System

Abstract

A system is provided.SOLUTION: This system includes a means for initializing a user, a means for acquiring the authentication and learning history of the user, a means for generating a question corresponding to the understanding level of the user, a means for inputting an answer, a means for determining an answer result and providing feedback, and a means for storing and analyzing the answer result and generating the next question.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] When studying for a language or qualification, memorizing vocabulary and terminology is an important and fundamental task, but traditional learning methods have several problems. Specifically, they require the effort of creating flashcards, can lead to boredom from repeatedly solving the same questions, and are difficult to connect to true understanding. Furthermore, there is a lack of a system that automatically generates questions optimal for each individual user's level of understanding. This can prevent users from studying efficiently, potentially resulting in a loss of motivation to learn. Therefore, there is a need for a system that can automatically generate questions tailored to the user's level of understanding and enable efficient learning. [Means for solving the problem]

[0005] The present invention is a system that includes a means for performing user initial settings, a means for authenticating the user and acquiring their learning history, a means for generating questions based on the user's level of understanding, a means for inputting answers, a means for evaluating the answer results and providing feedback, and a means for saving and analyzing the answer results and generating the next question. This allows the user to continue solving questions that are optimal for their level of understanding. Furthermore, the answer results are instantly fed back, allowing learning to proceed based on the user's level of understanding and proficiency. This system overcomes the shortcomings of traditional learning methods and provides an environment in which users can study efficiently and effectively.

[0006] "User" refers to an individual or subject who uses the system to learn words and terms related to a particular subject area.

[0007] "Initialization" refers to a series of procedures in which the system collects and configures basic information about the user at startup.

[0008] "Authentication" refers to the process of checking login information to ensure a user is a legitimate user.

[0009] "Study history" refers to a record of a user's past learning activities, including whether answers were correct or incorrect and the types of questions.

[0010] "Understanding" refers to an index that indicates how accurately a user understands words and terms in a particular field.

[0011] "Question generation" refers to the process of creating appropriate questions to be posed next based on the user's level of understanding.

[0012] "Answer input" refers to the act of a user inputting an answer to a question via a terminal.

[0013] "Answer result" refers to the result of determining whether the answer entered by the user is correct or incorrect, and details of that result.

[0014] "Feedback" refers to the act of providing test results and grades to users, allowing them to recognize their own level of understanding.

[0015] "Storage and analysis" refers to the process of storing the answer results in a database and analyzing them to evaluate the user's learning tendencies and level of understanding.

[0016] "Next question generation" refers to the process of creating the next appropriate question based on the stored and analyzed data. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] This invention relates to a system that automatically generates questions according to the user's level of understanding, analyzes the answers, and provides the next most appropriate questions. This system operates in cooperation with a server, terminals, and users.

[0039] System Overview

[0040] 1. Initial Setup

[0041] When a user registers or logs in, the server collects basic information about the user and sets up the initial settings, including the user's learning goals, current level, and learning history.

[0042] 2. User authentication and data acquisition

[0043] A user logs into the system using a terminal, and the login information is sent from the terminal to the server, which then authenticates the user by checking it against information in a database.

[0044] If authentication is successful, the server retrieves the user's past learning history from a database and evaluates their current level of understanding based on that data.

[0045] 3. Problem generation

[0046] The server uses a generative AI model to create the next question based on the user's level of understanding. The questions are optimized taking into account the user's past answers and current level of understanding.

[0047] 4. Answer input and result feedback

[0048] The user answers questions via the terminal, and the user's answers are sent to the server.

[0049] The server evaluates the received answers and provides feedback to the user, which may include explanations of correct and incorrect answers and additional learning resources.

[0050] 5. Data accumulation and analysis

[0051] The server stores the answer results in a database, including whether the answer was correct, the time it took to answer, and the difficulty of the question.

[0052] The server analyzes this data using a generative AI model to assess the user's learning habits and comprehension. For example, if a user frequently makes mistakes on a particular type of question, the server will focus on questions in that area.

[0053] 6. Next problem generation

[0054] Based on the analysis results, the server adjusts the content and difficulty of the next question, allowing users to always solve questions at the optimal level.

[0055] The new questions generated are sent to the terminal again, and the next learning cycle begins.

[0056] Specific examples

[0057] Consider the case where User A logs into the system and begins his or her first learning session.

[0058] 1. User A's initial settings

[0059] User A sets his / her learning goal and current level (e.g., intermediate).

[0060] The server uses this information to generate an appropriate initial problem set.

[0061] 2. User A's learning process

[0062] The question is "Choose the meaning of 'abate': a) increase, b) decrease, c) maintain."

[0063] User A selects "b) Decrease."

[0064] The server receives User A's answer, determines that it is correct, and provides feedback saying, "That's correct. 'abate' means 'decrease'."

[0065] The results are stored in a database, and the server uses this information to generate the next question.

[0066] 3. Generate the next question for User A

[0067] The server evaluates user A's understanding and then generates the question "Choose the meaning of 'nuance': a) subtle, b) direct, c) obvious."

[0068] This new question is sent to the terminal, and User A continues learning.

[0069] By repeating this process, users can obtain a learning experience that is optimized for their level of understanding. This system supports efficient and effective learning, helping users achieve their goals in a short period of time.

[0070] The processing flow will be explained below.

[0071] Step 1:

[0072] Initial Setup

[0073] The server loads a dataset of domain-related words, terms, meanings, and usage, including dictionary data, example sentence data, and past user learning data.

[0074] Step 2:

[0075] User Authentication

[0076] A user accesses the system from a terminal and logs in by entering a user ID and password. The terminal sends this authentication information to the server.

[0077] Step 3:

[0078] Authentication Results

[0079] The server compares the received authentication information with the user data in the database and performs authentication. If authentication is successful, the server retrieves the user's learning history from the database.

[0080] Step 4:

[0081] Assessment of understanding

[0082] The server evaluates the user's current level of understanding based on the acquired learning history, including past correct answer rates and trends in questions that were incorrectly answered.

[0083] Step 5:

[0084] First problem generation

[0085] The server uses a generative AI model to generate questions tailored to the user's level of understanding. For example, an intermediate-level user might be asked, "Choose the meaning of 'abate'."

[0086] Step 6:

[0087] Submit an issue

[0088] The server sends the generated questions to the terminal, where the user can check the questions.

[0089] Step 7:

[0090] Enter your answer

[0091] The user enters answers to questions using a terminal, and the answers are sent from the terminal to the server.

[0092] Step 8:

[0093] Judging the answer

[0094] The server evaluates the received answer and determines whether it is correct or incorrect. For example, "If you chose 'abate' as meaning 'to decrease,' check if this is correct."

[0095] Step 9:

[0096] feedback

[0097] The server generates feedback based on the answer, for example, "Your answer is correct. 'abate' means 'decrease'," and sends it to the device.

[0098] Step 10:

[0099] Data storage

[0100] The server stores the answer results in a database, which records correct and incorrect answers, answer time, and question difficulty.

[0101] Step 11:

[0102] Analyzing the data

[0103] The server analyzes the stored data using a generative AI model to evaluate the user's answering tendencies and strengths and weaknesses.

[0104] Step 12:

[0105] Next problem generation

[0106] Based on the analysis results, the server uses the generative AI model to create the next appropriate question, thereby continuously providing questions that are appropriate for the level.

[0107] Step 13:

[0108] Submit a new issue

[0109] The server sends the newly generated problem to the device, and the user attempts the next problem, and the process is repeated.

[0110] Example 1

[0111] 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."

[0112] Current educational systems lack the ability to provide questions that are individually optimized for a user's level of understanding. This reduces the user's learning efficiency and makes effective learning difficult. Furthermore, continuous feedback and learning history management are insufficient, and it is often difficult to properly set the next learning step based on the user's level of understanding. This can reduce learning effectiveness and cause the learning process to stagnate.

[0113] 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.

[0114] In this invention, the server includes a means for performing user initial settings, a means for authenticating the user and acquiring their learning history, a means for using a generative AI model to generate questions according to the user's level of understanding, a means for judging the answer results and providing feedback, and a means for saving and analyzing the answer results and generating the next question. This makes it possible to generate optimal questions and provide feedback according to the user's level of understanding, thereby improving learning effectiveness.

[0115] "User" refers to an individual or group that uses the system to study.

[0116] "Initial settings" refers to the information input and setup process that users go through when they start using the system, including the user's basic information, learning objectives, current level, etc.

[0117] "Authentication" is the process by which a server verifies a user's information and authorizes access rights when a user logs into a system.

[0118] "Study history" is a collection of data such as records of the user's past studies, grades, answer history, etc.

[0119] "Level of understanding" is an index that indicates how much a user understands a particular learning content.

[0120] A "question" is one of the quizzes or assignments provided by the system to assess and improve the user's understanding.

[0121] A "generative AI model" is an algorithm that uses machine learning to generate questions based on the user's level of understanding.

[0122] An "answer" is a response provided by a user to a question posed by the system.

[0123] "Feedback" refers to the system's response to the user's answer, such as evaluation or explanation.

[0124] "Saving" refers to the act of recording data such as the user's learning history and answer results in a database.

[0125] "Analysis" is the process of using stored data to evaluate a user's learning trends and comprehension.

[0126] This invention is a system that automatically generates questions according to the user's level of understanding, analyzes the answers, and provides the next most appropriate questions. This system operates in cooperation with the server, terminals, and users.

[0127] System Overview

[0128] Initial Setup

[0129] The server collects basic information about the user when the user registers or logs in. This information includes the user's learning goals, current level, and learning history, and is saved in a database. The server completes the initial setup when the user sets their learning goals and current level (e.g., intermediate).

[0130] User authentication and data acquisition

[0131] A user logs into the system using a terminal. The login information is sent from the terminal to the server using SSL / TLS. The server authenticates the user by checking it against information in a database, and if authentication is successful, it retrieves the user's past learning history and evaluates their current level of understanding.

[0132] problem generation

[0133] The server uses a generative AI model (e.g., GPT-4) to generate questions based on the user's level of understanding. The server optimizes the next question to be presented, taking into account the user's past answers and current level of understanding.

[0134] For example, the following prompt can be used:

[0135] "A user is learning intermediate level English vocabulary. Please generate the following questions for him. Based on his previous answers and statistics, he makes a lot of mistakes in the 'choose meaning' format. Please create a question containing the word 'nuance'. The format is as follows:

[0136] Choose the meaning of 'nuance': a) subtle, b) direct, c) obvious."

[0137] Answer input and result feedback

[0138] Users answer questions via their devices. The answers are immediately sent from the device to the server, which evaluates the answers. The server then provides feedback to the user, including explanations of correct and incorrect answers and additional learning resources as needed.

[0139] Data accumulation and analysis

[0140] The server stores all answer results in a database. This stored data includes whether the answer was correct, the time it took to complete the answer, and the difficulty of the question. The server analyzes this data using a generative AI model to evaluate the user's learning tendency and level of understanding.

[0141] Next problem generation

[0142] Based on the analysis results, the server adjusts the content and difficulty of the next questions. The generated questions are then sent back to the device to start the user's next learning cycle, providing a continuously optimized learning experience.

[0143] Specific examples

[0144] Below is an example of User A logging into the system for the first time and starting a learning session.

[0145] 1. Initial Setup

[0146] User A enters his / her learning objectives and current level (e.g., intermediate) in the application and presses the submit button. The server receives the input information and saves it in the database.

[0147] 2. Learning Process

[0148] User A enters his / her username and password on the login screen and clicks the login button.

[0149] The device sends login information to the server, which then authenticates it. After successful authentication, the learning history is acquired.

[0150] The server sends the generated AI model a prompt: "Please choose the meaning of 'abate': a) increase, b) decrease, c) maintain," and sends the generated problem to the device.

[0151] User A selects "b) Decrease."

[0152] The device sends this answer to the server, which judges the answer and provides feedback.

[0153] By repeating this process, users can always get the best learning experience. The system supports efficient and effective learning, helping users achieve their goals.

[0154] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0155] Step 1:

[0156] Initial Setup

[0157] A user accesses the new registration or login screen using a device. The user enters basic information such as name, email address, learning objectives, and current level, and clicks the submit button. The device sends the input data to the server. The server stores the received data in a database and completes the initial setup.

[0158] Input: User enters and submits basic information

[0159] Output: Save basic information to the database

[0160] Step 2:

[0161] User authentication and data acquisition

[0162] To log in using a terminal, a user enters a username and password and presses the login button. The terminal encrypts this authentication information using the SSL / TLS protocol and sends it to the server. The server performs authentication by comparing it with information in a database. If authentication is successful, the server retrieves past learning history from the database and evaluates the user's current level of understanding based on that data.

[0163] Input: User enters and submits login information

[0164] Output: Acquisition of learning history from the database and evaluation of comprehension

[0165] Step 3:

[0166] problem generation

[0167] The server uses a generative AI model (e.g., GPT-4) to create the next question to be posed based on the user's level of understanding. The server creates a prompt sentence taking into account the user's past answers and current level of understanding, and sends it to the generative AI model. The generated question is then sent from the server to the device.

[0168] Input: User's learning history and comprehension

[0169] Output: Generated issues sent to terminal

[0170] For example, "A user is learning intermediate level English vocabulary. Please generate the following questions for him. Based on his previous answers and statistical data, he makes a lot of mistakes in the 'choose meaning' format. Please create a question containing the word 'nuance'. The format is as follows:

[0171] Please choose the meaning of 'nuance': a) subtle, b) direct, c) obvious."

[0172] Step 4:

[0173] Answer input and result feedback

[0174] The user answers questions via the device. The user's answers are sent from the device to the server. The server evaluates the received answers and generates a correct / incorrect result. It also generates feedback including explanations of correct / incorrect answers and additional learning resources and sends it to the device.

[0175] Input: User's answer

[0176] Output: Generate feedback and send it to the device

[0177] Step 5:

[0178] Data accumulation and analysis

[0179] The server stores all answer results in a database. This stored data includes whether the answer was correct or incorrect, the time it took to complete the answer, and the difficulty of the question. Using a generative AI model, the server analyzes this data and evaluates the user's learning tendency and level of understanding.

[0180] Input: User's answer result

[0181] Output: Evaluation of learning tendency and comprehension

[0182] Step 6:

[0183] Next problem generation

[0184] The server then adjusts the content and difficulty of the next questions based on the analysis results. The generated questions are then sent back to the user's device, and the user's next learning cycle begins. This allows the user to always tackle questions at the optimal level.

[0185] Input: Analysis results

[0186] Output: Generate the next problem and send it to the terminal

[0187] This allows users to have a continuously optimized learning experience and progress effectively with their studies.

[0188] (Application example 1)

[0189] 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."

[0190] Conventional systems have limitations in their ability to provide optimal questions based on the user's level of understanding, making efficient learning difficult. Furthermore, they lack the ability to evaluate users' learning tendencies in detail, making it impossible to provide optimal learning programs for individual users. Under these circumstances, there is a need to improve the efficiency of employee training, especially in brick-and-mortar stores, but achieving this is difficult.

[0191] 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.

[0192] In this invention, the server includes means for performing user initial settings, means for authenticating the user and acquiring the user's learning history, means for generating questions according to the user's level of understanding, means for inputting answers, means for judging the answer results and providing feedback, means for saving and analyzing the answer results and generating the next question, means for evaluating the user's learning tendency, and means for generating a prompt sentence for generating the next most appropriate question. This makes it possible to provide questions optimized for each user's individual level of understanding and to progress with subsequent learning, thereby realizing more efficient employee training, particularly in physical stores.

[0193] The "means for initial user settings" is a means for collecting basic information about the user, their learning goals, and their current level, and registering them in the system.

[0194] The "means for authenticating a user and acquiring a learning history" refers to a means for authenticating a user based on the information provided by the user when logging in, and acquiring the user's past learning history from a database.

[0195] "Means for generating questions according to the user's level of understanding" refers to a means for creating appropriate questions using a generative AI model based on the user's learning history and answer results.

[0196] "Means for inputting answers" refers to the means by which a user inputs answers to questions into the system.

[0197] The "means for determining the answer result and providing feedback" is a means for analyzing the answer entered by the user, determining whether it is correct or incorrect, and providing the user with feedback based on the result.

[0198] The "means for saving and analyzing the answer results and generating the next question" is a means for saving the user's answer results in a database and analyzing them to generate the next question to be asked.

[0199] The "means for assessing the user's learning tendency" is a means for analyzing the collected data and assessing the user's strengths and weaknesses.

[0200] The "means for generating a prompt sentence for generating the next most suitable question" is a means for creating a prompt sentence for generating the next most suitable question to be asked based on the user's level of understanding and learning tendencies.

[0201] This invention is a system that automatically generates appropriate questions based on the user's level of understanding. This system operates with the cooperation of a server, terminals, and users.

[0202] 1. Initial Setup

[0203] When a user registers or logs in, the server collects basic information about the user and sets up the initial settings, including the user's learning goals, current level, learning history, etc. The server stores this information in a database and estimates the user's initial level.

[0204] 2. User authentication and data acquisition

[0205] Users log in to the system through their terminal. The login information is sent from the terminal to the server, and the server authenticates the user by comparing it with information in the database. If authentication is successful, the server retrieves the user's past learning history from the database and evaluates their current level of understanding based on that data.

[0206] 3. Problem generation

[0207] The server uses a generative AI model to automatically generate questions based on the user's level of understanding. It then generates prompts to optimize the questions, taking into account the user's past answers and current level of understanding. These prompts have the following format:

[0208] User level: Intermediate

[0209] User History: Completed training on past case management.

[0210] Next, generate the question to be asked:

[0211] 4. Answer input and result feedback

[0212] Users answer questions via their device. The answers are sent from the device to the server, which analyzes them to determine whether they are correct or incorrect and provides feedback. The feedback may include detailed explanations of correct and incorrect answers and additional learning resources.

[0213] 5. Data accumulation and analysis

[0214] The server stores the answers in a database. The stored data includes whether the answer was correct, the time it took to answer, and the difficulty of the question. The server analyzes this data using a generative AI model to evaluate the user's learning habits and comprehension. For example, if a user frequently makes mistakes on a certain type of question, the server will focus on that area.

[0215] 6. Next problem generation

[0216] The server then uses the results of the analysis to adjust the content and difficulty of the next questions, which are then sent back to the device, starting the next learning cycle.

[0217] Hardware and software used

[0218] Hardware: Servers, devices (smartphones, tablets, etc.)

[0219] Software: Databases (MySQL, PostgreSQL), generative AI models (OpenAI GPT-3), analysis tools (Scikit-learn)

[0220] Specific examples

[0221] For example, user A logs into the system and begins his first study session. If user A is initially set to "intermediate," the server generates the following questions:

[0222] "Choose the meaning of 'abate': a) to increase, b) to decrease, c) to maintain."

[0223] If User A selects "b) Decrease," the server determines this is the correct answer and provides the following feedback:

[0224] "That's correct. 'abate' means 'to decrease'."

[0225] The server then evaluates User A's understanding and generates the following questions:

[0226] "Choose the meaning of 'nuance': a) subtle, b) direct, c) obvious."

[0227] In this way, user A can always solve problems that are optimized for his or her level of understanding.

[0228] The above is a concrete implementation method of this system. This system can provide an individually optimized learning experience that takes into account the user's learning tendencies and level of understanding. It is expected to be particularly useful in improving the efficiency of employee training in brick-and-mortar stores.

[0229] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0230] Step 1: Initial Setup

[0231] A user uses a terminal to register or log in. At this time, the server collects the user's basic information (learning objectives, current level, learning history, etc.) and stores it in a database. The input is the user's basic information, and the output is the user information stored in the database. Based on this information, the server estimates the user's initial level.

[0232] Step 2: User authentication and data acquisition

[0233] When a user logs in via a terminal, the server receives authentication information. The server compares this information with information in a database to authenticate the user. The input is the user's login information, and the output is whether the authentication was successful. If the authentication is successful, the server retrieves the user's past learning history from the database and evaluates the user's current level of understanding.

[0234] Step 3: Problem generation

[0235] The server uses a generative AI model to generate questions based on the user's level of understanding. A prompt is generated, and the AI ​​model creates questions based on this. The input is the user's learning history, comprehension data, and the prompt, and the output is the generated question. Specifically, the prompt is sent to the generative AI model via an API.

[0236] Step 4: Answer entry and feedback

[0237] The user answers questions via a terminal. The input is the user's answer to the question, and the output is the answer result (correctness or incorrectness) and feedback. The server receives the answer from the terminal, analyzes it to determine whether it is correct or incorrect, and generates detailed feedback to provide to the user.

[0238] Step 5: Data collection and analysis

[0239] The server stores the user's answer results in a database. The input is the answer results (correct or incorrect, time taken to answer, difficulty of the question, etc.), and the output is the analysis data stored in the database. Using this, the server evaluates the user's learning tendency and level of understanding through a generative AI model.

[0240] Step 6: Generate the next problem

[0241] Based on the analysis results, the server readjusts the content and difficulty of the next question to be presented. The input is the analysis results and prompt text, and the output is the next question to be generated. Specifically, a prompt text is generated based on the analysis results, and this is provided to the generative AI model to generate a new question. The new question is then sent back to the device, and the user begins the next learning cycle.

[0242] 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.

[0243] This invention relates to a system that automatically generates questions according to the user's level of understanding, analyzes the answers to provide the next most appropriate questions, and recognizes the user's emotions to optimize the learning experience. This system operates in cooperation with a server, terminal, user, and emotion engine.

[0244] System Overview

[0245] 1. Initial Setup

[0246] When a user registers or logs in, the server collects basic information about the user and sets up the initial settings, including the user's learning goals, current level, and learning history.

[0247] 2. User authentication and data acquisition

[0248] A user logs into the system using a terminal, and the login information is sent from the terminal to the server, which then authenticates the user by checking it against information in a database.

[0249] If authentication is successful, the server retrieves the user's past learning history from a database and evaluates their current level of understanding based on that data.

[0250] 3. Problem generation

[0251] The server uses a generative AI model to create the next question based on the user's level of understanding. The questions are optimized taking into account the user's past answers and current level of understanding.

[0252] 4. Answer input and result feedback

[0253] The user answers questions via the terminal, and the user's answers are sent to the server.

[0254] The server evaluates the received answers and provides feedback to the user, which may include explanations of correct and incorrect answers and additional learning resources.

[0255] 5. Data accumulation and analysis

[0256] The server stores the answer results in a database, including correct and incorrect answers, the time it took to answer, and the difficulty of the questions.

[0257] The server analyzes this data using a generative AI model to assess the user's learning habits and comprehension. For example, if a user frequently makes mistakes on a particular type of question, the server will focus on questions in that area.

[0258] 6. Next problem generation

[0259] Based on the analysis results, the server adjusts the content and difficulty of the next question, allowing users to always solve questions at the optimal level.

[0260] The new questions generated are sent to the terminal again, and the next learning cycle begins.

[0261] Introducing the Emotion Engine

[0262] 1. Emotion recognition

[0263] When a user uses the device to answer questions, the device uses a camera and microphone to capture the user's facial expressions and tone of voice.

[0264] The device uses an emotion recognition engine to determine the user's emotional state from the captured data, which can include happiness, sadness, stress, excitement, etc.

[0265] 2. Transmission and analysis of emotional data

[0266] The device transmits the recognized emotion data to the server.

[0267] The server analyzes this emotional data and adjusts the difficulty and content of the questions based on the user's current emotional state, and also optimizes the form and content of the feedback to suit the user's emotions.

[0268] 3. Emotion-based problem generation and feedback

[0269] The server generates new problems taking into account the emotional data. For example, if the user is feeling stressed, it may lower the difficulty level or provide feedback including encouraging messages.

[0270] This information is also sent to the terminal, and the user's next learning cycle is initiated in an emotionally sensitive manner.

[0271] Specific examples

[0272] Consider the case where User B logs into the system and begins a normal learning session.

[0273] 1. User B's initial settings

[0274] User B sets his / her learning goal and current level. For example, User B wants to move from beginner to intermediate level.

[0275] The server uses this information to generate an appropriate initial problem set.

[0276] 2. User B's learning process

[0277] The question asks, "Choose the meaning of 'serene': a) noisy, b) quiet, c) pleasant."

[0278] User B selects "b) Quiet."

[0279] The server receives User B's answer, determines that it is correct, and provides feedback saying, "That's correct. 'serene' means 'quiet'."

[0280] At the same time, the device captures User B's facial expression and uses an emotion recognition engine to determine that he or she is under low stress.

[0281] 3. The next problem occurs

[0282] Since User B is not feeling stressed, the server generates a slightly more difficult question: "Choose the meaning of 'melancholy': a) enthusiastic, b) depressed, c) lively."

[0283] A new question is sent to the terminal and User B continues learning.

[0284] By repeating this process, users can obtain a learning experience that is optimized for their level of understanding and emotional state. This system supports efficient and effective learning and keeps users motivated to learn.

[0285] The processing flow will be explained below.

[0286] Step 1:

[0287] Initial Setup

[0288] The server loads a dataset of domain-related words, terms, meanings, and usage, including dictionary data, example sentence data, and past user learning data.

[0289] Step 2:

[0290] User Login

[0291] The user logs in by entering their user ID and password from the terminal. The terminal sends this authentication information to the server.

[0292] Step 3:

[0293] certification

[0294] The server compares the received authentication information with the user data in the database to authenticate the user. If authentication is successful, the server retrieves the user's learning history from the database.

[0295] Step 4:

[0296] Assessment of understanding

[0297] The server evaluates the user's current level of understanding based on the acquired learning history, including past correct answer rates and trends in questions that were incorrectly answered.

[0298] Step 5:

[0299] Preparing the emotion recognition engine

[0300] The device prepares a camera and microphone to capture the user's facial expressions and tone of voice, thereby collecting emotional data in real time.

[0301] Step 6:

[0302] First problem generation

[0303] The server uses a generative AI model to generate questions tailored to the user's level of understanding. For example, an intermediate-level user might be asked, "Choose the meaning of 'abate'."

[0304] Step 7:

[0305] Submit an issue

[0306] The server sends the generated questions to the terminal, where the user can check the questions.

[0307] Step 8:

[0308] Enter your answer

[0309] The user uses the device to input answers to the questions. When inputting the answers, the device captures the user's facial expressions and voice and sends them to the emotion engine.

[0310] Step 9:

[0311] emotion recognition

[0312] The device uses an emotion engine to analyze the user's emotional state, for example, to determine whether the user is stressed or focused.

[0313] Step 10:

[0314] Submit your answer

[0315] The terminal transmits the user's answers and emotion data to the server.

[0316] Step 11:

[0317] Judging the answer

[0318] The server evaluates the received answer and checks whether it is correct or not. For example, "If you chose 'abate' as meaning 'to decrease,' check whether this is the correct answer."

[0319] Step 12:

[0320] Feedback Generation

[0321] The server generates feedback based on the answer, taking into account sentiment data and including encouraging messages such as "Correct! 'abate' means 'decrease'. You're doing great!"

[0322] Step 13:

[0323] Send Feedback

[0324] The server sends the feedback to the terminal, which displays the feedback to the user.

[0325] Step 14:

[0326] Data storage

[0327] The server stores the answer results and emotional data in a database, including correct / incorrect answers, answer time, question difficulty, emotional state, etc.

[0328] Step 15:

[0329] Analyzing the data

[0330] The server analyzes the saved answer results and emotional data using a generative AI model to evaluate the user's answering tendencies, strengths and weaknesses, and emotional tendencies.

[0331] Step 16:

[0332] Next problem generation

[0333] Based on the analysis results, the server adjusts the content and difficulty of the next question, taking into account emotional data, for example, by presenting easier questions if the user is tired.

[0334] Step 17:

[0335] Submit a new issue

[0336] The server sends the newly generated problem to the device, and the user attempts the next problem, and the process is repeated.

[0337] Example 2

[0338] 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."

[0339] Conventional learning systems have limited ability to generate questions that correspond to the user's level of understanding, making it difficult to adapt to each user's individual learning progress and emotional state. Furthermore, because they only consider the user's learning history, it is difficult to maintain motivation during learning. Furthermore, feedback on answer results is one-dimensional, which does not fully address individual learning needs. Therefore, to maximize the user's learning effectiveness, it is essential to dynamically generate questions and provide feedback that are optimized according to the user's level of understanding and emotional state.

[0340] 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.

[0341] In this invention, the server includes means for performing user initial settings, means for authenticating the user and acquiring the user's learning history, means for generating questions according to the user's level of understanding, means for inputting answers, means for judging the answer results and providing feedback, means for saving and analyzing the answer results and generating the next question, means for acquiring and analyzing the user's emotional data, and means for adjusting the difficulty of questions and feedback based on the user's emotional state. This makes it possible to always provide an optimal learning experience by taking into account the user's level of understanding and emotional state.

[0342] The "means for performing user initial settings" is a means for collecting basic information such as the user's learning objectives, current level, and learning history, and for performing the initial settings of the system.

[0343] The "means for authenticating a user and acquiring a learning history" refers to the means for verifying the login information entered when a user logs into the system and acquiring the user's past learning history from the database.

[0344] "Means for generating questions according to the user's level of understanding" refers to a means for dynamically generating the optimal question to be asked next using a generative AI model based on the user's learning history and latest answer results.

[0345] The "means for inputting an answer" is a means by which a user inputs an answer to a presented question and transmits the answer to the system.

[0346] The "means for determining the answer result and providing feedback" refers to the means by which the server determines the answer submitted by the user and provides feedback based on the result. This feedback includes determining whether the answer is correct or incorrect and providing learning resources.

[0347] The "means for saving and analyzing the answer results and generating the next question" is a means for saving the user's answer results in a database and analyzing them to generate the next optimal question.

[0348] The "means for acquiring and analyzing user emotional data" refers to a means for capturing the user's facial expressions and voice data using the device's camera and microphone, and analyzing the user's emotional state using an emotion recognition engine.

[0349] "Means for adjusting the difficulty of questions and feedback based on the user's emotional state" refers to means for dynamically adjusting the difficulty of questions and the content of feedback based on analyzed emotional data to suit the user's current emotional state.

[0350] This invention relates to a system that automatically generates questions according to the user's level of understanding, analyzes the answers to provide the next most appropriate questions, and recognizes the user's emotions to optimize the learning experience. This system operates in cooperation with a server, terminal, user, and emotion engine.

[0351] The outline of the system is as follows:

[0352] Initial Setup

[0353] When a user registers or logs in, the server collects basic information about the user and performs initial setup. This includes the user's learning goals, current level, learning history, etc. Specifically, the user sets their learning goals and current level. Based on this information, the server generates an appropriate initial problem set and stores it in the database. For example, User A wishes to "move from beginner to intermediate level English," and sets the basic information required for this.

[0354] User authentication and data acquisition

[0355] A user logs in to the system using a terminal. The login information is sent from the terminal to the server, and the server authenticates the user by comparing it with information in the database. If authentication is successful, the server retrieves the user's past learning history from the database and evaluates their current level of understanding based on that data. For example, User B logs in and their past learning data is retrieved.

[0356] problem generation

[0357] The server uses a generative AI model to generate the next question based on the user's level of understanding. The questions are optimized by taking into account the user's past answers and current level of understanding. For example, the server generates a question for User B: "Please choose the meaning of 'serene': a) noisy, b) quiet, c) comfortable."

[0358] Answer input and result feedback

[0359] The user answers questions via the terminal. The terminal sends the user's answers to the server. The server evaluates the received answers and provides feedback to the user on whether they are correct or incorrect. Specific feedback may include explanations of correct or incorrect answers and additional learning resources. For example, if user B selects "b) quiet," the server provides the following feedback: "That's correct. 'serene' means 'quiet.'"

[0360] Data accumulation and analysis

[0361] The server stores the answers in a database. The stored data includes correct and incorrect answers, the time it took to answer, and the difficulty of the questions. The server analyzes this data using a generative AI model to evaluate the user's learning habits and comprehension. For example, if a user frequently makes mistakes on a certain type of question, the server will focus on questions in that area.

[0362] Next problem generation

[0363] Based on the analysis results, the server readjusts the content and difficulty of the next question. This allows the user to always solve questions at the optimal level. The new questions generated are sent back to the device, and the next learning cycle begins. For example, if it is analyzed that User B is not feeling stressed, a question with a slightly higher level of difficulty is generated.

[0364] Introducing the Emotion Engine

[0365] When a user answers questions using the device, the device uses a camera and microphone to capture the user's facial expressions and tone of voice. The device then uses an emotion recognition engine to determine the user's emotional state from the captured data, which can include happiness, sadness, stress, and excitement. The recognized emotional data is sent to a server, which analyzes the emotional data and adjusts the difficulty and content of the questions based on the user's current emotional state. The form and content of the feedback is also optimized to match the user's emotions.

[0366] Specific examples

[0367] Consider the case where User B logs in to the system and begins a normal learning session. User B's initial setting is to set his / her learning goal as "Beginner to intermediate level English." The server generates an initial set of questions based on this information. For example, User B is presented with a question asking, "What is the meaning of 'serene'? a) noisy, b) quiet, c) comfortable." User B selects "b) quiet," and the server provides feedback saying, "That's correct. 'serene' means 'quiet.'" At the same time, the device captures User B's facial expression and determines that he / she is under low stress using an emotion recognition engine. Next, the server generates a slightly more difficult question, asking, "What is the meaning of 'melancholy'? a) enthusiastic, b) depressed, c) lively."

[0368] By repeating this process, users can obtain a learning experience that is optimized for their level of understanding and emotional state. This system supports efficient and effective learning and keeps users motivated to learn.

[0369] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0370] Step 1:

[0371] A new user registration or login is performed. The user uses a terminal to enter their ID and password or new registration information. The entered information is sent from the terminal to the server.

[0372] Input: User ID, password, new registration information

[0373] Output: Authentication information sent to the server

[0374] Specific operation: User A enters the necessary information into the new registration form on the device and presses the send button. The device then sends the entered information to the server.

[0375] Step 2:

[0376] The server authenticates the user by comparing login information and new registration information with information in the database. If authentication is successful, the server obtains the user's past learning history.

[0377] Input: The authentication information sent to the server

[0378] Output: Authentication results, learning history data

[0379] Specific operation: The server authenticates User A by checking against the database, and after successful authentication, retrieves User A's past learning history from the database.

[0380] Step 3:

[0381] The server performs initial setup based on the user's basic information, including the user's learning goals, current level, and learning history.

[0382] Input: Learning objectives, current level, learning history

[0383] Output: Initial setup data, initial problem set

[0384] Specific operation: User A sets "I want to move from beginner to intermediate level English," and the server generates an initial set of questions based on that information.

[0385] Step 4:

[0386] The server generates the next question based on the user's level of understanding, using a generative AI model to consider the user's past answers and current level of understanding to create the most appropriate question.

[0387] Input: User's comprehension data, answer results

[0388] Output: Next problem data

[0389] Specific operation: The server uses the generative AI model to generate a question for User B: "Please choose the meaning of 'serene': a) noisy, b) quiet, c) comfortable."

[0390] Step 5:

[0391] The user answers questions via the terminal and sends the answers, which are then sent to the server.

[0392] Input: User's answer data

[0393] Output: Answer data sent to the server

[0394] Specific operation: User B selects "b) Quiet" and the device sends the user's answer to the server.

[0395] Step 6:

[0396] The server evaluates the received answers and provides feedback to the user, including explanations of correct and incorrect answers and additional learning resources.

[0397] Input: User's answer data

[0398] Output: Feedback data

[0399] Specific behavior: The server judges the answer and provides feedback such as "Correct. 'serene' means 'quiet'."

[0400] Step 7:

[0401] The server stores the answer results in a database. The stored data includes correct answers, answer time, difficulty level of the question, etc. The server analyzes this data using a generative AI model.

[0402] Input: Answer result data

[0403] Output: Analysis data, storage data

[0404] Specific operation: The server stores User B's answer data in a database and analyzes it using a generative AI model.

[0405] Step 8:

[0406] The server then adjusts the content and difficulty of the next question based on the analysis results, and the new question is then sent back to the device.

[0407] Input: Analysis data

[0408] Output: Rescaled problem data

[0409] Specific operation: The server analyzes that User B is not feeling stressed, generates the next question "Please choose the meaning of 'melancholy': a) enthusiastic, b) depressed, c) lively" and sends it to the terminal.

[0410] Step 9:

[0411] The device uses a camera and microphone to capture the user's facial expressions and tone of voice, and an emotion recognition engine to determine the user's emotional state.

[0412] Input: facial expression data, voice data

[0413] Output: Emotion data

[0414] Specific operation: When User B answers the question, the device captures facial expression data and the emotion recognition engine determines that the user is under low stress.

[0415] Step 10:

[0416] The emotion recognition results are sent to a server, which analyzes the emotion data and adjusts the difficulty of the questions and feedback based on the user's current emotional state.

[0417] Input: Emotion data

[0418] Output: Adjusted problem data, feedback data

[0419] How it works: The device sends emotional data to the server, and the server adjusts the difficulty of the next question and feedback based on the emotional state.

[0420] (Application example 2)

[0421] 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."

[0422] Conventional learning management systems and task management systems for factory robots do not dynamically adjust tasks according to the user's or robot's level of understanding or workload, making efficient learning and work execution difficult. This has led to problems such as a decline in the user's motivation to learn and robot overload. Furthermore, these systems were unable to recognize and reflect emotions or workload conditions, preventing optimal feedback and task generation.

[0423] 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.

[0424] In this invention, the server includes means for performing user initial settings, means for authenticating the user and acquiring the user's learning history, means for generating questions according to the user's level of understanding, means for inputting answers, means for judging the answer results and providing feedback, means for saving and analyzing the answer results and generating the next question, means for the robot to learn a new task, means for adjusting the difficulty of the next task based on the task results, and means for recognizing the robot's load state and optimizing task execution efficiency. This enables efficient learning while increasing the user's motivation to learn, and enables optimal task execution while preventing the robot from being overloaded.

[0425] "User initial settings" refers to the process of collecting and setting basic information about a user's learning goals, current level, and learning history when the user registers or logs in.

[0426] "User authentication" is the process of verifying the user's identity when the user logs in to a system by sending the entered information to a server and comparing it with information in a database.

[0427] "Means for obtaining learning history" refers to the process by which the server reads past learning data from the database and uses it to evaluate the user's current level of understanding.

[0428] "Means for generating questions according to the user's level of understanding" refers to the process of using a generative AI model to create the optimal question to be asked next, based on the user's past answers and current level of understanding.

[0429] "Means for inputting answers" refers to the process in which a user inputs an answer to a question and the answer is sent to the server.

[0430] The "means for determining the answer result and providing feedback" is the process by which the server determines the received answer and provides the user with feedback on whether it is correct or not, as well as learning resources.

[0431] "Means for saving and analyzing the answer results and generating the next question" refers to the process in which the server saves the answer results in a database, analyzes them to evaluate the user's learning tendencies and level of understanding, and readjusts the content and difficulty of the next question to be asked.

[0432] "Means for robots to learn new tasks" refers to the process by which factory robots efficiently learn new jobs or tasks.

[0433] The "means for adjusting the difficulty of the next task based on the results of the task" is a process for dynamically adjusting the difficulty of the next task based on the results of the robot's task execution.

[0434] "Means for recognizing the load state of the robot and optimizing the efficiency of task execution" refers to a process for recognizing the load state of the robot and adjusting the difficulty and order of tasks to enable optimal task execution while preventing overload.

[0435] This invention is a system for maximizing the learning and working efficiency of users and robots, and is composed of a server, a terminal, a user, a robot, and an emotion engine. The system is specifically implemented as follows.

[0436] System Overview

[0437] Initial Setup

[0438] When a user performs initial setup, the server collects basic information about the user's learning goals, current level, and learning history. Based on this information, the server provides optimal initial setup for each user. The server also collects work goals and current task data for factory robots and performs initial setup.

[0439] User authentication and data acquisition

[0440] A user logs in to the system using a terminal. The login information is sent to the server, which then authenticates the user by comparing it with information in the database. If authentication is successful, the server retrieves the user's past learning history from the database and evaluates their current level of understanding.

[0441] problem generation

[0442] The server uses a generative AI model to create the next question based on the user's level of understanding. The questions are optimized by taking into account the user's past answers and current level of understanding. Similarly, the server analyzes the results of tasks for factory robots and generates the optimal next task to be performed.

[0443] Answer input and result feedback

[0444] Users answer questions via their device. The answers are sent from the device to the server, which evaluates them and provides feedback on whether the answer was correct or incorrect. Specific feedback may include explanations of correct or incorrect answers and additional learning resources. For robots, the server receives the results of the tasks performed, determines whether the robot was successful, and adjusts the difficulty of the next task based on the results.

[0445] Data accumulation and analysis

[0446] The server stores the answers and task execution results in a database. The stored data includes correct / incorrect answers, the time it took to answer, the difficulty of the question, the success / failure of the task, and the execution time. The server analyzes this data using a generative AI model to evaluate the user's learning tendency and level of understanding, as well as the robot's work efficiency.

[0447] Next problem generation

[0448] The server then adjusts the content and difficulty of the next question based on the analysis results, allowing users to always solve questions at the optimal level. The server also generates and suggests optimal tasks for the robot based on the analysis results.

[0449] Introducing the Emotion Engine

[0450] emotion recognition

[0451] When a user answers questions using the device, the device uses a camera and microphone to capture the user's facial expressions and tone of voice. An emotion recognition engine is used to determine the user's emotional state from the captured data. For robots, the emotional state (load state) is recognized based on the workload of performing the task.

[0452] Sending and analyzing emotional data

[0453] The device sends the recognized emotional data to a server, which analyzes the data and adjusts the difficulty and content of the questions and tasks based on the user's current emotional state and the robot's workload. The server also optimizes the form and content of feedback to match the user's emotional state.

[0454] Emotion-based problem generation and feedback

[0455] The server generates new problems and tasks taking into account the emotional data. For example, if the user is feeling stressed, it will lower the difficulty level slightly or provide feedback including an encouraging message. Also, if the robot is overloaded, it will reduce the difficulty of the next task. This information is sent to the terminal or robot, and the next cycle will begin taking into account the user's emotions and stress state.

[0456] Specific examples

[0457] Consider a case where a user logs in to the system and begins a learning session. For example, a question might appear: "Please choose the meaning of 'serene': a) noisy, b) quiet, c) comfortable." If the user selects "b) quiet," the server determines that this is the correct answer and provides feedback such as, "You're correct. 'serene' means 'quiet.'" The device simultaneously captures the user's facial expression and uses an emotion recognition engine to determine that the user is under stress. Also, if a factory robot performs a task called "assembly" and succeeds, the server suggests the slightly more difficult "inspection" task as the next task.

[0458] Prompt Sentence Examples

[0459] "The robot has succeeded five times and failed three times in the 'Inspect' task. What type and difficulty of task should it suggest next?"

[0460] "The user answered the 'serene' question correctly. Please generate a related vocabulary question for them to answer next."

[0461] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0462] Step 1:

[0463] The server provides the terminal with a screen for the user to perform initial setup. The user inputs information such as their learning objectives, current level, learning history, etc. The input data is sent to the server, which then stores the information in a database.

[0464] Step 2:

[0465] A user logs into the system using a terminal. The login information (user ID, password, etc.) is sent from the terminal to the server, which then authenticates the user by comparing it with information in the database. If authentication is successful, the server retrieves the user's past learning history from the database and sends that information to the terminal for display.

[0466] Step 3:

[0467] The server uses a generative AI model to generate questions based on the user's level of understanding. The generative AI model uses the user's past answers and current level of understanding as input data and outputs the optimal question to be posed next. This question is sent from the server to the device and displayed to the user.

[0468] Step 4:

[0469] The user answers the questions displayed via the terminal. The answer data is sent from the terminal to the server, and the server receives the answer data. The server compares the answer data with the correct answer data and determines whether the answer was correct or incorrect.

[0470] Step 5:

[0471] The server evaluates the answer and provides the result as feedback to the user. The feedback may include explanations of correct and incorrect answers and additional learning resources. The feedback data is sent from the server to the device and displayed to the user.

[0472] Step 6:

[0473] The server stores the answer results in a database. The stored data includes correct and incorrect answers, the time it took to answer, and the difficulty of the questions. This data serves as the basis for subsequent data analysis and question generation.

[0474] Step 7:

[0475] The server uses the stored data to analyze the user's learning habits and level of understanding using a generative AI model, and the analysis data is used to adjust the content and difficulty of the next questions.

[0476] Step 8:

[0477] The server then sends the newly generated questions to the device, and the next learning cycle begins, ensuring that the user is always challenged with questions of appropriate difficulty.

[0478] Step 9:

[0479] When a robot learns a new task, the server receives the robot's task settings and result data input via the terminal, and saves the robot's work history and current load status as data.

[0480] Step 10:

[0481] The server receives the results of the robot's tasks and analyzes the data on success and failure. Based on the analysis results, the data is processed to adjust the difficulty of the next task, and a new task is generated using the generative AI model. This data is then sent to the robot or the operator's device.

[0482] Step 11:

[0483] The emotion engine recognizes the robot's load state and adjusts to reduce the difficulty of the task if it is overloaded. The server generates feedback based on this situation and sends the feedback data to the robot and the operator's device.

[0484] Prompt Sentence Examples

[0485] "The robot has succeeded five times and failed three times in the 'Inspect' task. What type and difficulty of task should it suggest next?"

[0486] "The user answered the 'serene' question correctly. Please generate a related vocabulary question for them to answer next."

[0487] 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.

[0488] 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.

[0489] 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.

[0490] [Second embodiment]

[0491] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0492] 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.

[0493] 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).

[0494] 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.

[0495] 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.

[0496] 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).

[0497] 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.

[0498] 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.

[0499] 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.

[0500] 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.

[0501] 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.

[0502] 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."

[0503] This invention relates to a system that automatically generates questions according to the user's level of understanding, analyzes the answers, and provides the next most appropriate questions. This system operates in cooperation with a server, terminals, and users.

[0504] System Overview

[0505] 1. Initial Setup

[0506] When a user registers or logs in, the server collects basic information about the user and sets up the initial settings, including the user's learning goals, current level, and learning history.

[0507] 2. User authentication and data acquisition

[0508] A user logs into the system using a terminal, and the login information is sent from the terminal to the server, which then authenticates the user by checking it against information in a database.

[0509] If authentication is successful, the server retrieves the user's past learning history from a database and evaluates their current level of understanding based on that data.

[0510] 3. Problem generation

[0511] The server uses a generative AI model to create the next question based on the user's level of understanding. The questions are optimized taking into account the user's past answers and current level of understanding.

[0512] 4. Answer input and result feedback

[0513] The user answers questions via the terminal, and the user's answers are sent to the server.

[0514] The server evaluates the received answers and provides feedback to the user, which may include explanations of correct and incorrect answers and additional learning resources.

[0515] 5. Data accumulation and analysis

[0516] The server stores the answer results in a database, including whether the answer was correct, the time it took to answer, and the difficulty of the question.

[0517] The server analyzes this data using a generative AI model to assess the user's learning habits and comprehension. For example, if a user frequently makes mistakes on a particular type of question, the server will focus on questions in that area.

[0518] 6. Next problem generation

[0519] Based on the analysis results, the server adjusts the content and difficulty of the next question, allowing users to always solve questions at the optimal level.

[0520] The new questions generated are sent to the terminal again, and the next learning cycle begins.

[0521] Specific examples

[0522] Consider the case where User A logs into the system and begins his or her first learning session.

[0523] 1. User A's initial settings

[0524] User A sets his / her learning goal and current level (e.g., intermediate).

[0525] The server uses this information to generate an appropriate initial problem set.

[0526] 2. User A's learning process

[0527] The question is "Choose the meaning of 'abate': a) increase, b) decrease, c) maintain."

[0528] User A selects "b) Decrease."

[0529] The server receives User A's answer, determines that it is correct, and provides feedback saying, "That's correct. 'abate' means 'decrease'."

[0530] The results are stored in a database, and the server uses this information to generate the next question.

[0531] 3. Generate the next question for User A

[0532] The server evaluates user A's understanding and then generates the question "Choose the meaning of 'nuance': a) subtle, b) direct, c) obvious."

[0533] This new question is sent to the terminal, and User A continues learning.

[0534] By repeating this process, users can obtain a learning experience that is optimized for their level of understanding. This system supports efficient and effective learning, helping users achieve their goals in a short period of time.

[0535] The processing flow will be explained below.

[0536] Step 1:

[0537] Initial Setup

[0538] The server loads a dataset of domain-related words, terms, meanings, and usage, including dictionary data, example sentence data, and past user learning data.

[0539] Step 2:

[0540] User Authentication

[0541] A user accesses the system from a terminal and logs in by entering a user ID and password. The terminal sends this authentication information to the server.

[0542] Step 3:

[0543] Authentication Results

[0544] The server compares the received authentication information with the user data in the database and performs authentication. If authentication is successful, the server retrieves the user's learning history from the database.

[0545] Step 4:

[0546] Assessment of understanding

[0547] The server evaluates the user's current level of understanding based on the acquired learning history, including past correct answer rates and trends in questions that were incorrectly answered.

[0548] Step 5:

[0549] First problem generation

[0550] The server uses a generative AI model to generate questions tailored to the user's level of understanding. For example, an intermediate-level user might be asked, "Choose the meaning of 'abate'."

[0551] Step 6:

[0552] Submit an issue

[0553] The server sends the generated questions to the terminal, where the user can check the questions.

[0554] Step 7:

[0555] Enter your answer

[0556] The user enters answers to questions using a terminal, and the answers are sent from the terminal to the server.

[0557] Step 8:

[0558] Judging the answer

[0559] The server evaluates the received answer and determines whether it is correct or incorrect. For example, "If you chose 'abate' as meaning 'to decrease,' check if this is correct."

[0560] Step 9:

[0561] feedback

[0562] The server generates feedback based on the answer, for example, "Your answer is correct. 'abate' means 'decrease'," and sends it to the device.

[0563] Step 10:

[0564] Data storage

[0565] The server stores the answer results in a database, which records correct and incorrect answers, answer time, and question difficulty.

[0566] Step 11:

[0567] Analyzing the data

[0568] The server analyzes the stored data using a generative AI model to evaluate the user's answering tendencies and strengths and weaknesses.

[0569] Step 12:

[0570] Next problem generation

[0571] Based on the analysis results, the server uses the generative AI model to create the next appropriate question, thereby continuously providing questions that are appropriate for the level.

[0572] Step 13:

[0573] Submit a new issue

[0574] The server sends the newly generated problem to the device, and the user attempts the next problem, and the process is repeated.

[0575] Example 1

[0576] 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."

[0577] Current educational systems lack the ability to provide questions that are individually optimized for a user's level of understanding. This reduces the user's learning efficiency and makes effective learning difficult. Furthermore, continuous feedback and learning history management are insufficient, and it is often difficult to properly set the next learning step based on the user's level of understanding. This can reduce learning effectiveness and cause the learning process to stagnate.

[0578] 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.

[0579] In this invention, the server includes a means for performing user initial settings, a means for authenticating the user and acquiring their learning history, a means for using a generative AI model to generate questions according to the user's level of understanding, a means for judging the answer results and providing feedback, and a means for saving and analyzing the answer results and generating the next question. This makes it possible to generate optimal questions and provide feedback according to the user's level of understanding, thereby improving learning effectiveness.

[0580] "User" refers to an individual or group that uses the system to study.

[0581] "Initial settings" refers to the information input and setup process that users go through when they start using the system, including the user's basic information, learning objectives, current level, etc.

[0582] "Authentication" is the process by which a server verifies a user's information and authorizes access rights when a user logs into a system.

[0583] "Study history" is a collection of data such as records of the user's past studies, grades, answer history, etc.

[0584] "Level of understanding" is an index that indicates how much a user understands a particular learning content.

[0585] A "question" is one of the quizzes or assignments provided by the system to assess and improve the user's understanding.

[0586] A "generative AI model" is an algorithm that uses machine learning to generate questions based on the user's level of understanding.

[0587] An "answer" is a response provided by a user to a question posed by the system.

[0588] "Feedback" refers to the system's response to the user's answer, such as evaluation or explanation.

[0589] "Saving" refers to the act of recording data such as the user's learning history and answer results in a database.

[0590] "Analysis" is the process of using stored data to evaluate a user's learning trends and comprehension.

[0591] This invention is a system that automatically generates questions according to the user's level of understanding, analyzes the answers, and provides the next most appropriate questions. This system operates in cooperation with the server, terminals, and users.

[0592] System Overview

[0593] Initial Setup

[0594] The server collects basic information about the user when the user registers or logs in. This information includes the user's learning goals, current level, and learning history, and is saved in a database. The server completes the initial setup when the user sets their learning goals and current level (e.g., intermediate).

[0595] User authentication and data acquisition

[0596] A user logs into the system using a terminal. The login information is sent from the terminal to the server using SSL / TLS. The server authenticates the user by checking it against information in a database, and if authentication is successful, it retrieves the user's past learning history and evaluates their current level of understanding.

[0597] problem generation

[0598] The server uses a generative AI model (e.g., GPT-4) to generate questions based on the user's level of understanding. The server optimizes the next question to be presented, taking into account the user's past answers and current level of understanding.

[0599] For example, the following prompt can be used:

[0600] "A user is learning intermediate level English vocabulary. Please generate the following questions for him. Based on his previous answers and statistics, he makes a lot of mistakes in the 'choose meaning' format. Please create a question containing the word 'nuance'. The format is as follows:

[0601] Choose the meaning of 'nuance': a) subtle, b) direct, c) obvious."

[0602] Answer input and result feedback

[0603] Users answer questions via their devices. The answers are immediately sent from the device to the server, which evaluates the answers. The server then provides feedback to the user, including explanations of correct and incorrect answers and additional learning resources as needed.

[0604] Data accumulation and analysis

[0605] The server stores all answer results in a database. This stored data includes whether the answer was correct, the time it took to complete the answer, and the difficulty of the question. The server analyzes this data using a generative AI model to evaluate the user's learning tendency and level of understanding.

[0606] Next problem generation

[0607] Based on the analysis results, the server adjusts the content and difficulty of the next questions. The generated questions are then sent back to the device to start the user's next learning cycle, providing a continuously optimized learning experience.

[0608] Specific examples

[0609] Below is an example of User A logging into the system for the first time and starting a learning session.

[0610] 1. Initial Setup

[0611] User A enters his / her learning objectives and current level (e.g., intermediate) in the application and presses the submit button. The server receives the input information and saves it in the database.

[0612] 2. Learning Process

[0613] User A enters his / her username and password on the login screen and clicks the login button.

[0614] The device sends login information to the server, which then authenticates it. After successful authentication, the learning history is acquired.

[0615] The server sends the generated AI model a prompt: "Please choose the meaning of 'abate': a) increase, b) decrease, c) maintain," and sends the generated problem to the device.

[0616] User A selects "b) Decrease."

[0617] The device sends this answer to the server, which judges the answer and provides feedback.

[0618] By repeating this process, users can always get the best learning experience. The system supports efficient and effective learning, helping users achieve their goals.

[0619] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0620] Step 1:

[0621] Initial Setup

[0622] A user accesses the new registration or login screen using a device. The user enters basic information such as name, email address, learning objectives, and current level, and clicks the submit button. The device sends the input data to the server. The server stores the received data in a database and completes the initial setup.

[0623] Input: User enters and submits basic information

[0624] Output: Save basic information to the database

[0625] Step 2:

[0626] User authentication and data acquisition

[0627] To log in using a terminal, a user enters a username and password and presses the login button. The terminal encrypts this authentication information using the SSL / TLS protocol and sends it to the server. The server performs authentication by comparing it with information in a database. If authentication is successful, the server retrieves past learning history from the database and evaluates the user's current level of understanding based on that data.

[0628] Input: User enters and submits login information

[0629] Output: Acquisition of learning history from the database and evaluation of comprehension

[0630] Step 3:

[0631] problem generation

[0632] The server uses a generative AI model (e.g., GPT-4) to create the next question to be posed based on the user's level of understanding. The server creates a prompt sentence taking into account the user's past answers and current level of understanding, and sends it to the generative AI model. The generated question is then sent from the server to the device.

[0633] Input: User's learning history and comprehension

[0634] Output: Generated issues sent to terminal

[0635] For example, "A user is learning intermediate level English vocabulary. Please generate the following questions for him. Based on his previous answers and statistical data, he makes a lot of mistakes in the 'choose meaning' format. Please create a question containing the word 'nuance'. The format is as follows:

[0636] Please choose the meaning of 'nuance': a) subtle, b) direct, c) obvious."

[0637] Step 4:

[0638] Answer input and result feedback

[0639] The user answers questions via the device. The user's answers are sent from the device to the server. The server evaluates the received answers and generates a correct / incorrect result. It also generates feedback including explanations of correct / incorrect answers and additional learning resources and sends it to the device.

[0640] Input: User's answer

[0641] Output: Generate feedback and send it to the device

[0642] Step 5:

[0643] Data accumulation and analysis

[0644] The server stores all answer results in a database. This stored data includes whether the answer was correct or incorrect, the time it took to complete the answer, and the difficulty of the question. Using a generative AI model, the server analyzes this data and evaluates the user's learning tendency and level of understanding.

[0645] Input: User's answer result

[0646] Output: Evaluation of learning tendency and comprehension

[0647] Step 6:

[0648] Next problem generation

[0649] The server then adjusts the content and difficulty of the next questions based on the analysis results. The generated questions are then sent back to the user's device, and the user's next learning cycle begins. This allows the user to always tackle questions at the optimal level.

[0650] Input: Analysis results

[0651] Output: Generate the next problem and send it to the terminal

[0652] This allows users to have a continuously optimized learning experience and progress effectively with their studies.

[0653] (Application example 1)

[0654] 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."

[0655] Conventional systems have limitations in their ability to provide optimal questions based on the user's level of understanding, making efficient learning difficult. Furthermore, they lack the ability to evaluate users' learning tendencies in detail, making it impossible to provide optimal learning programs for individual users. Under these circumstances, there is a need to improve the efficiency of employee training, especially in brick-and-mortar stores, but achieving this is difficult.

[0656] 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.

[0657] In this invention, the server includes means for performing user initial settings, means for authenticating the user and acquiring the user's learning history, means for generating questions according to the user's level of understanding, means for inputting answers, means for judging the answer results and providing feedback, means for saving and analyzing the answer results and generating the next question, means for evaluating the user's learning tendency, and means for generating a prompt sentence for generating the next most appropriate question. This makes it possible to provide questions optimized for each user's individual level of understanding and to progress with subsequent learning, thereby realizing more efficient employee training, particularly in physical stores.

[0658] The "means for initial user settings" is a means for collecting basic information about the user, their learning goals, and their current level, and registering them in the system.

[0659] The "means for authenticating a user and acquiring a learning history" refers to a means for authenticating a user based on the information provided by the user when logging in, and acquiring the user's past learning history from a database.

[0660] "Means for generating questions according to the user's level of understanding" refers to a means for creating appropriate questions using a generative AI model based on the user's learning history and answer results.

[0661] "Means for inputting answers" refers to the means by which a user inputs answers to questions into the system.

[0662] The "means for determining the answer result and providing feedback" is a means for analyzing the answer entered by the user, determining whether it is correct or incorrect, and providing the user with feedback based on the result.

[0663] The "means for saving and analyzing the answer results and generating the next question" is a means for saving the user's answer results in a database and analyzing them to generate the next question to be asked.

[0664] The "means for assessing the user's learning tendency" is a means for analyzing the collected data and assessing the user's strengths and weaknesses.

[0665] The "means for generating a prompt sentence for generating the next most suitable question" is a means for creating a prompt sentence for generating the next most suitable question to be asked based on the user's level of understanding and learning tendencies.

[0666] This invention is a system that automatically generates appropriate questions based on the user's level of understanding. This system operates with the cooperation of a server, terminals, and users.

[0667] 1. Initial Setup

[0668] When a user registers or logs in, the server collects basic information about the user and sets up the initial settings, including the user's learning goals, current level, learning history, etc. The server stores this information in a database and estimates the user's initial level.

[0669] 2. User authentication and data acquisition

[0670] Users log in to the system through their terminal. The login information is sent from the terminal to the server, and the server authenticates the user by comparing it with information in the database. If authentication is successful, the server retrieves the user's past learning history from the database and evaluates their current level of understanding based on that data.

[0671] 3. Problem generation

[0672] The server uses a generative AI model to automatically generate questions based on the user's level of understanding. It then generates prompts to optimize the questions, taking into account the user's past answers and current level of understanding. These prompts have the following format:

[0673] User level: Intermediate

[0674] User History: Completed training on past case management.

[0675] Next, generate the question to be asked:

[0676] 4. Answer input and result feedback

[0677] Users answer questions via their device. The answers are sent from the device to the server, which analyzes them to determine whether they are correct or incorrect and provides feedback. The feedback may include detailed explanations of correct and incorrect answers and additional learning resources.

[0678] 5. Data accumulation and analysis

[0679] The server stores the answers in a database. The stored data includes whether the answer was correct, the time it took to answer, and the difficulty of the question. The server analyzes this data using a generative AI model to evaluate the user's learning habits and comprehension. For example, if a user frequently makes mistakes on a certain type of question, the server will focus on that area.

[0680] 6. Next problem generation

[0681] The server then uses the results of the analysis to adjust the content and difficulty of the next questions, which are then sent back to the device, starting the next learning cycle.

[0682] Hardware and software used

[0683] Hardware: Servers, devices (smartphones, tablets, etc.)

[0684] Software: Databases (MySQL, PostgreSQL), generative AI models (OpenAI GPT-3), analysis tools (Scikit-learn)

[0685] Specific examples

[0686] For example, user A logs into the system and begins his first study session. If user A is initially set to "intermediate," the server generates the following questions:

[0687] "Choose the meaning of 'abate': a) to increase, b) to decrease, c) to maintain."

[0688] If User A selects "b) Decrease," the server determines this is the correct answer and provides the following feedback:

[0689] "That's correct. 'abate' means 'to decrease'."

[0690] The server then evaluates User A's understanding and generates the following questions:

[0691] "Choose the meaning of 'nuance': a) subtle, b) direct, c) obvious."

[0692] In this way, user A can always solve problems that are optimized for his or her level of understanding.

[0693] The above is a concrete implementation method of this system. This system can provide an individually optimized learning experience that takes into account the user's learning tendencies and level of understanding. It is expected to be particularly useful in improving the efficiency of employee training in brick-and-mortar stores.

[0694] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0695] Step 1: Initial Setup

[0696] A user uses a terminal to register or log in. At this time, the server collects the user's basic information (learning objectives, current level, learning history, etc.) and stores it in a database. The input is the user's basic information, and the output is the user information stored in the database. Based on this information, the server estimates the user's initial level.

[0697] Step 2: User authentication and data acquisition

[0698] When a user logs in via a terminal, the server receives authentication information. The server compares this information with information in a database to authenticate the user. The input is the user's login information, and the output is whether the authentication was successful. If the authentication is successful, the server retrieves the user's past learning history from the database and evaluates the user's current level of understanding.

[0699] Step 3: Problem generation

[0700] The server uses a generative AI model to generate questions based on the user's level of understanding. A prompt is generated, and the AI ​​model creates questions based on this. The input is the user's learning history, comprehension data, and the prompt, and the output is the generated question. Specifically, the prompt is sent to the generative AI model via an API.

[0701] Step 4: Answer entry and feedback

[0702] The user answers questions via a terminal. The input is the user's answer to the question, and the output is the answer result (correctness or incorrectness) and feedback. The server receives the answer from the terminal, analyzes it to determine whether it is correct or incorrect, and generates detailed feedback to provide to the user.

[0703] Step 5: Data collection and analysis

[0704] The server stores the user's answer results in a database. The input is the answer results (correct or incorrect, time taken to answer, difficulty of the question, etc.), and the output is the analysis data stored in the database. Using this, the server evaluates the user's learning tendency and level of understanding through a generative AI model.

[0705] Step 6: Generate the next problem

[0706] Based on the analysis results, the server readjusts the content and difficulty of the next question to be presented. The input is the analysis results and prompt text, and the output is the next question to be generated. Specifically, a prompt text is generated based on the analysis results, and this is provided to the generative AI model to generate a new question. The new question is then sent back to the device, and the user begins the next learning cycle.

[0707] 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.

[0708] This invention relates to a system that automatically generates questions according to the user's level of understanding, analyzes the answers to provide the next most appropriate questions, and recognizes the user's emotions to optimize the learning experience. This system operates in cooperation with a server, terminal, user, and emotion engine.

[0709] System Overview

[0710] 1. Initial Setup

[0711] When a user registers or logs in, the server collects basic information about the user and sets up the initial settings, including the user's learning goals, current level, and learning history.

[0712] 2. User authentication and data acquisition

[0713] A user logs into the system using a terminal, and the login information is sent from the terminal to the server, which then authenticates the user by checking it against information in a database.

[0714] If authentication is successful, the server retrieves the user's past learning history from a database and evaluates their current level of understanding based on that data.

[0715] 3. Problem generation

[0716] The server uses a generative AI model to create the next question based on the user's level of understanding. The questions are optimized taking into account the user's past answers and current level of understanding.

[0717] 4. Answer input and result feedback

[0718] The user answers questions via the terminal, and the user's answers are sent to the server.

[0719] The server evaluates the received answers and provides feedback to the user, which may include explanations of correct and incorrect answers and additional learning resources.

[0720] 5. Data accumulation and analysis

[0721] The server stores the answer results in a database, including correct and incorrect answers, the time it took to answer, and the difficulty of the questions.

[0722] The server analyzes this data using a generative AI model to assess the user's learning habits and comprehension. For example, if a user frequently makes mistakes on a particular type of question, the server will focus on questions in that area.

[0723] 6. Next problem generation

[0724] Based on the analysis results, the server adjusts the content and difficulty of the next question, allowing users to always solve questions at the optimal level.

[0725] The new questions generated are sent to the terminal again, and the next learning cycle begins.

[0726] Introducing the Emotion Engine

[0727] 1. Emotion recognition

[0728] When a user uses the device to answer questions, the device uses a camera and microphone to capture the user's facial expressions and tone of voice.

[0729] The device uses an emotion recognition engine to determine the user's emotional state from the captured data, which can include happiness, sadness, stress, excitement, etc.

[0730] 2. Transmission and analysis of emotional data

[0731] The device transmits the recognized emotion data to the server.

[0732] The server analyzes this emotional data and adjusts the difficulty and content of the questions based on the user's current emotional state, and also optimizes the form and content of the feedback to suit the user's emotions.

[0733] 3. Emotion-based problem generation and feedback

[0734] The server generates new problems taking into account the emotional data. For example, if the user is feeling stressed, it may lower the difficulty level or provide feedback including encouraging messages.

[0735] This information is also sent to the terminal, and the user's next learning cycle is initiated in an emotionally sensitive manner.

[0736] Specific examples

[0737] Consider the case where User B logs into the system and begins a normal learning session.

[0738] 1. User B's initial settings

[0739] User B sets his / her learning goal and current level. For example, User B wants to move from beginner to intermediate level.

[0740] The server uses this information to generate an appropriate initial problem set.

[0741] 2. User B's learning process

[0742] The question asks, "Choose the meaning of 'serene': a) noisy, b) quiet, c) pleasant."

[0743] User B selects "b) Quiet."

[0744] The server receives User B's answer, determines that it is correct, and provides feedback saying, "That's correct. 'serene' means 'quiet'."

[0745] At the same time, the device captures User B's facial expression and uses an emotion recognition engine to determine that he or she is under low stress.

[0746] 3. The next problem occurs

[0747] Since User B is not feeling stressed, the server generates a slightly more difficult question: "Choose the meaning of 'melancholy': a) enthusiastic, b) depressed, c) lively."

[0748] A new question is sent to the terminal and User B continues learning.

[0749] By repeating this process, users can obtain a learning experience that is optimized for their level of understanding and emotional state. This system supports efficient and effective learning and keeps users motivated to learn.

[0750] The processing flow will be explained below.

[0751] Step 1:

[0752] Initial Setup

[0753] The server loads a dataset of domain-related words, terms, meanings, and usage, including dictionary data, example sentence data, and past user learning data.

[0754] Step 2:

[0755] User Login

[0756] The user logs in by entering their user ID and password from the terminal. The terminal sends this authentication information to the server.

[0757] Step 3:

[0758] certification

[0759] The server compares the received authentication information with the user data in the database to authenticate the user. If authentication is successful, the server retrieves the user's learning history from the database.

[0760] Step 4:

[0761] Assessment of understanding

[0762] The server evaluates the user's current level of understanding based on the acquired learning history, including past correct answer rates and trends in questions that were incorrectly answered.

[0763] Step 5:

[0764] Preparing the emotion recognition engine

[0765] The device prepares a camera and microphone to capture the user's facial expressions and tone of voice, thereby collecting emotional data in real time.

[0766] Step 6:

[0767] First problem generation

[0768] The server uses a generative AI model to generate questions tailored to the user's level of understanding. For example, an intermediate-level user might be asked, "Choose the meaning of 'abate'."

[0769] Step 7:

[0770] Submit an issue

[0771] The server sends the generated questions to the terminal, where the user can check the questions.

[0772] Step 8:

[0773] Enter your answer

[0774] The user uses the device to input answers to the questions. When inputting the answers, the device captures the user's facial expressions and voice and sends them to the emotion engine.

[0775] Step 9:

[0776] emotion recognition

[0777] The device uses an emotion engine to analyze the user's emotional state, for example, to determine whether the user is stressed or focused.

[0778] Step 10:

[0779] Submit your answer

[0780] The terminal transmits the user's answers and emotion data to the server.

[0781] Step 11:

[0782] Judging the answer

[0783] The server evaluates the received answer and checks whether it is correct or not. For example, "If you chose 'abate' as meaning 'to decrease,' check whether this is the correct answer."

[0784] Step 12:

[0785] Feedback Generation

[0786] The server generates feedback based on the answer, taking into account sentiment data and including encouraging messages such as "Correct! 'abate' means 'decrease'. You're doing great!"

[0787] Step 13:

[0788] Send Feedback

[0789] The server sends the feedback to the terminal, which displays the feedback to the user.

[0790] Step 14:

[0791] Data storage

[0792] The server stores the answer results and emotional data in a database, including correct / incorrect answers, answer time, question difficulty, emotional state, etc.

[0793] Step 15:

[0794] Analyzing the data

[0795] The server analyzes the saved answer results and emotional data using a generative AI model to evaluate the user's answering tendencies, strengths and weaknesses, and emotional tendencies.

[0796] Step 16:

[0797] Next problem generation

[0798] Based on the analysis results, the server adjusts the content and difficulty of the next question, taking into account emotional data, for example, by presenting easier questions if the user is tired.

[0799] Step 17:

[0800] Submit a new issue

[0801] The server sends the newly generated problem to the device, and the user attempts the next problem, and the process is repeated.

[0802] Example 2

[0803] 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."

[0804] Conventional learning systems have limited ability to generate questions that correspond to the user's level of understanding, making it difficult to adapt to each user's individual learning progress and emotional state. Furthermore, because they only consider the user's learning history, it is difficult to maintain motivation during learning. Furthermore, feedback on answer results is one-dimensional, which does not fully address individual learning needs. Therefore, to maximize the user's learning effectiveness, it is essential to dynamically generate questions and provide feedback that are optimized according to the user's level of understanding and emotional state.

[0805] 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.

[0806] In this invention, the server includes means for performing user initial settings, means for authenticating the user and acquiring the user's learning history, means for generating questions according to the user's level of understanding, means for inputting answers, means for judging the answer results and providing feedback, means for saving and analyzing the answer results and generating the next question, means for acquiring and analyzing the user's emotional data, and means for adjusting the difficulty of questions and feedback based on the user's emotional state. This makes it possible to always provide an optimal learning experience by taking into account the user's level of understanding and emotional state.

[0807] The "means for performing user initial settings" is a means for collecting basic information such as the user's learning objectives, current level, and learning history, and for performing the initial settings of the system.

[0808] The "means for authenticating a user and acquiring a learning history" refers to the means for verifying the login information entered when a user logs into the system and acquiring the user's past learning history from the database.

[0809] "Means for generating questions according to the user's level of understanding" refers to a means for dynamically generating the optimal question to be asked next using a generative AI model based on the user's learning history and latest answer results.

[0810] The "means for inputting an answer" is a means by which a user inputs an answer to a presented question and transmits the answer to the system.

[0811] The "means for determining the answer result and providing feedback" refers to the means by which the server determines the answer submitted by the user and provides feedback based on the result. This feedback includes determining whether the answer is correct or incorrect and providing learning resources.

[0812] The "means for saving and analyzing the answer results and generating the next question" is a means for saving the user's answer results in a database and analyzing them to generate the next optimal question.

[0813] The "means for acquiring and analyzing user emotional data" refers to a means for capturing the user's facial expressions and voice data using the device's camera and microphone, and analyzing the user's emotional state using an emotion recognition engine.

[0814] "Means for adjusting the difficulty of questions and feedback based on the user's emotional state" refers to means for dynamically adjusting the difficulty of questions and the content of feedback based on analyzed emotional data to suit the user's current emotional state.

[0815] This invention relates to a system that automatically generates questions according to the user's level of understanding, analyzes the answers to provide the next most appropriate questions, and recognizes the user's emotions to optimize the learning experience. This system operates in cooperation with a server, terminal, user, and emotion engine.

[0816] The outline of the system is as follows:

[0817] Initial Setup

[0818] When a user registers or logs in, the server collects basic information about the user and performs initial setup. This includes the user's learning goals, current level, learning history, etc. Specifically, the user sets their learning goals and current level. Based on this information, the server generates an appropriate initial problem set and stores it in the database. For example, User A wishes to "move from beginner to intermediate level English," and sets the basic information required for this.

[0819] User authentication and data acquisition

[0820] A user logs in to the system using a terminal. The login information is sent from the terminal to the server, and the server authenticates the user by comparing it with information in the database. If authentication is successful, the server retrieves the user's past learning history from the database and evaluates their current level of understanding based on that data. For example, User B logs in and their past learning data is retrieved.

[0821] problem generation

[0822] The server uses a generative AI model to generate the next question based on the user's level of understanding. The questions are optimized by taking into account the user's past answers and current level of understanding. For example, the server generates a question for User B: "Please choose the meaning of 'serene': a) noisy, b) quiet, c) comfortable."

[0823] Answer input and result feedback

[0824] The user answers questions via the terminal. The terminal sends the user's answers to the server. The server evaluates the received answers and provides feedback to the user on whether they are correct or incorrect. Specific feedback may include explanations of correct or incorrect answers and additional learning resources. For example, if user B selects "b) quiet," the server provides the following feedback: "That's correct. 'serene' means 'quiet.'"

[0825] Data accumulation and analysis

[0826] The server stores the answers in a database. The stored data includes correct and incorrect answers, the time it took to answer, and the difficulty of the questions. The server analyzes this data using a generative AI model to evaluate the user's learning habits and comprehension. For example, if a user frequently makes mistakes on a certain type of question, the server will focus on questions in that area.

[0827] Next problem generation

[0828] Based on the analysis results, the server readjusts the content and difficulty of the next question. This allows the user to always solve questions at the optimal level. The new questions generated are sent back to the device, and the next learning cycle begins. For example, if it is analyzed that User B is not feeling stressed, a question with a slightly higher level of difficulty is generated.

[0829] Introducing the Emotion Engine

[0830] When a user answers questions using the device, the device uses a camera and microphone to capture the user's facial expressions and tone of voice. The device then uses an emotion recognition engine to determine the user's emotional state from the captured data, which can include happiness, sadness, stress, and excitement. The recognized emotional data is sent to a server, which analyzes the emotional data and adjusts the difficulty and content of the questions based on the user's current emotional state. The form and content of the feedback is also optimized to match the user's emotions.

[0831] Specific examples

[0832] Consider the case where User B logs in to the system and begins a normal learning session. User B's initial setting is to set his / her learning goal as "Beginner to intermediate level English." The server generates an initial set of questions based on this information. For example, User B is presented with a question asking, "What is the meaning of 'serene'? a) noisy, b) quiet, c) comfortable." User B selects "b) quiet," and the server provides feedback saying, "That's correct. 'serene' means 'quiet.'" At the same time, the device captures User B's facial expression and determines that he / she is under low stress using an emotion recognition engine. Next, the server generates a slightly more difficult question, asking, "What is the meaning of 'melancholy'? a) enthusiastic, b) depressed, c) lively."

[0833] By repeating this process, users can obtain a learning experience that is optimized for their level of understanding and emotional state. This system supports efficient and effective learning and keeps users motivated to learn.

[0834] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0835] Step 1:

[0836] A new user registration or login is performed. The user uses a terminal to enter their ID and password or new registration information. The entered information is sent from the terminal to the server.

[0837] Input: User ID, password, new registration information

[0838] Output: Authentication information sent to the server

[0839] Specific operation: User A enters the necessary information into the new registration form on the device and presses the send button. The device then sends the entered information to the server.

[0840] Step 2:

[0841] The server authenticates the user by comparing login information and new registration information with information in the database. If authentication is successful, the server obtains the user's past learning history.

[0842] Input: The authentication information sent to the server

[0843] Output: Authentication results, learning history data

[0844] Specific operation: The server authenticates User A by checking against the database, and after successful authentication, retrieves User A's past learning history from the database.

[0845] Step 3:

[0846] The server performs initial setup based on the user's basic information, including the user's learning goals, current level, and learning history.

[0847] Input: Learning objectives, current level, learning history

[0848] Output: Initial setup data, initial problem set

[0849] Specific operation: User A sets "I want to move from beginner to intermediate level English," and the server generates an initial set of questions based on that information.

[0850] Step 4:

[0851] The server generates the next question based on the user's level of understanding, using a generative AI model to consider the user's past answers and current level of understanding to create the most appropriate question.

[0852] Input: User's comprehension data, answer results

[0853] Output: Next problem data

[0854] Specific operation: The server uses the generative AI model to generate a question for User B: "Please choose the meaning of 'serene': a) noisy, b) quiet, c) comfortable."

[0855] Step 5:

[0856] The user answers questions via the terminal and sends the answers, which are then sent to the server.

[0857] Input: User's answer data

[0858] Output: Answer data sent to the server

[0859] Specific operation: User B selects "b) Quiet" and the device sends the user's answer to the server.

[0860] Step 6:

[0861] The server evaluates the received answers and provides feedback to the user, including explanations of correct and incorrect answers and additional learning resources.

[0862] Input: User's answer data

[0863] Output: Feedback data

[0864] Specific behavior: The server judges the answer and provides feedback such as "Correct. 'serene' means 'quiet'."

[0865] Step 7:

[0866] The server stores the answer results in a database. The stored data includes correct answers, answer time, difficulty level of the question, etc. The server analyzes this data using a generative AI model.

[0867] Input: Answer result data

[0868] Output: Analysis data, storage data

[0869] Specific operation: The server stores User B's answer data in a database and analyzes it using a generative AI model.

[0870] Step 8:

[0871] The server then adjusts the content and difficulty of the next question based on the analysis results, and the new question is then sent back to the device.

[0872] Input: Analysis data

[0873] Output: Rescaled problem data

[0874] Specific operation: The server analyzes that User B is not feeling stressed, generates the next question "Please choose the meaning of 'melancholy': a) enthusiastic, b) depressed, c) lively" and sends it to the terminal.

[0875] Step 9:

[0876] The device uses a camera and microphone to capture the user's facial expressions and tone of voice, and an emotion recognition engine to determine the user's emotional state.

[0877] Input: facial expression data, voice data

[0878] Output: Emotion data

[0879] Specific operation: When User B answers the question, the device captures facial expression data and the emotion recognition engine determines that the user is under low stress.

[0880] Step 10:

[0881] The emotion recognition results are sent to a server, which analyzes the emotion data and adjusts the difficulty of the questions and feedback based on the user's current emotional state.

[0882] Input: Emotion data

[0883] Output: Adjusted problem data, feedback data

[0884] How it works: The device sends emotional data to the server, and the server adjusts the difficulty of the next question and feedback based on the emotional state.

[0885] (Application example 2)

[0886] 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."

[0887] Conventional learning management systems and task management systems for factory robots do not dynamically adjust tasks according to the user's or robot's level of understanding or workload, making efficient learning and work execution difficult. This has led to problems such as a decline in the user's motivation to learn and robot overload. Furthermore, these systems were unable to recognize and reflect emotions or workload conditions, preventing optimal feedback and task generation.

[0888] 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.

[0889] In this invention, the server includes means for performing user initial settings, means for authenticating the user and acquiring the user's learning history, means for generating questions according to the user's level of understanding, means for inputting answers, means for judging the answer results and providing feedback, means for saving and analyzing the answer results and generating the next question, means for the robot to learn a new task, means for adjusting the difficulty of the next task based on the task results, and means for recognizing the robot's load state and optimizing task execution efficiency. This enables efficient learning while increasing the user's motivation to learn, and enables optimal task execution while preventing the robot from being overloaded.

[0890] "User initial settings" refers to the process of collecting and setting basic information about a user's learning goals, current level, and learning history when the user registers or logs in.

[0891] "User authentication" is the process of verifying the user's identity when the user logs in to a system by sending the entered information to a server and comparing it with information in a database.

[0892] "Means for obtaining learning history" refers to the process by which the server reads past learning data from the database and uses it to evaluate the user's current level of understanding.

[0893] "Means for generating questions according to the user's level of understanding" refers to the process of using a generative AI model to create the optimal question to be asked next, based on the user's past answers and current level of understanding.

[0894] "Means for inputting answers" refers to the process in which a user inputs an answer to a question and the answer is sent to the server.

[0895] The "means for determining the answer result and providing feedback" is the process by which the server determines the received answer and provides the user with feedback on whether it is correct or not, as well as learning resources.

[0896] "Means for saving and analyzing the answer results and generating the next question" refers to the process in which the server saves the answer results in a database, analyzes them to evaluate the user's learning tendencies and level of understanding, and readjusts the content and difficulty of the next question to be asked.

[0897] "Means for robots to learn new tasks" refers to the process by which factory robots efficiently learn new jobs or tasks.

[0898] The "means for adjusting the difficulty of the next task based on the results of the task" is a process for dynamically adjusting the difficulty of the next task based on the results of the robot's task execution.

[0899] "Means for recognizing the load state of the robot and optimizing the efficiency of task execution" refers to a process for recognizing the load state of the robot and adjusting the difficulty and order of tasks to enable optimal task execution while preventing overload.

[0900] This invention is a system for maximizing the learning and working efficiency of users and robots, and is composed of a server, a terminal, a user, a robot, and an emotion engine. The system is specifically implemented as follows.

[0901] System Overview

[0902] Initial Setup

[0903] When a user performs initial setup, the server collects basic information about the user's learning goals, current level, and learning history. Based on this information, the server provides optimal initial setup for each user. The server also collects work goals and current task data for factory robots and performs initial setup.

[0904] User authentication and data acquisition

[0905] A user logs in to the system using a terminal. The login information is sent to the server, which then authenticates the user by comparing it with information in the database. If authentication is successful, the server retrieves the user's past learning history from the database and evaluates their current level of understanding.

[0906] problem generation

[0907] The server uses a generative AI model to create the next question based on the user's level of understanding. The questions are optimized by taking into account the user's past answers and current level of understanding. Similarly, the server analyzes the results of tasks for factory robots and generates the optimal next task to be performed.

[0908] Answer input and result feedback

[0909] Users answer questions via their device. The answers are sent from the device to the server, which evaluates them and provides feedback on whether the answer was correct or incorrect. Specific feedback may include explanations of correct or incorrect answers and additional learning resources. For robots, the server receives the results of the tasks performed, determines whether the robot was successful, and adjusts the difficulty of the next task based on the results.

[0910] Data accumulation and analysis

[0911] The server stores the answers and task execution results in a database. The stored data includes correct / incorrect answers, the time it took to answer, the difficulty of the question, the success / failure of the task, and the execution time. The server analyzes this data using a generative AI model to evaluate the user's learning tendency and level of understanding, as well as the robot's work efficiency.

[0912] Next problem generation

[0913] The server then adjusts the content and difficulty of the next question based on the analysis results, allowing users to always solve questions at the optimal level. The server also generates and suggests optimal tasks for the robot based on the analysis results.

[0914] Introducing the Emotion Engine

[0915] emotion recognition

[0916] When a user answers questions using the device, the device uses a camera and microphone to capture the user's facial expressions and tone of voice. An emotion recognition engine is used to determine the user's emotional state from the captured data. For robots, the emotional state (load state) is recognized based on the workload of performing the task.

[0917] Sending and analyzing emotional data

[0918] The device sends the recognized emotional data to a server, which analyzes the data and adjusts the difficulty and content of the questions and tasks based on the user's current emotional state and the robot's workload. The server also optimizes the form and content of feedback to match the user's emotional state.

[0919] Emotion-based problem generation and feedback

[0920] The server generates new problems and tasks taking into account the emotional data. For example, if the user is feeling stressed, it will lower the difficulty level slightly or provide feedback including an encouraging message. Also, if the robot is overloaded, it will reduce the difficulty of the next task. This information is sent to the terminal or robot, and the next cycle will begin taking into account the user's emotions and stress state.

[0921] Specific examples

[0922] Consider a case where a user logs in to the system and begins a learning session. For example, a question might appear: "Please choose the meaning of 'serene': a) noisy, b) quiet, c) comfortable." If the user selects "b) quiet," the server determines that this is the correct answer and provides feedback such as, "You're correct. 'serene' means 'quiet.'" The device simultaneously captures the user's facial expression and uses an emotion recognition engine to determine that the user is under stress. Also, if a factory robot performs a task called "assembly" and succeeds, the server suggests the slightly more difficult "inspection" task as the next task.

[0923] Prompt Sentence Examples

[0924] "The robot has succeeded five times and failed three times in the 'Inspect' task. What type and difficulty of task should it suggest next?"

[0925] "The user answered the 'serene' question correctly. Please generate a related vocabulary question for them to answer next."

[0926] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0927] Step 1:

[0928] The server provides the terminal with a screen for the user to perform initial setup. The user inputs information such as their learning objectives, current level, learning history, etc. The input data is sent to the server, which then stores the information in a database.

[0929] Step 2:

[0930] A user logs into the system using a terminal. The login information (user ID, password, etc.) is sent from the terminal to the server, which then authenticates the user by comparing it with information in the database. If authentication is successful, the server retrieves the user's past learning history from the database and sends that information to the terminal for display.

[0931] Step 3:

[0932] The server uses a generative AI model to generate questions based on the user's level of understanding. The generative AI model uses the user's past answers and current level of understanding as input data and outputs the optimal question to be posed next. This question is sent from the server to the device and displayed to the user.

[0933] Step 4:

[0934] The user answers the questions displayed via the terminal. The answer data is sent from the terminal to the server, and the server receives the answer data. The server compares the answer data with the correct answer data and determines whether the answer was correct or incorrect.

[0935] Step 5:

[0936] The server evaluates the answer and provides the result as feedback to the user. The feedback may include explanations of correct and incorrect answers and additional learning resources. The feedback data is sent from the server to the device and displayed to the user.

[0937] Step 6:

[0938] The server stores the answer results in a database. The stored data includes correct and incorrect answers, the time it took to answer, and the difficulty of the questions. This data serves as the basis for subsequent data analysis and question generation.

[0939] Step 7:

[0940] The server uses the stored data to analyze the user's learning habits and level of understanding using a generative AI model, and the analysis data is used to adjust the content and difficulty of the next questions.

[0941] Step 8:

[0942] The server then sends the newly generated questions to the device, and the next learning cycle begins, ensuring that the user is always challenged with questions of appropriate difficulty.

[0943] Step 9:

[0944] When a robot learns a new task, the server receives the robot's task settings and result data input via the terminal, and saves the robot's work history and current load status as data.

[0945] Step 10:

[0946] The server receives the results of the robot's tasks and analyzes the data on success and failure. Based on the analysis results, the data is processed to adjust the difficulty of the next task, and a new task is generated using the generative AI model. This data is then sent to the robot or the operator's device.

[0947] Step 11:

[0948] The emotion engine recognizes the robot's load state and adjusts to reduce the difficulty of the task if it is overloaded. The server generates feedback based on this situation and sends the feedback data to the robot and the operator's device.

[0949] Prompt Sentence Examples

[0950] "The robot has succeeded five times and failed three times in the 'Inspect' task. What type and difficulty of task should it suggest next?"

[0951] "The user answered the 'serene' question correctly. Please generate a related vocabulary question for them to answer next."

[0952] 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.

[0953] 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.

[0954] 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.

[0955] [Third embodiment]

[0956] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0957] 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.

[0958] 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).

[0959] 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.

[0960] 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.

[0961] 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).

[0962] 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.

[0963] 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.

[0964] 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.

[0965] 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.

[0966] 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.

[0967] 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."

[0968] This invention relates to a system that automatically generates questions according to the user's level of understanding, analyzes the answers, and provides the next most appropriate questions. This system operates in cooperation with a server, terminals, and users.

[0969] System Overview

[0970] 1. Initial Setup

[0971] When a user registers or logs in, the server collects basic information about the user and sets up the initial settings, including the user's learning goals, current level, and learning history.

[0972] 2. User authentication and data acquisition

[0973] A user logs into the system using a terminal, and the login information is sent from the terminal to the server, which then authenticates the user by checking it against information in a database.

[0974] If authentication is successful, the server retrieves the user's past learning history from a database and evaluates their current level of understanding based on that data.

[0975] 3. Problem generation

[0976] The server uses a generative AI model to create the next question based on the user's level of understanding. The questions are optimized taking into account the user's past answers and current level of understanding.

[0977] 4. Answer input and result feedback

[0978] The user answers questions via the terminal, and the user's answers are sent to the server.

[0979] The server evaluates the received answers and provides feedback to the user, which may include explanations of correct and incorrect answers and additional learning resources.

[0980] 5. Data accumulation and analysis

[0981] The server stores the answer results in a database, including whether the answer was correct, the time it took to answer, and the difficulty of the question.

[0982] The server analyzes this data using a generative AI model to assess the user's learning habits and comprehension. For example, if a user frequently makes mistakes on a particular type of question, the server will focus on questions in that area.

[0983] 6. Next problem generation

[0984] Based on the analysis results, the server adjusts the content and difficulty of the next question, allowing users to always solve questions at the optimal level.

[0985] The new questions generated are sent to the terminal again, and the next learning cycle begins.

[0986] Specific examples

[0987] Consider the case where User A logs into the system and begins his or her first learning session.

[0988] 1. User A's initial settings

[0989] User A sets his / her learning goal and current level (e.g., intermediate).

[0990] The server uses this information to generate an appropriate initial problem set.

[0991] 2. User A's learning process

[0992] The question is "Choose the meaning of 'abate': a) increase, b) decrease, c) maintain."

[0993] User A selects "b) Decrease."

[0994] The server receives User A's answer, determines that it is correct, and provides feedback saying, "That's correct. 'abate' means 'decrease'."

[0995] The results are stored in a database, and the server uses this information to generate the next question.

[0996] 3. Generate the next question for User A

[0997] The server evaluates user A's understanding and then generates the question "Choose the meaning of 'nuance': a) subtle, b) direct, c) obvious."

[0998] This new question is sent to the terminal, and User A continues learning.

[0999] By repeating this process, users can obtain a learning experience that is optimized for their level of understanding. This system supports efficient and effective learning, helping users achieve their goals in a short period of time.

[1000] The processing flow will be explained below.

[1001] Step 1:

[1002] Initial Setup

[1003] The server loads a dataset of domain-related words, terms, meanings, and usage, including dictionary data, example sentence data, and past user learning data.

[1004] Step 2:

[1005] User Authentication

[1006] A user accesses the system from a terminal and logs in by entering a user ID and password. The terminal sends this authentication information to the server.

[1007] Step 3:

[1008] Authentication Results

[1009] The server compares the received authentication information with the user data in the database and performs authentication. If authentication is successful, the server retrieves the user's learning history from the database.

[1010] Step 4:

[1011] Assessment of understanding

[1012] The server evaluates the user's current level of understanding based on the acquired learning history, including past correct answer rates and trends in questions that were incorrectly answered.

[1013] Step 5:

[1014] First problem generation

[1015] The server uses a generative AI model to generate questions tailored to the user's level of understanding. For example, an intermediate-level user might be asked, "Choose the meaning of 'abate'."

[1016] Step 6:

[1017] Submit an issue

[1018] The server sends the generated questions to the terminal, where the user can check the questions.

[1019] Step 7:

[1020] Enter your answer

[1021] The user enters answers to questions using a terminal, and the answers are sent from the terminal to the server.

[1022] Step 8:

[1023] Judging the answer

[1024] The server evaluates the received answer and determines whether it is correct or incorrect. For example, "If you chose 'abate' as meaning 'to decrease,' check if this is correct."

[1025] Step 9:

[1026] feedback

[1027] The server generates feedback based on the answer, for example, "Your answer is correct. 'abate' means 'decrease'," and sends it to the device.

[1028] Step 10:

[1029] Data storage

[1030] The server stores the answer results in a database, which records correct and incorrect answers, answer time, and question difficulty.

[1031] Step 11:

[1032] Analyzing the data

[1033] The server analyzes the stored data using a generative AI model to evaluate the user's answering tendencies and strengths and weaknesses.

[1034] Step 12:

[1035] Next problem generation

[1036] Based on the analysis results, the server uses the generative AI model to create the next appropriate question, thereby continuously providing questions that are appropriate for the level.

[1037] Step 13:

[1038] Submit a new issue

[1039] The server sends the newly generated problem to the device, and the user attempts the next problem, and the process is repeated.

[1040] Example 1

[1041] 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."

[1042] Current educational systems lack the ability to provide questions that are individually optimized for a user's level of understanding. This reduces the user's learning efficiency and makes effective learning difficult. Furthermore, continuous feedback and learning history management are insufficient, and it is often difficult to properly set the next learning step based on the user's level of understanding. This can reduce learning effectiveness and cause the learning process to stagnate.

[1043] 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.

[1044] In this invention, the server includes a means for performing user initial settings, a means for authenticating the user and acquiring their learning history, a means for using a generative AI model to generate questions according to the user's level of understanding, a means for judging the answer results and providing feedback, and a means for saving and analyzing the answer results and generating the next question. This makes it possible to generate optimal questions and provide feedback according to the user's level of understanding, thereby improving learning effectiveness.

[1045] "User" refers to an individual or group that uses the system to study.

[1046] "Initial settings" refers to the information input and setup process that users go through when they start using the system, including the user's basic information, learning objectives, current level, etc.

[1047] "Authentication" is the process by which a server verifies a user's information and authorizes access rights when a user logs into a system.

[1048] "Study history" is a collection of data such as records of the user's past studies, grades, answer history, etc.

[1049] "Level of understanding" is an index that indicates how much a user understands a particular learning content.

[1050] A "question" is one of the quizzes or assignments provided by the system to assess and improve the user's understanding.

[1051] A "generative AI model" is an algorithm that uses machine learning to generate questions based on the user's level of understanding.

[1052] An "answer" is a response provided by a user to a question posed by the system.

[1053] "Feedback" refers to the system's response to the user's answer, such as evaluation or explanation.

[1054] "Saving" refers to the act of recording data such as the user's learning history and answer results in a database.

[1055] "Analysis" is the process of using stored data to evaluate a user's learning trends and comprehension.

[1056] This invention is a system that automatically generates questions according to the user's level of understanding, analyzes the answers, and provides the next most appropriate questions. This system operates in cooperation with the server, terminals, and users.

[1057] System Overview

[1058] Initial Setup

[1059] The server collects basic information about the user when the user registers or logs in. This information includes the user's learning goals, current level, and learning history, and is saved in a database. The server completes the initial setup when the user sets their learning goals and current level (e.g., intermediate).

[1060] User authentication and data acquisition

[1061] A user logs into the system using a terminal. The login information is sent from the terminal to the server using SSL / TLS. The server authenticates the user by checking it against information in a database, and if authentication is successful, it retrieves the user's past learning history and evaluates their current level of understanding.

[1062] problem generation

[1063] The server uses a generative AI model (e.g., GPT-4) to generate questions based on the user's level of understanding. The server optimizes the next question to be presented, taking into account the user's past answers and current level of understanding.

[1064] For example, the following prompt can be used:

[1065] "A user is learning intermediate level English vocabulary. Please generate the following questions for him. Based on his previous answers and statistics, he makes a lot of mistakes in the 'choose meaning' format. Please create a question containing the word 'nuance'. The format is as follows:

[1066] Choose the meaning of 'nuance': a) subtle, b) direct, c) obvious."

[1067] Answer input and result feedback

[1068] Users answer questions via their devices. The answers are immediately sent from the device to the server, which evaluates the answers. The server then provides feedback to the user, including explanations of correct and incorrect answers and additional learning resources as needed.

[1069] Data accumulation and analysis

[1070] The server stores all answer results in a database. This stored data includes whether the answer was correct, the time it took to complete the answer, and the difficulty of the question. The server analyzes this data using a generative AI model to evaluate the user's learning tendency and level of understanding.

[1071] Next problem generation

[1072] Based on the analysis results, the server adjusts the content and difficulty of the next questions. The generated questions are then sent back to the device to start the user's next learning cycle, providing a continuously optimized learning experience.

[1073] Specific examples

[1074] Below is an example of User A logging into the system for the first time and starting a learning session.

[1075] 1. Initial Setup

[1076] User A enters his / her learning objectives and current level (e.g., intermediate) in the application and presses the submit button. The server receives the input information and saves it in the database.

[1077] 2. Learning Process

[1078] User A enters his / her username and password on the login screen and clicks the login button.

[1079] The device sends login information to the server, which then authenticates it. After successful authentication, the learning history is acquired.

[1080] The server sends the generated AI model a prompt: "Please choose the meaning of 'abate': a) increase, b) decrease, c) maintain," and sends the generated problem to the device.

[1081] User A selects "b) Decrease."

[1082] The device sends this answer to the server, which judges the answer and provides feedback.

[1083] By repeating this process, users can always get the best learning experience. The system supports efficient and effective learning, helping users achieve their goals.

[1084] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1085] Step 1:

[1086] Initial Setup

[1087] A user accesses the new registration or login screen using a device. The user enters basic information such as name, email address, learning objectives, and current level, and clicks the submit button. The device sends the input data to the server. The server stores the received data in a database and completes the initial setup.

[1088] Input: User enters and submits basic information

[1089] Output: Save basic information to the database

[1090] Step 2:

[1091] User authentication and data acquisition

[1092] To log in using a terminal, a user enters a username and password and presses the login button. The terminal encrypts this authentication information using the SSL / TLS protocol and sends it to the server. The server performs authentication by comparing it with information in a database. If authentication is successful, the server retrieves past learning history from the database and evaluates the user's current level of understanding based on that data.

[1093] Input: User enters and submits login information

[1094] Output: Acquisition of learning history from the database and evaluation of comprehension

[1095] Step 3:

[1096] problem generation

[1097] The server uses a generative AI model (e.g., GPT-4) to create the next question to be posed based on the user's level of understanding. The server creates a prompt sentence taking into account the user's past answers and current level of understanding, and sends it to the generative AI model. The generated question is then sent from the server to the device.

[1098] Input: User's learning history and comprehension

[1099] Output: Generated issues sent to terminal

[1100] For example, "A user is learning intermediate level English vocabulary. Please generate the following questions for him. Based on his previous answers and statistical data, he makes a lot of mistakes in the 'choose meaning' format. Please create a question containing the word 'nuance'. The format is as follows:

[1101] Please choose the meaning of 'nuance': a) subtle, b) direct, c) obvious."

[1102] Step 4:

[1103] Answer input and result feedback

[1104] The user answers questions via the device. The user's answers are sent from the device to the server. The server evaluates the received answers and generates a correct / incorrect result. It also generates feedback including explanations of correct / incorrect answers and additional learning resources and sends it to the device.

[1105] Input: User's answer

[1106] Output: Generate feedback and send it to the device

[1107] Step 5:

[1108] Data accumulation and analysis

[1109] The server stores all answer results in a database. This stored data includes whether the answer was correct or incorrect, the time it took to complete the answer, and the difficulty of the question. Using a generative AI model, the server analyzes this data and evaluates the user's learning tendency and level of understanding.

[1110] Input: User's answer result

[1111] Output: Evaluation of learning tendency and comprehension

[1112] Step 6:

[1113] Next problem generation

[1114] The server then adjusts the content and difficulty of the next questions based on the analysis results. The generated questions are then sent back to the user's device, and the user's next learning cycle begins. This allows the user to always tackle questions at the optimal level.

[1115] Input: Analysis results

[1116] Output: Generate the next problem and send it to the terminal

[1117] This allows users to have a continuously optimized learning experience and progress effectively with their studies.

[1118] (Application example 1)

[1119] 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."

[1120] Conventional systems have limitations in their ability to provide optimal questions based on the user's level of understanding, making efficient learning difficult. Furthermore, they lack the ability to evaluate users' learning tendencies in detail, making it impossible to provide optimal learning programs for individual users. Under these circumstances, there is a need to improve the efficiency of employee training, especially in brick-and-mortar stores, but achieving this is difficult.

[1121] 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.

[1122] In this invention, the server includes means for performing user initial settings, means for authenticating the user and acquiring the user's learning history, means for generating questions according to the user's level of understanding, means for inputting answers, means for judging the answer results and providing feedback, means for saving and analyzing the answer results and generating the next question, means for evaluating the user's learning tendency, and means for generating a prompt sentence for generating the next most appropriate question. This makes it possible to provide questions optimized for each user's individual level of understanding and to progress with subsequent learning, thereby realizing more efficient employee training, particularly in physical stores.

[1123] The "means for initial user settings" is a means for collecting basic information about the user, their learning goals, and their current level, and registering them in the system.

[1124] The "means for authenticating a user and acquiring a learning history" refers to a means for authenticating a user based on the information provided by the user when logging in, and acquiring the user's past learning history from a database.

[1125] "Means for generating questions according to the user's level of understanding" refers to a means for creating appropriate questions using a generative AI model based on the user's learning history and answer results.

[1126] "Means for inputting answers" refers to the means by which a user inputs answers to questions into the system.

[1127] The "means for determining the answer result and providing feedback" is a means for analyzing the answer entered by the user, determining whether it is correct or incorrect, and providing the user with feedback based on the result.

[1128] The "means for saving and analyzing the answer results and generating the next question" is a means for saving the user's answer results in a database and analyzing them to generate the next question to be asked.

[1129] The "means for assessing the user's learning tendency" is a means for analyzing the collected data and assessing the user's strengths and weaknesses.

[1130] The "means for generating a prompt sentence for generating the next most suitable question" is a means for creating a prompt sentence for generating the next most suitable question to be asked based on the user's level of understanding and learning tendencies.

[1131] This invention is a system that automatically generates appropriate questions based on the user's level of understanding. This system operates with the cooperation of a server, terminals, and users.

[1132] 1. Initial Setup

[1133] When a user registers or logs in, the server collects basic information about the user and sets up the initial settings, including the user's learning goals, current level, learning history, etc. The server stores this information in a database and estimates the user's initial level.

[1134] 2. User authentication and data acquisition

[1135] Users log in to the system through their terminal. The login information is sent from the terminal to the server, and the server authenticates the user by comparing it with information in the database. If authentication is successful, the server retrieves the user's past learning history from the database and evaluates their current level of understanding based on that data.

[1136] 3. Problem generation

[1137] The server uses a generative AI model to automatically generate questions based on the user's level of understanding. It then generates prompts to optimize the questions, taking into account the user's past answers and current level of understanding. These prompts have the following format:

[1138] User level: Intermediate

[1139] User History: Completed training on past case management.

[1140] Next, generate the question to be asked:

[1141] 4. Answer input and result feedback

[1142] Users answer questions via their device. The answers are sent from the device to the server, which analyzes them to determine whether they are correct or incorrect and provides feedback. The feedback may include detailed explanations of correct and incorrect answers and additional learning resources.

[1143] 5. Data accumulation and analysis

[1144] The server stores the answers in a database. The stored data includes whether the answer was correct, the time it took to answer, and the difficulty of the question. The server analyzes this data using a generative AI model to evaluate the user's learning habits and comprehension. For example, if a user frequently makes mistakes on a certain type of question, the server will focus on that area.

[1145] 6. Next problem generation

[1146] The server then uses the results of the analysis to adjust the content and difficulty of the next questions, which are then sent back to the device, starting the next learning cycle.

[1147] Hardware and software used

[1148] Hardware: Servers, devices (smartphones, tablets, etc.)

[1149] Software: Databases (MySQL, PostgreSQL), generative AI models (OpenAI GPT-3), analysis tools (Scikit-learn)

[1150] Specific examples

[1151] For example, user A logs into the system and begins his first study session. If user A is initially set to "intermediate," the server generates the following questions:

[1152] "Choose the meaning of 'abate': a) to increase, b) to decrease, c) to maintain."

[1153] If User A selects "b) Decrease," the server determines this is the correct answer and provides the following feedback:

[1154] "That's correct. 'abate' means 'to decrease'."

[1155] The server then evaluates User A's understanding and generates the following questions:

[1156] "Choose the meaning of 'nuance': a) subtle, b) direct, c) obvious."

[1157] In this way, user A can always solve problems that are optimized for his or her level of understanding.

[1158] The above is a concrete implementation method of this system. This system can provide an individually optimized learning experience that takes into account the user's learning tendencies and level of understanding. It is expected to be particularly useful in improving the efficiency of employee training in brick-and-mortar stores.

[1159] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1160] Step 1: Initial Setup

[1161] A user uses a terminal to register or log in. At this time, the server collects the user's basic information (learning objectives, current level, learning history, etc.) and stores it in a database. The input is the user's basic information, and the output is the user information stored in the database. Based on this information, the server estimates the user's initial level.

[1162] Step 2: User authentication and data acquisition

[1163] When a user logs in via a terminal, the server receives authentication information. The server compares this information with information in a database to authenticate the user. The input is the user's login information, and the output is whether the authentication was successful. If the authentication is successful, the server retrieves the user's past learning history from the database and evaluates the user's current level of understanding.

[1164] Step 3: Problem generation

[1165] The server uses a generative AI model to generate questions based on the user's level of understanding. A prompt is generated, and the AI ​​model creates questions based on this. The input is the user's learning history, comprehension data, and the prompt, and the output is the generated question. Specifically, the prompt is sent to the generative AI model via an API.

[1166] Step 4: Answer entry and feedback

[1167] The user answers questions via a terminal. The input is the user's answer to the question, and the output is the answer result (correctness or incorrectness) and feedback. The server receives the answer from the terminal, analyzes it to determine whether it is correct or incorrect, and generates detailed feedback to provide to the user.

[1168] Step 5: Data collection and analysis

[1169] The server stores the user's answer results in a database. The input is the answer results (correct or incorrect, time taken to answer, difficulty of the question, etc.), and the output is the analysis data stored in the database. Using this, the server evaluates the user's learning tendency and level of understanding through a generative AI model.

[1170] Step 6: Generate the next problem

[1171] Based on the analysis results, the server readjusts the content and difficulty of the next question to be presented. The input is the analysis results and prompt text, and the output is the next question to be generated. Specifically, a prompt text is generated based on the analysis results, and this is provided to the generative AI model to generate a new question. The new question is then sent back to the device, and the user begins the next learning cycle.

[1172] 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.

[1173] This invention relates to a system that automatically generates questions according to the user's level of understanding, analyzes the answers to provide the next most appropriate questions, and recognizes the user's emotions to optimize the learning experience. This system operates in cooperation with a server, terminal, user, and emotion engine.

[1174] System Overview

[1175] 1. Initial Setup

[1176] When a user registers or logs in, the server collects basic information about the user and sets up the initial settings, including the user's learning goals, current level, and learning history.

[1177] 2. User authentication and data acquisition

[1178] A user logs into the system using a terminal, and the login information is sent from the terminal to the server, which then authenticates the user by checking it against information in a database.

[1179] If authentication is successful, the server retrieves the user's past learning history from a database and evaluates their current level of understanding based on that data.

[1180] 3. Problem generation

[1181] The server uses a generative AI model to create the next question based on the user's level of understanding. The questions are optimized taking into account the user's past answers and current level of understanding.

[1182] 4. Answer input and result feedback

[1183] The user answers questions via the terminal, and the user's answers are sent to the server.

[1184] The server evaluates the received answers and provides feedback to the user, which may include explanations of correct and incorrect answers and additional learning resources.

[1185] 5. Data accumulation and analysis

[1186] The server stores the answer results in a database, including correct and incorrect answers, the time it took to answer, and the difficulty of the questions.

[1187] The server analyzes this data using a generative AI model to assess the user's learning habits and comprehension. For example, if a user frequently makes mistakes on a particular type of question, the server will focus on questions in that area.

[1188] 6. Next problem generation

[1189] Based on the analysis results, the server adjusts the content and difficulty of the next question, allowing users to always solve questions at the optimal level.

[1190] The new questions generated are sent to the terminal again, and the next learning cycle begins.

[1191] Introducing the Emotion Engine

[1192] 1. Emotion recognition

[1193] When a user uses the device to answer questions, the device uses a camera and microphone to capture the user's facial expressions and tone of voice.

[1194] The device uses an emotion recognition engine to determine the user's emotional state from the captured data, which can include happiness, sadness, stress, excitement, etc.

[1195] 2. Transmission and analysis of emotional data

[1196] The device transmits the recognized emotion data to the server.

[1197] The server analyzes this emotional data and adjusts the difficulty and content of the questions based on the user's current emotional state, and also optimizes the form and content of the feedback to suit the user's emotions.

[1198] 3. Emotion-based problem generation and feedback

[1199] The server generates new problems taking into account the emotional data. For example, if the user is feeling stressed, it may lower the difficulty level or provide feedback including encouraging messages.

[1200] This information is also sent to the terminal, and the user's next learning cycle is initiated in an emotionally sensitive manner.

[1201] Specific examples

[1202] Consider the case where User B logs into the system and begins a normal learning session.

[1203] 1. User B's initial settings

[1204] User B sets his / her learning goal and current level. For example, User B wants to move from beginner to intermediate level.

[1205] The server uses this information to generate an appropriate initial problem set.

[1206] 2. User B's learning process

[1207] The question asks, "Choose the meaning of 'serene': a) noisy, b) quiet, c) pleasant."

[1208] User B selects "b) Quiet."

[1209] The server receives User B's answer, determines that it is correct, and provides feedback saying, "That's correct. 'serene' means 'quiet'."

[1210] At the same time, the device captures User B's facial expression and uses an emotion recognition engine to determine that he or she is under low stress.

[1211] 3. The next problem occurs

[1212] Since User B is not feeling stressed, the server generates a slightly more difficult question: "Choose the meaning of 'melancholy': a) enthusiastic, b) depressed, c) lively."

[1213] A new question is sent to the terminal and User B continues learning.

[1214] By repeating this process, users can obtain a learning experience that is optimized for their level of understanding and emotional state. This system supports efficient and effective learning and keeps users motivated to learn.

[1215] The processing flow will be explained below.

[1216] Step 1:

[1217] Initial Setup

[1218] The server loads a dataset of domain-related words, terms, meanings, and usage, including dictionary data, example sentence data, and past user learning data.

[1219] Step 2:

[1220] User Login

[1221] The user logs in by entering their user ID and password from the terminal. The terminal sends this authentication information to the server.

[1222] Step 3:

[1223] certification

[1224] The server compares the received authentication information with the user data in the database to authenticate the user. If authentication is successful, the server retrieves the user's learning history from the database.

[1225] Step 4:

[1226] Assessment of understanding

[1227] The server evaluates the user's current level of understanding based on the acquired learning history, including past correct answer rates and trends in questions that were incorrectly answered.

[1228] Step 5:

[1229] Preparing the emotion recognition engine

[1230] The device prepares a camera and microphone to capture the user's facial expressions and tone of voice, thereby collecting emotional data in real time.

[1231] Step 6:

[1232] First problem generation

[1233] The server uses a generative AI model to generate questions tailored to the user's level of understanding. For example, an intermediate-level user might be asked, "Choose the meaning of 'abate'."

[1234] Step 7:

[1235] Submit an issue

[1236] The server sends the generated questions to the terminal, where the user can check the questions.

[1237] Step 8:

[1238] Enter your answer

[1239] The user uses the device to input answers to the questions. When inputting the answers, the device captures the user's facial expressions and voice and sends them to the emotion engine.

[1240] Step 9:

[1241] emotion recognition

[1242] The device uses an emotion engine to analyze the user's emotional state, for example, to determine whether the user is stressed or focused.

[1243] Step 10:

[1244] Submit your answer

[1245] The terminal transmits the user's answers and emotion data to the server.

[1246] Step 11:

[1247] Judging the answer

[1248] The server evaluates the received answer and checks whether it is correct or not. For example, "If you chose 'abate' as meaning 'to decrease,' check whether this is the correct answer."

[1249] Step 12:

[1250] Feedback Generation

[1251] The server generates feedback based on the answer, taking into account sentiment data and including encouraging messages such as "Correct! 'abate' means 'decrease'. You're doing great!"

[1252] Step 13:

[1253] Send Feedback

[1254] The server sends the feedback to the terminal, which displays the feedback to the user.

[1255] Step 14:

[1256] Data storage

[1257] The server stores the answer results and emotional data in a database, including correct / incorrect answers, answer time, question difficulty, emotional state, etc.

[1258] Step 15:

[1259] Analyzing the data

[1260] The server analyzes the saved answer results and emotional data using a generative AI model to evaluate the user's answering tendencies, strengths and weaknesses, and emotional tendencies.

[1261] Step 16:

[1262] Next problem generation

[1263] Based on the analysis results, the server adjusts the content and difficulty of the next question, taking into account emotional data, for example, by presenting easier questions if the user is tired.

[1264] Step 17:

[1265] Submit a new issue

[1266] The server sends the newly generated problem to the device, and the user attempts the next problem, and the process is repeated.

[1267] Example 2

[1268] 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."

[1269] Conventional learning systems have limited ability to generate questions that correspond to the user's level of understanding, making it difficult to adapt to each user's individual learning progress and emotional state. Furthermore, because they only consider the user's learning history, it is difficult to maintain motivation during learning. Furthermore, feedback on answer results is one-dimensional, which does not fully address individual learning needs. Therefore, to maximize the user's learning effectiveness, it is essential to dynamically generate questions and provide feedback that are optimized according to the user's level of understanding and emotional state.

[1270] 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.

[1271] In this invention, the server includes means for performing user initial settings, means for authenticating the user and acquiring the user's learning history, means for generating questions according to the user's level of understanding, means for inputting answers, means for judging the answer results and providing feedback, means for saving and analyzing the answer results and generating the next question, means for acquiring and analyzing the user's emotional data, and means for adjusting the difficulty of questions and feedback based on the user's emotional state. This makes it possible to always provide an optimal learning experience by taking into account the user's level of understanding and emotional state.

[1272] The "means for performing user initial settings" is a means for collecting basic information such as the user's learning objectives, current level, and learning history, and for performing the initial settings of the system.

[1273] The "means for authenticating a user and acquiring a learning history" refers to the means for verifying the login information entered when a user logs into the system and acquiring the user's past learning history from the database.

[1274] "Means for generating questions according to the user's level of understanding" refers to a means for dynamically generating the optimal question to be asked next using a generative AI model based on the user's learning history and latest answer results.

[1275] The "means for inputting an answer" is a means by which a user inputs an answer to a presented question and transmits the answer to the system.

[1276] The "means for determining the answer result and providing feedback" refers to the means by which the server determines the answer submitted by the user and provides feedback based on the result. This feedback includes determining whether the answer is correct or incorrect and providing learning resources.

[1277] The "means for saving and analyzing the answer results and generating the next question" is a means for saving the user's answer results in a database and analyzing them to generate the next optimal question.

[1278] The "means for acquiring and analyzing user emotional data" refers to a means for capturing the user's facial expressions and voice data using the device's camera and microphone, and analyzing the user's emotional state using an emotion recognition engine.

[1279] "Means for adjusting the difficulty of questions and feedback based on the user's emotional state" refers to means for dynamically adjusting the difficulty of questions and the content of feedback based on analyzed emotional data to suit the user's current emotional state.

[1280] This invention relates to a system that automatically generates questions according to the user's level of understanding, analyzes the answers to provide the next most appropriate questions, and recognizes the user's emotions to optimize the learning experience. This system operates in cooperation with a server, terminal, user, and emotion engine.

[1281] The outline of the system is as follows:

[1282] Initial Setup

[1283] When a user registers or logs in, the server collects basic information about the user and performs initial setup. This includes the user's learning goals, current level, learning history, etc. Specifically, the user sets their learning goals and current level. Based on this information, the server generates an appropriate initial problem set and stores it in the database. For example, User A wishes to "move from beginner to intermediate level English," and sets the basic information required for this.

[1284] User authentication and data acquisition

[1285] A user logs in to the system using a terminal. The login information is sent from the terminal to the server, and the server authenticates the user by comparing it with information in the database. If authentication is successful, the server retrieves the user's past learning history from the database and evaluates their current level of understanding based on that data. For example, User B logs in and their past learning data is retrieved.

[1286] problem generation

[1287] The server uses a generative AI model to generate the next question based on the user's level of understanding. The questions are optimized by taking into account the user's past answers and current level of understanding. For example, the server generates a question for User B: "Please choose the meaning of 'serene': a) noisy, b) quiet, c) comfortable."

[1288] Answer input and result feedback

[1289] The user answers questions via the terminal. The terminal sends the user's answers to the server. The server evaluates the received answers and provides feedback to the user on whether they are correct or incorrect. Specific feedback may include explanations of correct or incorrect answers and additional learning resources. For example, if user B selects "b) quiet," the server provides the following feedback: "That's correct. 'serene' means 'quiet.'"

[1290] Data accumulation and analysis

[1291] The server stores the answers in a database. The stored data includes correct and incorrect answers, the time it took to answer, and the difficulty of the questions. The server analyzes this data using a generative AI model to evaluate the user's learning habits and comprehension. For example, if a user frequently makes mistakes on a certain type of question, the server will focus on questions in that area.

[1292] Next problem generation

[1293] Based on the analysis results, the server readjusts the content and difficulty of the next question. This allows the user to always solve questions at the optimal level. The new questions generated are sent back to the device, and the next learning cycle begins. For example, if it is analyzed that User B is not feeling stressed, a question with a slightly higher level of difficulty is generated.

[1294] Introducing the Emotion Engine

[1295] When a user answers questions using the device, the device uses a camera and microphone to capture the user's facial expressions and tone of voice. The device then uses an emotion recognition engine to determine the user's emotional state from the captured data, which can include happiness, sadness, stress, and excitement. The recognized emotional data is sent to a server, which analyzes the emotional data and adjusts the difficulty and content of the questions based on the user's current emotional state. The form and content of the feedback is also optimized to match the user's emotions.

[1296] Specific examples

[1297] Consider the case where User B logs in to the system and begins a normal learning session. User B's initial setting is to set his / her learning goal as "Beginner to intermediate level English." The server generates an initial set of questions based on this information. For example, User B is presented with a question asking, "What is the meaning of 'serene'? a) noisy, b) quiet, c) comfortable." User B selects "b) quiet," and the server provides feedback saying, "That's correct. 'serene' means 'quiet.'" At the same time, the device captures User B's facial expression and determines that he / she is under low stress using an emotion recognition engine. Next, the server generates a slightly more difficult question, asking, "What is the meaning of 'melancholy'? a) enthusiastic, b) depressed, c) lively."

[1298] By repeating this process, users can obtain a learning experience that is optimized for their level of understanding and emotional state. This system supports efficient and effective learning and keeps users motivated to learn.

[1299] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1300] Step 1:

[1301] A new user registration or login is performed. The user uses a terminal to enter their ID and password or new registration information. The entered information is sent from the terminal to the server.

[1302] Input: User ID, password, new registration information

[1303] Output: Authentication information sent to the server

[1304] Specific operation: User A enters the necessary information into the new registration form on the device and presses the send button. The device then sends the entered information to the server.

[1305] Step 2:

[1306] The server authenticates the user by comparing login information and new registration information with information in the database. If authentication is successful, the server obtains the user's past learning history.

[1307] Input: The authentication information sent to the server

[1308] Output: Authentication results, learning history data

[1309] Specific operation: The server authenticates User A by checking against the database, and after successful authentication, retrieves User A's past learning history from the database.

[1310] Step 3:

[1311] The server performs initial setup based on the user's basic information, including the user's learning goals, current level, and learning history.

[1312] Input: Learning objectives, current level, learning history

[1313] Output: Initial setup data, initial problem set

[1314] Specific operation: User A sets "I want to move from beginner to intermediate level English," and the server generates an initial set of questions based on that information.

[1315] Step 4:

[1316] The server generates the next question based on the user's level of understanding, using a generative AI model to consider the user's past answers and current level of understanding to create the most appropriate question.

[1317] Input: User's comprehension data, answer results

[1318] Output: Next problem data

[1319] Specific operation: The server uses the generative AI model to generate a question for User B: "Please choose the meaning of 'serene': a) noisy, b) quiet, c) comfortable."

[1320] Step 5:

[1321] The user answers questions via the terminal and sends the answers, which are then sent to the server.

[1322] Input: User's answer data

[1323] Output: Answer data sent to the server

[1324] Specific operation: User B selects "b) Quiet" and the device sends the user's answer to the server.

[1325] Step 6:

[1326] The server evaluates the received answers and provides feedback to the user, including explanations of correct and incorrect answers and additional learning resources.

[1327] Input: User's answer data

[1328] Output: Feedback data

[1329] Specific behavior: The server judges the answer and provides feedback such as "Correct. 'serene' means 'quiet'."

[1330] Step 7:

[1331] The server stores the answer results in a database. The stored data includes correct answers, answer time, difficulty level of the question, etc. The server analyzes this data using a generative AI model.

[1332] Input: Answer result data

[1333] Output: Analysis data, storage data

[1334] Specific operation: The server stores User B's answer data in a database and analyzes it using a generative AI model.

[1335] Step 8:

[1336] The server then adjusts the content and difficulty of the next question based on the analysis results, and the new question is then sent back to the device.

[1337] Input: Analysis data

[1338] Output: Rescaled problem data

[1339] Specific operation: The server analyzes that User B is not feeling stressed, generates the next question "Please choose the meaning of 'melancholy': a) enthusiastic, b) depressed, c) lively" and sends it to the terminal.

[1340] Step 9:

[1341] The device uses a camera and microphone to capture the user's facial expressions and tone of voice, and an emotion recognition engine to determine the user's emotional state.

[1342] Input: facial expression data, voice data

[1343] Output: Emotion data

[1344] Specific operation: When User B answers the question, the device captures facial expression data and the emotion recognition engine determines that the user is under low stress.

[1345] Step 10:

[1346] The emotion recognition results are sent to a server, which analyzes the emotion data and adjusts the difficulty of the questions and feedback based on the user's current emotional state.

[1347] Input: Emotion data

[1348] Output: Adjusted problem data, feedback data

[1349] How it works: The device sends emotional data to the server, and the server adjusts the difficulty of the next question and feedback based on the emotional state.

[1350] (Application example 2)

[1351] 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."

[1352] Conventional learning management systems and task management systems for factory robots do not dynamically adjust tasks according to the user's or robot's level of understanding or workload, making efficient learning and work execution difficult. This has led to problems such as a decline in the user's motivation to learn and robot overload. Furthermore, these systems were unable to recognize and reflect emotions or workload conditions, preventing optimal feedback and task generation.

[1353] 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.

[1354] In this invention, the server includes means for performing user initial settings, means for authenticating the user and acquiring the user's learning history, means for generating questions according to the user's level of understanding, means for inputting answers, means for judging the answer results and providing feedback, means for saving and analyzing the answer results and generating the next question, means for the robot to learn a new task, means for adjusting the difficulty of the next task based on the task results, and means for recognizing the robot's load state and optimizing task execution efficiency. This enables efficient learning while increasing the user's motivation to learn, and enables optimal task execution while preventing the robot from being overloaded.

[1355] "User initial settings" refers to the process of collecting and setting basic information about a user's learning goals, current level, and learning history when the user registers or logs in.

[1356] "User authentication" is the process of verifying the user's identity when the user logs in to a system by sending the entered information to a server and comparing it with information in a database.

[1357] "Means for obtaining learning history" refers to the process by which the server reads past learning data from the database and uses it to evaluate the user's current level of understanding.

[1358] "Means for generating questions according to the user's level of understanding" refers to the process of using a generative AI model to create the optimal question to be asked next, based on the user's past answers and current level of understanding.

[1359] "Means for inputting answers" refers to the process in which a user inputs an answer to a question and the answer is sent to the server.

[1360] The "means for determining the answer result and providing feedback" is the process by which the server determines the received answer and provides the user with feedback on whether it is correct or not, as well as learning resources.

[1361] "Means for saving and analyzing the answer results and generating the next question" refers to the process in which the server saves the answer results in a database, analyzes them to evaluate the user's learning tendencies and level of understanding, and readjusts the content and difficulty of the next question to be asked.

[1362] "Means for robots to learn new tasks" refers to the process by which factory robots efficiently learn new jobs or tasks.

[1363] The "means for adjusting the difficulty of the next task based on the results of the task" is a process for dynamically adjusting the difficulty of the next task based on the results of the robot's task execution.

[1364] "Means for recognizing the load state of the robot and optimizing the efficiency of task execution" refers to a process for recognizing the load state of the robot and adjusting the difficulty and order of tasks to enable optimal task execution while preventing overload.

[1365] This invention is a system for maximizing the learning and working efficiency of users and robots, and is composed of a server, a terminal, a user, a robot, and an emotion engine. The system is specifically implemented as follows.

[1366] System Overview

[1367] Initial Setup

[1368] When a user performs initial setup, the server collects basic information about the user's learning goals, current level, and learning history. Based on this information, the server provides optimal initial setup for each user. The server also collects work goals and current task data for factory robots and performs initial setup.

[1369] User authentication and data acquisition

[1370] A user logs in to the system using a terminal. The login information is sent to the server, which then authenticates the user by comparing it with information in the database. If authentication is successful, the server retrieves the user's past learning history from the database and evaluates their current level of understanding.

[1371] problem generation

[1372] The server uses a generative AI model to create the next question based on the user's level of understanding. The questions are optimized by taking into account the user's past answers and current level of understanding. Similarly, the server analyzes the results of tasks for factory robots and generates the optimal next task to be performed.

[1373] Answer input and result feedback

[1374] Users answer questions via their device. The answers are sent from the device to the server, which evaluates them and provides feedback on whether the answer was correct or incorrect. Specific feedback may include explanations of correct or incorrect answers and additional learning resources. For robots, the server receives the results of the tasks performed, determines whether the robot was successful, and adjusts the difficulty of the next task based on the results.

[1375] Data accumulation and analysis

[1376] The server stores the answers and task execution results in a database. The stored data includes correct / incorrect answers, the time it took to answer, the difficulty of the question, the success / failure of the task, and the execution time. The server analyzes this data using a generative AI model to evaluate the user's learning tendency and level of understanding, as well as the robot's work efficiency.

[1377] Next problem generation

[1378] The server then adjusts the content and difficulty of the next question based on the analysis results, allowing users to always solve questions at the optimal level. The server also generates and suggests optimal tasks for the robot based on the analysis results.

[1379] Introducing the Emotion Engine

[1380] emotion recognition

[1381] When a user answers questions using the device, the device uses a camera and microphone to capture the user's facial expressions and tone of voice. An emotion recognition engine is used to determine the user's emotional state from the captured data. For robots, the emotional state (load state) is recognized based on the workload of performing the task.

[1382] Sending and analyzing emotional data

[1383] The device sends the recognized emotional data to a server, which analyzes the data and adjusts the difficulty and content of the questions and tasks based on the user's current emotional state and the robot's workload. The server also optimizes the form and content of feedback to match the user's emotional state.

[1384] Emotion-based problem generation and feedback

[1385] The server generates new problems and tasks taking into account the emotional data. For example, if the user is feeling stressed, it will lower the difficulty level slightly or provide feedback including an encouraging message. Also, if the robot is overloaded, it will reduce the difficulty of the next task. This information is sent to the terminal or robot, and the next cycle will begin taking into account the user's emotions and stress state.

[1386] Specific examples

[1387] Consider a case where a user logs in to the system and begins a learning session. For example, a question might appear: "Please choose the meaning of 'serene': a) noisy, b) quiet, c) comfortable." If the user selects "b) quiet," the server determines that this is the correct answer and provides feedback such as, "You're correct. 'serene' means 'quiet.'" The device simultaneously captures the user's facial expression and uses an emotion recognition engine to determine that the user is under stress. Also, if a factory robot performs a task called "assembly" and succeeds, the server suggests the slightly more difficult "inspection" task as the next task.

[1388] Prompt Sentence Examples

[1389] "The robot has succeeded five times and failed three times in the 'Inspect' task. What type and difficulty of task should it suggest next?"

[1390] "The user answered the 'serene' question correctly. Please generate a related vocabulary question for them to answer next."

[1391] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1392] Step 1:

[1393] The server provides the terminal with a screen for the user to perform initial setup. The user inputs information such as their learning objectives, current level, learning history, etc. The input data is sent to the server, which then stores the information in a database.

[1394] Step 2:

[1395] A user logs into the system using a terminal. The login information (user ID, password, etc.) is sent from the terminal to the server, which then authenticates the user by comparing it with information in the database. If authentication is successful, the server retrieves the user's past learning history from the database and sends that information to the terminal for display.

[1396] Step 3:

[1397] The server uses a generative AI model to generate questions based on the user's level of understanding. The generative AI model uses the user's past answers and current level of understanding as input data and outputs the optimal question to be posed next. This question is sent from the server to the device and displayed to the user.

[1398] Step 4:

[1399] The user answers the questions displayed via the terminal. The answer data is sent from the terminal to the server, and the server receives the answer data. The server compares the answer data with the correct answer data and determines whether the answer was correct or incorrect.

[1400] Step 5:

[1401] The server evaluates the answer and provides the result as feedback to the user. The feedback may include explanations of correct and incorrect answers and additional learning resources. The feedback data is sent from the server to the device and displayed to the user.

[1402] Step 6:

[1403] The server stores the answer results in a database. The stored data includes correct and incorrect answers, the time it took to answer, and the difficulty of the questions. This data serves as the basis for subsequent data analysis and question generation.

[1404] Step 7:

[1405] The server uses the stored data to analyze the user's learning habits and level of understanding using a generative AI model, and the analysis data is used to adjust the content and difficulty of the next questions.

[1406] Step 8:

[1407] The server then sends the newly generated questions to the device, and the next learning cycle begins, ensuring that the user is always challenged with questions of appropriate difficulty.

[1408] Step 9:

[1409] When a robot learns a new task, the server receives the robot's task settings and result data input via the terminal, and saves the robot's work history and current load status as data.

[1410] Step 10:

[1411] The server receives the results of the robot's tasks and analyzes the data on success and failure. Based on the analysis results, the data is processed to adjust the difficulty of the next task, and a new task is generated using the generative AI model. This data is then sent to the robot or the operator's device.

[1412] Step 11:

[1413] The emotion engine recognizes the robot's load state and adjusts to reduce the difficulty of the task if it is overloaded. The server generates feedback based on this situation and sends the feedback data to the robot and the operator's device.

[1414] Prompt Sentence Examples

[1415] "The robot has succeeded five times and failed three times in the 'Inspect' task. What type and difficulty of task should it suggest next?"

[1416] "The user answered the 'serene' question correctly. Please generate a related vocabulary question for them to answer next."

[1417] 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.

[1418] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1419] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1420] [Fourth embodiment]

[1421] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1422] 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.

[1423] 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).

[1424] 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.

[1425] 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.

[1426] 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).

[1427] 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.

[1428] 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.

[1429] 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.

[1430] 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.

[1431] 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.

[1432] 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.

[1433] 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."

[1434] This invention relates to a system that automatically generates questions according to the user's level of understanding, analyzes the answers, and provides the next most appropriate questions. This system operates in cooperation with a server, terminals, and users.

[1435] System Overview

[1436] 1. Initial Setup

[1437] When a user registers or logs in, the server collects basic information about the user and sets up the initial settings, including the user's learning goals, current level, and learning history.

[1438] 2. User authentication and data acquisition

[1439] A user logs into the system using a terminal, and the login information is sent from the terminal to the server, which then authenticates the user by checking it against information in a database.

[1440] If authentication is successful, the server retrieves the user's past learning history from a database and evaluates their current level of understanding based on that data.

[1441] 3. Problem generation

[1442] The server uses a generative AI model to create the next question based on the user's level of understanding. The questions are optimized taking into account the user's past answers and current level of understanding.

[1443] 4. Answer input and result feedback

[1444] The user answers questions via the terminal, and the user's answers are sent to the server.

[1445] The server evaluates the received answers and provides feedback to the user, which may include explanations of correct and incorrect answers and additional learning resources.

[1446] 5. Data accumulation and analysis

[1447] The server stores the answer results in a database, including whether the answer was correct, the time it took to answer, and the difficulty of the question.

[1448] The server analyzes this data using a generative AI model to assess the user's learning habits and comprehension. For example, if a user frequently makes mistakes on a particular type of question, the server will focus on questions in that area.

[1449] 6. Next problem generation

[1450] Based on the analysis results, the server adjusts the content and difficulty of the next question, allowing users to always solve questions at the optimal level.

[1451] The new questions generated are sent to the terminal again, and the next learning cycle begins.

[1452] Specific examples

[1453] Consider the case where User A logs into the system and begins his or her first learning session.

[1454] 1. User A's initial settings

[1455] User A sets his / her learning goal and current level (e.g., intermediate).

[1456] The server uses this information to generate an appropriate initial problem set.

[1457] 2. User A's learning process

[1458] The question is "Choose the meaning of 'abate': a) increase, b) decrease, c) maintain."

[1459] User A selects "b) Decrease."

[1460] The server receives User A's answer, determines that it is correct, and provides feedback saying, "That's correct. 'abate' means 'decrease'."

[1461] The results are stored in a database, and the server uses this information to generate the next question.

[1462] 3. Generate the next question for User A

[1463] The server evaluates user A's understanding and then generates the question "Choose the meaning of 'nuance': a) subtle, b) direct, c) obvious."

[1464] This new question is sent to the terminal, and User A continues learning.

[1465] By repeating this process, users can obtain a learning experience that is optimized for their level of understanding. This system supports efficient and effective learning, helping users achieve their goals in a short period of time.

[1466] The processing flow will be explained below.

[1467] Step 1:

[1468] Initial Setup

[1469] The server loads a dataset of domain-related words, terms, meanings, and usage, including dictionary data, example sentence data, and past user learning data.

[1470] Step 2:

[1471] User Authentication

[1472] A user accesses the system from a terminal and logs in by entering a user ID and password. The terminal sends this authentication information to the server.

[1473] Step 3:

[1474] Authentication Results

[1475] The server compares the received authentication information with the user data in the database and performs authentication. If authentication is successful, the server retrieves the user's learning history from the database.

[1476] Step 4:

[1477] Assessment of understanding

[1478] The server evaluates the user's current level of understanding based on the acquired learning history, including past correct answer rates and trends in questions that were incorrectly answered.

[1479] Step 5:

[1480] First problem generation

[1481] The server uses a generative AI model to generate questions tailored to the user's level of understanding. For example, an intermediate-level user might be asked, "Choose the meaning of 'abate'."

[1482] Step 6:

[1483] Submit an issue

[1484] The server sends the generated questions to the terminal, where the user can check the questions.

[1485] Step 7:

[1486] Enter your answer

[1487] The user enters answers to questions using a terminal, and the answers are sent from the terminal to the server.

[1488] Step 8:

[1489] Judging the answer

[1490] The server evaluates the received answer and determines whether it is correct or incorrect. For example, "If you chose 'abate' as meaning 'to decrease,' check if this is correct."

[1491] Step 9:

[1492] feedback

[1493] The server generates feedback based on the answer, for example, "Your answer is correct. 'abate' means 'decrease'," and sends it to the device.

[1494] Step 10:

[1495] Data storage

[1496] The server stores the answer results in a database, which records correct and incorrect answers, answer time, and question difficulty.

[1497] Step 11:

[1498] Analyzing the data

[1499] The server analyzes the stored data using a generative AI model to evaluate the user's answering tendencies and strengths and weaknesses.

[1500] Step 12:

[1501] Next problem generation

[1502] Based on the analysis results, the server uses the generative AI model to create the next appropriate question, thereby continuously providing questions that are appropriate for the level.

[1503] Step 13:

[1504] Submit a new issue

[1505] The server sends the newly generated problem to the device, and the user attempts the next problem, and the process is repeated.

[1506] Example 1

[1507] 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."

[1508] Current educational systems lack the ability to provide questions that are individually optimized for a user's level of understanding. This reduces the user's learning efficiency and makes effective learning difficult. Furthermore, continuous feedback and learning history management are insufficient, and it is often difficult to properly set the next learning step based on the user's level of understanding. This can reduce learning effectiveness and cause the learning process to stagnate.

[1509] 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.

[1510] In this invention, the server includes a means for performing user initial settings, a means for authenticating the user and acquiring their learning history, a means for using a generative AI model to generate questions according to the user's level of understanding, a means for judging the answer results and providing feedback, and a means for saving and analyzing the answer results and generating the next question. This makes it possible to generate optimal questions and provide feedback according to the user's level of understanding, thereby improving learning effectiveness.

[1511] "User" refers to an individual or group that uses the system to study.

[1512] "Initial settings" refers to the information input and setup process that users go through when they start using the system, including the user's basic information, learning objectives, current level, etc.

[1513] "Authentication" is the process by which a server verifies a user's information and authorizes access rights when a user logs into a system.

[1514] "Study history" is a collection of data such as records of the user's past studies, grades, answer history, etc.

[1515] "Level of understanding" is an index that indicates how much a user understands a particular learning content.

[1516] A "question" is one of the quizzes or assignments provided by the system to assess and improve the user's understanding.

[1517] A "generative AI model" is an algorithm that uses machine learning to generate questions based on the user's level of understanding.

[1518] An "answer" is a response provided by a user to a question posed by the system.

[1519] "Feedback" refers to the system's response to the user's answer, such as evaluation or explanation.

[1520] "Saving" refers to the act of recording data such as the user's learning history and answer results in a database.

[1521] "Analysis" is the process of using stored data to evaluate a user's learning trends and comprehension.

[1522] This invention is a system that automatically generates questions according to the user's level of understanding, analyzes the answers, and provides the next most appropriate questions. This system operates in cooperation with the server, terminals, and users.

[1523] System Overview

[1524] Initial Setup

[1525] The server collects basic information about the user when the user registers or logs in. This information includes the user's learning goals, current level, and learning history, and is saved in a database. The server completes the initial setup when the user sets their learning goals and current level (e.g., intermediate).

[1526] User authentication and data acquisition

[1527] A user logs into the system using a terminal. The login information is sent from the terminal to the server using SSL / TLS. The server authenticates the user by checking it against information in a database, and if authentication is successful, it retrieves the user's past learning history and evaluates their current level of understanding.

[1528] problem generation

[1529] The server uses a generative AI model (e.g., GPT-4) to generate questions based on the user's level of understanding. The server optimizes the next question to be presented, taking into account the user's past answers and current level of understanding.

[1530] For example, the following prompt can be used:

[1531] "A user is learning intermediate level English vocabulary. Please generate the following questions for him. Based on his previous answers and statistics, he makes a lot of mistakes in the 'choose meaning' format. Please create a question containing the word 'nuance'. The format is as follows:

[1532] Choose the meaning of 'nuance': a) subtle, b) direct, c) obvious."

[1533] Answer input and result feedback

[1534] Users answer questions via their devices. The answers are immediately sent from the device to the server, which evaluates the answers. The server then provides feedback to the user, including explanations of correct and incorrect answers and additional learning resources as needed.

[1535] Data accumulation and analysis

[1536] The server stores all answer results in a database. This stored data includes whether the answer was correct, the time it took to complete the answer, and the difficulty of the question. The server analyzes this data using a generative AI model to evaluate the user's learning tendency and level of understanding.

[1537] Next problem generation

[1538] Based on the analysis results, the server adjusts the content and difficulty of the next questions. The generated questions are then sent back to the device to start the user's next learning cycle, providing a continuously optimized learning experience.

[1539] Specific examples

[1540] Below is an example of User A logging into the system for the first time and starting a learning session.

[1541] 1. Initial Setup

[1542] User A enters his / her learning objectives and current level (e.g., intermediate) in the application and presses the submit button. The server receives the input information and saves it in the database.

[1543] 2. Learning Process

[1544] User A enters his / her username and password on the login screen and clicks the login button.

[1545] The device sends login information to the server, which then authenticates it. After successful authentication, the learning history is acquired.

[1546] The server sends the generated AI model a prompt: "Please choose the meaning of 'abate': a) increase, b) decrease, c) maintain," and sends the generated problem to the device.

[1547] User A selects "b) Decrease."

[1548] The device sends this answer to the server, which judges the answer and provides feedback.

[1549] By repeating this process, users can always get the best learning experience. The system supports efficient and effective learning, helping users achieve their goals.

[1550] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1551] Step 1:

[1552] Initial Setup

[1553] A user accesses the new registration or login screen using a device. The user enters basic information such as name, email address, learning objectives, and current level, and clicks the submit button. The device sends the input data to the server. The server stores the received data in a database and completes the initial setup.

[1554] Input: User enters and submits basic information

[1555] Output: Save basic information to the database

[1556] Step 2:

[1557] User authentication and data acquisition

[1558] To log in using a terminal, a user enters a username and password and presses the login button. The terminal encrypts this authentication information using the SSL / TLS protocol and sends it to the server. The server performs authentication by comparing it with information in a database. If authentication is successful, the server retrieves past learning history from the database and evaluates the user's current level of understanding based on that data.

[1559] Input: User enters and submits login information

[1560] Output: Acquisition of learning history from the database and evaluation of comprehension

[1561] Step 3:

[1562] problem generation

[1563] The server uses a generative AI model (e.g., GPT-4) to create the next question to be posed based on the user's level of understanding. The server creates a prompt sentence taking into account the user's past answers and current level of understanding, and sends it to the generative AI model. The generated question is then sent from the server to the device.

[1564] Input: User's learning history and comprehension

[1565] Output: Generated issues sent to terminal

[1566] For example, "A user is learning intermediate level English vocabulary. Please generate the following questions for him. Based on his previous answers and statistical data, he makes a lot of mistakes in the 'choose meaning' format. Please create a question containing the word 'nuance'. The format is as follows:

[1567] Please choose the meaning of 'nuance': a) subtle, b) direct, c) obvious."

[1568] Step 4:

[1569] Answer input and result feedback

[1570] The user answers questions via the device. The user's answers are sent from the device to the server. The server evaluates the received answers and generates a correct / incorrect result. It also generates feedback including explanations of correct / incorrect answers and additional learning resources and sends it to the device.

[1571] Input: User's answer

[1572] Output: Generate feedback and send it to the device

[1573] Step 5:

[1574] Data accumulation and analysis

[1575] The server stores all answer results in a database. This stored data includes whether the answer was correct or incorrect, the time it took to complete the answer, and the difficulty of the question. Using a generative AI model, the server analyzes this data and evaluates the user's learning tendency and level of understanding.

[1576] Input: User's answer result

[1577] Output: Evaluation of learning tendency and comprehension

[1578] Step 6:

[1579] Next problem generation

[1580] The server then adjusts the content and difficulty of the next questions based on the analysis results. The generated questions are then sent back to the user's device, and the user's next learning cycle begins. This allows the user to always tackle questions at the optimal level.

[1581] Input: Analysis results

[1582] Output: Generate the next problem and send it to the terminal

[1583] This allows users to have a continuously optimized learning experience and progress effectively with their studies.

[1584] (Application example 1)

[1585] 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."

[1586] Conventional systems have limitations in their ability to provide optimal questions based on the user's level of understanding, making efficient learning difficult. Furthermore, they lack the ability to evaluate users' learning tendencies in detail, making it impossible to provide optimal learning programs for individual users. Under these circumstances, there is a need to improve the efficiency of employee training, especially in brick-and-mortar stores, but achieving this is difficult.

[1587] 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.

[1588] In this invention, the server includes means for performing user initial settings, means for authenticating the user and acquiring the user's learning history, means for generating questions according to the user's level of understanding, means for inputting answers, means for judging the answer results and providing feedback, means for saving and analyzing the answer results and generating the next question, means for evaluating the user's learning tendency, and means for generating a prompt sentence for generating the next most appropriate question. This makes it possible to provide questions optimized for each user's individual level of understanding and to progress with subsequent learning, thereby realizing more efficient employee training, particularly in physical stores.

[1589] The "means for initial user settings" is a means for collecting basic information about the user, their learning goals, and their current level, and registering them in the system.

[1590] The "means for authenticating a user and acquiring a learning history" refers to a means for authenticating a user based on the information provided by the user when logging in, and acquiring the user's past learning history from a database.

[1591] "Means for generating questions according to the user's level of understanding" refers to a means for creating appropriate questions using a generative AI model based on the user's learning history and answer results.

[1592] "Means for inputting answers" refers to the means by which a user inputs answers to questions into the system.

[1593] The "means for determining the answer result and providing feedback" is a means for analyzing the answer entered by the user, determining whether it is correct or incorrect, and providing the user with feedback based on the result.

[1594] The "means for saving and analyzing the answer results and generating the next question" is a means for saving the user's answer results in a database and analyzing them to generate the next question to be asked.

[1595] The "means for assessing the user's learning tendency" is a means for analyzing the collected data and assessing the user's strengths and weaknesses.

[1596] The "means for generating a prompt sentence for generating the next most suitable question" is a means for creating a prompt sentence for generating the next most suitable question to be asked based on the user's level of understanding and learning tendencies.

[1597] This invention is a system that automatically generates appropriate questions based on the user's level of understanding. This system operates with the cooperation of a server, terminals, and users.

[1598] 1. Initial Setup

[1599] When a user registers or logs in, the server collects basic information about the user and sets up the initial settings, including the user's learning goals, current level, learning history, etc. The server stores this information in a database and estimates the user's initial level.

[1600] 2. User authentication and data acquisition

[1601] Users log in to the system through their terminal. The login information is sent from the terminal to the server, and the server authenticates the user by comparing it with information in the database. If authentication is successful, the server retrieves the user's past learning history from the database and evaluates their current level of understanding based on that data.

[1602] 3. Problem generation

[1603] The server uses a generative AI model to automatically generate questions based on the user's level of understanding. It then generates prompts to optimize the questions, taking into account the user's past answers and current level of understanding. These prompts have the following format:

[1604] User level: Intermediate

[1605] User History: Completed training on past case management.

[1606] Next, generate the question to be asked:

[1607] 4. Answer input and result feedback

[1608] Users answer questions via their device. The answers are sent from the device to the server, which analyzes them to determine whether they are correct or incorrect and provides feedback. The feedback may include detailed explanations of correct and incorrect answers and additional learning resources.

[1609] 5. Data accumulation and analysis

[1610] The server stores the answers in a database. The stored data includes whether the answer was correct, the time it took to answer, and the difficulty of the question. The server analyzes this data using a generative AI model to evaluate the user's learning habits and comprehension. For example, if a user frequently makes mistakes on a certain type of question, the server will focus on that area.

[1611] 6. Next problem generation

[1612] The server then uses the results of the analysis to adjust the content and difficulty of the next questions, which are then sent back to the device, starting the next learning cycle.

[1613] Hardware and software used

[1614] Hardware: Servers, devices (smartphones, tablets, etc.)

[1615] Software: Databases (MySQL, PostgreSQL), generative AI models (OpenAI GPT-3), analysis tools (Scikit-learn)

[1616] Specific examples

[1617] For example, user A logs into the system and begins his first study session. If user A is initially set to "intermediate," the server generates the following questions:

[1618] "Choose the meaning of 'abate': a) to increase, b) to decrease, c) to maintain."

[1619] If User A selects "b) Decrease," the server determines this is the correct answer and provides the following feedback:

[1620] "That's correct. 'abate' means 'to decrease'."

[1621] The server then evaluates User A's understanding and generates the following questions:

[1622] "Choose the meaning of 'nuance': a) subtle, b) direct, c) obvious."

[1623] In this way, user A can always solve problems that are optimized for his or her level of understanding.

[1624] The above is a concrete implementation method of this system. This system can provide an individually optimized learning experience that takes into account the user's learning tendencies and level of understanding. It is expected to be particularly useful in improving the efficiency of employee training in brick-and-mortar stores.

[1625] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1626] Step 1: Initial Setup

[1627] A user uses a terminal to register or log in. At this time, the server collects the user's basic information (learning objectives, current level, learning history, etc.) and stores it in a database. The input is the user's basic information, and the output is the user information stored in the database. Based on this information, the server estimates the user's initial level.

[1628] Step 2: User authentication and data acquisition

[1629] When a user logs in via a terminal, the server receives authentication information. The server compares this information with information in a database to authenticate the user. The input is the user's login information, and the output is whether the authentication was successful. If the authentication is successful, the server retrieves the user's past learning history from the database and evaluates the user's current level of understanding.

[1630] Step 3: Problem generation

[1631] The server uses a generative AI model to generate questions based on the user's level of understanding. A prompt is generated, and the AI ​​model creates questions based on this. The input is the user's learning history, comprehension data, and the prompt, and the output is the generated question. Specifically, the prompt is sent to the generative AI model via an API.

[1632] Step 4: Answer entry and feedback

[1633] The user answers questions via a terminal. The input is the user's answer to the question, and the output is the answer result (correctness or incorrectness) and feedback. The server receives the answer from the terminal, analyzes it to determine whether it is correct or incorrect, and generates detailed feedback to provide to the user.

[1634] Step 5: Data collection and analysis

[1635] The server stores the user's answer results in a database. The input is the answer results (correct or incorrect, time taken to answer, difficulty of the question, etc.), and the output is the analysis data stored in the database. Using this, the server evaluates the user's learning tendency and level of understanding through a generative AI model.

[1636] Step 6: Generate the next problem

[1637] Based on the analysis results, the server readjusts the content and difficulty of the next question to be presented. The input is the analysis results and prompt text, and the output is the next question to be generated. Specifically, a prompt text is generated based on the analysis results, and this is provided to the generative AI model to generate a new question. The new question is then sent back to the device, and the user begins the next learning cycle.

[1638] 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.

[1639] This invention relates to a system that automatically generates questions according to the user's level of understanding, analyzes the answers to provide the next most appropriate questions, and recognizes the user's emotions to optimize the learning experience. This system operates in cooperation with a server, terminal, user, and emotion engine.

[1640] System Overview

[1641] 1. Initial Setup

[1642] When a user registers or logs in, the server collects basic information about the user and sets up the initial settings, including the user's learning goals, current level, and learning history.

[1643] 2. User authentication and data acquisition

[1644] A user logs into the system using a terminal, and the login information is sent from the terminal to the server, which then authenticates the user by checking it against information in a database.

[1645] If authentication is successful, the server retrieves the user's past learning history from a database and evaluates their current level of understanding based on that data.

[1646] 3. Problem generation

[1647] The server uses a generative AI model to create the next question based on the user's level of understanding. The questions are optimized taking into account the user's past answers and current level of understanding.

[1648] 4. Answer input and result feedback

[1649] The user answers questions via the terminal, and the user's answers are sent to the server.

[1650] The server evaluates the received answers and provides feedback to the user, which may include explanations of correct and incorrect answers and additional learning resources.

[1651] 5. Data accumulation and analysis

[1652] The server stores the answer results in a database, including correct and incorrect answers, the time it took to answer, and the difficulty of the questions.

[1653] The server analyzes this data using a generative AI model to assess the user's learning habits and comprehension. For example, if a user frequently makes mistakes on a particular type of question, the server will focus on questions in that area.

[1654] 6. Next problem generation

[1655] Based on the analysis results, the server adjusts the content and difficulty of the next question, allowing users to always solve questions at the optimal level.

[1656] The new questions generated are sent to the terminal again, and the next learning cycle begins.

[1657] Introducing the Emotion Engine

[1658] 1. Emotion recognition

[1659] When a user uses the device to answer questions, the device uses a camera and microphone to capture the user's facial expressions and tone of voice.

[1660] The device uses an emotion recognition engine to determine the user's emotional state from the captured data, which can include happiness, sadness, stress, excitement, etc.

[1661] 2. Transmission and analysis of emotional data

[1662] The device transmits the recognized emotion data to the server.

[1663] The server analyzes this emotional data and adjusts the difficulty and content of the questions based on the user's current emotional state, and also optimizes the form and content of the feedback to suit the user's emotions.

[1664] 3. Emotion-based problem generation and feedback

[1665] The server generates new problems taking into account the emotional data. For example, if the user is feeling stressed, it may lower the difficulty level or provide feedback including encouraging messages.

[1666] This information is also sent to the terminal, and the user's next learning cycle is initiated in an emotionally sensitive manner.

[1667] Specific examples

[1668] Consider the case where User B logs into the system and begins a normal learning session.

[1669] 1. User B's initial settings

[1670] User B sets his / her learning goal and current level. For example, User B wants to move from beginner to intermediate level.

[1671] The server uses this information to generate an appropriate initial problem set.

[1672] 2. User B's learning process

[1673] The question asks, "Choose the meaning of 'serene': a) noisy, b) quiet, c) pleasant."

[1674] User B selects "b) Quiet."

[1675] The server receives User B's answer, determines that it is correct, and provides feedback saying, "That's correct. 'serene' means 'quiet'."

[1676] At the same time, the device captures User B's facial expression and uses an emotion recognition engine to determine that he or she is under low stress.

[1677] 3. The next problem occurs

[1678] Since User B is not feeling stressed, the server generates a slightly more difficult question: "Choose the meaning of 'melancholy': a) enthusiastic, b) depressed, c) lively."

[1679] A new question is sent to the terminal and User B continues learning.

[1680] By repeating this process, users can obtain a learning experience that is optimized for their level of understanding and emotional state. This system supports efficient and effective learning and keeps users motivated to learn.

[1681] The processing flow will be explained below.

[1682] Step 1:

[1683] Initial Setup

[1684] The server loads a dataset of domain-related words, terms, meanings, and usage, including dictionary data, example sentence data, and past user learning data.

[1685] Step 2:

[1686] User Login

[1687] The user logs in by entering their user ID and password from the terminal. The terminal sends this authentication information to the server.

[1688] Step 3:

[1689] certification

[1690] The server compares the received authentication information with the user data in the database to authenticate the user. If authentication is successful, the server retrieves the user's learning history from the database.

[1691] Step 4:

[1692] Assessment of understanding

[1693] The server evaluates the user's current level of understanding based on the acquired learning history, including past correct answer rates and trends in questions that were incorrectly answered.

[1694] Step 5:

[1695] Preparing the emotion recognition engine

[1696] The device prepares a camera and microphone to capture the user's facial expressions and tone of voice, thereby collecting emotional data in real time.

[1697] Step 6:

[1698] First problem generation

[1699] The server uses a generative AI model to generate questions tailored to the user's level of understanding. For example, an intermediate-level user might be asked, "Choose the meaning of 'abate'."

[1700] Step 7:

[1701] Submit an issue

[1702] The server sends the generated questions to the terminal, where the user can check the questions.

[1703] Step 8:

[1704] Enter your answer

[1705] The user uses the device to input answers to the questions. When inputting the answers, the device captures the user's facial expressions and voice and sends them to the emotion engine.

[1706] Step 9:

[1707] emotion recognition

[1708] The device uses an emotion engine to analyze the user's emotional state, for example, to determine whether the user is stressed or focused.

[1709] Step 10:

[1710] Submit your answer

[1711] The terminal transmits the user's answers and emotion data to the server.

[1712] Step 11:

[1713] Judging the answer

[1714] The server evaluates the received answer and checks whether it is correct or not. For example, "If you chose 'abate' as meaning 'to decrease,' check whether this is the correct answer."

[1715] Step 12:

[1716] Feedback Generation

[1717] The server generates feedback based on the answer, taking into account sentiment data and including encouraging messages such as "Correct! 'abate' means 'decrease'. You're doing great!"

[1718] Step 13:

[1719] Send Feedback

[1720] The server sends the feedback to the terminal, which displays the feedback to the user.

[1721] Step 14:

[1722] Data storage

[1723] The server stores the answer results and emotional data in a database, including correct / incorrect answers, answer time, question difficulty, emotional state, etc.

[1724] Step 15:

[1725] Analyzing the data

[1726] The server analyzes the saved answer results and emotional data using a generative AI model to evaluate the user's answering tendencies, strengths and weaknesses, and emotional tendencies.

[1727] Step 16:

[1728] Next problem generation

[1729] Based on the analysis results, the server adjusts the content and difficulty of the next question, taking into account emotional data, for example, by presenting easier questions if the user is tired.

[1730] Step 17:

[1731] Submit a new issue

[1732] The server sends the newly generated problem to the device, and the user attempts the next problem, and the process is repeated.

[1733] Example 2

[1734] 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."

[1735] Conventional learning systems have limited ability to generate questions that correspond to the user's level of understanding, making it difficult to adapt to each user's individual learning progress and emotional state. Furthermore, because they only consider the user's learning history, it is difficult to maintain motivation during learning. Furthermore, feedback on answer results is one-dimensional, which does not fully address individual learning needs. Therefore, to maximize the user's learning effectiveness, it is essential to dynamically generate questions and provide feedback that are optimized according to the user's level of understanding and emotional state.

[1736] 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.

[1737] In this invention, the server includes means for performing user initial settings, means for authenticating the user and acquiring the user's learning history, means for generating questions according to the user's level of understanding, means for inputting answers, means for judging the answer results and providing feedback, means for saving and analyzing the answer results and generating the next question, means for acquiring and analyzing the user's emotional data, and means for adjusting the difficulty of questions and feedback based on the user's emotional state. This makes it possible to always provide an optimal learning experience by taking into account the user's level of understanding and emotional state.

[1738] The "means for performing user initial settings" is a means for collecting basic information such as the user's learning objectives, current level, and learning history, and for performing the initial settings of the system.

[1739] The "means for authenticating a user and acquiring a learning history" refers to the means for verifying the login information entered when a user logs into the system and acquiring the user's past learning history from the database.

[1740] "Means for generating questions according to the user's level of understanding" refers to a means for dynamically generating the optimal question to be asked next using a generative AI model based on the user's learning history and latest answer results.

[1741] The "means for inputting an answer" is a means by which a user inputs an answer to a presented question and transmits the answer to the system.

[1742] The "means for determining the answer result and providing feedback" refers to the means by which the server determines the answer submitted by the user and provides feedback based on the result. This feedback includes determining whether the answer is correct or incorrect and providing learning resources.

[1743] The "means for saving and analyzing the answer results and generating the next question" is a means for saving the user's answer results in a database and analyzing them to generate the next optimal question.

[1744] The "means for acquiring and analyzing user emotional data" refers to a means for capturing the user's facial expressions and voice data using the device's camera and microphone, and analyzing the user's emotional state using an emotion recognition engine.

[1745] "Means for adjusting the difficulty of questions and feedback based on the user's emotional state" refers to means for dynamically adjusting the difficulty of questions and the content of feedback based on analyzed emotional data to suit the user's current emotional state.

[1746] This invention relates to a system that automatically generates questions according to the user's level of understanding, analyzes the answers to provide the next most appropriate questions, and recognizes the user's emotions to optimize the learning experience. This system operates in cooperation with a server, terminal, user, and emotion engine.

[1747] The outline of the system is as follows:

[1748] Initial Setup

[1749] When a user registers or logs in, the server collects basic information about the user and performs initial setup. This includes the user's learning goals, current level, learning history, etc. Specifically, the user sets their learning goals and current level. Based on this information, the server generates an appropriate initial problem set and stores it in the database. For example, User A wishes to "move from beginner to intermediate level English," and sets the basic information required for this.

[1750] User authentication and data acquisition

[1751] A user logs in to the system using a terminal. The login information is sent from the terminal to the server, and the server authenticates the user by comparing it with information in the database. If authentication is successful, the server retrieves the user's past learning history from the database and evaluates their current level of understanding based on that data. For example, User B logs in and their past learning data is retrieved.

[1752] problem generation

[1753] The server uses a generative AI model to generate the next question based on the user's level of understanding. The questions are optimized by taking into account the user's past answers and current level of understanding. For example, the server generates a question for User B: "Please choose the meaning of 'serene': a) noisy, b) quiet, c) comfortable."

[1754] Answer input and result feedback

[1755] The user answers questions via the terminal. The terminal sends the user's answers to the server. The server evaluates the received answers and provides feedback to the user on whether they are correct or incorrect. Specific feedback may include explanations of correct or incorrect answers and additional learning resources. For example, if user B selects "b) quiet," the server provides the following feedback: "That's correct. 'serene' means 'quiet.'"

[1756] Data accumulation and analysis

[1757] The server stores the answers in a database. The stored data includes correct and incorrect answers, the time it took to answer, and the difficulty of the questions. The server analyzes this data using a generative AI model to evaluate the user's learning habits and comprehension. For example, if a user frequently makes mistakes on a certain type of question, the server will focus on questions in that area.

[1758] Next problem generation

[1759] Based on the analysis results, the server readjusts the content and difficulty of the next question. This allows the user to always solve questions at the optimal level. The new questions generated are sent back to the device, and the next learning cycle begins. For example, if it is analyzed that User B is not feeling stressed, a question with a slightly higher level of difficulty is generated.

[1760] Introducing the Emotion Engine

[1761] When a user answers questions using the device, the device uses a camera and microphone to capture the user's facial expressions and tone of voice. The device then uses an emotion recognition engine to determine the user's emotional state from the captured data, which can include happiness, sadness, stress, and excitement. The recognized emotional data is sent to a server, which analyzes the emotional data and adjusts the difficulty and content of the questions based on the user's current emotional state. The form and content of the feedback is also optimized to match the user's emotions.

[1762] Specific examples

[1763] Consider the case where User B logs in to the system and begins a normal learning session. User B's initial setting is to set his / her learning goal as "Beginner to intermediate level English." The server generates an initial set of questions based on this information. For example, User B is presented with a question asking, "What is the meaning of 'serene'? a) noisy, b) quiet, c) comfortable." User B selects "b) quiet," and the server provides feedback saying, "That's correct. 'serene' means 'quiet.'" At the same time, the device captures User B's facial expression and determines that he / she is under low stress using an emotion recognition engine. Next, the server generates a slightly more difficult question, asking, "What is the meaning of 'melancholy'? a) enthusiastic, b) depressed, c) lively."

[1764] By repeating this process, users can obtain a learning experience that is optimized for their level of understanding and emotional state. This system supports efficient and effective learning and keeps users motivated to learn.

[1765] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1766] Step 1:

[1767] A new user registration or login is performed. The user uses a terminal to enter their ID and password or new registration information. The entered information is sent from the terminal to the server.

[1768] Input: User ID, password, new registration information

[1769] Output: Authentication information sent to the server

[1770] Specific operation: User A enters the necessary information into the new registration form on the device and presses the send button. The device then sends the entered information to the server.

[1771] Step 2:

[1772] The server authenticates the user by comparing login information and new registration information with information in the database. If authentication is successful, the server obtains the user's past learning history.

[1773] Input: The authentication information sent to the server

[1774] Output: Authentication results, learning history data

[1775] Specific operation: The server authenticates User A by checking against the database, and after successful authentication, retrieves User A's past learning history from the database.

[1776] Step 3:

[1777] The server performs initial setup based on the user's basic information, including the user's learning goals, current level, and learning history.

[1778] Input: Learning objectives, current level, learning history

[1779] Output: Initial setup data, initial problem set

[1780] Specific operation: User A sets "I want to move from beginner to intermediate level English," and the server generates an initial set of questions based on that information.

[1781] Step 4:

[1782] The server generates the next question based on the user's level of understanding, using a generative AI model to consider the user's past answers and current level of understanding to create the most appropriate question.

[1783] Input: User's comprehension data, answer results

[1784] Output: Next problem data

[1785] Specific operation: The server uses the generative AI model to generate a question for User B: "Please choose the meaning of 'serene': a) noisy, b) quiet, c) comfortable."

[1786] Step 5:

[1787] The user answers questions via the terminal and sends the answers, which are then sent to the server.

[1788] Input: User's answer data

[1789] Output: Answer data sent to the server

[1790] Specific operation: User B selects "b) Quiet" and the device sends the user's answer to the server.

[1791] Step 6:

[1792] The server evaluates the received answers and provides feedback to the user, including explanations of correct and incorrect answers and additional learning resources.

[1793] Input: User's answer data

[1794] Output: Feedback data

[1795] Specific behavior: The server judges the answer and provides feedback such as "Correct. 'serene' means 'quiet'."

[1796] Step 7:

[1797] The server stores the answer results in a database. The stored data includes correct answers, answer time, difficulty level of the question, etc. The server analyzes this data using a generative AI model.

[1798] Input: Answer result data

[1799] Output: Analysis data, storage data

[1800] Specific operation: The server stores User B's answer data in a database and analyzes it using a generative AI model.

[1801] Step 8:

[1802] The server then adjusts the content and difficulty of the next question based on the analysis results, and the new question is then sent back to the device.

[1803] Input: Analysis data

[1804] Output: Rescaled problem data

[1805] Specific operation: The server analyzes that User B is not feeling stressed, generates the next question "Please choose the meaning of 'melancholy': a) enthusiastic, b) depressed, c) lively" and sends it to the terminal.

[1806] Step 9:

[1807] The device uses a camera and microphone to capture the user's facial expressions and tone of voice, and an emotion recognition engine to determine the user's emotional state.

[1808] Input: facial expression data, voice data

[1809] Output: Emotion data

[1810] Specific operation: When User B answers the question, the device captures facial expression data and the emotion recognition engine determines that the user is under low stress.

[1811] Step 10:

[1812] The emotion recognition results are sent to a server, which analyzes the emotion data and adjusts the difficulty of the questions and feedback based on the user's current emotional state.

[1813] Input: Emotion data

[1814] Output: Adjusted problem data, feedback data

[1815] How it works: The device sends emotional data to the server, and the server adjusts the difficulty of the next question and feedback based on the emotional state.

[1816] (Application example 2)

[1817] 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."

[1818] Conventional learning management systems and task management systems for factory robots do not dynamically adjust tasks according to the user's or robot's level of understanding or workload, making efficient learning and work execution difficult. This has led to problems such as a decline in the user's motivation to learn and robot overload. Furthermore, these systems were unable to recognize and reflect emotions or workload conditions, preventing optimal feedback and task generation.

[1819] 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.

[1820] In this invention, the server includes means for performing user initial settings, means for authenticating the user and acquiring the user's learning history, means for generating questions according to the user's level of understanding, means for inputting answers, means for judging the answer results and providing feedback, means for saving and analyzing the answer results and generating the next question, means for the robot to learn a new task, means for adjusting the difficulty of the next task based on the task results, and means for recognizing the robot's load state and optimizing task execution efficiency. This enables efficient learning while increasing the user's motivation to learn, and enables optimal task execution while preventing the robot from being overloaded.

[1821] "User initial settings" refers to the process of collecting and setting basic information about a user's learning goals, current level, and learning history when the user registers or logs in.

[1822] "User authentication" is the process of verifying the user's identity when the user logs in to a system by sending the entered information to a server and comparing it with information in a database.

[1823] "Means for obtaining learning history" refers to the process by which the server reads past learning data from the database and uses it to evaluate the user's current level of understanding.

[1824] "Means for generating questions according to the user's level of understanding" refers to the process of using a generative AI model to create the optimal question to be asked next, based on the user's past answers and current level of understanding.

[1825] "Means for inputting answers" refers to the process in which a user inputs an answer to a question and the answer is sent to the server.

[1826] The "means for determining the answer result and providing feedback" is the process by which the server determines the received answer and provides the user with feedback on whether it is correct or not, as well as learning resources.

[1827] "Means for saving and analyzing the answer results and generating the next question" refers to the process in which the server saves the answer results in a database, analyzes them to evaluate the user's learning tendencies and level of understanding, and readjusts the content and difficulty of the next question to be asked.

[1828] "Means for robots to learn new tasks" refers to the process by which factory robots efficiently learn new jobs or tasks.

[1829] The "means for adjusting the difficulty of the next task based on the results of the task" is a process for dynamically adjusting the difficulty of the next task based on the results of the robot's task execution.

[1830] "Means for recognizing the load state of the robot and optimizing the efficiency of task execution" refers to a process for recognizing the load state of the robot and adjusting the difficulty and order of tasks to enable optimal task execution while preventing overload.

[1831] This invention is a system for maximizing the learning and working efficiency of users and robots, and is composed of a server, a terminal, a user, a robot, and an emotion engine. The system is specifically implemented as follows.

[1832] System Overview

[1833] Initial Setup

[1834] When a user performs initial setup, the server collects basic information about the user's learning goals, current level, and learning history. Based on this information, the server provides optimal initial setup for each user. The server also collects work goals and current task data for factory robots and performs initial setup.

[1835] User authentication and data acquisition

[1836] A user logs in to the system using a terminal. The login information is sent to the server, which then authenticates the user by comparing it with information in the database. If authentication is successful, the server retrieves the user's past learning history from the database and evaluates their current level of understanding.

[1837] problem generation

[1838] The server uses a generative AI model to create the next question based on the user's level of understanding. The questions are optimized by taking into account the user's past answers and current level of understanding. Similarly, the server analyzes the results of tasks for factory robots and generates the optimal next task to be performed.

[1839] Answer input and result feedback

[1840] Users answer questions via their device. The answers are sent from the device to the server, which evaluates them and provides feedback on whether the answer was correct or incorrect. Specific feedback may include explanations of correct or incorrect answers and additional learning resources. For robots, the server receives the results of the tasks performed, determines whether the robot was successful, and adjusts the difficulty of the next task based on the results.

[1841] Data accumulation and analysis

[1842] The server stores the answers and task execution results in a database. The stored data includes correct / incorrect answers, the time it took to answer, the difficulty of the question, the success / failure of the task, and the execution time. The server analyzes this data using a generative AI model to evaluate the user's learning tendency and level of understanding, as well as the robot's work efficiency.

[1843] Next problem generation

[1844] The server then adjusts the content and difficulty of the next question based on the analysis results, allowing users to always solve questions at the optimal level. The server also generates and suggests optimal tasks for the robot based on the analysis results.

[1845] Introducing the Emotion Engine

[1846] emotion recognition

[1847] When a user answers questions using the device, the device uses a camera and microphone to capture the user's facial expressions and tone of voice. An emotion recognition engine is used to determine the user's emotional state from the captured data. For robots, the emotional state (load state) is recognized based on the workload of performing the task.

[1848] Sending and analyzing emotional data

[1849] The device sends the recognized emotional data to a server, which analyzes the data and adjusts the difficulty and content of the questions and tasks based on the user's current emotional state and the robot's workload. The server also optimizes the form and content of feedback to match the user's emotional state.

[1850] Emotion-based problem generation and feedback

[1851] The server generates new problems and tasks taking into account the emotional data. For example, if the user is feeling stressed, it will lower the difficulty level slightly or provide feedback including an encouraging message. Also, if the robot is overloaded, it will reduce the difficulty of the next task. This information is sent to the terminal or robot, and the next cycle will begin taking into account the user's emotions and stress state.

[1852] Specific examples

[1853] Consider a case where a user logs in to the system and begins a learning session. For example, a question might appear: "Please choose the meaning of 'serene': a) noisy, b) quiet, c) comfortable." If the user selects "b) quiet," the server determines that this is the correct answer and provides feedback such as, "You're correct. 'serene' means 'quiet.'" The device simultaneously captures the user's facial expression and uses an emotion recognition engine to determine that the user is under stress. Also, if a factory robot performs a task called "assembly" and succeeds, the server suggests the slightly more difficult "inspection" task as the next task.

[1854] Prompt Sentence Examples

[1855] "The robot has succeeded five times and failed three times in the 'Inspect' task. What type and difficulty of task should it suggest next?"

[1856] "The user answered the 'serene' question correctly. Please generate a related vocabulary question for them to answer next."

[1857] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1858] Step 1:

[1859] The server provides the terminal with a screen for the user to perform initial setup. The user inputs information such as their learning objectives, current level, learning history, etc. The input data is sent to the server, which then stores the information in a database.

[1860] Step 2:

[1861] A user logs into the system using a terminal. The login information (user ID, password, etc.) is sent from the terminal to the server, which then authenticates the user by comparing it with information in the database. If authentication is successful, the server retrieves the user's past learning history from the database and sends that information to the terminal for display.

[1862] Step 3:

[1863] The server uses a generative AI model to generate questions based on the user's level of understanding. The generative AI model uses the user's past answers and current level of understanding as input data and outputs the optimal question to be posed next. This question is sent from the server to the device and displayed to the user.

[1864] Step 4:

[1865] The user answers the questions displayed via the terminal. The answer data is sent from the terminal to the server, and the server receives the answer data. The server compares the answer data with the correct answer data and determines whether the answer was correct or incorrect.

[1866] Step 5:

[1867] The server evaluates the answer and provides the result as feedback to the user. The feedback may include explanations of correct and incorrect answers and additional learning resources. The feedback data is sent from the server to the device and displayed to the user.

[1868] Step 6:

[1869] The server stores the answer results in a database. The stored data includes correct and incorrect answers, the time it took to answer, and the difficulty of the questions. This data serves as the basis for subsequent data analysis and question generation.

[1870] Step 7:

[1871] The server uses the stored data to analyze the user's learning habits and level of understanding using a generative AI model, and the analysis data is used to adjust the content and difficulty of the next questions.

[1872] Step 8:

[1873] The server then sends the newly generated questions to the device, and the next learning cycle begins, ensuring that the user is always challenged with questions of appropriate difficulty.

[1874] Step 9:

[1875] When a robot learns a new task, the server receives the robot's task settings and result data input via the terminal, and saves the robot's work history and current load status as data.

[1876] Step 10:

[1877] The server receives the results of the robot's tasks and analyzes the data on success and failure. Based on the analysis results, the data is processed to adjust the difficulty of the next task, and a new task is generated using the generative AI model. This data is then sent to the robot or the operator's device.

[1878] Step 11:

[1879] The emotion engine recognizes the robot's load state and adjusts to reduce the difficulty of the task if it is overloaded. The server generates feedback based on this situation and sends the feedback data to the robot and the operator's device.

[1880] Prompt Sentence Examples

[1881] "The robot has succeeded five times and failed three times in the 'Inspect' task. What type and difficulty of task should it suggest next?"

[1882] "The user answered the 'serene' question correctly. Please generate a related vocabulary question for them to answer next."

[1883] 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.

[1884] 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.

[1885] 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.

[1886] 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.

[1887] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1888] 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.

[1889] 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).

[1890] 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.

[1891] 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."

[1892] 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.

[1893] 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).

[1894] 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.

[1895] 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.

[1896] 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.

[1897] 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.

[1898] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1899] 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.

[1900] 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 ...

Claims

1. means for performing user initialization; a means for obtaining user authentication and learning history; A means for generating questions according to the user's level of understanding; a means for inputting answers; a means for determining the answer result and providing feedback; A means for storing and analyzing the answer results and generating the next question; A system including:

2. The system of claim 1 further comprising means for adjusting the difficulty of the questions based on the user's level of understanding.

3. 2. The system according to claim 1, further comprising means for storing the user's learning history and answer results as a database and analyzing the same.

Images