to the terminal, and when the user enters the answer, the answer is sent to the server. The server evaluates the answer and increases the difficulty if it is correct, or decreases it if it is incorrect. Please explain this process with a concrete example."

[1153] From the above explanation, the detailed operation and effects of the present invention can be understood.

[1154] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1155] Program processing flow

[1156] Step 1:

[1157] Start the program to generate questions

[1158] The server launches a "program for generating learning questions" using the "generative AI model."

[1159] Input: Current difficulty information, user learning history data.

[1160] Specific operation: The server obtains the current difficulty information and the user's learning history from the internal database and inputs them into the generative AI model.

[1161] Output: A new training problem is generated.

[1162] Step 2:

[1163] Send and display study questions on your device

[1164] The server converts the generated learning questions into JSON format and sends them to the terminal.

[1165] Input: The newly generated training problem.

[1166] Specific operation: The server formats the training problem as a JSON object and sends it to the device using a communication protocol (e.g., HTTP, WebSocket).

[1167] Output: The training problem sent to the device.

[1168] Step 3:

[1169] Displaying study questions to users

[1170] The terminal analyzes the received study questions and displays them on the user interface.

[1171] Input: Training question data from the server (JSON format).

[1172] Specific operation: The device parses the JSON data and displays the learning questions on the user's screen.

[1173] Output: The training question displayed in the user interface.

[1174] Step 4:

[1175] Enter the user's answer

[1176] The user inputs answers to the study questions displayed on the terminal.

[1177] Input: The study question displayed in the user interface.

[1178] Specific operation: The user enters the answer into the input form and clicks the submit button.

[1179] Output: The answer entered by the user.

[1180] Step 5:

[1181] Send the user's answer to the server

[1182] The device converts the user's answer into JSON format and sends it to the server.

[1183] Input: The answer entered by the user.

[1184] Specific operation: The device formats the answer data as a JSON object and sends it to the server using a communication protocol.

[1185] Output: The answer data sent to the server.

[1186] Step 6:

[1187] Judge the answer and adjust the difficulty level

[1188] The server receives the user's answer and determines whether it is correct or incorrect.

[1189] Input: User answer data, correct answer data for the learning questions.

[1190] Specific operation: The server compares the answer data with the correct answers to the learning questions and determines whether they are correct or not. Based on the result of the judgment, it determines the difficulty level of the next question.

[1191] Output: Judgment result and difficulty information for the next question.

[1192] Step 7:

[1193] Generate a feedback message

[1194] The server generates a feedback message for the user based on the determination result.

[1195] Input: Answer judgment result, difficulty information.

[1196] Specific operation: The server generates a feedback message in text format based on the judgment result and difficulty information.

[1197] Output: The generated feedback message.

[1198] Step 8:

[1199] Send and display feedback on the device

[1200] The server sends the generated feedback message to the terminal.

[1201] Input: Feedback message.

[1202] Specific operation: The server formats the feedback message as a JSON object and sends it to the device using a communication protocol.

[1203] Output: Feedback sent to the device.

[1204] Step 9:

[1205] Displaying feedback to the user

[1206] The terminal displays the received feedback message on a user interface.

[1207] Input: Feedback message from the server (JSON format).

[1208] Specific behavior: The device parses the JSON data and displays a feedback message on the user's screen, for example, "Correct! The difficulty level will increase."

[1209] Output: The feedback message displayed in the user interface.

[1210] (Application example 1)

[1211] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1212] Currently, most learning support systems for children are used at home or at school, making it difficult to make effective use of travel time. Furthermore, conventional systems only allow for the display of learning problems and the input of answers in limited environments, making it impossible to provide effective learning support in mobile devices such as self-driving vehicles. Furthermore, it is important to provide real-time feedback and appropriate difficulty adjustments to maintain learning motivation. Therefore, there is a need for a system that maximizes children's learning efficiency by providing learning problems while on the move, adjusting the difficulty level, and providing feedback in real time.

[1213] 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.

[1214] In this invention, the server includes means for generating study questions corresponding to the current level of difficulty, means for displaying the study questions, means for displaying the study questions on a mobile object, means for accepting a user's answer to the study questions by voice or touch operation, means for determining whether the user's answer is correct or incorrect, means for adjusting the difficulty of the study questions based on the determination result, and means for displaying feedback regarding the determination result and the difficulty level adjustment to the user. This enables learning activities even while on the move, and by providing effective feedback and difficulty level adjustment in real time, children's learning efficiency can be improved.

[1215] "Study Problems" are educational tasks or questions that children must complete and are automatically generated by the server.

[1216] A "user answer" is an answer provided by a user to a study question, and is input through voice or touch operation.

[1217] "Current difficulty" refers to the difficulty level of the study questions that is set based on the user's level of understanding and progress.

[1218] "Mobile object" refers to something in motion, such as an autonomous vehicle, and specifically refers to the in-car environment, including the infotainment system or tablet.

[1219] "Display means" refers to a device or function for visually or audibly presenting information such as study questions and feedback to the user.

[1220] "Voice input" refers to an input method in which a user provides answers to study questions using voice.

[1221] "Touch operation" refers to the user entering answers using the touchscreen of a tablet or infotainment system.

[1222] The "judging means" is a function that evaluates whether the user's answer is correct or incorrect and adjusts the difficulty level based on the result.

[1223] "Feedback" provides the user with information indicating the evaluation of their answer and next steps.

[1224] The present invention provides a system for automatically generating learning questions for children and adjusting the difficulty of the questions based on the user's answers. This system can be installed in an autonomous vehicle, enabling learning activities while traveling in the vehicle. A specific embodiment of the system is described below.

[1225] System Structure

[1226] This system mainly consists of a server and a terminal. The server generates learning questions, evaluates the user's answers, and provides the function to adjust the difficulty level. The terminal, especially the infotainment system or tablet in the autonomous vehicle, displays the learning questions to the user, collects the user's answers, and displays the feedback received from the server.

[1227] Server Operation

[1228] The server first generates learning questions using a question generation class. The generated learning questions are sent to the terminal and displayed to the user. The user's answers are then sent to the server via the terminal. The server compares the received answers with the correct answers, increasing the difficulty if they are correct and decreasing the difficulty if they are incorrect. This provides an appropriate learning environment according to the user's level of understanding and progress.

[1229] Device behavior

[1230] The device is an infotainment system or tablet installed in the autonomous vehicle, which displays the learning questions and accepts the user's answers. The user inputs their answers through touch or voice input. The answers are sent to a server, and the results and feedback on difficulty adjustments are displayed on the device. This allows users to continue learning without interruption even while on the move.

[1231] User Actions

[1232] The user, or child, works on learning problems while in the car. For example, when a math problem such as "15 + 7" appears, the user inputs the answer "22" using touch or voice input. The device sends the answer to the server, which evaluates the result and returns feedback. The user then works on the next problem based on the result.

[1233] Specific examples

[1234] In the first learning cycle, the problem generated by the server is "15 + 7." If the user answers "22," the server determines this is an incorrect answer and lowers the difficulty of the next problem. The device then displays feedback to the user saying, "This is incorrect. Proceed to the next problem."

[1235] In the second learning cycle, the server generates a question with a lower level of difficulty, such as "8 + 4." If the user answers "12," the server recognizes this as the correct answer and increases the difficulty of the next question. The device displays feedback saying, "Correct! The difficulty will increase."

[1236] Prompt Sentence Examples

[1237] Examples of prompts for generative AI models include:

[1238] "Current difficulty level is 2. Generate math problems for children."

[1239] "Please create a Japanese language question that corresponds to level 3."

[1240] This allows learning activities to be carried out while on the move, and by providing effective feedback and difficulty adjustments in real time, children's learning efficiency can be improved.

[1241] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1242] Step 1:

[1243] The server generates the training questions (input: current difficulty level, output: generated training questions)

[1244] The server generates learning problems based on the current level of difficulty. For example, it uses a generative AI model to input a prompt such as "Please generate a math problem of level 1" and outputs appropriate learning problems based on that. The server stores the generated learning problems and prepares them to be sent to the device.

[1245] Step 2:

[1246] The device displays the study questions (input: study questions received from the server, output: displayed study questions)

[1247] The device displays the learning questions received from the server to the user. During this process, the question is displayed on the screen or the user is informed of the question by voice output. For example, the question "15 + 7" is displayed on the screen.

[1248] Step 3:

[1249] User enters answer (input: study question, output: user answer)

[1250] The user inputs answers to the displayed study questions. The input method can be touch operation or voice input. For example, the user can provide the answer "22" by voice input.

[1251] Step 4:

[1252] The device receives the user's answer and sends it to the server (input: user's answer, output: sending the answer to the server)

[1253] The terminal receives the answer entered by the user and sends it to the server. The data includes the question ID along with the answer content.

[1254] Step 5:

[1255] The server judges the answer and adjusts the difficulty level (input: user's answer, output: judgement result and new difficulty level)

[1256] The server compares the received user answer with the correct answer data, and based on the results, increases the difficulty level if the answer is correct, or decreases it if the answer is incorrect. For example, if the answer "22" is incorrect, the difficulty level of the next question is lowered.

[1257] Step 6:

[1258] The server generates feedback and sends it to the device (input: judgment result and new difficulty level, output: feedback message).

[1259] The server generates a feedback message for the user based on the result of the judgment and the new difficulty level. For example, it generates a message such as "This is a mistake. Proceed to the next question." and sends it to the terminal.

[1260] Step 7:

[1261] The device displays the feedback (input: feedback message received from the server, output: displayed feedback)

[1262] The terminal displays the feedback message received from the server to the user. Feedback is provided by visual display or audio, allowing the user to confirm the results of their answers.

[1263] Step 8:

[1264] The device requests a new learning problem (input: new difficulty level, output: next learning problem)

[1265] After providing feedback to the server, the device requests the server to generate new learning questions corresponding to the new level of difficulty for the next learning cycle, thereby maintaining continuity of learning.

[1266] 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.

[1267] The present invention provides a learning support system for children that incorporates an emotion engine that recognizes the emotions of a user. Specific embodiments of the system will be described below.

[1268] This system mainly consists of a server, a terminal, and an emotion engine. The server generates learning questions, evaluates users' answers, and adjusts the difficulty level. The terminal displays learning questions to users, collects their answers, and displays feedback received from the server. The emotion engine recognizes users' emotions and adjusts the difficulty and type of learning questions based on those emotions.

[1269] Server Operation

[1270] The server first generates study questions using a problem generation class. The problem generation class stores the current difficulty level and creates appropriate study questions based on that level. For example, for math problems, a low level generates addition problems using random numbers in the range of 1 to 10, while a high level generates addition problems in the range of 1 to 20. For Japanese language problems, reading and writing tasks are presented according to the level of difficulty.

[1271] The generated learning questions are sent to the device and displayed to the user. The user's answers are then sent to the server via the device. The server compares the received answers with the correct answers, increasing the difficulty if they are correct and decreasing the difficulty if they are incorrect. Furthermore, the difficulty and type of learning questions are adjusted based on the user's emotions recognized by the emotion engine.

[1272] Device behavior

[1273] The device displays the study questions received from the server to the user. The question text is displayed on the screen so that the user can see the question content. When the user enters the answer to the study question, the answer is sent to the server. The device receives feedback from the server regarding the assessment result and difficulty level adjustment, and displays this to the user. For example, if the user answers correctly, it displays "You got it right! The difficulty level will be increased," and if the answer is incorrect, it displays "You got it wrong. The difficulty level will be lowered."

[1274] Emotion Engine Operation

[1275] The emotion engine measures data such as the user's facial expressions, voice, and input speed to recognize the user's emotions. For example, if it recognizes that the user is feeling stressed, it temporarily lowers the difficulty of the study questions to reduce the user's burden. On the other hand, if the user is feeling relaxed, it adjusts the difficulty level appropriately to maintain or increase it.

[1276] User Actions

[1277] The user answers the learning problems displayed on the device. For example, if the math problem is "5 + 3," the user enters "8" as the answer. The device then sends the answer to the server, which returns a judgment and feedback. The user can then move on to the next problem based on the result. The emotion engine also monitors the user's emotional state and adjusts the learning experience more appropriately, allowing the user to continue studying without stress.

[1278] Specific examples

[1279] In the first learning cycle, the problem generated by the server is "5 + 3." If the user answers "8," the server determines this is the correct answer and increases the difficulty of the next problem. The device then displays feedback to the user saying, "You got it right! The difficulty will increase." Also, if the emotion engine recognizes a relaxed state from the user's facial expressions and voice, the difficulty of the next problem will increase appropriately.

[1280] In the second learning cycle, the server generates a more difficult question, for example, "15 + 7." If the user answers "20," the server determines this is an incorrect answer and lowers the difficulty of the next question. Also, if the emotion engine recognizes that the user is feeling stressed, it appropriately lowers the difficulty of the next question to reduce the user's burden. The device displays feedback saying, "That's a mistake. We'll lower the difficulty."

[1281] In this way, the system can provide an appropriate learning environment by adjusting the difficulty and type of questions in real time based on the user's answers and emotional state. This continuous feedback and adjustment effectively supports the user's academic improvement.

[1282] Furthermore, this system can handle multiple subjects, such as math and Japanese. By automatically generating appropriate study questions according to difficulty level, it can help users study each subject in a balanced way.

[1283] As described above, the present invention is extremely effective as a learning support system for children, and can maximize the learning effect.

[1284] The processing flow will be explained below.

[1285] Step 1:

[1286] The server obtains the current difficulty level using an instance of the problem generator class. Specifically, it checks the initial difficulty level by referencing the property self.problem_generator.difficulty .

[1287] Step 2:

[1288] The server generates learning questions based on the acquired difficulty level. For example, if the difficulty level is 1, it generates addition questions using random numbers in the range of 1 to 10. The generated questions are stored in string format.

[1289] Step 3:

[1290] The server sends the generated learning questions to the device. Specifically, it transfers data including the question content (e.g., "5 + 3") to the device.

[1291] Step 4:

[1292] The terminal displays the transmitted study questions to the user, and displays the question text on the screen so that the user can visually recognize the question content.

[1293] Step 5:

[1294] The user answers the displayed study question. For example, the user answers "8" to the question "5 + 3."

[1295] Step 6:

[1296] The terminal collects the user's answers. Specifically, it stores the answers entered by the user as numerical values ​​and prepares to send the answer data to the server.

[1297] Step 7:

[1298] The terminal sends the collected answers of the user to the server, and the user's input data is passed to the server.

[1299] Step 8:

[1300] The server determines whether the received user answer is correct or incorrect. The server evaluates the question text and compares the correct answer with the user's answer. For example, the correct answer to "5 + 3" is "8," and if the user's answer is "8," it is determined to be correct.

[1301] Step 9:

[1302] The server adjusts the difficulty of the study questions based on the answers. If the user answers correctly, the difficulty level is increased, and if the user answers incorrectly, the difficulty level is decreased. For example, the difficulty level may be increased from 1 to 2, or decreased from 2 to 1.

[1303] Step 10:

[1304] The emotion engine analyzes the user's facial expressions, voice, typing speed, etc. to recognize the user's emotions, thereby determining whether the user is stressed or relaxed.

[1305] Step 11:

[1306] An emotion engine adjusts the difficulty or type of study questions based on the perceived user emotion, for example, if the user is stressed, the next study question will be less difficult.

[1307] Step 12:

[1308] The server generates feedback regarding the result of the judgment and the difficulty adjustment, and sends it to the device. It creates a feedback message (e.g., "You got it right! The difficulty will be increased." or "You got it wrong. The difficulty will be decreased.").

[1309] Step 13:

[1310] The terminal displays the feedback received from the server to the user, who can obtain information about his / her answer results and future study strategies.

[1311] Step 14:

[1312] The user checks the displayed feedback and moves on to the next problem. For example, if the emotion engine determines that the user is feeling stressed, the difficulty level of the next problem is set low. This cycle is repeated to maximize the user's learning effect.

[1313] Example 2

[1314] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1315] Conventional learning support systems adjust the difficulty of study questions based on the user's answers, but lack a mechanism for adjusting the learning experience based on the user's emotional state. As a result, if the user is stressed or overly relaxed, the difficulty level may not be adjusted appropriately, potentially reducing the learning effect. The present invention aims to recognize the user's emotions and adjust the difficulty and type of study questions based on that, allowing the user to continue learning in an optimal state.

[1316] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for generating study questions corresponding to the current level of difficulty, means for displaying the study questions, means for accepting a user's answers to the study questions, means for determining whether the user's answers are correct or incorrect, means for adjusting the difficulty of the study questions based on the determination result, means for collecting emotional data and recognizing the user's emotions, means for adjusting the difficulty or type of the study questions based on the emotion recognition, and means for displaying feedback regarding the determination result and the difficulty adjustment to the user. This makes it possible to comprehensively determine the user's answering status and emotional state and provide an appropriate learning environment in real time.

[1317] The following are definitions of important terms contained in the claims.

[1318] A "study question" is a math or language related challenge provided for the user to answer.

[1319] "Difficulty" is an indicator of the complexity of the study questions and the difficulty of solving them.

[1320] A "server" is a computer system that generates study questions, judges user answers, adjusts difficulty, and provides feedback.

[1321] A "terminal" is a device that displays study questions to a user, collects the user's answers, and displays feedback from the server.

[1322] "Emotion data" is information collected from the user's facial expression, voice, input speed, etc., and is data that indicates the user's emotional state.

[1323] An "emotion engine" is a software or hardware system for analyzing emotion data and recognizing a user's emotion.

[1324] "Feedback" is information that provides the user with the evaluation results of the user's answers, as well as study instructions and comments based on the evaluation results.

[1325] "Determination" is the process of determining whether the answer given by the user is correct or incorrect.

[1326] "Tuning" is the process of changing the difficulty and type of study questions based on the user's answers and emotional state.

[1327] "Display" refers to the act of visually presenting information on the screen of a terminal, such as showing study questions and feedback to the user.

[1328] The present invention is a learning support system for children that combines an emotion engine that recognizes the user's emotions. This system is mainly composed of a server, a terminal, and an emotion engine. Specific embodiments of the system are described below.

[1329] System Configuration

[1330] The system includes the following means:

[1331] 1. Server

[1332] 2. Terminal

[1333] 3. Emotion Engine

[1334] Server Operation

[1335] The server first generates learning problems using a problem generation class. The problem generation class stores the current difficulty level and creates appropriate learning problems based on that level. For example, in arithmetic, a low level of difficulty generates a simple addition problem like "5 + 3," while a high level of difficulty generates a more complex addition problem like "15 + 7." The generated learning problems are then sent to the device and displayed to the user. After the user's answer is sent to the server via the device, the server compares the answer with the correct answer and makes a judgment. If the answer is correct, the difficulty level is increased; if the answer is incorrect, the difficulty level is decreased. The difficulty and type of learning problems are further adjusted based on the user's emotional data recognized by the emotion engine.

[1336] Examples:

[1337] Example prompt: "The server generates a '5 + 3' problem and sends it to the terminal, then waits for the user's answer. After the user enters the answer, write a program that judges the answer and returns appropriate feedback. Also, add a function to adjust the difficulty of the problem using the user's emotional data."

[1338] Device behavior

[1339] The device displays the learning questions received from the server to the user. For example, the problem "5 + 3" is displayed on the screen, and the user inputs the answer to the problem. This answer is sent to the server, and the user checks the feedback from the server. The feedback from the server is displayed to the user as a message such as "That's correct! The difficulty will increase" or "That's incorrect. The difficulty will be lowered."

[1340] Emotion Engine Operation

[1341] The emotion engine uses emotion sensors to measure data such as the user's facial expressions, voice, and input speed. It then analyzes the collected data using an AI model to recognize the user's emotions. For example, it can determine whether the user is feeling stressed or relaxed based on data from the camera, microphone, and keyboard input speed. The recognized emotion data is sent to the server, which uses it as reference information to adjust the difficulty and type of the next learning problem.

[1342] User Actions

[1343] The user answers the study questions displayed on the device. For example, they enter "8" for the "5 + 3" question. After answering, the device sends the answer to the server and receives and displays feedback. This allows the user to prepare for the next question. The user can also see that their learning progress is optimized in real time according to the emotion recognition by the emotion engine.

[1344] This system comprehensively assesses the user's response status and emotional state, and adjusts the difficulty and type of study questions appropriately to provide an effective learning environment, which is expected to improve the user's academic ability.

[1345] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1346] The processing flow of the program of this system will be explained in detail below, divided into processing steps.

[1347] Step 1: Generate training questions

[1348] The server uses the problem generation class to generate problems based on the current difficulty level. For example, if the current difficulty level is low, the server generates a simple addition problem such as "5 + 3." The input for this problem generation is the current difficulty level data, and the output is the generated problem.

[1349] Step 2: Submit and view the exercises

[1350] The server sends the generated study questions to the terminal. The input is the generated study question data, and the output is a notification that the sending process is complete. The terminal then displays the received study questions on the screen. For example, a "5 + 3" problem is displayed on the screen. The input here is the study question data received from the server, and the output is the problem displayed on the screen in a format that the user can see.

[1351] Step 3: User answers

[1352] The user inputs answers to the study questions displayed on the terminal. For example, the user inputs "8" using the keyboard. The input is the data the user answered, and the output is the answer data stored inside the terminal.

[1353] Step 4: Submitting user answers

[1354] The terminal sends the user's answer to the server. The input is the user's answer data, and the output is a transmission completion notification to the server.

[1355] Step 5: Determine the answer

[1356] The server compares the received user answer with the correct answer and makes a judgment. For example, if the received answer is "8" and the question is the addition "5 + 3", it judges whether the answer is correct. The input is the user's answer data and the correct answer data, and the output is the judgment result data.

[1357] Step 6: Collect and recognize emotion data

[1358] The emotion engine collects data such as the user's facial expressions, voice, and input speed, and uses this data to recognize the user's emotions. For example, it acquires the user's facial expression data through a camera and analyzes it with an AI model to determine whether the user is relaxed or stressed. The input is emotion data, and the output is the user's emotion recognition result data.

[1359] Step 7: Adjusting the difficulty

[1360] The server adjusts the difficulty of the learning questions based on the answer judgment results and emotion recognition results. For example, if the user answers correctly and the emotion engine recognizes that the user is relaxed, the server increases the difficulty of the next question. The input is the judgment result data and emotion recognition result data, and the output is the adjusted difficulty data.

[1361] Step 8: Submit and view feedback

[1362] The server sends the judgment result and the difficulty adjustment result to the terminal, and the terminal displays them to the user. For example, a feedback message such as "Correct! The difficulty will increase." The input is the feedback data from the server, and the output is the feedback message displayed to the user.

[1363] Through the above specific processing steps, the system can comprehensively judge the user's answering situation and emotional state, and provide an appropriate learning environment in real time.

[1364] (Application example 2)

[1365] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1366] Conventional learning support systems and work support systems set the difficulty level unilaterally without considering the user's emotional state, which often led to stress and fatigue for the user. Furthermore, because the difficulty level was set uniformly, the user's learning effect and work efficiency were often reduced. In this modern age, where flexible responses according to the user's state are required, systems incorporating emotion recognition are becoming increasingly important.

[1367] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for generating study questions corresponding to the current level of difficulty, means for displaying study questions, means for accepting a user's answers to the study questions, means for determining whether the user's answers are correct or incorrect, means for adjusting the difficulty of the study questions based on the determination result, means for displaying feedback to the user regarding the determination result and the difficulty adjustment, means for recognizing the user's emotions, means for adjusting the difficulty and type of study questions based on the emotions, and means for feeding back the emotion recognition results to the work environment and adjusting the work difficulty appropriately. This provides an appropriate learning environment and work environment according to the user's emotional state, allowing the user to study and work efficiently without stress.

[1368] A "system" is a collection of multiple elements, each of which works together to achieve a specific function.

[1369] The "means for generating study questions" is a component within the system that has the function of creating questions that correspond to the user's study content.

[1370] The "means for displaying study questions" is a component that has the function of visually presenting study questions to the user.

[1371] The "means for accepting user answers" is a component that has the function of allowing the system to receive answers entered by the user to the study questions.

[1372] The "means for determining whether the answer is correct or incorrect" is a component that has the function of determining whether the user's answer is correct or not.

[1373] The "means for adjusting difficulty" is a component that has the function of automatically changing the difficulty of the next study question to be presented based on the user's answer.

[1374] The "means for displaying feedback to the user" is a component that has the function of conveying information about the answer result and difficulty level adjustment to the user.

[1375] The "means for recognizing user's emotions" is a component having a function for analyzing the user's emotional state (for example, stress, relaxation, motivation, etc.).

[1376] The "means for adjusting the difficulty and type of study questions based on emotions" is a component that has the function of appropriately changing the difficulty and type of study questions for the user based on the results of emotion recognition.

[1377] The "means for feeding back emotion recognition results to the work environment and adjusting the difficulty of the work appropriately" is a component that has the function of adjusting the work content and difficulty based on the user's emotion recognition results, thereby reducing the burden on the user.

[1378] The present invention is a learning and work support system that combines an emotion engine that recognizes the user's emotions. This system is composed of a server, a terminal, and an emotion engine.

[1379] The server first generates study questions using a problem generation class. The problem generation class stores the current difficulty level and creates appropriate study questions based on that level. For example, for arithmetic questions, a basic addition problem is generated if the difficulty level is low, and a more complex addition problem is generated if the difficulty level is high. For Japanese language questions, reading and writing tasks are presented according to the respective level of difficulty. The generated study questions are sent to the device and displayed to the user. The user's answers are then sent to the server via the device. The server compares the received answers with the correct answers and increases the difficulty level if they are correct, or decreases the difficulty level if they are incorrect. The server also adjusts the difficulty level and type of study questions based on the user's emotions recognized by the emotion engine.

[1380] The device displays the study questions received from the server to the user. The question text is displayed on the screen so that the user can see the question content. When the user enters the answer to the study question, the answer is sent to the server. The device receives feedback from the server regarding the assessment result and difficulty level adjustment, and displays this to the user. For example, if the user answers correctly, it displays "You got it right! The difficulty level will be increased," and if the answer is incorrect, it displays "You got it wrong. The difficulty level will be lowered."

[1381] The emotion engine measures data such as the user's facial expressions, voice, and input speed to recognize the user's emotions. For example, if it recognizes that the user is feeling stressed, it temporarily lowers the difficulty of the study questions to reduce the user's burden. On the other hand, if the user is feeling relaxed, it adjusts the difficulty level appropriately to maintain or increase it.

[1382] Furthermore, this invention can also be applied to assisting factory robots in their work. This system involves installing an emotion engine in a factory robot, recognizing the emotional state of a worker in real time, and adjusting the difficulty of the work based on the results. For example, if the emotion engine recognizes that a worker is under stress, it can assign the worker an easy task or suggest a temporary break. If the emotion engine recognizes that the worker is highly motivated, it can assign a difficult task.

[1383] To illustrate, consider the following scenario:

[1384] Example 1:

[1385] If the emotion engine recognizes that Worker A is under stress, it assigns him / her an easy task (e.g., sorting parts), thereby reducing the workload.

[1386] Example 2:

[1387] If Worker B is perceived as highly motivated, he or she will be assigned a more difficult task (e.g., assembling a complex machine), which will improve work efficiency.

[1388] Example prompt sentence:

[1389] "Recognize the facial expressions of the workers from the images and use an emotion engine to estimate their emotions. Assuming the emotion is stress, relaxation, or motivation, suggest an appropriate level of task difficulty depending on the emotion."

[1390] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1391] Step 1:

[1392] The server generates learning questions according to the current level of difficulty using a question generation class. At this time, the current level of difficulty is given as input, and learning content according to that level of difficulty (for example, addition problems in arithmetic or reading and writing problems in Japanese) is output.

[1393] Step 2:

[1394] The server sends the generated training questions to the terminal, where the input is the generated training questions and the output is the training question data sent to the terminal.

[1395] Step 3:

[1396] The terminal displays the exercises received from the server to the user, with the input being the exercises received from the server and the output being the text of the exercises displayed to the user.

[1397] Step 4:

[1398] The user inputs answers to the displayed study questions. The input is the study question and the user's answer, and the output is the user's answer data input to the terminal.

[1399] Step 5:

[1400] The terminal sends the user's answer to the server. The input is the user's answer data, and the output is the answer data sent to the server.

[1401] Step 6:

[1402] The server determines whether the user's answer is correct or incorrect. The input is the user's answer and the correct answer data, and the output is the judgment result (correct or incorrect).

[1403] Step 7:

[1404] The server adjusts the difficulty of the next study question based on the judgment result. The input is the judgment result, and the output is the difficulty data for the next study question.

[1405] Step 8:

[1406] The server generates feedback regarding the judgment result and the difficulty level adjustment and sends it to the terminal. The input is the judgment result and the adjusted difficulty level, and the output is a feedback message.

[1407] Step 9:

[1408] The terminal displays the feedback received from the server to the user. The input is the feedback message and the output is the feedback text displayed to the user.

[1409] Step 10:

[1410] The emotion engine measures and analyzes data such as the user's facial expressions, voice, and input speed to recognize the user's emotions. The input is the user's raw data (facial expressions, voice data, input speed data), and the output is the user's emotional state (stress, relaxation, motivation, etc.).

[1411] Step 11:

[1412] The server adjusts the difficulty and type of training questions based on the emotion recognition results. The input is the emotion recognition results, and the output is the adjusted difficulty and type of questions.

[1413] Step 12:

[1414] The server feeds back the emotion recognition results to the work environment and adjusts the task difficulty. The input is the emotion recognition results and the current task content, and the output is the adjusted task.

[1415] Step 13:

[1416] The terminal displays the adjusted work task to the user or the work robot or issues instructions to the user or the work robot. The input is the adjusted work task data, and the output is instructions to the user or the work robot.

[1417] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1418] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1419] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1420] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1421] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1422] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1423] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1424] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1425] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1426] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1427] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1428] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1429] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1430] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1431] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1432] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1433] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1434] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1435] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1436] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1437] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1438] The following is further disclosed regarding the above embodiment.

[1439] (Claim 1)

[1440] A system for generating learning questions for children and adjusting the difficulty level of the questions based on a user's answers, comprising:

[1441] A means for generating study questions corresponding to the current level of difficulty;

[1442] means for displaying the study questions;

[1443] means for accepting a user's answer to the study question;

[1444] means for determining whether the user's answer is correct or incorrect;

[1445] means for adjusting the difficulty level of the study questions based on the determination result;

[1446] means for displaying feedback regarding the determination result and difficulty level adjustment to a user;

[1447] A system including:

[1448] (Claim 2)

[1449] 10. The system of claim 1, further comprising means for generating math and language arts exercises.

[1450] (Claim 3)

[1451] 2. The system according to claim 1, wherein the difficulty level adjustment means increases the difficulty level when the user's answer is correct, and decreases the difficulty level when the user's answer is incorrect.

[1452] "Example 1"

[1453] (Claim 1)

[1454] A means for generating study questions for children using a program for generating study questions;

[1455] means for transmitting the study questions to a terminal and displaying them;

[1456] means for accepting a user's answer to the study question;

[1457] means for transmitting the user's answer to a server;

[1458] means for determining whether the answer is correct or incorrect and adjusting the difficulty level of the study questions based on the result;

[1459] means for generating feedback of the determination result and difficulty level adjustment and displaying it to the user;

[1460] A system including:

[1461] (Claim 2)

[1462] 10. The system of claim 1, further comprising means for generating math and language arts exercises.

[1463] (Claim 3)

[1464] 2. The system according to claim 1, wherein the difficulty level adjustment means increases the difficulty level when the user's answer is correct, and decreases the difficulty level when the user's answer is incorrect.

[1465] "Application Example 1"

[1466] (Claim 1)

[1467] A system for generating learning questions for children and adjusting the difficulty level of the questions based on a user's answers, comprising:

[1468] A means for generating study questions corresponding to the current level of difficulty;

[1469] means for displaying the study questions;

[1470] means for displaying the learning questions in a moving object;

[1471] means for accepting a user's answer to the study question by voice or touch operation;

[1472] means for determining whether the user's answer is correct or incorrect;

[1473] means for adjusting the difficulty level of the study questions based on the determination result;

[1474] means for displaying feedback regarding the determination result and difficulty level adjustment to a user;

[1475] A system including:

[1476] (Claim 2)

[1477] 10. The system of claim 1, further comprising means for generating math and language arts exercises.

[1478] (Claim 3)

[1479] 2. The system according to claim 1, wherein the difficulty level adjustment means increases the difficulty level when the user's answer is correct, and decreases the difficulty level when the user's answer is incorrect.

[1480] "Example 2: Combining Emotion Engines"

[1481] (Claim 1)

[1482] A system for generating learning questions for children and adjusting the difficulty level of the questions based on a user's answers, comprising:

[1483] A means for generating study questions corresponding to the current level of difficulty;

[1484] means for displaying the study questions;

[1485] means for accepting a user's answer to the study question;

[1486] means for determining whether the user's answer is correct or incorrect;

[1487] means for adjusting the difficulty level of the study questions based on the determination result;

[1488] means for collecting emotion data and recognizing the emotion of a user;

[1489] means for adjusting the difficulty or type of the learning questions based on the emotion recognition;

[1490] means for displaying feedback regarding the determination result and difficulty level adjustment to a user;

[1491] A system including:

[1492] (Claim 2)

[1493] 10. The system of claim 1, further comprising means for generating math and linguistics practice questions.

[1494] (Claim 3)

[1495] 2. The system of claim 1, wherein the difficulty level adjustment means increases the difficulty level if the user's answer is correct and decreases the difficulty level if the answer is incorrect, and decreases the difficulty level if the emotion recognition means determines that the user is feeling stressed.

[1496] "Application example 2 when combining emotion engines"

[1497] (Claim 1)

[1498] A system for generating learning questions for children and adjusting the difficulty level of the questions based on a user's answers, comprising:

[1499] A means for generating study questions corresponding to the current level of difficulty;

[1500] means for displaying the study questions;

[1501] means for accepting a user's answer to the study question;

[1502] means for determining whether the user's answer is correct or incorrect;

[1503] means for adjusting the difficulty level of the study questions based on the determination result;

[1504] means for displaying feedback regarding the determination result and difficulty level adjustment to a user;

[1505] means for recognizing a user's emotion;

[1506] a means for adjusting the difficulty and type of study questions based on the emotion;

[1507] a means for feeding back the emotion recognition result to the work environment and adjusting the work difficulty appropriately;

[1508] A system including:

[1509] (Claim 2)

[1510] 10. The system of claim 1, further comprising means for generating math and language arts exercises.

[1511] (Claim 3)

[1512] 2. The system according to claim 1, wherein the difficulty level adjustment means increases the difficulty level when the user's answer is correct, and decreases the difficulty level when the user's answer is incorrect. [Explanation of symbols]

[1513] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A system for generating learning questions for children and adjusting the difficulty level of the questions based on a user's answers, comprising: A means for generating study questions corresponding to the current level of difficulty; means for displaying the study questions; means for accepting a user's answer to the study question; means for determining whether the user's answer is correct or incorrect; means for adjusting the difficulty level of the study questions based on the determination result; means for displaying feedback regarding the determination result and difficulty level adjustment to a user; A system including:

2. 10. The system of claim 1, further comprising means for generating math and language arts exercises.

3. 2. The system according to claim 1, wherein said difficulty level adjusting means increases the difficulty level when said user's answer is correct, and decreases the difficulty level when said user's answer is incorrect.

Images