system

Abstract

We provide the system. [Solution] A means of analyzing examination questions based on curriculum data and evaluating the comprehensiveness of the scope of the questions, A method for selecting questions from a question database and optimizing the overall difficulty level of the exam, A means of detecting duplicate new questions by referring to past exam questions, A means of detecting text plagiarism by comparing it with an external database, A means of proposing an appropriate question format according to the purpose of the examination, A system that includes this.

Description

Technical Field

[0001] The technology of this disclosure relates to a system.

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the process of creating test questions, it is required to ensure the comprehensiveness of educational courses, appropriately adjust the overall difficulty level, avoid duplication with past test questions, and prevent plagiarism. However, to meet such requirements, a great deal of time and effort are needed, which places a heavy burden on teachers. Also, it is difficult to select a flexible question format according to the purpose of the test. It is required to solve this problem and support the creation of high-quality and efficient test questions.

Means for Solving the Problems

[0005] This invention provides a system that includes means for analyzing examination questions based on curriculum data and evaluating the comprehensiveness of the scope of questions; means for selecting questions from a question database and optimizing the overall difficulty level of the examination; means for detecting duplication of new questions by referring to past examination questions; means for detecting plagiarism of text by comparing with an external database; and means for proposing an appropriate question format according to the purpose of the examination. This enables the efficient and reliable creation of examination questions and reduces the burden on educators.

[0006] "Curriculum data" refers to data that contains information about the learning content and learning objectives set for each subject within an educational institution.

[0007] "Exam questions" refer to questions or quizzes used to evaluate a learner's knowledge and understanding.

[0008] "Comprehensiveness" is a concept that refers to a state in which a particular range or field is covered without bias as a whole.

[0009] "Difficulty level" is a measure that indicates the degree of difficulty required to answer an exam question.

[0010] A "question database" refers to a collection of data that has been accumulated from past exam questions.

[0011] "Duplicate" refers to a situation where newly created exam questions and past exam questions contain identical or similar content.

[0012] "Plagiarism" refers to the act of using another person's copyrighted work or idea without permission.

[0013] "Question format" refers to the way questions are phrased and the method of answering them in an exam. [Brief explanation of the drawing]

[0014] [Figure 1]It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

MODE FOR CARRYING OUT THE INVENTION

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0017] In the following embodiments, a tagged processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a tagged RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a tagged storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] In the following embodiments, a tagged communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. 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), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention relates to a system for teachers in educational institutions to efficiently create high-quality examination questions. This system evaluates examination questions based on curriculum data, ensuring comprehensive coverage of the subject matter and adjusting the overall difficulty level. Furthermore, it checks for duplication by comparing current questions with past examination questions to prevent plagiarism. The system also enables the suggestion of optimal question formats tailored to the purpose of the examination.

[0036] The server first receives curriculum data and then analyzes the comprehensiveness of the exam questions based on that data. This prevents specific topics from being inappropriately emphasized. For example, it adjusts the math exam to ensure that each topic in algebra and geometry is covered evenly.

[0037] Next, the server analyzes past questions provided from the question database and adjusts the difficulty level of newly created test questions to be uniform. Through this process, the difficulty distribution across the entire exam is optimized. For example, it ensures that the questions are balanced from basic to advanced levels according to the students' abilities.

[0038] The terminal compares the created test questions with past test questions to detect duplicates. It also investigates whether the question text and materials match widely available information to check for potential plagiarism.

[0039] Ultimately, the server suggests the optimal question format for the purpose and target audience of the exam. For example, it might generate a set of questions that combine essay questions to test the depth of knowledge with multiple-choice questions to test the breadth of knowledge.

[0040] Users can review the exam questions suggested by the system and make modifications as needed. In this way, the present invention can reduce the burden on instructors and provide students with exams of fair and appropriate difficulty levels.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The user enters exam information into the terminal. They input the subject, the purpose of the exam, the student's level, etc., and determine the basic settings for the exam.

[0044] Step 2:

[0045] The server retrieves curriculum data. It obtains curriculum information for the subjects to be tested and sets the criteria for the scope of the questions.

[0046] Step 3:

[0047] The server analyzes the comprehensiveness of the exam questions. Based on curriculum data, it evaluates whether the exam questions cover all necessary topics.

[0048] Step 4:

[0049] The server analyzes the problem database. It determines the difficulty level of each problem from the existing problems and selects new problems to optimize the overall difficulty balance of the exam.

[0050] Step 5:

[0051] The terminal checks for duplication with past questions. It compares the generated test questions with past test question data to identify questions that may be duplicates.

[0052] Step 6:

[0053] The server performs plagiarism and copyright checks. It compares new exam questions with external resources to verify that they are not plagiarized from existing copyrighted works.

[0054] Step 7:

[0055] The server proposes the question format. It suggests the most suitable question format (essay, multiple-choice, application problems, etc.) to the user according to the purpose of the exam.

[0056] Step 8:

[0057] The user performs the final review and revisions. They review the proposed test questions and format, and complete the final test questions by making any necessary corrections on their device.

[0058] (Example 1)

[0059] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0060] In modern education, the process of teachers creating exam questions is time-consuming and labor-intensive, and there are challenges in appropriately adjusting comprehensiveness and difficulty level. Furthermore, issues such as duplication with past questions and plagiarism contribute to a decline in the quality of education. Additionally, teachers are required to make judgments regarding the appropriate question format according to the purpose of the exam, which is a difficult task for many.

[0061] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0062] In this invention, the server includes a device that analyzes exam questions based on curriculum information and evaluates the comprehensiveness of the scope of the questions; a device that selects questions from a question database and optimizes the overall difficulty level of the exam; and a device that refers to past exam questions and detects duplication of new questions. This enables the effective creation and management of exam questions.

[0063] "Curriculum information" refers to data that outlines the plans and objectives of learning instruction at educational institutions, and includes detailed curriculum content for specific subjects or fields.

[0064] A "question database" is a collection of past exam questions, and is an information resource that stores related information such as the question text, answers, difficulty level, and the date the questions were asked.

[0065] A "learning model" is the structure of an algorithm trained using machine learning techniques with data, and it has the ability to make predictions and classifications based on new information.

[0066] "Question format" refers to the method of presenting questions used in exams and tests, and includes formats such as multiple-choice, written response, and fill-in-the-blank.

[0067] A "generative algorithm" is a mathematical or programmatic procedure for creating new output (in this case, exam questions) based on input data.

[0068] This invention provides a system for teachers in educational institutions to efficiently create high-quality examination questions. The following describes a specific form for implementing this system.

[0069] The server receives curriculum information and analyzes the comprehensiveness of the exam questions based on that data. Specific software used for this analysis includes data analysis tools (e.g., Python's pandas library). This analysis makes it possible to prevent specific topics from being overly or inappropriately covered. For example, in a mathematics exam, it verifies and adjusts to ensure that each topic in algebra and geometry is covered evenly.

[0070] Furthermore, the server references a database of past exam questions to optimize the difficulty level of newly created exam questions. Machine learning models (e.g., scikit-learn) are used to adjust the difficulty level. Specifically, they evaluate the difficulty of the questions and select questions appropriate to the students' learning levels.

[0071] The terminal is responsible for comparing newly created test questions with past questions and detecting similarities. A text matching tool (e.g., difflib) is used for text comparison. Furthermore, the terminal uses a cloud-based search tool to compare the questions with external sources and check for potential plagiarism.

[0072] Ultimately, the server proposes the optimal question format tailored to the purpose of the exam. This process utilizes a generative AI model. For example, it can propose a format that combines descriptive questions testing the depth of knowledge with multiple-choice questions testing the breadth of knowledge.

[0073] Users can review the set of test questions generated through these processes and make revisions as needed. By reviewing the questions via the GUI and inputting feedback into the system, the final test set is completed.

[0074] Examples of prompts to input into a generative AI model:

[0075] "Create a set of questions that cover all the necessary algebraic and geometric topics for a mathematics exam, adjusting the difficulty level to suit the students' abilities. Ensure there is no overlap with past questions, and propose a combination of written and multiple-choice questions."

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The server receives and analyzes curriculum information from educational institutions. The input is curriculum data, which is used to perform analysis to verify the comprehensiveness of the exam scope. Specifically, the server uses a data analysis tool to calculate the frequency of occurrence of each topic and generates a graph to visually display this information. This allows for verification of whether any particular topic is being covered excessively. The output is a report of the analysis results.

[0079] Step 2:

[0080] The server references a question database containing past exam questions. It uses past exam questions retrieved from the database as input. The server applies a machine learning model to predict the difficulty level of newly created questions and adjusts the overall difficulty level of the exam uniformly. Specifically, it performs classification and clustering using the machine learning model to balance the difficulty levels. The output provides a list of the adjusted difficulty distributions.

[0081] Step 3:

[0082] The terminal compares newly created test questions with past question data. The input consists of data for both the new questions and past questions. The terminal uses a text comparison algorithm to evaluate similarity and determine if there are duplicates. Specifically, it generates similarity scores for the past and new questions, highlights questions with high scores, and notifies the user. The output is a list of similarity judgments.

[0083] Step 4:

[0084] The terminal cross-references questions with external sources to prevent plagiarism. New question data is used as input. Cloud search tools are utilized to compare the question text with widely available literature and information. Specifically, the system searches for the question text, measures the degree of similarity, and compiles the results into a report. The output provides a plagiarism risk assessment report.

[0085] Step 5:

[0086] The server proposes the optimal question format based on the purpose and target audience of the exam. It uses analyzed exam question data and exam purpose information as input. A generative AI model is used to generate the optimal structure of the exam questions. Specifically, it automatically generates suggestions combining multiple formats, such as written and multiple-choice questions. The output is a set of recommended exam formats.

[0087] Step 6:

[0088] The user reviews the generated set of exam questions and makes corrections as needed. The system provides a set of exam questions as input. The user reviews the questions using a GUI and edits, deletes, and adds questions through an intuitive interface. Specific actions include changing the order of questions via drag-and-drop and adding comments. The output is the final, corrected set of exam questions.

[0089] (Application Example 1)

[0090] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0091] This invention aims to solve the problem of the need for a system in educational institutions and homes to efficiently create and evaluate the quality of examination questions according to the progress of individual learners. In conventional examination question creation, teachers and educators currently spend a great deal of time and effort ensuring comprehensiveness, difficulty level, and preventing duplication and plagiarism. Furthermore, it is difficult to provide appropriate examinations for each learner, sometimes resulting in unfair evaluation. Therefore, there is a need for new technologies in educational environments that enable efficient preparation of examination questions and fair and appropriate evaluation.

[0092] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0093] In this invention, the server includes means for analyzing exam questions based on curriculum data and evaluating the comprehensiveness of the scope of questions; means for selecting questions from a set of question data and optimizing the overall difficulty level of the evaluation; and means for referring to past exam questions and detecting duplication of new questions. This enables the efficient construction of exam questions tailored to individual learners, and allows for fair and high-quality evaluation.

[0094] "Curriculum data" refers to a collection of information that systematically organizes the topics and content that students should learn, based on a specific educational program or curriculum guideline.

[0095] An "exam question" is a series of questions or tasks created for the purpose of evaluating a learner's knowledge and understanding.

[0096] "Means for evaluating comprehensiveness" refer to methods and systems for verifying and evaluating whether the examination questions adequately include all the topics and important items that should be covered.

[0097] A "question data set" is a collection of questions gathered from past exams and educational resources.

[0098] "Methods for optimizing difficulty level" refer to methods of adjusting and standardizing the difficulty level of exam questions in order to provide learners with an appropriate challenge throughout the entire exam.

[0099] "Means for detecting duplication" refers to methods for verifying whether newly created test questions are identical or similar to questions that have existed in the past.

[0100] "External information sets" refer to all information resources that exist externally, such as books, websites, and learning materials.

[0101] "Means of detecting plagiarism in documents" refers to methods for verifying whether exam questions are inappropriately quoted or copied from other content.

[0102] "Methods for proposing question formats" refer to methods of analyzing and proposing what type of questions should be asked, depending on the purpose of the exam and the level of the learners.

[0103] "Learning progress" is an indicator that shows how far a learner has progressed towards a specific learning objective or curriculum.

[0104] "Individualized test questions" are questions that are customized according to each learner's learning progress and level of understanding.

[0105] "Means of providing evaluation feedback" refers to methods of providing learners with the results and evaluations of the tests they have taken, in order to guide their future learning.

[0106] Embodiments of this invention include a system for efficiently and accurately providing test questions to learners in educational institutions and home environments. A server receives curriculum data and analyzes the comprehensiveness of the test questions based on its content. This process utilizes data processing algorithms to evaluate whether each topic is covered adequately and without omission. This is particularly useful in achieving an even topic distribution in subjects such as mathematics and science.

[0107] Next, the server analyzes the selected questions from the question data set and optimizes the overall difficulty level of the exam. During this process, an AI algorithm is used to score the questions and adjust the difficulty level according to the students' learning progress. For example, questions are arranged so that the difficulty level gradually increases from the basics.

[0108] The server also runs a search algorithm to prevent duplication between past exam questions and newly created questions. This allows for a fresh and meaningful learning experience for students. Furthermore, the reliability of the exam is maintained by detecting the use of fraudulent documents by comparing them with external information sets.

[0109] The terminal presents the generated test questions to learners and provides real-time evaluation feedback. Teachers and administrators, as users, can input test information through this terminal and perform final checks and adjustments to the questions.

[0110] For example, language exams may generate personalized questions designed to reinforce specific grammatical points. For instance, correction questions such as "Transform the following sentence into the correct form" might be presented in real time.

[0111] Examples of prompt statements for a generative AI model are as follows:

[0112] "Please generate intermediate-level exam questions on solving quadratic equations. Please include detailed information about the knowledge required to answer them."

[0113] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0114] Step 1:

[0115] The server receives curriculum data and analyzes it. It takes learning topic information and related data as input and generates comprehensiveness assessment results as output. Specifically, it evaluates whether each topic is adequately covered based on a data processing algorithm.

[0116] Step 2:

[0117] The server selects exam questions by referring to a set of question data. It receives historically accumulated question sets and current curriculum data as input, and generates a list of selected questions as output. Specifically, it uses an AI algorithm to calculate difficulty scores and ensure that the exam questions are placed at appropriate levels.

[0118] Step 3:

[0119] The server compares past exam questions to detect duplicates in new exam questions. It takes newly generated exam questions and past exam data as input and generates a report indicating whether or not there are duplicates as output. Specifically, it executes a search algorithm to compare the similarity of the question texts.

[0120] Step 4:

[0121] The server compares new exam questions with external information sets to check for plagiarism. Inputs include new exam questions and external information such as online databases. Outputs provide analysis results indicating whether or not plagiarism has occurred. Specifically, it performs document similarity analysis using natural language processing techniques.

[0122] Step 5:

[0123] The terminal presents the generated test questions and feedback to the target learner. The user reviews the questions and makes corrections and final checks to the test information through the terminal. The input is the generated test questions and learner information, and the output is the presentation of the test to the learner and the feedback results. Specific operations include displaying results through the user interface.

[0124] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0125] This invention provides a system for teachers in educational institutions to create efficient and high-quality examination questions, and incorporates an emotion engine that recognizes user emotions. This system analyzes examination questions based on curriculum data to ensure comprehensive coverage of the subject matter. It also selects questions from a question database to optimize the overall difficulty level of the examination. Furthermore, it guarantees quality by checking for duplication by comparing with past examination questions and evaluating the risk of plagiarism through comparison with external materials.

[0126] The server suggests the optimal question format that best suits the purpose of the exam. In addition, an emotion engine recognizes the user's emotional state, analyzing the emotions the user exhibits while creating exam questions (e.g., stress or decreased concentration) and providing corresponding feedback. For example, if the emotion engine determines that the user is confused, the server will suggest simplifying the exam setup.

[0127] The terminal uses an emotion engine to monitor the user's state in real time based on the test information entered by the user. It provides an interface that allows the user to review and adjust the test questions and format as needed, reducing the complexity and potential for errors during the process.

[0128] The server completes the exam if it determines that the configured exam questions and format meet the final criteria. Furthermore, it uses user feedback detected by the emotion engine to improve the future exam question creation process.

[0129] As a concrete example, in the creation of mathematics exam questions, when a user encounters a difficult problem, the emotion engine detects the user's stress level, and the server provides hints for the problem or suggests adjusting the difficulty level accordingly. In this way, the present invention reduces the burden on educators and enables smooth and effective creation of exam questions.

[0130] The following describes the processing flow.

[0131] Step 1:

[0132] The user enters exam information into the terminal. This includes basic exam information such as the subject, purpose, and student level.

[0133] Step 2:

[0134] The server retrieves the curriculum data and begins analysis. Based on the curriculum, it evaluates whether the exam questions cover all the necessary topics.

[0135] Step 3:

[0136] The emotion engine analyzes the user's emotional state in real time. It detects stress and fatigue based on the user's facial expressions and actions when they input test information.

[0137] Step 4:

[0138] The server analyzes the problem database and selects problems based on their difficulty level. It also considers data from the emotion engine and adjusts problem selection according to the user's state.

[0139] Step 5:

[0140] The terminal checks for duplication with past questions. It compares the generated questions with past exam question data to identify similar or duplicate questions.

[0141] Step 6:

[0142] The server checks for plagiarism by comparing the text with an external database. It verifies that the text of the exam questions does not match any existing copyrighted works.

[0143] Step 7:

[0144] The server suggests the optimal question format. It informs the user of the format that suits the purpose of the exam and adjusts the suggestion as needed.

[0145] Step 8:

[0146] The emotion engine receives user feedback and determines if adjustments are needed. If the user is feeling confused or stressed, it works with the server to simplify or assist them.

[0147] Step 9:

[0148] The user performs a final review. They check the proposed test questions and format on their device and make any necessary revisions. They then approve the completed test.

[0149] (Example 2)

[0150] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0151] When teachers at educational institutions create exam questions, they are required to construct questions efficiently and with high quality while maintaining a balance between comprehensiveness of the scope of the material and difficulty level. However, current methods have several problems, including duplication, lack of comprehensiveness, the risk of unauthorized use, and decreased work efficiency due to emotional stress on users. There is a need to provide a means to solve these problems simultaneously.

[0152] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0153] In this invention, the server includes means for analyzing problems based on educational program data and evaluating the comprehensiveness of the problem range, means for selecting problems from a problem aggregation device and optimizing the overall difficulty level of the problems, and means for analyzing the user's emotional state and making adjustments based on user feedback. This enables efficient creation of examination questions, improving the quality of education and reducing the workload of teachers.

[0154] "Educational program data" refers to data containing information about curricula and syllabi used in educational institutions, and is used for analyzing and evaluating the scope of exam questions.

[0155] A "problem collection device" is a database or information system that collects and stores examination questions, and is used to select appropriate questions.

[0156] "User's emotional state" refers to the psychological state and emotions of the user while creating the test questions, including changes in stress levels and concentration.

[0157] "Adjustments based on user feedback" refers to the process of reviewing and adapting the content and format of exam questions based on feedback information obtained through the emotion engine and user input.

[0158] This invention relates to an examination question creation system that supports teachers in educational institutions. It mainly consists of three components: a server, a terminal, and a user. Its embodiments are described below.

[0159] The server analyzes exam questions based on educational program data, verifying the comprehensiveness of the scope of the questions and verifying any overlap in questions. Furthermore, the server selects the most suitable questions from the question aggregation device and performs calculations to adjust the overall difficulty level. This process utilizes specific AI algorithms and an emotion engine, allowing for real-time adjustments based on the user's emotional state. Specifically, the hardware used includes a database server and an AI calculation server.

[0160] The terminal provides an interface for users to input test information. As users input test details and settings through the terminal, it transmits this information to a server and receives analysis and suggestions. This interface is designed for user-friendly visibility and includes software to monitor the user's emotional state based on input speed and facial expression analysis.

[0161] Users can leverage these systems that support the generation of exam questions to flexibly design teaching materials and question formats. In particular, by utilizing generative AI models, it becomes easier to generate appropriate combinations of questions from complex sets and find the optimal question format.

[0162] As a concrete example, when a user creates a math exam question, they input a prompt such as "Create an exam that covers the basics of differential and integral calculus" into the generation AI model. As a result, the server selects highly relevant questions from the question ensemble and provides a well-balanced exam overall. Furthermore, if the user is confused by a particular question, the emotion engine detects this situation, and the server offers supplementary hints or simplified solutions.

[0163] In this way, the present invention makes it possible to create high-quality, student-friendly examination questions while reducing the burden on educators.

[0164] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0165] Step 1:

[0166] The user enters exam information using a terminal. This information includes the subject matter, scope of the questions, and desired difficulty level. The terminal checks the format of this data, verifies its validity, and then sends it to the server. This process involves verifying the input data and converting its format, ensuring the output is in the appropriate format for the server.

[0167] Step 2:

[0168] The server uses the received input data to reference educational program data and evaluate the comprehensiveness of the exam questions. Specifically, it calculates the extent to which the input question range covers the entire curriculum. This analysis process involves comparative calculations based on program data. The output is evaluation data regarding comprehensiveness.

[0169] Step 3:

[0170] The server uses data from the question aggregation device to select questions in order to optimize the overall difficulty level of the exam. Questions are selected using an AI algorithm, and their difficulty levels are adjusted to ensure balance. The input is the question database and difficulty criteria, and the output is the selected set of questions.

[0171] Step 4:

[0172] The device utilizes an emotion engine to monitor the user's emotional state in real time. This uses the user's facial expression data and input pace. The emotional data is analyzed, and if the user is experiencing stress, this information is fed back to the server. The output is data related to the user's emotional state.

[0173] Step 5:

[0174] The server receives feedback from the emotion engine and provides appropriate support to the user. For example, if the server detects that the user is stressed, it may offer hints for the test questions or suggest adjusting the difficulty level. The input is emotional feedback and selected questions, and the output is a set of questions adjusted based on the feedback.

[0175] Step 6:

[0176] Users review the exam question suggestions from the server and make corrections and verifications using a terminal as needed. The final set of exam questions is determined. The terminal provides an interface for final verification, and the output is the final version of the exam that the user has reviewed.

[0177] (Application Example 2)

[0178] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0179] Creating examination questions in educational institutions is a significant burden for teachers, as it requires generating high-quality questions that cover the entire curriculum. Furthermore, providing effective support tailored to learners' emotions and levels of understanding is challenging in home learning support. Solutions are needed to improve the quality of examination questions and learning support while achieving a more efficient process.

[0180] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0181] This invention includes a server that includes means for analyzing test questions based on curriculum data and evaluating the comprehensiveness of the test scope, means for selecting questions from a question data set and optimizing the overall difficulty level of the test, means for recognizing the user's emotional state in real time using emotion analysis technology and providing appropriate feedback, and means for analyzing the learner's state in an automated home device and automatically providing appropriate support. This makes it possible to improve the quality of test question creation and learning support in educational settings and home learning, and to realize an efficient process.

[0182] "Curriculum data" refers to information that summarizes the educational content and learning points formulated by teachers.

[0183] "Examination questions" refer to questions given for the purpose of evaluating learning in educational institutions.

[0184] "Comprehensiveness of the exam scope" is a measure used to evaluate the extent to which the exam questions cover the entire curriculum.

[0185] A "problem data collection" refers to a collection of information that contains a number of questions that could potentially be used as exam questions.

[0186] "Emotion analysis technology" refers to technology that identifies and analyzes emotions from a user's facial expressions and voice.

[0187] "User emotional state" refers to the internal state that indicates a user's emotional response.

[0188] "Appropriate feedback" refers to helpful information and advice provided according to the user's situation and needs.

[0189] "Household automated appliances" refer to automated devices used on a daily basis within the home.

[0190] "The learner's state" refers to the overall condition of an individual during learning, including their level of understanding, concentration, and emotions.

[0191] "Automatically providing assistance" refers to the act of a machine or system intervening to provide help when certain conditions are met.

[0192] This invention is an integrated system for efficiently creating test questions and providing learning support for educational institutions and homes. At the core of the system are means for analyzing curriculum data and optimizing test questions, and means for evaluating the user's emotional state in real time using emotion analysis technology and providing appropriate feedback.

[0193] The server evaluates the comprehensiveness of the exam scope based on curriculum data when creating exam questions. This automatically generates a set of questions that cover the entire curriculum. It also has a function to select the most suitable questions from the question data set and adjust the overall difficulty level of the exam.

[0194] The terminal provides an interface for the user to input test information, and based on this, sentiment analysis technology is applied to monitor the user's emotional state. The sentiment analysis technology used here utilizes a common sentiment recognition API (e.g., Microsoft® Azure® service) to analyze the user's facial expressions and voice.

[0195] As users create or study test questions, the system collects emotional data in real time and evaluates it using a generative AI model. For example, if the system determines that a user is under high stress, it will adjust the difficulty level of the test questions or automatically provide hints.

[0196] For example, if a user is trying to create a math test question but looks confused, the system will suggest, "This question seems a little difficult. Do you need a hint?" and provide changes to the question format or hints as needed.

[0197] An example of a prompt from a generative AI model is: "If stress is detected from a child's facial expression and tone of voice, suggest what encouraging messages and hints you can offer for the math problem."

[0198] In this way, the present invention can realize examinations and learning support tailored to the needs of educators and learners.

[0199] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0200] Step 1:

[0201] The server receives curriculum data as input and evaluates the comprehensiveness of the exam scope. To do this, it uses a data analysis algorithm to scan the curriculum data, evaluate how well the exam question set covers the overall educational objectives, and outputs an exam scope score.

[0202] Step 2:

[0203] The server takes the question data set as input and optimizes the overall difficulty level of the exam. At this stage, the difficulty level of each question is evaluated by an AI algorithm, and the set of questions with the most appropriate combination of difficulty levels is output.

[0204] Step 3:

[0205] The terminal receives exam information from the user as input and makes that information available for display and modification on the interface. Through this interface, the user can perform final checks and adjustments to the exam questions.

[0206] Step 4:

[0207] The device acquires data from the user's facial expressions and voice as input and uses emotion analysis technology to evaluate the user's emotional state. Based on this analysis, it outputs a score indicating the user's emotional state.

[0208] Step 5:

[0209] The server receives the sentiment analysis results as input and uses a generative AI model to generate appropriate feedback. This feedback is output in a form that includes adjusting the difficulty of the test questions and providing encouraging messages, depending on the user's emotional state.

[0210] Step 6:

[0211] Users review feedback provided via their devices and adjust exam questions as needed. This enhances the user's exam creation process and provides better learning support.

[0212] Step 7:

[0213] A prompt message is automatically generated and recorded for future improvement. For example, it might output something like, "If stress is detected from the child's facial expression and tone of voice, please suggest what encouraging message and hints you can offer for the math problem."

[0214] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0215] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0216] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0217] [Second Embodiment]

[0218] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0219] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0220] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0221] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0222] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0223] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0224] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0225] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0226] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0227] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0228] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0229] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0230] This invention relates to a system for teachers in educational institutions to efficiently create high-quality examination questions. This system evaluates examination questions based on curriculum data, ensuring comprehensive coverage of the subject matter and adjusting the overall difficulty level. Furthermore, it checks for duplication by comparing current questions with past examination questions to prevent plagiarism. The system also enables the suggestion of optimal question formats tailored to the purpose of the examination.

[0231] The server first receives curriculum data and then analyzes the comprehensiveness of the exam questions based on that data. This prevents specific topics from being inappropriately emphasized. For example, it adjusts the math exam to ensure that each topic in algebra and geometry is covered evenly.

[0232] Next, the server analyzes past questions provided from the question database and adjusts the difficulty level of newly created test questions to be uniform. Through this process, the difficulty distribution across the entire exam is optimized. For example, it ensures that the questions are balanced from basic to advanced levels according to the students' abilities.

[0233] The terminal compares the created test questions with past test questions to detect duplicates. It also investigates whether the question text and materials match widely available information to check for potential plagiarism.

[0234] Ultimately, the server suggests the optimal question format for the purpose and target audience of the exam. For example, it might generate a set of questions that combine essay questions to test the depth of knowledge with multiple-choice questions to test the breadth of knowledge.

[0235] Users can review the exam questions suggested by the system and make modifications as needed. In this way, the present invention can reduce the burden on instructors and provide students with exams of fair and appropriate difficulty levels.

[0236] The following describes the processing flow.

[0237] Step 1:

[0238] The user enters exam information into the terminal. They input the subject, the purpose of the exam, the student's level, etc., and determine the basic settings for the exam.

[0239] Step 2:

[0240] The server retrieves curriculum data. It obtains curriculum information for the subjects to be tested and sets the criteria for the scope of the questions.

[0241] Step 3:

[0242] The server analyzes the comprehensiveness of the exam questions. Based on curriculum data, it evaluates whether the exam questions cover all necessary topics.

[0243] Step 4:

[0244] The server analyzes the problem database. It determines the difficulty level of each problem from the existing problems and selects new problems to optimize the overall difficulty balance of the exam.

[0245] Step 5:

[0246] The terminal checks for duplication with past questions. It compares the generated test questions with past test question data to identify questions that may be duplicates.

[0247] Step 6:

[0248] The server performs plagiarism and copyright checks. It compares new exam questions with external resources to verify that they are not plagiarized from existing copyrighted works.

[0249] Step 7:

[0250] The server proposes the question format. It suggests the most suitable question format (essay, multiple-choice, application problems, etc.) to the user according to the purpose of the exam.

[0251] Step 8:

[0252] The user performs the final review and revisions. They review the proposed test questions and format, and complete the final test questions by making any necessary corrections on their device.

[0253] (Example 1)

[0254] Next, we will describe Example 1. 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."

[0255] In modern education, the process of teachers creating exam questions is time-consuming and labor-intensive, and there are challenges in appropriately adjusting comprehensiveness and difficulty level. Furthermore, issues such as duplication with past questions and plagiarism contribute to a decline in the quality of education. Additionally, teachers are required to make judgments regarding the appropriate question format according to the purpose of the exam, which is a difficult task for many.

[0256] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0257] In this invention, the server includes a device that analyzes exam questions based on curriculum information and evaluates the comprehensiveness of the scope of the questions; a device that selects questions from a question database and optimizes the overall difficulty level of the exam; and a device that refers to past exam questions and detects duplication of new questions. This enables the effective creation and management of exam questions.

[0258] "Curriculum information" refers to data that outlines the plans and objectives of learning instruction at educational institutions, and includes detailed curriculum content for specific subjects or fields.

[0259] A "question database" is a collection of past exam questions, and is an information resource that stores related information such as the question text, answers, difficulty level, and the date the questions were asked.

[0260] A "learning model" is the structure of an algorithm trained using machine learning techniques with data, and it has the ability to make predictions and classifications based on new information.

[0261] "Question format" refers to the method of presenting questions used in exams and tests, and includes formats such as multiple-choice, written response, and fill-in-the-blank.

[0262] A "generative algorithm" is a mathematical or programmatic procedure for creating new output (in this case, exam questions) based on input data.

[0263] This invention provides a system for teachers in educational institutions to efficiently create high-quality examination questions. The following describes a specific form for implementing this system.

[0264] The server receives curriculum information and analyzes the comprehensiveness of the exam questions based on that data. Specific software used for this analysis includes data analysis tools (e.g., Python's pandas library). This analysis makes it possible to prevent specific topics from being overly or inappropriately covered. For example, in a mathematics exam, it verifies and adjusts to ensure that each topic in algebra and geometry is covered evenly.

[0265] Furthermore, the server references a database of past exam questions to optimize the difficulty level of newly created exam questions. Machine learning models (e.g., scikit-learn) are used to adjust the difficulty level. Specifically, they evaluate the difficulty of the questions and select questions appropriate to the students' learning levels.

[0266] The terminal is responsible for comparing newly created test questions with past questions and detecting similarities. A text matching tool (e.g., difflib) is used for text comparison. Furthermore, the terminal uses a cloud-based search tool to compare the questions with external sources and check for potential plagiarism.

[0267] Ultimately, the server proposes the optimal question format tailored to the purpose of the exam. This process utilizes a generative AI model. For example, it can propose a format that combines descriptive questions testing the depth of knowledge with multiple-choice questions testing the breadth of knowledge.

[0268] Users can review the set of test questions generated through these processes and make revisions as needed. By reviewing the questions via the GUI and inputting feedback into the system, the final test set is completed.

[0269] Examples of prompts to input into a generative AI model:

[0270] "Create a set of questions that cover all the necessary algebraic and geometric topics for a mathematics exam, adjusting the difficulty level to suit the students' abilities. Ensure there is no overlap with past questions, and propose a combination of written and multiple-choice questions."

[0271] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0272] Step 1:

[0273] The server receives and analyzes curriculum information from educational institutions. The input is curriculum data, which is used to perform analysis to verify the comprehensiveness of the exam scope. Specifically, the server uses a data analysis tool to calculate the frequency of occurrence of each topic and generates a graph to visually display this information. This allows for verification of whether any particular topic is being covered excessively. The output is a report of the analysis results.

[0274] Step 2:

[0275] The server references a question database containing past exam questions. It uses past exam questions retrieved from the database as input. The server applies a machine learning model to predict the difficulty level of newly created questions and adjusts the overall difficulty level of the exam uniformly. Specifically, it performs classification and clustering using the machine learning model to balance the difficulty levels. The output provides a list of the adjusted difficulty distributions.

[0276] Step 3:

[0277] The terminal collates newly created test questions with past question data. As input, the data of new questions and past questions are used. The terminal uses a text comparison algorithm to evaluate similarity and determine the presence of duplicates. As a specific operation, a similarity score for past questions and new questions is generated, and questions with high scores are highlighted and notified. As output, a similarity determination list is generated.

[0278] Step 4:

[0279] The terminal collates with an external information source to prevent question theft. As input, the data of new questions is used. Utilize a cloud search tool to compare the question text with widely circulated literature and information. As a specific operation, search for the question text and measure the degree of match, and summarize the results in a report. As output, a report on the possibility of theft is provided.

[0280] Step 5:

[0281] The server proposes an optimal question format according to the purpose and target of the test. As input, the analyzed test question data and test purpose information are used. Use a generative AI model to generate an optimal configuration of test questions. Specifically, automatically generate a proposal combining multiple formats such as descriptive and selective. As output, a set of recommended test formats is generated.

[0282] Step 6:

[0283] The user checks the generated set of test questions and makes corrections as necessary. As input, there is the set of test questions presented by the system. The user uses the GUI to check the questions and edits, deletes, and adds questions through an intuitive interface. As a specific operation, it is possible to change the order of questions by drag & drop and input comments. As output, a corrected final set of test questions is obtained.

[0284] (Application Example 1)

[0285] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0286] The present invention aims to solve the problem that there is a need for a system in educational institutions and homes to create efficient and high-quality test questions according to the progress of individual learners and evaluate their quality. In conventional test question creation, teachers and educators currently spend a lot of time and effort on the comprehensiveness, difficulty level, and prevention of duplication and plagiarism of test questions. Furthermore, it is difficult to provide an appropriate test for each learner, and fair evaluation may not be carried out. For this reason, in the educational environment, there is a need for a new technology that can efficiently prepare test questions and enable fair and appropriate evaluation.

[0287] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0288] In this invention, the server includes means for analyzing test questions based on educational curriculum data and evaluating the comprehensiveness of the question scope, means for selecting questions from the question data set and optimizing the overall difficulty level of the evaluation, and means for referring to past test questions and detecting duplicates of new questions. Thereby, it is possible to efficiently construct test questions according to individual learners and enable fair and high-quality evaluation.

[0289] "Educational curriculum data" is a collection of information that systematically summarizes the topics and content that students should learn based on a specific educational program or curriculum guidelines.

[0290] "Test questions" are a series of questions and tasks created for the purpose of evaluating learners' knowledge and understanding.

[0291] "Means for evaluating comprehensiveness" is a method or system for verifying and evaluating whether test questions appropriately include all topics and important items that should be covered.

[0292] A "question data set" is a collection of questions gathered from past exams and educational resources.

[0293] "Methods for optimizing difficulty level" refer to methods of adjusting and standardizing the difficulty level of exam questions in order to provide learners with an appropriate challenge throughout the entire exam.

[0294] "Means for detecting duplication" refers to methods for verifying whether newly created test questions are identical or similar to questions that have existed in the past.

[0295] "External information sets" refer to all information resources that exist externally, such as books, websites, and learning materials.

[0296] "Means of detecting plagiarism in documents" refers to methods for verifying whether exam questions are inappropriately quoted or copied from other content.

[0297] "Methods for proposing question formats" refer to methods of analyzing and proposing what type of questions should be asked, depending on the purpose of the exam and the level of the learners.

[0298] "Learning progress" is an indicator that shows how far a learner has progressed towards a specific learning objective or curriculum.

[0299] "Individualized test questions" are questions that are customized according to each learner's learning progress and level of understanding.

[0300] "Means of providing evaluation feedback" refers to methods of providing learners with the results and evaluations of the tests they have taken, in order to guide their future learning.

[0301] Embodiments of this invention include a system for efficiently and accurately providing test questions to learners in educational institutions and home environments. The server receives educational curriculum data and analyzes the comprehensiveness of test questions based on its content. In this process, data processing algorithms are utilized to evaluate whether each topic is covered without omission or redundancy. This is particularly useful for achieving an even distribution of topics in subjects such as mathematics and science.

[0302] Next, the server analyzes the questions selected from the question data set to optimize the difficulty level of the entire test. At this time, the AI algorithm is used to score the questions, and the difficulty level is adjusted according to the learning progress of the students. For example, the questions are arranged so that the difficulty level increases sequentially from the basics.

[0303] The server also executes a search algorithm to prevent duplication between past test questions and newly created questions. This enables the provision of a fresh and meaningful learning experience for students. Furthermore, by comparing with external information sets and detecting the use of unauthorized documents, the reliability of the test is maintained.

[0304] The terminal presents the generated test questions to the learner and provides real-time evaluation feedback. Teachers and administrators, who are users, can input test information via this terminal and perform final confirmation and adjustment of the questions.

[0305] As a specific example, individualized questions may be generated to reinforce specific grammar items in a language test. For example, proofreading questions such as "Please transform the following sentence into an appropriate form" are presented in real time.

[0306] Examples of prompt sentences for the generation AI model are as follows.

[0307] "Please generate intermediate-level test questions regarding the solution of quadratic equations. Also, output including the details of the knowledge required for the answers."

[0308] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0309] Step 1:

[0310] The server receives curriculum data and analyzes it. It takes learning topic information and related data as input and generates comprehensiveness assessment results as output. Specifically, it evaluates whether each topic is adequately covered based on a data processing algorithm.

[0311] Step 2:

[0312] The server selects exam questions by referring to a set of question data. It receives historically accumulated question sets and current curriculum data as input, and generates a list of selected questions as output. Specifically, it uses an AI algorithm to calculate difficulty scores and ensure that the exam questions are placed at appropriate levels.

[0313] Step 3:

[0314] The server compares past exam questions to detect duplicates in new exam questions. It takes newly generated exam questions and past exam data as input and generates a report indicating whether or not there are duplicates as output. Specifically, it executes a search algorithm to compare the similarity of the question texts.

[0315] Step 4:

[0316] The server compares new exam questions with external information sets to check for plagiarism. Inputs include new exam questions and external information such as online databases. Outputs provide analysis results indicating whether or not plagiarism has occurred. Specifically, it performs document similarity analysis using natural language processing techniques.

[0317] Step 5:

[0318] The terminal presents the generated test questions and feedback to the target learner. The user reviews the questions and makes corrections and final checks to the test information through the terminal. The input is the generated test questions and learner information, and the output is the presentation of the test to the learner and the feedback results. Specific operations include displaying results through the user interface.

[0319] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0320] This invention provides a system for teachers in educational institutions to create efficient and high-quality examination questions, and incorporates an emotion engine that recognizes user emotions. This system analyzes examination questions based on curriculum data to ensure comprehensive coverage of the subject matter. It also selects questions from a question database to optimize the overall difficulty level of the examination. Furthermore, it guarantees quality by checking for duplication by comparing with past examination questions and evaluating the risk of plagiarism through comparison with external materials.

[0321] The server suggests the optimal question format that best suits the purpose of the exam. In addition, an emotion engine recognizes the user's emotional state, analyzing the emotions the user exhibits while creating exam questions (e.g., stress or decreased concentration) and providing corresponding feedback. For example, if the emotion engine determines that the user is confused, the server will suggest simplifying the exam setup.

[0322] The terminal uses an emotion engine to monitor the user's state in real time based on the test information entered by the user. It provides an interface that allows the user to review and adjust the test questions and format as needed, reducing the complexity and potential for errors during the process.

[0323] The server completes the exam if it determines that the configured exam questions and format meet the final criteria. Furthermore, it uses user feedback detected by the emotion engine to improve the future exam question creation process.

[0324] As a concrete example, in the creation of mathematics exam questions, when a user encounters a difficult problem, the emotion engine detects the user's stress level, and the server provides hints for the problem or suggests adjusting the difficulty level accordingly. In this way, the present invention reduces the burden on educators and enables smooth and effective creation of exam questions.

[0325] The following describes the processing flow.

[0326] Step 1:

[0327] The user enters exam information into the terminal. This includes basic exam information such as the subject, purpose, and student level.

[0328] Step 2:

[0329] The server retrieves the curriculum data and begins analysis. Based on the curriculum, it evaluates whether the exam questions cover all the necessary topics.

[0330] Step 3:

[0331] The emotion engine analyzes the user's emotional state in real time. It detects stress and fatigue based on the user's facial expressions and actions when they input test information.

[0332] Step 4:

[0333] The server analyzes the problem database and selects problems based on their difficulty level. It also considers data from the emotion engine and adjusts problem selection according to the user's state.

[0334] Step 5:

[0335] The terminal checks for duplication with past questions. It compares the generated questions with past exam question data to identify similar or duplicate questions.

[0336] Step 6:

[0337] The server checks for plagiarism by comparing the text with an external database. It verifies that the text of the exam questions does not match any existing copyrighted works.

[0338] Step 7:

[0339] The server suggests the optimal question format. It informs the user of the format that suits the purpose of the exam and adjusts the suggestion as needed.

[0340] Step 8:

[0341] The emotion engine receives user feedback and determines if adjustments are needed. If the user is feeling confused or stressed, it works with the server to simplify or assist them.

[0342] Step 9:

[0343] The user performs a final review. They check the proposed test questions and format on their device and make any necessary revisions. They then approve the completed test.

[0344] (Example 2)

[0345] Next, we will describe Example 2. 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".

[0346] When teachers at educational institutions create exam questions, they are required to construct questions efficiently and with high quality while maintaining a balance between comprehensiveness of the scope of the material and difficulty level. However, current methods have several problems, including duplication, lack of comprehensiveness, the risk of unauthorized use, and decreased work efficiency due to emotional stress on users. There is a need to provide a means to solve these problems simultaneously.

[0347] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0348] In this invention, the server includes means for analyzing problems based on educational program data and evaluating the comprehensiveness of the problem range, means for selecting problems from a problem aggregation device and optimizing the overall difficulty level of the problems, and means for analyzing the user's emotional state and making adjustments based on user feedback. This enables efficient creation of examination questions, improving the quality of education and reducing the workload of teachers.

[0349] "Educational program data" refers to data containing information about curricula and syllabi used in educational institutions, and is used for analyzing and evaluating the scope of exam questions.

[0350] A "problem collection device" is a database or information system that collects and stores examination questions, and is used to select appropriate questions.

[0351] "User's emotional state" refers to the psychological state and emotions of the user while creating the test questions, including changes in stress levels and concentration.

[0352] "Adjustments based on user feedback" refers to the process of reviewing and adapting the content and format of exam questions based on feedback information obtained through the emotion engine and user input.

[0353] This invention relates to an examination question creation system that supports teachers in educational institutions. It mainly consists of three components: a server, a terminal, and a user. Its embodiments are described below.

[0354] The server analyzes exam questions based on educational program data, verifying the comprehensiveness of the scope of the questions and verifying any overlap in questions. Furthermore, the server selects the most suitable questions from the question aggregation device and performs calculations to adjust the overall difficulty level. This process utilizes specific AI algorithms and an emotion engine, allowing for real-time adjustments based on the user's emotional state. Specifically, the hardware used includes a database server and an AI calculation server.

[0355] The terminal provides an interface for users to input test information. As users input test details and settings through the terminal, it transmits this information to a server and receives analysis and suggestions. This interface is designed for user-friendly visibility and includes software to monitor the user's emotional state based on input speed and facial expression analysis.

[0356] Users can leverage these systems that support the generation of exam questions to flexibly design teaching materials and question formats. In particular, by utilizing generative AI models, it becomes easier to generate appropriate combinations of questions from complex sets and find the optimal question format.

[0357] As a concrete example, when a user creates a math exam question, they input a prompt such as "Create an exam that covers the basics of differential and integral calculus" into the generation AI model. As a result, the server selects highly relevant questions from the question ensemble and provides a well-balanced exam overall. Furthermore, if the user is confused by a particular question, the emotion engine detects this situation, and the server offers supplementary hints or simplified solutions.

[0358] In this way, the present invention makes it possible to create high-quality, student-friendly examination questions while reducing the burden on educators.

[0359] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0360] Step 1:

[0361] The user enters exam information using a terminal. This information includes the subject matter, scope of the questions, and desired difficulty level. The terminal checks the format of this data, verifies its validity, and then sends it to the server. This process involves verifying the input data and converting its format, ensuring the output is in the appropriate format for the server.

[0362] Step 2:

[0363] The server uses the received input data to reference educational program data and evaluate the comprehensiveness of the exam questions. Specifically, it calculates the extent to which the input question range covers the entire curriculum. This analysis process involves comparative calculations based on program data. The output is evaluation data regarding comprehensiveness.

[0364] Step 3:

[0365] The server uses data from the question aggregation device to select questions in order to optimize the overall difficulty level of the exam. Questions are selected using an AI algorithm, and their difficulty levels are adjusted to ensure balance. The input is the question database and difficulty criteria, and the output is the selected set of questions.

[0366] Step 4:

[0367] The device utilizes an emotion engine to monitor the user's emotional state in real time. This uses the user's facial expression data and input pace. The emotional data is analyzed, and if the user is experiencing stress, this information is fed back to the server. The output is data related to the user's emotional state.

[0368] Step 5:

[0369] The server receives feedback from the emotion engine and provides appropriate support to the user. For example, if the server detects that the user is stressed, it may offer hints for the test questions or suggest adjusting the difficulty level. The input is emotional feedback and selected questions, and the output is a set of questions adjusted based on the feedback.

[0370] Step 6:

[0371] Users review the exam question suggestions from the server and make corrections and verifications using a terminal as needed. The final set of exam questions is determined. The terminal provides an interface for final verification, and the output is the final version of the exam that the user has reviewed.

[0372] (Application Example 2)

[0373] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0374] Creating examination questions in educational institutions is a significant burden for teachers, as it requires generating high-quality questions that cover the entire curriculum. Furthermore, providing effective support tailored to learners' emotions and levels of understanding is challenging in home learning support. Solutions are needed to improve the quality of examination questions and learning support while achieving a more efficient process.

[0375] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0376] This invention includes a server that includes means for analyzing test questions based on curriculum data and evaluating the comprehensiveness of the test scope, means for selecting questions from a question data set and optimizing the overall difficulty level of the test, means for recognizing the user's emotional state in real time using emotion analysis technology and providing appropriate feedback, and means for analyzing the learner's state in an automated home device and automatically providing appropriate support. This makes it possible to improve the quality of test question creation and learning support in educational settings and home learning, and to realize an efficient process.

[0377] "Curriculum data" refers to information that summarizes the educational content and learning points formulated by teachers.

[0378] "Examination questions" refer to questions given for the purpose of evaluating learning in educational institutions.

[0379] "Comprehensiveness of the exam scope" is a measure used to evaluate the extent to which the exam questions cover the entire curriculum.

[0380] A "problem data collection" refers to a collection of information that contains a number of questions that could potentially be used as exam questions.

[0381] "Emotion analysis technology" refers to technology that identifies and analyzes emotions from a user's facial expressions and voice.

[0382] "User emotional state" refers to the internal state that indicates a user's emotional response.

[0383] "Appropriate feedback" refers to helpful information and advice provided according to the user's situation and needs.

[0384] "Household automated appliances" refer to automated devices used on a daily basis within the home.

[0385] "The learner's state" refers to the overall condition of an individual during learning, including their level of understanding, concentration, and emotions.

[0386] "Automatically providing assistance" refers to the act of a machine or system intervening to provide help when certain conditions are met.

[0387] This invention is an integrated system for efficiently creating test questions and providing learning support for educational institutions and homes. At the core of the system are means for analyzing curriculum data and optimizing test questions, and means for evaluating the user's emotional state in real time using emotion analysis technology and providing appropriate feedback.

[0388] The server evaluates the comprehensiveness of the exam scope based on curriculum data when creating exam questions. This automatically generates a set of questions that cover the entire curriculum. It also has a function to select the most suitable questions from the question data set and adjust the overall difficulty level of the exam.

[0389] The terminal provides an interface for the user to input test information, and based on this, sentiment analysis technology is applied to monitor the user's emotional state. The sentiment analysis technology used here utilizes a common sentiment recognition API (e.g., a Microsoft Azure service) to analyze the user's facial expressions and voice.

[0390] As users create or study test questions, the system collects emotional data in real time and evaluates it using a generative AI model. For example, if the system determines that a user is under high stress, it will adjust the difficulty level of the test questions or automatically provide hints.

[0391] For example, if a user is trying to create a math test question but looks confused, the system will suggest, "This question seems a little difficult. Do you need a hint?" and provide changes to the question format or hints as needed.

[0392] An example of a prompt from a generative AI model is: "If stress is detected from a child's facial expression and tone of voice, suggest what encouraging messages and hints you can offer for the math problem."

[0393] In this way, the present invention can realize examinations and learning support tailored to the needs of educators and learners.

[0394] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0395] Step 1:

[0396] The server receives curriculum data as input and evaluates the comprehensiveness of the exam scope. To do this, it uses a data analysis algorithm to scan the curriculum data, evaluate how well the exam question set covers the overall educational objectives, and outputs an exam scope score.

[0397] Step 2:

[0398] The server takes the question data set as input and optimizes the overall difficulty level of the exam. At this stage, the difficulty level of each question is evaluated by an AI algorithm, and the set of questions with the most appropriate combination of difficulty levels is output.

[0399] Step 3:

[0400] The terminal receives exam information from the user as input and makes that information available for display and modification on the interface. Through this interface, the user can perform final checks and adjustments to the exam questions.

[0401] Step 4:

[0402] The device acquires data from the user's facial expressions and voice as input and uses emotion analysis technology to evaluate the user's emotional state. Based on this analysis, it outputs a score indicating the user's emotional state.

[0403] Step 5:

[0404] The server receives the sentiment analysis results as input and uses a generative AI model to generate appropriate feedback. This feedback is output in a form that includes adjusting the difficulty of the test questions and providing encouraging messages, depending on the user's emotional state.

[0405] Step 6:

[0406] Users review feedback provided via their devices and adjust exam questions as needed. This enhances the user's exam creation process and provides better learning support.

[0407] Step 7:

[0408] A prompt message is automatically generated and recorded for future improvement. For example, it might output something like, "If stress is detected from the child's facial expression and tone of voice, please suggest what encouraging message and hints you can offer for the math problem."

[0409] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0410] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0411] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0412] [Third Embodiment]

[0413] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0414] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0415] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0416] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0417] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0418] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0419] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0420] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0421] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0422] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0423] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0424] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0425] This invention relates to a system for teachers in educational institutions to efficiently create high-quality examination questions. This system evaluates examination questions based on curriculum data, ensuring comprehensive coverage of the subject matter and adjusting the overall difficulty level. Furthermore, it checks for duplication by comparing current questions with past examination questions to prevent plagiarism. The system also enables the suggestion of optimal question formats tailored to the purpose of the examination.

[0426] The server first receives curriculum data and then analyzes the comprehensiveness of the exam questions based on that data. This prevents specific topics from being inappropriately emphasized. For example, it adjusts the math exam to ensure that each topic in algebra and geometry is covered evenly.

[0427] Next, the server analyzes past questions provided from the question database and adjusts the difficulty level of newly created test questions to be uniform. Through this process, the difficulty distribution across the entire exam is optimized. For example, it ensures that the questions are balanced from basic to advanced levels according to the students' abilities.

[0428] The terminal compares the created test questions with past test questions to detect duplicates. It also investigates whether the question text and materials match widely available information to check for potential plagiarism.

[0429] Ultimately, the server suggests the optimal question format for the purpose and target audience of the exam. For example, it might generate a set of questions that combine essay questions to test the depth of knowledge with multiple-choice questions to test the breadth of knowledge.

[0430] Users can review the exam questions suggested by the system and make modifications as needed. In this way, the present invention can reduce the burden on instructors and provide students with exams of fair and appropriate difficulty levels.

[0431] The following describes the processing flow.

[0432] Step 1:

[0433] The user enters exam information into the terminal. They input the subject, the purpose of the exam, the student's level, etc., and determine the basic settings for the exam.

[0434] Step 2:

[0435] The server retrieves curriculum data. It obtains curriculum information for the subjects to be tested and sets the criteria for the scope of the questions.

[0436] Step 3:

[0437] The server analyzes the comprehensiveness of the exam questions. Based on curriculum data, it evaluates whether the exam questions cover all necessary topics.

[0438] Step 4:

[0439] The server analyzes the problem database. It determines the difficulty level of each problem from the existing problems and selects new problems to optimize the overall difficulty balance of the exam.

[0440] Step 5:

[0441] The terminal checks for duplication with past questions. It compares the generated test questions with past test question data to identify questions that may be duplicates.

[0442] Step 6:

[0443] The server performs plagiarism and copyright checks. It compares new exam questions with external resources to verify that they are not plagiarized from existing copyrighted works.

[0444] Step 7:

[0445] The server proposes the question format. It suggests the most suitable question format (essay, multiple-choice, application problems, etc.) to the user according to the purpose of the exam.

[0446] Step 8:

[0447] The user performs the final review and revisions. They review the proposed test questions and format, and complete the final test questions by making any necessary corrections on their device.

[0448] (Example 1)

[0449] Next, we will describe Example 1. 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."

[0450] In modern education, the process of teachers creating exam questions is time-consuming and labor-intensive, and there are challenges in appropriately adjusting comprehensiveness and difficulty level. Furthermore, issues such as duplication with past questions and plagiarism contribute to a decline in the quality of education. Additionally, teachers are required to make judgments regarding the appropriate question format according to the purpose of the exam, which is a difficult task for many.

[0451] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0452] In this invention, the server includes a device that analyzes exam questions based on curriculum information and evaluates the comprehensiveness of the scope of the questions; a device that selects questions from a question database and optimizes the overall difficulty level of the exam; and a device that refers to past exam questions and detects duplication of new questions. This enables the effective creation and management of exam questions.

[0453] "Curriculum information" refers to data that outlines the plans and objectives of learning instruction at educational institutions, and includes detailed curriculum content for specific subjects or fields.

[0454] A "question database" is a collection of past exam questions, and is an information resource that stores related information such as the question text, answers, difficulty level, and the date the questions were asked.

[0455] A "learning model" is the structure of an algorithm trained using machine learning techniques with data, and it has the ability to make predictions and classifications based on new information.

[0456] "Question format" refers to the method of presenting questions used in exams and tests, and includes formats such as multiple-choice, written response, and fill-in-the-blank.

[0457] A "generative algorithm" is a mathematical or programmatic procedure for creating new output (in this case, exam questions) based on input data.

[0458] This invention provides a system for teachers in educational institutions to efficiently create high-quality examination questions. The following describes a specific form for implementing this system.

[0459] The server receives curriculum information and analyzes the comprehensiveness of the exam questions based on that data. Specific software used for this analysis includes data analysis tools (e.g., Python's pandas library). This analysis makes it possible to prevent specific topics from being overly or inappropriately covered. For example, in a mathematics exam, it verifies and adjusts to ensure that each topic in algebra and geometry is covered evenly.

[0460] Furthermore, the server references a database of past exam questions to optimize the difficulty level of newly created exam questions. Machine learning models (e.g., scikit-learn) are used to adjust the difficulty level. Specifically, they evaluate the difficulty of the questions and select questions appropriate to the students' learning levels.

[0461] The terminal is responsible for comparing newly created test questions with past questions and detecting similarities. A text matching tool (e.g., difflib) is used for text comparison. Furthermore, the terminal uses a cloud-based search tool to compare the questions with external sources and check for potential plagiarism.

[0462] Ultimately, the server proposes the optimal question format tailored to the purpose of the exam. This process utilizes a generative AI model. For example, it can propose a format that combines descriptive questions testing the depth of knowledge with multiple-choice questions testing the breadth of knowledge.

[0463] Users can review the set of test questions generated through these processes and make revisions as needed. By reviewing the questions via the GUI and inputting feedback into the system, the final test set is completed.

[0464] Examples of prompts to input into a generative AI model:

[0465] "Create a set of questions that cover all the necessary algebraic and geometric topics for a mathematics exam, adjusting the difficulty level to suit the students' abilities. Ensure there is no overlap with past questions, and propose a combination of written and multiple-choice questions."

[0466] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0467] Step 1:

[0468] The server receives and analyzes curriculum information from educational institutions. The input is curriculum data, which is used to perform analysis to verify the comprehensiveness of the exam scope. Specifically, the server uses a data analysis tool to calculate the frequency of occurrence of each topic and generates a graph to visually display this information. This allows for verification of whether any particular topic is being covered excessively. The output is a report of the analysis results.

[0469] Step 2:

[0470] The server references a question database containing past exam questions. It uses past exam questions retrieved from the database as input. The server applies a machine learning model to predict the difficulty level of newly created questions and adjusts the overall difficulty level of the exam uniformly. Specifically, it performs classification and clustering using the machine learning model to balance the difficulty levels. The output provides a list of the adjusted difficulty distributions.

[0471] Step 3:

[0472] The terminal compares newly created test questions with past question data. The input consists of data for both the new questions and past questions. The terminal uses a text comparison algorithm to evaluate similarity and determine if there are duplicates. Specifically, it generates similarity scores for the past and new questions, highlights questions with high scores, and notifies the user. The output is a list of similarity judgments.

[0473] Step 4:

[0474] The terminal cross-references questions with external sources to prevent plagiarism. New question data is used as input. Cloud search tools are utilized to compare the question text with widely available literature and information. Specifically, the system searches for the question text, measures the degree of similarity, and compiles the results into a report. The output provides a plagiarism risk assessment report.

[0475] Step 5:

[0476] The server proposes the optimal question format based on the purpose and target audience of the exam. It uses analyzed exam question data and exam purpose information as input. A generative AI model is used to generate the optimal structure of the exam questions. Specifically, it automatically generates suggestions combining multiple formats, such as written and multiple-choice questions. The output is a set of recommended exam formats.

[0477] Step 6:

[0478] The user reviews the generated set of exam questions and makes corrections as needed. The system provides a set of exam questions as input. The user reviews the questions using a GUI and edits, deletes, and adds questions through an intuitive interface. Specific actions include changing the order of questions via drag-and-drop and adding comments. The output is the final, corrected set of exam questions.

[0479] (Application Example 1)

[0480] Next, we will explain Application Example 1. In the following explanation, 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."

[0481] This invention aims to solve the problem of the need for a system in educational institutions and homes to efficiently create and evaluate the quality of examination questions according to the progress of individual learners. In conventional examination question creation, teachers and educators currently spend a great deal of time and effort ensuring comprehensiveness, difficulty level, and preventing duplication and plagiarism. Furthermore, it is difficult to provide appropriate examinations for each learner, sometimes resulting in unfair evaluation. Therefore, there is a need for new technologies in educational environments that enable efficient preparation of examination questions and fair and appropriate evaluation.

[0482] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0483] In this invention, the server includes means for analyzing exam questions based on curriculum data and evaluating the comprehensiveness of the scope of questions; means for selecting questions from a set of question data and optimizing the overall difficulty level of the evaluation; and means for referring to past exam questions and detecting duplication of new questions. This enables the efficient construction of exam questions tailored to individual learners, and allows for fair and high-quality evaluation.

[0484] "Curriculum data" refers to a collection of information that systematically organizes the topics and content that students should learn, based on a specific educational program or curriculum guideline.

[0485] An "exam question" is a series of questions or tasks created for the purpose of evaluating a learner's knowledge and understanding.

[0486] "Means for evaluating comprehensiveness" refer to methods and systems for verifying and evaluating whether the examination questions adequately include all the topics and important items that should be covered.

[0487] A "question data set" is a collection of questions gathered from past exams and educational resources.

[0488] "Methods for optimizing difficulty level" refer to methods of adjusting and standardizing the difficulty level of exam questions in order to provide learners with an appropriate challenge throughout the entire exam.

[0489] "Means for detecting duplication" refers to methods for verifying whether newly created test questions are identical or similar to questions that have existed in the past.

[0490] "External information sets" refer to all information resources that exist externally, such as books, websites, and learning materials.

[0491] "Means of detecting plagiarism in documents" refers to methods for verifying whether exam questions are inappropriately quoted or copied from other content.

[0492] "Methods for proposing question formats" refer to methods of analyzing and proposing what type of questions should be asked, depending on the purpose of the exam and the level of the learners.

[0493] "Learning progress" is an indicator that shows how far a learner has progressed towards a specific learning objective or curriculum.

[0494] "Individualized test questions" are questions that are customized according to each learner's learning progress and level of understanding.

[0495] "Means of providing evaluation feedback" refers to methods of providing learners with the results and evaluations of the tests they have taken, in order to guide their future learning.

[0496] Embodiments of this invention include a system for efficiently and accurately providing test questions to learners in educational institutions and home environments. A server receives curriculum data and analyzes the comprehensiveness of the test questions based on its content. This process utilizes data processing algorithms to evaluate whether each topic is covered adequately and without omission. This is particularly useful in achieving an even topic distribution in subjects such as mathematics and science.

[0497] Next, the server analyzes the selected questions from the question data set and optimizes the overall difficulty level of the exam. During this process, an AI algorithm is used to score the questions and adjust the difficulty level according to the students' learning progress. For example, questions are arranged so that the difficulty level gradually increases from the basics.

[0498] The server also runs a search algorithm to prevent duplication between past exam questions and newly created questions. This allows for a fresh and meaningful learning experience for students. Furthermore, the reliability of the exam is maintained by detecting the use of fraudulent documents by comparing them with external information sets.

[0499] The terminal presents the generated test questions to learners and provides real-time evaluation feedback. Teachers and administrators, as users, can input test information through this terminal and perform final checks and adjustments to the questions.

[0500] For example, language exams may generate personalized questions designed to reinforce specific grammatical points. For instance, correction questions such as "Transform the following sentence into the correct form" might be presented in real time.

[0501] Examples of prompt statements for a generative AI model are as follows:

[0502] "Please generate intermediate-level exam questions on solving quadratic equations. Please include detailed information about the knowledge required to answer them."

[0503] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0504] Step 1:

[0505] The server receives curriculum data and analyzes it. It takes learning topic information and related data as input and generates comprehensiveness assessment results as output. Specifically, it evaluates whether each topic is adequately covered based on a data processing algorithm.

[0506] Step 2:

[0507] The server selects exam questions by referring to a set of question data. It receives historically accumulated question sets and current curriculum data as input, and generates a list of selected questions as output. Specifically, it uses an AI algorithm to calculate difficulty scores and ensure that the exam questions are placed at appropriate levels.

[0508] Step 3:

[0509] The server compares past exam questions to detect duplicates in new exam questions. It takes newly generated exam questions and past exam data as input and generates a report indicating whether or not there are duplicates as output. Specifically, it executes a search algorithm to compare the similarity of the question texts.

[0510] Step 4:

[0511] The server compares new exam questions with external information sets to check for plagiarism. Inputs include new exam questions and external information such as online databases. Outputs provide analysis results indicating whether or not plagiarism has occurred. Specifically, it performs document similarity analysis using natural language processing techniques.

[0512] Step 5:

[0513] The terminal presents the generated test questions and feedback to the target learner. The user reviews the questions and makes corrections and final checks to the test information through the terminal. The input is the generated test questions and learner information, and the output is the presentation of the test to the learner and the feedback results. Specific operations include displaying results through the user interface.

[0514] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0515] This invention provides a system for teachers in educational institutions to create efficient and high-quality examination questions, and incorporates an emotion engine that recognizes user emotions. This system analyzes examination questions based on curriculum data to ensure comprehensive coverage of the subject matter. It also selects questions from a question database to optimize the overall difficulty level of the examination. Furthermore, it guarantees quality by checking for duplication by comparing with past examination questions and evaluating the risk of plagiarism through comparison with external materials.

[0516] The server suggests the optimal question format that best suits the purpose of the exam. In addition, an emotion engine recognizes the user's emotional state, analyzing the emotions the user exhibits while creating exam questions (e.g., stress or decreased concentration) and providing corresponding feedback. For example, if the emotion engine determines that the user is confused, the server will suggest simplifying the exam setup.

[0517] The terminal uses an emotion engine to monitor the user's state in real time based on the test information entered by the user. It provides an interface that allows the user to review and adjust the test questions and format as needed, reducing the complexity and potential for errors during the process.

[0518] The server completes the exam if it determines that the configured exam questions and format meet the final criteria. Furthermore, it uses user feedback detected by the emotion engine to improve the future exam question creation process.

[0519] As a concrete example, in the creation of mathematics exam questions, when a user encounters a difficult problem, the emotion engine detects the user's stress level, and the server provides hints for the problem or suggests adjusting the difficulty level accordingly. In this way, the present invention reduces the burden on educators and enables smooth and effective creation of exam questions.

[0520] The following describes the processing flow.

[0521] Step 1:

[0522] The user enters exam information into the terminal. This includes basic exam information such as the subject, purpose, and student level.

[0523] Step 2:

[0524] The server retrieves the curriculum data and begins analysis. Based on the curriculum, it evaluates whether the exam questions cover all the necessary topics.

[0525] Step 3:

[0526] The emotion engine analyzes the user's emotional state in real time. It detects stress and fatigue based on the user's facial expressions and actions when they input test information.

[0527] Step 4:

[0528] The server analyzes the problem database and selects problems based on their difficulty level. It also considers data from the emotion engine and adjusts problem selection according to the user's state.

[0529] Step 5:

[0530] The terminal checks for duplication with past questions. It compares the generated questions with past exam question data to identify similar or duplicate questions.

[0531] Step 6:

[0532] The server checks for plagiarism by comparing the text with an external database. It verifies that the text of the exam questions does not match any existing copyrighted works.

[0533] Step 7:

[0534] The server suggests the optimal question format. It informs the user of the format that suits the purpose of the exam and adjusts the suggestion as needed.

[0535] Step 8:

[0536] The emotion engine receives user feedback and determines if adjustments are needed. If the user is feeling confused or stressed, it works with the server to simplify or assist them.

[0537] Step 9:

[0538] The user performs a final review. They check the proposed test questions and format on their device and make any necessary revisions. They then approve the completed test.

[0539] (Example 2)

[0540] Next, we will describe Example 2. 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."

[0541] When teachers at educational institutions create exam questions, they are required to construct questions efficiently and with high quality while maintaining a balance between comprehensiveness of the scope of the material and difficulty level. However, current methods have several problems, including duplication, lack of comprehensiveness, the risk of unauthorized use, and decreased work efficiency due to emotional stress on users. There is a need to provide a means to solve these problems simultaneously.

[0542] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0543] In this invention, the server includes means for analyzing problems based on educational program data and evaluating the comprehensiveness of the problem range, means for selecting problems from a problem aggregation device and optimizing the overall difficulty level of the problems, and means for analyzing the user's emotional state and making adjustments based on user feedback. This enables efficient creation of examination questions, improving the quality of education and reducing the workload of teachers.

[0544] "Educational program data" refers to data containing information about curricula and syllabi used in educational institutions, and is used for analyzing and evaluating the scope of exam questions.

[0545] A "problem collection device" is a database or information system that collects and stores examination questions, and is used to select appropriate questions.

[0546] "User's emotional state" refers to the psychological state and emotions of the user while creating the test questions, including changes in stress levels and concentration.

[0547] "Adjustments based on user feedback" refers to the process of reviewing and adapting the content and format of exam questions based on feedback information obtained through the emotion engine and user input.

[0548] This invention relates to an examination question creation system that supports teachers in educational institutions. It mainly consists of three components: a server, a terminal, and a user. Its embodiments are described below.

[0549] The server analyzes exam questions based on educational program data, verifying the comprehensiveness of the scope of the questions and verifying any overlap in questions. Furthermore, the server selects the most suitable questions from the question aggregation device and performs calculations to adjust the overall difficulty level. This process utilizes specific AI algorithms and an emotion engine, allowing for real-time adjustments based on the user's emotional state. Specifically, the hardware used includes a database server and an AI calculation server.

[0550] The terminal provides an interface for users to input test information. As users input test details and settings through the terminal, it transmits this information to a server and receives analysis and suggestions. This interface is designed for user-friendly visibility and includes software to monitor the user's emotional state based on input speed and facial expression analysis.

[0551] Users can leverage these systems that support the generation of exam questions to flexibly design teaching materials and question formats. In particular, by utilizing generative AI models, it becomes easier to generate appropriate combinations of questions from complex sets and find the optimal question format.

[0552] As a concrete example, when a user creates a math exam question, they input a prompt such as "Create an exam that covers the basics of differential and integral calculus" into the generation AI model. As a result, the server selects highly relevant questions from the question ensemble and provides a well-balanced exam overall. Furthermore, if the user is confused by a particular question, the emotion engine detects this situation, and the server offers supplementary hints or simplified solutions.

[0553] In this way, the present invention makes it possible to create high-quality, student-friendly examination questions while reducing the burden on educators.

[0554] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0555] Step 1:

[0556] The user enters exam information using a terminal. This information includes the subject matter, scope of the questions, and desired difficulty level. The terminal checks the format of this data, verifies its validity, and then sends it to the server. This process involves verifying the input data and converting its format, ensuring the output is in the appropriate format for the server.

[0557] Step 2:

[0558] The server uses the received input data to reference educational program data and evaluate the comprehensiveness of the exam questions. Specifically, it calculates the extent to which the input question range covers the entire curriculum. This analysis process involves comparative calculations based on program data. The output is evaluation data regarding comprehensiveness.

[0559] Step 3:

[0560] The server uses data from the question aggregation device to select questions in order to optimize the overall difficulty level of the exam. Questions are selected using an AI algorithm, and their difficulty levels are adjusted to ensure balance. The input is the question database and difficulty criteria, and the output is the selected set of questions.

[0561] Step 4:

[0562] The device utilizes an emotion engine to monitor the user's emotional state in real time. This uses the user's facial expression data and input pace. The emotional data is analyzed, and if the user is experiencing stress, this information is fed back to the server. The output is data related to the user's emotional state.

[0563] Step 5:

[0564] The server receives feedback from the emotion engine and provides appropriate support to the user. For example, if the server detects that the user is stressed, it may offer hints for the test questions or suggest adjusting the difficulty level. The input is emotional feedback and selected questions, and the output is a set of questions adjusted based on the feedback.

[0565] Step 6:

[0566] Users review the exam question suggestions from the server and make corrections and verifications using a terminal as needed. The final set of exam questions is determined. The terminal provides an interface for final verification, and the output is the final version of the exam that the user has reviewed.

[0567] (Application Example 2)

[0568] Next, we will explain application example 2. In the following explanation, 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."

[0569] Creating examination questions in educational institutions is a significant burden for teachers, as it requires generating high-quality questions that cover the entire curriculum. Furthermore, providing effective support tailored to learners' emotions and levels of understanding is challenging in home learning support. Solutions are needed to improve the quality of examination questions and learning support while achieving a more efficient process.

[0570] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0571] This invention includes a server that includes means for analyzing test questions based on curriculum data and evaluating the comprehensiveness of the test scope, means for selecting questions from a question data set and optimizing the overall difficulty level of the test, means for recognizing the user's emotional state in real time using emotion analysis technology and providing appropriate feedback, and means for analyzing the learner's state in an automated home device and automatically providing appropriate support. This makes it possible to improve the quality of test question creation and learning support in educational settings and home learning, and to realize an efficient process.

[0572] "Curriculum data" refers to information that summarizes the educational content and learning points formulated by teachers.

[0573] "Examination questions" refer to questions given for the purpose of evaluating learning in educational institutions.

[0574] "Comprehensiveness of the exam scope" is a measure used to evaluate the extent to which the exam questions cover the entire curriculum.

[0575] A "problem data collection" refers to a collection of information that contains a number of questions that could potentially be used as exam questions.

[0576] "Emotion analysis technology" refers to technology that identifies and analyzes emotions from a user's facial expressions and voice.

[0577] "User emotional state" refers to the internal state that indicates a user's emotional response.

[0578] "Appropriate feedback" refers to helpful information and advice provided according to the user's situation and needs.

[0579] "Household automated appliances" refer to automated devices used on a daily basis within the home.

[0580] "The learner's state" refers to the overall condition of an individual during learning, including their level of understanding, concentration, and emotions.

[0581] "Automatically providing assistance" refers to the act of a machine or system intervening to provide help when certain conditions are met.

[0582] This invention is an integrated system for efficiently creating test questions and providing learning support for educational institutions and homes. At the core of the system are means for analyzing curriculum data and optimizing test questions, and means for evaluating the user's emotional state in real time using emotion analysis technology and providing appropriate feedback.

[0583] The server evaluates the comprehensiveness of the exam scope based on curriculum data when creating exam questions. This automatically generates a set of questions that cover the entire curriculum. It also has a function to select the most suitable questions from the question data set and adjust the overall difficulty level of the exam.

[0584] The terminal provides an interface for the user to input test information, and based on this, sentiment analysis technology is applied to monitor the user's emotional state. The sentiment analysis technology used here utilizes a common sentiment recognition API (e.g., a Microsoft Azure service) to analyze the user's facial expressions and voice.

[0585] As users create or study test questions, the system collects emotional data in real time and evaluates it using a generative AI model. For example, if the system determines that a user is under high stress, it will adjust the difficulty level of the test questions or automatically provide hints.

[0586] For example, if a user is trying to create a math test question but looks confused, the system will suggest, "This question seems a little difficult. Do you need a hint?" and provide changes to the question format or hints as needed.

[0587] An example of a prompt from a generative AI model is: "If stress is detected from a child's facial expression and tone of voice, suggest what encouraging messages and hints you can offer for the math problem."

[0588] In this way, the present invention can realize examinations and learning support tailored to the needs of educators and learners.

[0589] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0590] Step 1:

[0591] The server receives curriculum data as input and evaluates the comprehensiveness of the exam scope. To do this, it uses a data analysis algorithm to scan the curriculum data, evaluate how well the exam question set covers the overall educational objectives, and outputs an exam scope score.

[0592] Step 2:

[0593] The server takes the question data set as input and optimizes the overall difficulty level of the exam. At this stage, the difficulty level of each question is evaluated by an AI algorithm, and the set of questions with the most appropriate combination of difficulty levels is output.

[0594] Step 3:

[0595] The terminal receives exam information from the user as input and makes that information available for display and modification on the interface. Through this interface, the user can perform final checks and adjustments to the exam questions.

[0596] Step 4:

[0597] The device acquires data from the user's facial expressions and voice as input and uses emotion analysis technology to evaluate the user's emotional state. Based on this analysis, it outputs a score indicating the user's emotional state.

[0598] Step 5:

[0599] The server receives the sentiment analysis results as input and uses a generative AI model to generate appropriate feedback. This feedback is output in a form that includes adjusting the difficulty of the test questions and providing encouraging messages, depending on the user's emotional state.

[0600] Step 6:

[0601] Users review feedback provided via their devices and adjust exam questions as needed. This enhances the user's exam creation process and provides better learning support.

[0602] Step 7:

[0603] A prompt message is automatically generated and recorded for future improvement. For example, it might output something like, "If stress is detected from the child's facial expression and tone of voice, please suggest what encouraging message and hints you can offer for the math problem."

[0604] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0605] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0606] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0607] [Fourth Embodiment]

[0608] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0609] As shown in Figure 7, the 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.

[0610] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0611] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0612] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0613] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0614] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0615] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0616] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0617] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0618] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0619] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0620] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0621] This invention relates to a system for teachers in educational institutions to efficiently create high-quality examination questions. This system evaluates examination questions based on curriculum data, ensuring comprehensive coverage of the subject matter and adjusting the overall difficulty level. Furthermore, it checks for duplication by comparing current questions with past examination questions to prevent plagiarism. The system also enables the suggestion of optimal question formats tailored to the purpose of the examination.

[0622] The server first receives curriculum data and then analyzes the comprehensiveness of the exam questions based on that data. This prevents specific topics from being inappropriately emphasized. For example, it adjusts the math exam to ensure that each topic in algebra and geometry is covered evenly.

[0623] Next, the server analyzes past questions provided from the question database and adjusts the difficulty level of newly created test questions to be uniform. Through this process, the difficulty distribution across the entire exam is optimized. For example, it ensures that the questions are balanced from basic to advanced levels according to the students' abilities.

[0624] The terminal compares the created test questions with past test questions to detect duplicates. It also investigates whether the question text and materials match widely available information to check for potential plagiarism.

[0625] Ultimately, the server suggests the optimal question format for the purpose and target audience of the exam. For example, it might generate a set of questions that combine essay questions to test the depth of knowledge with multiple-choice questions to test the breadth of knowledge.

[0626] Users can review the exam questions suggested by the system and make modifications as needed. In this way, the present invention can reduce the burden on instructors and provide students with exams of fair and appropriate difficulty levels.

[0627] The following describes the processing flow.

[0628] Step 1:

[0629] The user enters exam information into the terminal. They input the subject, the purpose of the exam, the student's level, etc., and determine the basic settings for the exam.

[0630] Step 2:

[0631] The server retrieves curriculum data. It obtains curriculum information for the subjects to be tested and sets the criteria for the scope of the questions.

[0632] Step 3:

[0633] The server analyzes the comprehensiveness of the exam questions. Based on curriculum data, it evaluates whether the exam questions cover all necessary topics.

[0634] Step 4:

[0635] The server analyzes the problem database. It determines the difficulty level of each problem from the existing problems and selects new problems to optimize the overall difficulty balance of the exam.

[0636] Step 5:

[0637] The terminal checks for duplication with past questions. It compares the generated test questions with past test question data to identify questions that may be duplicates.

[0638] Step 6:

[0639] The server performs plagiarism and copyright checks. It compares new exam questions with external resources to verify that they are not plagiarized from existing copyrighted works.

[0640] Step 7:

[0641] The server proposes the question format. It suggests the most suitable question format (essay, multiple-choice, application problems, etc.) to the user according to the purpose of the exam.

[0642] Step 8:

[0643] The user performs the final review and revisions. They review the proposed test questions and format, and complete the final test questions by making any necessary corrections on their device.

[0644] (Example 1)

[0645] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0646] In modern education, the process of teachers creating exam questions is time-consuming and labor-intensive, and there are challenges in appropriately adjusting comprehensiveness and difficulty level. Furthermore, issues such as duplication with past questions and plagiarism contribute to a decline in the quality of education. Additionally, teachers are required to make judgments regarding the appropriate question format according to the purpose of the exam, which is a difficult task for many.

[0647] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0648] In this invention, the server includes a device that analyzes exam questions based on curriculum information and evaluates the comprehensiveness of the scope of the questions; a device that selects questions from a question database and optimizes the overall difficulty level of the exam; and a device that refers to past exam questions and detects duplication of new questions. This enables the effective creation and management of exam questions.

[0649] "Curriculum information" refers to data that outlines the plans and objectives of learning instruction at educational institutions, and includes detailed curriculum content for specific subjects or fields.

[0650] A "question database" is a collection of past exam questions, and is an information resource that stores related information such as the question text, answers, difficulty level, and the date the questions were asked.

[0651] A "learning model" is the structure of an algorithm trained using machine learning techniques with data, and it has the ability to make predictions and classifications based on new information.

[0652] "Question format" refers to the method of presenting questions used in exams and tests, and includes formats such as multiple-choice, written response, and fill-in-the-blank.

[0653] A "generative algorithm" is a mathematical or programmatic procedure for creating new output (in this case, exam questions) based on input data.

[0654] This invention provides a system for teachers in educational institutions to efficiently create high-quality examination questions. The following describes a specific form for implementing this system.

[0655] The server receives curriculum information and analyzes the comprehensiveness of the exam questions based on that data. Specific software used for this analysis includes data analysis tools (e.g., Python's pandas library). This analysis makes it possible to prevent specific topics from being overly or inappropriately covered. For example, in a mathematics exam, it verifies and adjusts to ensure that each topic in algebra and geometry is covered evenly.

[0656] Furthermore, the server references a database of past exam questions to optimize the difficulty level of newly created exam questions. Machine learning models (e.g., scikit-learn) are used to adjust the difficulty level. Specifically, they evaluate the difficulty of the questions and select questions appropriate to the students' learning levels.

[0657] The terminal is responsible for comparing newly created test questions with past questions and detecting similarities. A text matching tool (e.g., difflib) is used for text comparison. Furthermore, the terminal uses a cloud-based search tool to compare the questions with external sources and check for potential plagiarism.

[0658] Ultimately, the server proposes the optimal question format tailored to the purpose of the exam. This process utilizes a generative AI model. For example, it can propose a format that combines descriptive questions testing the depth of knowledge with multiple-choice questions testing the breadth of knowledge.

[0659] Users can review the set of test questions generated through these processes and make revisions as needed. By reviewing the questions via the GUI and inputting feedback into the system, the final test set is completed.

[0660] Examples of prompts to input into a generative AI model:

[0661] "Create a set of questions that cover all the necessary algebraic and geometric topics for a mathematics exam, adjusting the difficulty level to suit the students' abilities. Ensure there is no overlap with past questions, and propose a combination of written and multiple-choice questions."

[0662] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0663] Step 1:

[0664] The server receives and analyzes curriculum information from educational institutions. The input is curriculum data, which is used to perform analysis to verify the comprehensiveness of the exam scope. Specifically, the server uses a data analysis tool to calculate the frequency of occurrence of each topic and generates a graph to visually display this information. This allows for verification of whether any particular topic is being covered excessively. The output is a report of the analysis results.

[0665] Step 2:

[0666] The server references a question database containing past exam questions. It uses past exam questions retrieved from the database as input. The server applies a machine learning model to predict the difficulty level of newly created questions and adjusts the overall difficulty level of the exam uniformly. Specifically, it performs classification and clustering using the machine learning model to balance the difficulty levels. The output provides a list of the adjusted difficulty distributions.

[0667] Step 3:

[0668] The terminal compares newly created test questions with past question data. The input consists of data for both the new questions and past questions. The terminal uses a text comparison algorithm to evaluate similarity and determine if there are duplicates. Specifically, it generates similarity scores for the past and new questions, highlights questions with high scores, and notifies the user. The output is a list of similarity judgments.

[0669] Step 4:

[0670] The terminal cross-references questions with external sources to prevent plagiarism. New question data is used as input. Cloud search tools are utilized to compare the question text with widely available literature and information. Specifically, the system searches for the question text, measures the degree of similarity, and compiles the results into a report. The output provides a plagiarism risk assessment report.

[0671] Step 5:

[0672] The server proposes the optimal question format based on the purpose and target audience of the exam. It uses analyzed exam question data and exam purpose information as input. A generative AI model is used to generate the optimal structure of the exam questions. Specifically, it automatically generates suggestions combining multiple formats, such as written and multiple-choice questions. The output is a set of recommended exam formats.

[0673] Step 6:

[0674] The user reviews the generated set of exam questions and makes corrections as needed. The system provides a set of exam questions as input. The user reviews the questions using a GUI and edits, deletes, and adds questions through an intuitive interface. Specific actions include changing the order of questions via drag-and-drop and adding comments. The output is the final, corrected set of exam questions.

[0675] (Application Example 1)

[0676] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0677] This invention aims to solve the problem of the need for a system in educational institutions and homes to efficiently create and evaluate the quality of examination questions according to the progress of individual learners. In conventional examination question creation, teachers and educators currently spend a great deal of time and effort ensuring comprehensiveness, difficulty level, and preventing duplication and plagiarism. Furthermore, it is difficult to provide appropriate examinations for each learner, sometimes resulting in unfair evaluation. Therefore, there is a need for new technologies in educational environments that enable efficient preparation of examination questions and fair and appropriate evaluation.

[0678] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0679] In this invention, the server includes means for analyzing exam questions based on curriculum data and evaluating the comprehensiveness of the scope of questions; means for selecting questions from a set of question data and optimizing the overall difficulty level of the evaluation; and means for referring to past exam questions and detecting duplication of new questions. This enables the efficient construction of exam questions tailored to individual learners, and allows for fair and high-quality evaluation.

[0680] "Curriculum data" refers to a collection of information that systematically organizes the topics and content that students should learn, based on a specific educational program or curriculum guideline.

[0681] An "exam question" is a series of questions or tasks created for the purpose of evaluating a learner's knowledge and understanding.

[0682] "Means for evaluating comprehensiveness" refer to methods and systems for verifying and evaluating whether the examination questions adequately include all the topics and important items that should be covered.

[0683] A "question data set" is a collection of questions gathered from past exams and educational resources.

[0684] "Methods for optimizing difficulty level" refer to methods of adjusting and standardizing the difficulty level of exam questions in order to provide learners with an appropriate challenge throughout the entire exam.

[0685] "Means for detecting duplication" refers to methods for verifying whether newly created test questions are identical or similar to questions that have existed in the past.

[0686] "External information sets" refer to all information resources that exist externally, such as books, websites, and learning materials.

[0687] "Means of detecting plagiarism in documents" refers to methods for verifying whether exam questions are inappropriately quoted or copied from other content.

[0688] "Methods for proposing question formats" refer to methods of analyzing and proposing what type of questions should be asked, depending on the purpose of the exam and the level of the learners.

[0689] "Learning progress" is an indicator that shows how far a learner has progressed towards a specific learning objective or curriculum.

[0690] "Individualized test questions" are questions that are customized according to each learner's learning progress and level of understanding.

[0691] "Means of providing evaluation feedback" refers to methods of providing learners with the results and evaluations of the tests they have taken, in order to guide their future learning.

[0692] Embodiments of this invention include a system for efficiently and accurately providing test questions to learners in educational institutions and home environments. A server receives curriculum data and analyzes the comprehensiveness of the test questions based on its content. This process utilizes data processing algorithms to evaluate whether each topic is covered adequately and without omission. This is particularly useful in achieving an even topic distribution in subjects such as mathematics and science.

[0693] Next, the server analyzes the selected questions from the question data set and optimizes the overall difficulty level of the exam. During this process, an AI algorithm is used to score the questions and adjust the difficulty level according to the students' learning progress. For example, questions are arranged so that the difficulty level gradually increases from the basics.

[0694] The server also runs a search algorithm to prevent duplication between past exam questions and newly created questions. This allows for a fresh and meaningful learning experience for students. Furthermore, the reliability of the exam is maintained by detecting the use of fraudulent documents by comparing them with external information sets.

[0695] The terminal presents the generated test questions to learners and provides real-time evaluation feedback. Teachers and administrators, as users, can input test information through this terminal and perform final checks and adjustments to the questions.

[0696] For example, language exams may generate personalized questions designed to reinforce specific grammatical points. For instance, correction questions such as "Transform the following sentence into the correct form" might be presented in real time.

[0697] Examples of prompt statements for a generative AI model are as follows:

[0698] "Please generate intermediate-level exam questions on solving quadratic equations. Please include detailed information about the knowledge required to answer them."

[0699] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0700] Step 1:

[0701] The server receives curriculum data and analyzes it. It takes learning topic information and related data as input and generates comprehensiveness assessment results as output. Specifically, it evaluates whether each topic is adequately covered based on a data processing algorithm.

[0702] Step 2:

[0703] The server selects exam questions by referring to a set of question data. It receives historically accumulated question sets and current curriculum data as input, and generates a list of selected questions as output. Specifically, it uses an AI algorithm to calculate difficulty scores and ensure that the exam questions are placed at appropriate levels.

[0704] Step 3:

[0705] The server compares past exam questions to detect duplicates in new exam questions. It takes newly generated exam questions and past exam data as input and generates a report indicating whether or not there are duplicates as output. Specifically, it executes a search algorithm to compare the similarity of the question texts.

[0706] Step 4:

[0707] The server compares new exam questions with external information sets to check for plagiarism. Inputs include new exam questions and external information such as online databases. Outputs provide analysis results indicating whether or not plagiarism has occurred. Specifically, it performs document similarity analysis using natural language processing techniques.

[0708] Step 5:

[0709] The terminal presents the generated test questions and feedback to the target learner. The user reviews the questions and makes corrections and final checks to the test information through the terminal. The input is the generated test questions and learner information, and the output is the presentation of the test to the learner and the feedback results. Specific operations include displaying results through the user interface.

[0710] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0711] This invention provides a system for teachers in educational institutions to create efficient and high-quality examination questions, and incorporates an emotion engine that recognizes user emotions. This system analyzes examination questions based on curriculum data to ensure comprehensive coverage of the subject matter. It also selects questions from a question database to optimize the overall difficulty level of the examination. Furthermore, it guarantees quality by checking for duplication by comparing with past examination questions and evaluating the risk of plagiarism through comparison with external materials.

[0712] The server suggests the optimal question format that best suits the purpose of the exam. In addition, an emotion engine recognizes the user's emotional state, analyzing the emotions the user exhibits while creating exam questions (e.g., stress or decreased concentration) and providing corresponding feedback. For example, if the emotion engine determines that the user is confused, the server will suggest simplifying the exam setup.

[0713] The terminal uses an emotion engine to monitor the user's state in real time based on the test information entered by the user. It provides an interface that allows the user to review and adjust the test questions and format as needed, reducing the complexity and potential for errors during the process.

[0714] The server completes the exam if it determines that the configured exam questions and format meet the final criteria. Furthermore, it uses user feedback detected by the emotion engine to improve the future exam question creation process.

[0715] As a concrete example, in the creation of mathematics exam questions, when a user encounters a difficult problem, the emotion engine detects the user's stress level, and the server provides hints for the problem or suggests adjusting the difficulty level accordingly. In this way, the present invention reduces the burden on educators and enables smooth and effective creation of exam questions.

[0716] The following describes the processing flow.

[0717] Step 1:

[0718] The user enters exam information into the terminal. This includes basic exam information such as the subject, purpose, and student level.

[0719] Step 2:

[0720] The server retrieves the curriculum data and begins analysis. Based on the curriculum, it evaluates whether the exam questions cover all the necessary topics.

[0721] Step 3:

[0722] The emotion engine analyzes the user's emotional state in real time. It detects stress and fatigue based on the user's facial expressions and actions when they input test information.

[0723] Step 4:

[0724] The server analyzes the problem database and selects problems based on their difficulty level. It also considers data from the emotion engine and adjusts problem selection according to the user's state.

[0725] Step 5:

[0726] The terminal checks for duplication with past questions. It compares the generated questions with past exam question data to identify similar or duplicate questions.

[0727] Step 6:

[0728] The server checks for plagiarism by comparing the text with an external database. It verifies that the text of the exam questions does not match any existing copyrighted works.

[0729] Step 7:

[0730] The server suggests the optimal question format. It informs the user of the format that suits the purpose of the exam and adjusts the suggestion as needed.

[0731] Step 8:

[0732] The emotion engine receives user feedback and determines if adjustments are needed. If the user is feeling confused or stressed, it works with the server to simplify or assist them.

[0733] Step 9:

[0734] The user performs a final review. They check the proposed test questions and format on their device and make any necessary revisions. They then approve the completed test.

[0735] (Example 2)

[0736] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0737] When teachers at educational institutions create exam questions, they are required to construct questions efficiently and with high quality while maintaining a balance between comprehensiveness of the scope of the material and difficulty level. However, current methods have several problems, including duplication, lack of comprehensiveness, the risk of unauthorized use, and decreased work efficiency due to emotional stress on users. There is a need to provide a means to solve these problems simultaneously.

[0738] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0739] In this invention, the server includes means for analyzing problems based on educational program data and evaluating the comprehensiveness of the problem range, means for selecting problems from a problem aggregation device and optimizing the overall difficulty level of the problems, and means for analyzing the user's emotional state and making adjustments based on user feedback. This enables efficient creation of examination questions, improving the quality of education and reducing the workload of teachers.

[0740] "Educational program data" refers to data containing information about curricula and syllabi used in educational institutions, and is used for analyzing and evaluating the scope of exam questions.

[0741] A "problem collection device" is a database or information system that collects and stores examination questions, and is used to select appropriate questions.

[0742] "User's emotional state" refers to the psychological state and emotions of the user while creating the test questions, including changes in stress levels and concentration.

[0743] "Adjustments based on user feedback" refers to the process of reviewing and adapting the content and format of exam questions based on feedback information obtained through the emotion engine and user input.

[0744] This invention relates to an examination question creation system that supports teachers in educational institutions. It mainly consists of three components: a server, a terminal, and a user. Its embodiments are described below.

[0745] The server analyzes exam questions based on educational program data, verifying the comprehensiveness of the scope of the questions and verifying any overlap in questions. Furthermore, the server selects the most suitable questions from the question aggregation device and performs calculations to adjust the overall difficulty level. This process utilizes specific AI algorithms and an emotion engine, allowing for real-time adjustments based on the user's emotional state. Specifically, the hardware used includes a database server and an AI calculation server.

[0746] The terminal provides an interface for users to input test information. As users input test details and settings through the terminal, it transmits this information to a server and receives analysis and suggestions. This interface is designed for user-friendly visibility and includes software to monitor the user's emotional state based on input speed and facial expression analysis.

[0747] Users can leverage these systems that support the generation of exam questions to flexibly design teaching materials and question formats. In particular, by utilizing generative AI models, it becomes easier to generate appropriate combinations of questions from complex sets and find the optimal question format.

[0748] As a concrete example, when a user creates a math exam question, they input a prompt such as "Create an exam that covers the basics of differential and integral calculus" into the generation AI model. As a result, the server selects highly relevant questions from the question ensemble and provides a well-balanced exam overall. Furthermore, if the user is confused by a particular question, the emotion engine detects this situation, and the server offers supplementary hints or simplified solutions.

[0749] In this way, the present invention makes it possible to create high-quality, student-friendly examination questions while reducing the burden on educators.

[0750] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0751] Step 1:

[0752] The user enters exam information using a terminal. This information includes the subject matter, scope of the questions, and desired difficulty level. The terminal checks the format of this data, verifies its validity, and then sends it to the server. This process involves verifying the input data and converting its format, ensuring the output is in the appropriate format for the server.

[0753] Step 2:

[0754] The server uses the received input data to reference educational program data and evaluate the comprehensiveness of the exam questions. Specifically, it calculates the extent to which the input question range covers the entire curriculum. This analysis process involves comparative calculations based on program data. The output is evaluation data regarding comprehensiveness.

[0755] Step 3:

[0756] The server uses data from the question aggregation device to select questions in order to optimize the overall difficulty level of the exam. Questions are selected using an AI algorithm, and their difficulty levels are adjusted to ensure balance. The input is the question database and difficulty criteria, and the output is the selected set of questions.

[0757] Step 4:

[0758] The device utilizes an emotion engine to monitor the user's emotional state in real time. This uses the user's facial expression data and input pace. The emotional data is analyzed, and if the user is experiencing stress, this information is fed back to the server. The output is data related to the user's emotional state.

[0759] Step 5:

[0760] The server receives feedback from the emotion engine and provides appropriate support to the user. For example, if the server detects that the user is stressed, it may offer hints for the test questions or suggest adjusting the difficulty level. The input is emotional feedback and selected questions, and the output is a set of questions adjusted based on the feedback.

[0761] Step 6:

[0762] Users review the exam question suggestions from the server and make corrections and verifications using a terminal as needed. The final set of exam questions is determined. The terminal provides an interface for final verification, and the output is the final version of the exam that the user has reviewed.

[0763] (Application Example 2)

[0764] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0765] Creating examination questions in educational institutions is a significant burden for teachers, as it requires generating high-quality questions that cover the entire curriculum. Furthermore, providing effective support tailored to learners' emotions and levels of understanding is challenging in home learning support. Solutions are needed to improve the quality of examination questions and learning support while achieving a more efficient process.

[0766] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0767] This invention includes a server that includes means for analyzing test questions based on curriculum data and evaluating the comprehensiveness of the test scope, means for selecting questions from a question data set and optimizing the overall difficulty level of the test, means for recognizing the user's emotional state in real time using emotion analysis technology and providing appropriate feedback, and means for analyzing the learner's state in an automated home device and automatically providing appropriate support. This makes it possible to improve the quality of test question creation and learning support in educational settings and home learning, and to realize an efficient process.

[0768] "Curriculum data" refers to information that summarizes the educational content and learning points formulated by teachers.

[0769] "Examination questions" refer to questions given for the purpose of evaluating learning in educational institutions.

[0770] "Comprehensiveness of the exam scope" is a measure used to evaluate the extent to which the exam questions cover the entire curriculum.

[0771] A "problem data collection" refers to a collection of information that contains a number of questions that could potentially be used as exam questions.

[0772] "Emotion analysis technology" refers to technology that identifies and analyzes emotions from a user's facial expressions and voice.

[0773] "User emotional state" refers to the internal state that indicates a user's emotional response.

[0774] "Appropriate feedback" refers to helpful information and advice provided according to the user's situation and needs.

[0775] "Household automated appliances" refer to automated devices used on a daily basis within the home.

[0776] "The learner's state" refers to the overall condition of an individual during learning, including their level of understanding, concentration, and emotions.

[0777] "Automatically providing assistance" refers to the act of a machine or system intervening to provide help when certain conditions are met.

[0778] This invention is an integrated system for efficiently creating test questions and providing learning support for educational institutions and homes. At the core of the system are means for analyzing curriculum data and optimizing test questions, and means for evaluating the user's emotional state in real time using emotion analysis technology and providing appropriate feedback.

[0779] The server evaluates the comprehensiveness of the exam scope based on curriculum data when creating exam questions. This automatically generates a set of questions that cover the entire curriculum. It also has a function to select the most suitable questions from the question data set and adjust the overall difficulty level of the exam.

[0780] The terminal provides an interface for the user to input test information, and based on this, sentiment analysis technology is applied to monitor the user's emotional state. The sentiment analysis technology used here utilizes a common sentiment recognition API (e.g., a Microsoft Azure service) to analyze the user's facial expressions and voice.

[0781] As users create or study test questions, the system collects emotional data in real time and evaluates it using a generative AI model. For example, if the system determines that a user is under high stress, it will adjust the difficulty level of the test questions or automatically provide hints.

[0782] For example, if a user is trying to create a math test question but looks confused, the system will suggest, "This question seems a little difficult. Do you need a hint?" and provide changes to the question format or hints as needed.

[0783] An example of a prompt from a generative AI model is: "If stress is detected from a child's facial expression and tone of voice, suggest what encouraging messages and hints you can offer for the math problem."

[0784] In this way, the present invention can realize examinations and learning support tailored to the needs of educators and learners.

[0785] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0786] Step 1:

[0787] The server receives curriculum data as input and evaluates the comprehensiveness of the exam scope. To do this, it uses a data analysis algorithm to scan the curriculum data, evaluate how well the exam question set covers the overall educational objectives, and outputs an exam scope score.

[0788] Step 2:

[0789] The server takes the question data set as input and optimizes the overall difficulty level of the exam. At this stage, the difficulty level of each question is evaluated by an AI algorithm, and the set of questions with the most appropriate combination of difficulty levels is output.

[0790] Step 3:

[0791] The terminal receives exam information from the user as input and makes that information available for display and modification on the interface. Through this interface, the user can perform final checks and adjustments to the exam questions.

[0792] Step 4:

[0793] The device acquires data from the user's facial expressions and voice as input and uses emotion analysis technology to evaluate the user's emotional state. Based on this analysis, it outputs a score indicating the user's emotional state.

[0794] Step 5:

[0795] The server receives the sentiment analysis results as input and uses a generative AI model to generate appropriate feedback. This feedback is output in a form that includes adjusting the difficulty of the test questions and providing encouraging messages, depending on the user's emotional state.

[0796] Step 6:

[0797] Users review feedback provided via their devices and adjust exam questions as needed. This enhances the user's exam creation process and provides better learning support.

[0798] Step 7:

[0799] A prompt message is automatically generated and recorded for future improvement. For example, it might output something like, "If stress is detected from the child's facial expression and tone of voice, please suggest what encouraging message and hints you can offer for the math problem."

[0800] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0801] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0802] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0803] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0804] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0805] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0806] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0807] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0808] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0809] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0810] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0811] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0812] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0813] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0814] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0815] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0816] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0817] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0818] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0819] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0820] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0821] The following is further disclosed regarding the embodiments described above.

[0822] (Claim 1)

[0823] A means of analyzing examination questions based on curriculum data and evaluating the comprehensiveness of the scope of the questions,

[0824] A method for selecting questions from a question database and optimizing the overall difficulty level of the exam,

[0825] A means of detecting duplicate new questions by referring to past exam questions,

[0826] A means of detecting text plagiarism by comparing it with an external database,

[0827] A means of proposing an appropriate question format according to the purpose of the examination,

[0828] A system that includes this.

[0829] (Claim 2)

[0830] The system according to claim 1, which allows a user to input test information and modify or finalize test questions.

[0831] (Claim 3)

[0832] The system according to claim 1, comprising means for scoring the comprehensiveness and difficulty level of examination questions using an AI algorithm.

[0833] "Example 1"

[0834] (Claim 1)

[0835] A device that analyzes exam questions based on curriculum information and evaluates the comprehensiveness of the scope of the questions,

[0836] A device that selects questions from a question database and optimizes the overall difficulty level of the exam,

[0837] A device that refers to past exam questions and detects duplicate new questions,

[0838] A device that detects plagiarism in text by comparing it with external sources,

[0839] A device that proposes an appropriate question format according to the purpose of the test,

[0840] A device for visualizing the results of the analysis of exam questions,

[0841] A device including a learning model for predicting and adjusting the difficulty level of new test questions,

[0842] A device that checks for similarity in test questions and indicates the possibility of duplication,

[0843] A device that proposes the structure of test questions using a generation algorithm,

[0844] Intellectual media including

[0845] (Claim 2)

[0846] The intellectual medium according to claim 1, which allows a user to input test information and modify or finalize test questions.

[0847] (Claim 3)

[0848] The intelligent medium according to claim 1, comprising a device that scores the comprehensiveness and difficulty level of test questions using a learning model.

[0849] "Application Example 1"

[0850] (Claim 1)

[0851] A means of analyzing examination questions based on curriculum data and evaluating the comprehensiveness of the scope of the questions,

[0852] A method for selecting problems from a problem data set and optimizing the overall difficulty level of the evaluation,

[0853] A means of detecting duplicate new questions by referring to past exam questions,

[0854] A means of detecting plagiarism in a document by comparing it with an external set of information,

[0855] A means of proposing an appropriate question format according to the purpose of the examination,

[0856] A means for generating individualized test questions based on learning progress,

[0857] A means of providing learners with evaluation feedback on the generated test questions,

[0858] A system that includes this.

[0859] (Claim 2)

[0860] The system according to claim 1, which enables users to input evaluation information and adjust or finalize test questions.

[0861] (Claim 3)

[0862] The system according to claim 1, comprising means for using an AI algorithm to score the comprehensiveness and difficulty level of exam questions and to provide feedback according to the learner's progress.

[0863] "Example 2 of combining an emotion engine"

[0864] (Claim 1)

[0865] A means of analyzing problems based on educational program data and evaluating the comprehensiveness of the problem scope,

[0866] A means for selecting problems from a problem collection device and optimizing the overall difficulty level of the problems,

[0867] A means of detecting duplicate new problems by referring to past problems,

[0868] A means of detecting unauthorized use of text by comparing it with external information,

[0869] A means of analyzing the user's emotional state and making adjustments based on user feedback,

[0870] A means of proposing the optimal format according to the purpose of the test,

[0871] A system that includes this.

[0872] (Claim 2)

[0873] The system according to claim 1, which allows a user to input information and correct or finalize problems.

[0874] (Claim 3)

[0875] The system according to claim 1, comprising means for evaluating the comprehensiveness and difficulty of a problem using a generative model.

[0876] "Application example 2 when combining with an emotional engine"

[0877] (Claim 1)

[0878] A means of analyzing examination questions based on curriculum data and evaluating the comprehensiveness of the scope of the questions,

[0879] A method for selecting questions from a collection of question data and optimizing the overall difficulty level of the exam,

[0880] A means of detecting duplicate new questions by referring to past exam questions,

[0881] A means of detecting text plagiarism compared to external data sets,

[0882] A means of proposing an appropriate question format according to the purpose of the examination,

[0883] A means of recognizing a user's emotional state in real time using emotion analysis technology and providing appropriate feedback,

[0884] A means for analyzing the learner's condition in an automated device for home use and automatically providing appropriate support,

[0885] A system that includes this.

[0886] (Claim 2)

[0887] The system according to claim 1, which allows a user to input test information and make corrections or final checks on test tasks.

[0888] (Claim 3)

[0889] The system according to claim 1, comprising means for scoring the comprehensiveness and difficulty level of examination tasks using a generative AI algorithm. [Explanation of symbols]

[0890] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of analyzing examination questions based on curriculum data and evaluating the comprehensiveness of the scope of the questions, A method for selecting questions from a question database and optimizing the overall difficulty level of the exam, A means of detecting duplicate new questions by referring to past exam questions, A means of detecting text plagiarism by comparing it with an external database, A means of proposing an appropriate question format according to the purpose of the examination, A system that includes this.

2. The system according to claim 1, which allows a user to input test information and make corrections and final checks on test questions.

3. The system according to claim 1, comprising means for scoring the comprehensiveness and difficulty level of examination questions using an AI algorithm.

Images