system

Abstract

Provide a system. A terminal for inputting learning preference data; a server that analyzes data received from the terminal; A generative AI that receives the analysis results from the server and generates individually optimized problem sets; A server that transmits the problem set received from the generative AI to a terminal; means for displaying the transmitted problem set to a user in the terminal; 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] Traditional learning methods make it difficult for students to select learning content that suits their strengths and weaknesses, and provide incomplete questions optimized for individual learning needs. As a result, each student's learning efficiency decreases, leading to imbalances in learning progress and comprehension. Furthermore, fixed problem sets have a uniform quantity and quality of questions, making it impossible to customize for each student, limiting the effectiveness of learning. [Means for solving the problem]

[0005] In this invention, students input their desired learning data from a terminal, which is then analyzed by a server. Generative AI then generates an individually optimized problem set based on the analysis results. This problem set is then sent via the server to the terminal, which then displays it to the user. This makes it possible to provide problems optimized for each student's strengths and weaknesses and learning needs, significantly improving learning efficiency and effectiveness.

[0006] A "terminal" is a device used by a user to input study data and display problem sets.

[0007] A "server" is a computing system that analyzes data received from a terminal and communicates data with the generative AI and the terminal.

[0008] "Generative AI" is an artificial intelligence system that generates individually optimized problem sets based on data received from a server.

[0009] "Study preference data" is data that includes information such as the subjects and scope that the user wants to study, as well as their strengths and weaknesses.

[0010] A "problem set" is a collection of learning problems generated by generative AI that are suited to individual users.

[0011] "Analysis" refers to data processing performed by the server to send appropriate instructions to the generative AI based on the user's learning history and wishes.

[0012] A "user" is a person who operates a terminal to input desired study data and solve the generated problem set.

[0013] "Learning history data" is data that includes information such as past learning content and test results, and indicates the user's learning status. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] The present invention is a system that combines a terminal, a server, and a generative AI to provide problem sets optimized for the learning needs of each student. A specific embodiment of this system is shown below.

[0036] 1. Overview of the entire system

[0037] This system consists of a device used by the user (e.g., a tablet device), a server, and a generative AI. The user inputs the data they wish to learn through the device, and the data is sent to the generative AI via the server. The generative AI generates an individually optimized problem set based on the received data, and sends it back to the device via the server. Finally, the user can solve the customized problem set on their device.

[0038] 2. User terminal operation

[0039] The user operates the device to input their desired study data. Specifically, they input the subject they want to study (e.g., mathematics), the range of study (e.g., geometry), and their strengths and weaknesses. The device then sends this information to the server.

[0040] Example: Student A logs in to a tablet device and inputs that he / she is weak in mathematics geometry, especially the "properties of triangles." The device sends this data to the server.

[0041] 3. Server Operation

[0042] The server analyzes the learning request data received from the device. Based on the analysis results, it sends data to the generative AI requesting it to generate an optimized problem set. When the problem set is returned from the generative AI, it is sent to the user's device.

[0043] Example: The server analyzes the data of Student A and instructs the generative AI to create problems specific to "geometry triangles." The server receives the necessary problem set from the generative AI and sends it to Student A's device.

[0044] 4. How generative AI works

[0045] The generative AI generates an appropriate problem set based on the learning preference data received from the server and the analysis results. The generated problems are adjusted according to the user's strengths and weaknesses and learning progress.

[0046] Example: A generative AI generates a balanced set of problems for Student A, including basic problems on the "properties of triangles," applied problems, and problems from other areas, and sends them back to the server.

[0047] 5. Viewing and answering problem sets

[0048] The terminal receives the problem set from the server and displays it to the user. The user solves the problem and inputs the answer. The terminal also sends the answer data to the server.

[0049] Example: Student A solves a customized problem set displayed on a tablet device. When he enters his answers, they are sent to the server.

[0050] 6. Providing Feedback

[0051] The server automatically scores the received answer data and generates feedback, which is then sent back to the user's device and displayed to the user.

[0052] Example: The server grades Student A's answers and generates feedback such as "This is the correct answer" or "This is incorrect." This feedback is sent to Student A's device and displayed.

[0053] The above-described embodiment allows students (users) to receive a learning experience optimized to their needs, thereby enabling them to study efficiently and effectively and improve their academic performance.

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] The user starts the application on the device and enters the user ID and password on the login screen. The device sends this login information to the server.

[0057] Step 2:

[0058] The server receives the login information and authenticates the user by checking the database. If authentication is successful, the server retrieves the user's past learning history data from the database and sends it to the terminal.

[0059] Step 3:

[0060] The device displays the received learning history data and prompts the user to enter desired learning data. The user enters the desired subjects, scope, strengths and weaknesses, etc. The device then sends this desired learning data to the server.

[0061] Step 4:

[0062] The server receives the learning preference data and analyzes it in combination with existing learning history data. Based on the analysis results, it prepares data to request the generative AI to generate a customized problem set, and sends it to the generative AI.

[0063] Step 5:

[0064] The generative AI generates individually optimized problem sets based on the data received from the server, and the generated problem sets are sent back to the server.

[0065] Step 6:

[0066] The server receives the problem set returned by the generative AI and sends it to the user's device, allowing the user to receive a customized problem set.

[0067] Step 7:

[0068] The terminal displays the received problem set to the user. The user solves the displayed problem and inputs the answer. The input answer is sent from the terminal to the server.

[0069] Step 8:

[0070] The server analyzes the answer data received from the user, automatically scores the answers, generates the scoring results and feedback, and sends them to the user's terminal.

[0071] Step 9:

[0072] The device displays the feedback received from the server to the user, who then checks the feedback and plans their next learning experience.

[0073] Example 1

[0074] 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."

[0075] The current educational system faces the challenge of providing learning materials optimized for each student's learning needs. A method is needed to generate appropriate problem sets based on each student's strengths and weaknesses and learning progress, and to provide them in a timely manner. It is also necessary to introduce a system that provides prompt and accurate feedback on answers.

[0076] 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.

[0077] In this invention, the server includes a means for analyzing the study data, a means for receiving question data sets from a generative artificial intelligence that generates individually optimized question data sets, and a means for scoring the user's answer data and generating feedback. This makes it possible to generate and provide an optimal question set based on the study data and analysis results, and to provide rapid feedback on the answers.

[0078] "Study preference data" refers to information such as the subjects, scope, and areas of strength and weakness that a user wishes to study.

[0079] "Device" refers to input and display devices such as tablet terminals and personal computers operated by users.

[0080] "Data processing device" refers to a server that analyzes input data and manages and transmits data and feedback from generative artificial intelligence.

[0081] "Generative artificial intelligence" refers to an AI model that generates individually optimized sets of problem data based on analysis results.

[0082] "Question data group" refers to multiple question sets generated by generative artificial intelligence and optimized to the user's learning needs.

[0083] "Feedback" refers to evaluation information such as whether the questions answered by the user are correct or incorrect, and advice.

[0084] This system is comprised of a device where users input their desired learning data, a data processing device (server) that analyzes the data to generate appropriate problem data sets and processes and manages the analysis results, and generative artificial intelligence. This system makes it possible to provide problem sets optimized for the user's learning needs and provide rapid feedback.

[0085] 1. User terminal configuration and operation

[0086] The device operated by the user can be a tablet or PC. The user inputs their desired study data through the device. Specifically, they input the subject they want to study (e.g., mathematics), the range of study (e.g., geometry), and their strengths and weaknesses.

[0087] Examples:

[0088] Student A logs in to the tablet device and enters that he or she is focusing on mathematics geometry, particularly the properties of triangles, which is something he or she is weak at.

[0089] 2. Server Configuration and Operation

[0090] The server analyzes the received learning data and sends the analysis results to the generative AI. The analysis is performed using Python scripts and a database management system. The server also plays a role in sending the problem data received from the generative AI to the user's device.

[0091] Examples:

[0092] The server analyzes Student A's data and identifies learning needs specific to "triangles in geometry." It then sends a prompt to the generative AI to "generate a set of problems related to the properties of triangles."

[0093] 3. Structure and operation of generative artificial intelligence

[0094] The generative AI generates a set of question data based on the analysis results. The generated questions are adjusted according to the user's strengths and weaknesses and learning progress. The generated set of question data is sent to the user's device via the server.

[0095] Examples:

[0096] The generative artificial intelligence generates a balanced set of problems for Student A, including basic problems on the "properties of triangles," applied problems, and problems from other related areas, and sends it back to the server.

[0097] Example prompt sentence:

[0098] "Generate a problem set for Student A that includes basic problems about the properties of triangles, applied problems, and related problems from another area."

[0099] 4. User answers and feedback

[0100] The user answers questions on their device and sends the data to the server, which then scores the answers and generates feedback, which is then sent back to the user's device and displayed to the user.

[0101] Examples:

[0102] When Student A solves the displayed problem and enters the answer, the device sends the answer data to the server. The server grades the answer and generates feedback such as "This is the correct answer" or "This is incorrect" and sends it to Student A's device.

[0103] In this way, the present invention allows users to receive an individually optimized learning experience, resulting in efficient and effective learning.

[0104] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0105] Step 1:

[0106] The user inputs the desired learning data into the terminal.

[0107] Specific behavior:

[0108] The user uses a tablet device or computer to input the subject being studied (e.g., mathematics), range of study (e.g., geometry), and strengths and weaknesses (e.g., properties of triangles).

[0109] input:

[0110] Information on study subjects, scope, strengths and weaknesses.

[0111] output:

[0112] Learning preference data entered into the terminal.

[0113] Step 2:

[0114] The terminal transmits the learning request data to the server.

[0115] Specific behavior:

[0116] The device uses the REST API to send the learning request data to the server.

[0117] input:

[0118] Learning preference data entered into the terminal.

[0119] output:

[0120] Learning preference data sent to the server.

[0121] Step 3:

[0122] The server analyzes the learning preference data.

[0123] Specific behavior:

[0124] The server uses a Python script to analyze the received data and identify the user's learning needs.

[0125] input:

[0126] Learning preference data sent to the server.

[0127] output:

[0128] User learning needs data as a result of analysis.

[0129] Step 4:

[0130] The server sends the analysis results to the generative AI.

[0131] Specific behavior:

[0132] The server sends the analysis results to the generative AI as a prompt.

[0133] input:

[0134] User learning needs data as a result of analysis.

[0135] output:

[0136] The prompt sent to the generative AI.

[0137] Example prompt sentence:

[0138] "Generate a problem set for Student A that includes basic problems about the properties of triangles, applied problems, and related problems from another area."

[0139] Step 5:

[0140] The generative AI generates a set of problem data and sends it back to the server.

[0141] Specific behavior:

[0142] The generative AI generates a set of problem data based on the prompt text and sends it back to the server.

[0143] input:

[0144] The prompt sent to the generative AI.

[0145] output:

[0146] Generated problem data set.

[0147] Step 6:

[0148] The server sends a set of question data to the terminal.

[0149] Specific behavior:

[0150] The server sends the generated question data set to the terminal in JSON format.

[0151] input:

[0152] Generated problem data set.

[0153] output:

[0154] A set of question data in JSON format sent to the device.

[0155] Step 7:

[0156] The terminal displays the problem data set to the user.

[0157] Specific behavior:

[0158] The terminal displays the received question data group to the user.

[0159] input:

[0160] The problem data set sent to the terminal.

[0161] output:

[0162] A set of problem data displayed on the user's terminal.

[0163] Step 8:

[0164] The user solves the problem and inputs the answer data into the terminal.

[0165] Specific behavior:

[0166] The user solves the problem on the terminal and inputs the answer data.

[0167] input:

[0168] User answer data.

[0169] output:

[0170] Answer data entered into the terminal.

[0171] Step 9:

[0172] The terminal sends the answer data to the server.

[0173] Specific behavior:

[0174] The device sends the answer data to the server via the REST API.

[0175] input:

[0176] Answer data entered into the terminal.

[0177] output:

[0178] The answer data sent to the server.

[0179] Step 10:

[0180] The server grades the answer data and generates feedback.

[0181] Specific behavior:

[0182] The server uses a Python script to grade the answer data and generate feedback.

[0183] input:

[0184] The answer data sent to the server.

[0185] output:

[0186] Generated feedback data.

[0187] Step 11:

[0188] The server sends the feedback to the device.

[0189] Specific behavior:

[0190] The server sends the feedback data to the terminal.

[0191] input:

[0192] Generated feedback data.

[0193] output:

[0194] Feedback data sent to the device.

[0195] Step 12:

[0196] The device displays the feedback to the user.

[0197] Specific behavior:

[0198] The terminal displays the received feedback to the user.

[0199] input:

[0200] Feedback data sent to the device.

[0201] output:

[0202] Feedback displayed on the user's device.

[0203] (Application example 1)

[0204] 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."

[0205] Conventional learning systems have had difficulty providing content optimized to the learning needs of each individual student. Furthermore, they lacked a means to provide immediate, appropriate feedback on answers, which resulted in insufficient improvement in students' learning effectiveness.

[0206] 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.

[0207] In this invention, the server includes a terminal for inputting desired learning data, a means for analyzing data received from the terminal, a means for transmitting problem sets received from the generative AI to the terminal, a means for a user to input answers and transmit the answers to the server, a means for the server to grade the answer data received and generate feedback, and a means for transmitting the generated feedback to the terminal, thereby making it possible to provide problem sets optimized for the learning needs of each student and provide immediate feedback on their answers.

[0208] "Study preference data" is information such as the subjects the user wants to study, the scope of study, areas of strength and weakness, etc.

[0209] A "terminal" is a device that allows a user to input desired study data and answers and transmit them to a server.

[0210] A "server" is a device that analyzes data received from a terminal, sends instructions to the generative AI, and transmits the generated data to the terminal.

[0211] "Generative AI" is artificial intelligence that generates individually optimized problem sets based on data received from a server.

[0212] A "problem set" is a set of practice questions and learning materials provided to users that are generated by generative AI based on desired learning data.

[0213] "Answer data" is data that includes the answers that a user gives to a question set.

[0214] "Feedback" is information including the results of scoring the user's answers, explanations, and areas for improvement.

[0215] The "display means" is a function for displaying the generated problem set and feedback on the user terminal.

[0216] "Means of transmission" refers to the function of transmitting data generated by the generative AI and data from the server to the user's terminal.

[0217] This invention is a system that combines terminals, servers, and generative AI to provide problem sets optimized for the learning needs of each student. The elements and specific steps for realizing this system are described below.

[0218] Overall system overview

[0219] The system consists of a device used by the user (e.g., a smartphone), a server, and a generative AI. The user inputs the data they wish to learn through the device, which is then sent to the generative AI via the server. The generative AI generates an individually optimized problem set based on the received data, which is then sent back to the device via the server. Finally, the user can solve the customized problem set on their device.

[0220] Device behavior

[0221] The user operates the terminal to input their desired study data. Specifically, they input the subject they want to study (e.g., mathematics), the range of study (e.g., geometry), and their strengths and weaknesses. The terminal then sends this information to the server.

[0222] Example: A student logs in to their smartphone and inputs that they are focusing on geometry in mathematics, especially that they are weak in the "properties of triangles." The device then sends this data to a server.

[0223] Server Operation

[0224] The server analyzes the learning request data received from the device. Based on the analysis results, it sends data to the generative AI requesting it to generate an optimized problem set. When the problem set is returned from the generative AI, it is sent to the user's device.

[0225] Example: The server analyzes the student's data and instructs the generative AI to create problems specific to "geometry triangles." The server receives the necessary problem set from the generative AI and sends it to the student's device.

[0226] How generative AI works

[0227] The generative AI generates an appropriate problem set based on the learning preference data received from the server and the analysis results. The generated problems are adjusted according to the user's strengths and weaknesses and learning progress.

[0228] Example: A generative AI generates a balanced set of problems for a student, including basic problems on the "properties of triangles," applied problems, and problems from other areas, and sends them back to the server.

[0229] View and answer problem sets

[0230] The terminal receives the problem set from the server and displays it to the user. The user solves the problem and inputs the answer. The terminal also sends the answer data to the server.

[0231] Example: A student solves a customized set of problems displayed on their smartphone, enters their answers, and sends them to a server.

[0232] Providing Feedback

[0233] The server automatically scores the received answer data and generates feedback, which is then sent back to the user's device and displayed to the user.

[0234] Example: The server grades the student's answers and generates feedback such as "This is the correct answer" or "This is the wrong answer." This feedback is sent to the student's device and displayed.

[0235] Hardware and software used

[0236] Device: Smartphone

[0237] Server: A server with data analysis and transmission / reception functions

[0238] Generative AI: Artificial intelligence that generates problem sets based on user learning data

[0239] Software libraries: requests (for sending and receiving data), framework for displaying user interfaces

[0240] Prompt Sentence Examples

[0241] Here is the user data:

[0242] Subject: Mathematics

[0243] Range: Geometry

[0244] Weakness: Triangular nature

[0245] Based on this data, please suggest study materials:

[0246] basic problems

[0247] Applied Problems

[0248] Video lectures

[0249] Additional questions based on feedback

[0250] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0251] Step 1:

[0252] The user operates the device to input desired study data. The user inputs the subject they wish to study, the range of study, and areas of strength and weakness, and sends this data from the device to the server. Specifically, the user enters the subject (mathematics), range of study (geometry), and areas of strength and weakness (e.g., "properties of triangles") into the smartphone input form, and then presses the send button.

[0253] Input: Study preferences (subjects, scope, areas of strength and weakness)

[0254] Output: Learning preference data sent to the server

[0255] Step 2:

[0256] The server analyzes the learning request data received from the device. Here, the data is formatted and preprocessed. As a result of the analysis, the learning needs become clear and the data to be passed to the generative AI is determined.

[0257] Input: Study Desired Data

[0258] Output: Analysis results (learning needs)

[0259] Step 3:

[0260] The server sends data to the generative AI to request it to generate an optimized problem set based on the analysis results. The generative AI then receives the analysis results and begins the process of generating a problem set.

[0261] Input: Analysis results

[0262] Output: Instruction data for generative AI

[0263] Step 4:

[0264] Based on the analysis results, the generative AI generates individually optimized problem sets, using prompts to generate appropriate problem sets (basic problems, applied problems, video lectures, additional problems, etc.).

[0265] Input: Analysis results, prompt text

[0266] Output: Optimized problem set

[0267] Step 5:

[0268] The server sends the problem set received from the generative AI to the device, allowing the user to receive the problem set on their smartphone.

[0269] Input: Optimized problem set

[0270] Output: Data sent to the terminal

[0271] Step 6:

[0272] The device displays the received problem set to the user, who then solves the problem and enters the answer. Specifically, the problem is displayed on the smartphone screen, and the user enters the answer in an input form.

[0273] Input: Data to send to the terminal

[0274] Output: The problem set that is displayed to the user

[0275] Step 7:

[0276] The user inputs the answer and sends the answer data from the terminal to the server, where it is ready to be analyzed and scored.

[0277] Input: User's answer data

[0278] Output: Answer data sent to the server

[0279] Step 8:

[0280] The server scores the received answer data and generates feedback. Based on the scoring results, it determines whether the answer is correct or incorrect and generates useful feedback.

[0281] Input: Answer data

[0282] Output: Generated feedback

[0283] Step 9:

[0284] The server sends the generated feedback to the terminal, allowing the user to receive the feedback immediately.

[0285] Input: Generated feedback

[0286] Output: Data sent to the terminal

[0287] Step 10:

[0288] The device displays the received feedback to the user, who can then check their own answers and use the feedback to improve their future learning.

[0289] Input: Data to send to the terminal

[0290] Output: Feedback that is displayed to the user

[0291] 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.

[0292] The present invention is a system that combines a terminal, a server, a generative AI, and an emotion engine that recognizes the user's emotions to provide problem sets optimized for each student's learning needs and emotional state. A specific embodiment of this system is shown below.

[0293] 1. Overview of the entire system

[0294] This system consists of a device used by the user (e.g., a tablet device), a server, a generative AI, and an emotion engine. When a user inputs the data they wish to learn through the device, the emotion engine recognizes the user's emotional data, and this data is sent to the generative AI via the server. Based on the received data, the generative AI generates an individually optimized problem set, which is then sent to the device via the server again. Ultimately, the user can solve a customized problem set on the device that also takes into account their emotional state.

[0295] 2. User terminal operation

[0296] The user operates the device to input their desired study data. Specifically, they input the subject they want to study (e.g., mathematics), the range of subjects (e.g., geometry), and their strengths and weaknesses. The device's built-in emotion engine also uses a camera and microphone to recognize emotion data from the user's facial expressions and voice. The device then sends this information to the server.

[0297] Example: Student A logs in to a tablet device and inputs that he / she is focusing on mathematics geometry, especially the "properties of triangles," and is weak in this field. The emotion engine analyzes Student A's facial expressions and recognizes signs of stress. The device sends the learning preference data and emotion data to the server.

[0298] 3. Server Operation

[0299] The server analyzes the learning preference data and emotional data received from the device. Based on the analysis results, it prepares data to request the generative AI to generate a customized problem set and sends this to the generative AI. The emotional data is used as additional information to adjust the difficulty and type of problems.

[0300] Example: The server analyzes Student A's data and instructs the generative AI to create problems specific to "geometry triangles." It also adjusts the difficulty of the problems appropriately based on emotional data to reduce stress. The server receives the necessary problem set from the generative AI and sends it to Student A's device.

[0301] 4. How generative AI works

[0302] The generative AI generates an appropriate set of problems based on the learning preference and emotional data received from the server. The problems are adjusted based on the user's strengths and weaknesses, learning progress, and emotional state.

[0303] Example: A generative AI generates a balanced set of problems for Student A, including basic problems on the "properties of triangles," applied problems, and problems from other areas, and sends them back to the server. Based on stress data, the initial problems are set relatively easy.

[0304] 5. Viewing and answering problem sets

[0305] The terminal receives the problem set from the server and displays it to the user. The user solves the problem and inputs the answer. The input answer is sent from the terminal to the server.

[0306] Example: Student A solves a customized problem set displayed on a tablet device. When he enters his answers, they are sent to the server.

[0307] 6. Providing Feedback

[0308] The server automatically scores the received answer data and generates feedback. The generated feedback is then sent back to the user's device and displayed to the user. The emotion engine then analyzes the user's response and reflects it in future learning plans.

[0309] Example: The server grades Student A's answers and generates feedback such as "This is the correct answer" or "This is incorrect." The emotion engine also analyzes Student A's facial expressions when receiving the feedback and reflects this in the next learning session. This feedback is sent to Student A's device and displayed.

[0310] The above-described embodiment allows students (users) to receive a learning experience optimized for their needs and emotional state, thereby enabling efficient and effective learning, improving academic ability, and reducing psychological stress.

[0311] The processing flow will be explained below.

[0312] Step 1:

[0313] The user starts the application on the device and enters the user ID and password on the login screen. The device sends this login information to the server.

[0314] Step 2:

[0315] The server receives the login information and authenticates the user by checking the database. If authentication is successful, the server retrieves the user's past learning history data from the database and sends it to the terminal.

[0316] Step 3:

[0317] The device displays the received learning history data and prompts the user to enter their desired learning data. The user enters the subjects they wish to study, the scope of study, their strengths and weaknesses, etc. The emotion engine also uses a camera and microphone to recognize emotional data from the user's facial expressions and voice. The device then sends this data to the server.

[0318] Step 4:

[0319] The server receives the learning preference data and emotion data, analyzes it in combination with existing learning history data, and prepares data to request the generative AI to generate a customized problem set based on the analysis results, and sends this data to the generative AI.

[0320] Step 5:

[0321] The generative AI generates individually optimized problem sets based on the data received from the server, and the generated problem sets are sent back to the server.

[0322] Step 6:

[0323] The server receives the problem set returned by the generative AI and sends it to the user's device, where the user receives a customized problem set that takes into account their emotional state.

[0324] Step 7:

[0325] The terminal displays the received problem set to the user. The user solves the displayed problem and inputs the answer. The input answer is sent from the terminal to the server.

[0326] Step 8:

[0327] The server analyzes the answer data received from the user and automatically scores them. It generates the scoring results and feedback and sends them to the user's device. The emotion engine also analyzes the user's reaction to the feedback and reflects that data in future study plans.

[0328] Step 9:

[0329] The device displays the feedback received from the server to the user. The user checks the feedback and plans their next learning. The emotion engine analyzes the user's reaction and updates the emotion data as necessary.

[0330] Example 2

[0331] 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."

[0332] Conventional learning support systems generate problem sets based solely on the user's learning preferences, which does not take into account the user's emotional state, resulting in poor learning outcomes. Furthermore, feedback is not provided in real time, making it difficult to maintain the user's motivation. These issues must be resolved to improve the user's learning experience.

[0333] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0334] In this invention, the server includes a means for analyzing learning preference data and emotional data, a means for cooperating with a generative AI that generates individually optimized problem sets, and a means for receiving and scoring the user's answer data and generating feedback. This makes it possible to provide a customized problem set that takes the user's emotional state into consideration, and improve the user's learning effectiveness and motivation through real-time feedback.

[0335] "Study preference data" is data that indicates the user's learning preferences, such as the subjects and scope they wish to study, and their strengths and weaknesses.

[0336] "Emotion data" is data that represents the user's emotional state, such as stress, joy, excitement, or other psychological state.

[0337] A "terminal" is a device through which a user inputs learning preference data and emotion data, and specifically refers to a tablet terminal, smartphone, PC, etc.

[0338] The "server" is a computer system that receives and analyzes data sent from the device, and works in conjunction with the generative AI and the device to perform various learning support processes.

[0339] "Generative AI" is an artificial intelligence system that generates individually optimized problem sets based on learning preference data and emotional data received from a server.

[0340] A "problem set" refers to multiple learning problems presented to the user, generated by generative AI based on the user's learning preferences and emotional data.

[0341] "Feedback" is information that the server uses to grade the user's answer data and inform the user whether the answer was correct or not, and what improvements need to be made.

[0342] The present invention is a system that combines a terminal, a server, a generative AI, and an emotion engine that recognizes the user's emotions to provide problem sets optimized for each student's learning needs and emotional state. A specific embodiment of this system is shown below.

[0343] Overall system overview

[0344] This system consists of a device used by the user (e.g., a tablet device), a server, a generative AI, and an emotion engine. When a user inputs the data they wish to learn through the device, the emotion engine recognizes the user's emotional data, and this data is sent to the generative AI via the server. Based on the received data, the generative AI generates an individually optimized problem set, which is then sent to the device via the server again. Ultimately, the user can solve a customized problem set on the device that also takes into account their emotional state.

[0345] User terminal operation

[0346] The user operates the device to input their desired study data. Specifically, they input the subject they want to study (e.g., mathematics), the range of subjects (e.g., geometry), and their strengths and weaknesses. The device's built-in emotion engine also uses a camera and microphone to recognize emotion data from the user's facial expressions and voice. The device then sends this information to the server.

[0347] Examples:

[0348] Student A logs in to a tablet device and inputs that he / she is focusing on mathematics geometry, especially the "properties of triangles," and is weak in this field. The emotion engine analyzes Student A's facial expressions and recognizes signs of stress. The device then sends the learning preference data and emotion data to the server.

[0349] Prompt statement:

[0350] "I'm eager to learn about geometry, but I just can't understand the properties of triangles. Emotionally, I'm feeling a bit stressed."

[0351] Server Operation

[0352] The server analyzes the learning preference data and emotional data received from the device. Based on the analysis results, it prepares data to request the generative AI to generate a customized problem set and sends this to the generative AI. The emotional data is used as additional information to adjust the difficulty and type of problems.

[0353] Examples:

[0354] The server analyzes Student A's data and instructs the generative AI to create problems specific to "geometric triangles." It also adjusts the difficulty of the problems appropriately based on emotional data to reduce stress. The server receives the necessary problem set from the generative AI and sends it to Student A's device.

[0355] How generative AI works

[0356] The generative AI generates an appropriate set of problems based on the learning preference and emotional data received from the server. The problems are adjusted based on the user's strengths and weaknesses, learning progress, and emotional state.

[0357] Examples:

[0358] The generative AI generates a balanced set of problems for Student A, including basic problems on the "properties of triangles," applied problems, and problems from other areas, and sends it back to the server. Based on the stress data, the initial problems are set relatively easy.

[0359] View and answer problem sets

[0360] The terminal receives the problem set from the server and displays it to the user. The user solves the problem and inputs the answer. The input answer is sent from the terminal to the server.

[0361] Examples:

[0362] Student A solves a customized problem set displayed on a tablet device. When he enters his answers, they are sent to the server.

[0363] Providing Feedback

[0364] The server automatically scores the received answer data and generates feedback. The generated feedback is then sent back to the user's device and displayed to the user. The emotion engine then analyzes the user's response and reflects it in future learning plans.

[0365] Examples:

[0366] The server grades Student A's answers and generates feedback such as "This is the correct answer" or "This is incorrect." The emotion engine also analyzes Student A's facial expressions when receiving the feedback and reflects this in the next learning session. This feedback is sent to Student A's device and displayed.

[0367] The above-described embodiment allows students (users) to receive a learning experience optimized for their needs and emotional state, thereby enabling efficient and effective learning, improving academic ability, and reducing psychological stress.

[0368] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0369] Step 1:

[0370] The user operates the terminal and inputs their desired study data. Specifically, the user inputs the subjects, scope, and areas of strength and weakness they wish to study, which then become the input data for the terminal. The input data is sent to the computer system as "study preference data."

[0371] Specific behavior:

[0372] Student A types "math," "geometry," and "properties of triangles" into his tablet.

[0373] input:

[0374] Information about the subjects you want to study, the scope, and your strengths and weaknesses

[0375] output:

[0376] Learning preference data

[0377] Step 2:

[0378] The device uses an emotion engine to acquire emotion data. The camera and microphone are used to capture the user's facial expressions and voice in real time, which the emotion engine then analyzes. The analysis results become "emotion data."

[0379] Specific behavior:

[0380] The camera on the tablet device captures Student A's facial expression, and "stress" is recognized through facial analysis.

[0381] input:

[0382] User's facial expressions and voice

[0383] output:

[0384] Emotional Data

[0385] Step 3:

[0386] The device sends the learning preference data and emotion data to the server, using the HTTPS protocol to ensure data security.

[0387] Specific behavior:

[0388] The tablet device sends data including "mathematics," "geometry," "weakness in the properties of triangles," and "stress" to the server.

[0389] input:

[0390] Learning preference data, emotion data

[0391] output:

[0392] Data sent to the server

[0393] Step 4:

[0394] The server analyzes the training data and emotion data. It uses a database and shell scripts to perform the appropriate analysis. The analysis results become the input data for the next step.

[0395] Specific behavior:

[0396] The server identifies high learning needs and "stress" regarding "geometry" and "properties of triangles."

[0397] input:

[0398] Learning preference data, emotion data

[0399] output:

[0400] Analysis results

[0401] Step 5:

[0402] The server requests the generative AI to generate a problem set based on the analysis results, and sends an API request to the generative AI to generate the necessary data.

[0403] Specific behavior:

[0404] The server requests the generative AI to generate a problem set that corresponds to "geometry," "properties of triangles," and "stress level."

[0405] input:

[0406] Analysis results

[0407] output:

[0408] Data sent to generative AI

[0409] Step 6:

[0410] The generative AI generates a problem set based on the received data. It uses a generative AI model to generate problems based on a pre-trained dataset and sends them back to the server.

[0411] Specific behavior:

[0412] The generative AI creates balanced problems related to the "properties of triangles" and sends them back to the server.

[0413] input:

[0414] Generation request data

[0415] output:

[0416] Generated problem set

[0417] Step 7:

[0418] The server sends the generated problem set to the terminal, again using the HTTPS protocol.

[0419] Specific behavior:

[0420] The server sends a set of problems about the properties of triangles to Student A's tablet device.

[0421] input:

[0422] Generated problem set

[0423] output:

[0424] Problem set sent to device

[0425] Step 8:

[0426] The terminal displays the received problem set to the user. The user interface has an intuitive and easy-to-understand design.

[0427] Specific behavior:

[0428] The tablet device displays a question about the properties of triangles to Student A.

[0429] input:

[0430] Problem set sent to device

[0431] output:

[0432] Issues seen by users

[0433] Step 9:

[0434] The user answers the questions on the device and sends them. The device then sends the answer data to the server.

[0435] Specific behavior:

[0436] Student A answers the question, enters the answer, and presses the send button.

[0437] input:

[0438] User Answer

[0439] output:

[0440] Answer data sent to the server

[0441] Step 10:

[0442] The server scores the received answer data and generates feedback using a scoring algorithm for high-precision analysis.

[0443] Specific behavior:

[0444] The server grades Student A's answers and generates feedback.

[0445] input:

[0446] Answer data

[0447] output:

[0448] Scoring results and feedback

[0449] Step 11:

[0450] The server generates feedback and sends it to the device, along with a comment that takes into account the emotion data.

[0451] Specific behavior:

[0452] The server sends feedback to Student A's device, such as "This is the correct answer" or "This is incorrect."

[0453] input:

[0454] feedback

[0455] output:

[0456] Feedback sent to device

[0457] Step 12:

[0458] The device displays the feedback to the user, who can then accept the feedback and enter additional comments.

[0459] Specific behavior:

[0460] The tablet device displays feedback to Student A such as "This is the correct answer" or "This is incorrect."

[0461] input:

[0462] Feedback sent to device

[0463] output:

[0464] Feedback displayed to the user

[0465] Step 13:

[0466] The device uses an emotion engine to analyze the user's reaction to the displayed feedback and reflects this in the next learning content.

[0467] Specific behavior:

[0468] The tablet camera reanalyzes Student A's facial expressions to confirm stress relief. This information is reflected in the next learning session.

[0469] input:

[0470] User Reactions

[0471] output:

[0472] Data to be reflected in the next study plan

[0473] (Application example 2)

[0474] 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."

[0475] Many modern learning systems can provide problem sets optimized for individual learning needs, but they rarely take the user's emotional state into consideration. As a result, learning effectiveness can decrease and motivation to learn can decline. Furthermore, even in physical stores, there is a lack of product recommendations that take the customer's emotional state into account, resulting in low customer satisfaction. Therefore, there is a need for the development of a system that analyzes users' emotions and provides appropriate learning and product recommendations based on their state.

[0476] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0477] In this invention, the server includes means for acquiring emotional data using an emotion engine that recognizes the emotional state of the user, means for the server to generate product suggestions based on the emotional data in accordance with the emotional state, and means for presenting the suggested product information to the user, thereby enabling an individually optimized learning experience and product suggestions tailored to the user's emotional state.

[0478] A "terminal" is an information processing device into which a user inputs desired study data and which displays problem sets and product information sent from a server.

[0479] The "server" is a central information processing device that analyzes data received from the terminal and works in conjunction with the generative AI and emotion engine to generate and transmit optimized problem sets and product proposals.

[0480] "Generative AI" is an artificial intelligence system that generates individually optimized problem sets and product suggestions based on data sent from a server.

[0481] An "emotion engine" is software or hardware that recognizes the user's emotional state from facial expressions, voice, etc., and acquires emotional data.

[0482] "Emotion data" is information indicating the user's emotional state obtained by the emotion engine.

[0483] "Product proposal" is data that the server generates based on emotion data and other information, proposing products suitable for the user.

[0484] A "problem set" is a series of problems generated by generative AI that are optimized for the user's learning needs.

[0485] The "display means" is a function or device for visually presenting the problem set and product suggestions received by the terminal to the user.

[0486] "User" refers to an individual who uses the system to input desired study data and view and operate the displayed problem sets and product information.

[0487] This invention is a system consisting of a terminal, a server, a generative AI, and an emotion engine, which provides problem sets and product suggestions optimized for the user's learning needs and emotional state.

[0488] 1. Overview of the entire system

[0489] This system consists of a device used by the user, a server that analyzes the data, a generative AI, and an emotion engine. The user inputs the learning data they wish to use into the device, and the emotion engine recognizes the user's emotional data. This data is sent to the generative AI via the server, and the generative AI uses the received data to generate individually optimized problem sets and product suggestions, which are then sent back to the device via the server.

[0490] 2. User terminal operation

[0491] The user operates the device to input their study preferences. Specifically, they input the subjects and scope they want to study, as well as their strengths and weaknesses. The device's built-in emotion engine also uses a camera and microphone to recognize emotional data from the user's facial expressions and voice. The device then sends this information to the server.

[0492] Specific examples

[0493] User A logs in to their smartphone and enters their desired learning data. User A's emotion engine then detects stress levels from their facial expressions. This data is then sent to the server.

[0494] 3. Server Operation

[0495] The server analyzes the learning preference data and emotional data received from the device. Based on the analysis results, it prepares data to request the generative AI to generate individually optimized problem sets and product proposals, and sends this to the generative AI. The emotional data is used as additional information to adjust the difficulty and type of problems or the content of product proposals.

[0496] Specific examples

[0497] The server analyzes User A's data and instructs the generative AI on questions specialized for specific learning topics. It also appropriately adjusts the difficulty of the suggested products and questions based on the emotional data. The problem sets and product suggestions received from the generative AI are then sent back to User A's device.

[0498] 4. How generative AI works

[0499] The generative AI generates appropriate problem sets and product suggestions based on the learning preference and emotional data sent from the server. The generated content is adjusted based on the user's strengths and weaknesses, learning progress, and even emotional state.

[0500] Specific examples

[0501] The generative AI generates a problem set related to the properties of triangles and product suggestions for relaxation items for User A. The generated content is sent to the device via the server.

[0502] 5. Display and suggest problem sets and product suggestions

[0503] The terminal receives the problem sets and product suggestions from the server and displays them to the user, who can then solve the problems and check the product suggestions.

[0504] Specific examples

[0505] User A solves a customized problem set displayed on his / her smartphone. At the same time, he / she checks the product suggestions displayed and selects the products he / she is interested in.

[0506] 6. Providing Feedback

[0507] The server scores and evaluates the received answer data and product selection information, and generates feedback. The generated feedback is then sent back to the user's device and displayed to the user. The emotion engine then analyzes the user's reactions again and reflects them in future study plans and product suggestions.

[0508] Specific examples

[0509] The server grades User A's answers and generates feedback such as "This is the correct answer" or "This is incorrect." Furthermore, the emotion engine analyzes User A's facial expressions when receiving the feedback and reflects this in the next learning session and product suggestions. This feedback is sent to User A's device and displayed.

[0510] Prompt Sentence Examples

[0511] "Please suggest the best relaxation products for customers who are feeling stressed."

[0512] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0513] Step 1:

[0514] The user operates the terminal to input the data they wish to learn, and emotional data is collected using a camera and microphone.

[0515] (Input) User's desired learning data (e.g., subject and scope) and emotional data (e.g., facial expressions and voice)

[0516] (Operation) The device allows the user to input the desired learning data, and the built-in emotion engine uses the camera and microphone to analyze the user's emotions and recognize the emotion data.

[0517] (Output) The learning target data and emotion data are sent from the terminal to the server.

[0518] Step 2:

[0519] The server analyzes the learning preference data and emotion data received from the terminal.

[0520] (Input) Learning preference data and emotion data sent from the device

[0521] (Operation) The server analyzes the learning preference data to identify the user's needs. Based on the emotion data, the server evaluates the user's emotional state.

[0522] (Output) Data based on the analysis results is sent to the generative AI.

[0523] Step 3:

[0524] Based on the data received from the server, the generative AI generates individually optimized problem sets and product suggestions.

[0525] (Input) Analysis data sent from the server

[0526] (Operation) Generative AI generates problem sets and product suggestions based on the user's learning needs and emotional state. The generative AI model is used to generate suggestions in response to a specific prompt (e.g., "Please suggest the best relaxation products for a customer who is feeling stressed.").

[0527] (Output) The generated problem set and product proposals are sent back to the server.

[0528] Step 4:

[0529] The server sends the problem sets and product suggestions received from the generative AI to the terminal.

[0530] (Input) Problem sets and product suggestions sent from generative AI

[0531] (Operation) The server organizes the received data and sends it to the terminal.

[0532] (Output) The problem set and product suggestions are sent to the terminal.

[0533] Step 5:

[0534] The terminal displays the transmitted problem set and product suggestions to the user.

[0535] (Input) Problem sets and product proposals sent from the server

[0536] (Operation) The data received by the terminal is displayed on the screen for visual display to the user.

[0537] (Output) The user can see the problem set and product suggestions.

[0538] Step 6:

[0539] The user solves the displayed problem set and enters the answers into the terminal, or checks and selects product suggestions.

[0540] (Input) User answers and product selection information

[0541] (Operation) The terminal collects the user's input data and sends it to the server.

[0542] (Output) Answer data and product selection information are sent from the terminal to the server.

[0543] Step 7:

[0544] The server scores the answers received, generates feedback, and analyzes the user's reactions using an emotion engine.

[0545] (Input) Answer data and emotion data sent from the device

[0546] (Operation) The server automatically scores the answer data and generates feedback. At the same time, the emotion engine analyzes the user's reactions and reflects them in future study plans and product suggestions.

[0547] (Output) The generated feedback and analysis results are sent to the terminal and displayed to the user.

[0548] Step 8:

[0549] Feedback from the server and the next learning plan are displayed on the device, allowing the user to proceed with their next learning or purchase.

[0550] (Input) Feedback sent from the server and next lesson plan information

[0551] (Operation) The device displays feedback and upcoming study plans to the user, allowing the user to prepare for the next study session.

[0552] (Output) The user is ready to learn or buy something next.

[0553] 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.

[0554] 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.

[0555] 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.

[0556] [Second embodiment]

[0557] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0558] 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.

[0559] 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).

[0560] 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.

[0561] 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.

[0562] 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).

[0563] 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.

[0564] 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.

[0565] 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.

[0566] 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.

[0567] 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.

[0568] 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."

[0569] The present invention is a system that combines a terminal, a server, and a generative AI to provide problem sets optimized for the learning needs of each student. A specific embodiment of this system is shown below.

[0570] 1. Overview of the entire system

[0571] This system consists of a device used by the user (e.g., a tablet device), a server, and a generative AI. The user inputs the data they wish to learn through the device, and the data is sent to the generative AI via the server. The generative AI generates an individually optimized problem set based on the received data, and sends it back to the device via the server. Finally, the user can solve the customized problem set on their device.

[0572] 2. User terminal operation

[0573] The user operates the device to input their desired study data. Specifically, they input the subject they want to study (e.g., mathematics), the range of study (e.g., geometry), and their strengths and weaknesses. The device then sends this information to the server.

[0574] Example: Student A logs in to a tablet device and inputs that he / she is weak in mathematics geometry, especially the "properties of triangles." The device sends this data to the server.

[0575] 3. Server Operation

[0576] The server analyzes the learning request data received from the device. Based on the analysis results, it sends data to the generative AI requesting it to generate an optimized problem set. When the problem set is returned from the generative AI, it is sent to the user's device.

[0577] Example: The server analyzes the data of Student A and instructs the generative AI to create problems specific to "geometry triangles." The server receives the necessary problem set from the generative AI and sends it to Student A's device.

[0578] 4. How generative AI works

[0579] The generative AI generates an appropriate problem set based on the learning preference data received from the server and the analysis results. The generated problems are adjusted according to the user's strengths and weaknesses and learning progress.

[0580] Example: A generative AI generates a balanced set of problems for Student A, including basic problems on the "properties of triangles," applied problems, and problems from other areas, and sends them back to the server.

[0581] 5. Viewing and answering problem sets

[0582] The terminal receives the problem set from the server and displays it to the user. The user solves the problem and inputs the answer. The terminal also sends the answer data to the server.

[0583] Example: Student A solves a customized problem set displayed on a tablet device. When he enters his answers, they are sent to the server.

[0584] 6. Providing Feedback

[0585] The server automatically scores the received answer data and generates feedback, which is then sent back to the user's device and displayed to the user.

[0586] Example: The server grades Student A's answers and generates feedback such as "This is the correct answer" or "This is incorrect." This feedback is sent to Student A's device and displayed.

[0587] The above-described embodiment allows students (users) to receive a learning experience optimized to their needs, thereby enabling them to study efficiently and effectively and improve their academic performance.

[0588] The processing flow will be explained below.

[0589] Step 1:

[0590] The user starts the application on the device and enters the user ID and password on the login screen. The device sends this login information to the server.

[0591] Step 2:

[0592] The server receives the login information and authenticates the user by checking the database. If authentication is successful, the server retrieves the user's past learning history data from the database and sends it to the terminal.

[0593] Step 3:

[0594] The device displays the received learning history data and prompts the user to enter desired learning data. The user enters the desired subjects, scope, strengths and weaknesses, etc. The device then sends this desired learning data to the server.

[0595] Step 4:

[0596] The server receives the learning preference data and analyzes it in combination with existing learning history data. Based on the analysis results, it prepares data to request the generative AI to generate a customized problem set, and sends it to the generative AI.

[0597] Step 5:

[0598] The generative AI generates individually optimized problem sets based on the data received from the server, and the generated problem sets are sent back to the server.

[0599] Step 6:

[0600] The server receives the problem set returned by the generative AI and sends it to the user's device, allowing the user to receive a customized problem set.

[0601] Step 7:

[0602] The terminal displays the received problem set to the user. The user solves the displayed problem and inputs the answer. The input answer is sent from the terminal to the server.

[0603] Step 8:

[0604] The server analyzes the answer data received from the user, automatically scores the answers, generates the scoring results and feedback, and sends them to the user's terminal.

[0605] Step 9:

[0606] The device displays the feedback received from the server to the user, who then checks the feedback and plans their next learning experience.

[0607] Example 1

[0608] 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."

[0609] The current educational system faces the challenge of providing learning materials optimized for each student's learning needs. A method is needed to generate appropriate problem sets based on each student's strengths and weaknesses and learning progress, and to provide them in a timely manner. It is also necessary to introduce a system that provides prompt and accurate feedback on answers.

[0610] 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.

[0611] In this invention, the server includes a means for analyzing the study data, a means for receiving question data sets from a generative artificial intelligence that generates individually optimized question data sets, and a means for scoring the user's answer data and generating feedback. This makes it possible to generate and provide an optimal question set based on the study data and analysis results, and to provide rapid feedback on the answers.

[0612] "Study preference data" refers to information such as the subjects, scope, and areas of strength and weakness that a user wishes to study.

[0613] "Device" refers to input and display devices such as tablet terminals and personal computers operated by users.

[0614] "Data processing device" refers to a server that analyzes input data and manages and transmits data and feedback from generative artificial intelligence.

[0615] "Generative artificial intelligence" refers to an AI model that generates individually optimized sets of problem data based on analysis results.

[0616] "Question data group" refers to multiple question sets generated by generative artificial intelligence and optimized to the user's learning needs.

[0617] "Feedback" refers to evaluation information such as whether the questions answered by the user are correct or incorrect, and advice.

[0618] This system is comprised of a device where users input their desired learning data, a data processing device (server) that analyzes the data to generate appropriate problem data sets and processes and manages the analysis results, and generative artificial intelligence. This system makes it possible to provide problem sets optimized for the user's learning needs and provide rapid feedback.

[0619] 1. User terminal configuration and operation

[0620] The device operated by the user can be a tablet or PC. The user inputs their desired study data through the device. Specifically, they input the subject they want to study (e.g., mathematics), the range of study (e.g., geometry), and their strengths and weaknesses.

[0621] Examples:

[0622] Student A logs in to the tablet device and enters that he or she is focusing on mathematics geometry, particularly the properties of triangles, which is something he or she is weak at.

[0623] 2. Server Configuration and Operation

[0624] The server analyzes the received learning data and sends the analysis results to the generative AI. The analysis is performed using Python scripts and a database management system. The server also plays a role in sending the problem data received from the generative AI to the user's device.

[0625] Examples:

[0626] The server analyzes Student A's data and identifies learning needs specific to "triangles in geometry." It then sends a prompt to the generative AI to "generate a set of problems related to the properties of triangles."

[0627] 3. Structure and operation of generative artificial intelligence

[0628] The generative AI generates a set of question data based on the analysis results. The generated questions are adjusted according to the user's strengths and weaknesses and learning progress. The generated set of question data is sent to the user's device via the server.

[0629] Examples:

[0630] The generative artificial intelligence generates a balanced set of problems for Student A, including basic problems on the "properties of triangles," applied problems, and problems from other related areas, and sends it back to the server.

[0631] Example prompt sentence:

[0632] "Generate a problem set for Student A that includes basic problems about the properties of triangles, applied problems, and related problems from another area."

[0633] 4. User answers and feedback

[0634] The user answers questions on their device and sends the data to the server, which then scores the answers and generates feedback, which is then sent back to the user's device and displayed to the user.

[0635] Examples:

[0636] When Student A solves the displayed problem and enters the answer, the device sends the answer data to the server. The server grades the answer and generates feedback such as "This is the correct answer" or "This is incorrect" and sends it to Student A's device.

[0637] In this way, the present invention allows users to receive an individually optimized learning experience, resulting in efficient and effective learning.

[0638] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0639] Step 1:

[0640] The user inputs the desired learning data into the terminal.

[0641] Specific behavior:

[0642] The user uses a tablet device or computer to input the subject being studied (e.g., mathematics), range of study (e.g., geometry), and strengths and weaknesses (e.g., properties of triangles).

[0643] input:

[0644] Information on study subjects, scope, strengths and weaknesses.

[0645] output:

[0646] Learning preference data entered into the terminal.

[0647] Step 2:

[0648] The terminal transmits the learning request data to the server.

[0649] Specific behavior:

[0650] The device uses the REST API to send the learning request data to the server.

[0651] input:

[0652] Learning preference data entered into the terminal.

[0653] output:

[0654] Learning preference data sent to the server.

[0655] Step 3:

[0656] The server analyzes the learning preference data.

[0657] Specific behavior:

[0658] The server uses a Python script to analyze the received data and identify the user's learning needs.

[0659] input:

[0660] Learning preference data sent to the server.

[0661] output:

[0662] User learning needs data as a result of analysis.

[0663] Step 4:

[0664] The server sends the analysis results to the generative AI.

[0665] Specific behavior:

[0666] The server sends the analysis results to the generative AI as a prompt.

[0667] input:

[0668] User learning needs data as a result of analysis.

[0669] output:

[0670] The prompt sent to the generative AI.

[0671] Example prompt sentence:

[0672] "Generate a problem set for Student A that includes basic problems about the properties of triangles, applied problems, and related problems from another area."

[0673] Step 5:

[0674] The generative AI generates a set of problem data and sends it back to the server.

[0675] Specific behavior:

[0676] The generative AI generates a set of problem data based on the prompt text and sends it back to the server.

[0677] input:

[0678] The prompt sent to the generative AI.

[0679] output:

[0680] Generated problem data set.

[0681] Step 6:

[0682] The server sends a set of question data to the terminal.

[0683] Specific behavior:

[0684] The server sends the generated question data set to the terminal in JSON format.

[0685] input:

[0686] Generated problem data set.

[0687] output:

[0688] A set of question data in JSON format sent to the device.

[0689] Step 7:

[0690] The terminal displays the problem data set to the user.

[0691] Specific behavior:

[0692] The terminal displays the received question data group to the user.

[0693] input:

[0694] The problem data set sent to the terminal.

[0695] output:

[0696] A set of problem data displayed on the user's terminal.

[0697] Step 8:

[0698] The user solves the problem and inputs the answer data into the terminal.

[0699] Specific behavior:

[0700] The user solves the problem on the terminal and inputs the answer data.

[0701] input:

[0702] User answer data.

[0703] output:

[0704] Answer data entered into the terminal.

[0705] Step 9:

[0706] The terminal sends the answer data to the server.

[0707] Specific behavior:

[0708] The device sends the answer data to the server via the REST API.

[0709] input:

[0710] Answer data entered into the terminal.

[0711] output:

[0712] The answer data sent to the server.

[0713] Step 10:

[0714] The server grades the answer data and generates feedback.

[0715] Specific behavior:

[0716] The server uses a Python script to grade the answer data and generate feedback.

[0717] input:

[0718] The answer data sent to the server.

[0719] output:

[0720] Generated feedback data.

[0721] Step 11:

[0722] The server sends the feedback to the device.

[0723] Specific behavior:

[0724] The server sends the feedback data to the terminal.

[0725] input:

[0726] Generated feedback data.

[0727] output:

[0728] Feedback data sent to the device.

[0729] Step 12:

[0730] The device displays the feedback to the user.

[0731] Specific behavior:

[0732] The terminal displays the received feedback to the user.

[0733] input:

[0734] Feedback data sent to the device.

[0735] output:

[0736] Feedback displayed on the user's device.

[0737] (Application example 1)

[0738] 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."

[0739] Conventional learning systems have had difficulty providing content optimized to the learning needs of each individual student. Furthermore, they lacked a means to provide immediate, appropriate feedback on answers, which resulted in insufficient improvement in students' learning effectiveness.

[0740] 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.

[0741] In this invention, the server includes a terminal for inputting desired learning data, a means for analyzing data received from the terminal, a means for transmitting problem sets received from the generative AI to the terminal, a means for a user to input answers and transmit the answers to the server, a means for the server to grade the answer data received and generate feedback, and a means for transmitting the generated feedback to the terminal, thereby making it possible to provide problem sets optimized for the learning needs of each student and provide immediate feedback on their answers.

[0742] "Study preference data" is information such as the subjects the user wants to study, the scope of study, areas of strength and weakness, etc.

[0743] A "terminal" is a device that allows a user to input desired study data and answers and transmit them to a server.

[0744] A "server" is a device that analyzes data received from a terminal, sends instructions to the generative AI, and transmits the generated data to the terminal.

[0745] "Generative AI" is artificial intelligence that generates individually optimized problem sets based on data received from a server.

[0746] A "problem set" is a set of practice questions and learning materials provided to users that are generated by generative AI based on desired learning data.

[0747] "Answer data" is data that includes the answers that a user gives to a question set.

[0748] "Feedback" is information including the results of scoring the user's answers, explanations, and areas for improvement.

[0749] The "display means" is a function for displaying the generated problem set and feedback on the user terminal.

[0750] "Means of transmission" refers to the function of transmitting data generated by the generative AI and data from the server to the user's terminal.

[0751] This invention is a system that combines terminals, servers, and generative AI to provide problem sets optimized for the learning needs of each student. The elements and specific steps for realizing this system are described below.

[0752] Overall system overview

[0753] The system consists of a device used by the user (e.g., a smartphone), a server, and a generative AI. The user inputs the data they wish to learn through the device, which is then sent to the generative AI via the server. The generative AI generates an individually optimized problem set based on the received data, which is then sent back to the device via the server. Finally, the user can solve the customized problem set on their device.

[0754] Device behavior

[0755] The user operates the terminal to input their desired study data. Specifically, they input the subject they want to study (e.g., mathematics), the range of study (e.g., geometry), and their strengths and weaknesses. The terminal then sends this information to the server.

[0756] Example: A student logs in to their smartphone and inputs that they are focusing on geometry in mathematics, especially that they are weak in the "properties of triangles." The device then sends this data to a server.

[0757] Server Operation

[0758] The server analyzes the learning request data received from the device. Based on the analysis results, it sends data to the generative AI requesting it to generate an optimized problem set. When the problem set is returned from the generative AI, it is sent to the user's device.

[0759] Example: The server analyzes the student's data and instructs the generative AI to create problems specific to "geometry triangles." The server receives the necessary problem set from the generative AI and sends it to the student's device.

[0760] How generative AI works

[0761] The generative AI generates an appropriate problem set based on the learning preference data received from the server and the analysis results. The generated problems are adjusted according to the user's strengths and weaknesses and learning progress.

[0762] Example: A generative AI generates a balanced set of problems for a student, including basic problems on the "properties of triangles," applied problems, and problems from other areas, and sends them back to the server.

[0763] View and answer problem sets

[0764] The terminal receives the problem set from the server and displays it to the user. The user solves the problem and inputs the answer. The terminal also sends the answer data to the server.

[0765] Example: A student solves a customized set of problems displayed on their smartphone, enters their answers, and sends them to a server.

[0766] Providing Feedback

[0767] The server automatically scores the received answer data and generates feedback, which is then sent back to the user's device and displayed to the user.

[0768] Example: The server grades the student's answers and generates feedback such as "This is the correct answer" or "This is the wrong answer." This feedback is sent to the student's device and displayed.

[0769] Hardware and software used

[0770] Device: Smartphone

[0771] Server: A server with data analysis and transmission / reception functions

[0772] Generative AI: Artificial intelligence that generates problem sets based on user learning data

[0773] Software libraries: requests (for sending and receiving data), framework for displaying user interfaces

[0774] Prompt Sentence Examples

[0775] Here is the user data:

[0776] Subject: Mathematics

[0777] Range: Geometry

[0778] Weakness: Triangular nature

[0779] Based on this data, please suggest study materials:

[0780] basic problems

[0781] Applied Problems

[0782] Video lectures

[0783] Additional questions based on feedback

[0784] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0785] Step 1:

[0786] The user operates the device to input desired study data. The user inputs the subject they wish to study, the range of study, and areas of strength and weakness, and sends this data from the device to the server. Specifically, the user enters the subject (mathematics), range of study (geometry), and areas of strength and weakness (e.g., "properties of triangles") into the smartphone input form, and then presses the send button.

[0787] Input: Study preferences (subjects, scope, areas of strength and weakness)

[0788] Output: Learning preference data sent to the server

[0789] Step 2:

[0790] The server analyzes the learning request data received from the device. Here, the data is formatted and preprocessed. As a result of the analysis, the learning needs become clear and the data to be passed to the generative AI is determined.

[0791] Input: Study Desired Data

[0792] Output: Analysis results (learning needs)

[0793] Step 3:

[0794] The server sends data to the generative AI to request it to generate an optimized problem set based on the analysis results. The generative AI then receives the analysis results and begins the process of generating a problem set.

[0795] Input: Analysis results

[0796] Output: Instruction data for generative AI

[0797] Step 4:

[0798] Based on the analysis results, the generative AI generates individually optimized problem sets, using prompts to generate appropriate problem sets (basic problems, applied problems, video lectures, additional problems, etc.).

[0799] Input: Analysis results, prompt text

[0800] Output: Optimized problem set

[0801] Step 5:

[0802] The server sends the problem set received from the generative AI to the device, allowing the user to receive the problem set on their smartphone.

[0803] Input: Optimized problem set

[0804] Output: Data sent to the terminal

[0805] Step 6:

[0806] The device displays the received problem set to the user, who then solves the problem and enters the answer. Specifically, the problem is displayed on the smartphone screen, and the user enters the answer in an input form.

[0807] Input: Data to send to the terminal

[0808] Output: The problem set that is displayed to the user

[0809] Step 7:

[0810] The user inputs the answer and sends the answer data from the terminal to the server, where it is ready to be analyzed and scored.

[0811] Input: User's answer data

[0812] Output: Answer data sent to the server

[0813] Step 8:

[0814] The server scores the received answer data and generates feedback. Based on the scoring results, it determines whether the answer is correct or incorrect and generates useful feedback.

[0815] Input: Answer data

[0816] Output: Generated feedback

[0817] Step 9:

[0818] The server sends the generated feedback to the terminal, allowing the user to receive the feedback immediately.

[0819] Input: Generated feedback

[0820] Output: Data sent to the terminal

[0821] Step 10:

[0822] The device displays the received feedback to the user, who can then check their own answers and use the feedback to improve their future learning.

[0823] Input: Data to send to the terminal

[0824] Output: Feedback that is displayed to the user

[0825] 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.

[0826] The present invention is a system that combines a terminal, a server, a generative AI, and an emotion engine that recognizes the user's emotions to provide problem sets optimized for each student's learning needs and emotional state. A specific embodiment of this system is shown below.

[0827] 1. Overview of the entire system

[0828] This system consists of a device used by the user (e.g., a tablet device), a server, a generative AI, and an emotion engine. When a user inputs the data they wish to learn through the device, the emotion engine recognizes the user's emotional data, and this data is sent to the generative AI via the server. Based on the received data, the generative AI generates an individually optimized problem set, which is then sent to the device via the server again. Ultimately, the user can solve a customized problem set on the device that also takes into account their emotional state.

[0829] 2. User terminal operation

[0830] The user operates the device to input their desired study data. Specifically, they input the subject they want to study (e.g., mathematics), the range of subjects (e.g., geometry), and their strengths and weaknesses. The device's built-in emotion engine also uses a camera and microphone to recognize emotion data from the user's facial expressions and voice. The device then sends this information to the server.

[0831] Example: Student A logs in to a tablet device and inputs that he / she is focusing on mathematics geometry, especially the "properties of triangles," and is weak in this field. The emotion engine analyzes Student A's facial expressions and recognizes signs of stress. The device sends the learning preference data and emotion data to the server.

[0832] 3. Server Operation

[0833] The server analyzes the learning preference data and emotional data received from the device. Based on the analysis results, it prepares data to request the generative AI to generate a customized problem set and sends this to the generative AI. The emotional data is used as additional information to adjust the difficulty and type of problems.

[0834] Example: The server analyzes Student A's data and instructs the generative AI to create problems specific to "geometry triangles." It also adjusts the difficulty of the problems appropriately based on emotional data to reduce stress. The server receives the necessary problem set from the generative AI and sends it to Student A's device.

[0835] 4. How generative AI works

[0836] The generative AI generates an appropriate set of problems based on the learning preference and emotional data received from the server. The problems are adjusted based on the user's strengths and weaknesses, learning progress, and emotional state.

[0837] Example: A generative AI generates a balanced set of problems for Student A, including basic problems on the "properties of triangles," applied problems, and problems from other areas, and sends them back to the server. Based on stress data, the initial problems are set relatively easy.

[0838] 5. Viewing and answering problem sets

[0839] The terminal receives the problem set from the server and displays it to the user. The user solves the problem and inputs the answer. The input answer is sent from the terminal to the server.

[0840] Example: Student A solves a customized problem set displayed on a tablet device. When he enters his answers, they are sent to the server.

[0841] 6. Providing Feedback

[0842] The server automatically scores the received answer data and generates feedback. The generated feedback is then sent back to the user's device and displayed to the user. The emotion engine then analyzes the user's response and reflects it in future learning plans.

[0843] Example: The server grades Student A's answers and generates feedback such as "This is the correct answer" or "This is incorrect." The emotion engine also analyzes Student A's facial expressions when receiving the feedback and reflects this in the next learning session. This feedback is sent to Student A's device and displayed.

[0844] The above-described embodiment allows students (users) to receive a learning experience optimized for their needs and emotional state, thereby enabling efficient and effective learning, improving academic ability, and reducing psychological stress.

[0845] The processing flow will be explained below.

[0846] Step 1:

[0847] The user starts the application on the device and enters the user ID and password on the login screen. The device sends this login information to the server.

[0848] Step 2:

[0849] The server receives the login information and authenticates the user by checking the database. If authentication is successful, the server retrieves the user's past learning history data from the database and sends it to the terminal.

[0850] Step 3:

[0851] The device displays the received learning history data and prompts the user to enter their desired learning data. The user enters the subjects they wish to study, the scope of study, their strengths and weaknesses, etc. The emotion engine also uses a camera and microphone to recognize emotional data from the user's facial expressions and voice. The device then sends this data to the server.

[0852] Step 4:

[0853] The server receives the learning preference data and emotion data, analyzes it in combination with existing learning history data, and prepares data to request the generative AI to generate a customized problem set based on the analysis results, and sends this data to the generative AI.

[0854] Step 5:

[0855] The generative AI generates individually optimized problem sets based on the data received from the server, and the generated problem sets are sent back to the server.

[0856] Step 6:

[0857] The server receives the problem set returned by the generative AI and sends it to the user's device, where the user receives a customized problem set that takes into account their emotional state.

[0858] Step 7:

[0859] The terminal displays the received problem set to the user. The user solves the displayed problem and inputs the answer. The input answer is sent from the terminal to the server.

[0860] Step 8:

[0861] The server analyzes the answer data received from the user and automatically scores them. It generates the scoring results and feedback and sends them to the user's device. The emotion engine also analyzes the user's reaction to the feedback and reflects that data in future study plans.

[0862] Step 9:

[0863] The device displays the feedback received from the server to the user. The user checks the feedback and plans their next learning. The emotion engine analyzes the user's reaction and updates the emotion data as necessary.

[0864] Example 2

[0865] 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."

[0866] Conventional learning support systems generate problem sets based solely on the user's learning preferences, which does not take into account the user's emotional state, resulting in poor learning outcomes. Furthermore, feedback is not provided in real time, making it difficult to maintain the user's motivation. These issues must be resolved to improve the user's learning experience.

[0867] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0868] In this invention, the server includes a means for analyzing learning preference data and emotional data, a means for cooperating with a generative AI that generates individually optimized problem sets, and a means for receiving and scoring the user's answer data and generating feedback. This makes it possible to provide a customized problem set that takes the user's emotional state into consideration, and improve the user's learning effectiveness and motivation through real-time feedback.

[0869] "Study preference data" is data that indicates the user's learning preferences, such as the subjects and scope they wish to study, and their strengths and weaknesses.

[0870] "Emotion data" is data that represents the user's emotional state, such as stress, joy, excitement, or other psychological state.

[0871] A "terminal" is a device through which a user inputs learning preference data and emotion data, and specifically refers to a tablet terminal, smartphone, PC, etc.

[0872] The "server" is a computer system that receives and analyzes data sent from the device, and works in conjunction with the generative AI and the device to perform various learning support processes.

[0873] "Generative AI" is an artificial intelligence system that generates individually optimized problem sets based on learning preference data and emotional data received from a server.

[0874] A "problem set" refers to multiple learning problems presented to the user, generated by generative AI based on the user's learning preferences and emotional data.

[0875] "Feedback" is information that the server uses to grade the user's answer data and inform the user whether the answer was correct or not, and what improvements need to be made.

[0876] The present invention is a system that combines a terminal, a server, a generative AI, and an emotion engine that recognizes the user's emotions to provide problem sets optimized for each student's learning needs and emotional state. A specific embodiment of this system is shown below.

[0877] Overall system overview

[0878] This system consists of a device used by the user (e.g., a tablet device), a server, a generative AI, and an emotion engine. When a user inputs the data they wish to learn through the device, the emotion engine recognizes the user's emotional data, and this data is sent to the generative AI via the server. Based on the received data, the generative AI generates an individually optimized problem set, which is then sent to the device via the server again. Ultimately, the user can solve a customized problem set on the device that also takes into account their emotional state.

[0879] User terminal operation

[0880] The user operates the device to input their desired study data. Specifically, they input the subject they want to study (e.g., mathematics), the range of subjects (e.g., geometry), and their strengths and weaknesses. The device's built-in emotion engine also uses a camera and microphone to recognize emotion data from the user's facial expressions and voice. The device then sends this information to the server.

[0881] Examples:

[0882] Student A logs in to a tablet device and inputs that he / she is focusing on mathematics geometry, especially the "properties of triangles," and is weak in this field. The emotion engine analyzes Student A's facial expressions and recognizes signs of stress. The device then sends the learning preference data and emotion data to the server.

[0883] Prompt statement:

[0884] "I'm eager to learn about geometry, but I just can't understand the properties of triangles. Emotionally, I'm feeling a bit stressed."

[0885] Server Operation

[0886] The server analyzes the learning preference data and emotional data received from the device. Based on the analysis results, it prepares data to request the generative AI to generate a customized problem set and sends this to the generative AI. The emotional data is used as additional information to adjust the difficulty and type of problems.

[0887] Examples:

[0888] The server analyzes Student A's data and instructs the generative AI to create problems specific to "geometric triangles." It also adjusts the difficulty of the problems appropriately based on emotional data to reduce stress. The server receives the necessary problem set from the generative AI and sends it to Student A's device.

[0889] How generative AI works

[0890] The generative AI generates an appropriate set of problems based on the learning preference and emotional data received from the server. The problems are adjusted based on the user's strengths and weaknesses, learning progress, and emotional state.

[0891] Examples:

[0892] The generative AI generates a balanced set of problems for Student A, including basic problems on the "properties of triangles," applied problems, and problems from other areas, and sends it back to the server. Based on the stress data, the initial problems are set relatively easy.

[0893] View and answer problem sets

[0894] The terminal receives the problem set from the server and displays it to the user. The user solves the problem and inputs the answer. The input answer is sent from the terminal to the server.

[0895] Examples:

[0896] Student A solves a customized problem set displayed on a tablet device. When he enters his answers, they are sent to the server.

[0897] Providing Feedback

[0898] The server automatically scores the received answer data and generates feedback. The generated feedback is then sent back to the user's device and displayed to the user. The emotion engine then analyzes the user's response and reflects it in future learning plans.

[0899] Examples:

[0900] The server grades Student A's answers and generates feedback such as "This is the correct answer" or "This is incorrect." The emotion engine also analyzes Student A's facial expressions when receiving the feedback and reflects this in the next learning session. This feedback is sent to Student A's device and displayed.

[0901] The above-described embodiment allows students (users) to receive a learning experience optimized for their needs and emotional state, thereby enabling efficient and effective learning, improving academic ability, and reducing psychological stress.

[0902] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0903] Step 1:

[0904] The user operates the terminal and inputs their desired study data. Specifically, the user inputs the subjects, scope, and areas of strength and weakness they wish to study, which then become the input data for the terminal. The input data is sent to the computer system as "study preference data."

[0905] Specific behavior:

[0906] Student A types "math," "geometry," and "properties of triangles" into his tablet.

[0907] input:

[0908] Information about the subjects you want to study, the scope, and your strengths and weaknesses

[0909] output:

[0910] Learning preference data

[0911] Step 2:

[0912] The device uses an emotion engine to acquire emotion data. The camera and microphone are used to capture the user's facial expressions and voice in real time, which the emotion engine then analyzes. The analysis results become "emotion data."

[0913] Specific behavior:

[0914] The camera on the tablet device captures Student A's facial expression, and "stress" is recognized through facial analysis.

[0915] input:

[0916] User's facial expressions and voice

[0917] output:

[0918] Emotional Data

[0919] Step 3:

[0920] The device sends the learning preference data and emotion data to the server, using the HTTPS protocol to ensure data security.

[0921] Specific behavior:

[0922] The tablet device sends data including "mathematics," "geometry," "weakness in the properties of triangles," and "stress" to the server.

[0923] input:

[0924] Learning preference data, emotion data

[0925] output:

[0926] Data sent to the server

[0927] Step 4:

[0928] The server analyzes the training data and emotion data. It uses a database and shell scripts to perform the appropriate analysis. The analysis results become the input data for the next step.

[0929] Specific behavior:

[0930] The server identifies high learning needs and "stress" regarding "geometry" and "properties of triangles."

[0931] input:

[0932] Learning preference data, emotion data

[0933] output:

[0934] Analysis results

[0935] Step 5:

[0936] The server requests the generative AI to generate a problem set based on the analysis results, and sends an API request to the generative AI to generate the necessary data.

[0937] Specific behavior:

[0938] The server requests the generative AI to generate a problem set that corresponds to "geometry," "properties of triangles," and "stress level."

[0939] input:

[0940] Analysis results

[0941] output:

[0942] Data sent to generative AI

[0943] Step 6:

[0944] The generative AI generates a problem set based on the received data. It uses a generative AI model to generate problems based on a pre-trained dataset and sends them back to the server.

[0945] Specific behavior:

[0946] The generative AI creates balanced problems related to the "properties of triangles" and sends them back to the server.

[0947] input:

[0948] Generation request data

[0949] output:

[0950] Generated problem set

[0951] Step 7:

[0952] The server sends the generated problem set to the terminal, again using the HTTPS protocol.

[0953] Specific behavior:

[0954] The server sends a set of problems about the properties of triangles to Student A's tablet device.

[0955] input:

[0956] Generated problem set

[0957] output:

[0958] Problem set sent to device

[0959] Step 8:

[0960] The terminal displays the received problem set to the user. The user interface has an intuitive and easy-to-understand design.

[0961] Specific behavior:

[0962] The tablet device displays a question about the properties of triangles to Student A.

[0963] input:

[0964] Problem set sent to device

[0965] output:

[0966] Issues seen by users

[0967] Step 9:

[0968] The user answers the questions on the device and sends them. The device then sends the answer data to the server.

[0969] Specific behavior:

[0970] Student A answers the question, enters the answer, and presses the send button.

[0971] input:

[0972] User Answer

[0973] output:

[0974] Answer data sent to the server

[0975] Step 10:

[0976] The server scores the received answer data and generates feedback using a scoring algorithm for high-precision analysis.

[0977] Specific behavior:

[0978] The server grades Student A's answers and generates feedback.

[0979] input:

[0980] Answer data

[0981] output:

[0982] Scoring results and feedback

[0983] Step 11:

[0984] The server generates feedback and sends it to the device, along with a comment that takes into account the emotion data.

[0985] Specific behavior:

[0986] The server sends feedback to Student A's device, such as "This is the correct answer" or "This is incorrect."

[0987] input:

[0988] feedback

[0989] output:

[0990] Feedback sent to device

[0991] Step 12:

[0992] The device displays the feedback to the user, who can then accept the feedback and enter additional comments.

[0993] Specific behavior:

[0994] The tablet device displays feedback to Student A such as "This is the correct answer" or "This is incorrect."

[0995] input:

[0996] Feedback sent to device

[0997] output:

[0998] Feedback displayed to the user

[0999] Step 13:

[1000] The device uses an emotion engine to analyze the user's reaction to the displayed feedback and reflects this in the next learning content.

[1001] Specific behavior:

[1002] The tablet camera reanalyzes Student A's facial expressions to confirm stress relief. This information is reflected in the next learning session.

[1003] input:

[1004] User Reactions

[1005] output:

[1006] Data to be reflected in the next study plan

[1007] (Application example 2)

[1008] 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."

[1009] Many modern learning systems can provide problem sets optimized for individual learning needs, but they rarely take the user's emotional state into consideration. As a result, learning effectiveness can decrease and motivation to learn can decline. Furthermore, even in physical stores, there is a lack of product recommendations that take the customer's emotional state into account, resulting in low customer satisfaction. Therefore, there is a need for the development of a system that analyzes users' emotions and provides appropriate learning and product recommendations based on their state.

[1010] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1011] In this invention, the server includes means for acquiring emotional data using an emotion engine that recognizes the emotional state of the user, means for the server to generate product suggestions based on the emotional data in accordance with the emotional state, and means for presenting the suggested product information to the user, thereby enabling an individually optimized learning experience and product suggestions tailored to the user's emotional state.

[1012] A "terminal" is an information processing device into which a user inputs desired study data and which displays problem sets and product information sent from a server.

[1013] The "server" is a central information processing device that analyzes data received from the terminal and works in conjunction with the generative AI and emotion engine to generate and transmit optimized problem sets and product proposals.

[1014] "Generative AI" is an artificial intelligence system that generates individually optimized problem sets and product suggestions based on data sent from a server.

[1015] An "emotion engine" is software or hardware that recognizes the user's emotional state from facial expressions, voice, etc., and acquires emotional data.

[1016] "Emotion data" is information indicating the user's emotional state obtained by the emotion engine.

[1017] "Product proposal" is data that the server generates based on emotion data and other information, proposing products suitable for the user.

[1018] A "problem set" is a series of problems generated by generative AI that are optimized for the user's learning needs.

[1019] The "display means" is a function or device for visually presenting the problem set and product suggestions received by the terminal to the user.

[1020] "User" refers to an individual who uses the system to input desired study data and view and operate the displayed problem sets and product information.

[1021] This invention is a system consisting of a terminal, a server, a generative AI, and an emotion engine, which provides problem sets and product suggestions optimized for the user's learning needs and emotional state.

[1022] 1. Overview of the entire system

[1023] This system consists of a device used by the user, a server that analyzes the data, a generative AI, and an emotion engine. The user inputs the learning data they wish to use into the device, and the emotion engine recognizes the user's emotional data. This data is sent to the generative AI via the server, and the generative AI uses the received data to generate individually optimized problem sets and product suggestions, which are then sent back to the device via the server.

[1024] 2. User terminal operation

[1025] The user operates the device to input their study preferences. Specifically, they input the subjects and scope they want to study, as well as their strengths and weaknesses. The device's built-in emotion engine also uses a camera and microphone to recognize emotional data from the user's facial expressions and voice. The device then sends this information to the server.

[1026] Specific examples

[1027] User A logs in to their smartphone and enters their desired learning data. User A's emotion engine then detects stress levels from their facial expressions. This data is then sent to the server.

[1028] 3. Server Operation

[1029] The server analyzes the learning preference data and emotional data received from the device. Based on the analysis results, it prepares data to request the generative AI to generate individually optimized problem sets and product proposals, and sends this to the generative AI. The emotional data is used as additional information to adjust the difficulty and type of problems or the content of product proposals.

[1030] Specific examples

[1031] The server analyzes User A's data and instructs the generative AI on questions specialized for specific learning topics. It also appropriately adjusts the difficulty of the suggested products and questions based on the emotional data. The problem sets and product suggestions received from the generative AI are then sent back to User A's device.

[1032] 4. How generative AI works

[1033] The generative AI generates appropriate problem sets and product suggestions based on the learning preference and emotional data sent from the server. The generated content is adjusted based on the user's strengths and weaknesses, learning progress, and even emotional state.

[1034] Specific examples

[1035] The generative AI generates a problem set related to the properties of triangles and product suggestions for relaxation items for User A. The generated content is sent to the device via the server.

[1036] 5. Display and suggest problem sets and product suggestions

[1037] The terminal receives the problem sets and product suggestions from the server and displays them to the user, who can then solve the problems and check the product suggestions.

[1038] Specific examples

[1039] User A solves a customized problem set displayed on his / her smartphone. At the same time, he / she checks the product suggestions displayed and selects the products he / she is interested in.

[1040] 6. Providing Feedback

[1041] The server scores and evaluates the received answer data and product selection information, and generates feedback. The generated feedback is then sent back to the user's device and displayed to the user. The emotion engine then analyzes the user's reactions again and reflects them in future study plans and product suggestions.

[1042] Specific examples

[1043] The server grades User A's answers and generates feedback such as "This is the correct answer" or "This is incorrect." Furthermore, the emotion engine analyzes User A's facial expressions when receiving the feedback and reflects this in the next learning session and product suggestions. This feedback is sent to User A's device and displayed.

[1044] Prompt Sentence Examples

[1045] "Please suggest the best relaxation products for customers who are feeling stressed."

[1046] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1047] Step 1:

[1048] The user operates the terminal to input the data they wish to learn, and emotional data is collected using a camera and microphone.

[1049] (Input) User's desired learning data (e.g., subject and scope) and emotional data (e.g., facial expressions and voice)

[1050] (Operation) The device allows the user to input the desired learning data, and the built-in emotion engine uses the camera and microphone to analyze the user's emotions and recognize the emotion data.

[1051] (Output) The learning target data and emotion data are sent from the terminal to the server.

[1052] Step 2:

[1053] The server analyzes the learning preference data and emotion data received from the terminal.

[1054] (Input) Learning preference data and emotion data sent from the device

[1055] (Operation) The server analyzes the learning preference data to identify the user's needs. Based on the emotion data, the server evaluates the user's emotional state.

[1056] (Output) Data based on the analysis results is sent to the generative AI.

[1057] Step 3:

[1058] Based on the data received from the server, the generative AI generates individually optimized problem sets and product suggestions.

[1059] (Input) Analysis data sent from the server

[1060] (Operation) Generative AI generates problem sets and product suggestions based on the user's learning needs and emotional state. The generative AI model is used to generate suggestions in response to a specific prompt (e.g., "Please suggest the best relaxation products for a customer who is feeling stressed.").

[1061] (Output) The generated problem set and product proposals are sent back to the server.

[1062] Step 4:

[1063] The server sends the problem sets and product suggestions received from the generative AI to the terminal.

[1064] (Input) Problem sets and product suggestions sent from generative AI

[1065] (Operation) The server organizes the received data and sends it to the terminal.

[1066] (Output) The problem set and product suggestions are sent to the terminal.

[1067] Step 5:

[1068] The terminal displays the transmitted problem set and product suggestions to the user.

[1069] (Input) Problem sets and product proposals sent from the server

[1070] (Operation) The data received by the terminal is displayed on the screen for visual display to the user.

[1071] (Output) The user can see the problem set and product suggestions.

[1072] Step 6:

[1073] The user solves the displayed problem set and enters the answers into the terminal, or checks and selects product suggestions.

[1074] (Input) User answers and product selection information

[1075] (Operation) The terminal collects the user's input data and sends it to the server.

[1076] (Output) Answer data and product selection information are sent from the terminal to the server.

[1077] Step 7:

[1078] The server scores the answers received, generates feedback, and analyzes the user's reactions using an emotion engine.

[1079] (Input) Answer data and emotion data sent from the device

[1080] (Operation) The server automatically scores the answer data and generates feedback. At the same time, the emotion engine analyzes the user's reactions and reflects them in future study plans and product suggestions.

[1081] (Output) The generated feedback and analysis results are sent to the terminal and displayed to the user.

[1082] Step 8:

[1083] Feedback from the server and the next learning plan are displayed on the device, allowing the user to proceed with their next learning or purchase.

[1084] (Input) Feedback sent from the server and next lesson plan information

[1085] (Operation) The device displays feedback and upcoming study plans to the user, allowing the user to prepare for the next study session.

[1086] (Output) The user is ready to learn or buy something next.

[1087] 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.

[1088] 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.

[1089] 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.

[1090] [Third embodiment]

[1091] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1092] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1093] 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).

[1094] 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.

[1095] 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.

[1096] 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).

[1097] 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.

[1098] 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.

[1099] 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.

[1100] 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.

[1101] 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.

[1102] 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."

[1103] The present invention is a system that combines a terminal, a server, and a generative AI to provide problem sets optimized for the learning needs of each student. A specific embodiment of this system is shown below.

[1104] 1. Overview of the entire system

[1105] This system consists of a device used by the user (e.g., a tablet device), a server, and a generative AI. The user inputs the data they wish to learn through the device, and the data is sent to the generative AI via the server. The generative AI generates an individually optimized problem set based on the received data, and sends it back to the device via the server. Finally, the user can solve the customized problem set on their device.

[1106] 2. User terminal operation

[1107] The user operates the device to input their desired study data. Specifically, they input the subject they want to study (e.g., mathematics), the range of study (e.g., geometry), and their strengths and weaknesses. The device then sends this information to the server.

[1108] Example: Student A logs in to a tablet device and inputs that he / she is weak in mathematics geometry, especially the "properties of triangles." The device sends this data to the server.

[1109] 3. Server Operation

[1110] The server analyzes the learning request data received from the device. Based on the analysis results, it sends data to the generative AI requesting it to generate an optimized problem set. When the problem set is returned from the generative AI, it is sent to the user's device.

[1111] Example: The server analyzes the data of Student A and instructs the generative AI to create problems specific to "geometry triangles." The server receives the necessary problem set from the generative AI and sends it to Student A's device.

[1112] 4. How generative AI works

[1113] The generative AI generates an appropriate problem set based on the learning preference data received from the server and the analysis results. The generated problems are adjusted according to the user's strengths and weaknesses and learning progress.

[1114] Example: A generative AI generates a balanced set of problems for Student A, including basic problems on the "properties of triangles," applied problems, and problems from other areas, and sends them back to the server.

[1115] 5. Viewing and answering problem sets

[1116] The terminal receives the problem set from the server and displays it to the user. The user solves the problem and inputs the answer. The terminal also sends the answer data to the server.

[1117] Example: Student A solves a customized problem set displayed on a tablet device. When he enters his answers, they are sent to the server.

[1118] 6. Providing Feedback

[1119] The server automatically scores the received answer data and generates feedback, which is then sent back to the user's device and displayed to the user.

[1120] Example: The server grades Student A's answers and generates feedback such as "This is the correct answer" or "This is incorrect." This feedback is sent to Student A's device and displayed.

[1121] The above-described embodiment allows students (users) to receive a learning experience optimized to their needs, thereby enabling them to study efficiently and effectively and improve their academic performance.

[1122] The processing flow will be explained below.

[1123] Step 1:

[1124] The user starts the application on the device and enters the user ID and password on the login screen. The device sends this login information to the server.

[1125] Step 2:

[1126] The server receives the login information and authenticates the user by checking the database. If authentication is successful, the server retrieves the user's past learning history data from the database and sends it to the terminal.

[1127] Step 3:

[1128] The device displays the received learning history data and prompts the user to enter desired learning data. The user enters the desired subjects, scope, strengths and weaknesses, etc. The device then sends this desired learning data to the server.

[1129] Step 4:

[1130] The server receives the learning preference data and analyzes it in combination with existing learning history data. Based on the analysis results, it prepares data to request the generative AI to generate a customized problem set, and sends it to the generative AI.

[1131] Step 5:

[1132] The generative AI generates individually optimized problem sets based on the data received from the server, and the generated problem sets are sent back to the server.

[1133] Step 6:

[1134] The server receives the problem set returned by the generative AI and sends it to the user's device, allowing the user to receive a customized problem set.

[1135] Step 7:

[1136] The terminal displays the received problem set to the user. The user solves the displayed problem and inputs the answer. The input answer is sent from the terminal to the server.

[1137] Step 8:

[1138] The server analyzes the answer data received from the user, automatically scores the answers, generates the scoring results and feedback, and sends them to the user's terminal.

[1139] Step 9:

[1140] The device displays the feedback received from the server to the user, who then checks the feedback and plans their next learning experience.

[1141] Example 1

[1142] 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."

[1143] The current educational system faces the challenge of providing learning materials optimized for each student's learning needs. A method is needed to generate appropriate problem sets based on each student's strengths and weaknesses and learning progress, and to provide them in a timely manner. It is also necessary to introduce a system that provides prompt and accurate feedback on answers.

[1144] 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.

[1145] In this invention, the server includes a means for analyzing the study data, a means for receiving question data sets from a generative artificial intelligence that generates individually optimized question data sets, and a means for scoring the user's answer data and generating feedback. This makes it possible to generate and provide an optimal question set based on the study data and analysis results, and to provide rapid feedback on the answers.

[1146] "Study preference data" refers to information such as the subjects, scope, and areas of strength and weakness that a user wishes to study.

[1147] "Device" refers to input and display devices such as tablet terminals and personal computers operated by users.

[1148] "Data processing device" refers to a server that analyzes input data and manages and transmits data and feedback from generative artificial intelligence.

[1149] "Generative artificial intelligence" refers to an AI model that generates individually optimized sets of problem data based on analysis results.

[1150] "Question data group" refers to multiple question sets generated by generative artificial intelligence and optimized to the user's learning needs.

[1151] "Feedback" refers to evaluation information such as whether the questions answered by the user are correct or incorrect, and advice.

[1152] This system is comprised of a device where users input their desired learning data, a data processing device (server) that analyzes the data to generate appropriate problem data sets and processes and manages the analysis results, and generative artificial intelligence. This system makes it possible to provide problem sets optimized for the user's learning needs and provide rapid feedback.

[1153] 1. User terminal configuration and operation

[1154] The device operated by the user can be a tablet or PC. The user inputs their desired study data through the device. Specifically, they input the subject they want to study (e.g., mathematics), the range of study (e.g., geometry), and their strengths and weaknesses.

[1155] Examples:

[1156] Student A logs in to the tablet device and enters that he or she is focusing on mathematics geometry, particularly the properties of triangles, which is something he or she is weak at.

[1157] 2. Server Configuration and Operation

[1158] The server analyzes the received learning data and sends the analysis results to the generative AI. The analysis is performed using Python scripts and a database management system. The server also plays a role in sending the problem data received from the generative AI to the user's device.

[1159] Examples:

[1160] The server analyzes Student A's data and identifies learning needs specific to "triangles in geometry." It then sends a prompt to the generative AI to "generate a set of problems related to the properties of triangles."

[1161] 3. Structure and operation of generative artificial intelligence

[1162] The generative AI generates a set of question data based on the analysis results. The generated questions are adjusted according to the user's strengths and weaknesses and learning progress. The generated set of question data is sent to the user's device via the server.

[1163] Examples:

[1164] The generative artificial intelligence generates a balanced set of problems for Student A, including basic problems on the "properties of triangles," applied problems, and problems from other related areas, and sends it back to the server.

[1165] Example prompt sentence:

[1166] "Generate a problem set for Student A that includes basic problems about the properties of triangles, applied problems, and related problems from another area."

[1167] 4. User answers and feedback

[1168] The user answers questions on their device and sends the data to the server, which then scores the answers and generates feedback, which is then sent back to the user's device and displayed to the user.

[1169] Examples:

[1170] When Student A solves the displayed problem and enters the answer, the device sends the answer data to the server. The server grades the answer and generates feedback such as "This is the correct answer" or "This is incorrect" and sends it to Student A's device.

[1171] In this way, the present invention allows users to receive an individually optimized learning experience, resulting in efficient and effective learning.

[1172] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1173] Step 1:

[1174] The user inputs the desired learning data into the terminal.

[1175] Specific behavior:

[1176] The user uses a tablet device or computer to input the subject being studied (e.g., mathematics), range of study (e.g., geometry), and strengths and weaknesses (e.g., properties of triangles).

[1177] input:

[1178] Information on study subjects, scope, strengths and weaknesses.

[1179] output:

[1180] Learning preference data entered into the terminal.

[1181] Step 2:

[1182] The terminal transmits the learning request data to the server.

[1183] Specific behavior:

[1184] The device uses the REST API to send the learning request data to the server.

[1185] input:

[1186] Learning preference data entered into the terminal.

[1187] output:

[1188] Learning preference data sent to the server.

[1189] Step 3:

[1190] The server analyzes the learning preference data.

[1191] Specific behavior:

[1192] The server uses a Python script to analyze the received data and identify the user's learning needs.

[1193] input:

[1194] Learning preference data sent to the server.

[1195] output:

[1196] User learning needs data as a result of analysis.

[1197] Step 4:

[1198] The server sends the analysis results to the generative AI.

[1199] Specific behavior:

[1200] The server sends the analysis results to the generative AI as a prompt.

[1201] input:

[1202] User learning needs data as a result of analysis.

[1203] output:

[1204] The prompt sent to the generative AI.

[1205] Example prompt sentence:

[1206] "Generate a problem set for Student A that includes basic problems about the properties of triangles, applied problems, and related problems from another area."

[1207] Step 5:

[1208] The generative AI generates a set of problem data and sends it back to the server.

[1209] Specific behavior:

[1210] The generative AI generates a set of problem data based on the prompt text and sends it back to the server.

[1211] input:

[1212] The prompt sent to the generative AI.

[1213] output:

[1214] Generated problem data set.

[1215] Step 6:

[1216] The server sends a set of question data to the terminal.

[1217] Specific behavior:

[1218] The server sends the generated question data set to the terminal in JSON format.

[1219] input:

[1220] Generated problem data set.

[1221] output:

[1222] A set of question data in JSON format sent to the device.

[1223] Step 7:

[1224] The terminal displays the problem data set to the user.

[1225] Specific behavior:

[1226] The terminal displays the received question data group to the user.

[1227] input:

[1228] The problem data set sent to the terminal.

[1229] output:

[1230] A set of problem data displayed on the user's terminal.

[1231] Step 8:

[1232] The user solves the problem and inputs the answer data into the terminal.

[1233] Specific behavior:

[1234] The user solves the problem on the terminal and inputs the answer data.

[1235] input:

[1236] User answer data.

[1237] output:

[1238] Answer data entered into the terminal.

[1239] Step 9:

[1240] The terminal sends the answer data to the server.

[1241] Specific behavior:

[1242] The device sends the answer data to the server via the REST API.

[1243] input:

[1244] Answer data entered into the terminal.

[1245] output:

[1246] The answer data sent to the server.

[1247] Step 10:

[1248] The server grades the answer data and generates feedback.

[1249] Specific behavior:

[1250] The server uses a Python script to grade the answer data and generate feedback.

[1251] input:

[1252] The answer data sent to the server.

[1253] output:

[1254] Generated feedback data.

[1255] Step 11:

[1256] The server sends the feedback to the device.

[1257] Specific behavior:

[1258] The server sends the feedback data to the terminal.

[1259] input:

[1260] Generated feedback data.

[1261] output:

[1262] Feedback data sent to the device.

[1263] Step 12:

[1264] The device displays the feedback to the user.

[1265] Specific behavior:

[1266] The terminal displays the received feedback to the user.

[1267] input:

[1268] Feedback data sent to the device.

[1269] output:

[1270] Feedback displayed on the user's device.

[1271] (Application example 1)

[1272] 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."

[1273] Conventional learning systems have had difficulty providing content optimized to the learning needs of each individual student. Furthermore, they lacked a means to provide immediate, appropriate feedback on answers, which resulted in insufficient improvement in students' learning effectiveness.

[1274] 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.

[1275] In this invention, the server includes a terminal for inputting desired learning data, a means for analyzing data received from the terminal, a means for transmitting problem sets received from the generative AI to the terminal, a means for a user to input answers and transmit the answers to the server, a means for the server to grade the answer data received and generate feedback, and a means for transmitting the generated feedback to the terminal, thereby making it possible to provide problem sets optimized for the learning needs of each student and provide immediate feedback on their answers.

[1276] "Study preference data" is information such as the subjects the user wants to study, the scope of study, areas of strength and weakness, etc.

[1277] A "terminal" is a device that allows a user to input desired study data and answers and transmit them to a server.

[1278] A "server" is a device that analyzes data received from a terminal, sends instructions to the generative AI, and transmits the generated data to the terminal.

[1279] "Generative AI" is artificial intelligence that generates individually optimized problem sets based on data received from a server.

[1280] A "problem set" is a set of practice questions and learning materials provided to users that are generated by generative AI based on desired learning data.

[1281] "Answer data" is data that includes the answers that a user gives to a question set.

[1282] "Feedback" is information including the results of scoring the user's answers, explanations, and areas for improvement.

[1283] The "display means" is a function for displaying the generated problem set and feedback on the user terminal.

[1284] "Means of transmission" refers to the function of transmitting data generated by the generative AI and data from the server to the user's terminal.

[1285] This invention is a system that combines terminals, servers, and generative AI to provide problem sets optimized for the learning needs of each student. The elements and specific steps for realizing this system are described below.

[1286] Overall system overview

[1287] The system consists of a device used by the user (e.g., a smartphone), a server, and a generative AI. The user inputs the data they wish to learn through the device, which is then sent to the generative AI via the server. The generative AI generates an individually optimized problem set based on the received data, which is then sent back to the device via the server. Finally, the user can solve the customized problem set on their device.

[1288] Device behavior

[1289] The user operates the terminal to input their desired study data. Specifically, they input the subject they want to study (e.g., mathematics), the range of study (e.g., geometry), and their strengths and weaknesses. The terminal then sends this information to the server.

[1290] Example: A student logs in to their smartphone and inputs that they are focusing on geometry in mathematics, especially that they are weak in the "properties of triangles." The device then sends this data to a server.

[1291] Server Operation

[1292] The server analyzes the learning request data received from the device. Based on the analysis results, it sends data to the generative AI requesting it to generate an optimized problem set. When the problem set is returned from the generative AI, it is sent to the user's device.

[1293] Example: The server analyzes the student's data and instructs the generative AI to create problems specific to "geometry triangles." The server receives the necessary problem set from the generative AI and sends it to the student's device.

[1294] How generative AI works

[1295] The generative AI generates an appropriate problem set based on the learning preference data received from the server and the analysis results. The generated problems are adjusted according to the user's strengths and weaknesses and learning progress.

[1296] Example: A generative AI generates a balanced set of problems for a student, including basic problems on the "properties of triangles," applied problems, and problems from other areas, and sends them back to the server.

[1297] View and answer problem sets

[1298] The terminal receives the problem set from the server and displays it to the user. The user solves the problem and inputs the answer. The terminal also sends the answer data to the server.

[1299] Example: A student solves a customized set of problems displayed on their smartphone, enters their answers, and sends them to a server.

[1300] Providing Feedback

[1301] The server automatically scores the received answer data and generates feedback, which is then sent back to the user's device and displayed to the user.

[1302] Example: The server grades the student's answers and generates feedback such as "This is the correct answer" or "This is the wrong answer." This feedback is sent to the student's device and displayed.

[1303] Hardware and software used

[1304] Device: Smartphone

[1305] Server: A server with data analysis and transmission / reception functions

[1306] Generative AI: Artificial intelligence that generates problem sets based on user learning data

[1307] Software libraries: requests (for sending and receiving data), framework for displaying user interfaces

[1308] Prompt Sentence Examples

[1309] Here is the user data:

[1310] Subject: Mathematics

[1311] Range: Geometry

[1312] Weakness: Triangular nature

[1313] Based on this data, please suggest study materials:

[1314] basic problems

[1315] Applied Problems

[1316] Video lectures

[1317] Additional questions based on feedback

[1318] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1319] Step 1:

[1320] The user operates the device to input desired study data. The user inputs the subject they wish to study, the range of study, and areas of strength and weakness, and sends this data from the device to the server. Specifically, the user enters the subject (mathematics), range of study (geometry), and areas of strength and weakness (e.g., "properties of triangles") into the smartphone input form, and then presses the send button.

[1321] Input: Study preferences (subjects, scope, areas of strength and weakness)

[1322] Output: Learning preference data sent to the server

[1323] Step 2:

[1324] The server analyzes the learning request data received from the device. Here, the data is formatted and preprocessed. As a result of the analysis, the learning needs become clear and the data to be passed to the generative AI is determined.

[1325] Input: Study Desired Data

[1326] Output: Analysis results (learning needs)

[1327] Step 3:

[1328] The server sends data to the generative AI to request it to generate an optimized problem set based on the analysis results. The generative AI then receives the analysis results and begins the process of generating a problem set.

[1329] Input: Analysis results

[1330] Output: Instruction data for generative AI

[1331] Step 4:

[1332] Based on the analysis results, the generative AI generates individually optimized problem sets, using prompts to generate appropriate problem sets (basic problems, applied problems, video lectures, additional problems, etc.).

[1333] Input: Analysis results, prompt text

[1334] Output: Optimized problem set

[1335] Step 5:

[1336] The server sends the problem set received from the generative AI to the device, allowing the user to receive the problem set on their smartphone.

[1337] Input: Optimized problem set

[1338] Output: Data sent to the terminal

[1339] Step 6:

[1340] The device displays the received problem set to the user, who then solves the problem and enters the answer. Specifically, the problem is displayed on the smartphone screen, and the user enters the answer in an input form.

[1341] Input: Data to send to the terminal

[1342] Output: The problem set that is displayed to the user

[1343] Step 7:

[1344] The user inputs the answer and sends the answer data from the terminal to the server, where it is ready to be analyzed and scored.

[1345] Input: User's answer data

[1346] Output: Answer data sent to the server

[1347] Step 8:

[1348] The server scores the received answer data and generates feedback. Based on the scoring results, it determines whether the answer is correct or incorrect and generates useful feedback.

[1349] Input: Answer data

[1350] Output: Generated feedback

[1351] Step 9:

[1352] The server sends the generated feedback to the terminal, allowing the user to receive the feedback immediately.

[1353] Input: Generated feedback

[1354] Output: Data sent to the terminal

[1355] Step 10:

[1356] The device displays the received feedback to the user, who can then check their own answers and use the feedback to improve their future learning.

[1357] Input: Data to send to the terminal

[1358] Output: Feedback that is displayed to the user

[1359] 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.

[1360] The present invention is a system that combines a terminal, a server, a generative AI, and an emotion engine that recognizes the user's emotions to provide problem sets optimized for each student's learning needs and emotional state. A specific embodiment of this system is shown below.

[1361] 1. Overview of the entire system

[1362] This system consists of a device used by the user (e.g., a tablet device), a server, a generative AI, and an emotion engine. When a user inputs the data they wish to learn through the device, the emotion engine recognizes the user's emotional data, and this data is sent to the generative AI via the server. Based on the received data, the generative AI generates an individually optimized problem set, which is then sent to the device via the server again. Ultimately, the user can solve a customized problem set on the device that also takes into account their emotional state.

[1363] 2. User terminal operation

[1364] The user operates the device to input their desired study data. Specifically, they input the subject they want to study (e.g., mathematics), the range of subjects (e.g., geometry), and their strengths and weaknesses. The device's built-in emotion engine also uses a camera and microphone to recognize emotion data from the user's facial expressions and voice. The device then sends this information to the server.

[1365] Example: Student A logs in to a tablet device and inputs that he / she is focusing on mathematics geometry, especially the "properties of triangles," and is weak in this field. The emotion engine analyzes Student A's facial expressions and recognizes signs of stress. The device sends the learning preference data and emotion data to the server.

[1366] 3. Server Operation

[1367] The server analyzes the learning preference data and emotional data received from the device. Based on the analysis results, it prepares data to request the generative AI to generate a customized problem set and sends this to the generative AI. The emotional data is used as additional information to adjust the difficulty and type of problems.

[1368] Example: The server analyzes Student A's data and instructs the generative AI to create problems specific to "geometry triangles." It also adjusts the difficulty of the problems appropriately based on emotional data to reduce stress. The server receives the necessary problem set from the generative AI and sends it to Student A's device.

[1369] 4. How generative AI works

[1370] The generative AI generates an appropriate set of problems based on the learning preference and emotional data received from the server. The problems are adjusted based on the user's strengths and weaknesses, learning progress, and emotional state.

[1371] Example: A generative AI generates a balanced set of problems for Student A, including basic problems on the "properties of triangles," applied problems, and problems from other areas, and sends them back to the server. Based on stress data, the initial problems are set relatively easy.

[1372] 5. Viewing and answering problem sets

[1373] The terminal receives the problem set from the server and displays it to the user. The user solves the problem and inputs the answer. The input answer is sent from the terminal to the server.

[1374] Example: Student A solves a customized problem set displayed on a tablet device. When he enters his answers, they are sent to the server.

[1375] 6. Providing Feedback

[1376] The server automatically scores the received answer data and generates feedback. The generated feedback is then sent back to the user's device and displayed to the user. The emotion engine then analyzes the user's response and reflects it in future learning plans.

[1377] Example: The server grades Student A's answers and generates feedback such as "This is the correct answer" or "This is incorrect." The emotion engine also analyzes Student A's facial expressions when receiving the feedback and reflects this in the next learning session. This feedback is sent to Student A's device and displayed.

[1378] The above-described embodiment allows students (users) to receive a learning experience optimized for their needs and emotional state, thereby enabling efficient and effective learning, improving academic ability, and reducing psychological stress.

[1379] The processing flow will be explained below.

[1380] Step 1:

[1381] The user starts the application on the device and enters the user ID and password on the login screen. The device sends this login information to the server.

[1382] Step 2:

[1383] The server receives the login information and authenticates the user by checking the database. If authentication is successful, the server retrieves the user's past learning history data from the database and sends it to the terminal.

[1384] Step 3:

[1385] The device displays the received learning history data and prompts the user to enter their desired learning data. The user enters the subjects they wish to study, the scope of study, their strengths and weaknesses, etc. The emotion engine also uses a camera and microphone to recognize emotional data from the user's facial expressions and voice. The device then sends this data to the server.

[1386] Step 4:

[1387] The server receives the learning preference data and emotion data, analyzes it in combination with existing learning history data, and prepares data to request the generative AI to generate a customized problem set based on the analysis results, and sends this data to the generative AI.

[1388] Step 5:

[1389] The generative AI generates individually optimized problem sets based on the data received from the server, and the generated problem sets are sent back to the server.

[1390] Step 6:

[1391] The server receives the problem set returned by the generative AI and sends it to the user's device, where the user receives a customized problem set that takes into account their emotional state.

[1392] Step 7:

[1393] The terminal displays the received problem set to the user. The user solves the displayed problem and inputs the answer. The input answer is sent from the terminal to the server.

[1394] Step 8:

[1395] The server analyzes the answer data received from the user and automatically scores them. It generates the scoring results and feedback and sends them to the user's device. The emotion engine also analyzes the user's reaction to the feedback and reflects that data in future study plans.

[1396] Step 9:

[1397] The device displays the feedback received from the server to the user. The user checks the feedback and plans their next learning. The emotion engine analyzes the user's reaction and updates the emotion data as necessary.

[1398] Example 2

[1399] 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."

[1400] Conventional learning support systems generate problem sets based solely on the user's learning preferences, which does not take into account the user's emotional state, resulting in poor learning outcomes. Furthermore, feedback is not provided in real time, making it difficult to maintain the user's motivation. These issues must be resolved to improve the user's learning experience.

[1401] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1402] In this invention, the server includes a means for analyzing learning preference data and emotional data, a means for cooperating with a generative AI that generates individually optimized problem sets, and a means for receiving and scoring the user's answer data and generating feedback. This makes it possible to provide a customized problem set that takes the user's emotional state into consideration, and improve the user's learning effectiveness and motivation through real-time feedback.

[1403] "Study preference data" is data that indicates the user's learning preferences, such as the subjects and scope they wish to study, and their strengths and weaknesses.

[1404] "Emotion data" is data that represents the user's emotional state, such as stress, joy, excitement, or other psychological state.

[1405] A "terminal" is a device through which a user inputs learning preference data and emotion data, and specifically refers to a tablet terminal, smartphone, PC, etc.

[1406] The "server" is a computer system that receives and analyzes data sent from the device, and works in conjunction with the generative AI and the device to perform various learning support processes.

[1407] "Generative AI" is an artificial intelligence system that generates individually optimized problem sets based on learning preference data and emotional data received from a server.

[1408] A "problem set" refers to multiple learning problems presented to the user, generated by generative AI based on the user's learning preferences and emotional data.

[1409] "Feedback" is information that the server uses to grade the user's answer data and inform the user whether the answer was correct or not, and what improvements need to be made.

[1410] The present invention is a system that combines a terminal, a server, a generative AI, and an emotion engine that recognizes the user's emotions to provide problem sets optimized for each student's learning needs and emotional state. A specific embodiment of this system is shown below.

[1411] Overall system overview

[1412] This system consists of a device used by the user (e.g., a tablet device), a server, a generative AI, and an emotion engine. When a user inputs the data they wish to learn through the device, the emotion engine recognizes the user's emotional data, and this data is sent to the generative AI via the server. Based on the received data, the generative AI generates an individually optimized problem set, which is then sent to the device via the server again. Ultimately, the user can solve a customized problem set on the device that also takes into account their emotional state.

[1413] User terminal operation

[1414] The user operates the device to input their desired study data. Specifically, they input the subject they want to study (e.g., mathematics), the range of subjects (e.g., geometry), and their strengths and weaknesses. The device's built-in emotion engine also uses a camera and microphone to recognize emotion data from the user's facial expressions and voice. The device then sends this information to the server.

[1415] Examples:

[1416] Student A logs in to a tablet device and inputs that he / she is focusing on mathematics geometry, especially the "properties of triangles," and is weak in this field. The emotion engine analyzes Student A's facial expressions and recognizes signs of stress. The device then sends the learning preference data and emotion data to the server.

[1417] Prompt statement:

[1418] "I'm eager to learn about geometry, but I just can't understand the properties of triangles. Emotionally, I'm feeling a bit stressed."

[1419] Server Operation

[1420] The server analyzes the learning preference data and emotional data received from the device. Based on the analysis results, it prepares data to request the generative AI to generate a customized problem set and sends this to the generative AI. The emotional data is used as additional information to adjust the difficulty and type of problems.

[1421] Examples:

[1422] The server analyzes Student A's data and instructs the generative AI to create problems specific to "geometric triangles." It also adjusts the difficulty of the problems appropriately based on emotional data to reduce stress. The server receives the necessary problem set from the generative AI and sends it to Student A's device.

[1423] How generative AI works

[1424] The generative AI generates an appropriate set of problems based on the learning preference and emotional data received from the server. The problems are adjusted based on the user's strengths and weaknesses, learning progress, and emotional state.

[1425] Examples:

[1426] The generative AI generates a balanced set of problems for Student A, including basic problems on the "properties of triangles," applied problems, and problems from other areas, and sends it back to the server. Based on the stress data, the initial problems are set relatively easy.

[1427] View and answer problem sets

[1428] The terminal receives the problem set from the server and displays it to the user. The user solves the problem and inputs the answer. The input answer is sent from the terminal to the server.

[1429] Examples:

[1430] Student A solves a customized problem set displayed on a tablet device. When he enters his answers, they are sent to the server.

[1431] Providing Feedback

[1432] The server automatically scores the received answer data and generates feedback. The generated feedback is then sent back to the user's device and displayed to the user. The emotion engine then analyzes the user's response and reflects it in future learning plans.

[1433] Examples:

[1434] The server grades Student A's answers and generates feedback such as "This is the correct answer" or "This is incorrect." The emotion engine also analyzes Student A's facial expressions when receiving the feedback and reflects this in the next learning session. This feedback is sent to Student A's device and displayed.

[1435] The above-described embodiment allows students (users) to receive a learning experience optimized for their needs and emotional state, thereby enabling efficient and effective learning, improving academic ability, and reducing psychological stress.

[1436] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1437] Step 1:

[1438] The user operates the terminal and inputs their desired study data. Specifically, the user inputs the subjects, scope, and areas of strength and weakness they wish to study, which then become the input data for the terminal. The input data is sent to the computer system as "study preference data."

[1439] Specific behavior:

[1440] Student A types "math," "geometry," and "properties of triangles" into his tablet.

[1441] input:

[1442] Information about the subjects you want to study, the scope, and your strengths and weaknesses

[1443] output:

[1444] Learning preference data

[1445] Step 2:

[1446] The device uses an emotion engine to acquire emotion data. The camera and microphone are used to capture the user's facial expressions and voice in real time, which the emotion engine then analyzes. The analysis results become "emotion data."

[1447] Specific behavior:

[1448] The camera on the tablet device captures Student A's facial expression, and "stress" is recognized through facial analysis.

[1449] input:

[1450] User's facial expressions and voice

[1451] output:

[1452] Emotional Data

[1453] Step 3:

[1454] The device sends the learning preference data and emotion data to the server, using the HTTPS protocol to ensure data security.

[1455] Specific behavior:

[1456] The tablet device sends data including "mathematics," "geometry," "weakness in the properties of triangles," and "stress" to the server.

[1457] input:

[1458] Learning preference data, emotion data

[1459] output:

[1460] Data sent to the server

[1461] Step 4:

[1462] The server analyzes the training data and emotion data. It uses a database and shell scripts to perform the appropriate analysis. The analysis results become the input data for the next step.

[1463] Specific behavior:

[1464] The server identifies high learning needs and "stress" regarding "geometry" and "properties of triangles."

[1465] input:

[1466] Learning preference data, emotion data

[1467] output:

[1468] Analysis results

[1469] Step 5:

[1470] The server requests the generative AI to generate a problem set based on the analysis results, and sends an API request to the generative AI to generate the necessary data.

[1471] Specific behavior:

[1472] The server requests the generative AI to generate a problem set that corresponds to "geometry," "properties of triangles," and "stress level."

[1473] input:

[1474] Analysis results

[1475] output:

[1476] Data sent to generative AI

[1477] Step 6:

[1478] The generative AI generates a problem set based on the received data. It uses a generative AI model to generate problems based on a pre-trained dataset and sends them back to the server.

[1479] Specific behavior:

[1480] The generative AI creates balanced problems related to the "properties of triangles" and sends them back to the server.

[1481] input:

[1482] Generation request data

[1483] output:

[1484] Generated problem set

[1485] Step 7:

[1486] The server sends the generated problem set to the terminal, again using the HTTPS protocol.

[1487] Specific behavior:

[1488] The server sends a set of problems about the properties of triangles to Student A's tablet device.

[1489] input:

[1490] Generated problem set

[1491] output:

[1492] Problem set sent to device

[1493] Step 8:

[1494] The terminal displays the received problem set to the user. The user interface has an intuitive and easy-to-understand design.

[1495] Specific behavior:

[1496] The tablet device displays a question about the properties of triangles to Student A.

[1497] input:

[1498] Problem set sent to device

[1499] output:

[1500] Issues seen by users

[1501] Step 9:

[1502] The user answers the questions on the device and sends them. The device then sends the answer data to the server.

[1503] Specific behavior:

[1504] Student A answers the question, enters the answer, and presses the send button.

[1505] input:

[1506] User Answer

[1507] output:

[1508] Answer data sent to the server

[1509] Step 10:

[1510] The server scores the received answer data and generates feedback using a scoring algorithm for high-precision analysis.

[1511] Specific behavior:

[1512] The server grades Student A's answers and generates feedback.

[1513] input:

[1514] Answer data

[1515] output:

[1516] Scoring results and feedback

[1517] Step 11:

[1518] The server generates feedback and sends it to the device, along with a comment that takes into account the emotion data.

[1519] Specific behavior:

[1520] The server sends feedback to Student A's device, such as "This is the correct answer" or "This is incorrect."

[1521] input:

[1522] feedback

[1523] output:

[1524] Feedback sent to device

[1525] Step 12:

[1526] The device displays the feedback to the user, who can then accept the feedback and enter additional comments.

[1527] Specific behavior:

[1528] The tablet device displays feedback to Student A such as "This is the correct answer" or "This is incorrect."

[1529] input:

[1530] Feedback sent to device

[1531] output:

[1532] Feedback displayed to the user

[1533] Step 13:

[1534] The device uses an emotion engine to analyze the user's reaction to the displayed feedback and reflects this in the next learning content.

[1535] Specific behavior:

[1536] The tablet camera reanalyzes Student A's facial expressions to confirm stress relief. This information is reflected in the next learning session.

[1537] input:

[1538] User Reactions

[1539] output:

[1540] Data to be reflected in the next study plan

[1541] (Application example 2)

[1542] 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."

[1543] Many modern learning systems can provide problem sets optimized for individual learning needs, but they rarely take the user's emotional state into consideration. As a result, learning effectiveness can decrease and motivation to learn can decline. Furthermore, even in physical stores, there is a lack of product recommendations that take the customer's emotional state into account, resulting in low customer satisfaction. Therefore, there is a need for the development of a system that analyzes users' emotions and provides appropriate learning and product recommendations based on their state.

[1544] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1545] In this invention, the server includes means for acquiring emotional data using an emotion engine that recognizes the emotional state of the user, means for the server to generate product suggestions based on the emotional data in accordance with the emotional state, and means for presenting the suggested product information to the user, thereby enabling an individually optimized learning experience and product suggestions tailored to the user's emotional state.

[1546] A "terminal" is an information processing device into which a user inputs desired study data and which displays problem sets and product information sent from a server.

[1547] The "server" is a central information processing device that analyzes data received from the terminal and works in conjunction with the generative AI and emotion engine to generate and transmit optimized problem sets and product proposals.

[1548] "Generative AI" is an artificial intelligence system that generates individually optimized problem sets and product suggestions based on data sent from a server.

[1549] An "emotion engine" is software or hardware that recognizes the user's emotional state from facial expressions, voice, etc., and acquires emotional data.

[1550] "Emotion data" is information indicating the user's emotional state obtained by the emotion engine.

[1551] "Product proposal" is data that the server generates based on emotion data and other information, proposing products suitable for the user.

[1552] A "problem set" is a series of problems generated by generative AI that are optimized for the user's learning needs.

[1553] The "display means" is a function or device for visually presenting the problem set and product suggestions received by the terminal to the user.

[1554] "User" refers to an individual who uses the system to input desired study data and view and operate the displayed problem sets and product information.

[1555] This invention is a system consisting of a terminal, a server, a generative AI, and an emotion engine, which provides problem sets and product suggestions optimized for the user's learning needs and emotional state.

[1556] 1. Overview of the entire system

[1557] This system consists of a device used by the user, a server that analyzes the data, a generative AI, and an emotion engine. The user inputs the learning data they wish to use into the device, and the emotion engine recognizes the user's emotional data. This data is sent to the generative AI via the server, and the generative AI uses the received data to generate individually optimized problem sets and product suggestions, which are then sent back to the device via the server.

[1558] 2. User terminal operation

[1559] The user operates the device to input their study preferences. Specifically, they input the subjects and scope they want to study, as well as their strengths and weaknesses. The device's built-in emotion engine also uses a camera and microphone to recognize emotional data from the user's facial expressions and voice. The device then sends this information to the server.

[1560] Specific examples

[1561] User A logs in to their smartphone and enters their desired learning data. User A's emotion engine then detects stress levels from their facial expressions. This data is then sent to the server.

[1562] 3. Server Operation

[1563] The server analyzes the learning preference data and emotional data received from the device. Based on the analysis results, it prepares data to request the generative AI to generate individually optimized problem sets and product proposals, and sends this to the generative AI. The emotional data is used as additional information to adjust the difficulty and type of problems or the content of product proposals.

[1564] Specific examples

[1565] The server analyzes User A's data and instructs the generative AI on questions specialized for specific learning topics. It also appropriately adjusts the difficulty of the suggested products and questions based on the emotional data. The problem sets and product suggestions received from the generative AI are then sent back to User A's device.

[1566] 4. How generative AI works

[1567] The generative AI generates appropriate problem sets and product suggestions based on the learning preference and emotional data sent from the server. The generated content is adjusted based on the user's strengths and weaknesses, learning progress, and even emotional state.

[1568] Specific examples

[1569] The generative AI generates a problem set related to the properties of triangles and product suggestions for relaxation items for User A. The generated content is sent to the device via the server.

[1570] 5. Display and suggest problem sets and product suggestions

[1571] The terminal receives the problem sets and product suggestions from the server and displays them to the user, who can then solve the problems and check the product suggestions.

[1572] Specific examples

[1573] User A solves a customized problem set displayed on his / her smartphone. At the same time, he / she checks the product suggestions displayed and selects the products he / she is interested in.

[1574] 6. Providing Feedback

[1575] The server scores and evaluates the received answer data and product selection information, and generates feedback. The generated feedback is then sent back to the user's device and displayed to the user. The emotion engine then analyzes the user's reactions again and reflects them in future study plans and product suggestions.

[1576] Specific examples

[1577] The server grades User A's answers and generates feedback such as "This is the correct answer" or "This is incorrect." Furthermore, the emotion engine analyzes User A's facial expressions when receiving the feedback and reflects this in the next learning session and product suggestions. This feedback is sent to User A's device and displayed.

[1578] Prompt Sentence Examples

[1579] "Please suggest the best relaxation products for customers who are feeling stressed."

[1580] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1581] Step 1:

[1582] The user operates the terminal to input the data they wish to learn, and emotional data is collected using a camera and microphone.

[1583] (Input) User's desired learning data (e.g., subject and scope) and emotional data (e.g., facial expressions and voice)

[1584] (Operation) The device allows the user to input the desired learning data, and the built-in emotion engine uses the camera and microphone to analyze the user's emotions and recognize the emotion data.

[1585] (Output) The learning target data and emotion data are sent from the terminal to the server.

[1586] Step 2:

[1587] The server analyzes the learning preference data and emotion data received from the terminal.

[1588] (Input) Learning preference data and emotion data sent from the device

[1589] (Operation) The server analyzes the learning preference data to identify the user's needs. Based on the emotion data, the server evaluates the user's emotional state.

[1590] (Output) Data based on the analysis results is sent to the generative AI.

[1591] Step 3:

[1592] Based on the data received from the server, the generative AI generates individually optimized problem sets and product suggestions.

[1593] (Input) Analysis data sent from the server

[1594] (Operation) Generative AI generates problem sets and product suggestions based on the user's learning needs and emotional state. The generative AI model is used to generate suggestions in response to a specific prompt (e.g., "Please suggest the best relaxation products for a customer who is feeling stressed.").

[1595] (Output) The generated problem set and product proposals are sent back to the server.

[1596] Step 4:

[1597] The server sends the problem sets and product suggestions received from the generative AI to the terminal.

[1598] (Input) Problem sets and product suggestions sent from generative AI

[1599] (Operation) The server organizes the received data and sends it to the terminal.

[1600] (Output) The problem set and product suggestions are sent to the terminal.

[1601] Step 5:

[1602] The terminal displays the transmitted problem set and product suggestions to the user.

[1603] (Input) Problem sets and product proposals sent from the server

[1604] (Operation) The data received by the terminal is displayed on the screen for visual display to the user.

[1605] (Output) The user can see the problem set and product suggestions.

[1606] Step 6:

[1607] The user solves the displayed problem set and enters the answers into the terminal, or checks and selects product suggestions.

[1608] (Input) User answers and product selection information

[1609] (Operation) The terminal collects the user's input data and sends it to the server.

[1610] (Output) Answer data and product selection information are sent from the terminal to the server.

[1611] Step 7:

[1612] The server scores the answers received, generates feedback, and analyzes the user's reactions using an emotion engine.

[1613] (Input) Answer data and emotion data sent from the device

[1614] (Operation) The server automatically scores the answer data and generates feedback. At the same time, the emotion engine analyzes the user's reactions and reflects them in future study plans and product suggestions.

[1615] (Output) The generated feedback and analysis results are sent to the terminal and displayed to the user.

[1616] Step 8:

[1617] Feedback from the server and the next learning plan are displayed on the device, allowing the user to proceed with their next learning or purchase.

[1618] (Input) Feedback sent from the server and next lesson plan information

[1619] (Operation) The device displays feedback and upcoming study plans to the user, allowing the user to prepare for the next study session.

[1620] (Output) The user is ready to learn or buy something next.

[1621] 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.

[1622] 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.

[1623] 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.

[1624] [Fourth embodiment]

[1625] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1626] 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.

[1627] 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).

[1628] 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.

[1629] 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.

[1630] 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).

[1631] 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.

[1632] 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.

[1633] 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.

[1634] 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.

[1635] 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.

[1636] 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.

[1637] 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."

[1638] The present invention is a system that combines a terminal, a server, and a generative AI to provide problem sets optimized for the learning needs of each student. A specific embodiment of this system is shown below.

[1639] 1. Overview of the entire system

[1640] This system consists of a device used by the user (e.g., a tablet device), a server, and a generative AI. The user inputs the data they wish to learn through the device, and the data is sent to the generative AI via the server. The generative AI generates an individually optimized problem set based on the received data, and sends it back to the device via the server. Finally, the user can solve the customized problem set on their device.

[1641] 2. User terminal operation

[1642] The user operates the device to input their desired study data. Specifically, they input the subject they want to study (e.g., mathematics), the range of study (e.g., geometry), and their strengths and weaknesses. The device then sends this information to the server.

[1643] Example: Student A logs in to a tablet device and inputs that he / she is weak in mathematics geometry, especially the "properties of triangles." The device sends this data to the server.

[1644] 3. Server Operation

[1645] The server analyzes the learning request data received from the device. Based on the analysis results, it sends data to the generative AI requesting it to generate an optimized problem set. When the problem set is returned from the generative AI, it is sent to the user's device.

[1646] Example: The server analyzes the data of Student A and instructs the generative AI to create problems specific to "geometry triangles." The server receives the necessary problem set from the generative AI and sends it to Student A's device.

[1647] 4. How generative AI works

[1648] The generative AI generates an appropriate problem set based on the learning preference data received from the server and the analysis results. The generated problems are adjusted according to the user's strengths and weaknesses and learning progress.

[1649] Example: A generative AI generates a balanced set of problems for Student A, including basic problems on the "properties of triangles," applied problems, and problems from other areas, and sends them back to the server.

[1650] 5. Viewing and answering problem sets

[1651] The terminal receives the problem set from the server and displays it to the user. The user solves the problem and inputs the answer. The terminal also sends the answer data to the server.

[1652] Example: Student A solves a customized problem set displayed on a tablet device. When he enters his answers, they are sent to the server.

[1653] 6. Providing Feedback

[1654] The server automatically scores the received answer data and generates feedback, which is then sent back to the user's device and displayed to the user.

[1655] Example: The server grades Student A's answers and generates feedback such as "This is the correct answer" or "This is incorrect." This feedback is sent to Student A's device and displayed.

[1656] The above-described embodiment allows students (users) to receive a learning experience optimized to their needs, thereby enabling them to study efficiently and effectively and improve their academic performance.

[1657] The processing flow will be explained below.

[1658] Step 1:

[1659] The user starts the application on the device and enters the user ID and password on the login screen. The device sends this login information to the server.

[1660] Step 2:

[1661] The server receives the login information and authenticates the user by checking the database. If authentication is successful, the server retrieves the user's past learning history data from the database and sends it to the terminal.

[1662] Step 3:

[1663] The device displays the received learning history data and prompts the user to enter desired learning data. The user enters the desired subjects, scope, strengths and weaknesses, etc. The device then sends this desired learning data to the server.

[1664] Step 4:

[1665] The server receives the learning preference data and analyzes it in combination with existing learning history data. Based on the analysis results, it prepares data to request the generative AI to generate a customized problem set, and sends it to the generative AI.

[1666] Step 5:

[1667] The generative AI generates individually optimized problem sets based on the data received from the server, and the generated problem sets are sent back to the server.

[1668] Step 6:

[1669] The server receives the problem set returned by the generative AI and sends it to the user's device, allowing the user to receive a customized problem set.

[1670] Step 7:

[1671] The terminal displays the received problem set to the user. The user solves the displayed problem and inputs the answer. The input answer is sent from the terminal to the server.

[1672] Step 8:

[1673] The server analyzes the answer data received from the user, automatically scores the answers, generates the scoring results and feedback, and sends them to the user's terminal.

[1674] Step 9:

[1675] The device displays the feedback received from the server to the user, who then checks the feedback and plans their next learning experience.

[1676] Example 1

[1677] 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."

[1678] The current educational system faces the challenge of providing learning materials optimized for each student's learning needs. A method is needed to generate appropriate problem sets based on each student's strengths and weaknesses and learning progress, and to provide them in a timely manner. It is also necessary to introduce a system that provides prompt and accurate feedback on answers.

[1679] 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.

[1680] In this invention, the server includes a means for analyzing the study data, a means for receiving question data sets from a generative artificial intelligence that generates individually optimized question data sets, and a means for scoring the user's answer data and generating feedback. This makes it possible to generate and provide an optimal question set based on the study data and analysis results, and to provide rapid feedback on the answers.

[1681] "Study preference data" refers to information such as the subjects, scope, and areas of strength and weakness that a user wishes to study.

[1682] "Device" refers to input and display devices such as tablet terminals and personal computers operated by users.

[1683] "Data processing device" refers to a server that analyzes input data and manages and transmits data and feedback from generative artificial intelligence.

[1684] "Generative artificial intelligence" refers to an AI model that generates individually optimized sets of problem data based on analysis results.

[1685] "Question data group" refers to multiple question sets generated by generative artificial intelligence and optimized to the user's learning needs.

[1686] "Feedback" refers to evaluation information such as whether the questions answered by the user are correct or incorrect, and advice.

[1687] This system is comprised of a device where users input their desired learning data, a data processing device (server) that analyzes the data to generate appropriate problem data sets and processes and manages the analysis results, and generative artificial intelligence. This system makes it possible to provide problem sets optimized for the user's learning needs and provide rapid feedback.

[1688] 1. User terminal configuration and operation

[1689] The device operated by the user can be a tablet or PC. The user inputs their desired study data through the device. Specifically, they input the subject they want to study (e.g., mathematics), the range of study (e.g., geometry), and their strengths and weaknesses.

[1690] Examples:

[1691] Student A logs in to the tablet device and enters that he or she is focusing on mathematics geometry, particularly the properties of triangles, which is something he or she is weak at.

[1692] 2. Server Configuration and Operation

[1693] The server analyzes the received learning data and sends the analysis results to the generative AI. The analysis is performed using Python scripts and a database management system. The server also plays a role in sending the problem data received from the generative AI to the user's device.

[1694] Examples:

[1695] The server analyzes Student A's data and identifies learning needs specific to "triangles in geometry." It then sends a prompt to the generative AI to "generate a set of problems related to the properties of triangles."

[1696] 3. Structure and operation of generative artificial intelligence

[1697] The generative AI generates a set of question data based on the analysis results. The generated questions are adjusted according to the user's strengths and weaknesses and learning progress. The generated set of question data is sent to the user's device via the server.

[1698] Examples:

[1699] The generative artificial intelligence generates a balanced set of problems for Student A, including basic problems on the "properties of triangles," applied problems, and problems from other related areas, and sends it back to the server.

[1700] Example prompt sentence:

[1701] "Generate a problem set for Student A that includes basic problems about the properties of triangles, applied problems, and related problems from another area."

[1702] 4. User answers and feedback

[1703] The user answers questions on their device and sends the data to the server, which then scores the answers and generates feedback, which is then sent back to the user's device and displayed to the user.

[1704] Examples:

[1705] When Student A solves the displayed problem and enters the answer, the device sends the answer data to the server. The server grades the answer and generates feedback such as "This is the correct answer" or "This is incorrect" and sends it to Student A's device.

[1706] In this way, the present invention allows users to receive an individually optimized learning experience, resulting in efficient and effective learning.

[1707] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1708] Step 1:

[1709] The user inputs the desired learning data into the terminal.

[1710] Specific behavior:

[1711] The user uses a tablet device or computer to input the subject being studied (e.g., mathematics), range of study (e.g., geometry), and strengths and weaknesses (e.g., properties of triangles).

[1712] input:

[1713] Information on study subjects, scope, strengths and weaknesses.

[1714] output:

[1715] Learning preference data entered into the terminal.

[1716] Step 2:

[1717] The terminal transmits the learning request data to the server.

[1718] Specific behavior:

[1719] The device uses the REST API to send the learning request data to the server.

[1720] input:

[1721] Learning preference data entered into the terminal.

[1722] output:

[1723] Learning preference data sent to the server.

[1724] Step 3:

[1725] The server analyzes the learning preference data.

[1726] Specific behavior:

[1727] The server uses a Python script to analyze the received data and identify the user's learning needs.

[1728] input:

[1729] Learning preference data sent to the server.

[1730] output:

[1731] User learning needs data as a result of analysis.

[1732] Step 4:

[1733] The server sends the analysis results to the generative AI.

[1734] Specific behavior:

[1735] The server sends the analysis results to the generative AI as a prompt.

[1736] input:

[1737] User learning needs data as a result of analysis.

[1738] output:

[1739] The prompt sent to the generative AI.

[1740] Example prompt sentence:

[1741] "Generate a problem set for Student A that includes basic problems about the properties of triangles, applied problems, and related problems from another area."

[1742] Step 5:

[1743] The generative AI generates a set of problem data and sends it back to the server.

[1744] Specific behavior:

[1745] The generative AI generates a set of problem data based on the prompt text and sends it back to the server.

[1746] input:

[1747] The prompt sent to the generative AI.

[1748] output:

[1749] Generated problem data set.

[1750] Step 6:

[1751] The server sends a set of question data to the terminal.

[1752] Specific behavior:

[1753] The server sends the generated question data set to the terminal in JSON format.

[1754] input:

[1755] Generated problem data set.

[1756] output:

[1757] A set of question data in JSON format sent to the device.

[1758] Step 7:

[1759] The terminal displays the problem data set to the user.

[1760] Specific behavior:

[1761] The terminal displays the received question data group to the user.

[1762] input:

[1763] The problem data set sent to the terminal.

[1764] output:

[1765] A set of problem data displayed on the user's terminal.

[1766] Step 8:

[1767] The user solves the problem and inputs the answer data into the terminal.

[1768] Specific behavior:

[1769] The user solves the problem on the terminal and inputs the answer data.

[1770] input:

[1771] User answer data.

[1772] output:

[1773] Answer data entered into the terminal.

[1774] Step 9:

[1775] The terminal sends the answer data to the server.

[1776] Specific behavior:

[1777] The device sends the answer data to the server via the REST API.

[1778] input:

[1779] Answer data entered into the terminal.

[1780] output:

[1781] The answer data sent to the server.

[1782] Step 10:

[1783] The server grades the answer data and generates feedback.

[1784] Specific behavior:

[1785] The server uses a Python script to grade the answer data and generate feedback.

[1786] input:

[1787] The answer data sent to the server.

[1788] output:

[1789] Generated feedback data.

[1790] Step 11:

[1791] The server sends the feedback to the device.

[1792] Specific behavior:

[1793] The server sends the feedback data to the terminal.

[1794] input:

[1795] Generated feedback data.

[1796] output:

[1797] Feedback data sent to the device.

[1798] Step 12:

[1799] The device displays the feedback to the user.

[1800] Specific behavior:

[1801] The terminal displays the received feedback to the user.

[1802] input:

[1803] Feedback data sent to the device.

[1804] output:

[1805] Feedback displayed on the user's device.

[1806] (Application example 1)

[1807] 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."

[1808] Conventional learning systems have had difficulty providing content optimized to the learning needs of each individual student. Furthermore, they lacked a means to provide immediate, appropriate feedback on answers, which resulted in insufficient improvement in students' learning effectiveness.

[1809] 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.

[1810] In this invention, the server includes a terminal for inputting desired learning data, a means for analyzing data received from the terminal, a means for transmitting problem sets received from the generative AI to the terminal, a means for a user to input answers and transmit the answers to the server, a means for the server to grade the answer data received and generate feedback, and a means for transmitting the generated feedback to the terminal, thereby making it possible to provide problem sets optimized for the learning needs of each student and provide immediate feedback on their answers.

[1811] "Study preference data" is information such as the subjects the user wants to study, the scope of study, areas of strength and weakness, etc.

[1812] A "terminal" is a device that allows a user to input desired study data and answers and transmit them to a server.

[1813] A "server" is a device that analyzes data received from a terminal, sends instructions to the generative AI, and transmits the generated data to the terminal.

[1814] "Generative AI" is artificial intelligence that generates individually optimized problem sets based on data received from a server.

[1815] A "problem set" is a set of practice questions and learning materials provided to users that are generated by generative AI based on desired learning data.

[1816] "Answer data" is data that includes the answers that a user gives to a question set.

[1817] "Feedback" is information including the results of scoring the user's answers, explanations, and areas for improvement.

[1818] The "display means" is a function for displaying the generated problem set and feedback on the user terminal.

[1819] "Means of transmission" refers to the function of transmitting data generated by the generative AI and data from the server to the user's terminal.

[1820] This invention is a system that combines terminals, servers, and generative AI to provide problem sets optimized for the learning needs of each student. The elements and specific steps for realizing this system are described below.

[1821] Overall system overview

[1822] The system consists of a device used by the user (e.g., a smartphone), a server, and a generative AI. The user inputs the data they wish to learn through the device, which is then sent to the generative AI via the server. The generative AI generates an individually optimized problem set based on the received data, which is then sent back to the device via the server. Finally, the user can solve the customized problem set on their device.

[1823] Device behavior

[1824] The user operates the terminal to input their desired study data. Specifically, they input the subject they want to study (e.g., mathematics), the range of study (e.g., geometry), and their strengths and weaknesses. The terminal then sends this information to the server.

[1825] Example: A student logs in to their smartphone and inputs that they are focusing on geometry in mathematics, especially that they are weak in the "properties of triangles." The device then sends this data to a server.

[1826] Server Operation

[1827] The server analyzes the learning request data received from the device. Based on the analysis results, it sends data to the generative AI requesting it to generate an optimized problem set. When the problem set is returned from the generative AI, it is sent to the user's device.

[1828] Example: The server analyzes the student's data and instructs the generative AI to create problems specific to "geometry triangles." The server receives the necessary problem set from the generative AI and sends it to the student's device.

[1829] How generative AI works

[1830] The generative AI generates an appropriate problem set based on the learning preference data received from the server and the analysis results. The generated problems are adjusted according to the user's strengths and weaknesses and learning progress.

[1831] Example: A generative AI generates a balanced set of problems for a student, including basic problems on the "properties of triangles," applied problems, and problems from other areas, and sends them back to the server.

[1832] View and answer problem sets

[1833] The terminal receives the problem set from the server and displays it to the user. The user solves the problem and inputs the answer. The terminal also sends the answer data to the server.

[1834] Example: A student solves a customized set of problems displayed on their smartphone, enters their answers, and sends them to a server.

[1835] Providing Feedback

[1836] The server automatically scores the received answer data and generates feedback, which is then sent back to the user's device and displayed to the user.

[1837] Example: The server grades the student's answers and generates feedback such as "This is the correct answer" or "This is the wrong answer." This feedback is sent to the student's device and displayed.

[1838] Hardware and software used

[1839] Device: Smartphone

[1840] Server: A server with data analysis and transmission / reception functions

[1841] Generative AI: Artificial intelligence that generates problem sets based on user learning data

[1842] Software libraries: requests (for sending and receiving data), framework for displaying user interfaces

[1843] Prompt Sentence Examples

[1844] Here is the user data:

[1845] Subject: Mathematics

[1846] Range: Geometry

[1847] Weakness: Triangular nature

[1848] Based on this data, please suggest study materials:

[1849] basic problems

[1850] Applied Problems

[1851] Video lectures

[1852] Additional questions based on feedback

[1853] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1854] Step 1:

[1855] The user operates the device to input desired study data. The user inputs the subject they wish to study, the range of study, and areas of strength and weakness, and sends this data from the device to the server. Specifically, the user enters the subject (mathematics), range of study (geometry), and areas of strength and weakness (e.g., "properties of triangles") into the smartphone input form, and then presses the send button.

[1856] Input: Study preferences (subjects, scope, areas of strength and weakness)

[1857] Output: Learning preference data sent to the server

[1858] Step 2:

[1859] The server analyzes the learning request data received from the device. Here, the data is formatted and preprocessed. As a result of the analysis, the learning needs become clear and the data to be passed to the generative AI is determined.

[1860] Input: Study Desired Data

[1861] Output: Analysis results (learning needs)

[1862] Step 3:

[1863] The server sends data to the generative AI to request it to generate an optimized problem set based on the analysis results. The generative AI then receives the analysis results and begins the process of generating a problem set.

[1864] Input: Analysis results

[1865] Output: Instruction data for generative AI

[1866] Step 4:

[1867] Based on the analysis results, the generative AI generates individually optimized problem sets, using prompts to generate appropriate problem sets (basic problems, applied problems, video lectures, additional problems, etc.).

[1868] Input: Analysis results, prompt text

[1869] Output: Optimized problem set

[1870] Step 5:

[1871] The server sends the problem set received from the generative AI to the device, allowing the user to receive the problem set on their smartphone.

[1872] Input: Optimized problem set

[1873] Output: Data sent to the terminal

[1874] Step 6:

[1875] The device displays the received problem set to the user, who then solves the problem and enters the answer. Specifically, the problem is displayed on the smartphone screen, and the user enters the answer in an input form.

[1876] Input: Data to send to the terminal

[1877] Output: The problem set that is displayed to the user

[1878] Step 7:

[1879] The user inputs the answer and sends the answer data from the terminal to the server, where it is ready to be analyzed and scored.

[1880] Input: User's answer data

[1881] Output: Answer data sent to the server

[1882] Step 8:

[1883] The server scores the received answer data and generates feedback. Based on the scoring results, it determines whether the answer is correct or incorrect and generates useful feedback.

[1884] Input: Answer data

[1885] Output: Generated feedback

[1886] Step 9:

[1887] The server sends the generated feedback to the terminal, allowing the user to receive the feedback immediately.

[1888] Input: Generated feedback

[1889] Output: Data sent to the terminal

[1890] Step 10:

[1891] The device displays the received feedback to the user, who can then check their own answers and use the feedback to improve their future learning.

[1892] Input: Data to send to the terminal

[1893] Output: Feedback that is displayed to the user

[1894] 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.

[1895] The present invention is a system that combines a terminal, a server, a generative AI, and an emotion engine that recognizes the user's emotions to provide problem sets optimized for each student's learning needs and emotional state. A specific embodiment of this system is shown below.

[1896] 1. Overview of the entire system

[1897] This system consists of a device used by the user (e.g., a tablet device), a server, a generative AI, and an emotion engine. When a user inputs the data they wish to learn through the device, the emotion engine recognizes the user's emotional data, and this data is sent to the generative AI via the server. Based on the received data, the generative AI generates an individually optimized problem set, which is then sent to the device via the server again. Ultimately, the user can solve a customized problem set on the device that also takes into account their emotional state.

[1898] 2. User terminal operation

[1899] The user operates the device to input their desired study data. Specifically, they input the subject they want to study (e.g., mathematics), the range of subjects (e.g., geometry), and their strengths and weaknesses. The device's built-in emotion engine also uses a camera and microphone to recognize emotion data from the user's facial expressions and voice. The device then sends this information to the server.

[1900] Example: Student A logs in to a tablet device and inputs that he / she is focusing on mathematics geometry, especially the "properties of triangles," and is weak in this field. The emotion engine analyzes Student A's facial expressions and recognizes signs of stress. The device sends the learning preference data and emotion data to the server.

[1901] 3. Server Operation

[1902] The server analyzes the learning preference data and emotional data received from the device. Based on the analysis results, it prepares data to request the generative AI to generate a customized problem set and sends this to the generative AI. The emotional data is used as additional information to adjust the difficulty and type of problems.

[1903] Example: The server analyzes Student A's data and instructs the generative AI to create problems specific to "geometry triangles." It also adjusts the difficulty of the problems appropriately based on emotional data to reduce stress. The server receives the necessary problem set from the generative AI and sends it to Student A's device.

[1904] 4. How generative AI works

[1905] The generative AI generates an appropriate set of problems based on the learning preference and emotional data received from the server. The problems are adjusted based on the user's strengths and weaknesses, learning progress, and emotional state.

[1906] Example: A generative AI generates a balanced set of problems for Student A, including basic problems on the "properties of triangles," applied problems, and problems from other areas, and sends them back to the server. Based on stress data, the initial problems are set relatively easy.

[1907] 5. Viewing and answering problem sets

[1908] The terminal receives the problem set from the server and displays it to the user. The user solves the problem and inputs the answer. The input answer is sent from the terminal to the server.

[1909] Example: Student A solves a customized problem set displayed on a tablet device. When he enters his answers, they are sent to the server.

[1910] 6. Providing Feedback

[1911] The server automatically scores the received answer data and generates feedback. The generated feedback is then sent back to the user's device and displayed to the user. The emotion engine then analyzes the user's response and reflects it in future learning plans.

[1912] Example: The server grades Student A's answers and generates feedback such as "This is the correct answer" or "This is incorrect." The emotion engine also analyzes Student A's facial expressions when receiving the feedback and reflects this in the next learning session. This feedback is sent to Student A's device and displayed.

[1913] The above-described embodiment allows students (users) to receive a learning experience optimized for their needs and emotional state, thereby enabling efficient and effective learning, improving academic ability, and reducing psychological stress.

[1914] The processing flow will be explained below.

[1915] Step 1:

[1916] The user starts the application on the device and enters the user ID and password on the login screen. The device sends this login information to the server.

[1917] Step 2:

[1918] The server receives the login information and authenticates the user by checking the database. If authentication is successful, the server retrieves the user's past learning history data from the database and sends it to the terminal.

[1919] Step 3:

[1920] The device displays the received learning history data and prompts the user to enter their desired learning data. The user enters the subjects they wish to study, the scope of study, their strengths and weaknesses, etc. The emotion engine also uses a camera and microphone to recognize emotional data from the user's facial expressions and voice. The device then sends this data to the server.

[1921] Step 4:

[1922] The server receives the learning preference data and emotion data, analyzes it in combination with existing learning history data, and prepares data to request the generative AI to generate a customized problem set based on the analysis results, and sends this data to the generative AI.

[1923] Step 5:

[1924] The generative AI generates individually optimized problem sets based on the data received from the server, and the generated problem sets are sent back to the server.

[1925] Step 6:

[1926] The server receives the problem set returned by the generative AI and sends it to the user's device, where the user receives a customized problem set that takes into account their emotional state.

[1927] Step 7:

[1928] The terminal displays the received problem set to the user. The user solves the displayed problem and inputs the answer. The input answer is sent from the terminal to the server.

[1929] Step 8:

[1930] The server analyzes the answer data received from the user and automatically scores them. It generates the scoring results and feedback and sends them to the user's device. The emotion engine also analyzes the user's reaction to the feedback and reflects that data in future study plans.

[1931] Step 9:

[1932] The device displays the feedback received from the server to the user. The user checks the feedback and plans their next learning. The emotion engine analyzes the user's reaction and updates the emotion data as necessary.

[1933] Example 2

[1934] 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."

[1935] Conventional learning support systems generate problem sets based solely on the user's learning preferences, which does not take into account the user's emotional state, resulting in poor learning outcomes. Furthermore, feedback is not provided in real time, making it difficult to maintain the user's motivation. These issues must be resolved to improve the user's learning experience.

[1936] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1937] In this invention, the server includes a means for analyzing learning preference data and emotional data, a means for cooperating with a generative AI that generates individually optimized problem sets, and a means for receiving and scoring the user's answer data and generating feedback. This makes it possible to provide a customized problem set that takes the user's emotional state into consideration, and improve the user's learning effectiveness and motivation through real-time feedback.

[1938] "Study preference data" is data that indicates the user's learning preferences, such as the subjects and scope they wish to study, and their strengths and weaknesses.

[1939] "Emotion data" is data that represents the user's emotional state, such as stress, joy, excitement, or other psychological state.

[1940] A "terminal" is a device through which a user inputs learning preference data and emotion data, and specifically refers to a tablet terminal, smartphone, PC, etc.

[1941] The "server" is a computer system that receives and analyzes data sent from the device, and works in conjunction with the generative AI and the device to perform various learning support processes.

[1942] "Generative AI" is an artificial intelligence system that generates individually optimized problem sets based on learning preference data and emotional data received from a server.

[1943] A "problem set" refers to multiple learning problems presented to the user, generated by generative AI based on the user's learning preferences and emotional data.

[1944] "Feedback" is information that the server uses to grade the user's answer data and inform the user whether the answer was correct or not, and what improvements need to be made.

[1945] The present invention is a system that combines a terminal, a server, a generative AI, and an emotion engine that recognizes the user's emotions to provide problem sets optimized for each student's learning needs and emotional state. A specific embodiment of this system is shown below.

[1946] Overall system overview

[1947] This system consists of a device used by the user (e.g., a tablet device), a server, a generative AI, and an emotion engine. When a user inputs the data they wish to learn through the device, the emotion engine recognizes the user's emotional data, and this data is sent to the generative AI via the server. Based on the received data, the generative AI generates an individually optimized problem set, which is then sent to the device via the server again. Ultimately, the user can solve a customized problem set on the device that also takes into account their emotional state.

[1948] User terminal operation

[1949] The user operates the device to input their desired study data. Specifically, they input the subject they want to study (e.g., mathematics), the range of subjects (e.g., geometry), and their strengths and weaknesses. The device's built-in emotion engine also uses a camera and microphone to recognize emotion data from the user's facial expressions and voice. The device then sends this information to the server.

[1950] Examples:

[1951] Student A logs in to a tablet device and inputs that he / she is focusing on mathematics geometry, especially the "properties of triangles," and is weak in this field. The emotion engine analyzes Student A's facial expressions and recognizes signs of stress. The device then sends the learning preference data and emotion data to the server.

[1952] Prompt statement:

[1953] "I'm eager to learn about geometry, but I just can't understand the properties of triangles. Emotionally, I'm feeling a bit stressed."

[1954] Server Operation

[1955] The server analyzes the learning preference data and emotional data received from the device. Based on the analysis results, it prepares data to request the generative AI to generate a customized problem set and sends this to the generative AI. The emotional data is used as additional information to adjust the difficulty and type of problems.

[1956] Examples:

[1957] The server analyzes Student A's data and instructs the generative AI to create problems specific to "geometric triangles." It also adjusts the difficulty of the problems appropriately based on emotional data to reduce stress. The server receives the necessary problem set from the generative AI and sends it to Student A's device.

[1958] How generative AI works

[1959] The generative AI generates an appropriate set of problems based on the learning preference and emotional data received from the server. The problems are adjusted based on the user's strengths and weaknesses, learning progress, and emotional state.

[1960] Examples:

[1961] The generative AI generates a balanced set of problems for Student A, including basic problems on the "properties of triangles," applied problems, and problems from other areas, and sends it back to the server. Based on the stress data, the initial problems are set relatively easy.

[1962] View and answer problem sets

[1963] The terminal receives the problem set from the server and displays it to the user. The user solves the problem and inputs the answer. The input answer is sent from the terminal to the server.

[1964] Examples:

[1965] Student A solves a customized problem set displayed on a tablet device. When he enters his answers, they are sent to the server.

[1966] Providing Feedback

[1967] The server automatically scores the received answer data and generates feedback. The generated feedback is then sent back to the user's device and displayed to the user. The emotion engine then analyzes the user's response and reflects it in future learning plans.

[1968] Examples:

[1969] The server grades Student A's answers and generates feedback such as "This is the correct answer" or "This is incorrect." The emotion engine also analyzes Student A's facial expressions when receiving the feedback and reflects this in the next learning session. This feedback is sent to Student A's device and displayed.

[1970] The above-described embodiment allows students (users) to receive a learning experience optimized for their needs and emotional state, thereby enabling efficient and effective learning, improving academic ability, and reducing psychological stress.

[1971] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1972] Step 1:

[1973] The user operates the terminal and inputs their desired study data. Specifically, the user inputs the subjects, scope, and areas of strength and weakness they wish to study, which then become the input data for the terminal. The input data is sent to the computer system as "study preference data."

[1974] Specific behavior:

[1975] Student A types "math," "geometry," and "properties of triangles" into his tablet.

[1976] input:

[1977] Information about the subjects you want to study, the scope, and your strengths and weaknesses

[1978] output:

[1979] Learning preference data

[1980] Step 2:

[1981] The device uses an emotion engine to acquire emotion data. The camera and microphone are used to capture the user's facial expressions and voice in real time, which the emotion engine then analyzes. The analysis results become "emotion data."

[1982] Specific behavior:

[1983] The camera on the tablet device captures Student A's facial expression, and "stress" is recognized through facial analysis.

[1984] input:

[1985] User's facial expressions and voice

[1986] output:

[1987] Emotional Data

[1988] Step 3:

[1989] The device sends the learning preference data and emotion data to the server, using the HTTPS protocol to ensure data security.

[1990] Specific behavior:

[1991] The tablet device sends data including "mathematics," "geometry," "weakness in the properties of triangles," and "stress" to the server.

[1992] input:

[1993] Learning preference data, emotion data

[1994] output:

[1995] Data sent to the server

[1996] Step 4:

[1997] The server analyzes the training data and emotion data. It uses a database and shell scripts to perform the appropriate analysis. The analysis results become the input data for the next step.

[1998] Specific behavior:

[1999] The server identifies high learning needs and "stress" regarding "geometry" and "properties of triangles."

[2000] input:

[2001] Learning preference data, emotion data

[2002] output:

[2003] Analysis results

[2004] Step 5:

[2005] The server requests the generative AI to generate a problem set based on the analysis results, and sends an API request to the generative AI to generate the necessary data.

[2006] Specific behavior:

[2007] The server requests the generative AI to generate a problem set that corresponds to "geometry," "properties of triangles," and "stress level."

[2008] input:

[2009] Analysis results

[2010] output:

[2011] Data sent to generative AI

[2012] Step 6:

[2013] The generative AI generates a problem set based on the received data. It uses a generative AI model to generate problems based on a pre-trained dataset and sends them back to the server.

[2014] Specific behavior:

[2015] The generative AI creates balanced problems related to the "properties of triangles" and sends them back to the server.

[2016] input:

[2017] Generation request data

[2018] output:

[2019] Generated problem set

[2020] Step 7:

[2021] The server sends the generated problem set to the terminal, again using the HTTPS protocol.

[2022] Specific behavior:

[2023] The server sends a set of problems about the properties of triangles to Student A's tablet device.

[2024] input:

[2025] Generated problem set

[2026] output:

[2027] Problem set sent to device

[2028] Step 8:

[2029] The terminal displays the received problem set to the user. The user interface has an intuitive and easy-to-understand design.

[2030] Specific behavior:

[2031] The tablet device displays a question about the properties of triangles to Student A.

[2032] input:

[2033] Problem set sent to device

[2034] output:

[2035] Issues seen by users

[2036] Step 9:

[2037] The user answers the questions on the device and sends them. The device then sends the answer data to the server.

[2038] Specific behavior:

[2039] Student A answers the question, enters the answer, and presses the send button.

[2040] input:

[2041] User Answer

[2042] output:

[2043] Answer data sent to the server

[2044] Step 10:

[2045] The server scores the received answer data and generates feedback using a scoring algorithm for high-precision analysis.

[2046] Specific behavior:

[2047] The server grades Student A's answers and generates feedback.

[2048] input:

[2049] Answer data

[2050] output:

[2051] Scoring results and feedback

[2052] Step 11:

[2053] The server generates feedback and sends it to the device, along with a comment that takes into account the emotion data.

[2054] Specific behavior:

[2055] The server sends feedback to Student A's device, such as "This is the correct answer" or "This is incorrect."

[2056] input:

[2057] feedback

[2058] output:

[2059] Feedback sent to device

[2060] Step 12:

[2061] The device displays the feedback to the user, who can then accept the feedback and enter additional comments.

[2062] Specific behavior:

[2063] The tablet device displays feedback to Student A such as "This is the correct answer" or "This is incorrect."

[2064] input:

[2065] Feedback sent to device

[2066] output:

[2067] Feedback displayed to the user

[2068] Step 13:

[2069] The device uses an emotion engine to analyze the user's reaction to the displayed feedback and reflects this in the next learning content.

[2070] Specific behavior:

[2071] The tablet camera reanalyzes Student A's facial expressions to confirm stress relief. This information is reflected in the next learning session.

[2072] input:

[2073] User Reactions

[2074] output:

[2075] Data to be reflected in the next study plan

[2076] (Application example 2)

[2077] 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."

[2078] Many modern learning systems can provide problem sets optimized for individual learning needs, but they rarely take the user's emotional state into consideration. As a result, learning effectiveness can decrease and motivation to learn can decline. Furthermore, even in physical stores, there is a lack of product recommendations that take the customer's emotional state into account, resulting in low customer satisfaction. Therefore, there is a need for the development of a system that analyzes users' emotions and provides appropriate learning and product recommendations based on their state.

[2079] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2080] In this invention, the server includes means for acquiring emotional data using an emotion engine that recognizes the emotional state of the user, means for the server to generate product suggestions based on the emotional data in accordance with the emotional state, and means for presenting the suggested product information to the user, thereby enabling an individually optimized learning experience and product suggestions tailored to the user's emotional state.

[2081] A "terminal" is an information processing device into which a user inputs desired study data and which displays problem sets and product information sent from a server.

[2082] The "server" is a central information processing device that analyzes data received from the terminal and works in conjunction with the generative AI and emotion engine to generate and transmit optimized problem sets and product proposals.

[2083] "Generative AI" is an artificial intelligence system that generates individually optimized problem sets and product suggestions based on data sent from a server.

[2084] An "emotion engine" is software or hardware that recognizes the user's emotional state from facial expressions, voice, etc., and acquires emotional data.

[2085] "Emotion data" is information indicating the user's emotional state obtained by the emotion engine.

[2086] "Product proposal" is data that the server generates based on emotion data and other information, proposing products suitable for the user.

[2087] A "problem set" is a series of problems generated by generative AI that are optimized for the user's learning needs.

[2088] The "display means" is a function or device for visually presenting the problem set and product suggestions received by the terminal to the user.

[2089] "User" refers to an individual who uses the system to input desired study data and view and operate the displayed problem sets and product information.

[2090] This invention is a system consisting of a terminal, a server, a generative AI, and an emotion engine, which provides problem sets and product suggestions optimized for the user's learning needs and emotional state.

[2091] 1. Overview of the entire system

[2092] This system consists of a device used by the user, a server that analyzes the data, a generative AI, and an emotion engine. The user inputs the learning data they wish to use into the device, and the emotion engine recognizes the user's emotional data. This data is sent to the generative AI via the server, and the generative AI uses the received data to generate individually optimized problem sets and product suggestions, which are then sent back to the device via the server.

[2093] 2. User terminal operation

[2094] The user operates the device to input their study preferences. Specifically, they input the subjects and scope they want to study, as well as their strengths and weaknesses. The device's built-in emotion engine also uses a camera and microphone to recognize emotional data from the user's facial expressions and voice. The device then sends this information to the server.

[2095] Specific examples

[2096] User A logs in to their smartphone and enters their desired learning data. User A's emotion engine then detects stress levels from their facial expressions. This data is then sent to the server.

[2097] 3. Server Operation

[2098] The server analyzes the learning preference data and emotional data received from the device. Based on the analysis results, it prepares data to request the generative AI to generate individually optimized problem sets and product proposals, and sends this to the generative AI. The emotional data is used as additional information to adjust the difficulty and type of problems or the content of product proposals.

[2099] Specific examples

[2100] The server analyzes User A's data and instructs the generative AI on questions specialized for specific learning topics. It also appropriately adjusts the difficulty of the suggested products and questions based on the emotional data. The problem sets and product suggestions received from the generative AI are then sent back to User A's device.

[2101] 4. How generative AI works

[2102] The generative AI generates appropriate problem sets and product suggestions based on the learning preference and emotional data sent from the server. The generated content is adjusted based on the user's strengths and weaknesses, learning progress, and even emotional state.

[2103] Specific examples

[2104] The generative AI generates a problem set related to the properties of triangles and product suggestions for relaxation items for User A. The generated content is sent to the device via the server.

[2105] 5. Display and suggest problem sets and product suggestions

[2106] The terminal receives the problem sets and product suggestions from the server and displays them to the user, who can then solve the problems and check the product suggestions.

[2107] Specific examples

[2108] User A solves a customized problem set displayed on his / her smartphone. At the same time, he / she checks the product suggestions displayed and selects the products he / she is interested in.

[2109] 6. Providing Feedback

[2110] The server scores and evaluates the received answer data and product selection information, and generates feedback. The generated feedback is then sent back to the user's device and displayed to the user. The emotion engine then analyzes the user's reactions again and reflects them in future study plans and product suggestions.

[2111] Specific examples

[2112] The server grades User A's answers and generates feedback such as "This is the correct answer" or "This is incorrect." Furthermore, the emotion engine analyzes User A's facial expressions when receiving the feedback and reflects this in the next learning session and product suggestions. This feedback is sent to User A's device and displayed.

[2113] Prompt Sentence Examples

[2114] "Please suggest the best relaxation products for customers who are feeling stressed."

[2115] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2116] Step 1:

[2117] The user operates the terminal to input the data they wish to learn, and emotional data is collected using a camera and microphone.

[2118] (Input) User's desired learning data (e.g., subject and scope) and emotional data (e.g., facial expressions and voice)

[2119] (Operation) The device allows the user to input the desired learning data, and the built-in emotion engine uses the camera and microphone to analyze the user's emotions and recognize the emotion data.

[2120] (Output) The learning target data and emotion data are sent from the terminal to the server.

[2121] Step 2:

[2122] The server analyzes the learning preference data and emotion data received from the terminal.

[2123] (Input) Learning preference data and emotion data sent from the device

[2124] (Operation) The server analyzes the learning preference data to identify the user's needs. Based on the emotion data, the server evaluates the user's emotional state.

[2125] (Output) Data based on the analysis results is sent to the generative AI.

[2126] Step 3:

[2127] Based on the data received from the server, the generative AI generates individually optimized problem sets and product suggestions.

[2128] (Input) Analysis data sent from the server

[2129] (Operation) Generative AI generates problem sets and product suggestions based on the user's learning needs and emotional state. The generative AI model is used to generate suggestions in response to a specific prompt (e.g., "Please suggest the best relaxation products for a customer who is feeling stressed.").

[2130] (Output) The generated problem set and product proposals are sent back to the server.

[2131] Step 4:

[2132] The server sends the problem sets and product suggestions received from the generative AI to the terminal.

[2133] (Input) Problem sets and product suggestions sent from generative AI

[2134] (Operation) The server organizes the received data and sends it to the terminal.

[2135] (Output) The problem set and product suggestions are sent to the terminal.

[2136] Step 5:

[2137] The terminal displays the transmitted problem set and product suggestions to the user.

[2138] (Input) Problem sets and product proposals sent from the server

[2139] (Operation) The data received by the terminal is displayed on the screen for visual display to the user.

[2140] (Output) The user can see the problem set and product suggestions.

[2141] Step 6:

[2142] The user solves the displayed problem set and enters the answers into the terminal, or checks and selects product suggestions.

[2143] (Input) User answers and product selection information

[2144] (Operation) The terminal collects the user's input data and sends it to the server.

[2145] (Output) Answer data and product selection information are sent from the terminal to the server.

[2146] Step 7:

[2147] The server scores the answers received, generates feedback, and analyzes the user's reactions using an emotion engine.

[2148] (Input) Answer data and emotion data sent from the device

[2149] (Operation) The server automatically scores the answer data and generates feedback. At the same time, the emotion engine analyzes the user's reactions and reflects them in future study plans and product suggestions.

[2150] (Output) The generated feedback and analysis results are sent to the terminal and displayed to the user.

[2151] Step 8:

[2152] Feedback from the server and the next learning plan are displayed on the device, allowing the user to proceed with their next learning or purchase.

[2153] (Input) Feedback sent from the server and next lesson plan information

[2154] (Operation) The device displays feedback and upcoming study plans to the user, allowing the user to prepare for the next study session.

[2155] (Output) The user is ready to learn or buy something next.

[2156] 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.

[2157] 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.

[2158] 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.

[2159] 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.

[2160] FIG. 9 illustrates 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 behaviors 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.

[2161] 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.

[2162] 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).

[2163] 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.

[2164] 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."

[2165] 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.

[2166] 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).

[2167] 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.

[2168] 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.

[2169] 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.

[2170] 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.

[2171] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, 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 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.

[2172] 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.

[2173] 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.

[2174] 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.

[2175] 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.

[2176] 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.

[2177] The following is further disclosed regarding the above embodiment.

[2178] (Claim 1)

[2179] A terminal for inputting desired learning data;

[2180] a server that analyzes data received from the terminal;

[2181] A generative AI that receives the analysis results from the server and generates individually optimized problem sets;

[2182] A server that transmits the problem set received from the generative AI to a terminal;

[2183] means for displaying the transmitted problem set to a user in the terminal;

[2184] A system including:

[2185] (Claim 2)

[2186] The system of claim 1, which utilizes generative AI to generate individually optimized problem sets based on learning preference data and past learning history data.

[2187] (Claim 3)

[2188] The system of claim 1 further includes a means for the server to automatically send a problem set generated by the generative AI to a terminal after input of desired learning data, and for the terminal to display the problem set to the user.

[2189] "Example 1"

[2190] (Claim 1)

[2191] a device for inputting learning preference data;

[2192] a data processing device for analyzing data received from said device;

[2193] a generative artificial intelligence that receives the analysis results from the data processing device and generates individually optimized problem data sets;

[2194] a data processing device that transmits the question data group received from the generative artificial intelligence to a device;

[2195] means for displaying the transmitted question data group to a user in the device;

[2196] means for transmitting user answer data from said device to said data processing device;

[2197] a data processing device for scoring the answer data and generating feedback;

[2198] means for transmitting and displaying said feedback to said device;

[2199] A system including:

[2200] (Claim 2)

[2201] The system of claim 1, which utilizes generative artificial intelligence to generate individually optimized question data sets based on learning desire data and past learning history data.

[2202] (Claim 3)

[2203] The system of claim 1 further comprises a means for automatically transmitting a set of question data generated by the generative artificial intelligence to a data processing device after input of the desired learning data, and for the device to display the set of question data to the user.

[2204] "Application Example 1"

[2205] (Claim 1)

[2206] A terminal for inputting desired learning data;

[2207] a server that analyzes data received from the terminal;

[2208] A generative AI that receives the analysis results from the server and generates individually optimized problem sets;

[2209] A server that transmits the problem set received from the generative AI to a terminal;

[2210] means for displaying the transmitted problem set to a user in the terminal;

[2211] A means for a user to input an answer and transmit the answer to a server;

[2212] means for scoring the received answer data by the server and generating feedback;

[2213] means for transmitting the generated feedback to the terminal;

[2214] A system including:

[2215] (Claim 2)

[2216] The system of claim 1, which utilizes generative AI to generate individually optimized problem sets based on learning preference data and past learning history data.

[2217] (Claim 3)

[2218] The system of claim 1 further includes a means for the server to automatically send a problem set generated by the generative AI to a terminal after input of desired learning data, and for the terminal to display the problem set to the user.

[2219] "Example 2: Combining Emotion Engines"

[2220] (Claim 1)

[2221] a terminal for inputting learning preference data and emotion data;

[2222] a server that analyzes the learning intent data and emotion data received from the terminal;

[2223] A generative AI that receives the analysis results from the server and generates individually optimized problem sets;

[2224] A server that transmits the problem set received from the generative AI to a terminal;

[2225] means for displaying the transmitted problem set to a user in the terminal;

[2226] A server that receives and grades the user's answer data, generates feedback, and sends it to the device;

[2227] the terminal has means for displaying feedback to the user and means for reanalyzing the user's emotion data;

[2228] A system including:

[2229] (Claim 2)

[2230] 10. The system of claim 1, utilizing generative AI to generate individually optimized problem sets based on learning desire data and emotion data.

[2231] (Claim 3)

[2232] The system of claim 1 further comprises a means for acquiring emotional data after inputting desired learning data, a means for the server to automatically transmit the problem set generated by the generative AI to the terminal, and a means for the terminal to display the problem set to the user.

[2233] "Application example 2 when combining emotion engines"

[2234] (Claim 1)

[2235] A terminal for inputting desired learning data;

[2236] a server that analyzes data received from the terminal;

[2237] A generative AI that receives the analysis results from the server and generates individually optimized problem sets;

[2238] A server that transmits the problem set received from the generative AI to a terminal;

[2239] means for displaying the transmitted problem set to a user in the terminal;

[2240] means for acquiring emotion data using an emotion engine that recognizes the user's emotional state;

[2241] a means for generating a product proposal according to the emotional state based on the emotion data by the server;

[2242] means for presenting the suggested product information to a user;

[2243] A system including:

[2244] (Claim 2)

[2245] The system of claim 1, which utilizes generative AI to generate individually optimized problem sets based on learning preference data and past learning history data.

[2246] (Claim 3)

[2247] The system of claim 1 further includes a means for the server to automatically send a problem set generated by the generative AI to a terminal after input of desired learning data, and for the terminal to display the problem set to the user. [Explanation of symbols]

[2248] 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 terminal for inputting desired learning data; a server that analyzes data received from the terminal; A generative AI that receives the analysis results from the server and generates individually optimized problem sets; A server that transmits the problem set received from the generative AI to a terminal; means for displaying the transmitted problem set to a user in the terminal; A system including:

2. The system of claim 1, which utilizes a generative AI that generates individually optimized problem sets based on learning preference data and past learning history data.

3. 2. The system according to claim 1, further comprising a means for the server to automatically transmit a problem set generated by the generative AI to the terminal after input of desired learning data, and for the terminal to display the problem set to the user.

Images