System

Abstract

A system is provided.SOLUTION: A system comprising: input means for a user to specify a field, category, and difficulty of a problem; an artificial intelligence engine for generating the problem based on the specified information; output means for providing the generated problem and its answer to the user; and evaluation means for evaluating the answer input by the user and generating feedback.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] With existing problem sets, once a student has solved a problem, they need a new problem set to solve the same problem again, and the types and patterns are limited. Furthermore, paper-based problem sets often contain outdated information and errors. Furthermore, it is difficult to provide optimal problems tailored to the student's knowledge level, which makes learning inefficient. [Means for solving the problem]

[0005] The present invention is a system that includes an input means for a user to specify the field, category, and difficulty level of a question, an artificial intelligence engine for generating questions based on the specified information, an output means for providing the generated questions and their answers to the user, and an evaluation means for evaluating the answers input by the user and generating feedback. Furthermore, by providing a means for generating multiple questions based on the information specified by the user and randomly selecting and providing them, and a means for automatically adjusting the difficulty level of questions based on the user's knowledge level, it is possible to solve problems such as a lack of number of questions and patterns, outdated information, errors, and low learning efficiency.

[0006] "User" refers to a person who uses the system to solve problems and learn.

[0007] "Input means" refers to an interface that allows a user to specify the field, category, and difficulty level of a question.

[0008] An "artificial intelligence engine" refers to a system component that generates questions and solutions based on given information.

[0009] "Output means" refers to the component of the system that displays or provides the generated questions and their answers to the user.

[0010] "Evaluator" refers to the component of the system that evaluates the answers entered by the user and generates feedback.

[0011] "Discipline" refers to the area of ​​study or topic to which the problem belongs.

[0012] A "category" refers to a specific subtopic or theme within a field.

[0013] "Difficulty" refers to the level of difficulty of the question.

[0014] "Feedback" refers to the evaluation and advice provided to the user based on the answers they provide.

[0015] "Knowledge level" refers to the depth and scope of knowledge that a user already possesses.

[0016] "Random" means chosen at random without following any particular rules or patterns.

[0017] "Automatic" means that the system operates independently without the need for manual user intervention.

[0018] "Number of questions" refers to the total number of questions to be generated.

[0019] "Pattern" refers to the format and tendency of the questions generated. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] System Configuration Overview

[0042] This automatic question generation system consists of an input means for a user to specify the field, category, and difficulty level of the question, an artificial intelligence engine that generates questions based on this information, an output means for providing the generated questions and their answers, and an evaluation means for evaluating the answers entered by the user and providing feedback.

[0043] Specific implementation methods of the system

[0044] User Interface (UI)

[0045] The user accesses the problem generation system using a terminal. The interface allows the user to select the subject (e.g., mathematics, science), category (e.g., algebra, physics), and difficulty level (e.g., beginner, intermediate, advanced) using drop-down menus and text fields. Once the user completes these entries, they press the "Generate" button.

[0046] Server-side processing

[0047] The device sends the user's setting data (field, category, difficulty level) to the server. The server receives this data and instructs the AI ​​engine to generate questions. The AI ​​engine generates appropriate questions based on the specified field, category, and difficulty level.

[0048] AI problem generation engine

[0049] The AI ​​problem generation engine receives instructions from the server and generates problems as follows:

[0050] 1. Question structure

[0051] 2. Generating answers to problems

[0052] Examples:

[0053] Problem: Factor x^2 + 5x + 6 = 0.

[0054] Answer: (x + 2)(x + 3)

[0055] The generated questions and answers are sent back to the server, which then transmits them to the user's terminal.

[0056] Display and answer input

[0057] The user's device displays the generated questions. The user looks at the questions and enters their answers into the interface. Once the input is complete, the user presses the "Submit" button.

[0058] Answer evaluation and feedback

[0059] The device sends the answer entered by the user to the server. The server has the AI ​​evaluate the answer. The AI ​​evaluates the answer and determines whether it is correct or incorrect. Based on the evaluation result, the server generates a feedback message, which is sent back to the device and displayed to the user.

[0060] Examples:

[0061] If the user answers "(x + 2)(x + 3)" and it is evaluated as correct, the feedback message displayed is "Correct, well done!". If the user answers "(x + 3)(x + 2)", it is also evaluated as correct and the feedback message displayed is "Correct, well done!".

[0062] Update function

[0063] The system is regularly updated on the backend, so that questions are generated based on new content or information added to a field or category. The AI ​​also continuously updates its question generation algorithm based on the latest learning data.

[0064] Improved feedback accuracy

[0065] If the user enters an incorrect answer, the AI ​​provides detailed feedback explaining why the answer is incorrect, including steps and references to the correct answer.

[0066] In this way, the system can continuously provide learners with questions that best suit their needs, and seamlessly generate questions, evaluate answers, and provide feedback.

[0067] The processing flow will be explained below.

[0068] Step 1:

[0069] The user accesses the question generation system on the terminal and opens the setting screen.

[0070] Step 2:

[0071] The user selects the field, category, and difficulty level and presses the "Generate" button.

[0072] Step 3:

[0073] The device collects data on the user's selected field, category, and difficulty level.

[0074] Step 4:

[0075] The terminal transmits the collected setting data to the server.

[0076] Step 5:

[0077] The server analyzes the received configuration data and issues instructions to the AI ​​problem generation engine to generate problems.

[0078] Step 6:

[0079] The AI ​​question generation engine generates questions and answers based on specified conditions.

[0080] Step 7:

[0081] The server receives questions and answers generated by the AI ​​question generation engine.

[0082] Step 8:

[0083] The server transmits the generated question data to the terminal.

[0084] Step 9:

[0085] The terminal displays the problem to the user.

[0086] Step 10:

[0087] The user solves the problem, enters the answer into the terminal interface, and presses the "Submit" button.

[0088] Step 11:

[0089] The terminal collects the answers entered by the user.

[0090] Step 12:

[0091] The terminal sends the collected answers to the server.

[0092] Step 13:

[0093] The server issues instructions to the AI ​​to evaluate the received answers.

[0094] Step 14:

[0095] AI evaluates the user's answers and determines whether they are correct or incorrect.

[0096] Step 15:

[0097] The server receives the evaluation results from the AI ​​and generates a feedback message.

[0098] Step 16:

[0099] The server sends the generated feedback message to the terminal.

[0100] Step 17:

[0101] The terminal displays a feedback message to the user.

[0102] Example 1

[0103] 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."

[0104] Conventional automatic problem generation systems have limited functionality for generating appropriate problems based on user settings, and providing evaluation and feedback on answers, making them unable to fully meet users' learning needs. In particular, it has been difficult to provide detailed feedback on the answers entered by users, or to automatically update problems based on new data.

[0105] 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.

[0106] In this invention, the server includes an input means for a user to specify the field, category, and difficulty level of a question, an artificial intelligence engine for generating questions based on the specified information, and an output means for providing the generated questions and their answers to the user. This allows the user to specify specialized questions tailored to their learning needs and have their answers evaluated. The server also includes a data storage means for receiving and storing data transmitted from the user's device, a means for generating feedback messages from the artificial intelligence engine that evaluates the data and generates feedback and returning the feedback messages to the user's device, an update means for generating corresponding questions when new data is added to a specific field or category, and a means for providing feedback in detail explaining why the user's answer is incorrect when the user enters an incorrect answer. This allows the user to continuously progress in their learning through detailed feedback and updated questions, significantly improving their learning effectiveness.

[0107] The "input means" is a means for providing an interface for a user to specify the field, category, and difficulty level of a question.

[0108] An "artificial intelligence engine" is a program or system that generates questions and their answers based on specified information.

[0109] "Output means" refers to a display device or transmission means for providing the generated questions and their answers to the user.

[0110] An "evaluator" is a program or mechanism for evaluating answers entered by a user and generating feedback.

[0111] The "data storage means" is a storage device or database for receiving and storing data sent from the user's terminal at the server.

[0112] The "feedback message generating means" is a program or system for generating a feedback message from an artificial intelligence engine that evaluates data and generates feedback, and returning this to the user terminal.

[0113] An "updater" is a mechanism or program that generates questions corresponding to new data added to a particular field or category.

[0114] A "feedback providing means" is a program or system that, when a user enters an incorrect answer, provides feedback that explains in detail why the answer is incorrect.

[0115] MODE FOR CARRYING OUT THE INVENTION

[0116] System Configuration

[0117] The automatic question generation system of the present invention comprises an input means for a user to specify the field, category, and difficulty level of a question, an artificial intelligence engine for generating questions based on the specified information, an output means for providing the generated questions and their answers to the user, and an evaluation means for evaluating the answers entered by the user and generating feedback.

[0118] User Interface (UI)

[0119] A user accesses the automated problem generation system using a terminal. The interface includes drop-down menus and text fields that allow the user to specify the subject (e.g., mathematics, science), category (e.g., algebra, physics), and difficulty level (e.g., beginner, intermediate, advanced). Once the user completes the settings, they press a "Generate" button, which triggers the input mechanism.

[0120] Sending and Receiving Data

[0121] The user's terminal sends the setting data (field, category, difficulty level) to the server. The server receives this and stores it in the data storage means. This data will be used in the next step of the process.

[0122] Question generation instructions

[0123] The server analyzes the received data and instructs the AI ​​engine to generate questions and answers based on the specified field, category, and difficulty level.

[0124] Specifically, the problem is generated using the following steps:

[0125] 1. Question structure

[0126] 2. Generating answers to problems

[0127] As a concrete example, generate the following problem and its solution:

[0128] Problem: Factor x^2 + 5x + 6 = 0.

[0129] Answer:(x + 2)(x + 3)

[0130] Providing questions and answers

[0131] The generated questions and answers are sent back to the server, which then sends them to the user's terminal and provides them to the user, who then displays the questions on the user's terminal.

[0132] Enter answers to questions and submit

[0133] The user thinks of an answer to the displayed question and enters it into the interface. After entering the answer and pressing the "Send" button, the terminal sends the answer data to the server.

[0134] Answer evaluation and feedback

[0135] The server passes the received answer data to an AI engine, which evaluates the answer, determines whether it is correct, and generates a feedback message.

[0136] Specifically, it generates feedback like this:

[0137] If you get it right: "That's right, well done!"

[0138] Incorrect answer: "Sorry, you're wrong. The correct answer is (x + 2)(x + 3)."

[0139] The feedback message is sent from the server to the terminal and displayed to the user.

[0140] Improved update functionality and feedback

[0141] The system is regularly updated in the backend, and questions are generated accordingly as new data is added. Additionally, if a user enters an incorrect answer, feedback is provided detailing the error.

[0142] Specific examples of prompts to input to generative AI models

[0143] Below are some examples of prompts that can be used to generate questions:

[0144] "Generate problems for factoring quadratic equations at an elementary level in mathematics."

[0145] "Generate intermediate level physics problems related to mechanics."

[0146] This allows the system to provide optimal questions tailored to the user's learning needs, and by evaluating and providing feedback on answers, it can improve learning effectiveness.

[0147] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0148] Step 1: User specifies the problem

[0149] The user uses a terminal to access the interface of the automatic question generation system. The interface displays drop-down menus and text fields for selecting the field, category, and difficulty level. The user uses these to input the desired question settings. Once the input is complete, the user presses the "Generate" button. The input here is the field, category, and difficulty level, and the output is the user-selected setting data.

[0150] Step 2: Send data from the device to the server

[0151] The device sends the setting data (field, category, difficulty) entered by the user to the server via an HTTP request. The input is the setting data, and the output is a confirmation that the data was successfully sent to the server. At this time, the device displays an indicator indicating that the sending process is in progress.

[0152] Step 3: Server receives and analyzes data

[0153] The server receives the setting data sent from the terminal. This data is stored in the server's data storage means. The server then analyzes the received data and determines which field, category, and level of difficulty to generate questions for. The input is the received data, and the output is the analysis results.

[0154] Step 4: Submitting the question generation instructions

[0155] The server issues instructions to the AI ​​engine for generating questions based on the analysis results. These instructions include the field, category, and difficulty level. The server passes this configuration data to the AI ​​engine as a prompt. The input is the analysis results, and the output is instructions for generating questions.

[0156] Step 5: Generate questions using the AI ​​question generation engine

[0157] Based on the prompt received from the server, the AI ​​engine generates a problem and answer that meets the specified conditions. Specifically, it creates the structure of the problem and the corresponding answer. For example, in the field of mathematics, it generates a problem such as "factorize x^2 + 5x + 6 = 0" and its answer "(x + 2)(x + 3)". The input is the problem generation instruction, and the output is the generated problem and answer.

[0158] Step 6: Sending the generated data back to the server

[0159] The AI ​​engine sends the generated questions and answers back to the server. The server temporarily stores the received data. The input is the generated questions and answers, and the output is the receipt of the data by the server.

[0160] Step 7: Sending data from the server to the device

[0161] The server sends the generated questions and answers to the user's device. The data is sent using an HTTP response. The input is the questions and answer data stored on the server, and the output is a confirmation that the data was successfully sent to the device.

[0162] Step 8: User enters answer

[0163] The generated question is displayed on the terminal, and the user inputs the answer to the question into the interface. When input is complete, the user presses the "Submit" button. The input is the user's answer, and the output is the answer data ready for transmission.

[0164] Step 9: Send the answer from the device to the server

[0165] The terminal sends the answer entered by the user to the server via an HTTP request. The input is the user's answer data, and the output is a confirmation that the data was successfully sent to the server.

[0166] Step 10: Server evaluates the answer

[0167] The server passes the received answer data to an AI engine, which evaluates the answer. The AI ​​engine determines whether the answer is correct and generates an appropriate feedback message. The input is the user's answer data, and the output is the evaluation result and feedback message.

[0168] Step 11: Returning evaluation results and feedback

[0169] The server generates a feedback message and sends it to the user's device. The feedback includes whether the answer is correct or incorrect, and if incorrect, the reason for the error. The input is the evaluation result and the feedback message, and the output is a confirmation of successful data transmission to the device.

[0170] Step 12: Viewing feedback

[0171] The user's device displays the received feedback message on the interface. For example, messages such as "That's right, well done!" or "Sorry, you're wrong. The correct answer is (x + 2)(x + 3)" are displayed. The input is the feedback message, and the output is the feedback display to the user.

[0172] (Application example 1)

[0173] 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."

[0174] Currently, many brick-and-mortar store staff are required to undergo regular training on product knowledge and customer service skills, but the content is uniform, making it difficult to provide questions tailored to each staff member's knowledge level and required skills. Furthermore, previous training methods make it difficult to immediately evaluate staff answers and provide appropriate feedback. Therefore, it is necessary to provide an efficient training method that meets the needs of each individual staff member.

[0175] 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.

[0176] In this invention, the server includes an input means for a user to specify the field, category, and difficulty of a question, an artificial intelligence engine for generating questions based on the specified information, an output means for providing the generated questions and their answers to the user, an evaluation means for evaluating the answers input by the user and generating feedback, and a means for automatically generating and evaluating training and educational questions for staff. This makes it possible to efficiently provide questions tailored to the knowledge level and required skills of each staff member and to provide immediate feedback on the answers.

[0177] "Input means for the user to specify the field, category, and difficulty level of the problem" refers to an interface means for the user to specify information about the training or educational problem, and includes menus and input fields for selecting the field, category, and difficulty level.

[0178] An "artificial intelligence engine for generating questions based on specified information" is an artificial intelligence-based computer program for automatically generating appropriate training or educational questions based on subject, category, and difficulty information entered by a user.

[0179] "Output means for providing the generated questions and their answers to the user" refers to means for displaying or providing the questions and their answers generated by the artificial intelligence engine on the user's device, including the display of a smartphone or the screen of an application.

[0180] The "evaluation means for evaluating the answer entered by the user and generating feedback" refers to a program or algorithm that analyzes the answer entered by the user, determines whether it is correct or not, and provides feedback.

[0181] "Means for automatically generating and evaluating staff training and educational questions" refers to the overall system functionality for automatically generating training and educational questions for store staff using artificial intelligence and evaluating the answers.

[0182] "Efficient delivery with immediate feedback on answers" refers to the entire process of generating quick and appropriate training questions based on user-specified information, and then instantly evaluating and providing feedback on the answers provided by the user.

[0183] "Server" refers to a central computer or similar facility that performs various processes, such as generating questions, evaluating answers, and providing feedback, in practicing the invention.

[0184] overview

[0185] This invention is a system for automatically generating training and educational questions for store staff, evaluating the answers, and providing immediate feedback. The system consists of the following components: user input, question generation, answer evaluation, and feedback provision.

[0186] Hardware and Software Configuration

[0187] Hardware used

[0188] Smartphone: A device through which a user accesses an application.

[0189] Server: A central computer that performs question generation and evaluation functions and manages various data.

[0190] Software used

[0191] Programming language: Develop applications in Swift (for iOS) and Kotlin (for Android).

[0192] Framework: Uses Firebase for real-time database and serverless functions.

[0193] Generative AI model: We will use TensorFlow to implement the artificial intelligence model required for question generation and evaluation.

[0194] System Operation

[0195] User Input

[0196] Users access the application using their smartphones and enter information into the interface to select a training category (e.g., product knowledge, customer service skills) and difficulty level (beginner, intermediate, advanced). After entering the required information, the user presses the "Generate" button.

[0197] Problem generation

[0198] The server receives the user's input data (area, category, difficulty level) and issues question generation instructions to the generative AI model. The AI ​​model generates appropriate training questions based on the specified information. For example, an intermediate question on customer service skills might be, "How would you respond if a customer complained about a returned product?"

[0199] Providing problems

[0200] The generated questions and their answers are sent from the server to the user's smartphone, which displays the questions on an interface and allows the user to enter the answers.

[0201] Answer evaluation

[0202] When a user enters an answer and presses the "Submit" button, the answer is sent to the server. The server evaluates the answer using a generative AI model and determines whether it is correct. For example, if a user answers, "First, listen to the customer's story to the end, show empathy, and then quickly process the return," the AI ​​will determine this as the correct answer.

[0203] Providing Feedback

[0204] Based on the evaluation results, the server generates a feedback message and sends it to the user's smartphone. If the answer is correct, it displays "That's right, well done!", and if the answer is incorrect, it provides appropriate corrections and instructions for solving the problem.

[0205] Examples and prompts

[0206] Specific examples

[0207] For example, if a user selects "Intermediate" when generating training questions for customer service skills:

[0208] Problem: How do you respond when a customer complains about a return?

[0209] AI-generated answer (example): First, listen to the customer's story thoroughly, show empathy, and then quickly process the return.

[0210] Prompt example

[0211] Please generate training questions that meet the following criteria:

[0212] Category: Customer Service Skills

[0213] Difficulty: Intermediate

[0214] Problem Statement: How would you respond if a customer complained about a return?

[0215] Sample answer: First, listen to the customer thoroughly, show empathy, and then process the return promptly.

[0216] As described above, by clearly indicating the specific system configuration and processing content for implementing the invention, it is shown that the invention functions effectively in training staff in brick-and-mortar stores.

[0217] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0218] Step 1:

[0219] The user launches the application on their smartphone and selects a training category (e.g., product knowledge, customer service skills) and difficulty level (beginner, intermediate, advanced). After entering this information and pressing the "Generate" button, the device sends the input data to the server.

[0220] Input: Category and difficulty information

[0221] Output: Send category and difficulty selection data to the server

[0222] Step 2:

[0223] The server receives the selection data sent from the device and passes it to the generative AI model, which then generates appropriate training questions based on the specified information.

[0224] Input: Category and difficulty selection data

[0225] Output: Generated problem data

[0226] Step 3:

[0227] The server receives the generated question data and sends it to the user's smartphone, which displays the received question data on its interface and allows the user to enter answers.

[0228] Input: Generated problem data

[0229] Output: Problem displayed in terminal

[0230] Step 4:

[0231] When the user inputs an answer to the displayed question and presses the "Send" button, the terminal transmits the input answer data to the server.

[0232] Input: User's answer data

[0233] Output: Send answer data to the server

[0234] Step 5:

[0235] The server receives the user's answer data, passes it to the generative AI model, and evaluates the answer. The generative AI model determines whether the answer is correct or incorrect and returns the result to the server.

[0236] Input: User's answer data

[0237] Output: Evaluation result (correct / incorrect)

[0238] Step 6:

[0239] The server generates a feedback message based on the evaluation results and sends it to the user's smartphone, which then displays the feedback message on its interface.

[0240] Input: Evaluation result

[0241] Output: Generate and display feedback messages

[0242] Specific actions

[0243] Step 1

[0244] The user selects a category (e.g., customer service skills) and difficulty level (intermediate) in the application and presses the "Generate" button. The device converts the selected data into JSON format and sends it to the server as an HTTPS request.

[0245] Step 2

[0246] The server analyzes the received request, extracts data on the category and difficulty level, and inputs a prompt (e.g., "Customer service skills, intermediate") to the AI ​​model to instruct it to generate questions. The AI ​​model then generates appropriate questions and returns the data to the server.

[0247] Step 3

[0248] The server receives the generated problem data and sends it in JSON format to the user's device. The device displays the received problem on the interface, for example, "If a customer complains about a returned product, how would you respond?"

[0249] Step 4

[0250] The user enters the answer to the question (e.g., "First, listen to the customer's story until the end, show empathy, and then quickly process the return.") and presses the "Submit" button. The device converts the entered answer data into JSON format and sends it to the server as an HTTPS request.

[0251] Step 5

[0252] The server analyzes the received answer data and issues evaluation instructions to the generating AI model. The AI ​​model determines whether the answer is correct and returns an evaluation result, such as determining that the answer is "correct."

[0253] Step 6

[0254] The server generates a feedback message (e.g., "That's right, well done!") based on the evaluation result and sends it to the user's device in JSON format. The device then displays the feedback message on its interface for the user to see.

[0255] In this way, the present invention provides efficient and relevant training to users and provides immediate feedback on their answers.

[0256] 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.

[0257] System Configuration Overview

[0258] This automatic question generation system includes an input means for a user to specify the field, category, and difficulty level of the question, an artificial intelligence engine that generates questions based on this information, an output means for providing the generated questions and their answers, an evaluation means for evaluating the answers entered by the user and providing feedback, and an emotion engine that recognizes the user's emotions and adjusts the content of the questions based on them.

[0259] Specific implementation methods of the system

[0260] User Interface (UI)

[0261] The user accesses the problem generation system using a terminal. The interface allows the user to select the subject (e.g., mathematics, science), category (e.g., algebra, physics), and difficulty level (e.g., beginner, intermediate, advanced) using drop-down menus and text fields. Once the user completes these entries, they press the "Generate" button.

[0262] Server-side processing

[0263] The device sends the user's setting data (field, category, difficulty level) to the server. The server receives this data and instructs the AI ​​problem generation engine to generate questions. Based on the specified field, category, and difficulty level, the AI ​​engine generates appropriate questions.

[0264] AI problem generation engine

[0265] The AI ​​problem generation engine receives instructions from the server and generates questions and answers. For example, it generates questions as follows:

[0266] Problem: Factor $x^2 + 5x + 6 = 0$.

[0267] Answer: $(x + 2)(x + 3)$

[0268] The generated questions and answers are sent back to the server, which then transmits them to the user's terminal.

[0269] Emotional engine regulation

[0270] The emotion engine uses sensor data from the device's camera, microphone, and other devices to recognize the user's emotions (e.g., stress, fatigue, concentration) in real time. After the emotion engine evaluates the user's emotional state, it adjusts the difficulty and timing of questions based on the results.

[0271] As a specific example, if the user is determined to be in a high stress state, the emotion engine will lower the difficulty of the questions, thereby reducing the burden on the user.

[0272] Display and answer input

[0273] The user's device displays the generated questions. The user looks at the questions and enters their answers into the interface. Once the input is complete, the user presses the "Submit" button.

[0274] Answer evaluation and feedback

[0275] The device sends the answer entered by the user to the server. The server has the AI ​​evaluate the answer. The AI ​​evaluates the answer and determines whether it is correct or incorrect. Based on the evaluation result, the server generates a feedback message, which is sent back to the device and displayed to the user.

[0276] For example, if the user answers "(x + 2)(x + 3)" and this is evaluated as correct, the feedback message displayed will be "Correct, well done!". Also, if the user answers "(x + 3)(x + 2)", this will also be evaluated as correct and the feedback message displayed will be "Correct, well done!".

[0277] Update function

[0278] The system is regularly updated in the backend, especially when new content or information is added to a field or category, so that corresponding questions are generated. The emotion engine is also updated based on the latest data, continuously improving the accuracy of user emotion recognition.

[0279] Improved feedback accuracy

[0280] If the user enters an incorrect answer, the AI ​​provides detailed feedback explaining why the answer is incorrect, including steps and references to the correct answer. The emotional engine also adjusts the tone and content of the feedback appropriately, taking into account the user's emotional state.

[0281] In this way, the system maximizes users' learning efficiency and enhances their learning experience by seamlessly generating questions, evaluating answers, providing feedback, and adjusting to the user's emotions.

[0282] The processing flow will be explained below.

[0283] Step 1:

[0284] The user accesses the question generation system on the terminal and opens the setting screen.

[0285] Step 2:

[0286] The user selects the field, category, and difficulty level and presses the "Generate" button.

[0287] Step 3:

[0288] The device collects data on the user's selected field, category, and difficulty level.

[0289] Step 4:

[0290] The device sends the sensor data for the emotion engine to the server along with the configuration data collected.

[0291] Step 5:

[0292] The server analyzes the received configuration data and issues instructions to the AI ​​problem generation engine to generate problems.

[0293] Step 6:

[0294] The emotion engine analyzes sensor data from the device (e.g., camera footage and audio data) and evaluates the user's emotional state.

[0295] Step 7:

[0296] The AI ​​question generation engine generates questions and answers based on specified conditions.

[0297] Step 8:

[0298] The server receives questions and answers generated by the AI ​​question generation engine.

[0299] Step 9:

[0300] Based on the evaluation results of the emotion engine, the server adjusts the difficulty level of the questions and the timing of questions.

[0301] Step 10:

[0302] The server transmits the generated question data to the terminal.

[0303] Step 11:

[0304] The terminal displays the problem to the user.

[0305] Step 12:

[0306] The user solves the problem, enters the answer into the terminal interface, and presses the "Submit" button.

[0307] Step 13:

[0308] The terminal collects the answers entered by the user.

[0309] Step 14:

[0310] The terminal sends the collected answers to the server.

[0311] Step 15:

[0312] The server issues instructions to the AI ​​to evaluate the received answers.

[0313] Step 16:

[0314] AI evaluates the user's answers and determines whether they are correct or incorrect.

[0315] Step 17:

[0316] The server receives the evaluation results from the AI ​​and generates a feedback message.

[0317] Step 18:

[0318] The emotion engine reassess the user's emotional state and adjusts the presentation and tone of the feedback message.

[0319] Step 19:

[0320] The server sends the generated feedback message to the terminal.

[0321] Step 20:

[0322] The terminal displays a feedback message to the user.

[0323] Example 2

[0324] 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."

[0325] In conventional learning systems, although users can select the subject, category, and difficulty level of the questions, it is difficult to adjust the content of the questions according to the user's emotional state or to provide real-time feedback.In addition, it is difficult to provide questions of an appropriate difficulty level for users with a certain level of knowledge, which leads to problems that reduce learning efficiency.

[0326] 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.

[0327] In this invention, the server includes an input means for a user to specify the field, category, and difficulty level of a question, an artificial intelligence engine for generating questions based on the specified information, an output means for providing the generated questions and their answers to the user, an evaluation means for evaluating the answers input by the user and generating feedback, and an emotion engine for recognizing the user's emotions and adjusting the content of the questions based on the emotions, thereby maximizing the user's learning efficiency and improving each individual learning experience.

[0328] An "input means" is a device or interface that allows a user to specify the field, category, and difficulty level of a question.

[0329] An "artificial intelligence engine" is a computer program or system for generating questions based on specified information.

[0330] An "output means" is a device or mechanism for displaying or providing the generated questions and their solutions to the user.

[0331] An "evaluation means" is a device or system for evaluating answers entered by a user and generating feedback.

[0332] An "emotion engine" is a system or program that recognizes the user's emotions and adjusts the content and difficulty of the questions based on those emotions.

[0333] The "means for randomly selecting and providing" is a device or system for randomly selecting a question from a plurality of generated questions and providing it to the user.

[0334] "Automatic adjustment means" is a mechanism for automatically changing the difficulty of questions based on the user's knowledge level and emotional state.

[0335] MODE FOR CARRYING OUT THE INVENTION

[0336] This automatic problem generation system begins when a user uses a terminal to specify the problem's field, category, and difficulty level. The terminal's user interface (UI) allows selection using drop-down menus and text fields. The user selects the desired field (e.g., mathematics), category (e.g., algebra), and difficulty level (e.g., intermediate), and then presses the "Generate" button to complete these settings.

[0337] The device sends the configuration data selected by the user to the server. Specifically, the data is sent via an HTTP request. The server passes the received data to the AI ​​problem generation engine. The AI ​​problem generation engine generates problems based on the specified conditions. This process uses natural language processing and machine learning techniques. An example of a generated problem is "Factorize $x^2 + 5x + 6 = 0$." An example of a generated answer is "$(x + 2)(x + 3)$."

[0338] The server sends the generated questions and answers to the user's device. The device displays the received questions on the user interface. The user looks at the displayed questions and enters their answers. Specifically, the user enters "(x + 2)(x + 3)" in the text box and presses the "Submit" button.

[0339] The device sends the answer entered by the user to the server. The server evaluates the answer using an evaluation method. The evaluation method uses AI to determine whether the answer is correct or incorrect. The server generates a feedback message based on the evaluation result and sends it to the device. For example, if the user enters the correct answer, it displays "That's right, well done!"

[0340] Furthermore, the emotion engine evaluates the user's emotions in real time. Using data collected from the device's camera and microphone, it detects when the user is under high stress. Based on the results of this detection, the emotion engine adjusts the difficulty and timing of questions.

[0341] The system is also regularly updated on the backend. As new content and information is added, new questions can be generated based on that content. The emotion engine is also updated based on the latest data, improving the accuracy of user emotion recognition.

[0342] Here are some examples of prompts to input to the generative AI model:

[0343] "Generate problems in the following areas: mathematics, category: algebra, difficulty: intermediate."

[0344] Through this process, users can solve problems of appropriate difficulty and receive real-time feedback. The emotional engine adjusts the questions to reduce the burden on users and maximize learning efficiency.

[0345] keyword:

[0346] Generative AI model, prompt sentence

[0347] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0348] Step 1:

[0349] A user accesses the problem generation system using a terminal. The interface allows the user to select a subject (e.g., mathematics), a category (e.g., algebra), and a difficulty level (e.g., intermediate) using drop-down menus and text fields. Once the user has completed these entries, they press the "Generate" button. This action confirms the selected configuration data.

[0350] Step 2:

[0351] The device sends the user-selected setting data (field, category, difficulty level) to the server. Specifically, the data is sent using an HTTP request. The server receives and analyzes this data. The input is the setting data, and the output is the analyzed setting data.

[0352] Step 3:

[0353] The server passes the analyzed data to an AI problem generation engine. This engine generates questions and answers based on the specified conditions. The generation process uses natural language processing and machine learning algorithms. Specific data processing involves generating questions and their solutions (e.g., "Factorize $x^2 + 5x + 6 = 0$" and "$(x + 2)(x + 3)$"). The input is the analyzed configuration data, and the output is the generated questions and answers.

[0354] Step 4:

[0355] The server sends the generated questions and answers to the user's terminal. The terminal receives this data and displays the questions on a user interface. The display format is a text question and answer input field. The input is the generated question and answer, and the output is the displayed question.

[0356] Step 5:

[0357] The user checks the displayed question and enters the answer. Specifically, the user enters the answer (e.g., "(x + 2)(x + 3)") in the text box and presses the "Submit" button. This operation confirms the answer data. The input is the user's answer, and the output is the confirmed answer data.

[0358] Step 6:

[0359] The terminal sends the answer data entered by the user to the server. The sending method is usually an HTTP request. The server receives this data and analyzes it. The input is the user's answer data, and the output is the analyzed answer data.

[0360] Step 7:

[0361] The server evaluates the analyzed answer data using an evaluation means. Specifically, an AI model is used. It determines whether the answer is correct or incorrect and generates a feedback message based on the evaluation result. For example, feedback such as "That's correct, well done!" is generated. The input is the analyzed answer data, and the output is the feedback message.

[0362] Step 8:

[0363] The server sends the generated feedback message to the terminal. The terminal receives this message and displays it on the user interface. Specifically, the feedback is displayed in text format. The input is the feedback message, and the output is the displayed feedback message.

[0364] Step 9:

[0365] The emotion engine analyzes sensor data collected from the camera and microphone on the user's device. It evaluates the user's emotional state (e.g., stress, concentration) in real time and sends it to the server. The input is the sensor data, and the output is the evaluated emotional state data.

[0366] Step 10:

[0367] The server adjusts the difficulty and timing of questions based on the emotional state data. For example, if the user is in a high stress state, the settings are changed to present relatively easy questions. The input is the emotional state data, and the output is the adjusted question settings.

[0368] (Application example 2)

[0369] 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."

[0370] This invention relates to an automatic question generation system, and in particular to a system that enables flexible question generation and feedback that responds to the user's emotional state. Conventional question generation systems do not take into account the user's emotions or stress level, which can be burdensome for some users and discourage them from learning. Therefore, the objective of this system is to provide a more effective learning experience by recognizing the user's emotions in real time and appropriately adjusting the content and difficulty of the questions.

[0371] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes input means for the user to specify the field, category, and difficulty level of the question, an artificial intelligence engine for generating questions based on the specified information, output means for providing the generated questions and their answers to the user, evaluation means for evaluating the answers entered by the user and generating feedback, and emotion recognition means for recognizing the user's emotions in real time and adjusting the content of the questions based on that. This makes it possible to provide appropriate questions and feedback according to the emotional state of each user.

[0372] "Input means" refers to the method and device by which a user specifies the field, category, and difficulty level of a question.

[0373] "Artificial intelligence engine" refers to a computer program or algorithm for generating questions based on specified information.

[0374] "Output means" refers to a method and device for providing the generated questions and their answers to the user.

[0375] "Evaluation means" refers to the methods and algorithms for evaluating user-entered answers and generating feedback.

[0376] "Emotion recognition means" refers to a method and device for recognizing a user's emotions in real time and adjusting the content of questions based on that.

[0377] "Means for generating multiple questions" refers to methods and algorithms for creating a certain number of questions or more based on information specified by the user.

[0378] "Means for randomly selecting and providing" refers to methods and algorithms for randomly selecting from a plurality of generated questions and presenting them to the user.

[0379] "Means for automatically adjusting difficulty" refers to methods and algorithms for varying the difficulty of questions depending on the user's emotional state and knowledge level.

[0380] To implement this invention, a server, a user terminal, and a series of software modules are required. This invention mainly uses the following hardware and software:

[0381] Hardware

[0382] Server: A computer that receives user-specified information, generates questions using an artificial intelligence engine, and processes emotion recognition data.

[0383] User device: A device that is directly operated by the user, such as a smartphone or smart glasses. It is equipped with a camera and microphone and is used to acquire emotion recognition data.

[0384] software

[0385] Artificial Intelligence Engine: A program that generates questions based on user-specified subject areas, categories, and difficulty levels.

[0386] Emotion recognition engine: A module that analyzes the user's sensor data acquired through the camera and microphone and recognizes their emotional state.

[0387] Feedback generation module: A program that evaluates the answers entered by the user and generates appropriate feedback.

[0388] Specific technologies used include Python, OpenCV, and emotion recognition libraries (e.g., EmotionRecognizer).

[0389] System Operation

[0390] 1. User Input: The user accesses the system using a terminal and selects the subject, category, and difficulty level of the problem using drop-down menus and text fields. Once the selection is complete, the user presses the "Generate" button to send the input information to the server.

[0391] 2. Question generation: Based on the user's settings information received by the server, the AI ​​engine generates appropriate questions. The generated questions and answers are sent from the server to the user's device.

[0392] 3. Emotion recognition: The camera and microphone on the user's device capture the user's emotional data in real time and send it to the server, where the server's emotion recognition engine analyzes the data and determines the user's emotional state.

[0393] 4. Question Adjustment and Answer Evaluation: The difficulty and content of questions are adjusted based on the user's emotional state and presented to the user. When the user enters an answer, the answer is sent to the server and evaluated. Feedback is generated based on the evaluation results and displayed on the user's device.

[0394] Specific examples

[0395] For example, if a user selects the "Food category, easy level," they will be presented with a quiz like this: "Which country does this food originate from?" After the user answers, if the emotion recognition engine detects a stressed state, the difficulty of the next question will automatically decrease. Feedback will also include a message like "You got it right! Would you like to try the next question?"

[0396] Prompt Sentence Examples

[0397] "Generate quizzes at an easy level for food categories and assess customer answers in real time. Also, use emotion recognition to lower the difficulty of the next quiz if the customer is highly stressed."

[0398] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0399] Step 1:

[0400] A user accesses the system using a terminal and selects the field, category, and difficulty level from a drop-down menu or text field. The field, category, and difficulty level are entered as input data on the terminal, and the data is sent to the server.

[0401] Step 2:

[0402] The server instructs the AI ​​engine to generate questions based on the received user settings. The AI ​​engine processes the input data and generates questions and answers based on the specified information. The generated questions and answers are stored on the server.

[0403] Step 3:

[0404] The server sends the generated questions and answers to the user's terminal. The terminal displays the received questions, and the user deciphers the questions. The displayed questions appear on the user's terminal as output data.

[0405] Step 4:

[0406] The user inputs the answer through the terminal and presses the "Send" button. The input answer is sent from the terminal to the server.

[0407] Step 5:

[0408] The server passes the received answers to the evaluation means, which then judges whether the answers are correct or incorrect. Data processing involves comparing the input answers with the correct answer data and generating an evaluation result (correct, incorrect, etc.). The evaluation result is returned to the server.

[0409] Step 6:

[0410] The server generates a feedback message based on the evaluation result and sends the feedback to the user terminal, which displays the feedback message to inform the user of the result. The feedback message appears on the user terminal as output data.

[0411] Step 7:

[0412] The camera and microphone on the user's device capture the user's emotional data in real time and transmit the data to the server. Image data and voice data are sent as input data to the server.

[0413] Step 8:

[0414] The emotion recognition engine on the server analyzes the received emotion data and recognizes the user's emotional state (e.g., stress, concentration, etc.). As data processing, the emotion recognition model classifies the emotion data and generates a result. The emotion recognition result is stored on the server.

[0415] Step 9:

[0416] The server adjusts the difficulty and content of the next question based on the emotion recognition results. The adjusted question is regenerated by the AI ​​engine and sent to the server. The adjusted new question is stored on the server as output data.

[0417] Step 10:

[0418] The server sends the adjusted problem back to the user terminal, and the terminal presents the new problem to the user. The adjusted new problem is displayed on the user terminal as output data.

[0419] The above steps realize a system that presents appropriate questions and feedback according to the user's emotional state and setting information.

[0420] 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.

[0421] 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.

[0422] 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.

[0423] [Second embodiment]

[0424] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0425] 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.

[0426] 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).

[0427] 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.

[0428] 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.

[0429] 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).

[0430] 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.

[0431] 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.

[0432] 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.

[0433] 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.

[0434] 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.

[0435] 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."

[0436] System Configuration Overview

[0437] This automatic question generation system consists of an input means for a user to specify the field, category, and difficulty level of the question, an artificial intelligence engine that generates questions based on this information, an output means for providing the generated questions and their answers, and an evaluation means for evaluating the answers entered by the user and providing feedback.

[0438] Specific implementation methods of the system

[0439] User Interface (UI)

[0440] The user accesses the problem generation system using a terminal. The interface allows the user to select the subject (e.g., mathematics, science), category (e.g., algebra, physics), and difficulty level (e.g., beginner, intermediate, advanced) using drop-down menus and text fields. Once the user completes these entries, they press the "Generate" button.

[0441] Server-side processing

[0442] The device sends the user's setting data (field, category, difficulty level) to the server. The server receives this data and instructs the AI ​​engine to generate questions. The AI ​​engine generates appropriate questions based on the specified field, category, and difficulty level.

[0443] AI problem generation engine

[0444] The AI ​​problem generation engine receives instructions from the server and generates problems as follows:

[0445] 1. Question structure

[0446] 2. Generating answers to problems

[0447] Examples:

[0448] Problem: Factor x^2 + 5x + 6 = 0.

[0449] Answer: (x + 2)(x + 3)

[0450] The generated questions and answers are sent back to the server, which then transmits them to the user's terminal.

[0451] Display and answer input

[0452] The user's device displays the generated questions. The user looks at the questions and enters their answers into the interface. Once the input is complete, the user presses the "Submit" button.

[0453] Answer evaluation and feedback

[0454] The device sends the answer entered by the user to the server. The server has the AI ​​evaluate the answer. The AI ​​evaluates the answer and determines whether it is correct or incorrect. Based on the evaluation result, the server generates a feedback message, which is sent back to the device and displayed to the user.

[0455] Examples:

[0456] If the user answers "(x + 2)(x + 3)" and it is evaluated as correct, the feedback message displayed is "Correct, well done!". If the user answers "(x + 3)(x + 2)", it is also evaluated as correct and the feedback message displayed is "Correct, well done!".

[0457] Update function

[0458] The system is regularly updated on the backend, so that questions are generated based on new content or information added to a field or category. The AI ​​also continuously updates its question generation algorithm based on the latest learning data.

[0459] Improved feedback accuracy

[0460] If the user enters an incorrect answer, the AI ​​provides detailed feedback explaining why the answer is incorrect, including steps and references to the correct answer.

[0461] In this way, the system can continuously provide learners with questions that best suit their needs, and seamlessly generate questions, evaluate answers, and provide feedback.

[0462] The processing flow will be explained below.

[0463] Step 1:

[0464] The user accesses the question generation system on the terminal and opens the setting screen.

[0465] Step 2:

[0466] The user selects the field, category, and difficulty level and presses the "Generate" button.

[0467] Step 3:

[0468] The device collects data on the user's selected field, category, and difficulty level.

[0469] Step 4:

[0470] The terminal transmits the collected setting data to the server.

[0471] Step 5:

[0472] The server analyzes the received configuration data and issues instructions to the AI ​​problem generation engine to generate problems.

[0473] Step 6:

[0474] The AI ​​question generation engine generates questions and answers based on specified conditions.

[0475] Step 7:

[0476] The server receives questions and answers generated by the AI ​​question generation engine.

[0477] Step 8:

[0478] The server transmits the generated question data to the terminal.

[0479] Step 9:

[0480] The terminal displays the problem to the user.

[0481] Step 10:

[0482] The user solves the problem, enters the answer into the terminal interface, and presses the "Submit" button.

[0483] Step 11:

[0484] The terminal collects the answers entered by the user.

[0485] Step 12:

[0486] The terminal sends the collected answers to the server.

[0487] Step 13:

[0488] The server issues instructions to the AI ​​to evaluate the received answers.

[0489] Step 14:

[0490] AI evaluates the user's answers and determines whether they are correct or incorrect.

[0491] Step 15:

[0492] The server receives the evaluation results from the AI ​​and generates a feedback message.

[0493] Step 16:

[0494] The server sends the generated feedback message to the terminal.

[0495] Step 17:

[0496] The terminal displays a feedback message to the user.

[0497] Example 1

[0498] 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."

[0499] Conventional automatic problem generation systems have limited functionality for generating appropriate problems based on user settings, and providing evaluation and feedback on answers, making them unable to fully meet users' learning needs. In particular, it has been difficult to provide detailed feedback on the answers entered by users, or to automatically update problems based on new data.

[0500] 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.

[0501] In this invention, the server includes an input means for a user to specify the field, category, and difficulty level of a question, an artificial intelligence engine for generating questions based on the specified information, and an output means for providing the generated questions and their answers to the user. This allows the user to specify specialized questions tailored to their learning needs and have their answers evaluated. The server also includes a data storage means for receiving and storing data transmitted from the user's device, a means for generating feedback messages from the artificial intelligence engine that evaluates the data and generates feedback and returning the feedback messages to the user's device, an update means for generating corresponding questions when new data is added to a specific field or category, and a means for providing feedback in detail explaining why the user's answer is incorrect when the user enters an incorrect answer. This allows the user to continuously progress in their learning through detailed feedback and updated questions, significantly improving their learning effectiveness.

[0502] The "input means" is a means for providing an interface for a user to specify the field, category, and difficulty level of a question.

[0503] An "artificial intelligence engine" is a program or system that generates questions and their answers based on specified information.

[0504] "Output means" refers to a display device or transmission means for providing the generated questions and their answers to the user.

[0505] An "evaluator" is a program or mechanism for evaluating answers entered by a user and generating feedback.

[0506] The "data storage means" is a storage device or database for receiving and storing data sent from the user's terminal at the server.

[0507] The "feedback message generating means" is a program or system for generating a feedback message from an artificial intelligence engine that evaluates data and generates feedback, and returning this to the user terminal.

[0508] An "updater" is a mechanism or program that generates questions corresponding to new data added to a particular field or category.

[0509] A "feedback providing means" is a program or system that, when a user enters an incorrect answer, provides feedback that explains in detail why the answer is incorrect.

[0510] MODE FOR CARRYING OUT THE INVENTION

[0511] System Configuration

[0512] The automatic question generation system of the present invention comprises an input means for a user to specify the field, category, and difficulty level of a question, an artificial intelligence engine for generating questions based on the specified information, an output means for providing the generated questions and their answers to the user, and an evaluation means for evaluating the answers entered by the user and generating feedback.

[0513] User Interface (UI)

[0514] A user accesses the automated problem generation system using a terminal. The interface includes drop-down menus and text fields that allow the user to specify the subject (e.g., mathematics, science), category (e.g., algebra, physics), and difficulty level (e.g., beginner, intermediate, advanced). Once the user completes the settings, they press a "Generate" button, which triggers the input mechanism.

[0515] Sending and Receiving Data

[0516] The user's terminal sends the setting data (field, category, difficulty level) to the server. The server receives this and stores it in the data storage means. This data will be used in the next step of the process.

[0517] Question generation instructions

[0518] The server analyzes the received data and instructs the AI ​​engine to generate questions and answers based on the specified field, category, and difficulty level.

[0519] Specifically, the problem is generated using the following steps:

[0520] 1. Question structure

[0521] 2. Generating answers to problems

[0522] As a concrete example, generate the following problem and its solution:

[0523] Problem: Factor x^2 + 5x + 6 = 0.

[0524] Answer:(x + 2)(x + 3)

[0525] Providing questions and answers

[0526] The generated questions and answers are sent back to the server, which then sends them to the user's terminal and provides them to the user, who then displays the questions on the user's terminal.

[0527] Enter answers to questions and submit

[0528] The user thinks of an answer to the displayed question and enters it into the interface. After entering the answer and pressing the "Send" button, the terminal sends the answer data to the server.

[0529] Answer evaluation and feedback

[0530] The server passes the received answer data to an AI engine, which evaluates the answer, determines whether it is correct, and generates a feedback message.

[0531] Specifically, it generates feedback like this:

[0532] If you get it right: "That's right, well done!"

[0533] Incorrect answer: "Sorry, you're wrong. The correct answer is (x + 2)(x + 3)."

[0534] The feedback message is sent from the server to the terminal and displayed to the user.

[0535] Improved update functionality and feedback

[0536] The system is regularly updated in the backend, and questions are generated accordingly as new data is added. Additionally, if a user enters an incorrect answer, feedback is provided detailing the error.

[0537] Specific examples of prompts to input to generative AI models

[0538] Below are some examples of prompts that can be used to generate questions:

[0539] "Generate problems for factoring quadratic equations at an elementary level in mathematics."

[0540] "Generate intermediate level physics problems related to mechanics."

[0541] This allows the system to provide optimal questions tailored to the user's learning needs, and by evaluating and providing feedback on answers, it can improve learning effectiveness.

[0542] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0543] Step 1: User specifies the problem

[0544] The user uses a terminal to access the interface of the automatic question generation system. The interface displays drop-down menus and text fields for selecting the field, category, and difficulty level. The user uses these to input the desired question settings. Once the input is complete, the user presses the "Generate" button. The input here is the field, category, and difficulty level, and the output is the user-selected setting data.

[0545] Step 2: Send data from the device to the server

[0546] The device sends the setting data (field, category, difficulty) entered by the user to the server via an HTTP request. The input is the setting data, and the output is a confirmation that the data was successfully sent to the server. At this time, the device displays an indicator indicating that the sending process is in progress.

[0547] Step 3: Server receives and analyzes data

[0548] The server receives the setting data sent from the terminal. This data is stored in the server's data storage means. The server then analyzes the received data and determines which field, category, and level of difficulty to generate questions for. The input is the received data, and the output is the analysis results.

[0549] Step 4: Submitting the question generation instructions

[0550] The server issues instructions to the AI ​​engine for generating questions based on the analysis results. These instructions include the field, category, and difficulty level. The server passes this configuration data to the AI ​​engine as a prompt. The input is the analysis results, and the output is instructions for generating questions.

[0551] Step 5: Generate questions using the AI ​​question generation engine

[0552] Based on the prompt received from the server, the AI ​​engine generates a problem and answer that meets the specified conditions. Specifically, it creates the structure of the problem and the corresponding answer. For example, in the field of mathematics, it generates a problem such as "factorize x^2 + 5x + 6 = 0" and its answer "(x + 2)(x + 3)". The input is the problem generation instruction, and the output is the generated problem and answer.

[0553] Step 6: Sending the generated data back to the server

[0554] The AI ​​engine sends the generated questions and answers back to the server. The server temporarily stores the received data. The input is the generated questions and answers, and the output is the receipt of the data by the server.

[0555] Step 7: Sending data from the server to the device

[0556] The server sends the generated questions and answers to the user's device. The data is sent using an HTTP response. The input is the questions and answer data stored on the server, and the output is a confirmation that the data was successfully sent to the device.

[0557] Step 8: User enters answer

[0558] The generated question is displayed on the terminal, and the user inputs the answer to the question into the interface. When input is complete, the user presses the "Submit" button. The input is the user's answer, and the output is the answer data ready for transmission.

[0559] Step 9: Send the answer from the device to the server

[0560] The terminal sends the answer entered by the user to the server via an HTTP request. The input is the user's answer data, and the output is a confirmation that the data was successfully sent to the server.

[0561] Step 10: Server evaluates the answer

[0562] The server passes the received answer data to an AI engine, which evaluates the answer. The AI ​​engine determines whether the answer is correct and generates an appropriate feedback message. The input is the user's answer data, and the output is the evaluation result and feedback message.

[0563] Step 11: Returning evaluation results and feedback

[0564] The server generates a feedback message and sends it to the user's device. The feedback includes whether the answer is correct or incorrect, and if incorrect, the reason for the error. The input is the evaluation result and the feedback message, and the output is a confirmation of successful data transmission to the device.

[0565] Step 12: Viewing feedback

[0566] The user's device displays the received feedback message on the interface. For example, messages such as "That's right, well done!" or "Sorry, you're wrong. The correct answer is (x + 2)(x + 3)" are displayed. The input is the feedback message, and the output is the feedback display to the user.

[0567] (Application example 1)

[0568] 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."

[0569] Currently, many brick-and-mortar store staff are required to undergo regular training on product knowledge and customer service skills, but the content is uniform, making it difficult to provide questions tailored to each staff member's knowledge level and required skills. Furthermore, previous training methods make it difficult to immediately evaluate staff answers and provide appropriate feedback. Therefore, it is necessary to provide an efficient training method that meets the needs of each individual staff member.

[0570] 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.

[0571] In this invention, the server includes an input means for a user to specify the field, category, and difficulty of a question, an artificial intelligence engine for generating questions based on the specified information, an output means for providing the generated questions and their answers to the user, an evaluation means for evaluating the answers input by the user and generating feedback, and a means for automatically generating and evaluating training and educational questions for staff. This makes it possible to efficiently provide questions tailored to the knowledge level and required skills of each staff member and to provide immediate feedback on the answers.

[0572] "Input means for the user to specify the field, category, and difficulty level of the problem" refers to an interface means for the user to specify information about the training or educational problem, and includes menus and input fields for selecting the field, category, and difficulty level.

[0573] An "artificial intelligence engine for generating questions based on specified information" is an artificial intelligence-based computer program for automatically generating appropriate training or educational questions based on subject, category, and difficulty information entered by a user.

[0574] "Output means for providing the generated questions and their answers to the user" refers to means for displaying or providing the questions and their answers generated by the artificial intelligence engine on the user's device, including the display of a smartphone or the screen of an application.

[0575] The "evaluation means for evaluating the answer entered by the user and generating feedback" refers to a program or algorithm that analyzes the answer entered by the user, determines whether it is correct or not, and provides feedback.

[0576] "Means for automatically generating and evaluating staff training and educational questions" refers to the overall system functionality for automatically generating training and educational questions for store staff using artificial intelligence and evaluating the answers.

[0577] "Efficient delivery with immediate feedback on answers" refers to the entire process of generating quick and appropriate training questions based on user-specified information, and then instantly evaluating and providing feedback on the answers provided by the user.

[0578] "Server" refers to a central computer or similar facility that performs various processes, such as generating questions, evaluating answers, and providing feedback, in practicing the invention.

[0579] overview

[0580] This invention is a system for automatically generating training and educational questions for store staff, evaluating the answers, and providing immediate feedback. The system consists of the following components: user input, question generation, answer evaluation, and feedback provision.

[0581] Hardware and Software Configuration

[0582] Hardware used

[0583] Smartphone: A device through which a user accesses an application.

[0584] Server: A central computer that performs question generation and evaluation functions and manages various data.

[0585] Software used

[0586] Programming language: Develop applications in Swift (for iOS) and Kotlin (for Android).

[0587] Framework: Uses Firebase for real-time database and serverless functions.

[0588] Generative AI model: We will use TensorFlow to implement the artificial intelligence model required for question generation and evaluation.

[0589] System Operation

[0590] User Input

[0591] Users access the application using their smartphones and enter information into the interface to select a training category (e.g., product knowledge, customer service skills) and difficulty level (beginner, intermediate, advanced). After entering the required information, the user presses the "Generate" button.

[0592] Problem generation

[0593] The server receives the user's input data (area, category, difficulty level) and issues question generation instructions to the generative AI model. The AI ​​model generates appropriate training questions based on the specified information. For example, an intermediate question on customer service skills might be, "How would you respond if a customer complained about a returned product?"

[0594] Providing problems

[0595] The generated questions and their answers are sent from the server to the user's smartphone, which displays the questions on an interface and allows the user to enter the answers.

[0596] Answer evaluation

[0597] When a user enters an answer and presses the "Submit" button, the answer is sent to the server. The server evaluates the answer using a generative AI model and determines whether it is correct. For example, if a user answers, "First, listen to the customer's story to the end, show empathy, and then quickly process the return," the AI ​​will determine this as the correct answer.

[0598] Providing Feedback

[0599] Based on the evaluation results, the server generates a feedback message and sends it to the user's smartphone. If the answer is correct, it displays "That's right, well done!", and if the answer is incorrect, it provides appropriate corrections and instructions for solving the problem.

[0600] Examples and prompts

[0601] Specific examples

[0602] For example, if a user selects "Intermediate" when generating training questions for customer service skills:

[0603] Problem: How do you respond when a customer complains about a return?

[0604] AI-generated answer (example): First, listen to the customer's story thoroughly, show empathy, and then quickly process the return.

[0605] Prompt example

[0606] Please generate training questions that meet the following criteria:

[0607] Category: Customer Service Skills

[0608] Difficulty: Intermediate

[0609] Problem Statement: How would you respond if a customer complained about a return?

[0610] Sample answer: First, listen to the customer thoroughly, show empathy, and then process the return promptly.

[0611] As described above, by clearly indicating the specific system configuration and processing content for implementing the invention, it is shown that the invention functions effectively in training staff in brick-and-mortar stores.

[0612] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0613] Step 1:

[0614] The user launches the application on their smartphone and selects a training category (e.g., product knowledge, customer service skills) and difficulty level (beginner, intermediate, advanced). After entering this information and pressing the "Generate" button, the device sends the input data to the server.

[0615] Input: Category and difficulty information

[0616] Output: Send category and difficulty selection data to the server

[0617] Step 2:

[0618] The server receives the selection data sent from the device and passes it to the generative AI model, which then generates appropriate training questions based on the specified information.

[0619] Input: Category and difficulty selection data

[0620] Output: Generated problem data

[0621] Step 3:

[0622] The server receives the generated question data and sends it to the user's smartphone, which displays the received question data on its interface and allows the user to enter answers.

[0623] Input: Generated problem data

[0624] Output: Problem displayed in terminal

[0625] Step 4:

[0626] When the user inputs an answer to the displayed question and presses the "Send" button, the terminal transmits the input answer data to the server.

[0627] Input: User's answer data

[0628] Output: Send answer data to the server

[0629] Step 5:

[0630] The server receives the user's answer data, passes it to the generative AI model, and evaluates the answer. The generative AI model determines whether the answer is correct or incorrect and returns the result to the server.

[0631] Input: User's answer data

[0632] Output: Evaluation result (correct / incorrect)

[0633] Step 6:

[0634] The server generates a feedback message based on the evaluation results and sends it to the user's smartphone, which then displays the feedback message on its interface.

[0635] Input: Evaluation result

[0636] Output: Generate and display feedback messages

[0637] Specific actions

[0638] Step 1

[0639] The user selects a category (e.g., customer service skills) and difficulty level (intermediate) in the application and presses the "Generate" button. The device converts the selected data into JSON format and sends it to the server as an HTTPS request.

[0640] Step 2

[0641] The server analyzes the received request, extracts data on the category and difficulty level, and inputs a prompt (e.g., "Customer service skills, intermediate") to the AI ​​model to instruct it to generate questions. The AI ​​model then generates appropriate questions and returns the data to the server.

[0642] Step 3

[0643] The server receives the generated problem data and sends it in JSON format to the user's device. The device displays the received problem on the interface, for example, "If a customer complains about a returned product, how would you respond?"

[0644] Step 4

[0645] The user enters the answer to the question (e.g., "First, listen to the customer's story until the end, show empathy, and then quickly process the return.") and presses the "Submit" button. The device converts the entered answer data into JSON format and sends it to the server as an HTTPS request.

[0646] Step 5

[0647] The server analyzes the received answer data and issues evaluation instructions to the generating AI model. The AI ​​model determines whether the answer is correct and returns an evaluation result, such as determining that the answer is "correct."

[0648] Step 6

[0649] The server generates a feedback message (e.g., "That's right, well done!") based on the evaluation result and sends it to the user's device in JSON format. The device then displays the feedback message on its interface for the user to see.

[0650] In this way, the present invention provides efficient and relevant training to users and provides immediate feedback on their answers.

[0651] 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.

[0652] System Configuration Overview

[0653] This automatic question generation system includes an input means for a user to specify the field, category, and difficulty level of the question, an artificial intelligence engine that generates questions based on this information, an output means for providing the generated questions and their answers, an evaluation means for evaluating the answers entered by the user and providing feedback, and an emotion engine that recognizes the user's emotions and adjusts the content of the questions based on them.

[0654] Specific implementation methods of the system

[0655] User Interface (UI)

[0656] The user accesses the problem generation system using a terminal. The interface allows the user to select the subject (e.g., mathematics, science), category (e.g., algebra, physics), and difficulty level (e.g., beginner, intermediate, advanced) using drop-down menus and text fields. Once the user completes these entries, they press the "Generate" button.

[0657] Server-side processing

[0658] The device sends the user's setting data (field, category, difficulty level) to the server. The server receives this data and instructs the AI ​​problem generation engine to generate questions. Based on the specified field, category, and difficulty level, the AI ​​engine generates appropriate questions.

[0659] AI problem generation engine

[0660] The AI ​​problem generation engine receives instructions from the server and generates questions and answers. For example, it generates questions as follows:

[0661] Problem: Factor $x^2 + 5x + 6 = 0$.

[0662] Answer: $(x + 2)(x + 3)$

[0663] The generated questions and answers are sent back to the server, which then transmits them to the user's terminal.

[0664] Emotional engine regulation

[0665] The emotion engine uses sensor data from the device's camera, microphone, and other devices to recognize the user's emotions (e.g., stress, fatigue, concentration) in real time. After the emotion engine evaluates the user's emotional state, it adjusts the difficulty and timing of questions based on the results.

[0666] As a specific example, if the user is determined to be in a high stress state, the emotion engine will lower the difficulty of the questions, thereby reducing the burden on the user.

[0667] Display and answer input

[0668] The user's device displays the generated questions. The user looks at the questions and enters their answers into the interface. Once the input is complete, the user presses the "Submit" button.

[0669] Answer evaluation and feedback

[0670] The device sends the answer entered by the user to the server. The server has the AI ​​evaluate the answer. The AI ​​evaluates the answer and determines whether it is correct or incorrect. Based on the evaluation result, the server generates a feedback message, which is sent back to the device and displayed to the user.

[0671] For example, if the user answers "(x + 2)(x + 3)" and this is evaluated as correct, the feedback message displayed will be "Correct, well done!". Also, if the user answers "(x + 3)(x + 2)", this will also be evaluated as correct and the feedback message displayed will be "Correct, well done!".

[0672] Update function

[0673] The system is regularly updated in the backend, especially when new content or information is added to a field or category, so that corresponding questions are generated. The emotion engine is also updated based on the latest data, continuously improving the accuracy of user emotion recognition.

[0674] Improved feedback accuracy

[0675] If the user enters an incorrect answer, the AI ​​provides detailed feedback explaining why the answer is incorrect, including steps and references to the correct answer. The emotional engine also adjusts the tone and content of the feedback appropriately, taking into account the user's emotional state.

[0676] In this way, the system maximizes users' learning efficiency and enhances their learning experience by seamlessly generating questions, evaluating answers, providing feedback, and adjusting to the user's emotions.

[0677] The processing flow will be explained below.

[0678] Step 1:

[0679] The user accesses the question generation system on the terminal and opens the setting screen.

[0680] Step 2:

[0681] The user selects the field, category, and difficulty level and presses the "Generate" button.

[0682] Step 3:

[0683] The device collects data on the user's selected field, category, and difficulty level.

[0684] Step 4:

[0685] The device sends the sensor data for the emotion engine to the server along with the configuration data collected.

[0686] Step 5:

[0687] The server analyzes the received configuration data and issues instructions to the AI ​​problem generation engine to generate problems.

[0688] Step 6:

[0689] The emotion engine analyzes sensor data from the device (e.g., camera footage and audio data) and evaluates the user's emotional state.

[0690] Step 7:

[0691] The AI ​​question generation engine generates questions and answers based on specified conditions.

[0692] Step 8:

[0693] The server receives questions and answers generated by the AI ​​question generation engine.

[0694] Step 9:

[0695] Based on the evaluation results of the emotion engine, the server adjusts the difficulty level of the questions and the timing of questions.

[0696] Step 10:

[0697] The server transmits the generated question data to the terminal.

[0698] Step 11:

[0699] The terminal displays the problem to the user.

[0700] Step 12:

[0701] The user solves the problem, enters the answer into the terminal interface, and presses the "Submit" button.

[0702] Step 13:

[0703] The terminal collects the answers entered by the user.

[0704] Step 14:

[0705] The terminal sends the collected answers to the server.

[0706] Step 15:

[0707] The server issues instructions to the AI ​​to evaluate the received answers.

[0708] Step 16:

[0709] AI evaluates the user's answers and determines whether they are correct or incorrect.

[0710] Step 17:

[0711] The server receives the evaluation results from the AI ​​and generates a feedback message.

[0712] Step 18:

[0713] The emotion engine reassess the user's emotional state and adjusts the presentation and tone of the feedback message.

[0714] Step 19:

[0715] The server sends the generated feedback message to the terminal.

[0716] Step 20:

[0717] The terminal displays a feedback message to the user.

[0718] Example 2

[0719] 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."

[0720] In conventional learning systems, although users can select the subject, category, and difficulty level of the questions, it is difficult to adjust the content of the questions according to the user's emotional state or to provide real-time feedback.In addition, it is difficult to provide questions of an appropriate difficulty level for users with a certain level of knowledge, which leads to problems that reduce learning efficiency.

[0721] 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.

[0722] In this invention, the server includes an input means for a user to specify the field, category, and difficulty level of a question, an artificial intelligence engine for generating questions based on the specified information, an output means for providing the generated questions and their answers to the user, an evaluation means for evaluating the answers input by the user and generating feedback, and an emotion engine for recognizing the user's emotions and adjusting the content of the questions based on the emotions, thereby maximizing the user's learning efficiency and improving each individual learning experience.

[0723] An "input means" is a device or interface that allows a user to specify the field, category, and difficulty level of a question.

[0724] An "artificial intelligence engine" is a computer program or system for generating questions based on specified information.

[0725] An "output means" is a device or mechanism for displaying or providing the generated questions and their solutions to the user.

[0726] An "evaluation means" is a device or system for evaluating answers entered by a user and generating feedback.

[0727] An "emotion engine" is a system or program that recognizes the user's emotions and adjusts the content and difficulty of the questions based on those emotions.

[0728] The "means for randomly selecting and providing" is a device or system for randomly selecting a question from a plurality of generated questions and providing it to the user.

[0729] "Automatic adjustment means" is a mechanism for automatically changing the difficulty of questions based on the user's knowledge level and emotional state.

[0730] MODE FOR CARRYING OUT THE INVENTION

[0731] This automatic problem generation system begins when a user uses a terminal to specify the problem's field, category, and difficulty level. The terminal's user interface (UI) allows selection using drop-down menus and text fields. The user selects the desired field (e.g., mathematics), category (e.g., algebra), and difficulty level (e.g., intermediate), and then presses the "Generate" button to complete these settings.

[0732] The device sends the configuration data selected by the user to the server. Specifically, the data is sent via an HTTP request. The server passes the received data to the AI ​​problem generation engine. The AI ​​problem generation engine generates problems based on the specified conditions. This process uses natural language processing and machine learning techniques. An example of a generated problem is "Factorize $x^2 + 5x + 6 = 0$." An example of a generated answer is "$(x + 2)(x + 3)$."

[0733] The server sends the generated questions and answers to the user's device. The device displays the received questions on the user interface. The user looks at the displayed questions and enters their answers. Specifically, the user enters "(x + 2)(x + 3)" in the text box and presses the "Submit" button.

[0734] The device sends the answer entered by the user to the server. The server evaluates the answer using an evaluation method. The evaluation method uses AI to determine whether the answer is correct or incorrect. The server generates a feedback message based on the evaluation result and sends it to the device. For example, if the user enters the correct answer, it displays "That's right, well done!"

[0735] Furthermore, the emotion engine evaluates the user's emotions in real time. Using data collected from the device's camera and microphone, it detects when the user is under high stress. Based on the results of this detection, the emotion engine adjusts the difficulty and timing of questions.

[0736] The system is also regularly updated on the backend. As new content and information is added, new questions can be generated based on that content. The emotion engine is also updated based on the latest data, improving the accuracy of user emotion recognition.

[0737] Here are some examples of prompts to input to the generative AI model:

[0738] "Generate problems in the following areas: mathematics, category: algebra, difficulty: intermediate."

[0739] Through this process, users can solve problems of appropriate difficulty and receive real-time feedback. The emotional engine adjusts the questions to reduce the burden on users and maximize learning efficiency.

[0740] keyword:

[0741] Generative AI model, prompt sentence

[0742] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0743] Step 1:

[0744] A user accesses the problem generation system using a terminal. The interface allows the user to select a subject (e.g., mathematics), a category (e.g., algebra), and a difficulty level (e.g., intermediate) using drop-down menus and text fields. Once the user has completed these entries, they press the "Generate" button. This action confirms the selected configuration data.

[0745] Step 2:

[0746] The device sends the user-selected setting data (field, category, difficulty level) to the server. Specifically, the data is sent using an HTTP request. The server receives and analyzes this data. The input is the setting data, and the output is the analyzed setting data.

[0747] Step 3:

[0748] The server passes the analyzed data to an AI problem generation engine. This engine generates questions and answers based on the specified conditions. The generation process uses natural language processing and machine learning algorithms. Specific data processing involves generating questions and their solutions (e.g., "Factorize $x^2 + 5x + 6 = 0$" and "$(x + 2)(x + 3)$"). The input is the analyzed configuration data, and the output is the generated questions and answers.

[0749] Step 4:

[0750] The server sends the generated questions and answers to the user's terminal. The terminal receives this data and displays the questions on a user interface. The display format is a text question and answer input field. The input is the generated question and answer, and the output is the displayed question.

[0751] Step 5:

[0752] The user checks the displayed question and enters the answer. Specifically, the user enters the answer (e.g., "(x + 2)(x + 3)") in the text box and presses the "Submit" button. This operation confirms the answer data. The input is the user's answer, and the output is the confirmed answer data.

[0753] Step 6:

[0754] The terminal sends the answer data entered by the user to the server. The sending method is usually an HTTP request. The server receives this data and analyzes it. The input is the user's answer data, and the output is the analyzed answer data.

[0755] Step 7:

[0756] The server evaluates the analyzed answer data using an evaluation means. Specifically, an AI model is used. It determines whether the answer is correct or incorrect and generates a feedback message based on the evaluation result. For example, feedback such as "That's correct, well done!" is generated. The input is the analyzed answer data, and the output is the feedback message.

[0757] Step 8:

[0758] The server sends the generated feedback message to the terminal. The terminal receives this message and displays it on the user interface. Specifically, the feedback is displayed in text format. The input is the feedback message, and the output is the displayed feedback message.

[0759] Step 9:

[0760] The emotion engine analyzes sensor data collected from the camera and microphone on the user's device. It evaluates the user's emotional state (e.g., stress, concentration) in real time and sends it to the server. The input is the sensor data, and the output is the evaluated emotional state data.

[0761] Step 10:

[0762] The server adjusts the difficulty and timing of questions based on the emotional state data. For example, if the user is in a high stress state, the settings are changed to present relatively easy questions. The input is the emotional state data, and the output is the adjusted question settings.

[0763] (Application example 2)

[0764] 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."

[0765] This invention relates to an automatic question generation system, and in particular to a system that enables flexible question generation and feedback that responds to the user's emotional state. Conventional question generation systems do not take into account the user's emotions or stress level, which can be burdensome for some users and discourage them from learning. Therefore, the objective of this system is to provide a more effective learning experience by recognizing the user's emotions in real time and appropriately adjusting the content and difficulty of the questions.

[0766] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes input means for the user to specify the field, category, and difficulty level of the question, an artificial intelligence engine for generating questions based on the specified information, output means for providing the generated questions and their answers to the user, evaluation means for evaluating the answers entered by the user and generating feedback, and emotion recognition means for recognizing the user's emotions in real time and adjusting the content of the questions based on that. This makes it possible to provide appropriate questions and feedback according to the emotional state of each user.

[0767] "Input means" refers to the method and device by which a user specifies the field, category, and difficulty level of a question.

[0768] "Artificial intelligence engine" refers to a computer program or algorithm for generating questions based on specified information.

[0769] "Output means" refers to a method and device for providing the generated questions and their answers to the user.

[0770] "Evaluation means" refers to the methods and algorithms for evaluating user-entered answers and generating feedback.

[0771] "Emotion recognition means" refers to a method and device for recognizing a user's emotions in real time and adjusting the content of questions based on that.

[0772] "Means for generating multiple questions" refers to methods and algorithms for creating a certain number of questions or more based on information specified by the user.

[0773] "Means for randomly selecting and providing" refers to methods and algorithms for randomly selecting from a plurality of generated questions and presenting them to the user.

[0774] "Means for automatically adjusting difficulty" refers to methods and algorithms for varying the difficulty of questions depending on the user's emotional state and knowledge level.

[0775] To implement this invention, a server, a user terminal, and a series of software modules are required. This invention mainly uses the following hardware and software:

[0776] Hardware

[0777] Server: A computer that receives user-specified information, generates questions using an artificial intelligence engine, and processes emotion recognition data.

[0778] User device: A device that is directly operated by the user, such as a smartphone or smart glasses. It is equipped with a camera and microphone and is used to acquire emotion recognition data.

[0779] software

[0780] Artificial Intelligence Engine: A program that generates questions based on user-specified subject areas, categories, and difficulty levels.

[0781] Emotion recognition engine: A module that analyzes the user's sensor data acquired through the camera and microphone and recognizes their emotional state.

[0782] Feedback generation module: A program that evaluates the answers entered by the user and generates appropriate feedback.

[0783] Specific technologies used include Python, OpenCV, and emotion recognition libraries (e.g., EmotionRecognizer).

[0784] System Operation

[0785] 1. User Input: The user accesses the system using a terminal and selects the subject, category, and difficulty level of the problem using drop-down menus and text fields. Once the selection is complete, the user presses the "Generate" button to send the input information to the server.

[0786] 2. Question generation: Based on the user's settings information received by the server, the AI ​​engine generates appropriate questions. The generated questions and answers are sent from the server to the user's device.

[0787] 3. Emotion recognition: The camera and microphone on the user's device capture the user's emotional data in real time and send it to the server, where the server's emotion recognition engine analyzes the data and determines the user's emotional state.

[0788] 4. Question Adjustment and Answer Evaluation: The difficulty and content of questions are adjusted based on the user's emotional state and presented to the user. When the user enters an answer, the answer is sent to the server and evaluated. Feedback is generated based on the evaluation results and displayed on the user's device.

[0789] Specific examples

[0790] For example, if a user selects the "Food category, easy level," they will be presented with a quiz like this: "Which country does this food originate from?" After the user answers, if the emotion recognition engine detects a stressed state, the difficulty of the next question will automatically decrease. Feedback will also include a message like "You got it right! Would you like to try the next question?"

[0791] Prompt Sentence Examples

[0792] "Generate quizzes at an easy level for food categories and assess customer answers in real time. Also, use emotion recognition to lower the difficulty of the next quiz if the customer is highly stressed."

[0793] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0794] Step 1:

[0795] A user accesses the system using a terminal and selects the field, category, and difficulty level from a drop-down menu or text field. The field, category, and difficulty level are entered as input data on the terminal, and the data is sent to the server.

[0796] Step 2:

[0797] The server instructs the AI ​​engine to generate questions based on the received user settings. The AI ​​engine processes the input data and generates questions and answers based on the specified information. The generated questions and answers are stored on the server.

[0798] Step 3:

[0799] The server sends the generated questions and answers to the user's terminal. The terminal displays the received questions, and the user deciphers the questions. The displayed questions appear on the user's terminal as output data.

[0800] Step 4:

[0801] The user inputs the answer through the terminal and presses the "Send" button. The input answer is sent from the terminal to the server.

[0802] Step 5:

[0803] The server passes the received answers to the evaluation means, which then judges whether the answers are correct or incorrect. Data processing involves comparing the input answers with the correct answer data and generating an evaluation result (correct, incorrect, etc.). The evaluation result is returned to the server.

[0804] Step 6:

[0805] The server generates a feedback message based on the evaluation result and sends the feedback to the user terminal, which displays the feedback message to inform the user of the result. The feedback message appears on the user terminal as output data.

[0806] Step 7:

[0807] The camera and microphone on the user's device capture the user's emotional data in real time and transmit the data to the server. Image data and voice data are sent as input data to the server.

[0808] Step 8:

[0809] The emotion recognition engine on the server analyzes the received emotion data and recognizes the user's emotional state (e.g., stress, concentration, etc.). As data processing, the emotion recognition model classifies the emotion data and generates a result. The emotion recognition result is stored on the server.

[0810] Step 9:

[0811] The server adjusts the difficulty and content of the next question based on the emotion recognition results. The adjusted question is regenerated by the AI ​​engine and sent to the server. The adjusted new question is stored on the server as output data.

[0812] Step 10:

[0813] The server sends the adjusted problem back to the user terminal, and the terminal presents the new problem to the user. The adjusted new problem is displayed on the user terminal as output data.

[0814] The above steps realize a system that presents appropriate questions and feedback according to the user's emotional state and setting information.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] [Third embodiment]

[0819] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0820] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0821] 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).

[0822] 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.

[0823] 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.

[0824] 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).

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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."

[0831] System Configuration Overview

[0832] This automatic question generation system consists of an input means for a user to specify the field, category, and difficulty level of the question, an artificial intelligence engine that generates questions based on this information, an output means for providing the generated questions and their answers, and an evaluation means for evaluating the answers entered by the user and providing feedback.

[0833] Specific implementation methods of the system

[0834] User Interface (UI)

[0835] The user accesses the problem generation system using a terminal. The interface allows the user to select the subject (e.g., mathematics, science), category (e.g., algebra, physics), and difficulty level (e.g., beginner, intermediate, advanced) using drop-down menus and text fields. Once the user completes these entries, they press the "Generate" button.

[0836] Server-side processing

[0837] The device sends the user's setting data (field, category, difficulty level) to the server. The server receives this data and instructs the AI ​​engine to generate questions. The AI ​​engine generates appropriate questions based on the specified field, category, and difficulty level.

[0838] AI problem generation engine

[0839] The AI ​​problem generation engine receives instructions from the server and generates problems as follows:

[0840] 1. Question structure

[0841] 2. Generating answers to problems

[0842] Examples:

[0843] Problem: Factor x^2 + 5x + 6 = 0.

[0844] Answer: (x + 2)(x + 3)

[0845] The generated questions and answers are sent back to the server, which then transmits them to the user's terminal.

[0846] Display and answer input

[0847] The user's device displays the generated questions. The user looks at the questions and enters their answers into the interface. Once the input is complete, the user presses the "Submit" button.

[0848] Answer evaluation and feedback

[0849] The device sends the answer entered by the user to the server. The server has the AI ​​evaluate the answer. The AI ​​evaluates the answer and determines whether it is correct or incorrect. Based on the evaluation result, the server generates a feedback message, which is sent back to the device and displayed to the user.

[0850] Examples:

[0851] If the user answers "(x + 2)(x + 3)" and it is evaluated as correct, the feedback message displayed is "Correct, well done!". If the user answers "(x + 3)(x + 2)", it is also evaluated as correct and the feedback message displayed is "Correct, well done!".

[0852] Update function

[0853] The system is regularly updated on the backend, so that questions are generated based on new content or information added to a field or category. The AI ​​also continuously updates its question generation algorithm based on the latest learning data.

[0854] Improved feedback accuracy

[0855] If the user enters an incorrect answer, the AI ​​provides detailed feedback explaining why the answer is incorrect, including steps and references to the correct answer.

[0856] In this way, the system can continuously provide learners with questions that best suit their needs, and seamlessly generate questions, evaluate answers, and provide feedback.

[0857] The processing flow will be explained below.

[0858] Step 1:

[0859] The user accesses the question generation system on the terminal and opens the setting screen.

[0860] Step 2:

[0861] The user selects the field, category, and difficulty level and presses the "Generate" button.

[0862] Step 3:

[0863] The device collects data on the user's selected field, category, and difficulty level.

[0864] Step 4:

[0865] The terminal transmits the collected setting data to the server.

[0866] Step 5:

[0867] The server analyzes the received configuration data and issues instructions to the AI ​​problem generation engine to generate problems.

[0868] Step 6:

[0869] The AI ​​question generation engine generates questions and answers based on specified conditions.

[0870] Step 7:

[0871] The server receives questions and answers generated by the AI ​​question generation engine.

[0872] Step 8:

[0873] The server transmits the generated question data to the terminal.

[0874] Step 9:

[0875] The terminal displays the problem to the user.

[0876] Step 10:

[0877] The user solves the problem, enters the answer into the terminal interface, and presses the "Submit" button.

[0878] Step 11:

[0879] The terminal collects the answers entered by the user.

[0880] Step 12:

[0881] The terminal sends the collected answers to the server.

[0882] Step 13:

[0883] The server issues instructions to the AI ​​to evaluate the received answers.

[0884] Step 14:

[0885] AI evaluates the user's answers and determines whether they are correct or incorrect.

[0886] Step 15:

[0887] The server receives the evaluation results from the AI ​​and generates a feedback message.

[0888] Step 16:

[0889] The server sends the generated feedback message to the terminal.

[0890] Step 17:

[0891] The terminal displays a feedback message to the user.

[0892] Example 1

[0893] 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."

[0894] Conventional automatic problem generation systems have limited functionality for generating appropriate problems based on user settings, and providing evaluation and feedback on answers, making them unable to fully meet users' learning needs. In particular, it has been difficult to provide detailed feedback on the answers entered by users, or to automatically update problems based on new data.

[0895] 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.

[0896] In this invention, the server includes an input means for a user to specify the field, category, and difficulty level of a question, an artificial intelligence engine for generating questions based on the specified information, and an output means for providing the generated questions and their answers to the user. This allows the user to specify specialized questions tailored to their learning needs and have their answers evaluated. The server also includes a data storage means for receiving and storing data transmitted from the user's device, a means for generating feedback messages from the artificial intelligence engine that evaluates the data and generates feedback and returning the feedback messages to the user's device, an update means for generating corresponding questions when new data is added to a specific field or category, and a means for providing feedback in detail explaining why the user's answer is incorrect when the user enters an incorrect answer. This allows the user to continuously progress in their learning through detailed feedback and updated questions, significantly improving their learning effectiveness.

[0897] The "input means" is a means for providing an interface for a user to specify the field, category, and difficulty level of a question.

[0898] An "artificial intelligence engine" is a program or system that generates questions and their answers based on specified information.

[0899] "Output means" refers to a display device or transmission means for providing the generated questions and their answers to the user.

[0900] An "evaluator" is a program or mechanism for evaluating answers entered by a user and generating feedback.

[0901] The "data storage means" is a storage device or database for receiving and storing data sent from the user's terminal at the server.

[0902] The "feedback message generating means" is a program or system for generating a feedback message from an artificial intelligence engine that evaluates data and generates feedback, and returning this to the user terminal.

[0903] An "updater" is a mechanism or program that generates questions corresponding to new data added to a particular field or category.

[0904] A "feedback providing means" is a program or system that, when a user enters an incorrect answer, provides feedback that explains in detail why the answer is incorrect.

[0905] MODE FOR CARRYING OUT THE INVENTION

[0906] System Configuration

[0907] The automatic question generation system of the present invention comprises an input means for a user to specify the field, category, and difficulty level of a question, an artificial intelligence engine for generating questions based on the specified information, an output means for providing the generated questions and their answers to the user, and an evaluation means for evaluating the answers entered by the user and generating feedback.

[0908] User Interface (UI)

[0909] A user accesses the automated problem generation system using a terminal. The interface includes drop-down menus and text fields that allow the user to specify the subject (e.g., mathematics, science), category (e.g., algebra, physics), and difficulty level (e.g., beginner, intermediate, advanced). Once the user completes the settings, they press a "Generate" button, which triggers the input mechanism.

[0910] Sending and Receiving Data

[0911] The user's terminal sends the setting data (field, category, difficulty level) to the server. The server receives this and stores it in the data storage means. This data will be used in the next step of the process.

[0912] Question generation instructions

[0913] The server analyzes the received data and instructs the AI ​​engine to generate questions and answers based on the specified field, category, and difficulty level.

[0914] Specifically, the problem is generated using the following steps:

[0915] 1. Question structure

[0916] 2. Generating answers to problems

[0917] As a concrete example, generate the following problem and its solution:

[0918] Problem: Factor x^2 + 5x + 6 = 0.

[0919] Answer:(x + 2)(x + 3)

[0920] Providing questions and answers

[0921] The generated questions and answers are sent back to the server, which then sends them to the user's terminal and provides them to the user, who then displays the questions on the user's terminal.

[0922] Enter answers to questions and submit

[0923] The user thinks of an answer to the displayed question and enters it into the interface. After entering the answer and pressing the "Send" button, the terminal sends the answer data to the server.

[0924] Answer evaluation and feedback

[0925] The server passes the received answer data to an AI engine, which evaluates the answer, determines whether it is correct, and generates a feedback message.

[0926] Specifically, it generates feedback like this:

[0927] If you get it right: "That's right, well done!"

[0928] Incorrect answer: "Sorry, you're wrong. The correct answer is (x + 2)(x + 3)."

[0929] The feedback message is sent from the server to the terminal and displayed to the user.

[0930] Improved update functionality and feedback

[0931] The system is regularly updated in the backend, and questions are generated accordingly as new data is added. Additionally, if a user enters an incorrect answer, feedback is provided detailing the error.

[0932] Specific examples of prompts to input to generative AI models

[0933] Below are some examples of prompts that can be used to generate questions:

[0934] "Generate problems for factoring quadratic equations at an elementary level in mathematics."

[0935] "Generate intermediate level physics problems related to mechanics."

[0936] This allows the system to provide optimal questions tailored to the user's learning needs, and by evaluating and providing feedback on answers, it can improve learning effectiveness.

[0937] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0938] Step 1: User specifies the problem

[0939] The user uses a terminal to access the interface of the automatic question generation system. The interface displays drop-down menus and text fields for selecting the field, category, and difficulty level. The user uses these to input the desired question settings. Once the input is complete, the user presses the "Generate" button. The input here is the field, category, and difficulty level, and the output is the user-selected setting data.

[0940] Step 2: Send data from the device to the server

[0941] The device sends the setting data (field, category, difficulty) entered by the user to the server via an HTTP request. The input is the setting data, and the output is a confirmation that the data was successfully sent to the server. At this time, the device displays an indicator indicating that the sending process is in progress.

[0942] Step 3: Server receives and analyzes data

[0943] The server receives the setting data sent from the terminal. This data is stored in the server's data storage means. The server then analyzes the received data and determines which field, category, and level of difficulty to generate questions for. The input is the received data, and the output is the analysis results.

[0944] Step 4: Submitting the question generation instructions

[0945] The server issues instructions to the AI ​​engine for generating questions based on the analysis results. These instructions include the field, category, and difficulty level. The server passes this configuration data to the AI ​​engine as a prompt. The input is the analysis results, and the output is instructions for generating questions.

[0946] Step 5: Generate questions using the AI ​​question generation engine

[0947] Based on the prompt received from the server, the AI ​​engine generates a problem and answer that meets the specified conditions. Specifically, it creates the structure of the problem and the corresponding answer. For example, in the field of mathematics, it generates a problem such as "factorize x^2 + 5x + 6 = 0" and its answer "(x + 2)(x + 3)". The input is the problem generation instruction, and the output is the generated problem and answer.

[0948] Step 6: Sending the generated data back to the server

[0949] The AI ​​engine sends the generated questions and answers back to the server. The server temporarily stores the received data. The input is the generated questions and answers, and the output is the receipt of the data by the server.

[0950] Step 7: Sending data from the server to the device

[0951] The server sends the generated questions and answers to the user's device. The data is sent using an HTTP response. The input is the questions and answer data stored on the server, and the output is a confirmation that the data was successfully sent to the device.

[0952] Step 8: User enters answer

[0953] The generated question is displayed on the terminal, and the user inputs the answer to the question into the interface. When input is complete, the user presses the "Submit" button. The input is the user's answer, and the output is the answer data ready for transmission.

[0954] Step 9: Send the answer from the device to the server

[0955] The terminal sends the answer entered by the user to the server via an HTTP request. The input is the user's answer data, and the output is a confirmation that the data was successfully sent to the server.

[0956] Step 10: Server evaluates the answer

[0957] The server passes the received answer data to an AI engine, which evaluates the answer. The AI ​​engine determines whether the answer is correct and generates an appropriate feedback message. The input is the user's answer data, and the output is the evaluation result and feedback message.

[0958] Step 11: Returning evaluation results and feedback

[0959] The server generates a feedback message and sends it to the user's device. The feedback includes whether the answer is correct or incorrect, and if incorrect, the reason for the error. The input is the evaluation result and the feedback message, and the output is a confirmation of successful data transmission to the device.

[0960] Step 12: Viewing feedback

[0961] The user's device displays the received feedback message on the interface. For example, messages such as "That's right, well done!" or "Sorry, you're wrong. The correct answer is (x + 2)(x + 3)" are displayed. The input is the feedback message, and the output is the feedback display to the user.

[0962] (Application example 1)

[0963] 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."

[0964] Currently, many brick-and-mortar store staff are required to undergo regular training on product knowledge and customer service skills, but the content is uniform, making it difficult to provide questions tailored to each staff member's knowledge level and required skills. Furthermore, previous training methods make it difficult to immediately evaluate staff answers and provide appropriate feedback. Therefore, it is necessary to provide an efficient training method that meets the needs of each individual staff member.

[0965] 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.

[0966] In this invention, the server includes an input means for a user to specify the field, category, and difficulty of a question, an artificial intelligence engine for generating questions based on the specified information, an output means for providing the generated questions and their answers to the user, an evaluation means for evaluating the answers input by the user and generating feedback, and a means for automatically generating and evaluating training and educational questions for staff. This makes it possible to efficiently provide questions tailored to the knowledge level and required skills of each staff member and to provide immediate feedback on the answers.

[0967] "Input means for the user to specify the field, category, and difficulty level of the problem" refers to an interface means for the user to specify information about the training or educational problem, and includes menus and input fields for selecting the field, category, and difficulty level.

[0968] An "artificial intelligence engine for generating questions based on specified information" is an artificial intelligence-based computer program for automatically generating appropriate training or educational questions based on subject, category, and difficulty information entered by a user.

[0969] "Output means for providing the generated questions and their answers to the user" refers to means for displaying or providing the questions and their answers generated by the artificial intelligence engine on the user's device, including the display of a smartphone or the screen of an application.

[0970] The "evaluation means for evaluating the answer entered by the user and generating feedback" refers to a program or algorithm that analyzes the answer entered by the user, determines whether it is correct or not, and provides feedback.

[0971] "Means for automatically generating and evaluating staff training and educational questions" refers to the overall system functionality for automatically generating training and educational questions for store staff using artificial intelligence and evaluating the answers.

[0972] "Efficient delivery with immediate feedback on answers" refers to the entire process of generating quick and appropriate training questions based on user-specified information, and then instantly evaluating and providing feedback on the answers provided by the user.

[0973] "Server" refers to a central computer or similar facility that performs various processes, such as generating questions, evaluating answers, and providing feedback, in practicing the invention.

[0974] overview

[0975] This invention is a system for automatically generating training and educational questions for store staff, evaluating the answers, and providing immediate feedback. The system consists of the following components: user input, question generation, answer evaluation, and feedback provision.

[0976] Hardware and Software Configuration

[0977] Hardware used

[0978] Smartphone: A device through which a user accesses an application.

[0979] Server: A central computer that performs question generation and evaluation functions and manages various data.

[0980] Software used

[0981] Programming language: Develop applications in Swift (for iOS) and Kotlin (for Android).

[0982] Framework: Uses Firebase for real-time database and serverless functions.

[0983] Generative AI model: We will use TensorFlow to implement the artificial intelligence model required for question generation and evaluation.

[0984] System Operation

[0985] User Input

[0986] Users access the application using their smartphones and enter information into the interface to select a training category (e.g., product knowledge, customer service skills) and difficulty level (beginner, intermediate, advanced). After entering the required information, the user presses the "Generate" button.

[0987] Problem generation

[0988] The server receives the user's input data (area, category, difficulty level) and issues question generation instructions to the generative AI model. The AI ​​model generates appropriate training questions based on the specified information. For example, an intermediate question on customer service skills might be, "How would you respond if a customer complained about a returned product?"

[0989] Providing problems

[0990] The generated questions and their answers are sent from the server to the user's smartphone, which displays the questions on an interface and allows the user to enter the answers.

[0991] Answer evaluation

[0992] When a user enters an answer and presses the "Submit" button, the answer is sent to the server. The server evaluates the answer using a generative AI model and determines whether it is correct. For example, if a user answers, "First, listen to the customer's story to the end, show empathy, and then quickly process the return," the AI ​​will determine this as the correct answer.

[0993] Providing Feedback

[0994] Based on the evaluation results, the server generates a feedback message and sends it to the user's smartphone. If the answer is correct, it displays "That's right, well done!", and if the answer is incorrect, it provides appropriate corrections and instructions for solving the problem.

[0995] Examples and prompts

[0996] Specific examples

[0997] For example, if a user selects "Intermediate" when generating training questions for customer service skills:

[0998] Problem: How do you respond when a customer complains about a return?

[0999] AI-generated answer (example): First, listen to the customer's story thoroughly, show empathy, and then quickly process the return.

[1000] Prompt example

[1001] Please generate training questions that meet the following criteria:

[1002] Category: Customer Service Skills

[1003] Difficulty: Intermediate

[1004] Problem Statement: How would you respond if a customer complained about a return?

[1005] Sample answer: First, listen to the customer thoroughly, show empathy, and then process the return promptly.

[1006] As described above, by clearly indicating the specific system configuration and processing content for implementing the invention, it is shown that the invention functions effectively in training staff in brick-and-mortar stores.

[1007] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1008] Step 1:

[1009] The user launches the application on their smartphone and selects a training category (e.g., product knowledge, customer service skills) and difficulty level (beginner, intermediate, advanced). After entering this information and pressing the "Generate" button, the device sends the input data to the server.

[1010] Input: Category and difficulty information

[1011] Output: Send category and difficulty selection data to the server

[1012] Step 2:

[1013] The server receives the selection data sent from the device and passes it to the generative AI model, which then generates appropriate training questions based on the specified information.

[1014] Input: Category and difficulty selection data

[1015] Output: Generated problem data

[1016] Step 3:

[1017] The server receives the generated question data and sends it to the user's smartphone, which displays the received question data on its interface and allows the user to enter answers.

[1018] Input: Generated problem data

[1019] Output: Problem displayed in terminal

[1020] Step 4:

[1021] When the user inputs an answer to the displayed question and presses the "Send" button, the terminal transmits the input answer data to the server.

[1022] Input: User's answer data

[1023] Output: Send answer data to the server

[1024] Step 5:

[1025] The server receives the user's answer data, passes it to the generative AI model, and evaluates the answer. The generative AI model determines whether the answer is correct or incorrect and returns the result to the server.

[1026] Input: User's answer data

[1027] Output: Evaluation result (correct / incorrect)

[1028] Step 6:

[1029] The server generates a feedback message based on the evaluation results and sends it to the user's smartphone, which then displays the feedback message on its interface.

[1030] Input: Evaluation result

[1031] Output: Generate and display feedback messages

[1032] Specific actions

[1033] Step 1

[1034] The user selects a category (e.g., customer service skills) and difficulty level (intermediate) in the application and presses the "Generate" button. The device converts the selected data into JSON format and sends it to the server as an HTTPS request.

[1035] Step 2

[1036] The server analyzes the received request, extracts data on the category and difficulty level, and inputs a prompt (e.g., "Customer service skills, intermediate") to the AI ​​model to instruct it to generate questions. The AI ​​model then generates appropriate questions and returns the data to the server.

[1037] Step 3

[1038] The server receives the generated problem data and sends it in JSON format to the user's device. The device displays the received problem on the interface, for example, "If a customer complains about a returned product, how would you respond?"

[1039] Step 4

[1040] The user enters the answer to the question (e.g., "First, listen to the customer's story until the end, show empathy, and then quickly process the return.") and presses the "Submit" button. The device converts the entered answer data into JSON format and sends it to the server as an HTTPS request.

[1041] Step 5

[1042] The server analyzes the received answer data and issues evaluation instructions to the generating AI model. The AI ​​model determines whether the answer is correct and returns an evaluation result, such as determining that the answer is "correct."

[1043] Step 6

[1044] The server generates a feedback message (e.g., "That's right, well done!") based on the evaluation result and sends it to the user's device in JSON format. The device then displays the feedback message on its interface for the user to see.

[1045] In this way, the present invention provides efficient and relevant training to users and provides immediate feedback on their answers.

[1046] 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.

[1047] System Configuration Overview

[1048] This automatic question generation system includes an input means for a user to specify the field, category, and difficulty level of the question, an artificial intelligence engine that generates questions based on this information, an output means for providing the generated questions and their answers, an evaluation means for evaluating the answers entered by the user and providing feedback, and an emotion engine that recognizes the user's emotions and adjusts the content of the questions based on them.

[1049] Specific implementation methods of the system

[1050] User Interface (UI)

[1051] The user accesses the problem generation system using a terminal. The interface allows the user to select the subject (e.g., mathematics, science), category (e.g., algebra, physics), and difficulty level (e.g., beginner, intermediate, advanced) using drop-down menus and text fields. Once the user completes these entries, they press the "Generate" button.

[1052] Server-side processing

[1053] The device sends the user's setting data (field, category, difficulty level) to the server. The server receives this data and instructs the AI ​​problem generation engine to generate questions. Based on the specified field, category, and difficulty level, the AI ​​engine generates appropriate questions.

[1054] AI problem generation engine

[1055] The AI ​​problem generation engine receives instructions from the server and generates questions and answers. For example, it generates questions as follows:

[1056] Problem: Factor $x^2 + 5x + 6 = 0$.

[1057] Answer: $(x + 2)(x + 3)$

[1058] The generated questions and answers are sent back to the server, which then transmits them to the user's terminal.

[1059] Emotional engine regulation

[1060] The emotion engine uses sensor data from the device's camera, microphone, and other devices to recognize the user's emotions (e.g., stress, fatigue, concentration) in real time. After the emotion engine evaluates the user's emotional state, it adjusts the difficulty and timing of questions based on the results.

[1061] As a specific example, if the user is determined to be in a high stress state, the emotion engine will lower the difficulty of the questions, thereby reducing the burden on the user.

[1062] Display and answer input

[1063] The user's device displays the generated questions. The user looks at the questions and enters their answers into the interface. Once the input is complete, the user presses the "Submit" button.

[1064] Answer evaluation and feedback

[1065] The device sends the answer entered by the user to the server. The server has the AI ​​evaluate the answer. The AI ​​evaluates the answer and determines whether it is correct or incorrect. Based on the evaluation result, the server generates a feedback message, which is sent back to the device and displayed to the user.

[1066] For example, if the user answers "(x + 2)(x + 3)" and this is evaluated as correct, the feedback message displayed will be "Correct, well done!". Also, if the user answers "(x + 3)(x + 2)", this will also be evaluated as correct and the feedback message displayed will be "Correct, well done!".

[1067] Update function

[1068] The system is regularly updated in the backend, especially when new content or information is added to a field or category, so that corresponding questions are generated. The emotion engine is also updated based on the latest data, continuously improving the accuracy of user emotion recognition.

[1069] Improved feedback accuracy

[1070] If the user enters an incorrect answer, the AI ​​provides detailed feedback explaining why the answer is incorrect, including steps and references to the correct answer. The emotional engine also adjusts the tone and content of the feedback appropriately, taking into account the user's emotional state.

[1071] In this way, the system maximizes users' learning efficiency and enhances their learning experience by seamlessly generating questions, evaluating answers, providing feedback, and adjusting to the user's emotions.

[1072] The processing flow will be explained below.

[1073] Step 1:

[1074] The user accesses the question generation system on the terminal and opens the setting screen.

[1075] Step 2:

[1076] The user selects the field, category, and difficulty level and presses the "Generate" button.

[1077] Step 3:

[1078] The device collects data on the user's selected field, category, and difficulty level.

[1079] Step 4:

[1080] The device sends the sensor data for the emotion engine to the server along with the configuration data collected.

[1081] Step 5:

[1082] The server analyzes the received configuration data and issues instructions to the AI ​​problem generation engine to generate problems.

[1083] Step 6:

[1084] The emotion engine analyzes sensor data from the device (e.g., camera footage and audio data) and evaluates the user's emotional state.

[1085] Step 7:

[1086] The AI ​​question generation engine generates questions and answers based on specified conditions.

[1087] Step 8:

[1088] The server receives questions and answers generated by the AI ​​question generation engine.

[1089] Step 9:

[1090] Based on the evaluation results of the emotion engine, the server adjusts the difficulty level of the questions and the timing of questions.

[1091] Step 10:

[1092] The server transmits the generated question data to the terminal.

[1093] Step 11:

[1094] The terminal displays the problem to the user.

[1095] Step 12:

[1096] The user solves the problem, enters the answer into the terminal interface, and presses the "Submit" button.

[1097] Step 13:

[1098] The terminal collects the answers entered by the user.

[1099] Step 14:

[1100] The terminal sends the collected answers to the server.

[1101] Step 15:

[1102] The server issues instructions to the AI ​​to evaluate the received answers.

[1103] Step 16:

[1104] AI evaluates the user's answers and determines whether they are correct or incorrect.

[1105] Step 17:

[1106] The server receives the evaluation results from the AI ​​and generates a feedback message.

[1107] Step 18:

[1108] The emotion engine reassess the user's emotional state and adjusts the presentation and tone of the feedback message.

[1109] Step 19:

[1110] The server sends the generated feedback message to the terminal.

[1111] Step 20:

[1112] The terminal displays a feedback message to the user.

[1113] Example 2

[1114] 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."

[1115] In conventional learning systems, although users can select the subject, category, and difficulty level of the questions, it is difficult to adjust the content of the questions according to the user's emotional state or to provide real-time feedback.In addition, it is difficult to provide questions of an appropriate difficulty level for users with a certain level of knowledge, which leads to problems that reduce learning efficiency.

[1116] 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.

[1117] In this invention, the server includes an input means for a user to specify the field, category, and difficulty level of a question, an artificial intelligence engine for generating questions based on the specified information, an output means for providing the generated questions and their answers to the user, an evaluation means for evaluating the answers input by the user and generating feedback, and an emotion engine for recognizing the user's emotions and adjusting the content of the questions based on the emotions, thereby maximizing the user's learning efficiency and improving each individual learning experience.

[1118] An "input means" is a device or interface that allows a user to specify the field, category, and difficulty level of a question.

[1119] An "artificial intelligence engine" is a computer program or system for generating questions based on specified information.

[1120] An "output means" is a device or mechanism for displaying or providing the generated questions and their solutions to the user.

[1121] An "evaluation means" is a device or system for evaluating answers entered by a user and generating feedback.

[1122] An "emotion engine" is a system or program that recognizes the user's emotions and adjusts the content and difficulty of the questions based on those emotions.

[1123] The "means for randomly selecting and providing" is a device or system for randomly selecting a question from a plurality of generated questions and providing it to the user.

[1124] "Automatic adjustment means" is a mechanism for automatically changing the difficulty of questions based on the user's knowledge level and emotional state.

[1125] MODE FOR CARRYING OUT THE INVENTION

[1126] This automatic problem generation system begins when a user uses a terminal to specify the problem's field, category, and difficulty level. The terminal's user interface (UI) allows selection using drop-down menus and text fields. The user selects the desired field (e.g., mathematics), category (e.g., algebra), and difficulty level (e.g., intermediate), and then presses the "Generate" button to complete these settings.

[1127] The device sends the configuration data selected by the user to the server. Specifically, the data is sent via an HTTP request. The server passes the received data to the AI ​​problem generation engine. The AI ​​problem generation engine generates problems based on the specified conditions. This process uses natural language processing and machine learning techniques. An example of a generated problem is "Factorize $x^2 + 5x + 6 = 0$." An example of a generated answer is "$(x + 2)(x + 3)$."

[1128] The server sends the generated questions and answers to the user's device. The device displays the received questions on the user interface. The user looks at the displayed questions and enters their answers. Specifically, the user enters "(x + 2)(x + 3)" in the text box and presses the "Submit" button.

[1129] The device sends the answer entered by the user to the server. The server evaluates the answer using an evaluation method. The evaluation method uses AI to determine whether the answer is correct or incorrect. The server generates a feedback message based on the evaluation result and sends it to the device. For example, if the user enters the correct answer, it displays "That's right, well done!"

[1130] Furthermore, the emotion engine evaluates the user's emotions in real time. Using data collected from the device's camera and microphone, it detects when the user is under high stress. Based on the results of this detection, the emotion engine adjusts the difficulty and timing of questions.

[1131] The system is also regularly updated on the backend. As new content and information is added, new questions can be generated based on that content. The emotion engine is also updated based on the latest data, improving the accuracy of user emotion recognition.

[1132] Here are some examples of prompts to input to the generative AI model:

[1133] "Generate problems in the following areas: mathematics, category: algebra, difficulty: intermediate."

[1134] Through this process, users can solve problems of appropriate difficulty and receive real-time feedback. The emotional engine adjusts the questions to reduce the burden on users and maximize learning efficiency.

[1135] keyword:

[1136] Generative AI model, prompt sentence

[1137] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1138] Step 1:

[1139] A user accesses the problem generation system using a terminal. The interface allows the user to select a subject (e.g., mathematics), a category (e.g., algebra), and a difficulty level (e.g., intermediate) using drop-down menus and text fields. Once the user has completed these entries, they press the "Generate" button. This action confirms the selected configuration data.

[1140] Step 2:

[1141] The device sends the user-selected setting data (field, category, difficulty level) to the server. Specifically, the data is sent using an HTTP request. The server receives and analyzes this data. The input is the setting data, and the output is the analyzed setting data.

[1142] Step 3:

[1143] The server passes the analyzed data to an AI problem generation engine. This engine generates questions and answers based on the specified conditions. The generation process uses natural language processing and machine learning algorithms. Specific data processing involves generating questions and their solutions (e.g., "Factorize $x^2 + 5x + 6 = 0$" and "$(x + 2)(x + 3)$"). The input is the analyzed configuration data, and the output is the generated questions and answers.

[1144] Step 4:

[1145] The server sends the generated questions and answers to the user's terminal. The terminal receives this data and displays the questions on a user interface. The display format is a text question and answer input field. The input is the generated question and answer, and the output is the displayed question.

[1146] Step 5:

[1147] The user checks the displayed question and enters the answer. Specifically, the user enters the answer (e.g., "(x + 2)(x + 3)") in the text box and presses the "Submit" button. This operation confirms the answer data. The input is the user's answer, and the output is the confirmed answer data.

[1148] Step 6:

[1149] The terminal sends the answer data entered by the user to the server. The sending method is usually an HTTP request. The server receives this data and analyzes it. The input is the user's answer data, and the output is the analyzed answer data.

[1150] Step 7:

[1151] The server evaluates the analyzed answer data using an evaluation means. Specifically, an AI model is used. It determines whether the answer is correct or incorrect and generates a feedback message based on the evaluation result. For example, feedback such as "That's correct, well done!" is generated. The input is the analyzed answer data, and the output is the feedback message.

[1152] Step 8:

[1153] The server sends the generated feedback message to the terminal. The terminal receives this message and displays it on the user interface. Specifically, the feedback is displayed in text format. The input is the feedback message, and the output is the displayed feedback message.

[1154] Step 9:

[1155] The emotion engine analyzes sensor data collected from the camera and microphone on the user's device. It evaluates the user's emotional state (e.g., stress, concentration) in real time and sends it to the server. The input is the sensor data, and the output is the evaluated emotional state data.

[1156] Step 10:

[1157] The server adjusts the difficulty and timing of questions based on the emotional state data. For example, if the user is in a high stress state, the settings are changed to present relatively easy questions. The input is the emotional state data, and the output is the adjusted question settings.

[1158] (Application example 2)

[1159] 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."

[1160] This invention relates to an automatic question generation system, and in particular to a system that enables flexible question generation and feedback that responds to the user's emotional state. Conventional question generation systems do not take into account the user's emotions or stress level, which can be burdensome for some users and discourage them from learning. Therefore, the objective of this system is to provide a more effective learning experience by recognizing the user's emotions in real time and appropriately adjusting the content and difficulty of the questions.

[1161] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes input means for the user to specify the field, category, and difficulty level of the question, an artificial intelligence engine for generating questions based on the specified information, output means for providing the generated questions and their answers to the user, evaluation means for evaluating the answers entered by the user and generating feedback, and emotion recognition means for recognizing the user's emotions in real time and adjusting the content of the questions based on that. This makes it possible to provide appropriate questions and feedback according to the emotional state of each user.

[1162] "Input means" refers to the method and device by which a user specifies the field, category, and difficulty level of a question.

[1163] "Artificial intelligence engine" refers to a computer program or algorithm for generating questions based on specified information.

[1164] "Output means" refers to a method and device for providing the generated questions and their answers to the user.

[1165] "Evaluation means" refers to the methods and algorithms for evaluating user-entered answers and generating feedback.

[1166] "Emotion recognition means" refers to a method and device for recognizing a user's emotions in real time and adjusting the content of questions based on that.

[1167] "Means for generating multiple questions" refers to methods and algorithms for creating a certain number of questions or more based on information specified by the user.

[1168] "Means for randomly selecting and providing" refers to methods and algorithms for randomly selecting from a plurality of generated questions and presenting them to the user.

[1169] "Means for automatically adjusting difficulty" refers to methods and algorithms for varying the difficulty of questions depending on the user's emotional state and knowledge level.

[1170] To implement this invention, a server, a user terminal, and a series of software modules are required. This invention mainly uses the following hardware and software:

[1171] Hardware

[1172] Server: A computer that receives user-specified information, generates questions using an artificial intelligence engine, and processes emotion recognition data.

[1173] User device: A device that is directly operated by the user, such as a smartphone or smart glasses. It is equipped with a camera and microphone and is used to acquire emotion recognition data.

[1174] software

[1175] Artificial Intelligence Engine: A program that generates questions based on user-specified subject areas, categories, and difficulty levels.

[1176] Emotion recognition engine: A module that analyzes the user's sensor data acquired through the camera and microphone and recognizes their emotional state.

[1177] Feedback generation module: A program that evaluates the answers entered by the user and generates appropriate feedback.

[1178] Specific technologies used include Python, OpenCV, and emotion recognition libraries (e.g., EmotionRecognizer).

[1179] System Operation

[1180] 1. User Input: The user accesses the system using a terminal and selects the subject, category, and difficulty level of the problem using drop-down menus and text fields. Once the selection is complete, the user presses the "Generate" button to send the input information to the server.

[1181] 2. Question generation: Based on the user's settings information received by the server, the AI ​​engine generates appropriate questions. The generated questions and answers are sent from the server to the user's device.

[1182] 3. Emotion recognition: The camera and microphone on the user's device capture the user's emotional data in real time and send it to the server, where the server's emotion recognition engine analyzes the data and determines the user's emotional state.

[1183] 4. Question Adjustment and Answer Evaluation: The difficulty and content of questions are adjusted based on the user's emotional state and presented to the user. When the user enters an answer, the answer is sent to the server and evaluated. Feedback is generated based on the evaluation results and displayed on the user's device.

[1184] Specific examples

[1185] For example, if a user selects the "Food category, easy level," they will be presented with a quiz like this: "Which country does this food originate from?" After the user answers, if the emotion recognition engine detects a stressed state, the difficulty of the next question will automatically decrease. Feedback will also include a message like "You got it right! Would you like to try the next question?"

[1186] Prompt Sentence Examples

[1187] "Generate quizzes at an easy level for food categories and assess customer answers in real time. Also, use emotion recognition to lower the difficulty of the next quiz if the customer is highly stressed."

[1188] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1189] Step 1:

[1190] A user accesses the system using a terminal and selects the field, category, and difficulty level from a drop-down menu or text field. The field, category, and difficulty level are entered as input data on the terminal, and the data is sent to the server.

[1191] Step 2:

[1192] The server instructs the AI ​​engine to generate questions based on the received user settings. The AI ​​engine processes the input data and generates questions and answers based on the specified information. The generated questions and answers are stored on the server.

[1193] Step 3:

[1194] The server sends the generated questions and answers to the user's terminal. The terminal displays the received questions, and the user deciphers the questions. The displayed questions appear on the user's terminal as output data.

[1195] Step 4:

[1196] The user inputs the answer through the terminal and presses the "Send" button. The input answer is sent from the terminal to the server.

[1197] Step 5:

[1198] The server passes the received answers to the evaluation means, which then judges whether the answers are correct or incorrect. Data processing involves comparing the input answers with the correct answer data and generating an evaluation result (correct, incorrect, etc.). The evaluation result is returned to the server.

[1199] Step 6:

[1200] The server generates a feedback message based on the evaluation result and sends the feedback to the user terminal, which displays the feedback message to inform the user of the result. The feedback message appears on the user terminal as output data.

[1201] Step 7:

[1202] The camera and microphone on the user's device capture the user's emotional data in real time and transmit the data to the server. Image data and voice data are sent as input data to the server.

[1203] Step 8:

[1204] The emotion recognition engine on the server analyzes the received emotion data and recognizes the user's emotional state (e.g., stress, concentration, etc.). As data processing, the emotion recognition model classifies the emotion data and generates a result. The emotion recognition result is stored on the server.

[1205] Step 9:

[1206] The server adjusts the difficulty and content of the next question based on the emotion recognition results. The adjusted question is regenerated by the AI ​​engine and sent to the server. The adjusted new question is stored on the server as output data.

[1207] Step 10:

[1208] The server sends the adjusted problem back to the user terminal, and the terminal presents the new problem to the user. The adjusted new problem is displayed on the user terminal as output data.

[1209] The above steps realize a system that presents appropriate questions and feedback according to the user's emotional state and setting information.

[1210] 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.

[1211] 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.

[1212] 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.

[1213] [Fourth embodiment]

[1214] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1215] 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.

[1216] 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).

[1217] 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.

[1218] 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.

[1219] 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).

[1220] 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.

[1221] 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.

[1222] 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.

[1223] 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.

[1224] 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.

[1225] 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.

[1226] 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."

[1227] System Configuration Overview

[1228] This automatic question generation system consists of an input means for a user to specify the field, category, and difficulty level of the question, an artificial intelligence engine that generates questions based on this information, an output means for providing the generated questions and their answers, and an evaluation means for evaluating the answers entered by the user and providing feedback.

[1229] Specific implementation methods of the system

[1230] User Interface (UI)

[1231] The user accesses the problem generation system using a terminal. The interface allows the user to select the subject (e.g., mathematics, science), category (e.g., algebra, physics), and difficulty level (e.g., beginner, intermediate, advanced) using drop-down menus and text fields. Once the user completes these entries, they press the "Generate" button.

[1232] Server-side processing

[1233] The device sends the user's setting data (field, category, difficulty level) to the server. The server receives this data and instructs the AI ​​engine to generate questions. The AI ​​engine generates appropriate questions based on the specified field, category, and difficulty level.

[1234] AI problem generation engine

[1235] The AI ​​problem generation engine receives instructions from the server and generates problems as follows:

[1236] 1. Question structure

[1237] 2. Generating answers to problems

[1238] Examples:

[1239] Problem: Factor x^2 + 5x + 6 = 0.

[1240] Answer: (x + 2)(x + 3)

[1241] The generated questions and answers are sent back to the server, which then transmits them to the user's terminal.

[1242] Display and answer input

[1243] The user's device displays the generated questions. The user looks at the questions and enters their answers into the interface. Once the input is complete, the user presses the "Submit" button.

[1244] Answer evaluation and feedback

[1245] The device sends the answer entered by the user to the server. The server has the AI ​​evaluate the answer. The AI ​​evaluates the answer and determines whether it is correct or incorrect. Based on the evaluation result, the server generates a feedback message, which is sent back to the device and displayed to the user.

[1246] Examples:

[1247] If the user answers "(x + 2)(x + 3)" and it is evaluated as correct, the feedback message displayed is "Correct, well done!". If the user answers "(x + 3)(x + 2)", it is also evaluated as correct and the feedback message displayed is "Correct, well done!".

[1248] Update function

[1249] The system is regularly updated on the backend, so that questions are generated based on new content or information added to a field or category. The AI ​​also continuously updates its question generation algorithm based on the latest learning data.

[1250] Improved feedback accuracy

[1251] If the user enters an incorrect answer, the AI ​​provides detailed feedback explaining why the answer is incorrect, including steps and references to the correct answer.

[1252] In this way, the system can continuously provide learners with questions that best suit their needs, and seamlessly generate questions, evaluate answers, and provide feedback.

[1253] The processing flow will be explained below.

[1254] Step 1:

[1255] The user accesses the question generation system on the terminal and opens the setting screen.

[1256] Step 2:

[1257] The user selects the field, category, and difficulty level and presses the "Generate" button.

[1258] Step 3:

[1259] The device collects data on the user's selected field, category, and difficulty level.

[1260] Step 4:

[1261] The terminal transmits the collected setting data to the server.

[1262] Step 5:

[1263] The server analyzes the received configuration data and issues instructions to the AI ​​problem generation engine to generate problems.

[1264] Step 6:

[1265] The AI ​​question generation engine generates questions and answers based on specified conditions.

[1266] Step 7:

[1267] The server receives questions and answers generated by the AI ​​question generation engine.

[1268] Step 8:

[1269] The server transmits the generated question data to the terminal.

[1270] Step 9:

[1271] The terminal displays the problem to the user.

[1272] Step 10:

[1273] The user solves the problem, enters the answer into the terminal interface, and presses the "Submit" button.

[1274] Step 11:

[1275] The terminal collects the answers entered by the user.

[1276] Step 12:

[1277] The terminal sends the collected answers to the server.

[1278] Step 13:

[1279] The server issues instructions to the AI ​​to evaluate the received answers.

[1280] Step 14:

[1281] AI evaluates the user's answers and determines whether they are correct or incorrect.

[1282] Step 15:

[1283] The server receives the evaluation results from the AI ​​and generates a feedback message.

[1284] Step 16:

[1285] The server sends the generated feedback message to the terminal.

[1286] Step 17:

[1287] The terminal displays a feedback message to the user.

[1288] Example 1

[1289] 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."

[1290] Conventional automatic problem generation systems have limited functionality for generating appropriate problems based on user settings, and providing evaluation and feedback on answers, making them unable to fully meet users' learning needs. In particular, it has been difficult to provide detailed feedback on the answers entered by users, or to automatically update problems based on new data.

[1291] 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.

[1292] In this invention, the server includes an input means for a user to specify the field, category, and difficulty level of a question, an artificial intelligence engine for generating questions based on the specified information, and an output means for providing the generated questions and their answers to the user. This allows the user to specify specialized questions tailored to their learning needs and have their answers evaluated. The server also includes a data storage means for receiving and storing data transmitted from the user's device, a means for generating feedback messages from the artificial intelligence engine that evaluates the data and generates feedback and returning the feedback messages to the user's device, an update means for generating corresponding questions when new data is added to a specific field or category, and a means for providing feedback in detail explaining why the user's answer is incorrect when the user enters an incorrect answer. This allows the user to continuously progress in their learning through detailed feedback and updated questions, significantly improving their learning effectiveness.

[1293] The "input means" is a means for providing an interface for a user to specify the field, category, and difficulty level of a question.

[1294] An "artificial intelligence engine" is a program or system that generates questions and their answers based on specified information.

[1295] "Output means" refers to a display device or transmission means for providing the generated questions and their answers to the user.

[1296] An "evaluator" is a program or mechanism for evaluating answers entered by a user and generating feedback.

[1297] The "data storage means" is a storage device or database for receiving and storing data sent from the user's terminal at the server.

[1298] The "feedback message generating means" is a program or system for generating a feedback message from an artificial intelligence engine that evaluates data and generates feedback, and returning this to the user terminal.

[1299] An "updater" is a mechanism or program that generates questions corresponding to new data added to a particular field or category.

[1300] A "feedback providing means" is a program or system that, when a user enters an incorrect answer, provides feedback that explains in detail why the answer is incorrect.

[1301] MODE FOR CARRYING OUT THE INVENTION

[1302] System Configuration

[1303] The automatic question generation system of the present invention comprises an input means for a user to specify the field, category, and difficulty level of a question, an artificial intelligence engine for generating questions based on the specified information, an output means for providing the generated questions and their answers to the user, and an evaluation means for evaluating the answers entered by the user and generating feedback.

[1304] User Interface (UI)

[1305] A user accesses the automated problem generation system using a terminal. The interface includes drop-down menus and text fields that allow the user to specify the subject (e.g., mathematics, science), category (e.g., algebra, physics), and difficulty level (e.g., beginner, intermediate, advanced). Once the user completes the settings, they press a "Generate" button, which triggers the input mechanism.

[1306] Sending and Receiving Data

[1307] The user's terminal sends the setting data (field, category, difficulty level) to the server. The server receives this and stores it in the data storage means. This data will be used in the next step of the process.

[1308] Question generation instructions

[1309] The server analyzes the received data and instructs the AI ​​engine to generate questions and answers based on the specified field, category, and difficulty level.

[1310] Specifically, the problem is generated using the following steps:

[1311] 1. Question structure

[1312] 2. Generating answers to problems

[1313] As a concrete example, generate the following problem and its solution:

[1314] Problem: Factor x^2 + 5x + 6 = 0.

[1315] Answer:(x + 2)(x + 3)

[1316] Providing questions and answers

[1317] The generated questions and answers are sent back to the server, which then sends them to the user's terminal and provides them to the user, who then displays the questions on the user's terminal.

[1318] Enter answers to questions and submit

[1319] The user thinks of an answer to the displayed question and enters it into the interface. After entering the answer and pressing the "Send" button, the terminal sends the answer data to the server.

[1320] Answer evaluation and feedback

[1321] The server passes the received answer data to an AI engine, which evaluates the answer, determines whether it is correct, and generates a feedback message.

[1322] Specifically, it generates feedback like this:

[1323] If you get it right: "That's right, well done!"

[1324] Incorrect answer: "Sorry, you're wrong. The correct answer is (x + 2)(x + 3)."

[1325] The feedback message is sent from the server to the terminal and displayed to the user.

[1326] Improved update functionality and feedback

[1327] The system is regularly updated in the backend, and questions are generated accordingly as new data is added. Additionally, if a user enters an incorrect answer, feedback is provided detailing the error.

[1328] Specific examples of prompts to input to generative AI models

[1329] Below are some examples of prompts that can be used to generate questions:

[1330] "Generate problems for factoring quadratic equations at an elementary level in mathematics."

[1331] "Generate intermediate level physics problems related to mechanics."

[1332] This allows the system to provide optimal questions tailored to the user's learning needs, and by evaluating and providing feedback on answers, it can improve learning effectiveness.

[1333] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1334] Step 1: User specifies the problem

[1335] The user uses a terminal to access the interface of the automatic question generation system. The interface displays drop-down menus and text fields for selecting the field, category, and difficulty level. The user uses these to input the desired question settings. Once the input is complete, the user presses the "Generate" button. The input here is the field, category, and difficulty level, and the output is the user-selected setting data.

[1336] Step 2: Send data from the device to the server

[1337] The device sends the setting data (field, category, difficulty) entered by the user to the server via an HTTP request. The input is the setting data, and the output is a confirmation that the data was successfully sent to the server. At this time, the device displays an indicator indicating that the sending process is in progress.

[1338] Step 3: Server receives and analyzes data

[1339] The server receives the setting data sent from the terminal. This data is stored in the server's data storage means. The server then analyzes the received data and determines which field, category, and level of difficulty to generate questions for. The input is the received data, and the output is the analysis results.

[1340] Step 4: Submitting the question generation instructions

[1341] The server issues instructions to the AI ​​engine for generating questions based on the analysis results. These instructions include the field, category, and difficulty level. The server passes this configuration data to the AI ​​engine as a prompt. The input is the analysis results, and the output is instructions for generating questions.

[1342] Step 5: Generate questions using the AI ​​question generation engine

[1343] Based on the prompt received from the server, the AI ​​engine generates a problem and answer that meets the specified conditions. Specifically, it creates the structure of the problem and the corresponding answer. For example, in the field of mathematics, it generates a problem such as "factorize x^2 + 5x + 6 = 0" and its answer "(x + 2)(x + 3)". The input is the problem generation instruction, and the output is the generated problem and answer.

[1344] Step 6: Sending the generated data back to the server

[1345] The AI ​​engine sends the generated questions and answers back to the server. The server temporarily stores the received data. The input is the generated questions and answers, and the output is the receipt of the data by the server.

[1346] Step 7: Sending data from the server to the device

[1347] The server sends the generated questions and answers to the user's device. The data is sent using an HTTP response. The input is the questions and answer data stored on the server, and the output is a confirmation that the data was successfully sent to the device.

[1348] Step 8: User enters answer

[1349] The generated question is displayed on the terminal, and the user inputs the answer to the question into the interface. When input is complete, the user presses the "Submit" button. The input is the user's answer, and the output is the answer data ready for transmission.

[1350] Step 9: Send the answer from the device to the server

[1351] The terminal sends the answer entered by the user to the server via an HTTP request. The input is the user's answer data, and the output is a confirmation that the data was successfully sent to the server.

[1352] Step 10: Server evaluates the answer

[1353] The server passes the received answer data to an AI engine, which evaluates the answer. The AI ​​engine determines whether the answer is correct and generates an appropriate feedback message. The input is the user's answer data, and the output is the evaluation result and feedback message.

[1354] Step 11: Returning evaluation results and feedback

[1355] The server generates a feedback message and sends it to the user's device. The feedback includes whether the answer is correct or incorrect, and if incorrect, the reason for the error. The input is the evaluation result and the feedback message, and the output is a confirmation of successful data transmission to the device.

[1356] Step 12: Viewing feedback

[1357] The user's device displays the received feedback message on the interface. For example, messages such as "That's right, well done!" or "Sorry, you're wrong. The correct answer is (x + 2)(x + 3)" are displayed. The input is the feedback message, and the output is the feedback display to the user.

[1358] (Application example 1)

[1359] 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."

[1360] Currently, many brick-and-mortar store staff are required to undergo regular training on product knowledge and customer service skills, but the content is uniform, making it difficult to provide questions tailored to each staff member's knowledge level and required skills. Furthermore, previous training methods make it difficult to immediately evaluate staff answers and provide appropriate feedback. Therefore, it is necessary to provide an efficient training method that meets the needs of each individual staff member.

[1361] 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.

[1362] In this invention, the server includes an input means for a user to specify the field, category, and difficulty of a question, an artificial intelligence engine for generating questions based on the specified information, an output means for providing the generated questions and their answers to the user, an evaluation means for evaluating the answers input by the user and generating feedback, and a means for automatically generating and evaluating training and educational questions for staff. This makes it possible to efficiently provide questions tailored to the knowledge level and required skills of each staff member and to provide immediate feedback on the answers.

[1363] "Input means for the user to specify the field, category, and difficulty level of the problem" refers to an interface means for the user to specify information about the training or educational problem, and includes menus and input fields for selecting the field, category, and difficulty level.

[1364] An "artificial intelligence engine for generating questions based on specified information" is an artificial intelligence-based computer program for automatically generating appropriate training or educational questions based on subject, category, and difficulty information entered by a user.

[1365] "Output means for providing the generated questions and their answers to the user" refers to means for displaying or providing the questions and their answers generated by the artificial intelligence engine on the user's device, including the display of a smartphone or the screen of an application.

[1366] The "evaluation means for evaluating the answer entered by the user and generating feedback" refers to a program or algorithm that analyzes the answer entered by the user, determines whether it is correct or not, and provides feedback.

[1367] "Means for automatically generating and evaluating staff training and educational questions" refers to the overall system functionality for automatically generating training and educational questions for store staff using artificial intelligence and evaluating the answers.

[1368] "Efficient delivery with immediate feedback on answers" refers to the entire process of generating quick and appropriate training questions based on user-specified information, and then instantly evaluating and providing feedback on the answers provided by the user.

[1369] "Server" refers to a central computer or similar facility that performs various processes, such as generating questions, evaluating answers, and providing feedback, in practicing the invention.

[1370] overview

[1371] This invention is a system for automatically generating training and educational questions for store staff, evaluating the answers, and providing immediate feedback. The system consists of the following components: user input, question generation, answer evaluation, and feedback provision.

[1372] Hardware and Software Configuration

[1373] Hardware used

[1374] Smartphone: A device through which a user accesses an application.

[1375] Server: A central computer that performs question generation and evaluation functions and manages various data.

[1376] Software used

[1377] Programming language: Develop applications in Swift (for iOS) and Kotlin (for Android).

[1378] Framework: Uses Firebase for real-time database and serverless functions.

[1379] Generative AI model: We will use TensorFlow to implement the artificial intelligence model required for question generation and evaluation.

[1380] System Operation

[1381] User Input

[1382] Users access the application using their smartphones and enter information into the interface to select a training category (e.g., product knowledge, customer service skills) and difficulty level (beginner, intermediate, advanced). After entering the required information, the user presses the "Generate" button.

[1383] Problem generation

[1384] The server receives the user's input data (area, category, difficulty level) and issues question generation instructions to the generative AI model. The AI ​​model generates appropriate training questions based on the specified information. For example, an intermediate question on customer service skills might be, "How would you respond if a customer complained about a returned product?"

[1385] Providing problems

[1386] The generated questions and their answers are sent from the server to the user's smartphone, which displays the questions on an interface and allows the user to enter the answers.

[1387] Answer evaluation

[1388] When a user enters an answer and presses the "Submit" button, the answer is sent to the server. The server evaluates the answer using a generative AI model and determines whether it is correct. For example, if a user answers, "First, listen to the customer's story to the end, show empathy, and then quickly process the return," the AI ​​will determine this as the correct answer.

[1389] Providing Feedback

[1390] Based on the evaluation results, the server generates a feedback message and sends it to the user's smartphone. If the answer is correct, it displays "That's right, well done!", and if the answer is incorrect, it provides appropriate corrections and instructions for solving the problem.

[1391] Examples and prompts

[1392] Specific examples

[1393] For example, if a user selects "Intermediate" when generating training questions for customer service skills:

[1394] Problem: How do you respond when a customer complains about a return?

[1395] AI-generated answer (example): First, listen to the customer's story thoroughly, show empathy, and then quickly process the return.

[1396] Prompt example

[1397] Please generate training questions that meet the following criteria:

[1398] Category: Customer Service Skills

[1399] Difficulty: Intermediate

[1400] Problem Statement: How would you respond if a customer complained about a return?

[1401] Sample answer: First, listen to the customer thoroughly, show empathy, and then process the return promptly.

[1402] As described above, by clearly indicating the specific system configuration and processing content for implementing the invention, it is shown that the invention functions effectively in training staff in brick-and-mortar stores.

[1403] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1404] Step 1:

[1405] The user launches the application on their smartphone and selects a training category (e.g., product knowledge, customer service skills) and difficulty level (beginner, intermediate, advanced). After entering this information and pressing the "Generate" button, the device sends the input data to the server.

[1406] Input: Category and difficulty information

[1407] Output: Send category and difficulty selection data to the server

[1408] Step 2:

[1409] The server receives the selection data sent from the device and passes it to the generative AI model, which then generates appropriate training questions based on the specified information.

[1410] Input: Category and difficulty selection data

[1411] Output: Generated problem data

[1412] Step 3:

[1413] The server receives the generated question data and sends it to the user's smartphone, which displays the received question data on its interface and allows the user to enter answers.

[1414] Input: Generated problem data

[1415] Output: Problem displayed in terminal

[1416] Step 4:

[1417] When the user inputs an answer to the displayed question and presses the "Send" button, the terminal transmits the input answer data to the server.

[1418] Input: User's answer data

[1419] Output: Send answer data to the server

[1420] Step 5:

[1421] The server receives the user's answer data, passes it to the generative AI model, and evaluates the answer. The generative AI model determines whether the answer is correct or incorrect and returns the result to the server.

[1422] Input: User's answer data

[1423] Output: Evaluation result (correct / incorrect)

[1424] Step 6:

[1425] The server generates a feedback message based on the evaluation results and sends it to the user's smartphone, which then displays the feedback message on its interface.

[1426] Input: Evaluation result

[1427] Output: Generate and display feedback messages

[1428] Specific actions

[1429] Step 1

[1430] The user selects a category (e.g., customer service skills) and difficulty level (intermediate) in the application and presses the "Generate" button. The device converts the selected data into JSON format and sends it to the server as an HTTPS request.

[1431] Step 2

[1432] The server analyzes the received request, extracts data on the category and difficulty level, and inputs a prompt (e.g., "Customer service skills, intermediate") to the AI ​​model to instruct it to generate questions. The AI ​​model then generates appropriate questions and returns the data to the server.

[1433] Step 3

[1434] The server receives the generated problem data and sends it in JSON format to the user's device. The device displays the received problem on the interface, for example, "If a customer complains about a returned product, how would you respond?"

[1435] Step 4

[1436] The user enters the answer to the question (e.g., "First, listen to the customer's story until the end, show empathy, and then quickly process the return.") and presses the "Submit" button. The device converts the entered answer data into JSON format and sends it to the server as an HTTPS request.

[1437] Step 5

[1438] The server analyzes the received answer data and issues evaluation instructions to the generating AI model. The AI ​​model determines whether the answer is correct and returns an evaluation result, such as determining that the answer is "correct."

[1439] Step 6

[1440] The server generates a feedback message (e.g., "That's right, well done!") based on the evaluation result and sends it to the user's device in JSON format. The device then displays the feedback message on its interface for the user to see.

[1441] In this way, the present invention provides efficient and relevant training to users and provides immediate feedback on their answers.

[1442] 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.

[1443] System Configuration Overview

[1444] This automatic question generation system includes an input means for a user to specify the field, category, and difficulty level of the question, an artificial intelligence engine that generates questions based on this information, an output means for providing the generated questions and their answers, an evaluation means for evaluating the answers entered by the user and providing feedback, and an emotion engine that recognizes the user's emotions and adjusts the content of the questions based on them.

[1445] Specific implementation methods of the system

[1446] User Interface (UI)

[1447] The user accesses the problem generation system using a terminal. The interface allows the user to select the subject (e.g., mathematics, science), category (e.g., algebra, physics), and difficulty level (e.g., beginner, intermediate, advanced) using drop-down menus and text fields. Once the user completes these entries, they press the "Generate" button.

[1448] Server-side processing

[1449] The device sends the user's setting data (field, category, difficulty level) to the server. The server receives this data and instructs the AI ​​problem generation engine to generate questions. Based on the specified field, category, and difficulty level, the AI ​​engine generates appropriate questions.

[1450] AI problem generation engine

[1451] The AI ​​problem generation engine receives instructions from the server and generates questions and answers. For example, it generates questions as follows:

[1452] Problem: Factor $x^2 + 5x + 6 = 0$.

[1453] Answer: $(x + 2)(x + 3)$

[1454] The generated questions and answers are sent back to the server, which then transmits them to the user's terminal.

[1455] Emotional engine regulation

[1456] The emotion engine uses sensor data from the device's camera, microphone, and other devices to recognize the user's emotions (e.g., stress, fatigue, concentration) in real time. After the emotion engine evaluates the user's emotional state, it adjusts the difficulty and timing of questions based on the results.

[1457] As a specific example, if the user is determined to be in a high stress state, the emotion engine will lower the difficulty of the questions, thereby reducing the burden on the user.

[1458] Display and answer input

[1459] The user's device displays the generated questions. The user looks at the questions and enters their answers into the interface. Once the input is complete, the user presses the "Submit" button.

[1460] Answer evaluation and feedback

[1461] The device sends the answer entered by the user to the server. The server has the AI ​​evaluate the answer. The AI ​​evaluates the answer and determines whether it is correct or incorrect. Based on the evaluation result, the server generates a feedback message, which is sent back to the device and displayed to the user.

[1462] For example, if the user answers "(x + 2)(x + 3)" and this is evaluated as correct, the feedback message displayed will be "Correct, well done!". Also, if the user answers "(x + 3)(x + 2)", this will also be evaluated as correct and the feedback message displayed will be "Correct, well done!".

[1463] Update function

[1464] The system is regularly updated in the backend, especially when new content or information is added to a field or category, so that corresponding questions are generated. The emotion engine is also updated based on the latest data, continuously improving the accuracy of user emotion recognition.

[1465] Improved feedback accuracy

[1466] If the user enters an incorrect answer, the AI ​​provides detailed feedback explaining why the answer is incorrect, including steps and references to the correct answer. The emotional engine also adjusts the tone and content of the feedback appropriately, taking into account the user's emotional state.

[1467] In this way, the system maximizes users' learning efficiency and enhances their learning experience by seamlessly generating questions, evaluating answers, providing feedback, and adjusting to the user's emotions.

[1468] The processing flow will be explained below.

[1469] Step 1:

[1470] The user accesses the question generation system on the terminal and opens the setting screen.

[1471] Step 2:

[1472] The user selects the field, category, and difficulty level and presses the "Generate" button.

[1473] Step 3:

[1474] The device collects data on the user's selected field, category, and difficulty level.

[1475] Step 4:

[1476] The device sends the sensor data for the emotion engine to the server along with the configuration data collected.

[1477] Step 5:

[1478] The server analyzes the received configuration data and issues instructions to the AI ​​problem generation engine to generate problems.

[1479] Step 6:

[1480] The emotion engine analyzes sensor data from the device (e.g., camera footage and audio data) and evaluates the user's emotional state.

[1481] Step 7:

[1482] The AI ​​question generation engine generates questions and answers based on specified conditions.

[1483] Step 8:

[1484] The server receives questions and answers generated by the AI ​​question generation engine.

[1485] Step 9:

[1486] Based on the evaluation results of the emotion engine, the server adjusts the difficulty level of the questions and the timing of questions.

[1487] Step 10:

[1488] The server transmits the generated question data to the terminal.

[1489] Step 11:

[1490] The terminal displays the problem to the user.

[1491] Step 12:

[1492] The user solves the problem, enters the answer into the terminal interface, and presses the "Submit" button.

[1493] Step 13:

[1494] The terminal collects the answers entered by the user.

[1495] Step 14:

[1496] The terminal sends the collected answers to the server.

[1497] Step 15:

[1498] The server issues instructions to the AI ​​to evaluate the received answers.

[1499] Step 16:

[1500] AI evaluates the user's answers and determines whether they are correct or incorrect.

[1501] Step 17:

[1502] The server receives the evaluation results from the AI ​​and generates a feedback message.

[1503] Step 18:

[1504] The emotion engine reassess the user's emotional state and adjusts the presentation and tone of the feedback message.

[1505] Step 19:

[1506] The server sends the generated feedback message to the terminal.

[1507] Step 20:

[1508] The terminal displays a feedback message to the user.

[1509] Example 2

[1510] 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."

[1511] In conventional learning systems, although users can select the subject, category, and difficulty level of the questions, it is difficult to adjust the content of the questions according to the user's emotional state or to provide real-time feedback.In addition, it is difficult to provide questions of an appropriate difficulty level for users with a certain level of knowledge, which leads to problems that reduce learning efficiency.

[1512] 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.

[1513] In this invention, the server includes an input means for a user to specify the field, category, and difficulty level of a question, an artificial intelligence engine for generating questions based on the specified information, an output means for providing the generated questions and their answers to the user, an evaluation means for evaluating the answers input by the user and generating feedback, and an emotion engine for recognizing the user's emotions and adjusting the content of the questions based on the emotions, thereby maximizing the user's learning efficiency and improving each individual learning experience.

[1514] An "input means" is a device or interface that allows a user to specify the field, category, and difficulty level of a question.

[1515] An "artificial intelligence engine" is a computer program or system for generating questions based on specified information.

[1516] An "output means" is a device or mechanism for displaying or providing the generated questions and their solutions to the user.

[1517] An "evaluation means" is a device or system for evaluating answers entered by a user and generating feedback.

[1518] An "emotion engine" is a system or program that recognizes the user's emotions and adjusts the content and difficulty of the questions based on those emotions.

[1519] The "means for randomly selecting and providing" is a device or system for randomly selecting a question from a plurality of generated questions and providing it to the user.

[1520] "Automatic adjustment means" is a mechanism for automatically changing the difficulty of questions based on the user's knowledge level and emotional state.

[1521] MODE FOR CARRYING OUT THE INVENTION

[1522] This automatic problem generation system begins when a user uses a terminal to specify the problem's field, category, and difficulty level. The terminal's user interface (UI) allows selection using drop-down menus and text fields. The user selects the desired field (e.g., mathematics), category (e.g., algebra), and difficulty level (e.g., intermediate), and then presses the "Generate" button to complete these settings.

[1523] The device sends the configuration data selected by the user to the server. Specifically, the data is sent via an HTTP request. The server passes the received data to the AI ​​problem generation engine. The AI ​​problem generation engine generates problems based on the specified conditions. This process uses natural language processing and machine learning techniques. An example of a generated problem is "Factorize $x^2 + 5x + 6 = 0$." An example of a generated answer is "$(x + 2)(x + 3)$."

[1524] The server sends the generated questions and answers to the user's device. The device displays the received questions on the user interface. The user looks at the displayed questions and enters their answers. Specifically, the user enters "(x + 2)(x + 3)" in the text box and presses the "Submit" button.

[1525] The device sends the answer entered by the user to the server. The server evaluates the answer using an evaluation method. The evaluation method uses AI to determine whether the answer is correct or incorrect. The server generates a feedback message based on the evaluation result and sends it to the device. For example, if the user enters the correct answer, it displays "That's right, well done!"

[1526] Furthermore, the emotion engine evaluates the user's emotions in real time. Using data collected from the device's camera and microphone, it detects when the user is under high stress. Based on the results of this detection, the emotion engine adjusts the difficulty and timing of questions.

[1527] The system is also regularly updated on the backend. As new content and information is added, new questions can be generated based on that content. The emotion engine is also updated based on the latest data, improving the accuracy of user emotion recognition.

[1528] Here are some examples of prompts to input to the generative AI model:

[1529] "Generate problems in the following areas: mathematics, category: algebra, difficulty: intermediate."

[1530] Through this process, users can solve problems of appropriate difficulty and receive real-time feedback. The emotional engine adjusts the questions to reduce the burden on users and maximize learning efficiency.

[1531] keyword:

[1532] Generative AI model, prompt sentence

[1533] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1534] Step 1:

[1535] A user accesses the problem generation system using a terminal. The interface allows the user to select a subject (e.g., mathematics), a category (e.g., algebra), and a difficulty level (e.g., intermediate) using drop-down menus and text fields. Once the user has completed these entries, they press the "Generate" button. This action confirms the selected configuration data.

[1536] Step 2:

[1537] The device sends the user-selected setting data (field, category, difficulty level) to the server. Specifically, the data is sent using an HTTP request. The server receives and analyzes this data. The input is the setting data, and the output is the analyzed setting data.

[1538] Step 3:

[1539] The server passes the analyzed data to an AI problem generation engine. This engine generates questions and answers based on the specified conditions. The generation process uses natural language processing and machine learning algorithms. Specific data processing involves generating questions and their solutions (e.g., "Factorize $x^2 + 5x + 6 = 0$" and "$(x + 2)(x + 3)$"). The input is the analyzed configuration data, and the output is the generated questions and answers.

[1540] Step 4:

[1541] The server sends the generated questions and answers to the user's terminal. The terminal receives this data and displays the questions on a user interface. The display format is a text question and answer input field. The input is the generated question and answer, and the output is the displayed question.

[1542] Step 5:

[1543] The user checks the displayed question and enters the answer. Specifically, the user enters the answer (e.g., "(x + 2)(x + 3)") in the text box and presses the "Submit" button. This operation confirms the answer data. The input is the user's answer, and the output is the confirmed answer data.

[1544] Step 6:

[1545] The terminal sends the answer data entered by the user to the server. The sending method is usually an HTTP request. The server receives this data and analyzes it. The input is the user's answer data, and the output is the analyzed answer data.

[1546] Step 7:

[1547] The server evaluates the analyzed answer data using an evaluation means. Specifically, an AI model is used. It determines whether the answer is correct or incorrect and generates a feedback message based on the evaluation result. For example, feedback such as "That's correct, well done!" is generated. The input is the analyzed answer data, and the output is the feedback message.

[1548] Step 8:

[1549] The server sends the generated feedback message to the terminal. The terminal receives this message and displays it on the user interface. Specifically, the feedback is displayed in text format. The input is the feedback message, and the output is the displayed feedback message.

[1550] Step 9:

[1551] The emotion engine analyzes sensor data collected from the camera and microphone on the user's device. It evaluates the user's emotional state (e.g., stress, concentration) in real time and sends it to the server. The input is the sensor data, and the output is the evaluated emotional state data.

[1552] Step 10:

[1553] The server adjusts the difficulty and timing of questions based on the emotional state data. For example, if the user is in a high stress state, the settings are changed to present relatively easy questions. The input is the emotional state data, and the output is the adjusted question settings.

[1554] (Application example 2)

[1555] 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."

[1556] This invention relates to an automatic question generation system, and in particular to a system that enables flexible question generation and feedback that responds to the user's emotional state. Conventional question generation systems do not take into account the user's emotions or stress level, which can be burdensome for some users and discourage them from learning. Therefore, the objective of this system is to provide a more effective learning experience by recognizing the user's emotions in real time and appropriately adjusting the content and difficulty of the questions.

[1557] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes input means for the user to specify the field, category, and difficulty level of the question, an artificial intelligence engine for generating questions based on the specified information, output means for providing the generated questions and their answers to the user, evaluation means for evaluating the answers entered by the user and generating feedback, and emotion recognition means for recognizing the user's emotions in real time and adjusting the content of the questions based on that. This makes it possible to provide appropriate questions and feedback according to the emotional state of each user.

[1558] "Input means" refers to the method and device by which a user specifies the field, category, and difficulty level of a question.

[1559] "Artificial intelligence engine" refers to a computer program or algorithm for generating questions based on specified information.

[1560] "Output means" refers to a method and device for providing the generated questions and their answers to the user.

[1561] "Evaluation means" refers to the methods and algorithms for evaluating user-entered answers and generating feedback.

[1562] "Emotion recognition means" refers to a method and device for recognizing a user's emotions in real time and adjusting the content of questions based on that.

[1563] "Means for generating multiple questions" refers to methods and algorithms for creating a certain number of questions or more based on information specified by the user.

[1564] "Means for randomly selecting and providing" refers to methods and algorithms for randomly selecting from a plurality of generated questions and presenting them to the user.

[1565] "Means for automatically adjusting difficulty" refers to methods and algorithms for varying the difficulty of questions depending on the user's emotional state and knowledge level.

[1566] To implement this invention, a server, a user terminal, and a series of software modules are required. This invention mainly uses the following hardware and software:

[1567] Hardware

[1568] Server: A computer that receives user-specified information, generates questions using an artificial intelligence engine, and processes emotion recognition data.

[1569] User device: A device that is directly operated by the user, such as a smartphone or smart glasses. It is equipped with a camera and microphone and is used to acquire emotion recognition data.

[1570] software

[1571] Artificial Intelligence Engine: A program that generates questions based on user-specified subject areas, categories, and difficulty levels.

[1572] Emotion recognition engine: A module that analyzes the user's sensor data acquired through the camera and microphone and recognizes their emotional state.

[1573] Feedback generation module: A program that evaluates the answers entered by the user and generates appropriate feedback.

[1574] Specific technologies used include Python, OpenCV, and emotion recognition libraries (e.g., EmotionRecognizer).

[1575] System Operation

[1576] 1. User Input: The user accesses the system using a terminal and selects the subject, category, and difficulty level of the problem using drop-down menus and text fields. Once the selection is complete, the user presses the "Generate" button to send the input information to the server.

[1577] 2. Question generation: Based on the user's settings information received by the server, the AI ​​engine generates appropriate questions. The generated questions and answers are sent from the server to the user's device.

[1578] 3. Emotion recognition: The camera and microphone on the user's device capture the user's emotional data in real time and send it to the server, where the server's emotion recognition engine analyzes the data and determines the user's emotional state.

[1579] 4. Question Adjustment and Answer Evaluation: The difficulty and content of questions are adjusted based on the user's emotional state and presented to the user. When the user enters an answer, the answer is sent to the server and evaluated. Feedback is generated based on the evaluation results and displayed on the user's device.

[1580] Specific examples

[1581] For example, if a user selects the "Food category, easy level," they will be presented with a quiz like this: "Which country does this food originate from?" After the user answers, if the emotion recognition engine detects a stressed state, the difficulty of the next question will automatically decrease. Feedback will also include a message like "You got it right! Would you like to try the next question?"

[1582] Prompt Sentence Examples

[1583] "Generate quizzes at an easy level for food categories and assess customer answers in real time. Also, use emotion recognition to lower the difficulty of the next quiz if the customer is highly stressed."

[1584] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1585] Step 1:

[1586] A user accesses the system using a terminal and selects the field, category, and difficulty level from a drop-down menu or text field. The field, category, and difficulty level are entered as input data on the terminal, and the data is sent to the server.

[1587] Step 2:

[1588] The server instructs the AI ​​engine to generate questions based on the received user settings. The AI ​​engine processes the input data and generates questions and answers based on the specified information. The generated questions and answers are stored on the server.

[1589] Step 3:

[1590] The server sends the generated questions and answers to the user's terminal. The terminal displays the received questions, and the user deciphers the questions. The displayed questions appear on the user's terminal as output data.

[1591] Step 4:

[1592] The user inputs the answer through the terminal and presses the "Send" button. The input answer is sent from the terminal to the server.

[1593] Step 5:

[1594] The server passes the received answers to the evaluation means, which then judges whether the answers are correct or incorrect. Data processing involves comparing the input answers with the correct answer data and generating an evaluation result (correct, incorrect, etc.). The evaluation result is returned to the server.

[1595] Step 6:

[1596] The server generates a feedback message based on the evaluation result and sends the feedback to the user terminal, which displays the feedback message to inform the user of the result. The feedback message appears on the user terminal as output data.

[1597] Step 7:

[1598] The camera and microphone on the user's device capture the user's emotional data in real time and transmit the data to the server. Image data and voice data are sent as input data to the server.

[1599] Step 8:

[1600] The emotion recognition engine on the server analyzes the received emotion data and recognizes the user's emotional state (e.g., stress, concentration, etc.). As data processing, the emotion recognition model classifies the emotion data and generates a result. The emotion recognition result is stored on the server.

[1601] Step 9:

[1602] The server adjusts the difficulty and content of the next question based on the emotion recognition results. The adjusted question is regenerated by the AI ​​engine and sent to the server. The adjusted new question is stored on the server as output data.

[1603] Step 10:

[1604] The server sends the adjusted problem back to the user terminal, and the terminal presents the new problem to the user. The adjusted new problem is displayed on the user terminal as output data.

[1605] The above steps realize a system that presents appropriate questions and feedback according to the user's emotional state and setting information.

[1606] 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.

[1607] 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.

[1608] 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.

[1609] 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.

[1610] 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.

[1611] 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.

[1612] 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).

[1613] 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.

[1614] 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."

[1615] 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.

[1616] 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).

[1617] 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.

[1618] 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.

[1619] 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.

[1620] 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.

[1621] 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.

[1622] 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.

[1623] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1624] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1625] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1626] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1627] The following is further disclosed regarding the above embodiment.

[1628] (Claim 1)

[1629] an input means for a user to specify the subject, category, and difficulty level of the problem;

[1630] an artificial intelligence engine for generating questions based on specified information;

[1631] an output means for providing the generated questions and their answers to a user;

[1632] evaluation means for evaluating the answers entered by the user and generating feedback;

[1633] A system including:

[1634] (Claim 2)

[1635] 2. The system according to claim 1, further comprising means for generating a plurality of questions based on information specified by a user and randomly selecting and providing the questions.

[1636] (Claim 3)

[1637] 10. The system of claim 1, further comprising means for automatically adjusting the difficulty of the questions based on the knowledge level of the user.

[1638] "Example 1"

[1639] (Claim 1)

[1640] an input means for a user to specify the subject, category, and difficulty level of the problem;

[1641] an artificial intelligence engine for generating questions based on specified information;

[1642] an output means for providing the generated questions and their answers to a user;

[1643] evaluation means for evaluating the answers entered by the user and generating feedback;

[1644] a data storage means for receiving and storing data transmitted from a user's terminal in a server;

[1645] means for generating a feedback message from the artificial intelligence engine that evaluates the data and generates the feedback, and returning the feedback message to the user terminal;

[1646] An update mechanism to generate questions that correspond to new data added to a particular field or category;

[1647] a means for providing feedback to a user if the user enters an incorrect answer, providing detailed information about why the answer is incorrect;

[1648] A system including:

[1649] (Claim 2)

[1650] 2. The system according to claim 1, further comprising means for generating a plurality of questions based on information specified by a user and randomly selecting and providing the questions.

[1651] (Claim 3)

[1652] 10. The system of claim 1, further comprising means for automatically adjusting the difficulty of the questions based on the knowledge level of the user.

[1653] "Application Example 1"

[1654] (Claim 1)

[1655] an input means for a user to specify the subject, category, and difficulty level of the problem;

[1656] an artificial intelligence engine for generating questions based on specified information;

[1657] an output means for providing the generated questions and their answers to a user;

[1658] evaluation means for evaluating the answers entered by the user and generating feedback;

[1659] A means for automatically generating and evaluating staff training and education questions;

[1660] A system including:

[1661] (Claim 2)

[1662] 2. The system according to claim 1, further comprising means for generating a plurality of questions based on information specified by a user and randomly selecting and providing the questions.

[1663] (Claim 3)

[1664] 10. The system of claim 1, further comprising means for automatically adjusting the difficulty of the questions based on the knowledge level of the user.

[1665] "Example 2: Combining Emotion Engines"

[1666] (Claim 1)

[1667] an input means for a user to specify the subject, category, and difficulty level of the problem;

[1668] an artificial intelligence engine for generating questions based on specified information;

[1669] an output means for providing the generated questions and their answers to a user;

[1670] evaluation means for evaluating the answers entered by the user and generating feedback;

[1671] an emotion engine for recognizing a user's emotion and adjusting the content of the problem accordingly;

[1672] A system including:

[1673] (Claim 2)

[1674] 2. The system according to claim 1, further comprising means for generating a plurality of questions based on information specified by a user and randomly selecting and providing the questions.

[1675] (Claim 3)

[1676] 10. The system of claim 1, further comprising means for automatically adjusting the difficulty of the questions based on the knowledge level and emotional state of the user.

[1677] "Application example 2 when combining emotion engines"

[1678] (Claim 1)

[1679] an input means for a user to specify the subject, category, and difficulty level of the problem;

[1680] an artificial intelligence engine for generating questions based on specified information;

[1681] an output means for providing the generated questions and their answers to a user;

[1682] evaluation means for evaluating the answers entered by the user and generating feedback;

[1683] emotion recognition means for recognizing the user's emotions in real time and adjusting the content of questions based on the emotions;

[1684] A system including:

[1685] (Claim 2)

[1686] The system according to claim 1, further comprising means for generating a plurality of questions based on information specified by the user, randomly selecting and providing the questions, and means for automatically adjusting the difficulty level according to the emotional state of the user.

[1687] (Claim 3)

[1688] 10. The system of claim 1, further comprising means for automatically adjusting the difficulty of the questions based on the knowledge level and emotional state of the user. [Explanation of symbols]

[1689] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. an input means for a user to specify the subject, category, and difficulty level of the problem; an artificial intelligence engine for generating questions based on specified information; an output means for providing the generated questions and their answers to a user; evaluation means for evaluating the answers entered by the user and generating feedback; A system including:

2. 2. The system according to claim 1, further comprising means for generating a plurality of questions based on information specified by a user and randomly selecting and providing the questions.

3. 10. The system of claim 1, further comprising means for automatically adjusting the difficulty of the questions based on the knowledge level of the user.

Images