System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving and analyzing past test question data as input; means for generating mock test questions from the analyzed data; means for receiving and analyzing a user's answers; means for identifying areas of weakness based on the analyzed user's answers; means for generating next mock test questions reflecting the identified areas of weakness; means for allowing a user to input questions; and means for generating answers to the questions.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] Individuals aiming to obtain qualifications can effectively identify their weak areas and focus their study efforts on those areas. However, current learning systems and materials often do not adequately address individual learning needs. Furthermore, due to a lack of functionality to efficiently use past exam questions and automatically generate mock exams, it is difficult to prepare for exams tailored to individual learning progress. Furthermore, it is difficult to ask questions about questions and receive immediate answers. The challenge is to solve these problems and maximize the effectiveness of learning for qualifications. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides a system including means for receiving and analyzing past exam question data as input, means for generating mock exam questions from the analyzed data, means for receiving and analyzing the user's answers, means for identifying weak areas based on the analyzed user's answers, means for generating the next mock exam questions reflecting the identified weak areas, means for the user to input questions, and means for generating answers to the questions. Specifically, the system further includes means for analyzing past exam question data to identify the format and pattern of each question and store them in a database, and means for automatically scoring and calculating scores based on the user's answers, thereby automatically generating mock exams according to individual learning needs and enabling focused learning of weak areas and immediate response to questions.

[0006] "Past exam question data" is digital data containing the questions from qualification exams that have been conducted in the past.

[0007] "Means for analysis" are algorithms or programs that process input data and identify its structure and patterns.

[0008] The "means for generating mock test questions" is a program or device that has the function of automatically creating new test questions based on the analysis results.

[0009] The "means for receiving and analyzing the user's answer results" is a program or device that records the answers entered by the user and evaluates and analyzes them.

[0010] The "means for identifying weak areas" refers to identifying which areas are the user's weak points based on the user's answers.

[0011] The "means for generating next practice test questions" is a program or device that generates new practice test questions tailored to the user's learning needs, taking into account the identified weak areas.

[0012] The "means for inputting questions" is an interface that allows the user to input any questions or uncertainties that arise during the course of study into the system.

[0013] The "means for generating answers to questions" is a program or device that automatically provides appropriate answers to questions entered by a user.

[0014] "Means for storing data in a database" refers to a system that efficiently stores analyzed data and allows it to be accessed quickly when needed.

[0015] The "means for automatically scoring and calculating scores" refers to a program or device that has the function of automatically evaluating the user's answers and calculating scores. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] This invention is a system that automatically generates mock exam questions for qualification exams, providing users with an optimized learning experience. This system analyzes past exam question data, identifies weak areas based on the user's answers, and generates new mock exam questions that reflect this information. It also provides a function that allows users to ask questions that arise during their studies and provides instant answers.

[0038] Program processing

[0039] 1. Enter past exam questions

[0040] User: Upload past qualification exam question sets to the system in PDF or other formats.

[0041] Terminal: Receives uploads from users and sends files to the server.

[0042] Server: Analyzes the received file, extracts the content of the questions as text data, identifies the format and patterns of each question (e.g., words, options, answers), and stores them in a database.

[0043] 2. Generating mock test questions

[0044] Server: Generates mock test questions based on the analyzed data. It runs an algorithm that learns the patterns and formats of past exam questions and creates new mock questions.

[0045] Terminal: Prepares the generated practice test questions for display to the user.

[0046] User: When you are ready to take the practice test, click the "Start" button on your device.

[0047] 3. Mock test implementation and result analysis

[0048] User: Answer each question one by one, for example, by clicking on the appropriate answer for multiple choice questions.

[0049] Terminal: Records the user's answers in real time, and when all answers have been completed, the user clicks the "Submit" button, which sends the data to the server.

[0050] Server: Receives all answers and automatically scores them. Based on the scores and analysis results, analyzes the user's answering tendencies and identifies weak areas.

[0051] 4. Identify weaknesses and personalize

[0052] Server: Based on the analysis results, the user's weak areas (e.g., specific subjects or question formats) are stored in a database.

[0053] Server: When generating the next mock test questions, this weak area information is reflected and questions that focus on that area are generated.

[0054] Terminal: Prepares to display the newly generated practice test questions and notifies the user.

[0055] Users: They can take the mock exam again and get further learning benefits.

[0056] 5. Implementing chat functionality

[0057] User: During or after the mock test, if there are any questions that the user does not understand, the user can enter the questions through the terminal.

[0058] Terminal: Sends the user's question data to the server.

[0059] Server: Analyzes the question and generates an appropriate answer from training data and pre-prepared FAQs, including detailed explanations and additional references if necessary.

[0060] Terminal: Displays the generated answer to the user for further understanding.

[0061] Specific examples

[0062] 1. Enter past exam questions

[0063] User: "I'll upload the past three years' worth of exam questions in PDF format."

[0064] Terminal: "File received. Sending to server..."

[0065] Server: "Parsing file... Problem data extracted."

[0066] 2. Generating mock test questions

[0067] Server: "Generate mock exam questions based on past exam data..."

[0068] Terminal: "The practice test questions are ready. Would you like to begin?"

[0069] 3. Mock test implementation and result analysis

[0070] User: "Answer question 1. I choose option C."

[0071] Terminal: "Your answer has been recorded. Would you like to proceed to the next question?"

[0072] User: "I've answered all the questions. I'm going to submit it."

[0073] Terminal: "Sending answer to server..."

[0074] Server: "Analyzing your answer... Score 70. Math is my weak point."

[0075] 4. Identify weaknesses and personalize

[0076] Server: "We've saved your weak areas and will incorporate them into your next practice test."

[0077] Terminal: "New practice test questions are ready. Would you like to begin?"

[0078] 5. Implementing chat functionality

[0079] User: "I have a question about question 3. I don't understand option B. Can you explain it in more detail?"

[0080] Terminal: "Sending question to server..."

[0081] Server: "Parsing your question... generated a suitable answer."

[0082] Terminal: "Answers have arrived, with detailed explanations."

[0083] Through this system, users can efficiently prepare for qualification exams while checking their own progress and weak points. In addition, they can instantly resolve any questions they have, significantly improving their learning efficiency.

[0084] The processing flow will be explained below.

[0085] Program processing steps

[0086] Step 1:

[0087] User: Upload past qualification exam question sets to the system in PDF or other formats.

[0088] Step 2:

[0089] Terminal: Receives uploads from users and sends files to the server.

[0090] Step 3:

[0091] Server: Analyzes the received file, extracts the question content as text data, and identifies and classifies the format and patterns of each question (e.g., words, options, answers).

[0092] Step 4:

[0093] Server: Stores the analyzed data in a database and organizes the classified problem data.

[0094] Step 5:

[0095] Server: Based on a database of past questions, the server runs an algorithm that learns question trends and formats, and creates templates for automatically generating mock test questions.

[0096] Step 6:

[0097] Terminal: Notifies the user that the generated practice test questions are ready.

[0098] Step 7:

[0099] User: Clicks on the "Start" button to begin the practice test.

[0100] Step 8:

[0101] Terminal: displays practice test questions to the user.

[0102] Step 9:

[0103] User: Enters an answer for each question, e.g., for multiple choice questions, clicks on the appropriate answer.

[0104] Step 10:

[0105] Terminal: The user's answers are recorded in real time, and after all answers are completed, they are sent to the server by clicking the "Submit" button.

[0106] Step 11:

[0107] Server: Receives all answers and automatically grades them. Calculates scores and analyzes users' answering trends.

[0108] Step 12:

[0109] Server: Based on the analysis results, identify the user's weak areas and store the weak areas information in a database.

[0110] Step 13:

[0111] Server: When generating the next mock test questions, the server reflects the information on the identified weak areas and generates questions that focus on those areas.

[0112] Step 14:

[0113] Terminal: Notifies the user that the newly generated practice test questions are ready.

[0114] Step 15:

[0115] User: Take the practice test again and continue studying.

[0116] Step 16:

[0117] User: During or after the mock test, enter questions about any questions you don't understand through the terminal.

[0118] Step 17:

[0119] Terminal: Sends the user's question data to the server.

[0120] Step 18:

[0121] Server: Analyzes the question and generates an appropriate answer from learning data and pre-prepared FAQs.

[0122] Step 19:

[0123] Terminal: Displays the generated answer to the user to help them understand it.

[0124] This series of processes allows users to efficiently prepare for the qualification exam and also allows them to immediately resolve any questions they may have while studying.

[0125] Example 1

[0126] 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."

[0127] Conventional qualification exam study systems lack the ability to properly identify users' weak areas and focus their learning on those areas, as well as the ability to record answers in real time and provide immediate feedback. Furthermore, they lack the ability to provide immediate solutions to questions users may have during the exam. This can lead to lower user learning efficiency and potentially lower pass rates for qualification exams.

[0128] 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.

[0129] In this invention, the server includes means for receiving and analyzing past exam question data as input, means for generating mock exam questions from the analyzed data, means for receiving and analyzing the user's answers, means for identifying weak areas based on the analyzed user's answers, means for generating the next mock exam questions reflecting the identified weak areas, means for the user to input questions, means for generating answers to the questions, means for saving the weak areas in a database, means for recording answers during the mock exam in real time, and means for learning a model based on the database of past questions. This makes it possible to identify the user's weak areas and have them study them intensively, and can provide immediate answers to any questions that arise during study, thereby significantly improving study efficiency.

[0130] "Past exam question data" refers to information about questions and answers from previous exams.

[0131] "Means of analysis" is a function for analyzing input data and extracting and identifying useful information.

[0132] "Mock test questions" are provisional test questions that users answer as practice to prepare for the actual test.

[0133] "Means of generation" refers to the function for creating new information and content based on data.

[0134] "User's answer results" are answers selected by the user to the mock test questions and answer information.

[0135] A "weak area" is an area in which a user shows low scores in a particular genre or theme based on the results of a mock test.

[0136] "Means for inputting questions" refers to an interface or function that allows users to input doubts or questions to the system.

[0137] The "means for generating an answer" is a function for creating and providing an appropriate answer to a question entered by a user.

[0138] "Means for storing in a database" refers to the function of storing analyzed information and data for the long term and retrieving it as needed.

[0139] "Means for recording in real time" is a function for instantly recording information on a user's actions or answers the moment they occur.

[0140] "Means of learning the model" is a feature that allows the algorithm to learn patterns and rules using past data so that it can adapt to new situations.

[0141] The present invention provides a system for automatically generating mock questions for qualification examinations and providing users with an optimized learning experience. This system is realized through the interaction of a server, a terminal, and a user.

[0142] First, a user uploads past exam question data in a file format such as PDF to the system. The terminal receives the uploaded file and sends it to the server. The server analyzes the received PDF file and extracts text data using a file analysis tool (Apache (registered trademark) PDFBox as a specific example). It then uses a Natural Language Processing (NLP) model (spaCy or NLTK as a specific example) to identify information about questions, options, and answers, and stores this information in a database.

[0143] Next, the server generates mock test questions by learning the patterns and trends of each question using a machine learning algorithm (specifically, GPT-3 (registered trademark), BERT) based on a database of past questions. The generated mock test questions are sent to the terminal and displayed on the user interface. The user then clicks the start mock test button to begin the test.

[0144] During the mock test, the user answers each question and clicks the next button to proceed. The device records the user's answers in real time, and when the "Submit" button is clicked after the test is completed, the answer data is sent to the server. The server automatically scores the received answer data and calculates the user's score using a specific algorithm (for example, Scikit-learn or TENSORFLOW (registered trademark)). It also analyzes answer trends and records specific weak areas in a database.

[0145] After identifying weak areas, the server adjusts the algorithm to include content that emphasizes the user's weak areas when generating the next mock test questions, and prepares to display them on the device, allowing the user to focus on studying their weak areas.

[0146] During or after the mock test, users can enter questions about problems they didn't understand in the chat box. The device sends the entered question to the server, which analyzes it using an NLP model (specifically, BERT or GPT-3) to generate an appropriate answer. The generated answer references FAQ data and related materials in the database, and the device displays it to the user.

[0147] Specific examples

[0148] Enter past exam questions

[0149] User: "I'll upload the past three years' worth of exam questions in PDF format."

[0150] Terminal: "File received. Sending to server..."

[0151] Server: "Parsing file... Problem data extracted."

[0152] Mock test question generation

[0153] Server: "Generate mock exam questions based on past exam data..."

[0154] Terminal: "The practice test questions are ready. Would you like to begin?"

[0155] Mock test implementation and result analysis

[0156] User: "Answer question 1. I choose option C."

[0157] Terminal: "Your answer has been recorded. Would you like to proceed to the next question?"

[0158] User: "I've answered all the questions. I'm going to submit it."

[0159] Terminal: "Sending answer to server..."

[0160] Server: "Analyzing your answer... Score 70. Math is my weak point."

[0161] Identifying weaknesses and personalizing

[0162] Server: "We've saved your weak areas and will incorporate them into your next practice test."

[0163] Terminal: "New practice test questions are ready. Would you like to begin?"

[0164] Implementing chat functionality

[0165] User: "I have a question about question 3. I don't understand option B. Can you explain it in more detail?"

[0166] Terminal: "Sending question to server..."

[0167] Server: "Parsing your question... generated a suitable answer."

[0168] Terminal: "Answers have arrived, with detailed explanations."

[0169] Through this system, users can effectively prepare for qualification exams, identify their weaknesses through mock tests, and deepen their understanding. Real-time feedback and answers to questions also greatly improve learning efficiency.

[0170] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0171] Step 1: Upload past exam questions

[0172] User: Prepare past exam question data in PDF format and click the upload button on the device.

[0173] Input: Past exam question data (PDF file).

[0174] Terminal: Receives the PDF file from the user and sends it to the server in bytes.

[0175] Output: The PDF file sent to the server.

[0176] Specific operation: A file selection window is displayed, and after the user selects the target file, the upload operation is performed.

[0177] Step 2: Analyzing the file contents

[0178] Server: Convert the received PDF file into text data using a file analysis tool (such as Apache PDFBox).

[0179] Input: PDF file.

[0180] Server: The converted text data is processed using an NLP model (such as spaCy or NLTK) to identify test questions, answer choices, and answers.

[0181] Output: Structured exam question data.

[0182] What it does: It uses a PDF parsing library to extract text from PDFs and then uses an NLP model to perform natural language processing and identify specific patterns.

[0183] Step 3: Saving to the database

[0184] Server: Stores the analyzed problem data in a database (MySQL (registered trademark), PostgreSQL, etc.).

[0185] Input: Structured exam question data.

[0186] Output: Exam question data stored in a database.

[0187] What it does: Establishes a database connection and saves data using an SQL query.

[0188] Step 4: Generate practice test questions

[0189] Server: Generates new mock test questions using generative AI models (such as GPT-3 and BERT) based on past questions in the database.

[0190] Input: Past exam data in the database.

[0191] Output: Generated practice test questions.

[0192] What it does: Apply machine learning algorithms to generate and format new problem data.

[0193] Step 5: Prepare to view the practice test questions

[0194] Terminal: Receives the generated practice test questions and prepares them for display on the user interface.

[0195] Input: Generated practice test questions.

[0196] Output: Practice test questions displayed in the user interface.

[0197] What it does: Formats problem data and converts it into HTML or JSON for display in a browser or app interface.

[0198] Step 6: Start the practice test

[0199] User: Click the Start Practice Test button to begin the practice test.

[0200] Input: User's starting instructions.

[0201] Terminal: Displays test questions sequentially and accepts user answers in input format.

[0202] Output: The answer from the user.

[0203] Specific operation: When the start button is pressed, the screen will move to the question display screen and prepare the answer input field.

[0204] Step 7: Record and submit your answers

[0205] User: Answer each question and click the next button to proceed.

[0206] Input: User's answer data.

[0207] Terminal: Each answer is recorded in real time, and the answer data is sent to the server when the "Submit" button is clicked after the test is completed.

[0208] Output: The answer data sent to the server.

[0209] Specific operation: Once the answer has been entered, the next question will be displayed, and once all questions have been completed, the answer data will be sent to the server.

[0210] Step 8: Scoring and analyzing results

[0211] Server: Based on the received answer data, the server automatically scores the answers. Specifically, it calculates the score using an algorithm (such as Scikit-learn or TensorFlow).

[0212] Input: User's answer data.

[0213] Output: User's score and weak areas analysis.

[0214] Specific operation: The received data is input into the evaluation algorithm for scoring and performance analysis.

[0215] Step 9: Record your weaknesses

[0216] Server: Based on the analysis results, identify the weak areas of each user and store them in a database.

[0217] Input: User scores and analysis results.

[0218] Output: Weakness information stored in a database.

[0219] Specific operation: Analysis results are added and saved to the user profile in the database.

[0220] Step 10: Generate new practice questions

[0221] Server: When generating the next mock test questions, generate new questions that focus on the user's weak areas.

[0222] Input: Data on weak areas.

[0223] Output: The newly generated practice test questions.

[0224] Specific operation: Refer to information on weak areas and use a generative AI model to generate specialized questions.

[0225] Step 11: Notification of new practice test questions

[0226] Terminal: Prepares to display the generated practice test questions and notifies the user.

[0227] Input: Newly generated practice test questions.

[0228] Output: The new practice test question and notification message displayed in the user interface.

[0229] Specific behavior: Convert new problem data into a display format and notify the user, for example, with a notification banner.

[0230] Step 12: Submit your question

[0231] Users: During or after the mock exam, type questions into the chat box about any questions they didn't understand.

[0232] Input: The user's question.

[0233] Terminal: Sends the query data to the server.

[0234] Output: The query data sent to the server.

[0235] Specific operation: Questions entered in the chat box are transferred to the server in real time.

[0236] Step 13: Parsing the question and generating an answer

[0237] Server: Analyzes the question using an NLP model (such as BERT or GPT-3) and generates an appropriate answer.

[0238] Input: User question data.

[0239] Output: The generated answer.

[0240] Specific operation: Performs natural language processing of the question and generates an answer based on FAQ data and related materials in the database.

[0241] Step 14: View your answers

[0242] Terminal: Displays the generated answers in a user interface.

[0243] Input: Generated response data.

[0244] Output: The answer displayed in the user interface.

[0245] Specific operation: Convert the response data into an appropriate format and display it on the chat screen, etc.

[0246] In this way, by clearly indicating the specific operations, inputs, and outputs at each processing step, it is possible to understand in detail how the user, terminal, and server cooperate to operate the entire system.

[0247] (Application example 1)

[0248] 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."

[0249] When studying for qualification exams, users need more than just past exam question collections; they need effective study methods that focus on their weak areas. There is also a lack of ways to instantly resolve questions that arise during study. Furthermore, there is the challenge of providing these exam preparation materials using smart devices, regardless of location or time.

[0250] 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.

[0251] In this invention, the server includes a means for scanning past exam papers with a camera and transmitting the data to the server, a means for the user to take the mock exam through smart glasses, and a means for automatically scoring all answers and displaying the analysis results to the user, allowing the user to study efficiently and effectively anywhere and quickly resolve any questions.

[0252] "Past exam question data" refers to digital records of the content of questions from previous qualification exams.

[0253] An "analyzing means" is a computer program or algorithm that processes input data and analyzes it to understand its content and characteristics.

[0254] "Mock test questions" are virtual test questions that users answer as practice in preparation for the actual test.

[0255] "User" means an individual or learner who uses this system to prepare for a qualification exam.

[0256] "Answer results" are the contents of the answers provided by the user to the mock test.

[0257] "Weak areas" refer to areas or subjects in which the user frequently gets exam questions wrong.

[0258] A "question" is an inquiry about content that the user found difficult to understand during the mock test or during study.

[0259] An "answer" is an explanation or information provided in response to a user's question.

[0260] "Camera scanning" means using a camera to capture a digital image of a physical document and convert its contents into digital data.

[0261] A "server" is a powerful computer system for storing, processing, and serving data.

[0262] "Smart glasses" are eyeglass-shaped devices equipped with a display and computer functionality that allow the wearer to obtain visual information.

[0263] "Automatic scoring" is a function in which the system evaluates the user's answers and calculates the score.

[0264] "Analysis results" are information about the user's learning tendencies and weak areas that the system derives from the user's answers.

[0265] The present invention enables users to effectively study for qualification exams by using practice tests. The system includes a server, a terminal (e.g., smart glasses), and a user interface.

[0266] Program Generation and Explanation

[0267] 1. Enter past exam questions

[0268] The user scans a collection of past qualification exam questions with the camera in the smart glasses and sends the data to the server.

[0269] The server uses OCR (Optical Character Recognition) technology to convert the contents of the scanned question set into digital text, identify the question format and patterns, and store them in a database (e.g., using Google (registered trademark) Cloud Vision API).

[0270] 2. Generating mock test questions

[0271] The server generates mock test questions based on the stored data, learning the patterns and formats of past questions and creating new mock questions using a generative AI model (e.g., TensorFlow).

[0272] The terminal prepares to display the generated practice test questions to the user.

[0273] 3. Mock test implementation and result analysis

[0274] Users take practice tests through smart glasses and input their answers to each question.

[0275] The terminal collects the user's answers in real time and transmits the data to the server after all answers have been completed.

[0276] The server performs automatic scoring, analyzes the user's answering tendencies based on the scores and analysis results, and identifies weak areas.

[0277] 4. Identify weaknesses and personalize

[0278] The server stores the user's weak areas in a database based on the analysis results. This allows the server to reflect this information on the weak areas when generating the next mock test questions, and generate questions that focus on those areas.

[0279] The terminal notifies the user of the newly generated practice test questions.

[0280] 5. Implementing chat functionality

[0281] During or after the mock test, users can input questions about any questions they don't understand through the smart glasses.

[0282] The terminal transmits the user's question data to the server.

[0283] The server analyzes the question and generates an appropriate answer from learning data and pre-prepared FAQs.

[0284] The terminal displays the generated answers to the user for further understanding.

[0285] Examples of specific examples and prompt usage

[0286] 1. Enter past exam questions

[0287] User: "I'm going to scan the past three years of exam questions."

[0288] Smart Glasses: "Sending data to server..."

[0289] Server: "Parsing data... Problem data extracted."

[0290] 2. Generating mock test questions

[0291] System: "Preparing mock test questions based on past exam data... Completed."

[0292] 3. Mock test implementation and result analysis

[0293] User: "Answer question 1. I choose option C."

[0294] Smart Glasses: "Your answer has been recorded. Would you like to see the next question?"

[0295] 4. Identify weaknesses and personalize

[0296] Server: "A new question has been generated based on the results of the previous test."

[0297] 5. Implementing chat functionality

[0298] User: "I don't understand option A in this question."

[0299] Server: "Analyzing...generating appropriate answer."

[0300] Example prompts to input to the generative AI model

[0301] "Load question data, analyze it and generate new practice test questions."

[0302] "Analyze users' answer patterns and identify areas of weakness."

[0303] "Generate a suitable answer to this question."

[0304] This system allows users to learn efficiently and resolve their questions immediately. This is a specific mode for carrying out the invention.

[0305] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0306] Step 1:

[0307] The user scans a collection of past exam questions for qualification exams with the camera on the smart glasses and sends the data to the server. Specifically, the user sets the glasses to scan mode and has the camera read each page of the question collection. The scanned images are obtained as input, and the server uses OCR technology (e.g., Google Cloud Vision API) to convert these images into text data and store the content in a database. The analyzed text data is generated as output.

[0308] Step 2:

[0309] The server analyzes the stored text data and identifies patterns and formats of past questions. This analysis is performed using specific algorithms and machine learning models (e.g., TensorFlow). The input is the text data of past questions stored in the database, and the output is structured data that identifies the format and patterns of each question. The server uses this structured data for further processing.

[0310] Step 3:

[0311] The server generates mock exam questions based on the analyzed past exam data. It uses a generative AI model to create new questions. Structured data on the patterns and formats of past exam questions is used as input, and newly generated mock exam questions are obtained as output. This data is then ready to be sent to the device.

[0312] Step 4:

[0313] The device displays the generated mock test questions to the user. The user takes the mock test through the smart glasses and answers each question. The mock test questions are input, and the user's answers are sequentially collected as output. The device then sends this answer data to the server.

[0314] Step 5:

[0315] The server receives the user's answers sent from the device and automatically scores them. Scoring is done by comparing the user's answers with pre-set correct answer data. The input is the user's answer data, and the output is the score for each question and the total score. Furthermore, the server analyzes the user's answering tendencies based on the analysis results and identifies weak areas.

[0316] Step 6:

[0317] The server stores the identified weak areas in a database. This information is used to generate the next mock test questions. The input is the analysis results, and the output is the weak areas stored in the database.

[0318] Step 7:

[0319] The server sends the newly generated mock test questions to the terminal, and the terminal notifies the user. The input is the newly generated mock test questions, and the output is the notification to the user. The user receives the notification and is ready to take the next mock test.

[0320] Step 8:

[0321] If a user has any questions during or after the mock test, they can input them through the smart glasses. The device then sends the questions to the server. The input is the user's question, and the output is the transmission of the question data to the server.

[0322] Step 9:

[0323] The server analyzes the received question and generates an appropriate answer. If necessary, it references a generative AI model and a pre-prepared FAQ database. The input is the user's question data, and the output is the generated answer. This answer is sent to the terminal and displayed to the user.

[0324] Step 10:

[0325] The terminal displays the answer received from the server to the user. The input is the answer data from the server, and the output is information provided to the user. This allows the user to immediately resolve their question.

[0326] The above is a specific flow of the processing steps of the system, and describes the inputs and outputs used in each step, as well as data processing and calculations.

[0327] 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.

[0328] This system automatically generates mock exam questions for qualification exams and provides users with an optimized learning experience. In particular, it combines an emotion engine that recognizes the user's emotional state and reflects that information in adjusting the difficulty of the mock exam and providing study advice, thereby achieving even more advanced learning support.

[0329] Program processing

[0330] Enter past exam questions

[0331] 1. User: Upload past exam questions to the system in PDF or other format.

[0332] 2. Terminal: Receives uploads from users and sends files to the server.

[0333] 3. Server: Analyzes the received files, extracts the content of the questions as text data, and identifies and classifies the format and patterns of each question.

[0334] 4. Server: Stores and organizes the analyzed data in a database.

[0335] Mock test question generation

[0336] 1. Server: Based on a database of past questions, the server runs an algorithm that learns question trends and formats, and creates templates for automatically generating mock test questions.

[0337] 2. Terminal: Notifies the user that the generated practice test questions are ready.

[0338] 3. User: Clicks on the "Start" button to begin the practice test.

[0339] Mock test implementation and result analysis

[0340] 1. User: Enter the answers to each question and click the "Submit" button after completing all answers.

[0341] 2. Terminal: Records the user's answers and sends them to the server.

[0342] 3. Server: Receives answers, automatically grades them, calculates scores, analyzes user's answer patterns, and identifies weak areas.

[0343] 4. Server: Runs the emotion engine that recognizes the user's emotional state based on the analysis results.

[0344] Utilizing the Emotion Engine

[0345] 1. Server: Adjust the difficulty of the mock test questions based on the user's recognized emotional state (e.g., impatience, anxiety, relaxation, etc.).

[0346] 2. Server: Generates learning advice and encouraging messages according to the recognized user's emotional state.

[0347] 3. Terminal: Presents the user with tailored practice questions and advice.

[0348] 4. Users: Receive advice during their learning process and retake the mock exams.

[0349] Implementing chat functionality

[0350] 1. User: Enter a question about a problem you don't understand through the terminal.

[0351] 2. Terminal: Sends the user's question data to the server.

[0352] 3. Server: Analyzes the question and generates an appropriate answer from learning data and pre-prepared FAQs.

[0353] 4. Terminal: The generated answer is displayed to the user for further understanding.

[0354] Specific examples

[0355] 1. Enter past exam questions

[0356] User: "I'll upload the past three years' worth of exam questions in PDF format."

[0357] Terminal: "File received. Sending to server..."

[0358] Server: "Parsing file... Problem data extracted."

[0359] 2. Generating mock test questions

[0360] Server: "Generate mock exam questions based on past exam data..."

[0361] Terminal: "The practice test questions are ready. Would you like to begin?"

[0362] 3. Mock test implementation and result analysis

[0363] User: "Answer question 1. I choose option C."

[0364] Terminal: "Your answer has been recorded. Would you like to proceed to the next question?"

[0365] User: "I've answered all the questions. I'm going to submit it."

[0366] Terminal: "Sending answer to server..."

[0367] Server: "Analyzing your answer... Score is 70. Weak subject is math. Current emotional state is slightly anxious."

[0368] 4. Utilizing the Emotion Engine

[0369] Server: "Generate slightly easier practice questions based on your perceived anxiety state..."

[0370] Server: "Good job! Let's try this next problem. I think you'll feel more confident if you brush up on the basics in this area."

[0371] Terminal: "New practice test questions and advice displayed."

[0372] 5. Implementing chat functionality

[0373] User: "I have a question about question 3. I don't understand option B. Can you explain it in more detail?"

[0374] Terminal: "Sending question to server..."

[0375] Server: "Parsing your question... generated a suitable answer."

[0376] Terminal: "Answers have arrived, with detailed explanations."

[0377] This system provides an efficient and personalized learning experience while taking into account the user's progress and emotional state. By combining it with an emotion engine, it reduces the user's psychological burden and enables more effective learning support.

[0378] The processing flow will be explained below.

[0379] Program processing steps

[0380] Step 1:

[0381] User: Upload past qualification exam question sets to the system in PDF or other formats.

[0382] Step 2:

[0383] Terminal: Receives uploads from users and sends files to the server.

[0384] Step 3:

[0385] Server: Analyzes the received file, extracts the question content as text data, and identifies and classifies the format and patterns of each question (e.g., words, options, answers).

[0386] Step 4:

[0387] Server: Stores the analyzed data in a database and organizes the classified problem data.

[0388] Step 5:

[0389] Server: Based on a database of past questions, the server runs an algorithm that learns question trends and formats, and creates templates for automatically generating mock test questions.

[0390] Step 6:

[0391] Terminal: Notifies the user that the generated practice test questions are ready.

[0392] Step 7:

[0393] User: Clicks on the "Start" button to begin the practice test.

[0394] Step 8:

[0395] Terminal: displays practice test questions to the user.

[0396] Step 9:

[0397] User: Enters an answer for each question, e.g., for multiple choice questions, clicks on the appropriate answer.

[0398] Step 10:

[0399] Terminal: The user's answers are recorded in real time, and after all answers are completed, they are sent to the server by clicking the "Submit" button.

[0400] Step 11:

[0401] Server: Receives all answers and automatically grades them. Calculates scores and analyzes users' answering trends.

[0402] Step 12:

[0403] Server: Based on the analysis results, identify the user's weak areas and store the weak areas information in a database.

[0404] Step 13:

[0405] Server: When generating the next mock test questions, the server reflects the information on the identified weak areas and generates questions that focus on those areas.

[0406] Step 14:

[0407] Terminal: Notifies the user that the newly generated practice test questions are ready.

[0408] Step 15:

[0409] User: Take the practice test again and continue studying.

[0410] Step 16:

[0411] User: During or after the mock test, enter questions about any questions you don't understand through the terminal.

[0412] Step 17:

[0413] Terminal: Sends the user's question data to the server.

[0414] Step 18:

[0415] Server: Analyzes the question and generates an appropriate answer from learning data and pre-prepared FAQs.

[0416] Step 19:

[0417] Terminal: Displays the generated answer to the user to help them understand it.

[0418] Step 20:

[0419] Server: During or after the user answers, the server uses an emotion engine to recognize the user's emotional state, for example, by using a facial recognition camera or voice analysis.

[0420] Step 21:

[0421] Server: Runs an algorithm that adjusts the difficulty of practice test questions based on perceived emotional state (e.g., impatience, anxiety, relaxation).

[0422] Step 22:

[0423] Server: Generates learning advice and encouraging messages according to the user's emotional state.

[0424] Step 23:

[0425] Terminal: Displays the adjusted practice test questions and generated advice to the user.

[0426] Step 24:

[0427] Users: Retry the adjusted practice questions or continue studying as advised.

[0428] This series of processes allows users to efficiently prepare for qualification exams while taking into account their own progress and emotional state, and allows them to immediately resolve any questions they may have while studying.

[0429] Example 2

[0430] 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."

[0431] Conventional mock test systems generate mock test questions based on past exam questions and analyze users' answers. However, they lacked personalized learning support, such as adjusting the difficulty level based on the user's emotional state and providing study advice. As a result, some users found the test questions to be overly difficult, while others found them too easy, preventing effective learning. Furthermore, the system provided limited intuitive support and feedback for answers, preventing users from maximizing their learning effectiveness. A system that can solve these issues and provide a more personalized learning experience is needed.

[0432] 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.

[0433] In this invention, the server includes means for receiving and analyzing past exam question data as input, means for generating mock exam questions from the analyzed data, means for receiving and analyzing the user's answers, means for identifying weak areas based on the analyzed user's answers, means for generating next mock exam questions reflecting the identified weak areas, means for the user to input questions, means for generating answers to the questions, means for recognizing the user's emotional state, means for adjusting the difficulty of mock exam questions based on the recognized emotional state, and means for generating study advice according to the emotional state, thereby enabling personalized study support according to the user's emotional state and learning progress.

[0434] "Past exam question data" refers to data that includes the content and format of questions in exams that have been administered in the past.

[0435] "Means of analysis" refers to algorithms or software that analyze input data and extract and organize meaningful information.

[0436] "Means for generating mock test questions" refers to processes and systems for creating new mock test questions using algorithms based on past test question data.

[0437] "User's answer result" is data indicating the answer selected or written by the user to the mock test question.

[0438] The "means for receiving and analyzing answer results" refers to an algorithm or system that receives answer data submitted by users and analyzes whether the answers are correct or incorrect and the trends of each answer.

[0439] The "means for identifying weak areas" refers to an algorithm and system for analyzing the user's answers and identifying categories and patterns of questions with a low rate of correct answers.

[0440] "Means for user input of questions" are interfaces and devices that allow users to input questions about a particular problem.

[0441] "Means for generating answers" refers to processes or systems that generate answers using existing databases and AI models to provide appropriate answers to questions from users.

[0442] "Means for recognizing the user's emotional state" refers to an algorithm or system for assessing the user's mental and emotional state based on the user's behavioral data, answering tendencies, data from sensor devices, etc.

[0443] The "means for adjusting the difficulty of the mock test questions" refers to an algorithm and system for appropriately changing the difficulty of the mock test questions given in accordance with the user's emotional state and learning progress.

[0444] A "means for generating study advice" is an algorithm or system used to generate personalized study methods and encouraging messages based on the user's study situation and emotional state.

[0445] This invention is a system that automatically generates mock exam questions for qualification exams and provides users with an optimized learning experience. In particular, this system is equipped with an emotion engine that recognizes the user's emotional state and reflects this in adjusting the difficulty level of the mock exam and providing study advice, thereby achieving more advanced learning support.

[0446] System configuration

[0447] The system consists of three main components: a server, a terminal, and a user. The functions and specific operations of each component are explained below.

[0448] Enter past exam questions

[0449] 1. User: Upload past exam question collections to the system in PDF format. The user clicks the "Upload" button on the system interface and selects the PDF file from the file selection dialog.

[0450] 2. Terminal: Receives uploads from users and sends files to the server. The terminal sends files to the server via HTTP requests and displays a progress bar.

[0451] 3. Server: The received file is analyzed and the problem content is extracted as text data. Specifically, optical character recognition (OCR) software (e.g., Tesseract) is used to convert the PDF file into text data. Natural language processing (NLP) techniques are then used to identify problem formats and patterns. The analyzed data is then stored in a database (e.g., MySQL).

[0452] Mock test question generation

[0453] 1. Server: Learns question trends and formats based on a database of past questions. This is done using machine learning models (e.g., random forests, neural networks). Generates mock test question templates based on the learning results.

[0454] 2. Terminal: Notify the user that the generated practice test questions are ready, using a pop-up message or notification badge (e.g., "New practice test questions are available").

[0455] 3. User: Clicks the "Start" button to begin the mock test. The user clicks the "Start Test" button on the dashboard screen and moves to the test screen.

[0456] Mock test implementation and result analysis

[0457] 1. User: Enter the answer for each question and click the "Submit" button. The user selects or enters the answer for each question and clicks the "Submit" button after answering all questions.

[0458] 2. Terminal: Records the user's answers and sends them to the server. The answer data is sent to the server using an HTTP request.

[0459] 3. Server: Receives the answers and automatically scores them. The server compares the answers with the correct answer database and assigns a score. The server then analyzes the user's answering tendencies based on the analysis results and identifies weak areas.

[0460] 4. Server: Runs the emotion engine to recognize emotional states based on the analysis results, using data from emotion analysis APIs and sensor devices.

[0461] Utilizing the Emotion Engine

[0462] 1. Server: Adjust the difficulty of the mock test questions based on the user's perceived emotional state. Reset the difficulty parameters according to the user's emotional state (e.g., impatience, anxiety, relaxation).

[0463] 2. Server: Generates learning advice based on the user's emotional state. Natural language generation (NLG) technology is used to generate encouraging messages and advice on how to study.

[0464] 3. Terminal: The adjusted mock test questions and advice are presented to the user. The user then takes the advice into consideration and attempts a new mock test.

[0465] Implementing chat functionality

[0466] 1. User: Enter a question about a problem they don't understand. Open a chat window, enter a question, and click the send button.

[0467] 2. Terminal: Sends the question data to the server. Sends the question via HTTP request and displays a progress bar.

[0468] 3. Server: Analyzes the question and generates an appropriate answer from training data and FAQs. Answers are generated using natural language processing (NLP) technology and generative AI models (e.g., GPT-3).

[0469] 4. Terminal: Show the generated answer to the user. Show the answer in the chat window to help the user understand.

[0470] Specific examples

[0471] Enter past exam questions

[0472] User: "I'll upload the past three years' worth of exam questions in PDF format."

[0473] Terminal: "File received. Sending to server..."

[0474] Server: "Parsing file... Problem data extracted."

[0475] Mock test question generation

[0476] Server: "Generate mock exam questions based on past exam data..."

[0477] Terminal: "The practice test questions are ready. Would you like to begin?"

[0478] Mock test implementation and result analysis

[0479] User: "Answer question 1. I choose option C."

[0480] Terminal: "Your answer has been recorded. Would you like to proceed to the next question?"

[0481] User: "I've answered all the questions. I'm going to submit it."

[0482] Terminal: "Sending answer to server..."

[0483] Server: "Analyzing your answer... Score is 70. Weak subject is math. Current emotional state is slightly anxious."

[0484] Utilizing the Emotion Engine

[0485] Server: "Generate slightly easier practice questions based on your perceived anxiety state..."

[0486] Server: "You're doing great. I think you'll gain confidence if you brush up on the basics in this area."

[0487] Terminal: "New practice test questions and advice displayed."

[0488] Implementing chat functionality

[0489] User: "I have a question about question 3. I don't understand option B. Can you explain it in more detail?"

[0490] Terminal: "Sending question to server..."

[0491] Server: "Parsing your question... generated a suitable answer."

[0492] Terminal: "Answers have arrived, with detailed explanations."

[0493] This system provides an efficient and personalized learning experience while taking into account the user's progress and emotional state. By combining it with an emotion engine, it reduces the user's psychological burden and enables more effective learning support.

[0494] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0495] Step 1:

[0496] User: Upload past qualification exam question sets to the system in PDF or other formats.

[0497] Specific operation: The user clicks the "Upload" button on the system interface and selects a PDF file from the file selection dialog.

[0498] Input: Past exam question collection file in PDF format.

[0499] Output: The upload request is sent to the device.

[0500] Step 2:

[0501] Terminal: Receives uploads from users and sends files to the server.

[0502] Specific operation: The terminal sends the file to the server via an HTTP request and displays a progress bar.

[0503] Input: PDF file uploaded by user.

[0504] Output: The file is sent to the server.

[0505] Step 3:

[0506] Server: Analyzes the received file and extracts the problematic content as text data.

[0507] How it works: The server uses OCR (Optical Character Recognition) software (e.g., Tesseract) to convert PDF files into text data, and uses Natural Language Processing (NLP) techniques to identify problem formats and patterns. The parsed data is then stored in a database (e.g., MySQL).

[0508] Input: The PDF file sent to the server.

[0509] Output: Parsed problem information as text data.

[0510] Step 4:

[0511] Server: Learn question trends and formats based on a database of past questions.

[0512] Specific operation: Using machine learning models (e.g., random forests, neural networks), the system learns from past exam data and generates mock exam question templates based on the learning results.

[0513] Input: Past question data stored in the database.

[0514] Output: Generated mock exam question templates.

[0515] Step 5:

[0516] Terminal: Notifies the user that the generated practice test questions are ready.

[0517] Specific behavior: When a device receives a notification from the server, it displays a pop-up message or notification badge (e.g., "New practice test questions are available.").

[0518] Input: Notification information from the server.

[0519] Output: A notification message to the user.

[0520] Step 6:

[0521] User: Clicks on the "Start" button to begin the practice test.

[0522] Specific operation: The user clicks the "Start test" button on the dashboard screen to transition to the test screen.

[0523] Input: User action (button click).

[0524] Output: Transition to mock test screen.

[0525] Step 7:

[0526] User: Enter the answer to each question and click the "Submit" button.

[0527] Specific operation: The user selects or enters an answer for each question, and when all questions have been answered, clicks the "Submit" button.

[0528] Input: User's answer data.

[0529] Output: All answer data is recorded on the device.

[0530] Step 8:

[0531] Terminal: Records the user's answers and sends them to the server.

[0532] Specific operation: The device temporarily stores all answer data and sends it to the server using an HTTP request. A progress bar is displayed.

[0533] Input: User's answer data.

[0534] Output: The answer data is sent to the server.

[0535] Step 9:

[0536] Server: Receives answers, automatically grades them, calculates scores, analyzes user's answer patterns, and identifies weak areas.

[0537] Specific operations: Compare answers with a database of correct answers and perform scoring. Analyze answer trends and identify weak areas using statistical methods. Store data on weak areas in a database.

[0538] Input: Answer data and correct answer database.

[0539] Output: Scores and analysis results.

[0540] Step 10:

[0541] Server: Runs the emotion engine that recognizes the user's emotional state based on the analysis results.

[0542] Specific operation: Executes emotion recognition algorithms using analytical data and data from sensor devices.

[0543] Input: Analysis results and sensor device data.

[0544] Output: The user's emotional state.

[0545] Step 11:

[0546] Server: Adjusts the difficulty of practice test questions based on perceived emotional state.

[0547] Specific operation: Using the emotional state, the parameters of the mock test question generation algorithm are reset to adjust the difficulty level.

[0548] Input: User's emotional state and mock test template.

[0549] Output: Difficulty-adjusted practice test questions.

[0550] Step 12:

[0551] Server: Generates learning advice and encouraging messages depending on the recognized emotional state.

[0552] What it does: Uses natural language generation (NLG) technology to generate personalized advice and encouraging messages for users.

[0553] Input: The user's emotional state.

[0554] Output: Study advice and encouraging messages.

[0555] Step 13:

[0556] Terminal: Presents tailored practice test questions and advice to the user.

[0557] Specific operation: Receives data from the server and displays it on the device's UI.

[0558] Input: Tailored practice test questions and advice.

[0559] Output: What is displayed to the user.

[0560] Step 14:

[0561] Users: Receive advice as they progress and retake practice exams.

[0562] Specific operation: The user takes the advice provided into consideration and takes on a new mock test.

[0563] Enter: study advice.

[0564] Output: The mock test to try again.

[0565] Step 15:

[0566] User: Type in a question about a problem they don't understand.

[0567] What happens: A user opens a chat window, types a question, and clicks the send button.

[0568] Input: The user's question.

[0569] Output: Sending the question data by terminal.

[0570] Step 16:

[0571] Terminal: Sends the query data to the server.

[0572] Specific behavior: Sends a question via HTTP request and displays a progress bar.

[0573] Input: User question data.

[0574] Output: The query data is sent to the server.

[0575] Step 17:

[0576] Server: Analyzes the question and generates an appropriate answer from learning data and FAQs.

[0577] Specific operation: Generate answers using natural language processing (NLP) techniques and generative AI models (e.g., GPT-3).

[0578] Input: User question data.

[0579] Output: The generated answer.

[0580] Step 18:

[0581] Terminal: Displays the generated answer to the user.

[0582] Specific behavior: Displays the response received from the server in the chat window.

[0583] Input: The generated answer.

[0584] Output: Display the answer to the user.

[0585] (Application example 2)

[0586] 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."

[0587] Conventional qualification exam preparation systems have limited functionality for improving users' learning efficiency. In particular, they provide questions of a uniform level of difficulty without considering the user's emotional state, making it impossible to reduce the psychological burden during study. Furthermore, there is a lack of appropriate study support methods for effectively utilizing travel time in an autonomous vehicle. As a result, users tend to lose motivation to study, making it difficult to prepare for exams efficiently.

[0588] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving and analyzing past exam question data as input, means for generating mock exam questions from the analyzed data, means for receiving and analyzing the user's answers, means for identifying weak areas based on the analyzed user's answers, means for generating the next mock exam questions reflecting the identified weak areas, means for recognizing the user's emotional state in the autonomous vehicle, means for adjusting the difficulty of the mock exam questions based on the recognized emotional state, means for generating study advice and messages according to the recognized emotional state, means for the user to input a question, and means for generating an answer to the question. This enables flexible and personalized study support based on the user's emotional state.

[0589] "Past exam question data" refers to data on questions from past qualification exams, and is information stored in text format or scanned PDF format.

[0590] "Mock test questions" refer to virtual test questions that are generated based on past test question data and that users can answer as part of their exam preparation.

[0591] "Autonomous vehicle" means a vehicle that is driven automatically by on-board sensors and technological processing devices, without a human driver.

[0592] An "emotional state" is a psychological state that a user exhibits while answering a practice test, and examples include inner feelings such as impatience, anxiety, and relaxation.

[0593] "Adjusting the difficulty level" refers to the process of changing the difficulty of the mock test questions according to the user's emotional state and learning progress.

[0594] "Study advice" refers to specific advice and guidance provided to users to help them study effectively.

[0595] "Messages" refer to verbal notifications and encouraging statements that are generated based on the user's emotional state and answer status.

[0596] "Means for inputting questions" refers to an interface that allows users to inquire about any unclear points or doubts they may have during the mock test by inputting text or other methods to the system.

[0597] "Automatic scoring" refers to the process in which the system automatically calculates and evaluates the score based on the user's answers.

[0598] The term "weak area" refers to a learning area in which the user has been determined to have a low score and insufficient understanding, as identified from past answer results, etc.

[0599] This invention is a system that automatically generates mock exam questions for qualification exams and provides a learning experience that takes into account the user's emotional state. It is specifically designed to streamline learning in autonomous vehicles. The system is constructed as follows:

[0600] The entire system consists of the user's smartphone or tablet, a cloud server, an emotion recognition API, a natural language processing model, and a camera and microphone installed in the autonomous vehicle.

[0601] Input and analysis of past questions

[0602] Users use their smartphones or tablets to upload past exam question data in PDF format to a cloud server. The cloud server then uses a PDF analysis algorithm to convert the question data into text format, then identifies the format and patterns of each question and stores them in a database. This process can utilize cloud services such as Amazon Web Services (AWS®) and Google Cloud Platform (GCP).

[0603] Mock test question generation

[0604] The cloud server automatically generates mock test questions using a generative AI model (e.g., GPT-3 / 4) based on the stored past exam data. The generated questions are then sent to the user's smartphone or tablet.

[0605] User answers and analysis

[0606] Users answer mock test questions, and their answers are sent to a cloud server in real time. The cloud server automatically grades the answers and calculates the score. It also analyzes the user's answering habits and identifies weak areas.

[0607] Recognition and application of emotional states

[0608] The system uses cameras and microphones installed in autonomous vehicles to recognize the user's emotional state in real time. Emotion recognition utilizes Microsoft® Azure® Face API and Amazon Rekognition. The recognized emotional state (e.g., impatience, anxiety, relaxation, etc.) is analyzed on a cloud server, and the system adjusts the difficulty of the mock test questions and generates study advice and messages based on that information.

[0609] Questions and Answers

[0610] An interface is also provided for users to input any questions or concerns they may have during the mock test. The cloud server analyzes the user's questions using a natural language processing model (e.g., GPT-3 / 4) and generates appropriate answers. The generated answers are provided to the user in real time.

[0611] Specific examples

[0612] The user uploads the past five years of driving test question sets in PDF format from their smartphone to a cloud server.

[0613] The cloud server analyzes the file and extracts the problem data.

[0614] The server generates mock test questions based on past exam question data.

[0615] The user answers the practice test and sends the answers to the cloud server.

[0616] Your score will be automatically scored and you will be notified of your score and weak areas.

[0617] A camera and microphone are used to recognize the user's emotions inside an autonomous vehicle.

[0618] The server adjusts the difficulty of the mock test based on the emotional state and generates study advice.

[0619] The user enters a question, and the cloud server uses natural language processing to generate an appropriate answer.

[0620] Prompt Sentence Examples

[0621] Below are some example prompts for a generative AI model (e.g., GPT-3 / 4):

[0622] "The user is working on a mock exam in a self-driving vehicle. Provide appropriate advice based on the following information: mock exam score: 50; weaknesses: traffic rules; current emotional state: anxiety."

[0623] This enables flexible and personalized learning support based on the user's emotional state.

[0624] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0625] Step 1:

[0626] The user uploads past qualification exam question data in PDF format to a smartphone or tablet.

[0627] Input: Past exam data (PDF file)

[0628] Output: Uploaded PDF file

[0629] Specific operation: The user selects past exam question data from their device and clicks the upload button.

[0630] Step 2:

[0631] The device sends the uploaded PDF file to the cloud server.

[0632] Input: Uploaded PDF file

[0633] Output: PDF file sent to cloud server

[0634] Specific operation: The device receives the file and sends it to the cloud server via the network.

[0635] Step 3:

[0636] The server uses a PDF analysis algorithm to convert the PDF file into text data and identify problem formats and patterns.

[0637] Input: PDF file sent to the cloud server

[0638] Output: Textual problem data and identified format patterns

[0639] Specific operation: The server uses PDF analysis software (e.g., Tesseract OCR) to extract text data from the PDF, and then identifies the format and patterns of each question and stores them in a database.

[0640] Step 4:

[0641] Based on the past exam data stored on the server, mock exam questions are automatically generated using a generative AI model (e.g., GPT-3 / 4).

[0642] Input: Textual problem data and identified format patterns

[0643] Output: Generated practice test questions

[0644] Specific operation: The server learns question trends and formats from the stored data, generates new mock test questions using a generative AI model, and stores them in a database.

[0645] Step 5:

[0646] The terminal notifies the user that the practice test questions are ready.

[0647] Input: Generated practice test questions

[0648] Output: A message to inform the user

[0649] Specific operation: The terminal receives a notification from the server and notifies the user by message that the mock test is ready.

[0650] Step 6:

[0651] The user starts the practice test and enters answers to the questions.

[0652] Input: Generated practice test questions

[0653] Output: User's answer

[0654] Specific operation: The user inputs answers to each question on the terminal and records the answers on the terminal.

[0655] Step 7:

[0656] The device sends the user's answer to the cloud server.

[0657] Input: User's answer

[0658] Output: Answers sent to the cloud server

[0659] Specific operation: The device sends the recorded answers to the server via the network.

[0660] Step 8:

[0661] The server automatically grades the answers and calculates the score. It also analyzes the user's answering tendencies and identifies weak areas.

[0662] Input: Answers sent to the cloud server

[0663] Output: Marking results, scores, weak areas identified

[0664] Specific operation: The server executes the automatic scoring algorithm to calculate the score, and also uses the analysis algorithm to analyze the user's answering tendencies and identify weak areas.

[0665] Step 9:

[0666] Using cameras and microphones mounted on autonomous vehicles, the system recognizes the user's emotional state in real time.

[0667] Input: Real-time video and audio data from cameras and microphones

[0668] Output: Perceived emotional state

[0669] Specific operation: The cloud server uses an emotion recognition API (e.g., Amazon Rekognition or Microsoft Azure Face API) to analyze video and audio data and recognize the user's emotional state.

[0670] Step 10:

[0671] The server adjusts the difficulty of the practice test questions and generates study advice and messages based on the recognized emotional state.

[0672] Input: perceived emotional state, marking results, score, weak areas identified

[0673] Output: Tailored practice questions, study advice, and messages

[0674] Specific operation: The server changes the difficulty level of the practice test questions based on the user's emotional state and generates appropriate study advice and encouraging messages for the user.

[0675] Step 11:

[0676] The device presents the user with tailored practice test questions and study advice.

[0677] Input: Tailored practice test questions, study advice, messages

[0678] Output: What the user sees

[0679] Specific operation: The terminal receives information from the server and presents it on the screen in a format that is easy for the user to see.

[0680] Step 12:

[0681] The user inputs questions using an interface for inputting uncertainties or questions during the mock test.

[0682] Input: User question

[0683] Output: Question typed into the terminal

[0684] Specific operation: The user inputs a question through an input box on the terminal.

[0685] Step 13:

[0686] The device sends the user's question to the cloud server.

[0687] Input: User question

[0688] Output: Questions sent to the cloud server

[0689] Specific operation: The device sends the question to the server via the network.

[0690] Step 14:

[0691] The server analyzes the question and generates an appropriate answer.

[0692] Input: The question sent to the cloud server

[0693] Output: The generated answer

[0694] Specific operation: The server uses a natural language processing model (e.g., GPT-3 / 4) to analyze the question and generate an appropriate answer.

[0695] Step 15:

[0696] The terminal displays the generated answer to the user.

[0697] Input: Generated Answer

[0698] Output: The answer displayed to the user

[0699] Specific operation: The terminal receives the response from the server and presents it on the screen in an easy-to-read format for the user.

[0700] 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.

[0701] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0702] 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.

[0703] [Second embodiment]

[0704] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0705] 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.

[0706] 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).

[0707] 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.

[0708] 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.

[0709] 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).

[0710] 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.

[0711] 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.

[0712] 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.

[0713] 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.

[0714] 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.

[0715] 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."

[0716] This invention is a system that automatically generates mock exam questions for qualification exams, providing users with an optimized learning experience. This system analyzes past exam question data, identifies weak areas based on the user's answers, and generates new mock exam questions that reflect this information. It also provides a function that allows users to ask questions that arise during their studies and provides instant answers.

[0717] Program processing

[0718] 1. Enter past exam questions

[0719] User: Upload past qualification exam question sets to the system in PDF or other formats.

[0720] Terminal: Receives uploads from users and sends files to the server.

[0721] Server: Analyzes the received file, extracts the content of the questions as text data, identifies the format and patterns of each question (e.g., words, options, answers), and stores them in a database.

[0722] 2. Generating mock test questions

[0723] Server: Generates mock test questions based on the analyzed data. It runs an algorithm that learns the patterns and formats of past exam questions and creates new mock questions.

[0724] Terminal: Prepares the generated practice test questions for display to the user.

[0725] User: When you are ready to take the practice test, click the "Start" button on your device.

[0726] 3. Mock test implementation and result analysis

[0727] User: Answer each question one by one, for example, by clicking on the appropriate answer for multiple choice questions.

[0728] Terminal: Records the user's answers in real time, and when all answers have been completed, the user clicks the "Submit" button, which sends the data to the server.

[0729] Server: Receives all answers and automatically scores them. Based on the scores and analysis results, analyzes the user's answering tendencies and identifies weak areas.

[0730] 4. Identify weaknesses and personalize

[0731] Server: Based on the analysis results, the user's weak areas (e.g., specific subjects or question formats) are stored in a database.

[0732] Server: When generating the next mock test questions, this weak area information is reflected and questions that focus on that area are generated.

[0733] Terminal: Prepares to display the newly generated practice test questions and notifies the user.

[0734] Users: They can take the mock exam again and get further learning benefits.

[0735] 5. Implementing chat functionality

[0736] User: During or after the mock test, if there are any questions that the user does not understand, the user can enter the questions through the terminal.

[0737] Terminal: Sends the user's question data to the server.

[0738] Server: Analyzes the question and generates an appropriate answer from training data and pre-prepared FAQs, including detailed explanations and additional references if necessary.

[0739] Terminal: Displays the generated answer to the user for further understanding.

[0740] Specific examples

[0741] 1. Enter past exam questions

[0742] User: "I'll upload the past three years' worth of exam questions in PDF format."

[0743] Terminal: "File received. Sending to server..."

[0744] Server: "Parsing file... Problem data extracted."

[0745] 2. Generating mock test questions

[0746] Server: "Generate mock exam questions based on past exam data..."

[0747] Terminal: "The practice test questions are ready. Would you like to begin?"

[0748] 3. Mock test implementation and result analysis

[0749] User: "Answer question 1. I choose option C."

[0750] Terminal: "Your answer has been recorded. Would you like to proceed to the next question?"

[0751] User: "I've answered all the questions. I'm going to submit it."

[0752] Terminal: "Sending answer to server..."

[0753] Server: "Analyzing your answer... Score 70. Math is my weak point."

[0754] 4. Identify weaknesses and personalize

[0755] Server: "We've saved your weak areas and will incorporate them into your next practice test."

[0756] Terminal: "New practice test questions are ready. Would you like to begin?"

[0757] 5. Implementing chat functionality

[0758] User: "I have a question about question 3. I don't understand option B. Can you explain it in more detail?"

[0759] Terminal: "Sending question to server..."

[0760] Server: "Parsing your question... generated a suitable answer."

[0761] Terminal: "Answers have arrived, with detailed explanations."

[0762] Through this system, users can efficiently prepare for qualification exams while checking their own progress and weak points. In addition, they can instantly resolve any questions they have, significantly improving their learning efficiency.

[0763] The processing flow will be explained below.

[0764] Program processing steps

[0765] Step 1:

[0766] User: Upload past qualification exam question sets to the system in PDF or other formats.

[0767] Step 2:

[0768] Terminal: Receives uploads from users and sends files to the server.

[0769] Step 3:

[0770] Server: Analyzes the received file, extracts the question content as text data, and identifies and classifies the format and patterns of each question (e.g., words, options, answers).

[0771] Step 4:

[0772] Server: Stores the analyzed data in a database and organizes the classified problem data.

[0773] Step 5:

[0774] Server: Based on a database of past questions, the server runs an algorithm that learns question trends and formats, and creates templates for automatically generating mock test questions.

[0775] Step 6:

[0776] Terminal: Notifies the user that the generated practice test questions are ready.

[0777] Step 7:

[0778] User: Clicks on the "Start" button to begin the practice test.

[0779] Step 8:

[0780] Terminal: displays practice test questions to the user.

[0781] Step 9:

[0782] User: Enters an answer for each question, e.g., for multiple choice questions, clicks on the appropriate answer.

[0783] Step 10:

[0784] Terminal: The user's answers are recorded in real time, and after all answers are completed, they are sent to the server by clicking the "Submit" button.

[0785] Step 11:

[0786] Server: Receives all answers and automatically grades them. Calculates scores and analyzes users' answering trends.

[0787] Step 12:

[0788] Server: Based on the analysis results, identify the user's weak areas and store the weak areas information in a database.

[0789] Step 13:

[0790] Server: When generating the next mock test questions, the server reflects the information on the identified weak areas and generates questions that focus on those areas.

[0791] Step 14:

[0792] Terminal: Notifies the user that the newly generated practice test questions are ready.

[0793] Step 15:

[0794] User: Take the practice test again and continue studying.

[0795] Step 16:

[0796] User: During or after the mock test, enter questions about any questions you don't understand through the terminal.

[0797] Step 17:

[0798] Terminal: Sends the user's question data to the server.

[0799] Step 18:

[0800] Server: Analyzes the question and generates an appropriate answer from learning data and pre-prepared FAQs.

[0801] Step 19:

[0802] Terminal: Displays the generated answer to the user to help them understand it.

[0803] This series of processes allows users to efficiently prepare for the qualification exam and also allows them to immediately resolve any questions they may have while studying.

[0804] Example 1

[0805] 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."

[0806] Conventional qualification exam study systems lack the ability to properly identify users' weak areas and focus their learning on those areas, as well as the ability to record answers in real time and provide immediate feedback. Furthermore, they lack the ability to provide immediate solutions to questions users may have during the exam. This can lead to lower user learning efficiency and potentially lower pass rates for qualification exams.

[0807] 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.

[0808] In this invention, the server includes means for receiving and analyzing past exam question data as input, means for generating mock exam questions from the analyzed data, means for receiving and analyzing the user's answers, means for identifying weak areas based on the analyzed user's answers, means for generating the next mock exam questions reflecting the identified weak areas, means for the user to input questions, means for generating answers to the questions, means for saving the weak areas in a database, means for recording answers during the mock exam in real time, and means for learning a model based on the database of past questions. This makes it possible to identify the user's weak areas and have them study them intensively, and can provide immediate answers to any questions that arise during study, thereby significantly improving study efficiency.

[0809] "Past exam question data" refers to information about questions and answers from previous exams.

[0810] "Means of analysis" is a function for analyzing input data and extracting and identifying useful information.

[0811] "Mock test questions" are provisional test questions that users answer as practice to prepare for the actual test.

[0812] "Means of generation" refers to the function for creating new information and content based on data.

[0813] "User's answer results" are answers selected by the user to the mock test questions and answer information.

[0814] A "weak area" is an area in which a user shows low scores in a particular genre or theme based on the results of a mock test.

[0815] "Means for inputting questions" refers to an interface or function that allows users to input doubts or questions to the system.

[0816] The "means for generating an answer" is a function for creating and providing an appropriate answer to a question entered by a user.

[0817] "Means for storing in a database" refers to the function of storing analyzed information and data for the long term and retrieving it as needed.

[0818] "Means for recording in real time" is a function for instantly recording information on a user's actions or answers the moment they occur.

[0819] "Means of learning the model" is a feature that allows the algorithm to learn patterns and rules using past data so that it can adapt to new situations.

[0820] The present invention provides a system for automatically generating mock questions for qualification examinations and providing users with an optimized learning experience. This system is realized through the interaction of a server, a terminal, and a user.

[0821] First, a user uploads past exam question data to the system in a file format such as PDF. The terminal receives the uploaded file and sends it to the server. The server analyzes the received PDF file and extracts text data using a file analysis tool (Apache PDFBox as a specific example). It then uses a Natural Language Processing (NLP) model (spaCy or NLTK as a specific example) to identify information about the questions, options, and answers, and stores this information in a database.

[0822] Next, the server generates mock test questions by learning the patterns and trends of each question using a machine learning algorithm (specifically, GPT-3 or BERT) based on a database of past questions. The generated mock test questions are sent to the device and displayed on the user interface. The user then clicks the start mock test button to begin the test.

[0823] During the mock test, the user answers each question and clicks the next button to proceed. The device records the user's answers in real time, and when the "Submit" button is clicked after the test is completed, the answer data is sent to the server. The server automatically scores the received answer data and calculates the user's score using a specific algorithm (for example, Scikit-learn or TensorFlow). It also analyzes answer trends and records specific weak areas in a database.

[0824] After identifying weak areas, the server adjusts the algorithm to include content that emphasizes the user's weak areas when generating the next mock test questions, and prepares to display them on the device, allowing the user to focus on studying their weak areas.

[0825] During or after the mock test, users can enter questions about problems they didn't understand in the chat box. The device sends the entered question to the server, which analyzes it using an NLP model (specifically, BERT or GPT-3) to generate an appropriate answer. The generated answer references FAQ data and related materials in the database, and the device displays it to the user.

[0826] Specific examples

[0827] Enter past exam questions

[0828] User: "I'll upload the past three years' worth of exam questions in PDF format."

[0829] Terminal: "File received. Sending to server..."

[0830] Server: "Parsing file... Problem data extracted."

[0831] Mock test question generation

[0832] Server: "Generate mock exam questions based on past exam data..."

[0833] Terminal: "The practice test questions are ready. Would you like to begin?"

[0834] Mock test implementation and result analysis

[0835] User: "Answer question 1. I choose option C."

[0836] Terminal: "Your answer has been recorded. Would you like to proceed to the next question?"

[0837] User: "I've answered all the questions. I'm going to submit it."

[0838] Terminal: "Sending answer to server..."

[0839] Server: "Analyzing your answer... Score 70. Math is my weak point."

[0840] Identifying weaknesses and personalizing

[0841] Server: "We've saved your weak areas and will incorporate them into your next practice test."

[0842] Terminal: "New practice test questions are ready. Would you like to begin?"

[0843] Implementing chat functionality

[0844] User: "I have a question about question 3. I don't understand option B. Can you explain it in more detail?"

[0845] Terminal: "Sending question to server..."

[0846] Server: "Parsing your question... generated a suitable answer."

[0847] Terminal: "Answers have arrived, with detailed explanations."

[0848] Through this system, users can effectively prepare for qualification exams, identify their weaknesses through mock tests, and deepen their understanding. Real-time feedback and answers to questions also greatly improve learning efficiency.

[0849] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0850] Step 1: Upload past exam questions

[0851] User: Prepare past exam question data in PDF format and click the upload button on the device.

[0852] Input: Past exam question data (PDF file).

[0853] Terminal: Receives the PDF file from the user and sends it to the server in bytes.

[0854] Output: The PDF file sent to the server.

[0855] Specific operation: A file selection window is displayed, and after the user selects the target file, the upload operation is performed.

[0856] Step 2: Analyzing the file contents

[0857] Server: Convert the received PDF file into text data using a file analysis tool (such as Apache PDFBox).

[0858] Input: PDF file.

[0859] Server: The converted text data is processed using an NLP model (such as spaCy or NLTK) to identify test questions, answer choices, and answers.

[0860] Output: Structured exam question data.

[0861] What it does: It uses a PDF parsing library to extract text from PDFs and then uses an NLP model to perform natural language processing and identify specific patterns.

[0862] Step 3: Saving to the database

[0863] Server: Stores the analyzed problem data in a database (e.g., MySQL or PostgreSQL).

[0864] Input: Structured exam question data.

[0865] Output: Exam question data stored in a database.

[0866] What it does: Establishes a database connection and saves data using an SQL query.

[0867] Step 4: Generate practice test questions

[0868] Server: Generates new mock test questions using generative AI models (such as GPT-3 and BERT) based on past questions in the database.

[0869] Input: Past exam data in the database.

[0870] Output: Generated practice test questions.

[0871] What it does: Apply machine learning algorithms to generate and format new problem data.

[0872] Step 5: Prepare to view the practice test questions

[0873] Terminal: Receives the generated practice test questions and prepares them for display on the user interface.

[0874] Input: Generated practice test questions.

[0875] Output: Practice test questions displayed in the user interface.

[0876] What it does: Formats problem data and converts it into HTML or JSON for display in a browser or app interface.

[0877] Step 6: Start the practice test

[0878] User: Click the Start Practice Test button to begin the practice test.

[0879] Input: User's starting instructions.

[0880] Terminal: Displays test questions sequentially and accepts user answers in input format.

[0881] Output: The answer from the user.

[0882] Specific operation: When the start button is pressed, the screen will move to the question display screen and prepare the answer input field.

[0883] Step 7: Record and submit your answers

[0884] User: Answer each question and click the next button to proceed.

[0885] Input: User's answer data.

[0886] Terminal: Each answer is recorded in real time, and the answer data is sent to the server when the "Submit" button is clicked after the test is completed.

[0887] Output: The answer data sent to the server.

[0888] Specific operation: Once the answer has been entered, the next question will be displayed, and once all questions have been completed, the answer data will be sent to the server.

[0889] Step 8: Scoring and analyzing results

[0890] Server: Based on the received answer data, the server automatically scores the answers. Specifically, it calculates the score using an algorithm (such as Scikit-learn or TensorFlow).

[0891] Input: User's answer data.

[0892] Output: User's score and weak areas analysis.

[0893] Specific operation: The received data is input into the evaluation algorithm for scoring and performance analysis.

[0894] Step 9: Record your weaknesses

[0895] Server: Based on the analysis results, identify the weak areas of each user and store them in a database.

[0896] Input: User scores and analysis results.

[0897] Output: Weakness information stored in a database.

[0898] Specific operation: Analysis results are added and saved to the user profile in the database.

[0899] Step 10: Generate new practice questions

[0900] Server: When generating the next mock test questions, generate new questions that focus on the user's weak areas.

[0901] Input: Data on weak areas.

[0902] Output: The newly generated practice test questions.

[0903] Specific operation: Refer to information on weak areas and use a generative AI model to generate specialized questions.

[0904] Step 11: Notification of new practice test questions

[0905] Terminal: Prepares to display the generated practice test questions and notifies the user.

[0906] Input: Newly generated practice test questions.

[0907] Output: The new practice test question and notification message displayed in the user interface.

[0908] Specific behavior: Convert new problem data into a display format and notify the user, for example, with a notification banner.

[0909] Step 12: Submit your question

[0910] Users: During or after the mock exam, type questions into the chat box about any questions they didn't understand.

[0911] Input: The user's question.

[0912] Terminal: Sends the query data to the server.

[0913] Output: The query data sent to the server.

[0914] Specific operation: Questions entered in the chat box are transferred to the server in real time.

[0915] Step 13: Parsing the question and generating an answer

[0916] Server: Analyzes the question using an NLP model (such as BERT or GPT-3) and generates an appropriate answer.

[0917] Input: User question data.

[0918] Output: The generated answer.

[0919] Specific operation: Performs natural language processing of the question and generates an answer based on FAQ data and related materials in the database.

[0920] Step 14: View your answers

[0921] Terminal: Displays the generated answers in a user interface.

[0922] Input: Generated response data.

[0923] Output: The answer displayed in the user interface.

[0924] Specific operation: Convert the response data into an appropriate format and display it on the chat screen, etc.

[0925] In this way, by clearly indicating the specific operations, inputs, and outputs at each processing step, it is possible to understand in detail how the user, terminal, and server cooperate to operate the entire system.

[0926] (Application example 1)

[0927] 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."

[0928] When studying for qualification exams, users need more than just past exam question collections; they need effective study methods that focus on their weak areas. There is also a lack of ways to instantly resolve questions that arise during study. Furthermore, there is the challenge of providing these exam preparation materials using smart devices, regardless of location or time.

[0929] 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.

[0930] In this invention, the server includes a means for scanning past exam papers with a camera and transmitting the data to the server, a means for the user to take the mock exam through smart glasses, and a means for automatically scoring all answers and displaying the analysis results to the user, allowing the user to study efficiently and effectively anywhere and quickly resolve any questions.

[0931] "Past exam question data" refers to digital records of the content of questions from previous qualification exams.

[0932] An "analyzing means" is a computer program or algorithm that processes input data and analyzes it to understand its content and characteristics.

[0933] "Mock test questions" are virtual test questions that users answer as practice in preparation for the actual test.

[0934] "User" means an individual or learner who uses this system to prepare for a qualification exam.

[0935] "Answer results" are the contents of the answers provided by the user to the mock test.

[0936] "Weak areas" refer to areas or subjects in which the user frequently gets exam questions wrong.

[0937] A "question" is an inquiry about content that the user found difficult to understand during the mock test or during study.

[0938] An "answer" is an explanation or information provided in response to a user's question.

[0939] "Camera scanning" means using a camera to capture a digital image of a physical document and convert its contents into digital data.

[0940] A "server" is a powerful computer system for storing, processing, and serving data.

[0941] "Smart glasses" are eyeglass-shaped devices equipped with a display and computer functionality that allow the wearer to obtain visual information.

[0942] "Automatic scoring" is a function in which the system evaluates the user's answers and calculates the score.

[0943] "Analysis results" are information about the user's learning tendencies and weak areas that the system derives from the user's answers.

[0944] The present invention enables users to effectively study for qualification exams by using practice tests. The system includes a server, a terminal (e.g., smart glasses), and a user interface.

[0945] Program Generation and Explanation

[0946] 1. Enter past exam questions

[0947] The user scans a collection of past qualification exam questions with the camera in the smart glasses and sends the data to the server.

[0948] The server uses OCR (Optical Character Recognition) technology to convert the contents of the scanned question set into digital text, identify the question format and patterns, and store them in a database (e.g., using Google Cloud Vision API).

[0949] 2. Generating mock test questions

[0950] The server generates mock test questions based on the stored data, learning the patterns and formats of past questions and creating new mock questions using a generative AI model (e.g., TensorFlow).

[0951] The terminal prepares to display the generated practice test questions to the user.

[0952] 3. Mock test implementation and result analysis

[0953] Users take practice tests through smart glasses and input their answers to each question.

[0954] The terminal collects the user's answers in real time and transmits the data to the server after all answers have been completed.

[0955] The server performs automatic scoring, analyzes the user's answering tendencies based on the scores and analysis results, and identifies weak areas.

[0956] 4. Identify weaknesses and personalize

[0957] The server stores the user's weak areas in a database based on the analysis results. This allows the server to reflect this information on the weak areas when generating the next mock test questions, and generate questions that focus on those areas.

[0958] The terminal notifies the user of the newly generated practice test questions.

[0959] 5. Implementing chat functionality

[0960] During or after the mock test, users can input questions about any questions they don't understand through the smart glasses.

[0961] The terminal transmits the user's question data to the server.

[0962] The server analyzes the question and generates an appropriate answer from learning data and pre-prepared FAQs.

[0963] The terminal displays the generated answers to the user for further understanding.

[0964] Examples of specific examples and prompt usage

[0965] 1. Enter past exam questions

[0966] User: "I'm going to scan the past three years of exam questions."

[0967] Smart Glasses: "Sending data to server..."

[0968] Server: "Parsing data... Problem data extracted."

[0969] 2. Generating mock test questions

[0970] System: "Preparing mock test questions based on past exam data... Completed."

[0971] 3. Mock test implementation and result analysis

[0972] User: "Answer question 1. I choose option C."

[0973] Smart Glasses: "Your answer has been recorded. Would you like to see the next question?"

[0974] 4. Identify weaknesses and personalize

[0975] Server: "A new question has been generated based on the results of the previous test."

[0976] 5. Implementing chat functionality

[0977] User: "I don't understand option A in this question."

[0978] Server: "Analyzing...generating appropriate answer."

[0979] Example prompts to input to the generative AI model

[0980] "Load question data, analyze it and generate new practice test questions."

[0981] "Analyze users' answer patterns and identify areas of weakness."

[0982] "Generate a suitable answer to this question."

[0983] This system allows users to learn efficiently and resolve their questions immediately. This is a specific mode for carrying out the invention.

[0984] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0985] Step 1:

[0986] The user scans a collection of past exam questions for qualification exams with the camera on the smart glasses and sends the data to the server. Specifically, the user sets the glasses to scan mode and has the camera read each page of the question collection. The scanned images are obtained as input, and the server uses OCR technology (e.g., Google Cloud Vision API) to convert these images into text data and store the content in a database. The analyzed text data is generated as output.

[0987] Step 2:

[0988] The server analyzes the stored text data and identifies patterns and formats of past questions. This analysis is performed using specific algorithms and machine learning models (e.g., TensorFlow). The input is the text data of past questions stored in the database, and the output is structured data that identifies the format and patterns of each question. The server uses this structured data for further processing.

[0989] Step 3:

[0990] The server generates mock exam questions based on the analyzed past exam data. It uses a generative AI model to create new questions. Structured data on the patterns and formats of past exam questions is used as input, and newly generated mock exam questions are obtained as output. This data is then ready to be sent to the device.

[0991] Step 4:

[0992] The device displays the generated mock test questions to the user. The user takes the mock test through the smart glasses and answers each question. The mock test questions are input, and the user's answers are sequentially collected as output. The device then sends this answer data to the server.

[0993] Step 5:

[0994] The server receives the user's answers sent from the device and automatically scores them. Scoring is done by comparing the user's answers with pre-set correct answer data. The input is the user's answer data, and the output is the score for each question and the total score. Furthermore, the server analyzes the user's answering tendencies based on the analysis results and identifies weak areas.

[0995] Step 6:

[0996] The server stores the identified weak areas in a database. This information is used to generate the next mock test questions. The input is the analysis results, and the output is the weak areas stored in the database.

[0997] Step 7:

[0998] The server sends the newly generated mock test questions to the terminal, and the terminal notifies the user. The input is the newly generated mock test questions, and the output is the notification to the user. The user receives the notification and is ready to take the next mock test.

[0999] Step 8:

[1000] If a user has any questions during or after the mock test, they can input them through the smart glasses. The device then sends the questions to the server. The input is the user's question, and the output is the transmission of the question data to the server.

[1001] Step 9:

[1002] The server analyzes the received question and generates an appropriate answer. If necessary, it references a generative AI model and a pre-prepared FAQ database. The input is the user's question data, and the output is the generated answer. This answer is sent to the terminal and displayed to the user.

[1003] Step 10:

[1004] The terminal displays the answer received from the server to the user. The input is the answer data from the server, and the output is information provided to the user. This allows the user to immediately resolve their question.

[1005] The above is a specific flow of the processing steps of the system, and describes the inputs and outputs used in each step, as well as data processing and calculations.

[1006] 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.

[1007] This system automatically generates mock exam questions for qualification exams and provides users with an optimized learning experience. In particular, it combines an emotion engine that recognizes the user's emotional state and reflects that information in adjusting the difficulty of the mock exam and providing study advice, thereby achieving even more advanced learning support.

[1008] Program processing

[1009] Enter past exam questions

[1010] 1. User: Upload past exam questions to the system in PDF or other format.

[1011] 2. Terminal: Receives uploads from users and sends files to the server.

[1012] 3. Server: Analyzes the received files, extracts the content of the questions as text data, and identifies and classifies the format and patterns of each question.

[1013] 4. Server: Stores and organizes the analyzed data in a database.

[1014] Mock test question generation

[1015] 1. Server: Based on a database of past questions, the server runs an algorithm that learns question trends and formats, and creates templates for automatically generating mock test questions.

[1016] 2. Terminal: Notifies the user that the generated practice test questions are ready.

[1017] 3. User: Clicks on the "Start" button to begin the practice test.

[1018] Mock test implementation and result analysis

[1019] 1. User: Enter the answers to each question and click the "Submit" button after completing all answers.

[1020] 2. Terminal: Records the user's answers and sends them to the server.

[1021] 3. Server: Receives answers, automatically grades them, calculates scores, analyzes user's answer patterns, and identifies weak areas.

[1022] 4. Server: Runs the emotion engine that recognizes the user's emotional state based on the analysis results.

[1023] Utilizing the Emotion Engine

[1024] 1. Server: Adjust the difficulty of the mock test questions based on the user's recognized emotional state (e.g., impatience, anxiety, relaxation, etc.).

[1025] 2. Server: Generates learning advice and encouraging messages according to the recognized user's emotional state.

[1026] 3. Terminal: Presents the user with tailored practice questions and advice.

[1027] 4. Users: Receive advice during their learning process and retake the mock exams.

[1028] Implementing chat functionality

[1029] 1. User: Enter a question about a problem you don't understand through the terminal.

[1030] 2. Terminal: Sends the user's question data to the server.

[1031] 3. Server: Analyzes the question and generates an appropriate answer from learning data and pre-prepared FAQs.

[1032] 4. Terminal: The generated answer is displayed to the user for further understanding.

[1033] Specific examples

[1034] 1. Enter past exam questions

[1035] User: "I'll upload the past three years' worth of exam questions in PDF format."

[1036] Terminal: "File received. Sending to server..."

[1037] Server: "Parsing file... Problem data extracted."

[1038] 2. Generating mock test questions

[1039] Server: "Generate mock exam questions based on past exam data..."

[1040] Terminal: "The practice test questions are ready. Would you like to begin?"

[1041] 3. Mock test implementation and result analysis

[1042] User: "Answer question 1. I choose option C."

[1043] Terminal: "Your answer has been recorded. Would you like to proceed to the next question?"

[1044] User: "I've answered all the questions. I'm going to submit it."

[1045] Terminal: "Sending answer to server..."

[1046] Server: "Analyzing your answer... Score is 70. Weak subject is math. Current emotional state is slightly anxious."

[1047] 4. Utilizing the Emotion Engine

[1048] Server: "Generate slightly easier practice questions based on your perceived anxiety state..."

[1049] Server: "Good job! Let's try this next problem. I think you'll feel more confident if you brush up on the basics in this area."

[1050] Terminal: "New practice test questions and advice displayed."

[1051] 5. Implementing chat functionality

[1052] User: "I have a question about question 3. I don't understand option B. Can you explain it in more detail?"

[1053] Terminal: "Sending question to server..."

[1054] Server: "Parsing your question... generated a suitable answer."

[1055] Terminal: "Answers have arrived, with detailed explanations."

[1056] This system provides an efficient and personalized learning experience while taking into account the user's progress and emotional state. By combining it with an emotion engine, it reduces the user's psychological burden and enables more effective learning support.

[1057] The processing flow will be explained below.

[1058] Program processing steps

[1059] Step 1:

[1060] User: Upload past qualification exam question sets to the system in PDF or other formats.

[1061] Step 2:

[1062] Terminal: Receives uploads from users and sends files to the server.

[1063] Step 3:

[1064] Server: Analyzes the received file, extracts the question content as text data, and identifies and classifies the format and patterns of each question (e.g., words, options, answers).

[1065] Step 4:

[1066] Server: Stores the analyzed data in a database and organizes the classified problem data.

[1067] Step 5:

[1068] Server: Based on a database of past questions, the server runs an algorithm that learns question trends and formats, and creates templates for automatically generating mock test questions.

[1069] Step 6:

[1070] Terminal: Notifies the user that the generated practice test questions are ready.

[1071] Step 7:

[1072] User: Clicks on the "Start" button to begin the practice test.

[1073] Step 8:

[1074] Terminal: displays practice test questions to the user.

[1075] Step 9:

[1076] User: Enters an answer for each question, e.g., for multiple choice questions, clicks on the appropriate answer.

[1077] Step 10:

[1078] Terminal: The user's answers are recorded in real time, and after all answers are completed, they are sent to the server by clicking the "Submit" button.

[1079] Step 11:

[1080] Server: Receives all answers and automatically grades them. Calculates scores and analyzes users' answering trends.

[1081] Step 12:

[1082] Server: Based on the analysis results, identify the user's weak areas and store the weak areas information in a database.

[1083] Step 13:

[1084] Server: When generating the next mock test questions, the server reflects the information on the identified weak areas and generates questions that focus on those areas.

[1085] Step 14:

[1086] Terminal: Notifies the user that the newly generated practice test questions are ready.

[1087] Step 15:

[1088] User: Take the practice test again and continue studying.

[1089] Step 16:

[1090] User: During or after the mock test, enter questions about any questions you don't understand through the terminal.

[1091] Step 17:

[1092] Terminal: Sends the user's question data to the server.

[1093] Step 18:

[1094] Server: Analyzes the question and generates an appropriate answer from learning data and pre-prepared FAQs.

[1095] Step 19:

[1096] Terminal: Displays the generated answer to the user to help them understand it.

[1097] Step 20:

[1098] Server: During or after the user answers, the server uses an emotion engine to recognize the user's emotional state, for example, by using a facial recognition camera or voice analysis.

[1099] Step 21:

[1100] Server: Runs an algorithm that adjusts the difficulty of practice test questions based on perceived emotional state (e.g., impatience, anxiety, relaxation).

[1101] Step 22:

[1102] Server: Generates learning advice and encouraging messages according to the user's emotional state.

[1103] Step 23:

[1104] Terminal: Displays the adjusted practice test questions and generated advice to the user.

[1105] Step 24:

[1106] Users: Retry the adjusted practice questions or continue studying as advised.

[1107] This series of processes allows users to efficiently prepare for qualification exams while taking into account their own progress and emotional state, and allows them to immediately resolve any questions they may have while studying.

[1108] Example 2

[1109] 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."

[1110] Conventional mock test systems generate mock test questions based on past exam questions and analyze users' answers. However, they lacked personalized learning support, such as adjusting the difficulty level based on the user's emotional state and providing study advice. As a result, some users found the test questions to be overly difficult, while others found them too easy, preventing effective learning. Furthermore, the system provided limited intuitive support and feedback for answers, preventing users from maximizing their learning effectiveness. A system that can solve these issues and provide a more personalized learning experience is needed.

[1111] 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.

[1112] In this invention, the server includes means for receiving and analyzing past exam question data as input, means for generating mock exam questions from the analyzed data, means for receiving and analyzing the user's answers, means for identifying weak areas based on the analyzed user's answers, means for generating next mock exam questions reflecting the identified weak areas, means for the user to input questions, means for generating answers to the questions, means for recognizing the user's emotional state, means for adjusting the difficulty of mock exam questions based on the recognized emotional state, and means for generating study advice according to the emotional state, thereby enabling personalized study support according to the user's emotional state and learning progress.

[1113] "Past exam question data" refers to data that includes the content and format of questions in exams that have been administered in the past.

[1114] "Means of analysis" refers to algorithms or software that analyze input data and extract and organize meaningful information.

[1115] "Means for generating mock test questions" refers to processes and systems for creating new mock test questions using algorithms based on past test question data.

[1116] "User's answer result" is data indicating the answer selected or written by the user to the mock test question.

[1117] The "means for receiving and analyzing answer results" refers to an algorithm or system that receives answer data submitted by users and analyzes whether the answers are correct or incorrect and the trends of each answer.

[1118] The "means for identifying weak areas" refers to an algorithm and system for analyzing the user's answers and identifying categories and patterns of questions with a low rate of correct answers.

[1119] "Means for user input of questions" are interfaces and devices that allow users to input questions about a particular problem.

[1120] "Means for generating answers" refers to processes or systems that generate answers using existing databases and AI models to provide appropriate answers to questions from users.

[1121] "Means for recognizing the user's emotional state" refers to an algorithm or system for assessing the user's mental and emotional state based on the user's behavioral data, answering tendencies, data from sensor devices, etc.

[1122] The "means for adjusting the difficulty of the mock test questions" refers to an algorithm and system for appropriately changing the difficulty of the mock test questions given in accordance with the user's emotional state and learning progress.

[1123] A "means for generating study advice" is an algorithm or system used to generate personalized study methods and encouraging messages based on the user's study situation and emotional state.

[1124] This invention is a system that automatically generates mock exam questions for qualification exams and provides users with an optimized learning experience. In particular, this system is equipped with an emotion engine that recognizes the user's emotional state and reflects this in adjusting the difficulty level of the mock exam and providing study advice, thereby achieving more advanced learning support.

[1125] System configuration

[1126] The system consists of three main components: a server, a terminal, and a user. The functions and specific operations of each component are explained below.

[1127] Enter past exam questions

[1128] 1. User: Upload past exam question collections to the system in PDF format. The user clicks the "Upload" button on the system interface and selects the PDF file from the file selection dialog.

[1129] 2. Terminal: Receives uploads from users and sends files to the server. The terminal sends files to the server via HTTP requests and displays a progress bar.

[1130] 3. Server: The received file is analyzed and the problem content is extracted as text data. Specifically, optical character recognition (OCR) software (e.g., Tesseract) is used to convert the PDF file into text data. Natural language processing (NLP) techniques are then used to identify problem formats and patterns. The analyzed data is then stored in a database (e.g., MySQL).

[1131] Mock test question generation

[1132] 1. Server: Learns question trends and formats based on a database of past questions. This is done using machine learning models (e.g., random forests, neural networks). Generates mock test question templates based on the learning results.

[1133] 2. Terminal: Notify the user that the generated practice test questions are ready, using a pop-up message or notification badge (e.g., "New practice test questions are available").

[1134] 3. User: Clicks the "Start" button to begin the mock test. The user clicks the "Start Test" button on the dashboard screen and moves to the test screen.

[1135] Mock test implementation and result analysis

[1136] 1. User: Enter the answer for each question and click the "Submit" button. The user selects or enters the answer for each question and clicks the "Submit" button after answering all questions.

[1137] 2. Terminal: Records the user's answers and sends them to the server. The answer data is sent to the server using an HTTP request.

[1138] 3. Server: Receives the answers and automatically scores them. The server compares the answers with the correct answer database and assigns a score. The server then analyzes the user's answering tendencies based on the analysis results and identifies weak areas.

[1139] 4. Server: Runs the emotion engine to recognize emotional states based on the analysis results, using data from emotion analysis APIs and sensor devices.

[1140] Utilizing the Emotion Engine

[1141] 1. Server: Adjust the difficulty of the mock test questions based on the user's perceived emotional state. Reset the difficulty parameters according to the user's emotional state (e.g., impatience, anxiety, relaxation).

[1142] 2. Server: Generates learning advice based on the user's emotional state. Natural language generation (NLG) technology is used to generate encouraging messages and advice on how to study.

[1143] 3. Terminal: The adjusted mock test questions and advice are presented to the user. The user then takes the advice into consideration and attempts a new mock test.

[1144] Implementing chat functionality

[1145] 1. User: Enter a question about a problem they don't understand. Open a chat window, enter a question, and click the send button.

[1146] 2. Terminal: Sends the question data to the server. Sends the question via HTTP request and displays a progress bar.

[1147] 3. Server: Analyzes the question and generates an appropriate answer from training data and FAQs. Answers are generated using natural language processing (NLP) technology and generative AI models (e.g., GPT-3).

[1148] 4. Terminal: Show the generated answer to the user. Show the answer in the chat window to help the user understand.

[1149] Specific examples

[1150] Enter past exam questions

[1151] User: "I'll upload the past three years' worth of exam questions in PDF format."

[1152] Terminal: "File received. Sending to server..."

[1153] Server: "Parsing file... Problem data extracted."

[1154] Mock test question generation

[1155] Server: "Generate mock exam questions based on past exam data..."

[1156] Terminal: "The practice test questions are ready. Would you like to begin?"

[1157] Mock test implementation and result analysis

[1158] User: "Answer question 1. I choose option C."

[1159] Terminal: "Your answer has been recorded. Would you like to proceed to the next question?"

[1160] User: "I've answered all the questions. I'm going to submit it."

[1161] Terminal: "Sending answer to server..."

[1162] Server: "Analyzing your answer... Score is 70. Weak subject is math. Current emotional state is slightly anxious."

[1163] Utilizing the Emotion Engine

[1164] Server: "Generate slightly easier practice questions based on your perceived anxiety state..."

[1165] Server: "You're doing great. I think you'll gain confidence if you brush up on the basics in this area."

[1166] Terminal: "New practice test questions and advice displayed."

[1167] Implementing chat functionality

[1168] User: "I have a question about question 3. I don't understand option B. Can you explain it in more detail?"

[1169] Terminal: "Sending question to server..."

[1170] Server: "Parsing your question... generated a suitable answer."

[1171] Terminal: "Answers have arrived, with detailed explanations."

[1172] This system provides an efficient and personalized learning experience while taking into account the user's progress and emotional state. By combining it with an emotion engine, it reduces the user's psychological burden and enables more effective learning support.

[1173] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1174] Step 1:

[1175] User: Upload past qualification exam question sets to the system in PDF or other formats.

[1176] Specific operation: The user clicks the "Upload" button on the system interface and selects a PDF file from the file selection dialog.

[1177] Input: Past exam question collection file in PDF format.

[1178] Output: The upload request is sent to the device.

[1179] Step 2:

[1180] Terminal: Receives uploads from users and sends files to the server.

[1181] Specific operation: The terminal sends the file to the server via an HTTP request and displays a progress bar.

[1182] Input: PDF file uploaded by user.

[1183] Output: The file is sent to the server.

[1184] Step 3:

[1185] Server: Analyzes the received file and extracts the problematic content as text data.

[1186] How it works: The server uses OCR (Optical Character Recognition) software (e.g., Tesseract) to convert PDF files into text data, and uses Natural Language Processing (NLP) techniques to identify problem formats and patterns. The parsed data is then stored in a database (e.g., MySQL).

[1187] Input: The PDF file sent to the server.

[1188] Output: Parsed problem information as text data.

[1189] Step 4:

[1190] Server: Learn question trends and formats based on a database of past questions.

[1191] Specific operation: Using machine learning models (e.g., random forests, neural networks), the system learns from past exam data and generates mock exam question templates based on the learning results.

[1192] Input: Past question data stored in the database.

[1193] Output: Generated mock exam question templates.

[1194] Step 5:

[1195] Terminal: Notifies the user that the generated practice test questions are ready.

[1196] Specific behavior: When a device receives a notification from the server, it displays a pop-up message or notification badge (e.g., "New practice test questions are available.").

[1197] Input: Notification information from the server.

[1198] Output: A notification message to the user.

[1199] Step 6:

[1200] User: Clicks on the "Start" button to begin the practice test.

[1201] Specific operation: The user clicks the "Start test" button on the dashboard screen to transition to the test screen.

[1202] Input: User action (button click).

[1203] Output: Transition to mock test screen.

[1204] Step 7:

[1205] User: Enter the answer to each question and click the "Submit" button.

[1206] Specific operation: The user selects or enters an answer for each question, and when all questions have been answered, clicks the "Submit" button.

[1207] Input: User's answer data.

[1208] Output: All answer data is recorded on the device.

[1209] Step 8:

[1210] Terminal: Records the user's answers and sends them to the server.

[1211] Specific operation: The device temporarily stores all answer data and sends it to the server using an HTTP request. A progress bar is displayed.

[1212] Input: User's answer data.

[1213] Output: The answer data is sent to the server.

[1214] Step 9:

[1215] Server: Receives answers, automatically grades them, calculates scores, analyzes user's answer patterns, and identifies weak areas.

[1216] Specific operations: Compare answers with a database of correct answers and perform scoring. Analyze answer trends and identify weak areas using statistical methods. Store data on weak areas in a database.

[1217] Input: Answer data and correct answer database.

[1218] Output: Scores and analysis results.

[1219] Step 10:

[1220] Server: Runs the emotion engine that recognizes the user's emotional state based on the analysis results.

[1221] Specific operation: Executes emotion recognition algorithms using analytical data and data from sensor devices.

[1222] Input: Analysis results and sensor device data.

[1223] Output: The user's emotional state.

[1224] Step 11:

[1225] Server: Adjusts the difficulty of practice test questions based on perceived emotional state.

[1226] Specific operation: Using the emotional state, the parameters of the mock test question generation algorithm are reset to adjust the difficulty level.

[1227] Input: User's emotional state and mock test template.

[1228] Output: Difficulty-adjusted practice test questions.

[1229] Step 12:

[1230] Server: Generates learning advice and encouraging messages depending on the recognized emotional state.

[1231] What it does: Uses natural language generation (NLG) technology to generate personalized advice and encouraging messages for users.

[1232] Input: The user's emotional state.

[1233] Output: Study advice and encouraging messages.

[1234] Step 13:

[1235] Terminal: Presents tailored practice test questions and advice to the user.

[1236] Specific operation: Receives data from the server and displays it on the device's UI.

[1237] Input: Tailored practice test questions and advice.

[1238] Output: What is displayed to the user.

[1239] Step 14:

[1240] Users: Receive advice as they progress and retake practice exams.

[1241] Specific operation: The user takes the advice provided into consideration and takes on a new mock test.

[1242] Enter: study advice.

[1243] Output: The mock test to try again.

[1244] Step 15:

[1245] User: Type in a question about a problem they don't understand.

[1246] What happens: A user opens a chat window, types a question, and clicks the send button.

[1247] Input: The user's question.

[1248] Output: Sending the question data by terminal.

[1249] Step 16:

[1250] Terminal: Sends the query data to the server.

[1251] Specific behavior: Sends a question via HTTP request and displays a progress bar.

[1252] Input: User question data.

[1253] Output: The query data is sent to the server.

[1254] Step 17:

[1255] Server: Analyzes the question and generates an appropriate answer from learning data and FAQs.

[1256] Specific operation: Generate answers using natural language processing (NLP) techniques and generative AI models (e.g., GPT-3).

[1257] Input: User question data.

[1258] Output: The generated answer.

[1259] Step 18:

[1260] Terminal: Displays the generated answer to the user.

[1261] Specific behavior: Displays the response received from the server in the chat window.

[1262] Input: The generated answer.

[1263] Output: Display the answer to the user.

[1264] (Application example 2)

[1265] 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."

[1266] Conventional qualification exam preparation systems have limited functionality for improving users' learning efficiency. In particular, they provide questions of a uniform level of difficulty without considering the user's emotional state, making it impossible to reduce the psychological burden during study. Furthermore, there is a lack of appropriate study support methods for effectively utilizing travel time in an autonomous vehicle. As a result, users tend to lose motivation to study, making it difficult to prepare for exams efficiently.

[1267] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving and analyzing past exam question data as input, means for generating mock exam questions from the analyzed data, means for receiving and analyzing the user's answers, means for identifying weak areas based on the analyzed user's answers, means for generating the next mock exam questions reflecting the identified weak areas, means for recognizing the user's emotional state in the autonomous vehicle, means for adjusting the difficulty of the mock exam questions based on the recognized emotional state, means for generating study advice and messages according to the recognized emotional state, means for the user to input a question, and means for generating an answer to the question. This enables flexible and personalized study support based on the user's emotional state.

[1268] "Past exam question data" refers to data on questions from past qualification exams, and is information stored in text format or scanned PDF format.

[1269] "Mock test questions" refer to virtual test questions that are generated based on past test question data and that users can answer as part of their exam preparation.

[1270] "Autonomous vehicle" means a vehicle that is driven automatically by on-board sensors and technological processing devices, without a human driver.

[1271] An "emotional state" is a psychological state that a user exhibits while answering a practice test, and examples include inner feelings such as impatience, anxiety, and relaxation.

[1272] "Adjusting the difficulty level" refers to the process of changing the difficulty of the mock test questions according to the user's emotional state and learning progress.

[1273] "Study advice" refers to specific advice and guidance provided to users to help them study effectively.

[1274] "Messages" refer to verbal notifications and encouraging statements that are generated based on the user's emotional state and answer status.

[1275] "Means for inputting questions" refers to an interface that allows users to inquire about any unclear points or doubts they may have during the mock test by inputting text or other methods to the system.

[1276] "Automatic scoring" refers to the process in which the system automatically calculates and evaluates the score based on the user's answers.

[1277] The term "weak area" refers to a learning area in which the user has been determined to have a low score and insufficient understanding, as identified from past answer results, etc.

[1278] This invention is a system that automatically generates mock exam questions for qualification exams and provides a learning experience that takes into account the user's emotional state. It is specifically designed to streamline learning in autonomous vehicles. The system is constructed as follows:

[1279] The entire system consists of the user's smartphone or tablet, a cloud server, an emotion recognition API, a natural language processing model, and a camera and microphone installed in the autonomous vehicle.

[1280] Input and analysis of past questions

[1281] Users use their smartphones or tablets to upload past exam question data in PDF format to a cloud server. The cloud server then uses a PDF analysis algorithm to convert the question data into text format, then identifies the format and patterns of each question and stores them in a database. This process can be performed using cloud services such as Amazon Web Services (AWS) and Google Cloud Platform (GCP).

[1282] Mock test question generation

[1283] The cloud server automatically generates mock test questions using a generative AI model (e.g., GPT-3 / 4) based on the stored past exam data. The generated questions are then sent to the user's smartphone or tablet.

[1284] User answers and analysis

[1285] Users answer mock test questions, and their answers are sent to a cloud server in real time. The cloud server automatically grades the answers and calculates the score. It also analyzes the user's answering habits and identifies weak areas.

[1286] Recognition and application of emotional states

[1287] The system uses cameras and microphones installed in autonomous vehicles to recognize the user's emotional state in real time. Emotion recognition utilizes Microsoft Azure Face API and Amazon Rekognition. The recognized emotional state (e.g., impatience, anxiety, relaxation, etc.) is analyzed on a cloud server, and the system adjusts the difficulty of the mock test questions and generates study advice and messages based on that information.

[1288] Questions and Answers

[1289] An interface is also provided for users to input any questions or concerns they may have during the mock test. The cloud server analyzes the user's questions using a natural language processing model (e.g., GPT-3 / 4) and generates appropriate answers. The generated answers are provided to the user in real time.

[1290] Specific examples

[1291] The user uploads the past five years of driving test question sets in PDF format from their smartphone to a cloud server.

[1292] The cloud server analyzes the file and extracts the problem data.

[1293] The server generates mock test questions based on past exam question data.

[1294] The user answers the practice test and sends the answers to the cloud server.

[1295] Your score will be automatically scored and you will be notified of your score and weak areas.

[1296] A camera and microphone are used to recognize the user's emotions inside an autonomous vehicle.

[1297] The server adjusts the difficulty of the mock test based on the emotional state and generates study advice.

[1298] The user enters a question, and the cloud server uses natural language processing to generate an appropriate answer.

[1299] Prompt Sentence Examples

[1300] Below are some example prompts for a generative AI model (e.g., GPT-3 / 4):

[1301] "The user is working on a mock exam in a self-driving vehicle. Provide appropriate advice based on the following information: mock exam score: 50; weaknesses: traffic rules; current emotional state: anxiety."

[1302] This enables flexible and personalized learning support based on the user's emotional state.

[1303] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1304] Step 1:

[1305] The user uploads past qualification exam question data in PDF format to a smartphone or tablet.

[1306] Input: Past exam data (PDF file)

[1307] Output: Uploaded PDF file

[1308] Specific operation: The user selects past exam question data from their device and clicks the upload button.

[1309] Step 2:

[1310] The device sends the uploaded PDF file to the cloud server.

[1311] Input: Uploaded PDF file

[1312] Output: PDF file sent to cloud server

[1313] Specific operation: The device receives the file and sends it to the cloud server via the network.

[1314] Step 3:

[1315] The server uses a PDF analysis algorithm to convert the PDF file into text data and identify problem formats and patterns.

[1316] Input: PDF file sent to the cloud server

[1317] Output: Textual problem data and identified format patterns

[1318] Specific operation: The server uses PDF analysis software (e.g., Tesseract OCR) to extract text data from the PDF, and then identifies the format and patterns of each question and stores them in a database.

[1319] Step 4:

[1320] Based on the past exam data stored on the server, mock exam questions are automatically generated using a generative AI model (e.g., GPT-3 / 4).

[1321] Input: Textual problem data and identified format patterns

[1322] Output: Generated practice test questions

[1323] Specific operation: The server learns question trends and formats from the stored data, generates new mock test questions using a generative AI model, and stores them in a database.

[1324] Step 5:

[1325] The terminal notifies the user that the practice test questions are ready.

[1326] Input: Generated practice test questions

[1327] Output: A message to inform the user

[1328] Specific operation: The terminal receives a notification from the server and notifies the user by message that the mock test is ready.

[1329] Step 6:

[1330] The user starts the practice test and enters answers to the questions.

[1331] Input: Generated practice test questions

[1332] Output: User's answer

[1333] Specific operation: The user inputs answers to each question on the terminal and records the answers on the terminal.

[1334] Step 7:

[1335] The device sends the user's answer to the cloud server.

[1336] Input: User's answer

[1337] Output: Answers sent to the cloud server

[1338] Specific operation: The device sends the recorded answers to the server via the network.

[1339] Step 8:

[1340] The server automatically grades the answers and calculates the score. It also analyzes the user's answering tendencies and identifies weak areas.

[1341] Input: Answers sent to the cloud server

[1342] Output: Marking results, scores, weak areas identified

[1343] Specific operation: The server executes the automatic scoring algorithm to calculate the score, and also uses the analysis algorithm to analyze the user's answering tendencies and identify weak areas.

[1344] Step 9:

[1345] Using cameras and microphones mounted on autonomous vehicles, the system recognizes the user's emotional state in real time.

[1346] Input: Real-time video and audio data from cameras and microphones

[1347] Output: Perceived emotional state

[1348] Specific operation: The cloud server uses an emotion recognition API (e.g., Amazon Rekognition or Microsoft Azure Face API) to analyze video and audio data and recognize the user's emotional state.

[1349] Step 10:

[1350] The server adjusts the difficulty of the practice test questions and generates study advice and messages based on the recognized emotional state.

[1351] Input: perceived emotional state, marking results, score, weak areas identified

[1352] Output: Tailored practice questions, study advice, and messages

[1353] Specific operation: The server changes the difficulty level of the practice test questions based on the user's emotional state and generates appropriate study advice and encouraging messages for the user.

[1354] Step 11:

[1355] The device presents the user with tailored practice test questions and study advice.

[1356] Input: Tailored practice test questions, study advice, messages

[1357] Output: What the user sees

[1358] Specific operation: The terminal receives information from the server and presents it on the screen in a format that is easy for the user to see.

[1359] Step 12:

[1360] The user inputs questions using an interface for inputting uncertainties or questions during the mock test.

[1361] Input: User question

[1362] Output: Question typed into the terminal

[1363] Specific operation: The user inputs a question through an input box on the terminal.

[1364] Step 13:

[1365] The device sends the user's question to the cloud server.

[1366] Input: User question

[1367] Output: Questions sent to the cloud server

[1368] Specific operation: The device sends the question to the server via the network.

[1369] Step 14:

[1370] The server analyzes the question and generates an appropriate answer.

[1371] Input: The question sent to the cloud server

[1372] Output: The generated answer

[1373] Specific operation: The server uses a natural language processing model (e.g., GPT-3 / 4) to analyze the question and generate an appropriate answer.

[1374] Step 15:

[1375] The terminal displays the generated answer to the user.

[1376] Input: Generated Answer

[1377] Output: The answer displayed to the user

[1378] Specific operation: The terminal receives the response from the server and presents it on the screen in an easy-to-read format for the user.

[1379] 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.

[1380] 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.

[1381] 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.

[1382] [Third embodiment]

[1383] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1384] 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.

[1385] 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).

[1386] 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.

[1387] 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.

[1388] 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).

[1389] 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.

[1390] 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.

[1391] 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.

[1392] 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.

[1393] 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.

[1394] 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."

[1395] This invention is a system that automatically generates mock exam questions for qualification exams, providing users with an optimized learning experience. This system analyzes past exam question data, identifies weak areas based on the user's answers, and generates new mock exam questions that reflect this information. It also provides a function that allows users to ask questions that arise during their studies and provides instant answers.

[1396] Program processing

[1397] 1. Enter past exam questions

[1398] User: Upload past qualification exam question sets to the system in PDF or other formats.

[1399] Terminal: Receives uploads from users and sends files to the server.

[1400] Server: Analyzes the received file, extracts the content of the questions as text data, identifies the format and patterns of each question (e.g., words, options, answers), and stores them in a database.

[1401] 2. Generating mock test questions

[1402] Server: Generates mock test questions based on the analyzed data. It runs an algorithm that learns the patterns and formats of past exam questions and creates new mock questions.

[1403] Terminal: Prepares the generated practice test questions for display to the user.

[1404] User: When you are ready to take the practice test, click the "Start" button on your device.

[1405] 3. Mock test implementation and result analysis

[1406] User: Answer each question one by one, for example, by clicking on the appropriate answer for multiple choice questions.

[1407] Terminal: Records the user's answers in real time, and when all answers have been completed, the user clicks the "Submit" button, which sends the data to the server.

[1408] Server: Receives all answers and automatically scores them. Based on the scores and analysis results, analyzes the user's answering tendencies and identifies weak areas.

[1409] 4. Identify weaknesses and personalize

[1410] Server: Based on the analysis results, the user's weak areas (e.g., specific subjects or question formats) are stored in a database.

[1411] Server: When generating the next mock test questions, this weak area information is reflected and questions that focus on that area are generated.

[1412] Terminal: Prepares to display the newly generated practice test questions and notifies the user.

[1413] Users: They can take the mock exam again and get further learning benefits.

[1414] 5. Implementing chat functionality

[1415] User: During or after the mock test, if there are any questions that the user does not understand, the user can enter the questions through the terminal.

[1416] Terminal: Sends the user's question data to the server.

[1417] Server: Analyzes the question and generates an appropriate answer from training data and pre-prepared FAQs, including detailed explanations and additional references if necessary.

[1418] Terminal: Displays the generated answer to the user for further understanding.

[1419] Specific examples

[1420] 1. Enter past exam questions

[1421] User: "I'll upload the past three years' worth of exam questions in PDF format."

[1422] Terminal: "File received. Sending to server..."

[1423] Server: "Parsing file... Problem data extracted."

[1424] 2. Generating mock test questions

[1425] Server: "Generate mock exam questions based on past exam data..."

[1426] Terminal: "The practice test questions are ready. Would you like to begin?"

[1427] 3. Mock test implementation and result analysis

[1428] User: "Answer question 1. I choose option C."

[1429] Terminal: "Your answer has been recorded. Would you like to proceed to the next question?"

[1430] User: "I've answered all the questions. I'm going to submit it."

[1431] Terminal: "Sending answer to server..."

[1432] Server: "Analyzing your answer... Score 70. Math is my weak point."

[1433] 4. Identify weaknesses and personalize

[1434] Server: "We've saved your weak areas and will incorporate them into your next practice test."

[1435] Terminal: "New practice test questions are ready. Would you like to begin?"

[1436] 5. Implementing chat functionality

[1437] User: "I have a question about question 3. I don't understand option B. Can you explain it in more detail?"

[1438] Terminal: "Sending question to server..."

[1439] Server: "Parsing your question... generated a suitable answer."

[1440] Terminal: "Answers have arrived, with detailed explanations."

[1441] Through this system, users can efficiently prepare for qualification exams while checking their own progress and weak points. In addition, they can instantly resolve any questions they have, significantly improving their learning efficiency.

[1442] The processing flow will be explained below.

[1443] Program processing steps

[1444] Step 1:

[1445] User: Upload past qualification exam question sets to the system in PDF or other formats.

[1446] Step 2:

[1447] Terminal: Receives uploads from users and sends files to the server.

[1448] Step 3:

[1449] Server: Analyzes the received file, extracts the question content as text data, and identifies and classifies the format and patterns of each question (e.g., words, options, answers).

[1450] Step 4:

[1451] Server: Stores the analyzed data in a database and organizes the classified problem data.

[1452] Step 5:

[1453] Server: Based on a database of past questions, the server runs an algorithm that learns question trends and formats, and creates templates for automatically generating mock test questions.

[1454] Step 6:

[1455] Terminal: Notifies the user that the generated practice test questions are ready.

[1456] Step 7:

[1457] User: Clicks on the "Start" button to begin the practice test.

[1458] Step 8:

[1459] Terminal: displays practice test questions to the user.

[1460] Step 9:

[1461] User: Enters an answer for each question, e.g., for multiple choice questions, clicks on the appropriate answer.

[1462] Step 10:

[1463] Terminal: The user's answers are recorded in real time, and after all answers are completed, they are sent to the server by clicking the "Submit" button.

[1464] Step 11:

[1465] Server: Receives all answers and automatically grades them. Calculates scores and analyzes users' answering trends.

[1466] Step 12:

[1467] Server: Based on the analysis results, identify the user's weak areas and store the weak areas information in a database.

[1468] Step 13:

[1469] Server: When generating the next mock test questions, the server reflects the information on the identified weak areas and generates questions that focus on those areas.

[1470] Step 14:

[1471] Terminal: Notifies the user that the newly generated practice test questions are ready.

[1472] Step 15:

[1473] User: Take the practice test again and continue studying.

[1474] Step 16:

[1475] User: During or after the mock test, enter questions about any questions you don't understand through the terminal.

[1476] Step 17:

[1477] Terminal: Sends the user's question data to the server.

[1478] Step 18:

[1479] Server: Analyzes the question and generates an appropriate answer from learning data and pre-prepared FAQs.

[1480] Step 19:

[1481] Terminal: Displays the generated answer to the user to help them understand it.

[1482] This series of processes allows users to efficiently prepare for the qualification exam and also allows them to immediately resolve any questions they may have while studying.

[1483] Example 1

[1484] 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."

[1485] Conventional qualification exam study systems lack the ability to properly identify users' weak areas and focus their learning on those areas, as well as the ability to record answers in real time and provide immediate feedback. Furthermore, they lack the ability to provide immediate solutions to questions users may have during the exam. This can lead to lower user learning efficiency and potentially lower pass rates for qualification exams.

[1486] 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.

[1487] In this invention, the server includes means for receiving and analyzing past exam question data as input, means for generating mock exam questions from the analyzed data, means for receiving and analyzing the user's answers, means for identifying weak areas based on the analyzed user's answers, means for generating the next mock exam questions reflecting the identified weak areas, means for the user to input questions, means for generating answers to the questions, means for saving the weak areas in a database, means for recording answers during the mock exam in real time, and means for learning a model based on the database of past questions. This makes it possible to identify the user's weak areas and have them study them intensively, and can provide immediate answers to any questions that arise during study, thereby significantly improving study efficiency.

[1488] "Past exam question data" refers to information about questions and answers from previous exams.

[1489] "Means of analysis" is a function for analyzing input data and extracting and identifying useful information.

[1490] "Mock test questions" are provisional test questions that users answer as practice to prepare for the actual test.

[1491] "Means of generation" refers to the function for creating new information and content based on data.

[1492] "User's answer results" are answers selected by the user to the mock test questions and answer information.

[1493] A "weak area" is an area in which a user shows low scores in a particular genre or theme based on the results of a mock test.

[1494] "Means for inputting questions" refers to an interface or function that allows users to input doubts or questions to the system.

[1495] The "means for generating an answer" is a function for creating and providing an appropriate answer to a question entered by a user.

[1496] "Means for storing in a database" refers to the function of storing analyzed information and data for the long term and retrieving it as needed.

[1497] "Means for recording in real time" is a function for instantly recording information on a user's actions or answers the moment they occur.

[1498] "Means of learning the model" is a feature that allows the algorithm to learn patterns and rules using past data so that it can adapt to new situations.

[1499] The present invention provides a system for automatically generating mock questions for qualification examinations and providing users with an optimized learning experience. This system is realized through the interaction of a server, a terminal, and a user.

[1500] First, a user uploads past exam question data to the system in a file format such as PDF. The terminal receives the uploaded file and sends it to the server. The server analyzes the received PDF file and extracts text data using a file analysis tool (Apache PDFBox as a specific example). It then uses a Natural Language Processing (NLP) model (spaCy or NLTK as a specific example) to identify information about the questions, options, and answers, and stores this information in a database.

[1501] Next, the server generates mock test questions by learning the patterns and trends of each question using a machine learning algorithm (specifically, GPT-3 or BERT) based on a database of past questions. The generated mock test questions are sent to the device and displayed on the user interface. The user then clicks the start mock test button to begin the test.

[1502] During the mock test, the user answers each question and clicks the next button to proceed. The device records the user's answers in real time, and when the "Submit" button is clicked after the test is completed, the answer data is sent to the server. The server automatically scores the received answer data and calculates the user's score using a specific algorithm (for example, Scikit-learn or TensorFlow). It also analyzes answer trends and records specific weak areas in a database.

[1503] After identifying weak areas, the server adjusts the algorithm to include content that emphasizes the user's weak areas when generating the next mock test questions, and prepares to display them on the device, allowing the user to focus on studying their weak areas.

[1504] During or after the mock test, users can enter questions about problems they didn't understand in the chat box. The device sends the entered question to the server, which analyzes it using an NLP model (specifically, BERT or GPT-3) to generate an appropriate answer. The generated answer references FAQ data and related materials in the database, and the device displays it to the user.

[1505] Specific examples

[1506] Enter past exam questions

[1507] User: "I'll upload the past three years' worth of exam questions in PDF format."

[1508] Terminal: "File received. Sending to server..."

[1509] Server: "Parsing file... Problem data extracted."

[1510] Mock test question generation

[1511] Server: "Generate mock exam questions based on past exam data..."

[1512] Terminal: "The practice test questions are ready. Would you like to begin?"

[1513] Mock test implementation and result analysis

[1514] User: "Answer question 1. I choose option C."

[1515] Terminal: "Your answer has been recorded. Would you like to proceed to the next question?"

[1516] User: "I've answered all the questions. I'm going to submit it."

[1517] Terminal: "Sending answer to server..."

[1518] Server: "Analyzing your answer... Score 70. Math is my weak point."

[1519] Identifying weaknesses and personalizing

[1520] Server: "We've saved your weak areas and will incorporate them into your next practice test."

[1521] Terminal: "New practice test questions are ready. Would you like to begin?"

[1522] Implementing chat functionality

[1523] User: "I have a question about question 3. I don't understand option B. Can you explain it in more detail?"

[1524] Terminal: "Sending question to server..."

[1525] Server: "Parsing your question... generated a suitable answer."

[1526] Terminal: "Answers have arrived, with detailed explanations."

[1527] Through this system, users can effectively prepare for qualification exams, identify their weaknesses through mock tests, and deepen their understanding. Real-time feedback and answers to questions also greatly improve learning efficiency.

[1528] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1529] Step 1: Upload past exam questions

[1530] User: Prepare past exam question data in PDF format and click the upload button on the device.

[1531] Input: Past exam question data (PDF file).

[1532] Terminal: Receives the PDF file from the user and sends it to the server in bytes.

[1533] Output: The PDF file sent to the server.

[1534] Specific operation: A file selection window is displayed, and after the user selects the target file, the upload operation is performed.

[1535] Step 2: Analyzing the file contents

[1536] Server: Convert the received PDF file into text data using a file analysis tool (such as Apache PDFBox).

[1537] Input: PDF file.

[1538] Server: The converted text data is processed using an NLP model (such as spaCy or NLTK) to identify test questions, answer choices, and answers.

[1539] Output: Structured exam question data.

[1540] What it does: It uses a PDF parsing library to extract text from PDFs and then uses an NLP model to perform natural language processing and identify specific patterns.

[1541] Step 3: Saving to the database

[1542] Server: Stores the analyzed problem data in a database (e.g., MySQL or PostgreSQL).

[1543] Input: Structured exam question data.

[1544] Output: Exam question data stored in a database.

[1545] What it does: Establishes a database connection and saves data using an SQL query.

[1546] Step 4: Generate practice test questions

[1547] Server: Generates new mock test questions using generative AI models (such as GPT-3 and BERT) based on past questions in the database.

[1548] Input: Past exam data in the database.

[1549] Output: Generated practice test questions.

[1550] What it does: Apply machine learning algorithms to generate and format new problem data.

[1551] Step 5: Prepare to view the practice test questions

[1552] Terminal: Receives the generated practice test questions and prepares them for display on the user interface.

[1553] Input: Generated practice test questions.

[1554] Output: Practice test questions displayed in the user interface.

[1555] What it does: Formats problem data and converts it into HTML or JSON for display in a browser or app interface.

[1556] Step 6: Start the practice test

[1557] User: Click the Start Practice Test button to begin the practice test.

[1558] Input: User's starting instructions.

[1559] Terminal: Displays test questions sequentially and accepts user answers in input format.

[1560] Output: The answer from the user.

[1561] Specific operation: When the start button is pressed, the screen will move to the question display screen and prepare the answer input field.

[1562] Step 7: Record and submit your answers

[1563] User: Answer each question and click the next button to proceed.

[1564] Input: User's answer data.

[1565] Terminal: Each answer is recorded in real time, and the answer data is sent to the server when the "Submit" button is clicked after the test is completed.

[1566] Output: The answer data sent to the server.

[1567] Specific operation: Once the answer has been entered, the next question will be displayed, and once all questions have been completed, the answer data will be sent to the server.

[1568] Step 8: Scoring and analyzing results

[1569] Server: Based on the received answer data, the server automatically scores the answers. Specifically, it calculates the score using an algorithm (such as Scikit-learn or TensorFlow).

[1570] Input: User's answer data.

[1571] Output: User's score and weak areas analysis.

[1572] Specific operation: The received data is input into the evaluation algorithm for scoring and performance analysis.

[1573] Step 9: Record your weaknesses

[1574] Server: Based on the analysis results, identify the weak areas of each user and store them in a database.

[1575] Input: User scores and analysis results.

[1576] Output: Weakness information stored in a database.

[1577] Specific operation: Analysis results are added and saved to the user profile in the database.

[1578] Step 10: Generate new practice questions

[1579] Server: When generating the next mock test questions, generate new questions that focus on the user's weak areas.

[1580] Input: Data on weak areas.

[1581] Output: The newly generated practice test questions.

[1582] Specific operation: Refer to information on weak areas and use a generative AI model to generate specialized questions.

[1583] Step 11: Notification of new practice test questions

[1584] Terminal: Prepares to display the generated practice test questions and notifies the user.

[1585] Input: Newly generated practice test questions.

[1586] Output: The new practice test question and notification message displayed in the user interface.

[1587] Specific behavior: Convert new problem data into a display format and notify the user, for example, with a notification banner.

[1588] Step 12: Submit your question

[1589] Users: During or after the mock exam, type questions into the chat box about any questions they didn't understand.

[1590] Input: The user's question.

[1591] Terminal: Sends the query data to the server.

[1592] Output: The query data sent to the server.

[1593] Specific operation: Questions entered in the chat box are transferred to the server in real time.

[1594] Step 13: Parsing the question and generating an answer

[1595] Server: Analyzes the question using an NLP model (such as BERT or GPT-3) and generates an appropriate answer.

[1596] Input: User question data.

[1597] Output: The generated answer.

[1598] Specific operation: Performs natural language processing of the question and generates an answer based on FAQ data and related materials in the database.

[1599] Step 14: View your answers

[1600] Terminal: Displays the generated answers in a user interface.

[1601] Input: Generated response data.

[1602] Output: The answer displayed in the user interface.

[1603] Specific operation: Convert the response data into an appropriate format and display it on the chat screen, etc.

[1604] In this way, by clearly indicating the specific operations, inputs, and outputs at each processing step, it is possible to understand in detail how the user, terminal, and server cooperate to operate the entire system.

[1605] (Application example 1)

[1606] 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."

[1607] When studying for qualification exams, users need more than just past exam question collections; they need effective study methods that focus on their weak areas. There is also a lack of ways to instantly resolve questions that arise during study. Furthermore, there is the challenge of providing these exam preparation materials using smart devices, regardless of location or time.

[1608] 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.

[1609] In this invention, the server includes a means for scanning past exam papers with a camera and transmitting the data to the server, a means for the user to take the mock exam through smart glasses, and a means for automatically scoring all answers and displaying the analysis results to the user, allowing the user to study efficiently and effectively anywhere and quickly resolve any questions.

[1610] "Past exam question data" refers to digital records of the content of questions from previous qualification exams.

[1611] An "analyzing means" is a computer program or algorithm that processes input data and analyzes it to understand its content and characteristics.

[1612] "Mock test questions" are virtual test questions that users answer as practice in preparation for the actual test.

[1613] "User" means an individual or learner who uses this system to prepare for a qualification exam.

[1614] "Answer results" are the contents of the answers provided by the user to the mock test.

[1615] "Weak areas" refer to areas or subjects in which the user frequently gets exam questions wrong.

[1616] A "question" is an inquiry about content that the user found difficult to understand during the mock test or during study.

[1617] An "answer" is an explanation or information provided in response to a user's question.

[1618] "Camera scanning" means using a camera to capture a digital image of a physical document and convert its contents into digital data.

[1619] A "server" is a powerful computer system for storing, processing, and serving data.

[1620] "Smart glasses" are eyeglass-shaped devices equipped with a display and computer functionality that allow the wearer to obtain visual information.

[1621] "Automatic scoring" is a function in which the system evaluates the user's answers and calculates the score.

[1622] "Analysis results" are information about the user's learning tendencies and weak areas that the system derives from the user's answers.

[1623] The present invention enables users to effectively study for qualification exams by using practice tests. The system includes a server, a terminal (e.g., smart glasses), and a user interface.

[1624] Program Generation and Explanation

[1625] 1. Enter past exam questions

[1626] The user scans a collection of past qualification exam questions with the camera in the smart glasses and sends the data to the server.

[1627] The server uses OCR (Optical Character Recognition) technology to convert the contents of the scanned question set into digital text, identify the question format and patterns, and store them in a database (e.g., using Google Cloud Vision API).

[1628] 2. Generating mock test questions

[1629] The server generates mock test questions based on the stored data, learning the patterns and formats of past questions and creating new mock questions using a generative AI model (e.g., TensorFlow).

[1630] The terminal prepares to display the generated practice test questions to the user.

[1631] 3. Mock test implementation and result analysis

[1632] Users take practice tests through smart glasses and input their answers to each question.

[1633] The terminal collects the user's answers in real time and transmits the data to the server after all answers have been completed.

[1634] The server performs automatic scoring, analyzes the user's answering tendencies based on the scores and analysis results, and identifies weak areas.

[1635] 4. Identify weaknesses and personalize

[1636] The server stores the user's weak areas in a database based on the analysis results. This allows the server to reflect this information on the weak areas when generating the next mock test questions, and generate questions that focus on those areas.

[1637] The terminal notifies the user of the newly generated practice test questions.

[1638] 5. Implementing chat functionality

[1639] During or after the mock test, users can input questions about any questions they don't understand through the smart glasses.

[1640] The terminal transmits the user's question data to the server.

[1641] The server analyzes the question and generates an appropriate answer from learning data and pre-prepared FAQs.

[1642] The terminal displays the generated answers to the user for further understanding.

[1643] Examples of specific examples and prompt usage

[1644] 1. Enter past exam questions

[1645] User: "I'm going to scan the past three years of exam questions."

[1646] Smart Glasses: "Sending data to server..."

[1647] Server: "Parsing data... Problem data extracted."

[1648] 2. Generating mock test questions

[1649] System: "Preparing mock test questions based on past exam data... Completed."

[1650] 3. Mock test implementation and result analysis

[1651] User: "Answer question 1. I choose option C."

[1652] Smart Glasses: "Your answer has been recorded. Would you like to see the next question?"

[1653] 4. Identify weaknesses and personalize

[1654] Server: "A new question has been generated based on the results of the previous test."

[1655] 5. Implementing chat functionality

[1656] User: "I don't understand option A in this question."

[1657] Server: "Analyzing...generating appropriate answer."

[1658] Example prompts to input to the generative AI model

[1659] "Load question data, analyze it and generate new practice test questions."

[1660] "Analyze users' answer patterns and identify areas of weakness."

[1661] "Generate a suitable answer to this question."

[1662] This system allows users to learn efficiently and resolve their questions immediately. This is a specific mode for carrying out the invention.

[1663] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1664] Step 1:

[1665] The user scans a collection of past exam questions for qualification exams with the camera on the smart glasses and sends the data to the server. Specifically, the user sets the glasses to scan mode and has the camera read each page of the question collection. The scanned images are obtained as input, and the server uses OCR technology (e.g., Google Cloud Vision API) to convert these images into text data and store the content in a database. The analyzed text data is generated as output.

[1666] Step 2:

[1667] The server analyzes the stored text data and identifies patterns and formats of past questions. This analysis is performed using specific algorithms and machine learning models (e.g., TensorFlow). The input is the text data of past questions stored in the database, and the output is structured data that identifies the format and patterns of each question. The server uses this structured data for further processing.

[1668] Step 3:

[1669] The server generates mock exam questions based on the analyzed past exam data. It uses a generative AI model to create new questions. Structured data on the patterns and formats of past exam questions is used as input, and newly generated mock exam questions are obtained as output. This data is then ready to be sent to the device.

[1670] Step 4:

[1671] The device displays the generated mock test questions to the user. The user takes the mock test through the smart glasses and answers each question. The mock test questions are input, and the user's answers are sequentially collected as output. The device then sends this answer data to the server.

[1672] Step 5:

[1673] The server receives the user's answers sent from the device and automatically scores them. Scoring is done by comparing the user's answers with pre-set correct answer data. The input is the user's answer data, and the output is the score for each question and the total score. Furthermore, the server analyzes the user's answering tendencies based on the analysis results and identifies weak areas.

[1674] Step 6:

[1675] The server stores the identified weak areas in a database. This information is used to generate the next mock test questions. The input is the analysis results, and the output is the weak areas stored in the database.

[1676] Step 7:

[1677] The server sends the newly generated mock test questions to the terminal, and the terminal notifies the user. The input is the newly generated mock test questions, and the output is the notification to the user. The user receives the notification and is ready to take the next mock test.

[1678] Step 8:

[1679] If a user has any questions during or after the mock test, they can input them through the smart glasses. The device then sends the questions to the server. The input is the user's question, and the output is the transmission of the question data to the server.

[1680] Step 9:

[1681] The server analyzes the received question and generates an appropriate answer. If necessary, it references a generative AI model and a pre-prepared FAQ database. The input is the user's question data, and the output is the generated answer. This answer is sent to the terminal and displayed to the user.

[1682] Step 10:

[1683] The terminal displays the answer received from the server to the user. The input is the answer data from the server, and the output is information provided to the user. This allows the user to immediately resolve their question.

[1684] The above is a specific flow of the processing steps of the system, and describes the inputs and outputs used in each step, as well as data processing and calculations.

[1685] 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.

[1686] This system automatically generates mock exam questions for qualification exams and provides users with an optimized learning experience. In particular, it combines an emotion engine that recognizes the user's emotional state and reflects that information in adjusting the difficulty of the mock exam and providing study advice, thereby achieving even more advanced learning support.

[1687] Program processing

[1688] Enter past exam questions

[1689] 1. User: Upload past exam questions to the system in PDF or other format.

[1690] 2. Terminal: Receives uploads from users and sends files to the server.

[1691] 3. Server: Analyzes the received files, extracts the content of the questions as text data, and identifies and classifies the format and patterns of each question.

[1692] 4. Server: Stores and organizes the analyzed data in a database.

[1693] Mock test question generation

[1694] 1. Server: Based on a database of past questions, the server runs an algorithm that learns question trends and formats, and creates templates for automatically generating mock test questions.

[1695] 2. Terminal: Notifies the user that the generated practice test questions are ready.

[1696] 3. User: Clicks on the "Start" button to begin the practice test.

[1697] Mock test implementation and result analysis

[1698] 1. User: Enter the answers to each question and click the "Submit" button after completing all answers.

[1699] 2. Terminal: Records the user's answers and sends them to the server.

[1700] 3. Server: Receives answers, automatically grades them, calculates scores, analyzes user's answer patterns, and identifies weak areas.

[1701] 4. Server: Runs the emotion engine that recognizes the user's emotional state based on the analysis results.

[1702] Utilizing the Emotion Engine

[1703] 1. Server: Adjust the difficulty of the mock test questions based on the user's recognized emotional state (e.g., impatience, anxiety, relaxation, etc.).

[1704] 2. Server: Generates learning advice and encouraging messages according to the recognized user's emotional state.

[1705] 3. Terminal: Presents the user with tailored practice questions and advice.

[1706] 4. Users: Receive advice during their learning process and retake the mock exams.

[1707] Implementing chat functionality

[1708] 1. User: Enter a question about a problem you don't understand through the terminal.

[1709] 2. Terminal: Sends the user's question data to the server.

[1710] 3. Server: Analyzes the question and generates an appropriate answer from learning data and pre-prepared FAQs.

[1711] 4. Terminal: The generated answer is displayed to the user for further understanding.

[1712] Specific examples

[1713] 1. Enter past exam questions

[1714] User: "I'll upload the past three years' worth of exam questions in PDF format."

[1715] Terminal: "File received. Sending to server..."

[1716] Server: "Parsing file... Problem data extracted."

[1717] 2. Generating mock test questions

[1718] Server: "Generate mock exam questions based on past exam data..."

[1719] Terminal: "The practice test questions are ready. Would you like to begin?"

[1720] 3. Mock test implementation and result analysis

[1721] User: "Answer question 1. I choose option C."

[1722] Terminal: "Your answer has been recorded. Would you like to proceed to the next question?"

[1723] User: "I've answered all the questions. I'm going to submit it."

[1724] Terminal: "Sending answer to server..."

[1725] Server: "Analyzing your answer... Score is 70. Weak subject is math. Current emotional state is slightly anxious."

[1726] 4. Utilizing the Emotion Engine

[1727] Server: "Generate slightly easier practice questions based on your perceived anxiety state..."

[1728] Server: "Good job! Let's try this next problem. I think you'll feel more confident if you brush up on the basics in this area."

[1729] Terminal: "New practice test questions and advice displayed."

[1730] 5. Implementing chat functionality

[1731] User: "I have a question about question 3. I don't understand option B. Can you explain it in more detail?"

[1732] Terminal: "Sending question to server..."

[1733] Server: "Parsing your question... generated a suitable answer."

[1734] Terminal: "Answers have arrived, with detailed explanations."

[1735] This system provides an efficient and personalized learning experience while taking into account the user's progress and emotional state. By combining it with an emotion engine, it reduces the user's psychological burden and enables more effective learning support.

[1736] The processing flow will be explained below.

[1737] Program processing steps

[1738] Step 1:

[1739] User: Upload past qualification exam question sets to the system in PDF or other formats.

[1740] Step 2:

[1741] Terminal: Receives uploads from users and sends files to the server.

[1742] Step 3:

[1743] Server: Analyzes the received file, extracts the question content as text data, and identifies and classifies the format and patterns of each question (e.g., words, options, answers).

[1744] Step 4:

[1745] Server: Stores the analyzed data in a database and organizes the classified problem data.

[1746] Step 5:

[1747] Server: Based on a database of past questions, the server runs an algorithm that learns question trends and formats, and creates templates for automatically generating mock test questions.

[1748] Step 6:

[1749] Terminal: Notifies the user that the generated practice test questions are ready.

[1750] Step 7:

[1751] User: Clicks on the "Start" button to begin the practice test.

[1752] Step 8:

[1753] Terminal: displays practice test questions to the user.

[1754] Step 9:

[1755] User: Enters an answer for each question, e.g., for multiple choice questions, clicks on the appropriate answer.

[1756] Step 10:

[1757] Terminal: The user's answers are recorded in real time, and after all answers are completed, they are sent to the server by clicking the "Submit" button.

[1758] Step 11:

[1759] Server: Receives all answers and automatically grades them. Calculates scores and analyzes users' answering trends.

[1760] Step 12:

[1761] Server: Based on the analysis results, identify the user's weak areas and store the weak areas information in a database.

[1762] Step 13:

[1763] Server: When generating the next mock test questions, the server reflects the information on the identified weak areas and generates questions that focus on those areas.

[1764] Step 14:

[1765] Terminal: Notifies the user that the newly generated practice test questions are ready.

[1766] Step 15:

[1767] User: Take the practice test again and continue studying.

[1768] Step 16:

[1769] User: During or after the mock test, enter questions about any questions you don't understand through the terminal.

[1770] Step 17:

[1771] Terminal: Sends the user's question data to the server.

[1772] Step 18:

[1773] Server: Analyzes the question and generates an appropriate answer from learning data and pre-prepared FAQs.

[1774] Step 19:

[1775] Terminal: Displays the generated answer to the user to help them understand it.

[1776] Step 20:

[1777] Server: During or after the user answers, the server uses an emotion engine to recognize the user's emotional state, for example, by using a facial recognition camera or voice analysis.

[1778] Step 21:

[1779] Server: Runs an algorithm that adjusts the difficulty of practice test questions based on perceived emotional state (e.g., impatience, anxiety, relaxation).

[1780] Step 22:

[1781] Server: Generates learning advice and encouraging messages according to the user's emotional state.

[1782] Step 23:

[1783] Terminal: Displays the adjusted practice test questions and generated advice to the user.

[1784] Step 24:

[1785] Users: Retry the adjusted practice questions or continue studying as advised.

[1786] This series of processes allows users to efficiently prepare for qualification exams while taking into account their own progress and emotional state, and allows them to immediately resolve any questions they may have while studying.

[1787] Example 2

[1788] 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."

[1789] Conventional mock test systems generate mock test questions based on past exam questions and analyze users' answers. However, they lacked personalized learning support, such as adjusting the difficulty level based on the user's emotional state and providing study advice. As a result, some users found the test questions to be overly difficult, while others found them too easy, preventing effective learning. Furthermore, the system provided limited intuitive support and feedback for answers, preventing users from maximizing their learning effectiveness. A system that can solve these issues and provide a more personalized learning experience is needed.

[1790] 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.

[1791] In this invention, the server includes means for receiving and analyzing past exam question data as input, means for generating mock exam questions from the analyzed data, means for receiving and analyzing the user's answers, means for identifying weak areas based on the analyzed user's answers, means for generating next mock exam questions reflecting the identified weak areas, means for the user to input questions, means for generating answers to the questions, means for recognizing the user's emotional state, means for adjusting the difficulty of mock exam questions based on the recognized emotional state, and means for generating study advice according to the emotional state, thereby enabling personalized study support according to the user's emotional state and learning progress.

[1792] "Past exam question data" refers to data that includes the content and format of questions in exams that have been administered in the past.

[1793] "Means of analysis" refers to algorithms or software that analyze input data and extract and organize meaningful information.

[1794] "Means for generating mock test questions" refers to processes and systems for creating new mock test questions using algorithms based on past test question data.

[1795] "User's answer result" is data indicating the answer selected or written by the user to the mock test question.

[1796] The "means for receiving and analyzing answer results" refers to an algorithm or system that receives answer data submitted by users and analyzes whether the answers are correct or incorrect and the trends of each answer.

[1797] The "means for identifying weak areas" refers to an algorithm and system for analyzing the user's answers and identifying categories and patterns of questions with a low rate of correct answers.

[1798] "Means for user input of questions" are interfaces and devices that allow users to input questions about a particular problem.

[1799] "Means for generating answers" refers to processes or systems that generate answers using existing databases and AI models to provide appropriate answers to questions from users.

[1800] "Means for recognizing the user's emotional state" refers to an algorithm or system for assessing the user's mental and emotional state based on the user's behavioral data, answering tendencies, data from sensor devices, etc.

[1801] The "means for adjusting the difficulty of the mock test questions" refers to an algorithm and system for appropriately changing the difficulty of the mock test questions given in accordance with the user's emotional state and learning progress.

[1802] A "means for generating study advice" is an algorithm or system used to generate personalized study methods and encouraging messages based on the user's study situation and emotional state.

[1803] This invention is a system that automatically generates mock exam questions for qualification exams and provides users with an optimized learning experience. In particular, this system is equipped with an emotion engine that recognizes the user's emotional state and reflects this in adjusting the difficulty level of the mock exam and providing study advice, thereby achieving more advanced learning support.

[1804] System configuration

[1805] The system consists of three main components: a server, a terminal, and a user. The functions and specific operations of each component are explained below.

[1806] Enter past exam questions

[1807] 1. User: Upload past exam question collections to the system in PDF format. The user clicks the "Upload" button on the system interface and selects the PDF file from the file selection dialog.

[1808] 2. Terminal: Receives uploads from users and sends files to the server. The terminal sends files to the server via HTTP requests and displays a progress bar.

[1809] 3. Server: The received file is analyzed and the problem content is extracted as text data. Specifically, optical character recognition (OCR) software (e.g., Tesseract) is used to convert the PDF file into text data. Natural language processing (NLP) techniques are then used to identify problem formats and patterns. The analyzed data is then stored in a database (e.g., MySQL).

[1810] Mock test question generation

[1811] 1. Server: Learns question trends and formats based on a database of past questions. This is done using machine learning models (e.g., random forests, neural networks). Generates mock test question templates based on the learning results.

[1812] 2. Terminal: Notify the user that the generated practice test questions are ready, using a pop-up message or notification badge (e.g., "New practice test questions are available").

[1813] 3. User: Clicks the "Start" button to begin the mock test. The user clicks the "Start Test" button on the dashboard screen and moves to the test screen.

[1814] Mock test implementation and result analysis

[1815] 1. User: Enter the answer for each question and click the "Submit" button. The user selects or enters the answer for each question and clicks the "Submit" button after answering all questions.

[1816] 2. Terminal: Records the user's answers and sends them to the server. The answer data is sent to the server using an HTTP request.

[1817] 3. Server: Receives the answers and automatically scores them. The server compares the answers with the correct answer database and assigns a score. The server then analyzes the user's answering tendencies based on the analysis results and identifies weak areas.

[1818] 4. Server: Runs the emotion engine to recognize emotional states based on the analysis results, using data from emotion analysis APIs and sensor devices.

[1819] Utilizing the Emotion Engine

[1820] 1. Server: Adjust the difficulty of the mock test questions based on the user's perceived emotional state. Reset the difficulty parameters according to the user's emotional state (e.g., impatience, anxiety, relaxation).

[1821] 2. Server: Generates learning advice based on the user's emotional state. Natural language generation (NLG) technology is used to generate encouraging messages and advice on how to study.

[1822] 3. Terminal: The adjusted mock test questions and advice are presented to the user. The user then takes the advice into consideration and attempts a new mock test.

[1823] Implementing chat functionality

[1824] 1. User: Enter a question about a problem they don't understand. Open a chat window, enter a question, and click the send button.

[1825] 2. Terminal: Sends the question data to the server. Sends the question via HTTP request and displays a progress bar.

[1826] 3. Server: Analyzes the question and generates an appropriate answer from training data and FAQs. Answers are generated using natural language processing (NLP) technology and generative AI models (e.g., GPT-3).

[1827] 4. Terminal: Show the generated answer to the user. Show the answer in the chat window to help the user understand.

[1828] Specific examples

[1829] Enter past exam questions

[1830] User: "I'll upload the past three years' worth of exam questions in PDF format."

[1831] Terminal: "File received. Sending to server..."

[1832] Server: "Parsing file... Problem data extracted."

[1833] Mock test question generation

[1834] Server: "Generate mock exam questions based on past exam data..."

[1835] Terminal: "The practice test questions are ready. Would you like to begin?"

[1836] Mock test implementation and result analysis

[1837] User: "Answer question 1. I choose option C."

[1838] Terminal: "Your answer has been recorded. Would you like to proceed to the next question?"

[1839] User: "I've answered all the questions. I'm going to submit it."

[1840] Terminal: "Sending answer to server..."

[1841] Server: "Analyzing your answer... Score is 70. Weak subject is math. Current emotional state is slightly anxious."

[1842] Utilizing the Emotion Engine

[1843] Server: "Generate slightly easier practice questions based on your perceived anxiety state..."

[1844] Server: "You're doing great. I think you'll gain confidence if you brush up on the basics in this area."

[1845] Terminal: "New practice test questions and advice displayed."

[1846] Implementing chat functionality

[1847] User: "I have a question about question 3. I don't understand option B. Can you explain it in more detail?"

[1848] Terminal: "Sending question to server..."

[1849] Server: "Parsing your question... generated a suitable answer."

[1850] Terminal: "Answers have arrived, with detailed explanations."

[1851] This system provides an efficient and personalized learning experience while taking into account the user's progress and emotional state. By combining it with an emotion engine, it reduces the user's psychological burden and enables more effective learning support.

[1852] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1853] Step 1:

[1854] User: Upload past qualification exam question sets to the system in PDF or other formats.

[1855] Specific operation: The user clicks the "Upload" button on the system interface and selects a PDF file from the file selection dialog.

[1856] Input: Past exam question collection file in PDF format.

[1857] Output: The upload request is sent to the device.

[1858] Step 2:

[1859] Terminal: Receives uploads from users and sends files to the server.

[1860] Specific operation: The terminal sends the file to the server via an HTTP request and displays a progress bar.

[1861] Input: PDF file uploaded by user.

[1862] Output: The file is sent to the server.

[1863] Step 3:

[1864] Server: Analyzes the received file and extracts the problematic content as text data.

[1865] How it works: The server uses OCR (Optical Character Recognition) software (e.g., Tesseract) to convert PDF files into text data, and uses Natural Language Processing (NLP) techniques to identify problem formats and patterns. The parsed data is then stored in a database (e.g., MySQL).

[1866] Input: The PDF file sent to the server.

[1867] Output: Parsed problem information as text data.

[1868] Step 4:

[1869] Server: Learn question trends and formats based on a database of past questions.

[1870] Specific operation: Using machine learning models (e.g., random forests, neural networks), the system learns from past exam data and generates mock exam question templates based on the learning results.

[1871] Input: Past question data stored in the database.

[1872] Output: Generated mock exam question templates.

[1873] Step 5:

[1874] Terminal: Notifies the user that the generated practice test questions are ready.

[1875] Specific behavior: When a device receives a notification from the server, it displays a pop-up message or notification badge (e.g., "New practice test questions are available.").

[1876] Input: Notification information from the server.

[1877] Output: A notification message to the user.

[1878] Step 6:

[1879] User: Clicks on the "Start" button to begin the practice test.

[1880] Specific operation: The user clicks the "Start test" button on the dashboard screen to transition to the test screen.

[1881] Input: User action (button click).

[1882] Output: Transition to mock test screen.

[1883] Step 7:

[1884] User: Enter the answer to each question and click the "Submit" button.

[1885] Specific operation: The user selects or enters an answer for each question, and when all questions have been answered, clicks the "Submit" button.

[1886] Input: User's answer data.

[1887] Output: All answer data is recorded on the device.

[1888] Step 8:

[1889] Terminal: Records the user's answers and sends them to the server.

[1890] Specific operation: The device temporarily stores all answer data and sends it to the server using an HTTP request. A progress bar is displayed.

[1891] Input: User's answer data.

[1892] Output: The answer data is sent to the server.

[1893] Step 9:

[1894] Server: Receives answers, automatically grades them, calculates scores, analyzes user's answer patterns, and identifies weak areas.

[1895] Specific operations: Compare answers with a database of correct answers and perform scoring. Analyze answer trends and identify weak areas using statistical methods. Store data on weak areas in a database.

[1896] Input: Answer data and correct answer database.

[1897] Output: Scores and analysis results.

[1898] Step 10:

[1899] Server: Runs the emotion engine that recognizes the user's emotional state based on the analysis results.

[1900] Specific operation: Executes emotion recognition algorithms using analytical data and data from sensor devices.

[1901] Input: Analysis results and sensor device data.

[1902] Output: The user's emotional state.

[1903] Step 11:

[1904] Server: Adjusts the difficulty of practice test questions based on perceived emotional state.

[1905] Specific operation: Using the emotional state, the parameters of the mock test question generation algorithm are reset to adjust the difficulty level.

[1906] Input: User's emotional state and mock test template.

[1907] Output: Difficulty-adjusted practice test questions.

[1908] Step 12:

[1909] Server: Generates learning advice and encouraging messages depending on the recognized emotional state.

[1910] What it does: Uses natural language generation (NLG) technology to generate personalized advice and encouraging messages for users.

[1911] Input: The user's emotional state.

[1912] Output: Study advice and encouraging messages.

[1913] Step 13:

[1914] Terminal: Presents tailored practice test questions and advice to the user.

[1915] Specific operation: Receives data from the server and displays it on the device's UI.

[1916] Input: Tailored practice test questions and advice.

[1917] Output: What is displayed to the user.

[1918] Step 14:

[1919] Users: Receive advice as they progress and retake practice exams.

[1920] Specific operation: The user takes the advice provided into consideration and takes on a new mock test.

[1921] Enter: study advice.

[1922] Output: The mock test to try again.

[1923] Step 15:

[1924] User: Type in a question about a problem they don't understand.

[1925] What happens: A user opens a chat window, types a question, and clicks the send button.

[1926] Input: The user's question.

[1927] Output: Sending the question data by terminal.

[1928] Step 16:

[1929] Terminal: Sends the query data to the server.

[1930] Specific behavior: Sends a question via HTTP request and displays a progress bar.

[1931] Input: User question data.

[1932] Output: The query data is sent to the server.

[1933] Step 17:

[1934] Server: Analyzes the question and generates an appropriate answer from learning data and FAQs.

[1935] Specific operation: Generate answers using natural language processing (NLP) techniques and generative AI models (e.g., GPT-3).

[1936] Input: User question data.

[1937] Output: The generated answer.

[1938] Step 18:

[1939] Terminal: Displays the generated answer to the user.

[1940] Specific behavior: Displays the response received from the server in the chat window.

[1941] Input: The generated answer.

[1942] Output: Display the answer to the user.

[1943] (Application example 2)

[1944] 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."

[1945] Conventional qualification exam preparation systems have limited functionality for improving users' learning efficiency. In particular, they provide questions of a uniform level of difficulty without considering the user's emotional state, making it impossible to reduce the psychological burden during study. Furthermore, there is a lack of appropriate study support methods for effectively utilizing travel time in an autonomous vehicle. As a result, users tend to lose motivation to study, making it difficult to prepare for exams efficiently.

[1946] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving and analyzing past exam question data as input, means for generating mock exam questions from the analyzed data, means for receiving and analyzing the user's answers, means for identifying weak areas based on the analyzed user's answers, means for generating the next mock exam questions reflecting the identified weak areas, means for recognizing the user's emotional state in the autonomous vehicle, means for adjusting the difficulty of the mock exam questions based on the recognized emotional state, means for generating study advice and messages according to the recognized emotional state, means for the user to input a question, and means for generating an answer to the question. This enables flexible and personalized study support based on the user's emotional state.

[1947] "Past exam question data" refers to data on questions from past qualification exams, and is information stored in text format or scanned PDF format.

[1948] "Mock test questions" refer to virtual test questions that are generated based on past test question data and that users can answer as part of their exam preparation.

[1949] "Autonomous vehicle" means a vehicle that is driven automatically by on-board sensors and technological processing devices, without a human driver.

[1950] An "emotional state" is a psychological state that a user exhibits while answering a practice test, and examples include inner feelings such as impatience, anxiety, and relaxation.

[1951] "Adjusting the difficulty level" refers to the process of changing the difficulty of the mock test questions according to the user's emotional state and learning progress.

[1952] "Study advice" refers to specific advice and guidance provided to users to help them study effectively.

[1953] "Messages" refer to verbal notifications and encouraging statements that are generated based on the user's emotional state and answer status.

[1954] "Means for inputting questions" refers to an interface that allows users to inquire about any unclear points or doubts they may have during the mock test by inputting text or other methods to the system.

[1955] "Automatic scoring" refers to the process in which the system automatically calculates and evaluates the score based on the user's answers.

[1956] The term "weak area" refers to a learning area in which the user has been determined to have a low score and insufficient understanding, as identified from past answer results, etc.

[1957] This invention is a system that automatically generates mock exam questions for qualification exams and provides a learning experience that takes into account the user's emotional state. It is specifically designed to streamline learning in autonomous vehicles. The system is constructed as follows:

[1958] The entire system consists of the user's smartphone or tablet, a cloud server, an emotion recognition API, a natural language processing model, and a camera and microphone installed in the autonomous vehicle.

[1959] Input and analysis of past questions

[1960] Users use their smartphones or tablets to upload past exam question data in PDF format to a cloud server. The cloud server then uses a PDF analysis algorithm to convert the question data into text format, then identifies the format and patterns of each question and stores them in a database. This process can be performed using cloud services such as Amazon Web Services (AWS) and Google Cloud Platform (GCP).

[1961] Mock test question generation

[1962] The cloud server automatically generates mock test questions using a generative AI model (e.g., GPT-3 / 4) based on the stored past exam data. The generated questions are then sent to the user's smartphone or tablet.

[1963] User answers and analysis

[1964] Users answer mock test questions, and their answers are sent to a cloud server in real time. The cloud server automatically grades the answers and calculates the score. It also analyzes the user's answering habits and identifies weak areas.

[1965] Recognition and application of emotional states

[1966] The system uses cameras and microphones installed in autonomous vehicles to recognize the user's emotional state in real time. Emotion recognition utilizes Microsoft Azure Face API and Amazon Rekognition. The recognized emotional state (e.g., impatience, anxiety, relaxation, etc.) is analyzed on a cloud server, and the system adjusts the difficulty of the mock test questions and generates study advice and messages based on that information.

[1967] Questions and Answers

[1968] An interface is also provided for users to input any questions or concerns they may have during the mock test. The cloud server analyzes the user's questions using a natural language processing model (e.g., GPT-3 / 4) and generates appropriate answers. The generated answers are provided to the user in real time.

[1969] Specific examples

[1970] The user uploads the past five years of driving test question sets in PDF format from their smartphone to a cloud server.

[1971] The cloud server analyzes the file and extracts the problem data.

[1972] The server generates mock test questions based on past exam question data.

[1973] The user answers the practice test and sends the answers to the cloud server.

[1974] Your score will be automatically scored and you will be notified of your score and weak areas.

[1975] A camera and microphone are used to recognize the user's emotions inside an autonomous vehicle.

[1976] The server adjusts the difficulty of the mock test based on the emotional state and generates study advice.

[1977] The user enters a question, and the cloud server uses natural language processing to generate an appropriate answer.

[1978] Prompt Sentence Examples

[1979] Below are some example prompts for a generative AI model (e.g., GPT-3 / 4):

[1980] "The user is working on a mock exam in a self-driving vehicle. Provide appropriate advice based on the following information: mock exam score: 50; weaknesses: traffic rules; current emotional state: anxiety."

[1981] This enables flexible and personalized learning support based on the user's emotional state.

[1982] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1983] Step 1:

[1984] The user uploads past qualification exam question data in PDF format to a smartphone or tablet.

[1985] Input: Past exam data (PDF file)

[1986] Output: Uploaded PDF file

[1987] Specific operation: The user selects past exam question data from their device and clicks the upload button.

[1988] Step 2:

[1989] The device sends the uploaded PDF file to the cloud server.

[1990] Input: Uploaded PDF file

[1991] Output: PDF file sent to cloud server

[1992] Specific operation: The device receives the file and sends it to the cloud server via the network.

[1993] Step 3:

[1994] The server uses a PDF analysis algorithm to convert the PDF file into text data and identify problem formats and patterns.

[1995] Input: PDF file sent to the cloud server

[1996] Output: Textual problem data and identified format patterns

[1997] Specific operation: The server uses PDF analysis software (e.g., Tesseract OCR) to extract text data from the PDF, and then identifies the format and patterns of each question and stores them in a database.

[1998] Step 4:

[1999] Based on the past exam data stored on the server, mock exam questions are automatically generated using a generative AI model (e.g., GPT-3 / 4).

[2000] Input: Textual problem data and identified format patterns

[2001] Output: Generated practice test questions

[2002] Specific operation: The server learns question trends and formats from the stored data, generates new mock test questions using a generative AI model, and stores them in a database.

[2003] Step 5:

[2004] The terminal notifies the user that the practice test questions are ready.

[2005] Input: Generated practice test questions

[2006] Output: A message to inform the user

[2007] Specific operation: The terminal receives a notification from the server and notifies the user by message that the mock test is ready.

[2008] Step 6:

[2009] The user starts the practice test and enters answers to the questions.

[2010] Input: Generated practice test questions

[2011] Output: User's answer

[2012] Specific operation: The user inputs answers to each question on the terminal and records the answers on the terminal.

[2013] Step 7:

[2014] The device sends the user's answer to the cloud server.

[2015] Input: User's answer

[2016] Output: Answers sent to the cloud server

[2017] Specific operation: The device sends the recorded answers to the server via the network.

[2018] Step 8:

[2019] The server automatically grades the answers and calculates the score. It also analyzes the user's answering tendencies and identifies weak areas.

[2020] Input: Answers sent to the cloud server

[2021] Output: Marking results, scores, weak areas identified

[2022] Specific operation: The server executes the automatic scoring algorithm to calculate the score, and also uses the analysis algorithm to analyze the user's answering tendencies and identify weak areas.

[2023] Step 9:

[2024] Using cameras and microphones mounted on autonomous vehicles, the system recognizes the user's emotional state in real time.

[2025] Input: Real-time video and audio data from cameras and microphones

[2026] Output: Perceived emotional state

[2027] Specific operation: The cloud server uses an emotion recognition API (e.g., Amazon Rekognition or Microsoft Azure Face API) to analyze video and audio data and recognize the user's emotional state.

[2028] Step 10:

[2029] The server adjusts the difficulty of the practice test questions and generates study advice and messages based on the recognized emotional state.

[2030] Input: perceived emotional state, marking results, score, weak areas identified

[2031] Output: Tailored practice questions, study advice, and messages

[2032] Specific operation: The server changes the difficulty level of the practice test questions based on the user's emotional state and generates appropriate study advice and encouraging messages for the user.

[2033] Step 11:

[2034] The device presents the user with tailored practice test questions and study advice.

[2035] Input: Tailored practice test questions, study advice, messages

[2036] Output: What the user sees

[2037] Specific operation: The terminal receives information from the server and presents it on the screen in a format that is easy for the user to see.

[2038] Step 12:

[2039] The user inputs questions using an interface for inputting uncertainties or questions during the mock test.

[2040] Input: User question

[2041] Output: Question typed into the terminal

[2042] Specific operation: The user inputs a question through an input box on the terminal.

[2043] Step 13:

[2044] The device sends the user's question to the cloud server.

[2045] Input: User question

[2046] Output: Questions sent to the cloud server

[2047] Specific operation: The device sends the question to the server via the network.

[2048] Step 14:

[2049] The server analyzes the question and generates an appropriate answer.

[2050] Input: The question sent to the cloud server

[2051] Output: The generated answer

[2052] Specific operation: The server uses a natural language processing model (e.g., GPT-3 / 4) to analyze the question and generate an appropriate answer.

[2053] Step 15:

[2054] The terminal displays the generated answer to the user.

[2055] Input: Generated Answer

[2056] Output: The answer displayed to the user

[2057] Specific operation: The terminal receives the response from the server and presents it on the screen in an easy-to-read format for the user.

[2058] 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.

[2059] 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.

[2060] 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.

[2061] [Fourth embodiment]

[2062] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[2063] 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.

[2064] 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).

[2065] 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.

[2066] 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.

[2067] 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).

[2068] 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.

[2069] 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.

[2070] 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.

[2071] 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.

[2072] 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.

[2073] 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.

[2074] 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."

[2075] This invention is a system that automatically generates mock exam questions for qualification exams, providing users with an optimized learning experience. This system analyzes past exam question data, identifies weak areas based on the user's answers, and generates new mock exam questions that reflect this information. It also provides a function that allows users to ask questions that arise during their studies and provides instant answers.

[2076] Program processing

[2077] 1. Enter past exam questions

[2078] User: Upload past qualification exam question sets to the system in PDF or other formats.

[2079] Terminal: Receives uploads from users and sends files to the server.

[2080] Server: Analyzes the received file, extracts the content of the questions as text data, identifies the format and patterns of each question (e.g., words, options, answers), and stores them in a database.

[2081] 2. Generating mock test questions

[2082] Server: Generates mock test questions based on the analyzed data. It runs an algorithm that learns the patterns and formats of past exam questions and creates new mock questions.

[2083] Terminal: Prepares the generated practice test questions for display to the user.

[2084] User: When you are ready to take the practice test, click the "Start" button on your device.

[2085] 3. Mock test implementation and result analysis

[2086] User: Answer each question one by one, for example, by clicking on the appropriate answer for multiple choice questions.

[2087] Terminal: Records the user's answers in real time, and when all answers have been completed, the user clicks the "Submit" button, which sends the data to the server.

[2088] Server: Receives all answers and automatically scores them. Based on the scores and analysis results, analyzes the user's answering tendencies and identifies weak areas.

[2089] 4. Identify weaknesses and personalize

[2090] Server: Based on the analysis results, the user's weak areas (e.g., specific subjects or question formats) are stored in a database.

[2091] Server: When generating the next mock test questions, this weak area information is reflected and questions that focus on that area are generated.

[2092] Terminal: Prepares to display the newly generated practice test questions and notifies the user.

[2093] Users: They can take the mock exam again and get further learning benefits.

[2094] 5. Implementing chat functionality

[2095] User: During or after the mock test, if there are any questions that the user does not understand, the user can enter the questions through the terminal.

[2096] Terminal: Sends the user's question data to the server.

[2097] Server: Analyzes the question and generates an appropriate answer from training data and pre-prepared FAQs, including detailed explanations and additional references if necessary.

[2098] Terminal: Displays the generated answer to the user for further understanding.

[2099] Specific examples

[2100] 1. Enter past exam questions

[2101] User: "I'll upload the past three years' worth of exam questions in PDF format."

[2102] Terminal: "File received. Sending to server..."

[2103] Server: "Parsing file... Problem data extracted."

[2104] 2. Generating mock test questions

[2105] Server: "Generate mock exam questions based on past exam data..."

[2106] Terminal: "The practice test questions are ready. Would you like to begin?"

[2107] 3. Mock test implementation and result analysis

[2108] User: "Answer question 1. I choose option C."

[2109] Terminal: "Your answer has been recorded. Would you like to proceed to the next question?"

[2110] User: "I've answered all the questions. I'm going to submit it."

[2111] Terminal: "Sending answer to server..."

[2112] Server: "Analyzing your answer... Score 70. Math is my weak point."

[2113] 4. Identify weaknesses and personalize

[2114] Server: "We've saved your weak areas and will incorporate them into your next practice test."

[2115] Terminal: "New practice test questions are ready. Would you like to begin?"

[2116] 5. Implementing chat functionality

[2117] User: "I have a question about question 3. I don't understand option B. Can you explain it in more detail?"

[2118] Terminal: "Sending question to server..."

[2119] Server: "Parsing your question... generated a suitable answer."

[2120] Terminal: "Answers have arrived, with detailed explanations."

[2121] Through this system, users can efficiently prepare for qualification exams while checking their own progress and weak points. In addition, they can instantly resolve any questions they have, significantly improving their learning efficiency.

[2122] The processing flow will be explained below.

[2123] Program processing steps

[2124] Step 1:

[2125] User: Upload past qualification exam question sets to the system in PDF or other formats.

[2126] Step 2:

[2127] Terminal: Receives uploads from users and sends files to the server.

[2128] Step 3:

[2129] Server: Analyzes the received file, extracts the question content as text data, and identifies and classifies the format and patterns of each question (e.g., words, options, answers).

[2130] Step 4:

[2131] Server: Stores the analyzed data in a database and organizes the classified problem data.

[2132] Step 5:

[2133] Server: Based on a database of past questions, the server runs an algorithm that learns question trends and formats, and creates templates for automatically generating mock test questions.

[2134] Step 6:

[2135] Terminal: Notifies the user that the generated practice test questions are ready.

[2136] Step 7:

[2137] User: Clicks on the "Start" button to begin the practice test.

[2138] Step 8:

[2139] Terminal: displays practice test questions to the user.

[2140] Step 9:

[2141] User: Enters an answer for each question, e.g., for multiple choice questions, clicks on the appropriate answer.

[2142] Step 10:

[2143] Terminal: The user's answers are recorded in real time, and after all answers are completed, they are sent to the server by clicking the "Submit" button.

[2144] Step 11:

[2145] Server: Receives all answers and automatically grades them. Calculates scores and analyzes users' answering trends.

[2146] Step 12:

[2147] Server: Based on the analysis results, identify the user's weak areas and store the weak areas information in a database.

[2148] Step 13:

[2149] Server: When generating the next mock test questions, the server reflects the information on the identified weak areas and generates questions that focus on those areas.

[2150] Step 14:

[2151] Terminal: Notifies the user that the newly generated practice test questions are ready.

[2152] Step 15:

[2153] User: Take the practice test again and continue studying.

[2154] Step 16:

[2155] User: During or after the mock test, enter questions about any questions you don't understand through the terminal.

[2156] Step 17:

[2157] Terminal: Sends the user's question data to the server.

[2158] Step 18:

[2159] Server: Analyzes the question and generates an appropriate answer from learning data and pre-prepared FAQs.

[2160] Step 19:

[2161] Terminal: Displays the generated answer to the user to help them understand it.

[2162] This series of processes allows users to efficiently prepare for the qualification exam and also allows them to immediately resolve any questions they may have while studying.

[2163] Example 1

[2164] 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."

[2165] Conventional qualification exam study systems lack the ability to properly identify users' weak areas and focus their learning on those areas, as well as the ability to record answers in real time and provide immediate feedback. Furthermore, they lack the ability to provide immediate solutions to questions users may have during the exam. This can lead to lower user learning efficiency and potentially lower pass rates for qualification exams.

[2166] 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.

[2167] In this invention, the server includes means for receiving and analyzing past exam question data as input, means for generating mock exam questions from the analyzed data, means for receiving and analyzing the user's answers, means for identifying weak areas based on the analyzed user's answers, means for generating the next mock exam questions reflecting the identified weak areas, means for the user to input questions, means for generating answers to the questions, means for saving the weak areas in a database, means for recording answers during the mock exam in real time, and means for learning a model based on the database of past questions. This makes it possible to identify the user's weak areas and have them study them intensively, and can provide immediate answers to any questions that arise during study, thereby significantly improving study efficiency.

[2168] "Past exam question data" refers to information about questions and answers from previous exams.

[2169] "Means of analysis" is a function for analyzing input data and extracting and identifying useful information.

[2170] "Mock test questions" are provisional test questions that users answer as practice to prepare for the actual test.

[2171] "Means of generation" refers to the function for creating new information and content based on data.

[2172] "User's answer results" are answers selected by the user to the mock test questions and answer information.

[2173] A "weak area" is an area in which a user shows low scores in a particular genre or theme based on the results of a mock test.

[2174] "Means for inputting questions" refers to an interface or function that allows users to input doubts or questions to the system.

[2175] The "means for generating an answer" is a function for creating and providing an appropriate answer to a question entered by a user.

[2176] "Means for storing in a database" refers to the function of storing analyzed information and data for the long term and retrieving it as needed.

[2177] "Means for recording in real time" is a function for instantly recording information on a user's actions or answers the moment they occur.

[2178] "Means of learning the model" is a feature that allows the algorithm to learn patterns and rules using past data so that it can adapt to new situations.

[2179] The present invention provides a system for automatically generating mock questions for qualification examinations and providing users with an optimized learning experience. This system is realized through the interaction of a server, a terminal, and a user.

[2180] First, a user uploads past exam question data to the system in a file format such as PDF. The terminal receives the uploaded file and sends it to the server. The server analyzes the received PDF file and extracts text data using a file analysis tool (Apache PDFBox as a specific example). It then uses a Natural Language Processing (NLP) model (spaCy or NLTK as a specific example) to identify information about the questions, options, and answers, and stores this information in a database.

[2181] Next, the server generates mock test questions by learning the patterns and trends of each question using a machine learning algorithm (specifically, GPT-3 or BERT) based on a database of past questions. The generated mock test questions are sent to the device and displayed on the user interface. The user then clicks the start mock test button to begin the test.

[2182] During the mock test, the user answers each question and clicks the next button to proceed. The device records the user's answers in real time, and when the "Submit" button is clicked after the test is completed, the answer data is sent to the server. The server automatically scores the received answer data and calculates the user's score using a specific algorithm (for example, Scikit-learn or TensorFlow). It also analyzes answer trends and records specific weak areas in a database.

[2183] After identifying weak areas, the server adjusts the algorithm to include content that emphasizes the user's weak areas when generating the next mock test questions, and prepares to display them on the device, allowing the user to focus on studying their weak areas.

[2184] During or after the mock test, users can enter questions about problems they didn't understand in the chat box. The device sends the entered question to the server, which analyzes it using an NLP model (specifically, BERT or GPT-3) to generate an appropriate answer. The generated answer references FAQ data and related materials in the database, and the device displays it to the user.

[2185] Specific examples

[2186] Enter past exam questions

[2187] User: "I'll upload the past three years' worth of exam questions in PDF format."

[2188] Terminal: "File received. Sending to server..."

[2189] Server: "Parsing file... Problem data extracted."

[2190] Mock test question generation

[2191] Server: "Generate mock exam questions based on past exam data..."

[2192] Terminal: "The practice test questions are ready. Would you like to begin?"

[2193] Mock test implementation and result analysis

[2194] User: "Answer question 1. I choose option C."

[2195] Terminal: "Your answer has been recorded. Would you like to proceed to the next question?"

[2196] User: "I've answered all the questions. I'm going to submit it."

[2197] Terminal: "Sending answer to server..."

[2198] Server: "Analyzing your answer... Score 70. Math is my weak point."

[2199] Identifying weaknesses and personalizing

[2200] Server: "We've saved your weak areas and will incorporate them into your next practice test."

[2201] Terminal: "New practice test questions are ready. Would you like to begin?"

[2202] Implementing chat functionality

[2203] User: "I have a question about question 3. I don't understand option B. Can you explain it in more detail?"

[2204] Terminal: "Sending question to server..."

[2205] Server: "Parsing your question... generated a suitable answer."

[2206] Terminal: "Answers have arrived, with detailed explanations."

[2207] Through this system, users can effectively prepare for qualification exams, identify their weaknesses through mock tests, and deepen their understanding. Real-time feedback and answers to questions also greatly improve learning efficiency.

[2208] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2209] Step 1: Upload past exam questions

[2210] User: Prepare past exam question data in PDF format and click the upload button on the device.

[2211] Input: Past exam question data (PDF file).

[2212] Terminal: Receives the PDF file from the user and sends it to the server in bytes.

[2213] Output: The PDF file sent to the server.

[2214] Specific operation: A file selection window is displayed, and after the user selects the target file, the upload operation is performed.

[2215] Step 2: Analyzing the file contents

[2216] Server: Convert the received PDF file into text data using a file analysis tool (such as Apache PDFBox).

[2217] Input: PDF file.

[2218] Server: The converted text data is processed using an NLP model (such as spaCy or NLTK) to identify test questions, answer choices, and answers.

[2219] Output: Structured exam question data.

[2220] What it does: It uses a PDF parsing library to extract text from PDFs and then uses an NLP model to perform natural language processing and identify specific patterns.

[2221] Step 3: Saving to the database

[2222] Server: Stores the analyzed problem data in a database (e.g., MySQL or PostgreSQL).

[2223] Input: Structured exam question data.

[2224] Output: Exam question data stored in a database.

[2225] What it does: Establishes a database connection and saves data using an SQL query.

[2226] Step 4: Generate practice test questions

[2227] Server: Generates new mock test questions using generative AI models (such as GPT-3 and BERT) based on past questions in the database.

[2228] Input: Past exam data in the database.

[2229] Output: Generated practice test questions.

[2230] What it does: Apply machine learning algorithms to generate and format new problem data.

[2231] Step 5: Prepare to view the practice test questions

[2232] Terminal: Receives the generated practice test questions and prepares them for display on the user interface.

[2233] Input: Generated practice test questions.

[2234] Output: Practice test questions displayed in the user interface.

[2235] What it does: Formats problem data and converts it into HTML or JSON for display in a browser or app interface.

[2236] Step 6: Start the practice test

[2237] User: Click the Start Practice Test button to begin the practice test.

[2238] Input: User's starting instructions.

[2239] Terminal: Displays test questions sequentially and accepts user answers in input format.

[2240] Output: The answer from the user.

[2241] Specific operation: When the start button is pressed, the screen will move to the question display screen and prepare the answer input field.

[2242] Step 7: Record and submit your answers

[2243] User: Answer each question and click the next button to proceed.

[2244] Input: User's answer data.

[2245] Terminal: Each answer is recorded in real time, and the answer data is sent to the server when the "Submit" button is clicked after the test is completed.

[2246] Output: The answer data sent to the server.

[2247] Specific operation: Once the answer has been entered, the next question will be displayed, and once all questions have been completed, the answer data will be sent to the server.

[2248] Step 8: Scoring and analyzing results

[2249] Server: Based on the received answer data, the server automatically scores the answers. Specifically, it calculates the score using an algorithm (such as Scikit-learn or TensorFlow).

[2250] Input: User's answer data.

[2251] Output: User's score and weak areas analysis.

[2252] Specific operation: The received data is input into the evaluation algorithm for scoring and performance analysis.

[2253] Step 9: Record your weaknesses

[2254] Server: Based on the analysis results, identify the weak areas of each user and store them in a database.

[2255] Input: User scores and analysis results.

[2256] Output: Weakness information stored in a database.

[2257] Specific operation: Analysis results are added and saved to the user profile in the database.

[2258] Step 10: Generate new practice questions

[2259] Server: When generating the next mock test questions, generate new questions that focus on the user's weak areas.

[2260] Input: Data on weak areas.

[2261] Output: The newly generated practice test questions.

[2262] Specific operation: Refer to information on weak areas and use a generative AI model to generate specialized questions.

[2263] Step 11: Notification of new practice test questions

[2264] Terminal: Prepares to display the generated practice test questions and notifies the user.

[2265] Input: Newly generated practice test questions.

[2266] Output: The new practice test question and notification message displayed in the user interface.

[2267] Specific behavior: Convert new problem data into a display format and notify the user, for example, with a notification banner.

[2268] Step 12: Submit your question

[2269] Users: During or after the mock exam, type questions into the chat box about any questions they didn't understand.

[2270] Input: The user's question.

[2271] Terminal: Sends the query data to the server.

[2272] Output: The query data sent to the server.

[2273] Specific operation: Questions entered in the chat box are transferred to the server in real time.

[2274] Step 13: Parsing the question and generating an answer

[2275] Server: Analyzes the question using an NLP model (such as BERT or GPT-3) and generates an appropriate answer.

[2276] Input: User question data.

[2277] Output: The generated answer.

[2278] Specific operation: Performs natural language processing of the question and generates an answer based on FAQ data and related materials in the database.

[2279] Step 14: View your answers

[2280] Terminal: Displays the generated answers in a user interface.

[2281] Input: Generated response data.

[2282] Output: The answer displayed in the user interface.

[2283] Specific operation: Convert the response data into an appropriate format and display it on the chat screen, etc.

[2284] In this way, by clearly indicating the specific operations, inputs, and outputs at each processing step, it is possible to understand in detail how the user, terminal, and server cooperate to operate the entire system.

[2285] (Application example 1)

[2286] 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."

[2287] When studying for qualification exams, users need more than just past exam question collections; they need effective study methods that focus on their weak areas. There is also a lack of ways to instantly resolve questions that arise during study. Furthermore, there is the challenge of providing these exam preparation materials using smart devices, regardless of location or time.

[2288] 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.

[2289] In this invention, the server includes a means for scanning past exam papers with a camera and transmitting the data to the server, a means for the user to take the mock exam through smart glasses, and a means for automatically scoring all answers and displaying the analysis results to the user, allowing the user to study efficiently and effectively anywhere and quickly resolve any questions.

[2290] "Past exam question data" refers to digital records of the content of questions from previous qualification exams.

[2291] An "analyzing means" is a computer program or algorithm that processes input data and analyzes it to understand its content and characteristics.

[2292] "Mock test questions" are virtual test questions that users answer as practice in preparation for the actual test.

[2293] "User" means an individual or learner who uses this system to prepare for a qualification exam.

[2294] "Answer results" are the contents of the answers provided by the user to the mock test.

[2295] "Weak areas" refer to areas or subjects in which the user frequently gets exam questions wrong.

[2296] A "question" is an inquiry about content that the user found difficult to understand during the mock test or during study.

[2297] An "answer" is an explanation or information provided in response to a user's question.

[2298] "Camera scanning" means using a camera to capture a digital image of a physical document and convert its contents into digital data.

[2299] A "server" is a powerful computer system for storing, processing, and serving data.

[2300] "Smart glasses" are eyeglass-shaped devices equipped with a display and computer functionality that allow the wearer to obtain visual information.

[2301] "Automatic scoring" is a function in which the system evaluates the user's answers and calculates the score.

[2302] "Analysis results" are information about the user's learning tendencies and weak areas that the system derives from the user's answers.

[2303] The present invention enables users to effectively study for qualification exams by using practice tests. The system includes a server, a terminal (e.g., smart glasses), and a user interface.

[2304] Program Generation and Explanation

[2305] 1. Enter past exam questions

[2306] The user scans a collection of past qualification exam questions with the camera in the smart glasses and sends the data to the server.

[2307] The server uses OCR (Optical Character Recognition) technology to convert the contents of the scanned question set into digital text, identify the question format and patterns, and store them in a database (e.g., using Google Cloud Vision API).

[2308] 2. Generating mock test questions

[2309] The server generates mock test questions based on the stored data, learning the patterns and formats of past questions and creating new mock questions using a generative AI model (e.g., TensorFlow).

[2310] The terminal prepares to display the generated practice test questions to the user.

[2311] 3. Mock test implementation and result analysis

[2312] Users take practice tests through smart glasses and input their answers to each question.

[2313] The terminal collects the user's answers in real time and transmits the data to the server after all answers have been completed.

[2314] The server performs automatic scoring, analyzes the user's answering tendencies based on the scores and analysis results, and identifies weak areas.

[2315] 4. Identify weaknesses and personalize

[2316] The server stores the user's weak areas in a database based on the analysis results. This allows the server to reflect this information on the weak areas when generating the next mock test questions, and generate questions that focus on those areas.

[2317] The terminal notifies the user of the newly generated practice test questions.

[2318] 5. Implementing chat functionality

[2319] During or after the mock test, users can input questions about any questions they don't understand through the smart glasses.

[2320] The terminal transmits the user's question data to the server.

[2321] The server analyzes the question and generates an appropriate answer from learning data and pre-prepared FAQs.

[2322] The terminal displays the generated answers to the user for further understanding.

[2323] Examples of specific examples and prompt usage

[2324] 1. Enter past exam questions

[2325] User: "I'm going to scan the past three years of exam questions."

[2326] Smart Glasses: "Sending data to server..."

[2327] Server: "Parsing data... Problem data extracted."

[2328] 2. Generating mock test questions

[2329] System: "Preparing mock test questions based on past exam data... Completed."

[2330] 3. Mock test implementation and result analysis

[2331] User: "Answer question 1. I choose option C."

[2332] Smart Glasses: "Your answer has been recorded. Would you like to see the next question?"

[2333] 4. Identify weaknesses and personalize

[2334] Server: "A new question has been generated based on the results of the previous test."

[2335] 5. Implementing chat functionality

[2336] User: "I don't understand option A in this question."

[2337] Server: "Analyzing...generating appropriate answer."

[2338] Example prompts to input to the generative AI model

[2339] "Load question data, analyze it and generate new practice test questions."

[2340] "Analyze users' answer patterns and identify areas of weakness."

[2341] "Generate a suitable answer to this question."

[2342] This system allows users to learn efficiently and resolve their questions immediately. This is a specific mode for carrying out the invention.

[2343] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2344] Step 1:

[2345] The user scans a collection of past exam questions for qualification exams with the camera on the smart glasses and sends the data to the server. Specifically, the user sets the glasses to scan mode and has the camera read each page of the question collection. The scanned images are obtained as input, and the server uses OCR technology (e.g., Google Cloud Vision API) to convert these images into text data and store the content in a database. The analyzed text data is generated as output.

[2346] Step 2:

[2347] The server analyzes the stored text data and identifies patterns and formats of past questions. This analysis is performed using specific algorithms and machine learning models (e.g., TensorFlow). The input is the text data of past questions stored in the database, and the output is structured data that identifies the format and patterns of each question. The server uses this structured data for further processing.

[2348] Step 3:

[2349] The server generates mock exam questions based on the analyzed past exam data. It uses a generative AI model to create new questions. Structured data on the patterns and formats of past exam questions is used as input, and newly generated mock exam questions are obtained as output. This data is then ready to be sent to the device.

[2350] Step 4:

[2351] The device displays the generated mock test questions to the user. The user takes the mock test through the smart glasses and answers each question. The mock test questions are input, and the user's answers are sequentially collected as output. The device then sends this answer data to the server.

[2352] Step 5:

[2353] The server receives the user's answers sent from the device and automatically scores them. Scoring is done by comparing the user's answers with pre-set correct answer data. The input is the user's answer data, and the output is the score for each question and the total score. Furthermore, the server analyzes the user's answering tendencies based on the analysis results and identifies weak areas.

[2354] Step 6:

[2355] The server stores the identified weak areas in a database. This information is used to generate the next mock test questions. The input is the analysis results, and the output is the weak areas stored in the database.

[2356] Step 7:

[2357] The server sends the newly generated mock test questions to the terminal, and the terminal notifies the user. The input is the newly generated mock test questions, and the output is the notification to the user. The user receives the notification and is ready to take the next mock test.

[2358] Step 8:

[2359] If a user has any questions during or after the mock test, they can input them through the smart glasses. The device then sends the questions to the server. The input is the user's question, and the output is the transmission of the question data to the server.

[2360] Step 9:

[2361] The server analyzes the received question and generates an appropriate answer. If necessary, it references a generative AI model and a pre-prepared FAQ database. The input is the user's question data, and the output is the generated answer. This answer is sent to the terminal and displayed to the user.

[2362] Step 10:

[2363] The terminal displays the answer received from the server to the user. The input is the answer data from the server, and the output is information provided to the user. This allows the user to immediately resolve their question.

[2364] The above is a specific flow of the processing steps of the system, and describes the inputs and outputs used in each step, as well as data processing and calculations.

[2365] 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.

[2366] This system automatically generates mock exam questions for qualification exams and provides users with an optimized learning experience. In particular, it combines an emotion engine that recognizes the user's emotional state and reflects that information in adjusting the difficulty of the mock exam and providing study advice, thereby achieving even more advanced learning support.

[2367] Program processing

[2368] Enter past exam questions

[2369] 1. User: Upload past exam questions to the system in PDF or other format.

[2370] 2. Terminal: Receives uploads from users and sends files to the server.

[2371] 3. Server: Analyzes the received files, extracts the content of the questions as text data, and identifies and classifies the format and patterns of each question.

[2372] 4. Server: Stores and organizes the analyzed data in a database.

[2373] Mock test question generation

[2374] 1. Server: Based on a database of past questions, the server runs an algorithm that learns question trends and formats, and creates templates for automatically generating mock test questions.

[2375] 2. Terminal: Notifies the user that the generated practice test questions are ready.

[2376] 3. User: Clicks on the "Start" button to begin the practice test.

[2377] Mock test implementation and result analysis

[2378] 1. User: Enter the answers to each question and click the "Submit" button after completing all answers.

[2379] 2. Terminal: Records the user's answers and sends them to the server.

[2380] 3. Server: Receives answers, automatically grades them, calculates scores, analyzes user's answer patterns, and identifies weak areas.

[2381] 4. Server: Runs the emotion engine that recognizes the user's emotional state based on the analysis results.

[2382] Utilizing the Emotion Engine

[2383] 1. Server: Adjust the difficulty of the mock test questions based on the user's recognized emotional state (e.g., impatience, anxiety, relaxation, etc.).

[2384] 2. Server: Generates learning advice and encouraging messages according to the recognized user's emotional state.

[2385] 3. Terminal: Presents the user with tailored practice questions and advice.

[2386] 4. Users: Receive advice during their learning process and retake the mock exams.

[2387] Implementing chat functionality

[2388] 1. User: Enter a question about a problem you don't understand through the terminal.

[2389] 2. Terminal: Sends the user's question data to the server.

[2390] 3. Server: Analyzes the question and generates an appropriate answer from learning data and pre-prepared FAQs.

[2391] 4. Terminal: The generated answer is displayed to the user for further understanding.

[2392] Specific examples

[2393] 1. Enter past exam questions

[2394] User: "I'll upload the past three years' worth of exam questions in PDF format."

[2395] Terminal: "File received. Sending to server..."

[2396] Server: "Parsing file... Problem data extracted."

[2397] 2. Generating mock test questions

[2398] Server: "Generate mock exam questions based on past exam data..."

[2399] Terminal: "The practice test questions are ready. Would you like to begin?"

[2400] 3. Mock test implementation and result analysis

[2401] User: "Answer question 1. I choose option C."

[2402] Terminal: "Your answer has been recorded. Would you like to proceed to the next question?"

[2403] User: "I've answered all the questions. I'm going to submit it."

[2404] Terminal: "Sending answer to server..."

[2405] Server: "Analyzing your answer... Score is 70. Weak subject is math. Current emotional state is slightly anxious."

[2406] 4. Utilizing the Emotion Engine

[2407] Server: "Generate slightly easier practice questions based on your perceived anxiety state..."

[2408] Server: "Good job! Let's try this next problem. I think you'll feel more confident if you brush up on the basics in this area."

[2409] Terminal: "New practice test questions and advice displayed."

[2410] 5. Implementing chat functionality

[2411] User: "I have a question about question 3. I don't understand option B. Can you explain it in more detail?"

[2412] Terminal: "Sending question to server..."

[2413] Server: "Parsing your question... generated a suitable answer."

[2414] Terminal: "Answers have arrived, with detailed explanations."

[2415] This system provides an efficient and personalized learning experience while taking into account the user's progress and emotional state. By combining it with an emotion engine, it reduces the user's psychological burden and enables more effective learning support.

[2416] The processing flow will be explained below.

[2417] Program processing steps

[2418] Step 1:

[2419] User: Upload past qualification exam question sets to the system in PDF or other formats.

[2420] Step 2:

[2421] Terminal: Receives uploads from users and sends files to the server.

[2422] Step 3:

[2423] Server: Analyzes the received file, extracts the question content as text data, and identifies and classifies the format and patterns of each question (e.g., words, options, answers).

[2424] Step 4:

[2425] Server: Stores the analyzed data in a database and organizes the classified problem data.

[2426] Step 5:

[2427] Server: Based on a database of past questions, the server runs an algorithm that learns question trends and formats, and creates templates for automatically generating mock test questions.

[2428] Step 6:

[2429] Terminal: Notifies the user that the generated practice test questions are ready.

[2430] Step 7:

[2431] User: Clicks on the "Start" button to begin the practice test.

[2432] Step 8:

[2433] Terminal: displays practice test questions to the user.

[2434] Step 9:

[2435] User: Enters an answer for each question, e.g., for multiple choice questions, clicks on the appropriate answer.

[2436] Step 10:

[2437] Terminal: The user's answers are recorded in real time, and after all answers are completed, they are sent to the server by clicking the "Submit" button.

[2438] Step 11:

[2439] Server: Receives all answers and automatically grades them. Calculates scores and analyzes users' answering trends.

[2440] Step 12:

[2441] Server: Based on the analysis results, identify the user's weak areas and store the weak areas information in a database.

[2442] Step 13:

[2443] Server: When generating the next mock test questions, the server reflects the information on the identified weak areas and generates questions that focus on those areas.

[2444] Step 14:

[2445] Terminal: Notifies the user that the newly generated practice test questions are ready.

[2446] Step 15:

[2447] User: Take the practice test again and continue studying.

[2448] Step 16:

[2449] User: During or after the mock test, enter questions about any questions you don't understand through the terminal.

[2450] Step 17:

[2451] Terminal: Sends the user's question data to the server.

[2452] Step 18:

[2453] Server: Analyzes the question and generates an appropriate answer from learning data and pre-prepared FAQs.

[2454] Step 19:

[2455] Terminal: Displays the generated answer to the user to help them understand it.

[2456] Step 20:

[2457] Server: During or after the user answers, the server uses an emotion engine to recognize the user's emotional state, for example, by using a facial recognition camera or voice analysis.

[2458] Step 21:

[2459] Server: Runs an algorithm that adjusts the difficulty of practice test questions based on perceived emotional state (e.g., impatience, anxiety, relaxation).

[2460] Step 22:

[2461] Server: Generates learning advice and encouraging messages according to the user's emotional state.

[2462] Step 23:

[2463] Terminal: Displays the adjusted practice test questions and generated advice to the user.

[2464] Step 24:

[2465] Users: Retry the adjusted practice questions or continue studying as advised.

[2466] This series of processes allows users to efficiently prepare for qualification exams while taking into account their own progress and emotional state, and allows them to immediately resolve any questions they may have while studying.

[2467] Example 2

[2468] 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."

[2469] Conventional mock test systems generate mock test questions based on past exam questions and analyze users' answers. However, they lacked personalized learning support, such as adjusting the difficulty level based on the user's emotional state and providing study advice. As a result, some users found the test questions to be overly difficult, while others found them too easy, preventing effective learning. Furthermore, the system provided limited intuitive support and feedback for answers, preventing users from maximizing their learning effectiveness. A system that can solve these issues and provide a more personalized learning experience is needed.

[2470] 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.

[2471] In this invention, the server includes means for receiving and analyzing past exam question data as input, means for generating mock exam questions from the analyzed data, means for receiving and analyzing the user's answers, means for identifying weak areas based on the analyzed user's answers, means for generating next mock exam questions reflecting the identified weak areas, means for the user to input questions, means for generating answers to the questions, means for recognizing the user's emotional state, means for adjusting the difficulty of mock exam questions based on the recognized emotional state, and means for generating study advice according to the emotional state, thereby enabling personalized study support according to the user's emotional state and learning progress.

[2472] "Past exam question data" refers to data that includes the content and format of questions in exams that have been administered in the past.

[2473] "Means of analysis" refers to algorithms or software that analyze input data and extract and organize meaningful information.

[2474] "Means for generating mock test questions" refers to processes and systems for creating new mock test questions using algorithms based on past test question data.

[2475] "User's answer result" is data indicating the answer selected or written by the user to the mock test question.

[2476] The "means for receiving and analyzing answer results" refers to an algorithm or system that receives answer data submitted by users and analyzes whether the answers are correct or incorrect and the trends of each answer.

[2477] The "means for identifying weak areas" refers to an algorithm and system for analyzing the user's answers and identifying categories and patterns of questions with a low rate of correct answers.

[2478] "Means for user input of questions" are interfaces and devices that allow users to input questions about a particular problem.

[2479] "Means for generating answers" refers to processes or systems that generate answers using existing databases and AI models to provide appropriate answers to questions from users.

[2480] "Means for recognizing the user's emotional state" refers to an algorithm or system for assessing the user's mental and emotional state based on the user's behavioral data, answering tendencies, data from sensor devices, etc.

[2481] The "means for adjusting the difficulty of the mock test questions" refers to an algorithm and system for appropriately changing the difficulty of the mock test questions given in accordance with the user's emotional state and learning progress.

[2482] A "means for generating study advice" is an algorithm or system used to generate personalized study methods and encouraging messages based on the user's study situation and emotional state.

[2483] This invention is a system that automatically generates mock exam questions for qualification exams and provides users with an optimized learning experience. In particular, this system is equipped with an emotion engine that recognizes the user's emotional state and reflects this in adjusting the difficulty level of the mock exam and providing study advice, thereby achieving more advanced learning support.

[2484] System configuration

[2485] The system consists of three main components: a server, a terminal, and a user. The functions and specific operations of each component are explained below.

[2486] Enter past exam questions

[2487] 1. User: Upload past exam question collections to the system in PDF format. The user clicks the "Upload" button on the system interface and selects the PDF file from the file selection dialog.

[2488] 2. Terminal: Receives uploads from users and sends files to the server. The terminal sends files to the server via HTTP requests and displays a progress bar.

[2489] 3. Server: The received file is analyzed and the problem content is extracted as text data. Specifically, optical character recognition (OCR) software (e.g., Tesseract) is used to convert the PDF file into text data. Natural language processing (NLP) techniques are then used to identify problem formats and patterns. The analyzed data is then stored in a database (e.g., MySQL).

[2490] Mock test question generation

[2491] 1. Server: Learns question trends and formats based on a database of past questions. This is done using machine learning models (e.g., random forests, neural networks). Generates mock test question templates based on the learning results.

[2492] 2. Terminal: Notify the user that the generated practice test questions are ready, using a pop-up message or notification badge (e.g., "New practice test questions are available").

[2493] 3. User: Clicks the "Start" button to begin the mock test. The user clicks the "Start Test" button on the dashboard screen and moves to the test screen.

[2494] Mock test implementation and result analysis

[2495] 1. User: Enter the answer for each question and click the "Submit" button. The user selects or enters the answer for each question and clicks the "Submit" button after answering all questions.

[2496] 2. Terminal: Records the user's answers and sends them to the server. The answer data is sent to the server using an HTTP request.

[2497] 3. Server: Receives the answers and automatically scores them. The server compares the answers with the correct answer database and assigns a score. The server then analyzes the user's answering tendencies based on the analysis results and identifies weak areas.

[2498] 4. Server: Runs the emotion engine to recognize emotional states based on the analysis results, using data from emotion analysis APIs and sensor devices.

[2499] Utilizing the Emotion Engine

[2500] 1. Server: Adjust the difficulty of the mock test questions based on the user's perceived emotional state. Reset the difficulty parameters according to the user's emotional state (e.g., impatience, anxiety, relaxation).

[2501] 2. Server: Generates learning advice based on the user's emotional state. Natural language generation (NLG) technology is used to generate encouraging messages and advice on how to study.

[2502] 3. Terminal: The adjusted mock test questions and advice are presented to the user. The user then takes the advice into consideration and attempts a new mock test.

[2503] Implementing chat functionality

[2504] 1. User: Enter a question about a problem they don't understand. Open a chat window, enter a question, and click the send button.

[2505] 2. Terminal: Sends the question data to the server. Sends the question via HTTP request and displays a progress bar.

[2506] 3. Server: Analyzes the question and generates an appropriate answer from training data and FAQs. Answers are generated using natural language processing (NLP) technology and generative AI models (e.g., GPT-3).

[2507] 4. Terminal: Show the generated answer to the user. Show the answer in the chat window to help the user understand.

[2508] Specific examples

[2509] Enter past exam questions

[2510] User: "I'll upload the past three years' worth of exam questions in PDF format."

[2511] Terminal: "File received. Sending to server..."

[2512] Server: "Parsing file... Problem data extracted."

[2513] Mock test question generation

[2514] Server...

Claims

1. means for receiving and analyzing past exam question data as input; means for generating practice test questions from the analyzed data; a means for receiving and analyzing the user's answer results; A means for identifying weak areas based on the analyzed answers of the user; A means for generating questions for the next mock test that reflects the identified weak areas; a means for a user to input a question; means for generating an answer to said question; A system including:

2. 2. The system of claim 1, further comprising means for analyzing past exam question data to identify the format and pattern of each question and storing the identified format and pattern in a database.

3. 2. The system according to claim 1, further comprising means for automatically scoring the user's answers and calculating the score.

Images