system

Abstract

We provide the system. [Solution] Equipped with an information processing device for automating educational evaluation, A means for selecting multiple educational issues based on one or more conditions and automatically generating an educational assessment test, A means of performing automatic scoring by comparing the received answer data with the model answer, A system including means for generating and presenting scoring results and feedback.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is 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 conventional educational field, the lesson preparation and grading work done by teachers are enormous. As a result, a lot of time is consumed, which has an adverse impact on the quality of education and the health of teachers. In addition, it is difficult to provide individual feedback to each student and efficient learning guidance, and a large difference occurs in the learning progress and understanding level of students, which is also a problem. Therefore, there is a need for a system that can reduce the workload of teachers while enhancing the educational effect.

Means for Solving the Problems

[0005] The present invention provides a system equipped with an information processing device for automating educational assessment, which includes means for selecting multiple educational problems based on conditions and automatically generating an educational assessment test, means for performing automatic scoring by comparing received answer data with model answers, and means for generating and presenting scoring results and feedback. Furthermore, by including a function to analyze individual learning patterns based on the results of the educational assessment and provide optimal learning tasks, it is possible to improve the efficiency of teachers' work and enhance the accuracy of individualized instruction. In addition, the efficiency of selection can be improved when generating educational assessment tests by utilizing a shared problem database.

[0006] An "information processing device" is an electronic device used to input, process, and output data, and it performs calculations, data analysis, and presents results.

[0007] "Educational questions" are questions or assignments used in educational settings to assess students' understanding and abilities, and are designed according to their subject matter and difficulty level.

[0008] A "condition" refers to a criterion or constraint for performing a specific action or making a selection, and is a parameter set to obtain a specific result.

[0009] An "educational assessment test" is a set of educational questions designed to measure students' academic ability and understanding, and is structured according to the purpose of the assessment.

[0010] "Reception" refers to the process of obtaining data transmitted from other devices or systems, and is the starting point for processing.

[0011] "Answer data" refers to the answer information submitted by students for educational assessment tests, which is used for scoring and evaluation.

[0012] A "model answer" is a standard solution that shows the correct answer and solution procedure in an educational evaluation test, and is used as a scoring criterion.

[0013] "Automatic scoring" is a process in which a system compares the received answer data with the model answer to determine whether it is correct or incorrect and assigns a score.

[0014] "Feedback" refers to explanations and information on areas for improvement provided to students and teachers based on evaluation results, intended to guide future learning.

[0015] "Learning patterns" are analyses of individual students' learning characteristics and progress trends, and are used as a reference for instruction and assignment setting.

[0016] "Learning tasks" are educational activities or assignments that students are expected to undertake, and are set with the aim of acquiring specific learning content or skills.

[0017] A "problem database" is a collection of data constructed to accumulate educational problems and use them for searching and selection, and is used to generate educational evaluation tests. [Brief explanation of the drawing]

[0018] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This 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

[0019] 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.

[0020] First, the language used in the following description will be described.

[0021] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of 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.

[0022] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0023] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0024] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0025] 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."

[0026] [First Embodiment]

[0027] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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".

[0039] This invention is an automated educational evaluation system designed to reduce the burden on teachers in educational settings and improve the quality of education. The system aims to automate some of the diverse tasks performed by teachers by using an information processing device to select and automatically evaluate educational issues.

[0040] First, the user (teacher) uses a terminal to input parameters such as the test subject, difficulty level, and number of questions. The terminal sends these inputs to the server, which selects appropriate questions from the question database based on the conditions. Based on the selected questions, the server automatically generates an educational assessment test and sends the test back to the terminal. This process reduces the burden of manual question selection on the teacher.

[0041] Next, students write or type their answers and send the answer data to the server via their devices. The server compares the received answer data with the model answer and automatically grades it. The grading results are returned from the server to the devices, where users (teachers and students) can review them. Furthermore, based on the grading results, the server generates feedback and suggested learning tasks and provides them to the devices. This feedback is important for improving the quality of student learning.

[0042] For example, in a math test, if a user (teacher) requests 10 intermediate-level problems on quadratic equations, the server can select the appropriate problems from the database and automatically assemble an educational assessment test. When students take this test and enter their answers on their devices, the server quickly grades it and provides feedback tailored to each student's level of understanding.

[0043] Furthermore, the system can present individualized learning assignments based on each student's learning history and evaluation results, thereby promoting improved student comprehension. In this way, the present invention provides an innovative means to reduce the workload of teachers and support students' motivation and achievements in learning.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The user (teacher) inputs parameters such as the subject, difficulty level, and number of questions for the educational assessment test via their terminal. By clicking the submit button, this information is transferred to the server.

[0047] Step 2:

[0048] The server searches the problem database based on the received parameters. It selects educational problems that match the criteria and creates a list.

[0049] Step 3:

[0050] The server automatically configures the educational assessment test based on the selected educational questions. It then transmits the configured test content to the terminal.

[0051] Step 4:

[0052] The user (teacher) reviews the exam content on their device. They can add, delete, or modify questions as needed. Once the final exam content is confirmed, they instruct the server to save it.

[0053] Step 5:

[0054] The user (student) takes the exam and enters their answers using a terminal. The entered answer data is sent from the terminal to the server.

[0055] Step 6:

[0056] The server compares the received answer data with the model answer and automatically performs the scoring process. Partial credit is also considered during scoring.

[0057] Step 7:

[0058] The server generates the scoring results and sends them to the terminal along with feedback comments.

[0059] Step 8:

[0060] Users (teachers and students) can view grading results and feedback on their devices. Teachers can use this information to provide appropriate support tailored to each student's individual learning progress.

[0061] Step 9:

[0062] The server analyzes each student's evaluation results and learning history, and generates individually optimized learning assignments. The generated assignments are sent to the user (student), who can then review them and engage in self-study.

[0063] (Example 1)

[0064] 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."

[0065] Currently, teachers in schools must spend a great deal of time and effort creating and grading exam questions, and then provide feedback to each student. This increases the burden on teachers, making it difficult to maintain the quality of education. Furthermore, students lack assignments and feedback tailored to their individual learning levels, hindering efficient learning. Therefore, there is a need for a system that automates the educational evaluation process, reduces the burden on teachers, and provides more appropriate learning support to students.

[0066] 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.

[0067] In this invention, the server includes means for selecting questions from an information storage device and automatically generating an evaluation test based on multiple conditions such as the subject, difficulty level, and number of questions of the evaluation test entered by the user; means for mechanically scoring the received answer information by comparing it with a standard answer; means for automatically generating the scoring results and learning guidelines based on those results and presenting them through a display device; and means for providing individualized learning tasks based on the learner's learning history and evaluation results. This makes it possible to streamline the educational evaluation process, significantly reduce the burden on teachers, and provide students with more accurate feedback and learning support.

[0068] "Users" refer to individuals or organizations that use the system to create, manage, and evaluate exams, and typically include educators and teachers.

[0069] An "assessment test" is a set of questions or tasks administered to measure a learner's knowledge and understanding.

[0070] "Conditions" refer to the parameters and criteria considered when creating an exam, specifically including the subject matter, difficulty level, and number of questions.

[0071] An "information storage device" refers to hardware or a system that stores information in digital format and makes it accessible at a later date.

[0072] A "problem" is a question or task presented in a way that requires an answer, and it constitutes part of an evaluation test.

[0073] A "standard answer" refers to a correct or desirable example answer in an assessment test, and serves as a guideline for evaluating students' answers.

[0074] "Mechanical scoring" refers to the process of using computer algorithms to determine how closely an answer matches a standard answer and assign a score accordingly.

[0075] "Feedback" refers to the areas for improvement and learning guidelines given to learners based on the results of an assessment test.

[0076] "Learning guidelines" refer to the materials and assignments suggested to learners to work on next, in order to deepen their understanding.

[0077] This automated educational assessment system primarily consists of three components: a server, a terminal, and a user. The user (teacher) inputs parameters related to the test, such as the subject, difficulty level, and number of questions, through the terminal. This information is typically collected using software with a user-friendly interface. The terminal organizes this information, structures it in a format such as JSON, and sends it to the server.

[0078] The server analyzes the received parameters and manages the data necessary for evaluation using appropriate algorithms. It accesses the problem memory and performs query processing to select problems that meet the criteria. Subsequently, a generative AI model generates the optimal test configuration based on the problems. This process utilizes machine learning and optimization techniques to automatically create efficient and highly accurate test content.

[0079] Once the test configuration is complete, the server sends the test data back to the terminal. The terminal presents the test via a user interface, allowing students to answer the questions. The answers are sent back from the terminal to the server, which then performs automated scoring based on the answers. Natural language processing technology is used for scoring, and the answers are compared against a standard answer.

[0080] Once grading is complete, the server analyzes the results and uses a generative AI model to generate feedback and additional learning guidance. This feedback is provided to the user and students via their devices. Specifically, it includes explanations of the areas where students made mistakes and points to pay attention to.

[0081] As a concrete example, if a user (teacher) wants to create 10 intermediate-level problems on "quadratic equations," they would use a prompt like this: "Generate a set of 10 intermediate-level problems on quadratic equations and provide model answers for them." Based on this prompt, the system generates problems that meet the specified conditions and constitutes an educational assessment test.

[0082] In this way, this invention automates the entire educational evaluation process, reducing the burden on teachers while providing feedback and assignments tailored to each student's learning progress.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1: The user enters the parameters on the terminal.

[0085] The user uses a terminal to input parameters for the assessment test, including the test subject, difficulty level, and number of questions. The terminal receives this information and validates the input values ​​in real time. Specifically, it checks whether the input data is in the correct format and implements a function to notify the user if there is any incorrect data. The input parameters are structured in JSON format or similar and ready to be sent to the server.

[0086] Step 2: The terminal sends parameters to the server.

[0087] The terminal sends the formatted parameter data to the server. HTTP requests are used to securely transfer the data. After transmission, the terminal receives a response from the server indicating the progress of the test generation. This response is used to verify whether the parameters were processed correctly.

[0088] Step 3: The server selects the problem.

[0089] The server parses the received parameters and queries the problem database stored in the information storage device. Here, it performs data retrieval and selection to choose problems that match the parameters. Specifically, it uses SQL queries to filter problems that correspond to the specified subject and difficulty level. This result is prepared as initial data for the exam configuration.

[0090] Step 4: The server generates the test.

[0091] The server supplies the selected set of questions to the AI ​​model, which automatically creates the optimal test configuration. The AI ​​model considers the difficulty balance and subject matter relevance of the selected questions to create the most efficient question arrangement. The generated test is customized to reflect the conditions specified by the teacher.

[0092] Step 5: Send the test from the server to the terminal.

[0093] The server sends the generated test data to the terminal. The terminal analyzes the received data and prepares to display the test questions to the user. Here, a visual layout for data display is set up to provide an environment that makes it easy for students to answer the questions.

[0094] Step 6: Students submit their answers, and their devices send them to the server.

[0095] Students answer the test displayed on their device, and the device sends the answers to the server. The answer data is again structured in JSON format and passes integrity checks before transmission. The device monitors the transmission status to ensure that the data has arrived at the server correctly.

[0096] Step 7: The server automatically generates scoring and feedback.

[0097] The server analyzes the received answer data and scores it by comparing it to a benchmark answer. Here, natural language processing techniques and machine learning algorithms are used to evaluate the accuracy of the answers. Based on the scoring results, a generative AI model is used to generate individual feedback and learning guidelines. This feedback includes explanations for specific problems and recommended learning methods.

[0098] Step 8: Displaying feedback on the terminal

[0099] The server sends the generated feedback and learning guidelines to the device, which then displays them for the user or student to review. The feedback is presented visually in an easy-to-understand manner, providing information that helps improve student learning.

[0100] (Application Example 1)

[0101] 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."

[0102] Traditional education systems have suffered from a decline in the quality and efficiency of education due to the enormous amount of time and effort required for teachers to provide individualized learning guidance to students. Furthermore, there was the challenge of providing students with personalized learning content in a timely manner. To solve these problems and improve the quality of education, an efficient and automated educational assessment and learning support system is necessary.

[0103] 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.

[0104] In this invention, the server includes means for automating educational assessment via an information processing device, means for selecting educational questions based on multiple conditions and generating educational assessment tests, means for automatically scoring and providing feedback based on received answer data, means for delivering personalized learning content, and means for providing individual learning plans according to progress. This makes it possible to provide students with an effective and personalized learning experience while reducing the burden on teachers.

[0105] An "information processing device" is a device such as a computer or server that performs data input, processing, and output.

[0106] "Educational questions" are questions or tasks used as part of tests or quizzes to measure learners' knowledge and understanding.

[0107] "Conditions" refer to the elements used as criteria when selecting educational issues, such as difficulty level and subject matter.

[0108] An "educational assessment test" is an examination structured based on specific purposes and conditions to measure learners' knowledge and understanding.

[0109] "Answer data" refers to information that includes the answers that learners have provided to educational questions.

[0110] A "model answer" is an answer that has been set as the correct and standard answer to an educational question.

[0111] "Automatic grading" is a process in which a computer automatically evaluates a learner's answer by comparing it to a model answer.

[0112] "Feedback" refers to advice and evaluation information provided based on a learner's answers, and is useful for improving their learning.

[0113] A "user interface" is a means by which a user interacts with a system, inputting information and checking results.

[0114] "Personalized learning content" refers to educational materials that are individually tailored to the learner's needs and abilities.

[0115] "Learning history" refers to information that records a learner's past learning activities and progress.

[0116] An "individualized learning plan" is a plan of learning methods and curriculum designed to suit the learner.

[0117] The system for realizing this invention consists of a server acting as an information processing device and a terminal equipped with a user interface. The server executes a program to automate educational assessment, selects educational questions from a database based on specified conditions, and generates an educational assessment test. The server also compares the received answer data with model answers and automatically scores them. The software used is Python and the Django framework. MySQL® is used for database management, and TENSORFLOW® is used for implementing the AI ​​model.

[0118] Users (students or teachers) input learning themes and difficulty levels via their devices, and the server then personalizes and delivers the most suitable learning content based on this information. The devices have iOS or Android® applications installed, allowing users to check their learning history and progress. This enables learners to receive personalized learning plans tailored to their progress.

[0119] For example, if a learner wants to learn the basics of the subject "Science," they enter that information into their device, and the server automatically selects and delivers the appropriate video lectures and practice problems from its database. When the learner answers the practice problems, the server immediately grades them and provides feedback tailored to their level of understanding.

[0120] As an example of a prompt for a generative AI model, we can use the instruction, "Create an AI model that selects the most suitable content from the database based on the learning theme chosen by the user, and provides personalized feedback based on the learning history and evaluation results." This makes it possible to efficiently and effectively support the user's learning experience.

[0121] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0122] Step 1:

[0123] The user enters the learning theme and difficulty level through the terminal's user interface. This input data is sent to the server. The terminal formats this data and prepares it to be sent to the server according to the communication protocol.

[0124] Step 2:

[0125] The server analyzes the received input data and selects educational questions from the database based on the specified criteria. It then executes database queries to search for relevant video lectures and exercises and retrieves the IDs of the selected learning content.

[0126] Step 3:

[0127] The server uses the ID of the acquired learning content to retrieve relevant data (such as the URL of the video file and the quiz content) from the database and prepares to generate a personalized educational assessment test. This ensures that the selected content is optimized for the learner.

[0128] Step 4:

[0129] The generated educational assessment test data is sent to the terminal. The server creates a packet combining the learning content and the test, and sends it to the terminal. The terminal analyzes the received data and displays it on the user interface.

[0130] Step 5:

[0131] The user takes an educational assessment test provided on the device and enters their answers. The device collects the user's answer data and prepares to send it to the server as data.

[0132] Step 6:

[0133] The server automatically scores the received answer data by comparing it with the model answer. It performs comparative calculations on the data, calculates a score based on that, and generates a result. In this process, an AI model evaluates the accuracy of the answer.

[0134] Step 7:

[0135] Based on the scoring results, feedback is automatically generated and sent to the terminal. The server generates data packets to provide the user with the analysis results as feedback and sends them to the terminal. The terminal displays the received data and presents the feedback to the user.

[0136] Step 8:

[0137] The server records the user's learning history and evaluation results, and based on this, generates a personalized learning plan tailored to their progress and provides it to the user's device. This clarifies the direction of future learning, enabling more efficient learning.

[0138] 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.

[0139] This invention aims to further enhance the quality of education and achieve individual optimization by combining an emotion engine with an information processing system that automates educational evaluation. This system enables the automatic generation and scoring of educational evaluation tests, the provision of feedback, and the recognition of the user's emotional state by the emotion engine, as well as the dynamic adjustment of educational content based on that recognition.

[0140] First, the user (teacher) uses a terminal to input the settings information for the educational assessment test. This includes the subject, difficulty level, and number of questions. The input information is sent to the server, which uses this information to select appropriate educational questions from the question database and automatically generates the test. The generated educational assessment test is then sent to the terminal, where the user (teacher) can review the content and make corrections as needed.

[0141] During the test, users (students) answer questions on their devices, and their answer data is sent to the server. The server compares the answer data with model answers and automatically grades the answers. The grading results and feedback are returned to the device, which the user (student) can then review. In addition, the emotion engine recognizes the user's emotional state, such as their level of concentration and tension, through the device's camera and microphone. This information is sent to the server and considered during educational evaluation and feedback.

[0142] For example, if the emotion engine recognizes a user's (student's) facial expression indicating confusion during a math test, the server will adjust the feedback accordingly, providing support such as, "This part might be a little difficult; we'll give you a special hint." Furthermore, if it's determined that the student is struggling with a high-difficulty problem due to anxiety, the system can temporarily adjust the hints or the difficulty level of the problem.

[0143] Furthermore, based on data obtained from the emotion engine, the system analyzes individual learning patterns and provides the optimal learning tasks for the next user to tackle. In this way, the present invention considers the user's psychological state in real time and realizes multifaceted educational support.

[0144] The following describes the processing flow.

[0145] Step 1:

[0146] The user (teacher) uses a terminal to input parameters such as the subject, difficulty level, and number of questions for the educational assessment test. This information is transmitted and transferred to the server.

[0147] Step 2:

[0148] The server searches the problem database based on the received input parameters. It selects educational problems that match the criteria and creates a list.

[0149] Step 3:

[0150] The server automatically generates an educational assessment test based on the selected educational questions. The generated test content is sent to the terminal, making it available for the user (teacher) to review.

[0151] Step 4:

[0152] The user (teacher) reviews the test content generated on their device and makes corrections as needed. The finalized test information is sent to the server and registered.

[0153] Step 5:

[0154] During the exam, users (students) use their devices to answer the exam questions and input their answer data. The entered data is then sent to the server.

[0155] Step 6:

[0156] The server compares the received answer data with the model answer and automatically grades it. The results, along with feedback, are generated and sent back to the terminal.

[0157] Step 7:

[0158] Simultaneously, the emotion engine on the device analyzes the user's (student's) emotional state from their facial expressions and tone of voice. Information such as the student's level of concentration and tension is then transmitted to the server.

[0159] Step 8:

[0160] The server receives information from the emotion engine and adjusts feedback and learning advice as needed. For example, if concentration is waning, it may provide additional hints or adjust the difficulty level of the problem.

[0161] Step 9:

[0162] The server combines educational assessment results and sentiment data to analyze individual learning patterns. Based on these results, it generates optimized learning tasks and sends them to the device. Users (students) can then work on these individual tasks.

[0163] (Example 2)

[0164] 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".

[0165] Improving the quality of education requires individually optimized educational assessments and adjustments to educational content that take into account the user's emotional state. However, conventional systems do not adequately automate or individually optimize educational assessments, and furthermore, they have the challenge of dynamically adjusting educational content that takes user emotions into account.

[0166] 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.

[0167] In this invention, the server includes means for generating educational evaluation tests, means for automatically scoring answer data, and means for adjusting educational content through emotion analysis technology. This enables individually optimized educational support that takes into account the emotional state of each user.

[0168] An "information processing device" is a computing device or equipment for processing digital data, and plays a central role in realizing the automation of educational assessment.

[0169] "Educational issues" refer to questions, tasks, and other materials used in educational assessment tests to measure learners' understanding and skills.

[0170] "Means for generating educational assessment tests" refers to technology that has the function of automatically constructing tests by selecting appropriate educational questions from a question database based on set conditions.

[0171] "Methods for performing automated scoring" refer to technologies that automatically perform the process of comparing received answer data with model answers and calculating scores.

[0172] "Scoring results and feedback" refers to evaluation information such as scores and areas for improvement generated after automatic scoring, which is presented to the learner.

[0173] "Emotion analysis technology" is a technology that recognizes a user's emotional state from their facial expressions and voice, and processes that information as data.

[0174] "Means for dynamically adjusting educational content" refers to technologies that change and adjust the difficulty level of education and the content of feedback in real time based on the user's emotional state.

[0175] "Personalized learning support" refers to support that provides optimal educational content and feedback tailored to each user's abilities and emotional state.

[0176] This invention specifically demonstrates a method for providing individually optimized education through an information processing system that automates educational evaluation. The system mainly consists of a server, terminals used by users (teachers and students), and integrated sentiment analysis technology.

[0177] First, the user (teacher) uses a terminal to input the settings information for the educational assessment test. This input includes the test subject, difficulty level, and number of questions. The terminal sends this information to the server via the user interface. Based on the received information, the server selects appropriate educational questions from the question database and automatically generates the test. This process utilizes high-speed database searching and AI algorithms.

[0178] For the generated exams, users (teachers) can review the content on their devices and correct exam questions as needed. When students take the exam, they use their devices to answer the questions, and their answer data is sent back to the server. The server uses machine learning technology to automatically grade the answers by comparing them to model answers. The grading results and feedback are generated in real time and sent to the user's (student's) device.

[0179] Furthermore, the device is equipped with emotion analysis technology that can recognize the user's emotional state through their facial expressions and voice. This information is sent to a server and used for dynamic adjustment of educational content and individualized optimization of feedback. For example, if the server detects that a student is confused, it can provide special hints as support.

[0180] For example, if a student finds a math problem difficult, the system provides feedback such as, "This part may be difficult; we will provide a special hint." An example of a prompt to input to the generative AI model could be, "Suggest the optimal learning task based on the student's emotional state." In this way, the present invention can provide a learning experience tailored to individual users and improve the quality of education.

[0181] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0182] Step 1:

[0183] The user (teacher) uses a terminal to input setting information for the educational assessment test, such as the test subject, difficulty level, and number of questions. The entered data is immediately sent to the server. The input here is test setting information, and the output is the selection criteria for educational questions. The terminal analyzes the entered data in real time to check for missing required items or logical inconsistencies.

[0184] Step 2:

[0185] The server searches and selects appropriate educational questions from the question database based on the received exam configuration information. High-speed data query processing and conditional filtering are used for the search. This process transforms the input exam configuration information into the output of selected educational questions. The selected questions are then automatically generated as an exam.

[0186] Step 3:

[0187] The generated educational assessment test is sent from the server to the user's (teacher's) terminal. The teacher reviews the test content and makes corrections to the questions if necessary. The input is a selected set of educational questions, and the output is the corrected set of questions. The user can rearrange the questions by dragging and dropping them using the interface, and directly edit the question text.

[0188] Step 4:

[0189] The user (student) answers the exam questions via a terminal. The student's answers are sent from the terminal to the server. Here, the student's answers are the input, and the material for automatic grading is the output. The terminal adds a timestamp when inputting and also records the progress of the answer.

[0190] Step 5:

[0191] The server receives answer data submitted by students and performs automatic scoring by comparing it with model answers. This process involves checking for matches between answer choices and evaluating essay questions using natural language processing. The input is student answer data, and the output is the scoring results and feedback. The server then utilizes a generative AI model to perform the necessary analysis.

[0192] Step 6:

[0193] The device's built-in emotion analysis function analyzes the user's emotional state in real time, measuring concentration levels, stress levels, and other factors. The obtained emotional data is sent to a server. The input here is real-time emotional data, and the output is guidelines for adjusting educational content. The device also performs facial recognition technology for expression analysis and voice tone analysis.

[0194] Step 7:

[0195] The server dynamically adjusts educational content and feedback as needed, based on emotional data and scoring results. For example, if a student is deemed confused, special hints or simple problems are suggested. The input is emotional data and scoring results, and the output is adjusted educational content and feedback. Prompt messages enable the generating AI model to produce appropriate support. In this way, the system achieves individual optimization according to the user's state.

[0196] (Application Example 2)

[0197] 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".

[0198] Traditional educational evaluation systems have a problem in that they provide uniform evaluations and feedback without considering the emotional state of learners, making it difficult to provide individually optimized education. Similarly, in customer service at physical stores, the failure to consider the emotional state of customers can sometimes lead to inappropriate customer service.

[0199] 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.

[0200] In this invention, the server includes an information processing device for automating educational evaluation, an emotion analysis device for recognizing emotional states, means for selecting multiple educational problems based on one or more conditions and automatically generating an educational evaluation test, means for performing automatic scoring by comparing received answer data with model answers, means for generating and presenting scoring results and feedback, means for dynamically adjusting educational content based on emotional data acquired by the emotion analysis device, and means for generating customer service suggestions based on the customer's emotional state and displaying them on an information display device. This enables the provision of individually optimized feedback according to the learner's emotional state and appropriate customer service responses based on the customer's emotional state in physical stores.

[0201] An "information processing device" is a combination of hardware and software for inputting, processing, storing, and outputting data.

[0202] An "emotion analysis device" is a technological device that uses sensors and algorithms to recognize and analyze a person's emotional state.

[0203] An "educational assessment test" is a set of questions and tasks administered to measure a learner's level of understanding and ability.

[0204] "Dynamic adjustment" means instantly changing the content and parameters according to the situation and conditions at hand.

[0205] "Customer service suggestions" refer to guidance provided to customers, indicating information about the products and services offered and suggesting appropriate actions.

[0206] An "information display device" refers to a screen or device used to effectively display digital data.

[0207] In this embodiment, the server first provides a system that links an information processing device for automating educational assessment with an emotion analysis device for recognizing emotional states. The information processing device automatically constructs an educational assessment test for learners by selecting questions based on conditions from a shared question database. The terminal receives answer data and sends it to the server, which compares it with a model answer and performs automatic scoring. The scoring results are sent to the terminal and presented to the learner as feedback.

[0208] Furthermore, the emotion analysis device uses sensors to capture the learner's facial expressions and voice tone, and transmits this data to a server. Emotion analysis is performed using software such as Microsoft® Azure® Face API. This allows the server to adjust the educational content and difficulty level in real time based on the emotion data. In physical stores, the emotion analysis device recognizes the customer's emotional state, generates customer service suggestions based on that, and provides them to employees through an information display device.

[0209] For example, if an emotion analyzer detects that a learner's concentration level has decreased while the server is generating a mathematics education assessment test, the server can take action such as lowering the difficulty level or adding hints. Similarly, in a physical store, if a customer appears anxious, the server can suggest appropriate customer service methods to the employee.

[0210] An example of a prompt message might be: "Analyze the customer's emotional state and offer appropriate customer service suggestions. The customer appears a little anxious."

[0211] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0212] Step 1:

[0213] The server automatically generates an educational assessment test by selecting suitable questions from its question database based on the test settings information received from the terminal. The inputs here include the subject matter, difficulty level, and number of questions specified by the teacher, and the output is the generated educational assessment test. The server then sends this test to the terminal.

[0214] Step 2:

[0215] The user (student) answers the questions on a terminal. The terminal collects the user's answers as data and sends it to the server. The input is the user's answer data, and the output is the answer data sent to the server.

[0216] Step 3:

[0217] The server automatically scores the received answer data by comparing it with the model answer stored in the database. The input is the answer data and the model answer, and the output is the scoring result. Based on the output result, the server generates feedback and sends it to the terminal.

[0218] Step 4:

[0219] The emotion analysis device uses sensors to capture the user's (student's) facial expressions and voice in real time and transmits the data to a server. The input here is the user's facial expression data and voice data, and the output is the analyzed emotion data.

[0220] Step 5:

[0221] The server analyzes the user's current emotional state based on sentiment data and dynamically adjusts the educational content. This includes adjusting the difficulty of questions and providing hints. The input is the analyzed sentiment data, and the output is the adjusted educational content.

[0222] Step 6:

[0223] In physical stores, the terminal receives customer information and emotional data from an emotion analysis device, and sends this data to a server. The input is in-store customer data and emotional state data, and the output is customer service suggestions.

[0224] Step 7:

[0225] The server generates optimal customer service suggestions for the service staff based on the customer's emotional state and displays them on the information display device. The input is customer emotional state data, and the output is the customer service suggestion. It is also possible to use a generation AI model, and a possible prompt message would be, "Analyze the customer's emotional state and provide an appropriate customer service suggestion. The customer seems a little anxious."

[0226] 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.

[0227] 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.

[0228] 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.

[0229] [Second Embodiment]

[0230] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0231] 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.

[0232] 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).

[0233] 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.

[0234] 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.

[0235] 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).

[0236] 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.

[0237] 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.

[0238] 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.

[0239] 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.

[0240] 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.

[0241] 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".

[0242] This invention is an automated educational evaluation system designed to reduce the burden on teachers in educational settings and improve the quality of education. The system aims to automate some of the diverse tasks performed by teachers by using an information processing device to select and automatically evaluate educational issues.

[0243] First, the user (teacher) uses a terminal to input parameters such as the test subject, difficulty level, and number of questions. The terminal sends these inputs to the server, which selects appropriate questions from the question database based on the conditions. Based on the selected questions, the server automatically generates an educational assessment test and sends the test back to the terminal. This process reduces the burden of manual question selection on the teacher.

[0244] Next, students write or type their answers and send the answer data to the server via their devices. The server compares the received answer data with the model answer and automatically grades it. The grading results are returned from the server to the devices, where users (teachers and students) can review them. Furthermore, based on the grading results, the server generates feedback and suggested learning tasks and provides them to the devices. This feedback is important for improving the quality of student learning.

[0245] For example, in a math test, if a user (teacher) requests 10 intermediate-level problems on quadratic equations, the server can select the appropriate problems from the database and automatically assemble an educational assessment test. When students take this test and enter their answers on their devices, the server quickly grades it and provides feedback tailored to each student's level of understanding.

[0246] Furthermore, the system can present individualized learning assignments based on each student's learning history and evaluation results, thereby promoting improved student comprehension. In this way, the present invention provides an innovative means to reduce the workload of teachers and support students' motivation and achievements in learning.

[0247] The following describes the processing flow.

[0248] Step 1:

[0249] The user (teacher) inputs parameters such as the subject, difficulty level, and number of questions for the educational assessment test via their terminal. By clicking the submit button, this information is transferred to the server.

[0250] Step 2:

[0251] The server searches the problem database based on the received parameters. It selects educational problems that match the criteria and creates a list.

[0252] Step 3:

[0253] The server automatically configures the educational assessment test based on the selected educational questions. It then transmits the configured test content to the terminal.

[0254] Step 4:

[0255] The user (teacher) reviews the exam content on their device. They can add, delete, or modify questions as needed. Once the final exam content is confirmed, they instruct the server to save it.

[0256] Step 5:

[0257] The user (student) takes the exam and enters their answers using a terminal. The entered answer data is sent from the terminal to the server.

[0258] Step 6:

[0259] The server compares the received answer data with the model answer and automatically performs the scoring process. Partial credit is also considered during scoring.

[0260] Step 7:

[0261] The server generates the scoring results and sends them to the terminal along with feedback comments.

[0262] Step 8:

[0263] Users (teachers and students) can view grading results and feedback on their devices. Teachers can use this information to provide appropriate support tailored to each student's individual learning progress.

[0264] Step 9:

[0265] The server analyzes each student's evaluation results and learning history, and generates individually optimized learning assignments. The generated assignments are sent to the user (student), who can then review them and engage in self-study.

[0266] (Example 1)

[0267] 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."

[0268] Currently, teachers in schools must spend a great deal of time and effort creating and grading exam questions, and then provide feedback to each student. This increases the burden on teachers, making it difficult to maintain the quality of education. Furthermore, students lack assignments and feedback tailored to their individual learning levels, hindering efficient learning. Therefore, there is a need for a system that automates the educational evaluation process, reduces the burden on teachers, and provides more appropriate learning support to students.

[0269] 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.

[0270] In this invention, the server includes means for selecting questions from an information storage device and automatically generating an evaluation test based on multiple conditions such as the subject, difficulty level, and number of questions of the evaluation test entered by the user; means for mechanically scoring the received answer information by comparing it with a standard answer; means for automatically generating the scoring results and learning guidelines based on those results and presenting them through a display device; and means for providing individualized learning tasks based on the learner's learning history and evaluation results. This makes it possible to streamline the educational evaluation process, significantly reduce the burden on teachers, and provide students with more accurate feedback and learning support.

[0271] "Users" refer to individuals or organizations that use the system to create, manage, and evaluate exams, and typically include educators and teachers.

[0272] An "assessment test" is a set of questions or tasks administered to measure a learner's knowledge and understanding.

[0273] "Conditions" refer to the parameters and criteria considered when creating an exam, specifically including the subject matter, difficulty level, and number of questions.

[0274] An "information storage device" refers to hardware or a system that stores information in digital format and makes it accessible at a later date.

[0275] A "problem" is a question or task presented in a way that requires an answer, and it constitutes part of an evaluation test.

[0276] A "standard answer" refers to a correct or desirable example answer in an assessment test, and serves as a guideline for evaluating students' answers.

[0277] "Mechanical scoring" refers to the process of using computer algorithms to determine how closely an answer matches a standard answer and assign a score accordingly.

[0278] "Feedback" refers to the areas for improvement and learning guidelines given to learners based on the results of an assessment test.

[0279] "Learning guidelines" refer to the materials and assignments suggested to learners to work on next, in order to deepen their understanding.

[0280] This education evaluation automation system mainly consists of three components: a server, a terminal, and a user. The user (teacher) inputs parameters such as the topic, difficulty level, and number of questions related to the test through the terminal. This information is usually collected using software with a user-friendly interface. The terminal organizes this information, structures it in a format such as JSON, and sends it to the server.

[0281] The server analyzes the received parameters and manages the data required for evaluation using appropriate algorithms. Here, it accesses the question storage device and performs query processing to select questions that meet the conditions. Subsequently, a generation AI model generates an optimal test configuration based on the questions. In this process, machine learning and optimization techniques are used to automatically create efficient and accurate test content.

[0282] When the test configuration is completed, the server sends the test data back to the terminal. The terminal presents the test via the user interface, enabling students to answer. The answers are sent from the terminal back to the server again, and the server performs automatic grading based on the answers. Natural language processing technology and other methods are used for grading to compare with the reference answers.

[0283] When grading is completed, the server analyzes the results and uses the generation AI model to generate feedback and additional learning guidelines. This feedback is provided to the user and students through the terminal. Specifically, it includes explanations of the parts where students made mistakes and points to note.

[0284] As a specific example, when the user (teacher) wants to create 10 intermediate-level questions related to "quadratic equations", the following prompt sentence can be used: "Generate a set of 10 intermediate-level quadratic equation questions and also provide model answers for those questions." Based on this prompt sentence, the system generates questions that meet the specified conditions and constructs an education evaluation test.

[0285] In this way, this invention automates the entire education evaluation process, reduces the burden on teachers, and realizes the provision of feedback and tasks according to the learning situation of each student.

[0286] The flow of the specific process in Example 1 will be described with reference to FIG. 11.

[0287] Step 1: The user inputs parameters using a terminal

[0288] The user uses the terminal to input parameters of an evaluation test including the theme, difficulty level, and number of questions of the test. The terminal receives this information and performs real-time verification of the input values. Specifically, a function is implemented to check whether the input data is in the appropriate format and notify the user if there is incorrect data. The input parameters are structured in a format such as JSON and are ready to be sent to the server.

[0289] Step 2: The terminal sends the parameters to the server

[0290] The terminal sends the formatted parameter data to the server. At this time, HTTP requests are used to transfer the data securely. After sending, the progress status of test generation is received from the server as a response. This response is used to check whether the parameters have been correctly processed.

[0291] Step 3: The server selects questions

[0292] The server analyzes the received parameters and queries the question database stored in the information storage device. Here, data search and selection processes are performed to select questions that match the parameters. Specifically, SQL queries are used to filter questions corresponding to the specified theme and difficulty level. This result is prepared as initial data for test configuration.

[0293] Step 4: The server generates a test

[0294] The server supplies the selected set of questions to the AI ​​model, which automatically creates the optimal test configuration. The AI ​​model considers the difficulty balance and subject matter relevance of the selected questions to create the most efficient question arrangement. The generated test is customized to reflect the conditions specified by the teacher.

[0295] Step 5: Send the test from the server to the terminal.

[0296] The server sends the generated test data to the terminal. The terminal analyzes the received data and prepares to display the test questions to the user. Here, a visual layout for data display is set up to provide an environment that makes it easy for students to answer the questions.

[0297] Step 6: Students submit their answers, and their devices send them to the server.

[0298] Students answer the test displayed on their device, and the device sends the answers to the server. The answer data is again structured in JSON format and passes integrity checks before transmission. The device monitors the transmission status to ensure that the data has arrived at the server correctly.

[0299] Step 7: The server automatically generates scoring and feedback.

[0300] The server analyzes the received answer data and scores it by comparing it to a benchmark answer. Here, natural language processing techniques and machine learning algorithms are used to evaluate the accuracy of the answers. Based on the scoring results, a generative AI model is used to generate individual feedback and learning guidelines. This feedback includes explanations for specific problems and recommended learning methods.

[0301] Step 8: Displaying feedback on the terminal

[0302] The server sends the generated feedback and learning guidelines to the device, which then displays them for the user or student to review. The feedback is presented visually in an easy-to-understand manner, providing information that helps improve student learning.

[0303] (Application Example 1)

[0304] 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".

[0305] In a conventional education system, when a teacher provides individual learning guidance to students, a huge amount of time and labor are required, resulting in problems of reduced education quality and efficiency. There is also a problem that it is difficult to appropriately provide personalized learning content to students. To solve these problems and improve the quality of education, an efficient and automated education evaluation and learning support system is required.

[0306] 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.

[0307] In this invention, the server includes means for automating education evaluation via an information processing device, means for selecting education problems based on multiple conditions and generating an education evaluation test, means for automatically grading based on the received answer data and providing feedback, means for distributing personalized learning content, and means for providing an individual learning plan according to the progress. Thereby, it becomes possible to provide an effective and individualized learning experience for students while reducing the burden on teachers.

[0308] The "information processing device" is a device such as a computer or a server, which is a device for inputting, processing, and outputting data.

[0309] An "education problem" is a question or task used as part of a test or quiz for measuring the knowledge and understanding of learners.

[0310] A "condition" is an element used as a criterion when selecting an education problem, such as difficulty level or theme.

[0311] An "educational assessment test" is an examination structured based on specific purposes and conditions to measure learners' knowledge and understanding.

[0312] "Answer data" refers to information that includes the answers that learners have provided to educational questions.

[0313] A "model answer" is an answer that has been set as the correct and standard answer to an educational question.

[0314] "Automatic grading" is a process in which a computer automatically evaluates a learner's answer by comparing it to a model answer.

[0315] "Feedback" refers to advice and evaluation information provided based on a learner's answers, and is useful for improving their learning.

[0316] A "user interface" is a means by which a user interacts with a system, inputting information and checking results.

[0317] "Personalized learning content" refers to educational materials that are individually tailored to the learner's needs and abilities.

[0318] "Learning history" refers to information that records a learner's past learning activities and progress.

[0319] An "individualized learning plan" is a plan of learning methods and curriculum designed to suit the learner.

[0320] The system for realizing this invention consists of a server acting as an information processing device and a terminal equipped with a user interface. The server executes a program to automate educational assessment, selects educational questions from a database based on specified criteria, and generates an educational assessment test. The server also compares the received answer data with model answers and automatically grades them. The software used is Python and the Django framework. MySQL is used for database management, and TensorFlow is used for implementing the AI ​​model.

[0321] Users (students or teachers) input learning topics and difficulty levels via their devices, and the server then personalizes and delivers the most suitable learning content based on this information. The devices have iOS or Android applications installed, allowing users to check their learning history and progress. This enables learners to receive personalized learning plans tailored to their progress.

[0322] For example, if a learner wants to learn the basics of the subject "Science," they enter that information into their device, and the server automatically selects and delivers the appropriate video lectures and practice problems from its database. When the learner answers the practice problems, the server immediately grades them and provides feedback tailored to their level of understanding.

[0323] As an example of a prompt for a generative AI model, we can use the instruction, "Create an AI model that selects the most suitable content from the database based on the learning theme chosen by the user, and provides personalized feedback based on the learning history and evaluation results." This makes it possible to efficiently and effectively support the user's learning experience.

[0324] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0325] Step 1:

[0326] The user enters the learning theme and difficulty level through the terminal's user interface. This input data is sent to the server. The terminal formats this data and prepares it to be sent to the server according to the communication protocol.

[0327] Step 2:

[0328] The server analyzes the received input data and selects educational questions from the database based on the specified criteria. It then executes database queries to search for relevant video lectures and exercises and retrieves the IDs of the selected learning content.

[0329] Step 3:

[0330] The server uses the ID of the acquired learning content to retrieve relevant data (such as the URL of the video file and the quiz content) from the database and prepares to generate a personalized educational assessment test. This ensures that the selected content is optimized for the learner.

[0331] Step 4:

[0332] The generated educational assessment test data is sent to the terminal. The server creates a packet combining the learning content and the test, and sends it to the terminal. The terminal analyzes the received data and displays it on the user interface.

[0333] Step 5:

[0334] The user takes an educational assessment test provided on the device and enters their answers. The device collects the user's answer data and prepares to send it to the server as data.

[0335] Step 6:

[0336] The server automatically scores the received answer data by comparing it with the model answer. It performs comparative calculations on the data, calculates a score based on that, and generates a result. In this process, an AI model evaluates the accuracy of the answer.

[0337] Step 7:

[0338] Based on the scoring results, feedback is automatically generated and sent to the terminal. The server generates data packets to provide the user with the analysis results as feedback and sends them to the terminal. The terminal displays the received data and presents the feedback to the user.

[0339] Step 8:

[0340] The server records the user's learning history and evaluation results, and based on this, generates a personalized learning plan tailored to their progress and provides it to the user's device. This clarifies the direction of future learning, enabling more efficient learning.

[0341] 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.

[0342] This invention aims to further enhance the quality of education and achieve individual optimization by combining an emotion engine with an information processing system that automates educational evaluation. This system enables the automatic generation and scoring of educational evaluation tests, the provision of feedback, and the recognition of the user's emotional state by the emotion engine, as well as the dynamic adjustment of educational content based on that recognition.

[0343] First, the user (teacher) uses a terminal to input the settings information for the educational assessment test. This includes the subject, difficulty level, and number of questions. The input information is sent to the server, which uses this information to select appropriate educational questions from the question database and automatically generates the test. The generated educational assessment test is then sent to the terminal, where the user (teacher) can review the content and make corrections as needed.

[0344] During the test, users (students) answer questions on their devices, and their answer data is sent to the server. The server compares the answer data with model answers and automatically grades the answers. The grading results and feedback are returned to the device, which the user (student) can then review. In addition, the emotion engine recognizes the user's emotional state, such as their level of concentration and tension, through the device's camera and microphone. This information is sent to the server and considered during educational evaluation and feedback.

[0345] For example, if the emotion engine recognizes a user's (student's) facial expression indicating confusion during a math test, the server will adjust the feedback accordingly, providing support such as, "This part might be a little difficult; we'll give you a special hint." Furthermore, if it's determined that the student is struggling with a high-difficulty problem due to anxiety, the system can temporarily adjust the hints or the difficulty level of the problem.

[0346] Furthermore, based on data obtained from the emotion engine, the system analyzes individual learning patterns and provides the optimal learning tasks for the next user to tackle. In this way, the present invention considers the user's psychological state in real time and realizes multifaceted educational support.

[0347] The following describes the processing flow.

[0348] Step 1:

[0349] The user (teacher) uses a terminal to input parameters such as the subject, difficulty level, and number of questions for the educational assessment test. This information is transmitted and transferred to the server.

[0350] Step 2:

[0351] The server searches the problem database based on the received input parameters. It selects educational problems that match the criteria and creates a list.

[0352] Step 3:

[0353] The server automatically generates an educational assessment test based on the selected educational questions. The generated test content is sent to the terminal, making it available for the user (teacher) to review.

[0354] Step 4:

[0355] The user (teacher) reviews the test content generated on their device and makes corrections as needed. The finalized test information is sent to the server and registered.

[0356] Step 5:

[0357] During the exam, users (students) use their devices to answer the exam questions and input their answer data. The entered data is then sent to the server.

[0358] Step 6:

[0359] The server compares the received answer data with the model answer and automatically grades it. The results, along with feedback, are generated and sent back to the terminal.

[0360] Step 7:

[0361] Simultaneously, the emotion engine on the device analyzes the user's (student's) emotional state from their facial expressions and tone of voice. Information such as the student's level of concentration and tension is then transmitted to the server.

[0362] Step 8:

[0363] The server receives information from the emotion engine and adjusts feedback and learning advice as needed. For example, if concentration is waning, it may provide additional hints or adjust the difficulty level of the problem.

[0364] Step 9:

[0365] The server combines educational assessment results and sentiment data to analyze individual learning patterns. Based on these results, it generates optimized learning tasks and sends them to the device. Users (students) can then work on these individual tasks.

[0366] (Example 2)

[0367] 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".

[0368] Improving the quality of education requires individually optimized educational assessments and adjustments to educational content that take into account the user's emotional state. However, conventional systems do not adequately automate or individually optimize educational assessments, and furthermore, they have the challenge of dynamically adjusting educational content that takes user emotions into account.

[0369] 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.

[0370] In this invention, the server includes means for generating educational evaluation tests, means for automatically scoring answer data, and means for adjusting educational content through emotion analysis technology. This enables individually optimized educational support that takes into account the emotional state of each user.

[0371] An "information processing device" is a computing device or equipment for processing digital data, and plays a central role in realizing the automation of educational assessment.

[0372] "Educational issues" refer to questions, tasks, and other materials used in educational assessment tests to measure learners' understanding and skills.

[0373] "Means for generating educational assessment tests" refers to technology that has the function of automatically constructing tests by selecting appropriate educational questions from a question database based on set conditions.

[0374] "Methods for performing automated scoring" refer to technologies that automatically perform the process of comparing received answer data with model answers and calculating scores.

[0375] "Scoring results and feedback" refers to evaluation information such as scores and areas for improvement generated after automatic scoring, which is presented to the learner.

[0376] "Emotion analysis technology" is a technology that recognizes a user's emotional state from their facial expressions and voice, and processes that information as data.

[0377] "Means for dynamically adjusting educational content" refers to technologies that change and adjust the difficulty level of education and the content of feedback in real time based on the user's emotional state.

[0378] "Personalized learning support" refers to support that provides optimal educational content and feedback tailored to each user's abilities and emotional state.

[0379] This invention specifically demonstrates a method for providing individually optimized education through an information processing system that automates educational evaluation. The system mainly consists of a server, terminals used by users (teachers and students), and integrated sentiment analysis technology.

[0380] First, the user (teacher) uses a terminal to input the settings information for the educational assessment test. This input includes the test subject, difficulty level, and number of questions. The terminal sends this information to the server via the user interface. Based on the received information, the server selects appropriate educational questions from the question database and automatically generates the test. This process utilizes high-speed database searching and AI algorithms.

[0381] For the generated exams, users (teachers) can review the content on their devices and correct exam questions as needed. When students take the exam, they use their devices to answer the questions, and their answer data is sent back to the server. The server uses machine learning technology to automatically grade the answers by comparing them to model answers. The grading results and feedback are generated in real time and sent to the user's (student's) device.

[0382] Furthermore, the device is equipped with emotion analysis technology that can recognize the user's emotional state through their facial expressions and voice. This information is sent to a server and used for dynamic adjustment of educational content and individualized optimization of feedback. For example, if the server detects that a student is confused, it can provide special hints as support.

[0383] For example, if a student finds a math problem difficult, the system provides feedback such as, "This part may be difficult; we will provide a special hint." An example of a prompt to input to the generative AI model could be, "Suggest the optimal learning task based on the student's emotional state." In this way, the present invention can provide a learning experience tailored to individual users and improve the quality of education.

[0384] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0385] Step 1:

[0386] The user (teacher) uses a terminal to input setting information for the educational assessment test, such as the test subject, difficulty level, and number of questions. The entered data is immediately sent to the server. The input here is test setting information, and the output is the selection criteria for educational questions. The terminal analyzes the entered data in real time to check for missing required items or logical inconsistencies.

[0387] Step 2:

[0388] The server searches and selects appropriate educational questions from the question database based on the received exam configuration information. High-speed data query processing and conditional filtering are used for the search. This process transforms the input exam configuration information into the output of selected educational questions. The selected questions are then automatically generated as an exam.

[0389] Step 3:

[0390] The generated educational assessment test is sent from the server to the user's (teacher's) terminal. The teacher reviews the test content and makes corrections to the questions if necessary. The input is a selected set of educational questions, and the output is the corrected set of questions. The user can rearrange the questions by dragging and dropping them using the interface, and directly edit the question text.

[0391] Step 4:

[0392] The user (student) answers the exam questions via a terminal. The student's answers are sent from the terminal to the server. Here, the student's answers are the input, and the material for automatic grading is the output. The terminal adds a timestamp when inputting and also records the progress of the answer.

[0393] Step 5:

[0394] The server receives answer data submitted by students and performs automatic scoring by comparing it with model answers. This process involves checking for matches between answer choices and evaluating essay questions using natural language processing. The input is student answer data, and the output is the scoring results and feedback. The server then utilizes a generative AI model to perform the necessary analysis.

[0395] Step 6:

[0396] The device's built-in emotion analysis function analyzes the user's emotional state in real time, measuring concentration levels, stress levels, and other factors. The obtained emotional data is sent to a server. The input here is real-time emotional data, and the output is guidelines for adjusting educational content. The device also performs facial recognition technology for expression analysis and voice tone analysis.

[0397] Step 7:

[0398] The server dynamically adjusts educational content and feedback as needed, based on emotional data and scoring results. For example, if a student is deemed confused, special hints or simple problems are suggested. The input is emotional data and scoring results, and the output is adjusted educational content and feedback. Prompt messages enable the generating AI model to produce appropriate support. In this way, the system achieves individual optimization according to the user's state.

[0399] (Application Example 2)

[0400] 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."

[0401] Traditional educational evaluation systems have a problem in that they provide uniform evaluations and feedback without considering the emotional state of learners, making it difficult to provide individually optimized education. Similarly, in customer service at physical stores, the failure to consider the emotional state of customers can sometimes lead to inappropriate customer service.

[0402] 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.

[0403] In this invention, the server includes an information processing device for automating educational evaluation, an emotion analysis device for recognizing emotional states, means for selecting multiple educational problems based on one or more conditions and automatically generating an educational evaluation test, means for performing automatic scoring by comparing received answer data with model answers, means for generating and presenting scoring results and feedback, means for dynamically adjusting educational content based on emotional data acquired by the emotion analysis device, and means for generating customer service suggestions based on the customer's emotional state and displaying them on an information display device. This enables the provision of individually optimized feedback according to the learner's emotional state and appropriate customer service responses based on the customer's emotional state in physical stores.

[0404] An "information processing device" is a combination of hardware and software for inputting, processing, storing, and outputting data.

[0405] An "emotion analysis device" is a technological device that uses sensors and algorithms to recognize and analyze a person's emotional state.

[0406] An "educational assessment test" is a set of questions and tasks administered to measure a learner's level of understanding and ability.

[0407] "Dynamic adjustment" means instantly changing the content and parameters according to the situation and conditions at hand.

[0408] "Customer service suggestions" refer to guidance provided to customers, indicating information about the products and services offered and suggesting appropriate actions.

[0409] An "information display device" refers to a screen or device used to effectively display digital data.

[0410] In this embodiment, the server first provides a system that links an information processing device for automating educational assessment with an emotion analysis device for recognizing emotional states. The information processing device automatically constructs an educational assessment test for learners by selecting questions based on conditions from a shared question database. The terminal receives answer data and sends it to the server, which compares it with a model answer and performs automatic scoring. The scoring results are sent to the terminal and presented to the learner as feedback.

[0411] Furthermore, the emotion analysis device uses sensors to capture the learner's facial expressions and voice tone, and transmits this data to a server. Emotion analysis is performed using software such as Microsoft Azure's Face API. This allows the server to adjust the educational content and difficulty level in real time based on the emotion data. In physical stores, the emotion analysis device recognizes the customer's emotional state, generates customer service suggestions based on that, and provides them to employees through an information display device.

[0412] For example, if an emotion analyzer detects that a learner's concentration level has decreased while the server is generating a mathematics education assessment test, the server can take action such as lowering the difficulty level or adding hints. Similarly, in a physical store, if a customer appears anxious, the server can suggest appropriate customer service methods to the employee.

[0413] An example of a prompt message might be: "Analyze the customer's emotional state and offer appropriate customer service suggestions. The customer appears a little anxious."

[0414] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0415] Step 1:

[0416] The server automatically generates an educational assessment test by selecting suitable questions from its question database based on the test settings information received from the terminal. The inputs here include the subject matter, difficulty level, and number of questions specified by the teacher, and the output is the generated educational assessment test. The server then sends this test to the terminal.

[0417] Step 2:

[0418] The user (student) answers the questions on a terminal. The terminal collects the user's answers as data and sends it to the server. The input is the user's answer data, and the output is the answer data sent to the server.

[0419] Step 3:

[0420] The server automatically scores the received answer data by comparing it with the model answer stored in the database. The input is the answer data and the model answer, and the output is the scoring result. Based on the output result, the server generates feedback and sends it to the terminal.

[0421] Step 4:

[0422] The emotion analysis device uses sensors to capture the user's (student's) facial expressions and voice in real time and transmits the data to a server. The input here is the user's facial expression data and voice data, and the output is the analyzed emotion data.

[0423] Step 5:

[0424] The server analyzes the user's current emotional state based on sentiment data and dynamically adjusts the educational content. This includes adjusting the difficulty of questions and providing hints. The input is the analyzed sentiment data, and the output is the adjusted educational content.

[0425] Step 6:

[0426] In physical stores, the terminal receives customer information and emotional data from an emotion analysis device, and sends this data to a server. The input is in-store customer data and emotional state data, and the output is customer service suggestions.

[0427] Step 7:

[0428] The server generates optimal customer service suggestions for the service staff based on the customer's emotional state and displays them on the information display device. The input is customer emotional state data, and the output is the customer service suggestion. It is also possible to use a generation AI model, and a possible prompt message would be, "Analyze the customer's emotional state and provide an appropriate customer service suggestion. The customer seems a little anxious."

[0429] 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.

[0430] 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.

[0431] 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.

[0432] [Third Embodiment]

[0433] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0434] 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.

[0435] 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).

[0436] 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.

[0437] 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.

[0438] 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).

[0439] 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.

[0440] 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.

[0441] 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.

[0442] 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.

[0443] 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.

[0444] 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".

[0445] This invention is an automated educational evaluation system designed to reduce the burden on teachers in educational settings and improve the quality of education. The system aims to automate some of the diverse tasks performed by teachers by using an information processing device to select and automatically evaluate educational issues.

[0446] First, the user (teacher) uses a terminal to input parameters such as the test subject, difficulty level, and number of questions. The terminal sends these inputs to the server, which selects appropriate questions from the question database based on the conditions. Based on the selected questions, the server automatically generates an educational assessment test and sends the test back to the terminal. This process reduces the burden of manual question selection on the teacher.

[0447] Next, students write or type their answers and send the answer data to the server via their devices. The server compares the received answer data with the model answer and automatically grades it. The grading results are returned from the server to the devices, where users (teachers and students) can review them. Furthermore, based on the grading results, the server generates feedback and suggested learning tasks and provides them to the devices. This feedback is important for improving the quality of student learning.

[0448] For example, in a math test, if a user (teacher) requests 10 intermediate-level problems on quadratic equations, the server can select the appropriate problems from the database and automatically assemble an educational assessment test. When students take this test and enter their answers on their devices, the server quickly grades it and provides feedback tailored to each student's level of understanding.

[0449] Furthermore, the system can present individualized learning assignments based on each student's learning history and evaluation results, thereby promoting improved student comprehension. In this way, the present invention provides an innovative means to reduce the workload of teachers and support students' motivation and achievements in learning.

[0450] The following describes the processing flow.

[0451] Step 1:

[0452] The user (teacher) inputs parameters such as the subject, difficulty level, and number of questions for the educational assessment test via their terminal. By clicking the submit button, this information is transferred to the server.

[0453] Step 2:

[0454] The server searches the problem database based on the received parameters. It selects educational problems that match the criteria and creates a list.

[0455] Step 3:

[0456] The server automatically configures the educational assessment test based on the selected educational questions. It then transmits the configured test content to the terminal.

[0457] Step 4:

[0458] The user (teacher) reviews the exam content on their device. They can add, delete, or modify questions as needed. Once the final exam content is confirmed, they instruct the server to save it.

[0459] Step 5:

[0460] The user (student) takes the exam and enters their answers using a terminal. The entered answer data is sent from the terminal to the server.

[0461] Step 6:

[0462] The server compares the received answer data with the model answer and automatically performs the scoring process. Partial credit is also considered during scoring.

[0463] Step 7:

[0464] The server generates the scoring results and sends them to the terminal along with feedback comments.

[0465] Step 8:

[0466] Users (teachers and students) can view grading results and feedback on their devices. Teachers can use this information to provide appropriate support tailored to each student's individual learning progress.

[0467] Step 9:

[0468] The server analyzes each student's evaluation results and learning history, and generates individually optimized learning assignments. The generated assignments are sent to the user (student), who can then review them and engage in self-study.

[0469] (Example 1)

[0470] 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."

[0471] Currently, teachers in schools must spend a great deal of time and effort creating and grading exam questions, and then provide feedback to each student. This increases the burden on teachers, making it difficult to maintain the quality of education. Furthermore, students lack assignments and feedback tailored to their individual learning levels, hindering efficient learning. Therefore, there is a need for a system that automates the educational evaluation process, reduces the burden on teachers, and provides more appropriate learning support to students.

[0472] 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.

[0473] In this invention, the server includes means for selecting questions from an information storage device and automatically generating an evaluation test based on multiple conditions such as the subject, difficulty level, and number of questions of the evaluation test entered by the user; means for mechanically scoring the received answer information by comparing it with a standard answer; means for automatically generating the scoring results and learning guidelines based on those results and presenting them through a display device; and means for providing individualized learning tasks based on the learner's learning history and evaluation results. This makes it possible to streamline the educational evaluation process, significantly reduce the burden on teachers, and provide students with more accurate feedback and learning support.

[0474] "Users" refer to individuals or organizations that use the system to create, manage, and evaluate exams, and typically include educators and teachers.

[0475] An "assessment test" is a set of questions or tasks administered to measure a learner's knowledge and understanding.

[0476] "Conditions" refer to the parameters and criteria considered when creating an exam, specifically including the subject matter, difficulty level, and number of questions.

[0477] An "information storage device" refers to hardware or a system that stores information in digital format and makes it accessible at a later date.

[0478] A "problem" is a question or task presented in a way that requires an answer, and it constitutes part of an evaluation test.

[0479] A "standard answer" refers to a correct or desirable example answer in an assessment test, and serves as a guideline for evaluating students' answers.

[0480] "Mechanical scoring" refers to the process of using computer algorithms to determine how closely an answer matches a standard answer and assign a score accordingly.

[0481] "Feedback" refers to the areas for improvement and learning guidelines given to learners based on the results of an assessment test.

[0482] "Learning guidelines" refer to the materials and assignments suggested to learners to work on next, in order to deepen their understanding.

[0483] This automated educational assessment system primarily consists of three components: a server, a terminal, and a user. The user (teacher) inputs parameters related to the test, such as the subject, difficulty level, and number of questions, through the terminal. This information is typically collected using software with a user-friendly interface. The terminal organizes this information, structures it in a format such as JSON, and sends it to the server.

[0484] The server analyzes the received parameters and manages the data necessary for evaluation using appropriate algorithms. It accesses the problem memory and performs query processing to select problems that meet the criteria. Subsequently, a generative AI model generates the optimal test configuration based on the problems. This process utilizes machine learning and optimization techniques to automatically create efficient and highly accurate test content.

[0485] Once the test configuration is complete, the server sends the test data back to the terminal. The terminal presents the test via a user interface, allowing students to answer the questions. The answers are sent back from the terminal to the server, which then performs automated scoring based on the answers. Natural language processing technology is used for scoring, and the answers are compared against a standard answer.

[0486] Once grading is complete, the server analyzes the results and uses a generative AI model to generate feedback and additional learning guidance. This feedback is provided to the user and students via their devices. Specifically, it includes explanations of the areas where students made mistakes and points to pay attention to.

[0487] As a concrete example, if a user (teacher) wants to create 10 intermediate-level problems on "quadratic equations," they would use a prompt like this: "Generate a set of 10 intermediate-level problems on quadratic equations and provide model answers for them." Based on this prompt, the system generates problems that meet the specified conditions and constitutes an educational assessment test.

[0488] In this way, this invention automates the entire educational evaluation process, reducing the burden on teachers while providing feedback and assignments tailored to each student's learning progress.

[0489] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0490] Step 1: The user enters the parameters on the terminal.

[0491] The user uses a terminal to input parameters for the assessment test, including the test subject, difficulty level, and number of questions. The terminal receives this information and validates the input values ​​in real time. Specifically, it checks whether the input data is in the correct format and implements a function to notify the user if there is any incorrect data. The input parameters are structured in JSON format or similar and ready to be sent to the server.

[0492] Step 2: The terminal sends parameters to the server.

[0493] The terminal sends the formatted parameter data to the server. HTTP requests are used to securely transfer the data. After transmission, the terminal receives a response from the server indicating the progress of the test generation. This response is used to verify whether the parameters were processed correctly.

[0494] Step 3: The server selects the problem.

[0495] The server parses the received parameters and queries the problem database stored in the information storage device. Here, it performs data retrieval and selection to choose problems that match the parameters. Specifically, it uses SQL queries to filter problems that correspond to the specified subject and difficulty level. This result is prepared as initial data for the exam configuration.

[0496] Step 4: The server generates the test.

[0497] The server supplies the selected set of questions to the AI ​​model, which automatically creates the optimal test configuration. The AI ​​model considers the difficulty balance and subject matter relevance of the selected questions to create the most efficient question arrangement. The generated test is customized to reflect the conditions specified by the teacher.

[0498] Step 5: Send the test from the server to the terminal.

[0499] The server sends the generated test data to the terminal. The terminal analyzes the received data and prepares to display the test questions to the user. Here, a visual layout for data display is set up to provide an environment that makes it easy for students to answer the questions.

[0500] Step 6: Students submit their answers, and their devices send them to the server.

[0501] Students answer the test displayed on their device, and the device sends the answers to the server. The answer data is again structured in JSON format and passes integrity checks before transmission. The device monitors the transmission status to ensure that the data has arrived at the server correctly.

[0502] Step 7: The server automatically generates scoring and feedback.

[0503] The server analyzes the received answer data and scores it by comparing it to a benchmark answer. Here, natural language processing techniques and machine learning algorithms are used to evaluate the accuracy of the answers. Based on the scoring results, a generative AI model is used to generate individual feedback and learning guidelines. This feedback includes explanations for specific problems and recommended learning methods.

[0504] Step 8: Displaying feedback on the terminal

[0505] The server sends the generated feedback and learning guidelines to the device, which then displays them for the user or student to review. The feedback is presented visually in an easy-to-understand manner, providing information that helps improve student learning.

[0506] (Application Example 1)

[0507] 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."

[0508] Traditional education systems have suffered from a decline in the quality and efficiency of education due to the enormous amount of time and effort required for teachers to provide individualized learning guidance to students. Furthermore, there was the challenge of providing students with personalized learning content in a timely manner. To solve these problems and improve the quality of education, an efficient and automated educational assessment and learning support system is necessary.

[0509] 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.

[0510] In this invention, the server includes means for automating educational assessment via an information processing device, means for selecting educational questions based on multiple conditions and generating educational assessment tests, means for automatically scoring and providing feedback based on received answer data, means for delivering personalized learning content, and means for providing individual learning plans according to progress. This makes it possible to provide students with an effective and personalized learning experience while reducing the burden on teachers.

[0511] An "information processing device" is a device such as a computer or server that performs data input, processing, and output.

[0512] "Educational questions" are questions or tasks used as part of tests or quizzes to measure learners' knowledge and understanding.

[0513] "Conditions" refer to the elements used as criteria when selecting educational issues, such as difficulty level and subject matter.

[0514] An "educational assessment test" is an examination structured based on specific purposes and conditions to measure learners' knowledge and understanding.

[0515] "Answer data" refers to information that includes the answers that learners have provided to educational questions.

[0516] A "model answer" is an answer that has been set as the correct and standard answer to an educational question.

[0517] "Automatic grading" is a process in which a computer automatically evaluates a learner's answer by comparing it to a model answer.

[0518] "Feedback" refers to advice and evaluation information provided based on a learner's answers, and is useful for improving their learning.

[0519] A "user interface" is a means by which a user interacts with a system, inputting information and checking results.

[0520] "Personalized learning content" refers to educational materials that are individually tailored to the learner's needs and abilities.

[0521] "Learning history" refers to information that records a learner's past learning activities and progress.

[0522] An "individualized learning plan" is a plan of learning methods and curriculum designed to suit the learner.

[0523] The system for realizing this invention consists of a server acting as an information processing device and a terminal equipped with a user interface. The server executes a program to automate educational assessment, selects educational questions from a database based on specified criteria, and generates an educational assessment test. The server also compares the received answer data with model answers and automatically grades them. The software used is Python and the Django framework. MySQL is used for database management, and TensorFlow is used for implementing the AI ​​model.

[0524] Users (students or teachers) input learning topics and difficulty levels via their devices, and the server then personalizes and delivers the most suitable learning content based on this information. The devices have iOS or Android applications installed, allowing users to check their learning history and progress. This enables learners to receive personalized learning plans tailored to their progress.

[0525] For example, if a learner wants to learn the basics of the subject "Science," they enter that information into their device, and the server automatically selects and delivers the appropriate video lectures and practice problems from its database. When the learner answers the practice problems, the server immediately grades them and provides feedback tailored to their level of understanding.

[0526] As an example of a prompt for a generative AI model, we can use the instruction, "Create an AI model that selects the most suitable content from the database based on the learning theme chosen by the user, and provides personalized feedback based on the learning history and evaluation results." This makes it possible to efficiently and effectively support the user's learning experience.

[0527] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0528] Step 1:

[0529] The user enters the learning theme and difficulty level through the terminal's user interface. This input data is sent to the server. The terminal formats this data and prepares it to be sent to the server according to the communication protocol.

[0530] Step 2:

[0531] The server analyzes the received input data and selects educational questions from the database based on the specified criteria. It then executes database queries to search for relevant video lectures and exercises and retrieves the IDs of the selected learning content.

[0532] Step 3:

[0533] The server uses the ID of the acquired learning content to retrieve relevant data (such as the URL of the video file and the quiz content) from the database and prepares to generate a personalized educational assessment test. This ensures that the selected content is optimized for the learner.

[0534] Step 4:

[0535] The generated educational assessment test data is sent to the terminal. The server creates a packet combining the learning content and the test, and sends it to the terminal. The terminal analyzes the received data and displays it on the user interface.

[0536] Step 5:

[0537] The user takes an educational assessment test provided on the device and enters their answers. The device collects the user's answer data and prepares to send it to the server as data.

[0538] Step 6:

[0539] The server automatically scores the received answer data by comparing it with the model answer. It performs comparative calculations on the data, calculates a score based on that, and generates a result. In this process, an AI model evaluates the accuracy of the answer.

[0540] Step 7:

[0541] Based on the scoring results, feedback is automatically generated and sent to the terminal. The server generates data packets to provide the user with the analysis results as feedback and sends them to the terminal. The terminal displays the received data and presents the feedback to the user.

[0542] Step 8:

[0543] The server records the user's learning history and evaluation results, and based on this, generates a personalized learning plan tailored to their progress and provides it to the user's device. This clarifies the direction of future learning, enabling more efficient learning.

[0544] 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.

[0545] This invention aims to further enhance the quality of education and achieve individual optimization by combining an emotion engine with an information processing system that automates educational evaluation. This system enables the automatic generation and scoring of educational evaluation tests, the provision of feedback, and the recognition of the user's emotional state by the emotion engine, as well as the dynamic adjustment of educational content based on that recognition.

[0546] First, the user (teacher) uses a terminal to input the settings information for the educational assessment test. This includes the subject, difficulty level, and number of questions. The input information is sent to the server, which uses this information to select appropriate educational questions from the question database and automatically generates the test. The generated educational assessment test is then sent to the terminal, where the user (teacher) can review the content and make corrections as needed.

[0547] During the test, users (students) answer questions on their devices, and their answer data is sent to the server. The server compares the answer data with model answers and automatically grades the answers. The grading results and feedback are returned to the device, which the user (student) can then review. In addition, the emotion engine recognizes the user's emotional state, such as their level of concentration and tension, through the device's camera and microphone. This information is sent to the server and considered during educational evaluation and feedback.

[0548] For example, if the emotion engine recognizes a user's (student's) facial expression indicating confusion during a math test, the server will adjust the feedback accordingly, providing support such as, "This part might be a little difficult; we'll give you a special hint." Furthermore, if it's determined that the student is struggling with a high-difficulty problem due to anxiety, the system can temporarily adjust the hints or the difficulty level of the problem.

[0549] Furthermore, based on data obtained from the emotion engine, the system analyzes individual learning patterns and provides the optimal learning tasks for the next user to tackle. In this way, the present invention considers the user's psychological state in real time and realizes multifaceted educational support.

[0550] The following describes the processing flow.

[0551] Step 1:

[0552] The user (teacher) uses a terminal to input parameters such as the subject, difficulty level, and number of questions for the educational assessment test. This information is transmitted and transferred to the server.

[0553] Step 2:

[0554] The server searches the problem database based on the received input parameters. It selects educational problems that match the criteria and creates a list.

[0555] Step 3:

[0556] The server automatically generates an educational assessment test based on the selected educational questions. The generated test content is sent to the terminal, making it available for the user (teacher) to review.

[0557] Step 4:

[0558] The user (teacher) reviews the test content generated on their device and makes corrections as needed. The finalized test information is sent to the server and registered.

[0559] Step 5:

[0560] During the exam, users (students) use their devices to answer the exam questions and input their answer data. The entered data is then sent to the server.

[0561] Step 6:

[0562] The server compares the received answer data with the model answer and automatically grades it. The results, along with feedback, are generated and sent back to the terminal.

[0563] Step 7:

[0564] Simultaneously, the emotion engine on the device analyzes the user's (student's) emotional state from their facial expressions and tone of voice. Information such as the student's level of concentration and tension is then transmitted to the server.

[0565] Step 8:

[0566] The server receives information from the emotion engine and adjusts feedback and learning advice as needed. For example, if concentration is waning, it may provide additional hints or adjust the difficulty level of the problem.

[0567] Step 9:

[0568] The server combines educational assessment results and sentiment data to analyze individual learning patterns. Based on these results, it generates optimized learning tasks and sends them to the device. Users (students) can then work on these individual tasks.

[0569] (Example 2)

[0570] 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."

[0571] Improving the quality of education requires individually optimized educational assessments and adjustments to educational content that take into account the user's emotional state. However, conventional systems do not adequately automate or individually optimize educational assessments, and furthermore, they have the challenge of dynamically adjusting educational content that takes user emotions into account.

[0572] 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.

[0573] In this invention, the server includes means for generating educational evaluation tests, means for automatically scoring answer data, and means for adjusting educational content through emotion analysis technology. This enables individually optimized educational support that takes into account the emotional state of each user.

[0574] An "information processing device" is a computing device or equipment for processing digital data, and plays a central role in realizing the automation of educational assessment.

[0575] "Educational issues" refer to questions, tasks, and other materials used in educational assessment tests to measure learners' understanding and skills.

[0576] "Means for generating educational assessment tests" refers to technology that has the function of automatically constructing tests by selecting appropriate educational questions from a question database based on set conditions.

[0577] "Methods for performing automated scoring" refer to technologies that automatically perform the process of comparing received answer data with model answers and calculating scores.

[0578] "Scoring results and feedback" refers to evaluation information such as scores and areas for improvement generated after automatic scoring, which is presented to the learner.

[0579] "Emotion analysis technology" is a technology that recognizes a user's emotional state from their facial expressions and voice, and processes that information as data.

[0580] "Means for dynamically adjusting educational content" refers to technologies that change and adjust the difficulty level of education and the content of feedback in real time based on the user's emotional state.

[0581] "Personalized learning support" refers to support that provides optimal educational content and feedback tailored to each user's abilities and emotional state.

[0582] This invention specifically demonstrates a method for providing individually optimized education through an information processing system that automates educational evaluation. The system mainly consists of a server, terminals used by users (teachers and students), and integrated sentiment analysis technology.

[0583] First, the user (teacher) uses a terminal to input the settings information for the educational assessment test. This input includes the test subject, difficulty level, and number of questions. The terminal sends this information to the server via the user interface. Based on the received information, the server selects appropriate educational questions from the question database and automatically generates the test. This process utilizes high-speed database searching and AI algorithms.

[0584] For the generated exams, users (teachers) can review the content on their devices and correct exam questions as needed. When students take the exam, they use their devices to answer the questions, and their answer data is sent back to the server. The server uses machine learning technology to automatically grade the answers by comparing them to model answers. The grading results and feedback are generated in real time and sent to the user's (student's) device.

[0585] Furthermore, the device is equipped with emotion analysis technology that can recognize the user's emotional state through their facial expressions and voice. This information is sent to a server and used for dynamic adjustment of educational content and individualized optimization of feedback. For example, if the server detects that a student is confused, it can provide special hints as support.

[0586] For example, if a student finds a math problem difficult, the system provides feedback such as, "This part may be difficult; we will provide a special hint." An example of a prompt to input to the generative AI model could be, "Suggest the optimal learning task based on the student's emotional state." In this way, the present invention can provide a learning experience tailored to individual users and improve the quality of education.

[0587] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0588] Step 1:

[0589] The user (teacher) uses a terminal to input setting information for the educational assessment test, such as the test subject, difficulty level, and number of questions. The entered data is immediately sent to the server. The input here is test setting information, and the output is the selection criteria for educational questions. The terminal analyzes the entered data in real time to check for missing required items or logical inconsistencies.

[0590] Step 2:

[0591] The server searches and selects appropriate educational questions from the question database based on the received exam configuration information. High-speed data query processing and conditional filtering are used for the search. This process transforms the input exam configuration information into the output of selected educational questions. The selected questions are then automatically generated as an exam.

[0592] Step 3:

[0593] The generated educational assessment test is sent from the server to the user's (teacher's) terminal. The teacher reviews the test content and makes corrections to the questions if necessary. The input is a selected set of educational questions, and the output is the corrected set of questions. The user can rearrange the questions by dragging and dropping them using the interface, and directly edit the question text.

[0594] Step 4:

[0595] The user (student) answers the exam questions via a terminal. The student's answers are sent from the terminal to the server. Here, the student's answers are the input, and the material for automatic grading is the output. The terminal adds a timestamp when inputting and also records the progress of the answer.

[0596] Step 5:

[0597] The server receives answer data submitted by students and performs automatic scoring by comparing it with model answers. This process involves checking for matches between answer choices and evaluating essay questions using natural language processing. The input is student answer data, and the output is the scoring results and feedback. The server then utilizes a generative AI model to perform the necessary analysis.

[0598] Step 6:

[0599] The device's built-in emotion analysis function analyzes the user's emotional state in real time, measuring concentration levels, stress levels, and other factors. The obtained emotional data is sent to a server. The input here is real-time emotional data, and the output is guidelines for adjusting educational content. The device also performs facial recognition technology for expression analysis and voice tone analysis.

[0600] Step 7:

[0601] The server dynamically adjusts educational content and feedback as needed, based on emotional data and scoring results. For example, if a student is deemed confused, special hints or simple problems are suggested. The input is emotional data and scoring results, and the output is adjusted educational content and feedback. Prompt messages enable the generating AI model to produce appropriate support. In this way, the system achieves individual optimization according to the user's state.

[0602] (Application Example 2)

[0603] 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."

[0604] Traditional educational evaluation systems have a problem in that they provide uniform evaluations and feedback without considering the emotional state of learners, making it difficult to provide individually optimized education. Similarly, in customer service at physical stores, the failure to consider the emotional state of customers can sometimes lead to inappropriate customer service.

[0605] 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.

[0606] In this invention, the server includes an information processing device for automating educational evaluation, an emotion analysis device for recognizing emotional states, means for selecting multiple educational problems based on one or more conditions and automatically generating an educational evaluation test, means for performing automatic scoring by comparing received answer data with model answers, means for generating and presenting scoring results and feedback, means for dynamically adjusting educational content based on emotional data acquired by the emotion analysis device, and means for generating customer service suggestions based on the customer's emotional state and displaying them on an information display device. This enables the provision of individually optimized feedback according to the learner's emotional state and appropriate customer service responses based on the customer's emotional state in physical stores.

[0607] An "information processing device" is a combination of hardware and software for inputting, processing, storing, and outputting data.

[0608] An "emotion analysis device" is a technological device that uses sensors and algorithms to recognize and analyze a person's emotional state.

[0609] An "educational assessment test" is a set of questions and tasks administered to measure a learner's level of understanding and ability.

[0610] "Dynamic adjustment" means instantly changing the content and parameters according to the situation and conditions at hand.

[0611] "Customer service suggestions" refer to guidance provided to customers, indicating information about the products and services offered and suggesting appropriate actions.

[0612] An "information display device" refers to a screen or device used to effectively display digital data.

[0613] In this embodiment, the server first provides a system that links an information processing device for automating educational assessment with an emotion analysis device for recognizing emotional states. The information processing device automatically constructs an educational assessment test for learners by selecting questions based on conditions from a shared question database. The terminal receives answer data and sends it to the server, which compares it with a model answer and performs automatic scoring. The scoring results are sent to the terminal and presented to the learner as feedback.

[0614] Furthermore, the emotion analysis device uses sensors to capture the learner's facial expressions and voice tone, and transmits this data to a server. Emotion analysis is performed using software such as Microsoft Azure's Face API. This allows the server to adjust the educational content and difficulty level in real time based on the emotion data. In physical stores, the emotion analysis device recognizes the customer's emotional state, generates customer service suggestions based on that, and provides them to employees through an information display device.

[0615] For example, if an emotion analyzer detects that a learner's concentration level has decreased while the server is generating a mathematics education assessment test, the server can take action such as lowering the difficulty level or adding hints. Similarly, in a physical store, if a customer appears anxious, the server can suggest appropriate customer service methods to the employee.

[0616] An example of a prompt message might be: "Analyze the customer's emotional state and offer appropriate customer service suggestions. The customer appears a little anxious."

[0617] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0618] Step 1:

[0619] The server automatically generates an educational assessment test by selecting suitable questions from its question database based on the test settings information received from the terminal. The inputs here include the subject matter, difficulty level, and number of questions specified by the teacher, and the output is the generated educational assessment test. The server then sends this test to the terminal.

[0620] Step 2:

[0621] The user (student) answers the questions on a terminal. The terminal collects the user's answers as data and sends it to the server. The input is the user's answer data, and the output is the answer data sent to the server.

[0622] Step 3:

[0623] The server automatically scores the received answer data by comparing it with the model answer stored in the database. The input is the answer data and the model answer, and the output is the scoring result. Based on the output result, the server generates feedback and sends it to the terminal.

[0624] Step 4:

[0625] The emotion analysis device uses sensors to capture the user's (student's) facial expressions and voice in real time and transmits the data to a server. The input here is the user's facial expression data and voice data, and the output is the analyzed emotion data.

[0626] Step 5:

[0627] The server analyzes the user's current emotional state based on sentiment data and dynamically adjusts the educational content. This includes adjusting the difficulty of questions and providing hints. The input is the analyzed sentiment data, and the output is the adjusted educational content.

[0628] Step 6:

[0629] In physical stores, the terminal receives customer information and emotional data from an emotion analysis device, and sends this data to a server. The input is in-store customer data and emotional state data, and the output is customer service suggestions.

[0630] Step 7:

[0631] The server generates optimal customer service suggestions for the service staff based on the customer's emotional state and displays them on the information display device. The input is customer emotional state data, and the output is the customer service suggestion. It is also possible to use a generation AI model, and a possible prompt message would be, "Analyze the customer's emotional state and provide an appropriate customer service suggestion. The customer seems a little anxious."

[0632] 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.

[0633] 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.

[0634] 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.

[0635] [Fourth Embodiment]

[0636] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0637] 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.

[0638] 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).

[0639] 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.

[0640] 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.

[0641] 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).

[0642] 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.

[0643] 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.

[0644] 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.

[0645] 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.

[0646] 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.

[0647] 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.

[0648] 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".

[0649] This invention is an automated educational evaluation system designed to reduce the burden on teachers in educational settings and improve the quality of education. The system aims to automate some of the diverse tasks performed by teachers by using an information processing device to select and automatically evaluate educational issues.

[0650] First, the user (teacher) uses a terminal to input parameters such as the test subject, difficulty level, and number of questions. The terminal sends these inputs to the server, which selects appropriate questions from the question database based on the conditions. Based on the selected questions, the server automatically generates an educational assessment test and sends the test back to the terminal. This process reduces the burden of manual question selection on the teacher.

[0651] Next, students write or type their answers and send the answer data to the server via their devices. The server compares the received answer data with the model answer and automatically grades it. The grading results are returned from the server to the devices, where users (teachers and students) can review them. Furthermore, based on the grading results, the server generates feedback and suggested learning tasks and provides them to the devices. This feedback is important for improving the quality of student learning.

[0652] For example, in a math test, if a user (teacher) requests 10 intermediate-level problems on quadratic equations, the server can select the appropriate problems from the database and automatically assemble an educational assessment test. When students take this test and enter their answers on their devices, the server quickly grades it and provides feedback tailored to each student's level of understanding.

[0653] Furthermore, the system can present individualized learning assignments based on each student's learning history and evaluation results, thereby promoting improved student comprehension. In this way, the present invention provides an innovative means to reduce the workload of teachers and support students' motivation and achievements in learning.

[0654] The following describes the processing flow.

[0655] Step 1:

[0656] The user (teacher) inputs parameters such as the subject, difficulty level, and number of questions for the educational assessment test via their terminal. By clicking the submit button, this information is transferred to the server.

[0657] Step 2:

[0658] The server searches the problem database based on the received parameters. It selects educational problems that match the criteria and creates a list.

[0659] Step 3:

[0660] The server automatically configures the educational assessment test based on the selected educational questions. It then transmits the configured test content to the terminal.

[0661] Step 4:

[0662] The user (teacher) reviews the exam content on their device. They can add, delete, or modify questions as needed. Once the final exam content is confirmed, they instruct the server to save it.

[0663] Step 5:

[0664] The user (student) takes the exam and enters their answers using a terminal. The entered answer data is sent from the terminal to the server.

[0665] Step 6:

[0666] The server compares the received answer data with the model answer and automatically performs the scoring process. Partial credit is also considered during scoring.

[0667] Step 7:

[0668] The server generates the scoring results and sends them to the terminal along with feedback comments.

[0669] Step 8:

[0670] Users (teachers and students) can view grading results and feedback on their devices. Teachers can use this information to provide appropriate support tailored to each student's individual learning progress.

[0671] Step 9:

[0672] The server analyzes each student's evaluation results and learning history, and generates individually optimized learning assignments. The generated assignments are sent to the user (student), who can then review them and engage in self-study.

[0673] (Example 1)

[0674] 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".

[0675] Currently, teachers in schools must spend a great deal of time and effort creating and grading exam questions, and then provide feedback to each student. This increases the burden on teachers, making it difficult to maintain the quality of education. Furthermore, students lack assignments and feedback tailored to their individual learning levels, hindering efficient learning. Therefore, there is a need for a system that automates the educational evaluation process, reduces the burden on teachers, and provides more appropriate learning support to students.

[0676] 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.

[0677] In this invention, the server includes means for selecting questions from an information storage device and automatically generating an evaluation test based on multiple conditions such as the subject, difficulty level, and number of questions of the evaluation test entered by the user; means for mechanically scoring the received answer information by comparing it with a standard answer; means for automatically generating the scoring results and learning guidelines based on those results and presenting them through a display device; and means for providing individualized learning tasks based on the learner's learning history and evaluation results. This makes it possible to streamline the educational evaluation process, significantly reduce the burden on teachers, and provide students with more accurate feedback and learning support.

[0678] "Users" refer to individuals or organizations that use the system to create, manage, and evaluate exams, and typically include educators and teachers.

[0679] An "assessment test" is a set of questions or tasks administered to measure a learner's knowledge and understanding.

[0680] "Conditions" refer to the parameters and criteria considered when creating an exam, specifically including the subject matter, difficulty level, and number of questions.

[0681] An "information storage device" refers to hardware or a system that stores information in digital format and makes it accessible at a later date.

[0682] A "problem" is a question or task presented in a way that requires an answer, and it constitutes part of an evaluation test.

[0683] A "standard answer" refers to a correct or desirable example answer in an assessment test, and serves as a guideline for evaluating students' answers.

[0684] "Mechanical scoring" refers to the process of using computer algorithms to determine how closely an answer matches a standard answer and assign a score accordingly.

[0685] "Feedback" refers to the areas for improvement and learning guidelines given to learners based on the results of an assessment test.

[0686] "Learning guidelines" refer to the materials and assignments suggested to learners to work on next, in order to deepen their understanding.

[0687] This automated educational assessment system primarily consists of three components: a server, a terminal, and a user. The user (teacher) inputs parameters related to the test, such as the subject, difficulty level, and number of questions, through the terminal. This information is typically collected using software with a user-friendly interface. The terminal organizes this information, structures it in a format such as JSON, and sends it to the server.

[0688] The server analyzes the received parameters and manages the data necessary for evaluation using appropriate algorithms. It accesses the problem memory and performs query processing to select problems that meet the criteria. Subsequently, a generative AI model generates the optimal test configuration based on the problems. This process utilizes machine learning and optimization techniques to automatically create efficient and highly accurate test content.

[0689] Once the test configuration is complete, the server sends the test data back to the terminal. The terminal presents the test via a user interface, allowing students to answer the questions. The answers are sent back from the terminal to the server, which then performs automated scoring based on the answers. Natural language processing technology is used for scoring, and the answers are compared against a standard answer.

[0690] Once grading is complete, the server analyzes the results and uses a generative AI model to generate feedback and additional learning guidance. This feedback is provided to the user and students via their devices. Specifically, it includes explanations of the areas where students made mistakes and points to pay attention to.

[0691] As a concrete example, if a user (teacher) wants to create 10 intermediate-level problems on "quadratic equations," they would use a prompt like this: "Generate a set of 10 intermediate-level problems on quadratic equations and provide model answers for them." Based on this prompt, the system generates problems that meet the specified conditions and constitutes an educational assessment test.

[0692] In this way, this invention automates the entire educational evaluation process, reducing the burden on teachers while providing feedback and assignments tailored to each student's learning progress.

[0693] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0694] Step 1: The user enters the parameters on the terminal.

[0695] The user uses a terminal to input parameters for the assessment test, including the test subject, difficulty level, and number of questions. The terminal receives this information and validates the input values ​​in real time. Specifically, it checks whether the input data is in the correct format and implements a function to notify the user if there is any incorrect data. The input parameters are structured in JSON format or similar and ready to be sent to the server.

[0696] Step 2: The terminal sends parameters to the server.

[0697] The terminal sends the formatted parameter data to the server. HTTP requests are used to securely transfer the data. After transmission, the terminal receives a response from the server indicating the progress of the test generation. This response is used to verify whether the parameters were processed correctly.

[0698] Step 3: The server selects the problem.

[0699] The server parses the received parameters and queries the problem database stored in the information storage device. Here, it performs data retrieval and selection to choose problems that match the parameters. Specifically, it uses SQL queries to filter problems that correspond to the specified subject and difficulty level. This result is prepared as initial data for the exam configuration.

[0700] Step 4: The server generates the test.

[0701] The server supplies the selected set of questions to the AI ​​model, which automatically creates the optimal test configuration. The AI ​​model considers the difficulty balance and subject matter relevance of the selected questions to create the most efficient question arrangement. The generated test is customized to reflect the conditions specified by the teacher.

[0702] Step 5: Send the test from the server to the terminal.

[0703] The server sends the generated test data to the terminal. The terminal analyzes the received data and prepares to display the test questions to the user. Here, a visual layout for data display is set up to provide an environment that makes it easy for students to answer the questions.

[0704] Step 6: Students submit their answers, and their devices send them to the server.

[0705] Students answer the test displayed on their device, and the device sends the answers to the server. The answer data is again structured in JSON format and passes integrity checks before transmission. The device monitors the transmission status to ensure that the data has arrived at the server correctly.

[0706] Step 7: The server automatically generates scoring and feedback.

[0707] The server analyzes the received answer data and scores it by comparing it to a benchmark answer. Here, natural language processing techniques and machine learning algorithms are used to evaluate the accuracy of the answers. Based on the scoring results, a generative AI model is used to generate individual feedback and learning guidelines. This feedback includes explanations for specific problems and recommended learning methods.

[0708] Step 8: Displaying feedback on the terminal

[0709] The server sends the generated feedback and learning guidelines to the device, which then displays them for the user or student to review. The feedback is presented visually in an easy-to-understand manner, providing information that helps improve student learning.

[0710] (Application Example 1)

[0711] 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".

[0712] Traditional education systems have suffered from a decline in the quality and efficiency of education due to the enormous amount of time and effort required for teachers to provide individualized learning guidance to students. Furthermore, there was the challenge of providing students with personalized learning content in a timely manner. To solve these problems and improve the quality of education, an efficient and automated educational assessment and learning support system is necessary.

[0713] 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.

[0714] In this invention, the server includes means for automating educational assessment via an information processing device, means for selecting educational questions based on multiple conditions and generating educational assessment tests, means for automatically scoring and providing feedback based on received answer data, means for delivering personalized learning content, and means for providing individual learning plans according to progress. This makes it possible to provide students with an effective and personalized learning experience while reducing the burden on teachers.

[0715] An "information processing device" is a device such as a computer or server that performs data input, processing, and output.

[0716] "Educational questions" are questions or tasks used as part of tests or quizzes to measure learners' knowledge and understanding.

[0717] "Conditions" refer to the elements used as criteria when selecting educational issues, such as difficulty level and subject matter.

[0718] An "educational assessment test" is an examination structured based on specific purposes and conditions to measure learners' knowledge and understanding.

[0719] "Answer data" refers to information that includes the answers that learners have provided to educational questions.

[0720] A "model answer" is an answer that has been set as the correct and standard answer to an educational question.

[0721] "Automatic grading" is a process in which a computer automatically evaluates a learner's answer by comparing it to a model answer.

[0722] "Feedback" refers to advice and evaluation information provided based on a learner's answers, and is useful for improving their learning.

[0723] A "user interface" is a means by which a user interacts with a system, inputting information and checking results.

[0724] "Personalized learning content" refers to educational materials that are individually tailored to the learner's needs and abilities.

[0725] "Learning history" refers to information that records a learner's past learning activities and progress.

[0726] An "individualized learning plan" is a plan of learning methods and curriculum designed to suit the learner.

[0727] The system for realizing this invention consists of a server acting as an information processing device and a terminal equipped with a user interface. The server executes a program to automate educational assessment, selects educational questions from a database based on specified criteria, and generates an educational assessment test. The server also compares the received answer data with model answers and automatically grades them. The software used is Python and the Django framework. MySQL is used for database management, and TensorFlow is used for implementing the AI ​​model.

[0728] Users (students or teachers) input learning topics and difficulty levels via their devices, and the server then personalizes and delivers the most suitable learning content based on this information. The devices have iOS or Android applications installed, allowing users to check their learning history and progress. This enables learners to receive personalized learning plans tailored to their progress.

[0729] For example, if a learner wants to learn the basics of the subject "Science," they enter that information into their device, and the server automatically selects and delivers the appropriate video lectures and practice problems from its database. When the learner answers the practice problems, the server immediately grades them and provides feedback tailored to their level of understanding.

[0730] As an example of a prompt for a generative AI model, we can use the instruction, "Create an AI model that selects the most suitable content from the database based on the learning theme chosen by the user, and provides personalized feedback based on the learning history and evaluation results." This makes it possible to efficiently and effectively support the user's learning experience.

[0731] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0732] Step 1:

[0733] The user enters the learning theme and difficulty level through the terminal's user interface. This input data is sent to the server. The terminal formats this data and prepares it to be sent to the server according to the communication protocol.

[0734] Step 2:

[0735] The server analyzes the received input data and selects educational questions from the database based on the specified criteria. It then executes database queries to search for relevant video lectures and exercises and retrieves the IDs of the selected learning content.

[0736] Step 3:

[0737] The server uses the ID of the acquired learning content to retrieve relevant data (such as the URL of the video file and the quiz content) from the database and prepares to generate a personalized educational assessment test. This ensures that the selected content is optimized for the learner.

[0738] Step 4:

[0739] The generated educational assessment test data is sent to the terminal. The server creates a packet combining the learning content and the test, and sends it to the terminal. The terminal analyzes the received data and displays it on the user interface.

[0740] Step 5:

[0741] The user takes an educational assessment test provided on the device and enters their answers. The device collects the user's answer data and prepares to send it to the server as data.

[0742] Step 6:

[0743] The server automatically scores the received answer data by comparing it with the model answer. It performs comparative calculations on the data, calculates a score based on that, and generates a result. In this process, an AI model evaluates the accuracy of the answer.

[0744] Step 7:

[0745] Based on the scoring results, feedback is automatically generated and sent to the terminal. The server generates data packets to provide the user with the analysis results as feedback and sends them to the terminal. The terminal displays the received data and presents the feedback to the user.

[0746] Step 8:

[0747] The server records the user's learning history and evaluation results, and based on this, generates a personalized learning plan tailored to their progress and provides it to the user's device. This clarifies the direction of future learning, enabling more efficient learning.

[0748] 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.

[0749] This invention aims to further enhance the quality of education and achieve individual optimization by combining an emotion engine with an information processing system that automates educational evaluation. This system enables the automatic generation and scoring of educational evaluation tests, the provision of feedback, and the recognition of the user's emotional state by the emotion engine, as well as the dynamic adjustment of educational content based on that recognition.

[0750] First, the user (teacher) uses a terminal to input the settings information for the educational assessment test. This includes the subject, difficulty level, and number of questions. The input information is sent to the server, which uses this information to select appropriate educational questions from the question database and automatically generates the test. The generated educational assessment test is then sent to the terminal, where the user (teacher) can review the content and make corrections as needed.

[0751] During the test, users (students) answer questions on their devices, and their answer data is sent to the server. The server compares the answer data with model answers and automatically grades the answers. The grading results and feedback are returned to the device, which the user (student) can then review. In addition, the emotion engine recognizes the user's emotional state, such as their level of concentration and tension, through the device's camera and microphone. This information is sent to the server and considered during educational evaluation and feedback.

[0752] For example, if the emotion engine recognizes a user's (student's) facial expression indicating confusion during a math test, the server will adjust the feedback accordingly, providing support such as, "This part might be a little difficult; we'll give you a special hint." Furthermore, if it's determined that the student is struggling with a high-difficulty problem due to anxiety, the system can temporarily adjust the hints or the difficulty level of the problem.

[0753] Furthermore, based on data obtained from the emotion engine, the system analyzes individual learning patterns and provides the optimal learning tasks for the next user to tackle. In this way, the present invention considers the user's psychological state in real time and realizes multifaceted educational support.

[0754] The following describes the processing flow.

[0755] Step 1:

[0756] The user (teacher) uses a terminal to input parameters such as the subject, difficulty level, and number of questions for the educational assessment test. This information is transmitted and transferred to the server.

[0757] Step 2:

[0758] The server searches the problem database based on the received input parameters. It selects educational problems that match the criteria and creates a list.

[0759] Step 3:

[0760] The server automatically generates an educational assessment test based on the selected educational questions. The generated test content is sent to the terminal, making it available for the user (teacher) to review.

[0761] Step 4:

[0762] The user (teacher) reviews the test content generated on their device and makes corrections as needed. The finalized test information is sent to the server and registered.

[0763] Step 5:

[0764] During the exam, users (students) use their devices to answer the exam questions and input their answer data. The entered data is then sent to the server.

[0765] Step 6:

[0766] The server compares the received answer data with the model answer and automatically grades it. The results, along with feedback, are generated and sent back to the terminal.

[0767] Step 7:

[0768] Simultaneously, the emotion engine on the device analyzes the user's (student's) emotional state from their facial expressions and tone of voice. Information such as the student's level of concentration and tension is then transmitted to the server.

[0769] Step 8:

[0770] The server receives information from the emotion engine and adjusts feedback and learning advice as needed. For example, if concentration is waning, it may provide additional hints or adjust the difficulty level of the problem.

[0771] Step 9:

[0772] The server combines educational assessment results and sentiment data to analyze individual learning patterns. Based on these results, it generates optimized learning tasks and sends them to the device. Users (students) can then work on these individual tasks.

[0773] (Example 2)

[0774] 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".

[0775] Improving the quality of education requires individually optimized educational assessments and adjustments to educational content that take into account the user's emotional state. However, conventional systems do not adequately automate or individually optimize educational assessments, and furthermore, they have the challenge of dynamically adjusting educational content that takes user emotions into account.

[0776] 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.

[0777] In this invention, the server includes means for generating educational evaluation tests, means for automatically scoring answer data, and means for adjusting educational content through emotion analysis technology. This enables individually optimized educational support that takes into account the emotional state of each user.

[0778] An "information processing device" is a computing device or equipment for processing digital data, and plays a central role in realizing the automation of educational assessment.

[0779] "Educational issues" refer to questions, tasks, and other materials used in educational assessment tests to measure learners' understanding and skills.

[0780] "Means for generating educational assessment tests" refers to technology that has the function of automatically constructing tests by selecting appropriate educational questions from a question database based on set conditions.

[0781] "Methods for performing automated scoring" refer to technologies that automatically perform the process of comparing received answer data with model answers and calculating scores.

[0782] "Scoring results and feedback" refers to evaluation information such as scores and areas for improvement generated after automatic scoring, which is presented to the learner.

[0783] "Emotion analysis technology" is a technology that recognizes a user's emotional state from their facial expressions and voice, and processes that information as data.

[0784] "Means for dynamically adjusting educational content" refers to technologies that change and adjust the difficulty level of education and the content of feedback in real time based on the user's emotional state.

[0785] "Personalized learning support" refers to support that provides optimal educational content and feedback tailored to each user's abilities and emotional state.

[0786] This invention specifically demonstrates a method for providing individually optimized education through an information processing system that automates educational evaluation. The system mainly consists of a server, terminals used by users (teachers and students), and integrated sentiment analysis technology.

[0787] First, the user (teacher) uses a terminal to input the settings information for the educational assessment test. This input includes the test subject, difficulty level, and number of questions. The terminal sends this information to the server via the user interface. Based on the received information, the server selects appropriate educational questions from the question database and automatically generates the test. This process utilizes high-speed database searching and AI algorithms.

[0788] For the generated exams, users (teachers) can review the content on their devices and correct exam questions as needed. When students take the exam, they use their devices to answer the questions, and their answer data is sent back to the server. The server uses machine learning technology to automatically grade the answers by comparing them to model answers. The grading results and feedback are generated in real time and sent to the user's (student's) device.

[0789] Furthermore, the device is equipped with emotion analysis technology that can recognize the user's emotional state through their facial expressions and voice. This information is sent to a server and used for dynamic adjustment of educational content and individualized optimization of feedback. For example, if the server detects that a student is confused, it can provide special hints as support.

[0790] For example, if a student finds a math problem difficult, the system provides feedback such as, "This part may be difficult; we will provide a special hint." An example of a prompt to input to the generative AI model could be, "Suggest the optimal learning task based on the student's emotional state." In this way, the present invention can provide a learning experience tailored to individual users and improve the quality of education.

[0791] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0792] Step 1:

[0793] The user (teacher) uses a terminal to input setting information for the educational assessment test, such as the test subject, difficulty level, and number of questions. The entered data is immediately sent to the server. The input here is test setting information, and the output is the selection criteria for educational questions. The terminal analyzes the entered data in real time to check for missing required items or logical inconsistencies.

[0794] Step 2:

[0795] The server searches and selects appropriate educational questions from the question database based on the received exam configuration information. High-speed data query processing and conditional filtering are used for the search. This process transforms the input exam configuration information into the output of selected educational questions. The selected questions are then automatically generated as an exam.

[0796] Step 3:

[0797] The generated educational assessment test is sent from the server to the user's (teacher's) terminal. The teacher reviews the test content and makes corrections to the questions if necessary. The input is a selected set of educational questions, and the output is the corrected set of questions. The user can rearrange the questions by dragging and dropping them using the interface, and directly edit the question text.

[0798] Step 4:

[0799] The user (student) answers the exam questions via a terminal. The student's answers are sent from the terminal to the server. Here, the student's answers are the input, and the material for automatic grading is the output. The terminal adds a timestamp when inputting and also records the progress of the answer.

[0800] Step 5:

[0801] The server receives answer data submitted by students and performs automatic scoring by comparing it with model answers. This process involves checking for matches between answer choices and evaluating essay questions using natural language processing. The input is student answer data, and the output is the scoring results and feedback. The server then utilizes a generative AI model to perform the necessary analysis.

[0802] Step 6:

[0803] The device's built-in emotion analysis function analyzes the user's emotional state in real time, measuring concentration levels, stress levels, and other factors. The obtained emotional data is sent to a server. The input here is real-time emotional data, and the output is guidelines for adjusting educational content. The device also performs facial recognition technology for expression analysis and voice tone analysis.

[0804] Step 7:

[0805] The server dynamically adjusts educational content and feedback as needed, based on emotional data and scoring results. For example, if a student is deemed confused, special hints or simple problems are suggested. The input is emotional data and scoring results, and the output is adjusted educational content and feedback. Prompt messages enable the generating AI model to produce appropriate support. In this way, the system achieves individual optimization according to the user's state.

[0806] (Application Example 2)

[0807] 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".

[0808] Traditional educational evaluation systems have a problem in that they provide uniform evaluations and feedback without considering the emotional state of learners, making it difficult to provide individually optimized education. Similarly, in customer service at physical stores, the failure to consider the emotional state of customers can sometimes lead to inappropriate customer service.

[0809] 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.

[0810] In this invention, the server includes an information processing device for automating educational evaluation, an emotion analysis device for recognizing emotional states, means for selecting multiple educational problems based on one or more conditions and automatically generating an educational evaluation test, means for performing automatic scoring by comparing received answer data with model answers, means for generating and presenting scoring results and feedback, means for dynamically adjusting educational content based on emotional data acquired by the emotion analysis device, and means for generating customer service suggestions based on the customer's emotional state and displaying them on an information display device. This enables the provision of individually optimized feedback according to the learner's emotional state and appropriate customer service responses based on the customer's emotional state in physical stores.

[0811] An "information processing device" is a combination of hardware and software for inputting, processing, storing, and outputting data.

[0812] An "emotion analysis device" is a technological device that uses sensors and algorithms to recognize and analyze a person's emotional state.

[0813] An "educational assessment test" is a set of questions and tasks administered to measure a learner's level of understanding and ability.

[0814] "Dynamic adjustment" means instantly changing the content and parameters according to the situation and conditions at hand.

[0815] "Customer service suggestions" refer to guidance provided to customers, indicating information about the products and services offered and suggesting appropriate actions.

[0816] An "information display device" refers to a screen or device used to effectively display digital data.

[0817] In this embodiment, the server first provides a system that links an information processing device for automating educational assessment with an emotion analysis device for recognizing emotional states. The information processing device automatically constructs an educational assessment test for learners by selecting questions based on conditions from a shared question database. The terminal receives answer data and sends it to the server, which compares it with a model answer and performs automatic scoring. The scoring results are sent to the terminal and presented to the learner as feedback.

[0818] Furthermore, the emotion analysis device uses sensors to capture the learner's facial expressions and voice tone, and transmits this data to a server. Emotion analysis is performed using software such as Microsoft Azure's Face API. This allows the server to adjust the educational content and difficulty level in real time based on the emotion data. In physical stores, the emotion analysis device recognizes the customer's emotional state, generates customer service suggestions based on that, and provides them to employees through an information display device.

[0819] For example, if an emotion analyzer detects that a learner's concentration level has decreased while the server is generating a mathematics education assessment test, the server can take action such as lowering the difficulty level or adding hints. Similarly, in a physical store, if a customer appears anxious, the server can suggest appropriate customer service methods to the employee.

[0820] An example of a prompt message might be: "Analyze the customer's emotional state and offer appropriate customer service suggestions. The customer appears a little anxious."

[0821] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0822] Step 1:

[0823] The server automatically generates an educational assessment test by selecting suitable questions from its question database based on the test settings information received from the terminal. The inputs here include the subject matter, difficulty level, and number of questions specified by the teacher, and the output is the generated educational assessment test. The server then sends this test to the terminal.

[0824] Step 2:

[0825] The user (student) answers the questions on a terminal. The terminal collects the user's answers as data and sends it to the server. The input is the user's answer data, and the output is the answer data sent to the server.

[0826] Step 3:

[0827] The server automatically scores the received answer data by comparing it with the model answer stored in the database. The input is the answer data and the model answer, and the output is the scoring result. Based on the output result, the server generates feedback and sends it to the terminal.

[0828] Step 4:

[0829] The emotion analysis device uses sensors to capture the user's (student's) facial expressions and voice in real time and transmits the data to a server. The input here is the user's facial expression data and voice data, and the output is the analyzed emotion data.

[0830] Step 5:

[0831] The server analyzes the user's current emotional state based on sentiment data and dynamically adjusts the educational content. This includes adjusting the difficulty of questions and providing hints. The input is the analyzed sentiment data, and the output is the adjusted educational content.

[0832] Step 6:

[0833] In physical stores, the terminal receives customer information and emotional data from an emotion analysis device, and sends this data to a server. The input is in-store customer data and emotional state data, and the output is customer service suggestions.

[0834] Step 7:

[0835] The server generates optimal customer service suggestions for the service staff based on the customer's emotional state and displays them on the information display device. The input is customer emotional state data, and the output is the customer service suggestion. It is also possible to use a generation AI model, and a possible prompt message would be, "Analyze the customer's emotional state and provide an appropriate customer service suggestion. The customer seems a little anxious."

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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."

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] The following is further disclosed regarding the embodiments described above.

[0858] (Claim 1)

[0859] Equipped with an information processing device for automating educational evaluation,

[0860] A means for selecting multiple educational issues based on one or more conditions and automatically generating an educational assessment test,

[0861] A means of performing automatic scoring by comparing the received answer data with the model answer,

[0862] A system including means for generating and presenting scoring results and feedback.

[0863] (Claim 2)

[0864] The system according to claim 1, comprising means for analyzing individual learning patterns based on the results of educational evaluation and providing optimal learning tasks.

[0865] (Claim 3)

[0866] The system according to claim 1, further comprising means for using a shared question database when generating educational evaluation tests.

[0867] "Example 1"

[0868] (Claim 1)

[0869] A means for automatically generating an evaluation test by selecting questions from an information storage device based on multiple conditions such as the subject, difficulty level, and number of questions of the evaluation test entered by the user,

[0870] A method for mechanically scoring based on received answer information by comparing it with the standard answer,

[0871] A means for automatically generating scoring results and learning guidelines based on those results, and presenting them via a display device,

[0872] A means of providing individualized learning assignments based on learners' learning history and evaluation results,

[0873] A system that includes this.

[0874] (Claim 2)

[0875] The system according to claim 1, comprising means for utilizing a shared problem memory device when generating evaluation tests.

[0876] (Claim 3)

[0877] The system according to claim 1, comprising means for optimizing the automatic construction of exam questions and the generation of learning guidelines using generation AI technology.

[0878] "Application Example 1"

[0879] (Claim 1)

[0880] Equipped with an information processing device for automating educational evaluation,

[0881] A means for selecting multiple educational issues based on one or more conditions and automatically generating an educational assessment test,

[0882] A means of performing automatic scoring by comparing the received answer data with the model answer,

[0883] A means for generating and presenting scoring results and feedback,

[0884] A means for inputting learning themes and levels via a user interface,

[0885] A means of delivering personalized learning content,

[0886] A means of automatically evaluating quiz answers and providing feedback,

[0887] A means of managing learning history and providing individualized learning plans according to progress,

[0888] A system that includes this.

[0889] (Claim 2)

[0890] The system according to claim 1, comprising means for analyzing individual learning patterns based on the results of educational evaluations and providing optimal learning tasks, and means for delivering personalized learning content.

[0891] (Claim 3)

[0892] The system according to claim 1, further comprising means for using a shared question database when generating educational evaluation tests, and means for providing individualized learning plans according to progress.

[0893] "Example 2 of combining an emotion engine"

[0894] (Claim 1)

[0895] Equipped with an information processing device for automating educational evaluation,

[0896] A means for selecting multiple educational issues based on one or more conditions and automatically generating an educational assessment test,

[0897] A means of performing automatic scoring by comparing the received answer data with the model answer,

[0898] A means for generating and presenting scoring results and feedback,

[0899] A means of recognizing the user's emotional state using emotion analysis technology and dynamically adjusting educational content,

[0900] A means of providing personalized learning support by adjusting feedback based on received emotional data,

[0901] A system that includes this.

[0902] (Claim 2)

[0903] The system according to claim 1, comprising means for analyzing individual learning patterns and providing optimal learning tasks based on the results of educational evaluations and emotional state data.

[0904] (Claim 3)

[0905] The system according to claim 1, further comprising means for using a shared question database when generating educational evaluation tests, and means for dynamically adjusting educational evaluations using sentiment analysis data.

[0906] "Application example 2 when combining with an emotional engine"

[0907] (Claim 1)

[0908] It is equipped with an information processing device for automating educational evaluation and an emotion analysis device for recognizing emotional states.

[0909] A means for selecting multiple educational issues based on one or more conditions and automatically generating an educational assessment test,

[0910] A means of performing automatic scoring by comparing the received answer data with the model answer,

[0911] A means for generating and presenting scoring results and feedback,

[0912] A means for dynamically adjusting educational content based on emotional data acquired by an emotion analysis device,

[0913] A system that includes means for generating customer service suggestions based on the customer's emotional state and displaying them on an information display device.

[0914] (Claim 2)

[0915] The system according to claim 1, comprising means for analyzing individual learning patterns and providing optimal learning tasks based on the results of educational evaluations and emotional data.

[0916] (Claim 3)

[0917] The system according to claim 1, further comprising means for using a shared problem database and an emotion recognition database when generating educational evaluation tests and customer service suggestions. [Explanation of Symbols]

[0918] 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. Equipped with an information processing device for automating educational evaluation, A means for selecting multiple educational issues based on one or more conditions and automatically generating an educational assessment test, A means of performing automatic scoring by comparing the received answer data with the model answer, A system including means for generating and presenting scoring results and feedback.

2. The system according to claim 1, comprising means for analyzing individual learning patterns based on the results of educational evaluation and providing optimal learning tasks.

3. The system according to claim 1, further comprising means for using a shared question database when generating educational evaluation tests.

Images