system

Abstract

We provide the system. [Solution] A means of storing the analyzed educational information in a database, A means for generating new test questions using a generation device, A means of identifying areas of weakness based on the answer information of individual learners, A means of providing a learning plan based on identified areas of weakness, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in 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] Problems faced by modern learners include that it is economically and spatially difficult to collect a huge amount of reference materials and past problem sets in physical form, and there is a lack of a mechanism to effectively provide problems suitable for individual learners. In addition, since it is difficult for learners to accurately grasp their own weaknesses and respond individually, a method for improving learning efficiency is required.

Means for Solving the Problems

[0005] This invention creates new test questions using a generation device and identifies learners' weaknesses by analyzing their answer information using an analysis device. Furthermore, by providing a system that offers individually optimized learning plans based on this, learners can efficiently improve their academic ability and effectively prepare for exams. This system includes means for storing educational information in a database, means for generating questions using a generation device, means for identifying learners' weak areas, and means for providing learning plans based on the identified weak areas.

[0006] "Analyzed educational information" refers to learning-related data, such as key concepts and question trends extracted from textbooks and past exam questions.

[0007] "Means of storing in a database" refers to methods or devices for storing collected educational information in a standardized format and making it easily accessible.

[0008] "Means for generating new test questions using a generation device" refers to methods or devices that use algorithms to create questions of new formats and content based on analyzed educational information.

[0009] "Means for identifying weak areas based on individual learners' answer information" refers to methods and devices for analyzing answer data from problems solved by learners to identify areas of incorrect answers or insufficient understanding.

[0010] "Means of providing a learning plan" refers to methods and devices that present learners with optimized problems and learning schedules based on their identified areas of weakness. [Brief explanation of the drawing]

[0011] [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] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0018] 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."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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".

[0032] This invention provides a system that analyzes educational information and generates new test questions. This system operates based on the interaction between a server, a terminal, and a user, and provides learners with individually optimized learning plans.

[0033] The server first collects educational information and stores it in a database in a standardized format. This includes educational materials such as past exam questions and textbooks. The collected data is analyzed, and features based on question trends and learning themes are extracted. This analyzed data is then used to generate questions.

[0034] The server uses a generation device to generate new test questions based on the analysis results. The generated questions reflect the characteristics of the educational information and include a variety of question formats. Each generated question has attributes such as difficulty level and theme, and is stored in the database.

[0035] When a user begins learning, the device sends data to the server based on the user's learning goals and current level, requesting appropriate problems. The server selects the most suitable problems from the user's learning history and analysis results and sends them to the device. The user then works on these problems and enters their answers on the device.

[0036] The device provides immediate feedback upon receiving an answer. This feedback includes information on whether the answer is correct or incorrect, as well as detailed explanations. The answer information is sent to a server, which analyzes the answer patterns of individual learners. The analysis identifies the learner's weak areas, and a customized learning plan is created based on the results.

[0037] For example, if a user is preparing for an English exam, the server analyzes past English exam questions and generates new reading comprehension and grammar exercises. As the user works through these exercises, the device provides feedback tailored to the user's characteristics, and the server identifies grammar points the user struggles with. Subsequently, the server presents the user with a revised learning plan focusing on specific grammar points or themes. In this way, the user can use their time efficiently to progress with their studies.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The server collects educational information from textbooks and past exam questions and stores it in a database in a standardized format. During this process, data organization and duplicate removal are performed to ensure the information is accurate and uncluttered.

[0041] Step 2:

[0042] The server uses machine learning algorithms to analyze educational information stored in the database. This extracts characteristics of question trends, important themes, and related knowledge, and assigns them as attribute information.

[0043] Step 3:

[0044] The server uses a generator to create new test questions based on the analysis results. These questions have a set difficulty level and theme, and the generated questions are added to the database.

[0045] Step 4:

[0046] When users initiate a learning session via their device, they input information about their learning goals, areas of interest, and current level. This provides the data that forms the basis of their individualized learning plan.

[0047] Step 5:

[0048] The device sends a request for a set of questions to the server based on the collected user information. The server selects appropriate questions based on past learning history and current input and sends them to the device.

[0049] Step 6:

[0050] Users work on problems displayed on their devices and enter their answers into the device. The answers serve as an important indicator of the user's learning progress.

[0051] Step 7:

[0052] The device generates and presents immediate feedback to the user based on the entered answer. This feedback includes the accuracy rate and a detailed explanation.

[0053] Step 8:

[0054] The device sends the answer information to the server. The server analyzes this data to understand the user's answer patterns and areas of weakness.

[0055] Step 9:

[0056] The server builds a learning plan optimized for the user based on identified areas of weakness. This plan indicates the areas of focus for the next learning session.

[0057] Step 10:

[0058] The device presents the user with a customized learning plan and initiates the next practice cycle. The user continues learning according to this plan and improves their skills.

[0059] (Example 1)

[0060] 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."

[0061] In today's educational environment, there is a demand for efficient, individually optimized learning that can address the diverse needs of learners. However, traditional methods struggle to accommodate this individualization, with significant challenges particularly in analyzing learners' weaknesses and customizing learning plans. Furthermore, providing new test questions quickly and in diverse formats has also been difficult.

[0062] 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.

[0063] In this invention, the server includes means for collecting educational information and storing it in a database; means for analyzing the collected educational information to analyze question trends; means for generating new test questions using a generative AI model; means for providing optimal test questions based on individual learners' answer information and learning history; means for providing immediate feedback using learners' answer information; means for identifying weak areas based on answer patterns; and means for generating a learning plan based on the identified weak areas. This enables individually optimized and efficient learning support for learners.

[0064] "Educational information" refers to data related to learners' education, including past exam questions, textbooks, and reference materials.

[0065] "Means of storing information in a database" refers to technologies that store information in a structured format, enabling efficient searching and management.

[0066] "Means for analyzing collected educational information" refers to methods that use machine learning and data mining techniques to extract useful features and patterns from collected educational data.

[0067] A "generative AI model" is a computational model that uses artificial intelligence to generate new data and content, and is applied to areas such as natural language processing and image generation.

[0068] "Means for generating new test questions" refers to technology that automatically creates test questions based on educational information, and can dynamically adjust the difficulty level and format.

[0069] "Individual learner answer information" refers to data about the answers a specific learner gave to an exam or exercise, including their accuracy and answer patterns.

[0070] "Learning history" refers to information that records the learning activities and achievements a learner has experienced to date.

[0071] "Means of providing optimal test questions" refers to the technology of selecting and presenting appropriate test questions according to the learner's abilities and progress.

[0072] "Means of providing immediate feedback" refers to techniques that evaluate learners' answers on the spot and quickly provide information on correctness and explanations.

[0073] "Methods for identifying weak areas based on answer patterns" are techniques for analyzing learners' answer tendencies and revealing areas where they struggle and the frequency of their errors.

[0074] "Means for generating learning plans based on identified weak areas" refers to methods for automatically creating learning guidelines and materials that reflect areas for improvement in learners.

[0075] This invention provides a system that analyzes educational information, generates new test questions, and provides learners with individually optimized learning plans. Embodiments of this system are described below.

[0076] The server collects diverse educational information via the internet and internal networks. This includes past exam questions, textbooks, and reference materials, which are retrieved using web crawling technologies and APIs. This collected data undergoes a data cleaning process and is then stored in a standardized format in relational database management systems such as SQL.

[0077] Subsequently, the server proceeds to the data analysis stage, where it analyzes the collected information. This analysis uses a generative AI model, applying machine learning techniques to extract features related to the solicited question trends and learning themes. The analyzed data serves as the basis for creating questions.

[0078] By utilizing a generative AI model, new test questions are generated. This model leverages natural language processing technology to automatically create test questions with various themes and difficulty levels. For example, the server can use the OpenAI® API to generate new English reading comprehension questions based on a specified theme.

[0079] When a user begins learning, their device sends their learning goals and current level to the server. The server then selects the most suitable test questions based on the user's accumulated learning history and analytical data, and sends them to the user's device. This allows the user to work on questions that match their level and goals.

[0080] Once a user completes an answer, the device evaluates the answer and provides immediate feedback. This feedback includes not only correctness information but also a detailed explanation of the answer. This answer data is then sent back to the server, which analyzes the answer patterns to identify the learner's weaknesses.

[0081] The server generates and presents a personalized learning plan to the user based on identified weaknesses. This allows the user to efficiently overcome their weaknesses and progress in their learning.

[0082] For example, if a user is preparing for the TOEFL exam, the server generates new reading comprehension and multiple-choice questions based on data from previous English exams. By providing these questions to the user and offering feedback, the system can identify grammatical weaknesses and vocabulary deficiencies, and present a focused learning plan. This allows the user to prepare for the exam efficiently.

[0083] An example of a prompt message is "Analyze the question trends based on the past 10 years of nationwide mock exams," which instructs the user to analyze question trends based on the past 10 years of nationwide mock exams. This enables the system using the generative AI model to generate appropriate questions and provide learning support tailored to the user.

[0084] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0085] Step 1:

[0086] The server collects educational data from educational institutions and the internet. Specifically, it obtains textbooks, past exam questions, reference materials, etc., through web crawling technology and APIs. This data is processed using a text analysis library and converted into a standardized format. The converted data is then stored in an SQL database. The collected inputs are educational information in various forms, and the output is standardized data stored in the database.

[0087] Step 2:

[0088] The server analyzes the stored educational data. Using a generative AI model, it applies machine learning techniques to the data to extract characteristics of question trends and learning themes. This analysis primarily involves feature extraction from text data, performed through scoring and clustering. The input is the educational data in the database, and the output is the analysis result with extracted features. Specific operations include text classification and feature extraction using the Scikit-learn library.

[0089] Step 3:

[0090] The server generates new test questions using a generative AI model based on the analyzed data. The generative AI model uses natural language processing techniques to generate questions on various themes and formats. This generation process utilizes the generative AI model's API, taking the analysis results as input and producing new test questions as output. An example involves using the OpenAI API to create English reading comprehension questions.

[0091] Step 4:

[0092] The terminal sends the user's learning goals and current level to the server and requests appropriate problems. The server selects the most suitable problems based on the user's learning history and analysis results and sends them to the terminal. The input is the user's learning goals and current learning level information, and the output is the most suitable test questions provided to the user. This process involves data retrieval and filtering operations using SQL queries.

[0093] Step 5:

[0094] The user works on the test questions and enters their answers on a terminal. The terminal sends the answer data to the server, which evaluates the data. The server immediately determines whether the answers are correct or incorrect and provides feedback, including detailed explanations. The user's answer information is used as input, and feedback is provided as output. Specifically, this includes automated evaluation and generation of correct answer explanations using a Python script.

[0095] Step 6:

[0096] The server analyzes the user's past answer data and identifies weak areas from answer patterns. Machine learning techniques are used to analyze the learner's patterns and extract points that need improvement. The input to this process is the user's cumulative answer data, and the output is the identified weak areas. Specific processing includes pattern analysis based on decision trees and random forests.

[0097] Step 7:

[0098] The server generates a customized learning plan based on identified weakness areas. This plan serves as a guide for the user to efficiently overcome weaknesses and achieve their goals. Data on weakness areas is used as input, and the output is an individualized learning plan. Specific operations include programmatic control to send the generated learning plan to the terminal.

[0099] (Application Example 1)

[0100] 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."

[0101] In modern education systems, accurately understanding each learner's level of comprehension and weaknesses, and providing efficient, individually optimized learning plans, is a challenge. Furthermore, general, standardized tests and materials are often inadequate to suit the characteristics and goals of individual learners. Moreover, in online learning environments, it is difficult for learners to receive appropriate feedback tailored to their own progress.

[0102] 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.

[0103] In this invention, the server includes means for storing analyzed educational information in a database, means for generating new assessment questions using a generation device, means for identifying areas of weakness based on individual learners' answer information, means for using a smart device that proposes assessment questions to learners in a standardized format, and means for supplying personalized educational content based on learners' goals. This enables learners to receive individually optimized learning plans and feedback.

[0104] "Educational information" refers to information about learning materials, including past exam questions and textbooks.

[0105] A "database" is a system for efficiently storing and managing information and data.

[0106] A "generator" is a computerized unit used to create new evaluation problems.

[0107] An "assessment question" is a task created to measure a learner's level of understanding and proficiency.

[0108] An "individual learner" refers to a specific individual learner who is the subject of education.

[0109] A "weakness area" refers to learning content or topics that a learner is particularly unsure of.

[0110] A "learning strategy" is a learning plan designed to help learners achieve their goals efficiently.

[0111] A "smart device" is a digital device with internet connectivity used to present information to learners.

[0112] "Personalized educational content" refers to learning materials that are customized according to the learner's characteristics and goals.

[0113] The system for implementing this invention is designed to efficiently analyze educational information and provide learners with an individually optimized learning experience. The following describes each component of the system and its role.

[0114] The server first stores educational information in a database. This educational information includes past exam questions and learning materials, which are converted into a standardized format and stored. The server analyzes this accumulated data to extract question trends and learning themes. A generative AI model (e.g., OpenAI's GPT-4®) is used for this analysis to generate new assessment questions. This results in a variety of question formats, enabling the provision of personalized educational content to individual learners.

[0115] The system consists of smart devices such as smartphones and tablets, which present evaluation questions to users in a standardized format. Users can work on these questions and enter their answers to receive immediate feedback. This feedback includes correct / incorrect information and detailed explanations. When a user starts learning, they send their learning goals to the server, which then returns the most suitable questions based on the user's learning history.

[0116] The server identifies learners' weak areas based on the collected answer data. Machine learning techniques are used in this process to design learning strategies tailored to each learner's characteristics. Finally, the server provides personalized educational content to support learners in efficiently deepening their understanding and achieving their goals.

[0117] As a concrete example, when a server generates grammar and listening assessment questions for TOEIC exam preparation, it can send the following prompt to its AI model in response to a user requesting to "strengthen grammar and listening skills":

[0118] "Generate a new set of grammar and listening questions for a TOEIC exam preparation. Focus on these specific grammar points: conditional sentences and verb tenses."

[0119] This approach allows the system to provide learners with an efficient and fulfilling learning experience, enabling them to use their time effectively.

[0120] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0121] Step 1:

[0122] The server collects educational information and stores it in a database in a standardized format. Input includes past exam questions and teaching materials. This information is converted into a format that is easy to analyze and stored in a database that enables efficient searching and management.

[0123] Step 2:

[0124] The server analyzes educational information stored in the database to extract question trends and learning themes. The input is standardized educational information within the database. It analyzes this information and creates prompts to send to the AI ​​model. The output consists of characteristics and trends necessary for question generation.

[0125] Step 3:

[0126] The server generates new evaluation problems using a generative AI model. The inputs for this step are the analysis results and the generated prompt sentences. The AI ​​model generates problems based on these inputs and outputs evaluation problems in various formats.

[0127] Step 4:

[0128] The terminal sends the user's learning goals and learning history to the server and requests the provision of the most suitable problems. The input requires the user's learning-related information (learning goals, history). Based on this, the server selects appropriate problems and sends them back to the terminal.

[0129] Step 5:

[0130] The terminal presents the received evaluation questions to the user, who then works on the questions and enters their answers. The input is the evaluation questions sent from the server. The output is the user's answer information.

[0131] Step 6:

[0132] The device provides immediate feedback based on the user's answer. The input is the user's answer, and the output is feedback (correctness information and detailed explanations). This feedback helps deepen the user's understanding.

[0133] Step 7:

[0134] The server analyzes the answer information received from the user to identify the learner's weak areas. The input for this step is the user's answer information. Machine learning techniques are used for the analysis, and the output is the identified weak areas.

[0135] Step 8:

[0136] The server designs and delivers personalized learning strategies and educational content to the user based on identified areas of weakness. The input is the identified areas of weakness, and the output is the personalized educational content. This allows the user to learn efficiently.

[0137] 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.

[0138] This invention provides a system that generates new test questions based on educational information and analyzes individual learners' answer patterns to identify areas of weakness. This system achieves more effective learning support by combining it with an emotion engine that recognizes the user's emotions. The following describes specific embodiments for carrying out this invention.

[0139] The server first analyzes educational information and generates new test questions based on this analysis. These generated questions are stored in a database and provided to users when they attempt them. The server also collects and analyzes answer information from users to identify areas of weakness in learners. This identification is performed using machine learning techniques to improve accuracy.

[0140] The emotion engine analyzes the user's facial expressions and voice data during learning to monitor their psychological state. This emotion data is sent to the server in real time and used to optimize the learning environment. For example, if the user is feeling anxious or frustrated, the system will adjust the difficulty level of the problems or provide messages to boost their motivation.

[0141] As a concrete example, consider a user learning English. When the user enters their set goal into the device, the server selects and provides English problems that are suitable for that goal. As the user works on the problems, the emotion engine monitors the user's facial expressions, and if it determines that their concentration is waning, the server sends an encouraging message. Furthermore, if the user's weaknesses are identified from their answers, this information is reflected in the learning plan, and specialized problems are selected in the next learning session to help them overcome those weaknesses. In this way, users can learn at their own pace with more effective and individually tailored support.

[0142] The following describes the processing flow.

[0143] Step 1:

[0144] The server analyzes educational information stored in the database. This includes past exam questions and textbook content, and machine learning algorithms are used to identify exam trends and important themes.

[0145] Step 2:

[0146] The server uses a generator to create new test questions based on the analyzed information. The format and content of the questions vary, and they are categorized by difficulty level and theme, and stored in a database in a reusable format.

[0147] Step 3:

[0148] Users begin learning through their device, entering information about their goals and current knowledge level. This input data is sent to the server as the basis for a personalized learning experience.

[0149] Step 4:

[0150] The terminal requests the server to provide problems. The server selects a suitable set of problems based on individualized criteria and sends them to the terminal.

[0151] Step 5:

[0152] The user answers the questions presented on the device. The answers are entered into the device, and feedback is provided immediately. This feedback includes the accuracy rate and a detailed explanation of the answer.

[0153] Step 6:

[0154] The emotion engine analyzes the user's facial expressions and voice in real time during the learning process to measure their emotional state. It determines states such as anxiety, excitement, and calmness, and sends this information to the server.

[0155] Step 7:

[0156] The server analyzes emotional information and answer results in combination to evaluate the user's level of understanding and emotional state. Based on this evaluation, it adjusts the learning environment.

[0157] Step 8:

[0158] The server creates a new learning plan based on the evaluation results. This plan not only includes problems that address the user's weak areas, but also incorporates difficulty adjustments and messages that respond to the user's emotional state.

[0159] Step 9:

[0160] The device presents the user with a customized learning plan. The user then proceeds with the next learning session according to the updated plan. This ensures more effective and personalized learning over time.

[0161] (Example 2)

[0162] 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".

[0163] Traditional learning systems have struggled to systematically identify individual learners' weaknesses and provide optimized learning plans based on those weaknesses. Furthermore, they fail to consider learners' emotions, resulting in ineffective learning support.

[0164] 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.

[0165] In this invention, the server includes means for storing analyzed educational information, means for producing new test items using a generator, means for clarifying weak areas based on individual learners' answer information, means for presenting a learning plan based on the clarified weak areas, and means for recognizing learners' emotions and adaptively adjusting the learning environment. This makes it possible to enhance learning effectiveness and provide an individually optimized learning experience.

[0166] "Educational information" refers to information about knowledge and skills used for the purpose of improving learners' abilities.

[0167] A "generator" is a device or software that generates new content or data based on input information.

[0168] "Test items" refer to a collection of questions and tasks designed to assess a learner's understanding and knowledge.

[0169] An "individual learner" refers to an individual who learns independently using specific educational content or programs.

[0170] "Answer information" refers to the content of the answers provided by learners to the test items, and is data used to evaluate learning outcomes.

[0171] A "weakness area" refers to an area of ​​knowledge or skill that a learner is not considered to have fully understood or mastered.

[0172] "Clarification" refers to making unclear or ambiguous points specific and clearly stating them.

[0173] A "learning plan" refers to a schedule and content of learning designed to help learners efficiently achieve their goals.

[0174] "Emotion" is a general term for a learner's feelings and psychological state, and changes in these can affect learning performance.

[0175] "Adjustment" refers to changing settings or conditions to achieve the optimal state depending on the situation.

[0176] This invention is a system that provides a customized learning experience to individual learners based on educational information. The server analyzes educational information collected from an educational database. This analysis utilizes natural language processing technology to identify important concepts from the educational content. Next, a generative AI model is used to generate new test items based on the identified concepts. This generation process creates test items tailored to individual learners. The generated test items are stored in a database and provided to learners as needed.

[0177] The terminal receives access from a learner and requests the server to provide test items. The server selects pre-generated test items, taking into account the logged-in learner's learning history and set goals, and sends them to the terminal. The terminal presents these test items to the learner through its user interface. When the learner answers a question, the answer information is fed back from the terminal to the server.

[0178] The server analyzes the collected answer data and uses machine learning algorithms to identify the learner's weak areas. Based on the analysis, the server develops a personalized learning plan for the next lesson. This plan is designed to help learners progress more effectively. Furthermore, the system incorporates an emotion engine that analyzes the learner's emotions and has the ability to adjust the learning environment in real time. Emotional data is sent to the server, optimizing the learning experience based on the learner's concentration level and stress level.

[0179] As a concrete example, consider a case where an English learner sets the goal of "achieving a TOEIC score of 700 or higher." Based on this goal, the server selects TOEIC-related questions. The emotion engine monitors the learner's facial expressions, and if it detects a decline in concentration, the server sends an encouraging message.

[0180] An example of a prompt message is: "Describe how to select problems based on the learning objectives set by the user, and how to optimize learning support based on the user's emotional data during learning."

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

[0182] Step 1:

[0183] The server collects educational information from an educational database and uses natural language processing techniques to analyze important concepts and topics. The input is educational information, and the output is data categorized into important concepts. Based on this data, a generative AI model prepares to generate test items.

[0184] Step 2:

[0185] The server uses a generative AI model to generate new test items. The input is the conceptual data analyzed in step 1, and the output is the new test items. The generated test items are stored in the test item database. In this process, prompts are used to instruct the generative AI model on the format in which to create the questions.

[0186] Step 3:

[0187] The user logs into the terminal and sets specific learning objectives. The terminal sends this information to the server. The input is the user's learning objectives, and the output is personalized question request information. The server receives this information and selects questions from the test item database that match the user's objectives.

[0188] Step 4:

[0189] The server sends the selected test items to the user's terminal. The input is the requested test items, and the output is the questions presented on the user's terminal. The terminal displays the questions to the learner via the user interface and initiates the learning process.

[0190] Step 5:

[0191] When a user answers a question, that answer information is sent from the terminal to the server. The input is the user's answer data, and the output is the stored answer information. The server collects this answer information and evaluates the performance of individual learners.

[0192] Step 6:

[0193] The server analyzes the collected answer data using a machine learning algorithm to identify the user's weak areas. The input is the answer data, and the output is data on the identified weak areas. Based on this data, a learning plan for the next session is formulated.

[0194] Step 7:

[0195] The device uses its built-in emotion engine to collect emotional data from the user during learning. Input consists of the user's facial expressions and voice data, while output is analyzed emotional data. This emotional data is sent to a server and used to optimize the learning environment.

[0196] Step 8:

[0197] The server adjusts the learning environment based on emotional data, according to the learner's psychological state. The input is emotional data, and the output is the adjusted learning environment. It maintains learner motivation by providing encouraging messages and adjusting the difficulty of problems as needed.

[0198] (Application Example 2)

[0199] 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".

[0200] Traditional learning systems have struggled to accurately identify individual proficiency levels and weaknesses, and to provide support that takes into account the learner's mental state. Furthermore, the fixed learning environment and lack of flexibility to adapt to individual users prevented efficient training support.

[0201] 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.

[0202] In this invention, the server includes means for storing analyzed information in a database, means for generating new test questions using a generation device, means for identifying weak areas based on individual answer information, means for analyzing emotions and monitoring psychological state, and means for providing user support based on monitored emotions. This enables personalized training support for learners.

[0203] "Analyzed information" refers to data obtained by analyzing user learning history, answer data, and other similar information.

[0204] A "database" is a data management system for systematically storing analyzed information and generated test questions.

[0205] A "generation device" is a device that automatically creates new examination questions from existing educational information.

[0206] A "weakness area" refers to an area in which a learner's proficiency particularly needs improvement.

[0207] "Means of identification" refers to methods and devices for analyzing data such as learners' answer patterns to identify areas of weakness.

[0208] A "plan" is an instructional schedule created to help learners effectively progress in their studies, based on identified areas of weakness.

[0209] "Analyzing emotions" refers to assessing a user's psychological state by analyzing their facial expressions and voice data.

[0210] "Means of monitoring psychological state" refers to technologies that monitor a user's emotions in real time and track changes in those emotions.

[0211] "Means of providing support" refers to methods of providing appropriate advice, such as encouragement or solutions, according to the learner's psychological state.

[0212] The system for implementing this invention uses a server, an emotion analysis engine, a generation device, and a database, etc. First, the server analyzes educational information and generates new test questions. These questions are stored in the database and can be accessed from the user's terminal.

[0213] Learners can use their devices to answer the provided test questions. Once a user answers, the data is sent to a server, which uses machine learning techniques to analyze the answer patterns. This analysis identifies the individual learner's weak areas. This identified information is then fed back into the next learning plan, and individually tailored questions are prepared.

[0214] Furthermore, the emotion analysis engine works in conjunction with the device to collect the user's facial expressions and voice data. This allows the server to analyze emotions in real time and monitor their psychological state. As a result, if the learner shows signs of stress or decreased concentration, encouraging messages and appropriate advice are provided through the device.

[0215] As a concrete example, consider a scenario in assembly training where, as a user learns a new process, the system checks their learning progress and sends reassuring comments in real time. For example, a message like, "This part is a little difficult, but let's take it slow," might be displayed.

[0216] An example of a prompt is: "Design a system that uses TensorFlow and sentiment analysis tools to analyze the emotions and learning progress of factory staff working in real time and provide advice."

[0217] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0218] Step 1:

[0219] The server collects and analyzes educational information. Educational information is taken in as input, and the data is processed to extract necessary items. A new learning dataset is formed as output. This dataset is stored in a database and forms the basis for generating exam questions.

[0220] Step 2:

[0221] The server generates new test questions using a generator. An educational dataset is input, and questions are generated by an algorithm. These generated questions are stored in a database and output to learners as a set of questions provided via terminals.

[0222] Step 3:

[0223] The user answers the provided test questions using a terminal. The learner's answer information is sent to the server as input from the terminal. The answer information is then analyzed by the server, and the correctness of each answer is determined. An answer pattern is formed as output.

[0224] Step 4:

[0225] The server uses a machine learning model to analyze answer patterns and identify individual learners' weak areas. The input is answer patterns, and the learners' weaknesses are identified through data calculation and analysis. The identified weak areas become the output used to generate the next learning plan.

[0226] Step 5:

[0227] The device works in conjunction with an emotion analysis engine to collect the user's facial expressions and voice data. The input consists of voice and video data being trained. This data is analyzed in real time, and the user's psychological state is evaluated. As output, the user's emotional state is sent to a server and recorded.

[0228] Step 6:

[0229] The server analyzes the user's psychological state based on collected emotional data. Based on the analysis results, it evaluates the user's stress and concentration levels. Based on this evaluation, it determines actions regarding the next learning step. Encouraging messages and advice are generated as output.

[0230] Step 7:

[0231] The terminal provides appropriate feedback to the user based on instructions from the server. It receives output information from the server as input and displays messages to the user on the terminal. The messages are intended to adjust the learner's psychological state and improve their motivation to learn, thereby optimizing the learning environment.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] [Second Embodiment]

[0236] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0237] 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.

[0238] 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).

[0239] 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.

[0240] 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.

[0241] 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).

[0242] 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.

[0243] 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.

[0244] 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.

[0245] 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.

[0246] 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.

[0247] 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".

[0248] This invention provides a system that analyzes educational information and generates new test questions. This system operates based on the interaction between a server, a terminal, and a user, and provides learners with individually optimized learning plans.

[0249] The server first collects educational information and stores it in a database in a standardized format. This includes educational materials such as past exam questions and textbooks. The collected data is analyzed, and features based on question trends and learning themes are extracted. This analyzed data is then used to generate questions.

[0250] The server uses a generation device to generate new test questions based on the analysis results. The generated questions reflect the characteristics of the educational information and include a variety of question formats. Each generated question has attributes such as difficulty level and theme, and is stored in the database.

[0251] When a user begins learning, the device sends data to the server based on the user's learning goals and current level, requesting appropriate problems. The server selects the most suitable problems from the user's learning history and analysis results and sends them to the device. The user then works on these problems and enters their answers on the device.

[0252] The device provides immediate feedback upon receiving an answer. This feedback includes information on whether the answer is correct or incorrect, as well as detailed explanations. The answer information is sent to a server, which analyzes the answer patterns of individual learners. The analysis identifies the learner's weak areas, and a customized learning plan is created based on the results.

[0253] For example, if a user is preparing for an English exam, the server analyzes past English exam questions and generates new reading comprehension and grammar exercises. As the user works through these exercises, the device provides feedback tailored to the user's characteristics, and the server identifies grammar points the user struggles with. Subsequently, the server presents the user with a revised learning plan focusing on specific grammar points or themes. In this way, the user can use their time efficiently to progress with their studies.

[0254] The following describes the processing flow.

[0255] Step 1:

[0256] The server collects educational information from textbooks and past exam questions and stores it in a database in a standardized format. During this process, data organization and duplicate removal are performed to ensure the information is accurate and uncluttered.

[0257] Step 2:

[0258] The server uses machine learning algorithms to analyze educational information stored in the database. This extracts characteristics of question trends, important themes, and related knowledge, and assigns them as attribute information.

[0259] Step 3:

[0260] The server uses a generator to create new test questions based on the analysis results. These questions have a set difficulty level and theme, and the generated questions are added to the database.

[0261] Step 4:

[0262] When users initiate a learning session via their device, they input information about their learning goals, areas of interest, and current level. This provides the data that forms the basis of their individualized learning plan.

[0263] Step 5:

[0264] The device sends a request for a set of questions to the server based on the collected user information. The server selects appropriate questions based on past learning history and current input and sends them to the device.

[0265] Step 6:

[0266] Users work on problems displayed on their devices and enter their answers into the device. The answers serve as an important indicator of the user's learning progress.

[0267] Step 7:

[0268] The device generates and presents immediate feedback to the user based on the entered answer. This feedback includes the accuracy rate and a detailed explanation.

[0269] Step 8:

[0270] The device sends the answer information to the server. The server analyzes this data to understand the user's answer patterns and areas of weakness.

[0271] Step 9:

[0272] The server builds a learning plan optimized for the user based on identified areas of weakness. This plan indicates the areas of focus for the next learning session.

[0273] Step 10:

[0274] The device presents the user with a customized learning plan and initiates the next practice cycle. The user continues learning according to this plan and improves their skills.

[0275] (Example 1)

[0276] 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."

[0277] In today's educational environment, there is a demand for efficient, individually optimized learning that can address the diverse needs of learners. However, traditional methods struggle to accommodate this individualization, with significant challenges particularly in analyzing learners' weaknesses and customizing learning plans. Furthermore, providing new test questions quickly and in diverse formats has also been difficult.

[0278] 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.

[0279] In this invention, the server includes means for collecting educational information and storing it in a database, means for analyzing the collected educational information to analyze the question-setting tendency, means for generating new test questions using a generative AI model, means for providing optimal test questions based on the answer information and learning history of individual learners, means for providing immediate feedback using the learners' answer information, means for identifying weak areas based on the answer patterns, and means for generating a learning plan based on the identified weak areas. Thereby, it becomes possible to provide efficient learning support optimized for individual learners.

[0280] "Educational information" refers to data related to the education of learners and includes past test questions, textbooks, reference materials, etc.

[0281] "Means for storing in a database" is a technology for storing information in a structured format so that it can be efficiently searched and managed.

[0282] "Means for analyzing the collected educational information" is a method of extracting useful features and patterns from the collected educational data using machine learning and data mining techniques.

[0283] "Generative AI model" is a computational model for generating new data and content using artificial intelligence and is applied to natural language processing, image generation, etc.

[0284] "Means for generating new test questions" is a technology for automatically creating test questions based on educational information and can dynamically adjust the difficulty level and format.

[0285] "Answer information of individual learners" refers to data related to the answers given by specific learners to tests and exercises and includes their accuracy and answer patterns.

[0286] "Learning history" refers to information that records the learning activities and achievements experienced by learners so far.

[0287] "Means of providing optimal test questions" refers to the technology of selecting and presenting appropriate test questions according to the learner's abilities and progress.

[0288] "Means of providing immediate feedback" refers to techniques that evaluate learners' answers on the spot and quickly provide information on correctness and explanations.

[0289] "Methods for identifying weak areas based on answer patterns" are techniques for analyzing learners' answer tendencies and revealing areas where they struggle and the frequency of their errors.

[0290] "Means for generating learning plans based on identified weak areas" refers to methods for automatically creating learning guidelines and materials that reflect areas for improvement in learners.

[0291] This invention provides a system that analyzes educational information, generates new test questions, and provides learners with individually optimized learning plans. Embodiments of this system are described below.

[0292] The server collects diverse educational information via the internet and internal networks. This includes past exam questions, textbooks, and reference materials, which are retrieved using web crawling technologies and APIs. This collected data undergoes a data cleaning process and is then stored in a standardized format in relational database management systems such as SQL.

[0293] Subsequently, the server proceeds to the data analysis stage, where it analyzes the collected information. This analysis uses a generative AI model, applying machine learning techniques to extract features related to the solicited question trends and learning themes. The analyzed data serves as the basis for creating questions.

[0294] By using a generative AI model, new test questions are generated. This model utilizes natural language processing technology to automatically create test questions with various themes and difficulty levels. For example, the server can use the OpenAI API to generate new English reading comprehension questions based on a specified theme.

[0295] When a user begins learning, their device sends their learning goals and current level to the server. The server then selects the most suitable test questions based on the user's accumulated learning history and analytical data, and sends them to the user's device. This allows the user to work on questions that match their level and goals.

[0296] Once a user completes an answer, the device evaluates the answer and provides immediate feedback. This feedback includes not only correctness information but also a detailed explanation of the answer. This answer data is then sent back to the server, which analyzes the answer patterns to identify the learner's weaknesses.

[0297] The server generates and presents a personalized learning plan to the user based on identified weaknesses. This allows the user to efficiently overcome their weaknesses and progress in their learning.

[0298] For example, if a user is preparing for the TOEFL exam, the server generates new reading comprehension and multiple-choice questions based on data from previous English exams. By providing these questions to the user and offering feedback, the system can identify grammatical weaknesses and vocabulary deficiencies, and present a focused learning plan. This allows the user to prepare for the exam efficiently.

[0299] An example of a prompt message is "Analyze the question trends based on the past 10 years of nationwide mock exams," which instructs the user to analyze question trends based on the past 10 years of nationwide mock exams. This enables the system using the generative AI model to generate appropriate questions and provide learning support tailored to the user.

[0300] The flow of the specific process in Example 1 will be described using FIG. 11.

[0301] Step 1:

[0302] The server collects educational data from educational institutions or the Internet. Specifically, textbooks, past exam questions, reference materials, etc. are obtained through web crawling technology and APIs. These data are processed using a text analysis library and converted into a standardized format. The converted data is stored in a SQL database. The input collected is educational information in various forms, and the output is the standardized data stored in the database.

[0303] Step 2:

[0304] The server analyzes the stored educational data. Using a generative AI model, machine learning techniques are applied to the data to extract the characteristics of the question-setting tendency and learning themes. This analysis process is mainly the feature extraction of text data and is performed by scoring and clustering. The input is the educational data in the database, and the output is the analysis result with features extracted. Specific operations include text classification and feature extraction using the Scikit-learn library.

[0305] Step 3:

[0306] The server uses the generative AI model based on the analyzed data to generate new exam questions. The generative AI model generates questions of various themes and formats through natural language processing technology. In this generation process, the API of the generative AI model is used, taking the analysis result as the input and obtaining new exam questions as the output. Specific operations include using the OpenAI API to create English reading comprehension questions as an example.

[0307] Step 4:

[0308] The terminal sends the user's learning goals and current level to the server and requests appropriate problems. The server selects the most suitable problems based on the user's learning history and analysis results and sends them to the terminal. The input is the user's learning goals and current learning level information, and the output is the most suitable test questions provided to the user. This process involves data retrieval and filtering operations using SQL queries.

[0309] Step 5:

[0310] The user works on the test questions and enters their answers on a terminal. The terminal sends the answer data to the server, which evaluates the data. The server immediately determines whether the answers are correct or incorrect and provides feedback, including detailed explanations. The user's answer information is used as input, and feedback is provided as output. Specifically, this includes automated evaluation and generation of correct answer explanations using a Python script.

[0311] Step 6:

[0312] The server analyzes the user's past answer data and identifies weak areas from answer patterns. Machine learning techniques are used to analyze the learner's patterns and extract points that need improvement. The input to this process is the user's cumulative answer data, and the output is the identified weak areas. Specific processing includes pattern analysis based on decision trees and random forests.

[0313] Step 7:

[0314] The server generates a customized learning plan based on identified weakness areas. This plan serves as a guide for the user to efficiently overcome weaknesses and achieve their goals. Data on weakness areas is used as input, and the output is an individualized learning plan. Specific operations include programmatic control to send the generated learning plan to the terminal.

[0315] (Application Example 1)

[0316] 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 glasses 214 will be referred to as the "terminal."

[0317] In modern education systems, accurately understanding each learner's level of comprehension and weaknesses, and providing efficient, individually optimized learning plans, is a challenge. Furthermore, general, standardized tests and materials are often inadequate to suit the characteristics and goals of individual learners. Moreover, in online learning environments, it is difficult for learners to receive appropriate feedback tailored to their own progress.

[0318] 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.

[0319] In this invention, the server includes means for storing analyzed educational information in a database, means for generating new assessment questions using a generation device, means for identifying areas of weakness based on individual learners' answer information, means for using a smart device that proposes assessment questions to learners in a standardized format, and means for supplying personalized educational content based on learners' goals. This enables learners to receive individually optimized learning plans and feedback.

[0320] "Educational information" refers to information about learning materials, including past exam questions and textbooks.

[0321] A "database" is a system for efficiently storing and managing information and data.

[0322] A "generator" is a computerized unit used to create new evaluation problems.

[0323] An "assessment question" is a task created to measure a learner's level of understanding and proficiency.

[0324] An "individual learner" refers to a specific individual learner who is the subject of education.

[0325] A "weakness area" refers to learning content or topics that a learner is particularly unsure of.

[0326] A "learning strategy" is a learning plan designed to help learners achieve their goals efficiently.

[0327] A "smart device" is a digital device with internet connectivity used to present information to learners.

[0328] "Personalized educational content" refers to learning materials that are customized according to the learner's characteristics and goals.

[0329] The system for implementing this invention is designed to efficiently analyze educational information and provide learners with an individually optimized learning experience. The following describes each component of the system and its role.

[0330] The server first stores educational information in a database. This educational information includes past exam questions and learning materials, which are converted into a standardized format and stored. The server analyzes this accumulated data to extract question trends and learning themes. A generative AI model (e.g., OpenAI's GPT-4) is used for this analysis to generate new assessment questions. This results in a variety of question formats, enabling the provision of personalized educational content to individual learners.

[0331] The system consists of smart devices such as smartphones and tablets, which present evaluation questions to users in a standardized format. Users can work on these questions and enter their answers to receive immediate feedback. This feedback includes correct / incorrect information and detailed explanations. When a user starts learning, they send their learning goals to the server, which then returns the most suitable questions based on the user's learning history.

[0332] The server identifies learners' weak areas based on the collected answer data. Machine learning techniques are used in this process to design learning strategies tailored to each learner's characteristics. Finally, the server provides personalized educational content to support learners in efficiently deepening their understanding and achieving their goals.

[0333] As a concrete example, when a server generates grammar and listening assessment questions for TOEIC exam preparation, it can send the following prompt to its AI model in response to a user requesting to "strengthen grammar and listening skills":

[0334] "Generate a new set of grammar and listening questions for a TOEIC exam preparation. Focus on these specific grammar points: conditional sentences and verb tenses."

[0335] This approach allows the system to provide learners with an efficient and fulfilling learning experience, enabling them to use their time effectively.

[0336] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0337] Step 1:

[0338] The server collects educational information and stores it in a database in a standardized format. Input includes past exam questions and teaching materials. This information is converted into a format that is easy to analyze and stored in a database that enables efficient searching and management.

[0339] Step 2:

[0340] The server analyzes educational information stored in the database to extract question trends and learning themes. The input is standardized educational information within the database. It analyzes this information and creates prompts to send to the AI ​​model. The output consists of characteristics and trends necessary for question generation.

[0341] Step 3:

[0342] The server generates new evaluation problems using a generative AI model. The inputs for this step are the analysis results and the generated prompt sentences. The AI ​​model generates problems based on these inputs and outputs evaluation problems in various formats.

[0343] Step 4:

[0344] The terminal sends the user's learning goals and learning history to the server and requests the provision of the most suitable problems. The input requires the user's learning-related information (learning goals, history). Based on this, the server selects appropriate problems and sends them back to the terminal.

[0345] Step 5:

[0346] The terminal presents the received evaluation questions to the user, who then works on the questions and enters their answers. The input is the evaluation questions sent from the server. The output is the user's answer information.

[0347] Step 6:

[0348] The device provides immediate feedback based on the user's answer. The input is the user's answer, and the output is feedback (correctness information and detailed explanations). This feedback helps deepen the user's understanding.

[0349] Step 7:

[0350] The server analyzes the answer information received from the user to identify the learner's weak areas. The input for this step is the user's answer information. Machine learning techniques are used for the analysis, and the output is the identified weak areas.

[0351] Step 8:

[0352] The server designs and delivers personalized learning strategies and educational content to the user based on identified areas of weakness. The input is the identified areas of weakness, and the output is the personalized educational content. This allows the user to learn efficiently.

[0353] 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.

[0354] This invention provides a system that generates new test questions based on educational information and analyzes individual learners' answer patterns to identify areas of weakness. This system achieves more effective learning support by combining it with an emotion engine that recognizes the user's emotions. The following describes specific embodiments for carrying out this invention.

[0355] The server first analyzes educational information and generates new test questions based on this analysis. These generated questions are stored in a database and provided to users when they attempt them. The server also collects and analyzes answer information from users to identify areas of weakness in learners. This identification is performed using machine learning techniques to improve accuracy.

[0356] The emotion engine analyzes the user's facial expressions and voice data during learning to monitor their psychological state. This emotion data is sent to the server in real time and used to optimize the learning environment. For example, if the user is feeling anxious or frustrated, the system will adjust the difficulty level of the problems or provide messages to boost their motivation.

[0357] As a concrete example, consider a user learning English. When the user enters their set goal into the device, the server selects and provides English problems that are suitable for that goal. As the user works on the problems, the emotion engine monitors the user's facial expressions, and if it determines that their concentration is waning, the server sends an encouraging message. Furthermore, if the user's weaknesses are identified from their answers, this information is reflected in the learning plan, and specialized problems are selected in the next learning session to help them overcome those weaknesses. In this way, users can learn at their own pace with more effective and individually tailored support.

[0358] The following describes the processing flow.

[0359] Step 1:

[0360] The server analyzes educational information stored in the database. This includes past exam questions and textbook content, and machine learning algorithms are used to identify exam trends and important themes.

[0361] Step 2:

[0362] The server uses a generator to create new test questions based on the analyzed information. The format and content of the questions vary, and they are categorized by difficulty level and theme, and stored in a database in a reusable format.

[0363] Step 3:

[0364] Users begin learning through their device, entering information about their goals and current knowledge level. This input data is sent to the server as the basis for a personalized learning experience.

[0365] Step 4:

[0366] The terminal requests the server to provide problems. The server selects a suitable set of problems based on individualized criteria and sends them to the terminal.

[0367] Step 5:

[0368] The user answers the questions presented on the device. The answers are entered into the device, and feedback is provided immediately. This feedback includes the accuracy rate and a detailed explanation of the answer.

[0369] Step 6:

[0370] The emotion engine analyzes the user's facial expressions and voice in real time during the learning process to measure their emotional state. It determines states such as anxiety, excitement, and calmness, and sends this information to the server.

[0371] Step 7:

[0372] The server analyzes emotional information and answer results in combination to evaluate the user's level of understanding and emotional state. Based on this evaluation, it adjusts the learning environment.

[0373] Step 8:

[0374] The server creates a new learning plan based on the evaluation results. This plan not only includes problems that address the user's weak areas, but also incorporates difficulty adjustments and messages that respond to the user's emotional state.

[0375] Step 9:

[0376] The device presents the user with a customized learning plan. The user then proceeds with the next learning session according to the updated plan. This ensures more effective and personalized learning over time.

[0377] (Example 2)

[0378] 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".

[0379] Traditional learning systems have struggled to systematically identify individual learners' weaknesses and provide optimized learning plans based on those weaknesses. Furthermore, they fail to consider learners' emotions, resulting in ineffective learning support.

[0380] 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.

[0381] In this invention, the server includes means for storing analyzed educational information, means for producing new test items using a generator, means for clarifying weak areas based on individual learners' answer information, means for presenting a learning plan based on the clarified weak areas, and means for recognizing learners' emotions and adaptively adjusting the learning environment. This makes it possible to enhance learning effectiveness and provide an individually optimized learning experience.

[0382] "Educational information" refers to information about knowledge and skills used for the purpose of improving learners' abilities.

[0383] A "generator" is a device or software that generates new content or data based on input information.

[0384] "Test items" refer to a collection of questions and tasks designed to assess a learner's understanding and knowledge.

[0385] An "individual learner" refers to an individual who learns independently using specific educational content or programs.

[0386] "Answer information" refers to the content of the answers provided by learners to the test items, and is data used to evaluate learning outcomes.

[0387] A "weakness area" refers to an area of ​​knowledge or skill that a learner is not considered to have fully understood or mastered.

[0388] "Clarification" refers to making unclear or ambiguous points specific and clearly stating them.

[0389] A "learning plan" refers to a schedule and content of learning designed to help learners efficiently achieve their goals.

[0390] "Emotion" is a general term for a learner's feelings and psychological state, and changes in these can affect learning performance.

[0391] "Adjustment" refers to changing settings or conditions to achieve the optimal state depending on the situation.

[0392] This invention is a system that provides a customized learning experience to individual learners based on educational information. The server analyzes educational information collected from an educational database. This analysis utilizes natural language processing technology to identify important concepts from the educational content. Next, a generative AI model is used to generate new test items based on the identified concepts. This generation process creates test items tailored to individual learners. The generated test items are stored in a database and provided to learners as needed.

[0393] The terminal receives access from a learner and requests the server to provide test items. The server selects pre-generated test items, taking into account the logged-in learner's learning history and set goals, and sends them to the terminal. The terminal presents these test items to the learner through its user interface. When the learner answers a question, the answer information is fed back from the terminal to the server.

[0394] The server analyzes the collected answer data and uses machine learning algorithms to identify the learner's weak areas. Based on the analysis, the server develops a personalized learning plan for the next lesson. This plan is designed to help learners progress more effectively. Furthermore, the system incorporates an emotion engine that analyzes the learner's emotions and has the ability to adjust the learning environment in real time. Emotional data is sent to the server, optimizing the learning experience based on the learner's concentration level and stress level.

[0395] As a concrete example, consider a case where an English learner sets the goal of "achieving a TOEIC score of 700 or higher." Based on this goal, the server selects TOEIC-related questions. The emotion engine monitors the learner's facial expressions, and if it detects a decline in concentration, the server sends an encouraging message.

[0396] An example of a prompt message is: "Describe how to select problems based on the learning objectives set by the user, and how to optimize learning support based on the user's emotional data during learning."

[0397] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0398] Step 1:

[0399] The server collects educational information from an educational database and uses natural language processing techniques to analyze important concepts and topics. The input is educational information, and the output is data categorized into important concepts. Based on this data, a generative AI model prepares to generate test items.

[0400] Step 2:

[0401] The server uses a generative AI model to generate new test items. The input is the conceptual data analyzed in step 1, and the output is the new test items. The generated test items are stored in the test item database. In this process, prompts are used to instruct the generative AI model on the format in which to create the questions.

[0402] Step 3:

[0403] The user logs into the terminal and sets specific learning objectives. The terminal sends this information to the server. The input is the user's learning objectives, and the output is personalized question request information. The server receives this information and selects questions from the test item database that match the user's objectives.

[0404] Step 4:

[0405] The server sends the selected test items to the user's terminal. The input is the requested test items, and the output is the questions presented on the user's terminal. The terminal displays the questions to the learner via the user interface and initiates the learning process.

[0406] Step 5:

[0407] When a user answers a question, that answer information is sent from the terminal to the server. The input is the user's answer data, and the output is the stored answer information. The server collects this answer information and evaluates the performance of individual learners.

[0408] Step 6:

[0409] The server analyzes the collected answer data using a machine learning algorithm to identify the user's weak areas. The input is the answer data, and the output is data on the identified weak areas. Based on this data, a learning plan for the next session is formulated.

[0410] Step 7:

[0411] The device uses its built-in emotion engine to collect emotional data from the user during learning. Input consists of the user's facial expressions and voice data, while output is analyzed emotional data. This emotional data is sent to a server and used to optimize the learning environment.

[0412] Step 8:

[0413] The server adjusts the learning environment based on emotional data, according to the learner's psychological state. The input is emotional data, and the output is the adjusted learning environment. It maintains learner motivation by providing encouraging messages and adjusting the difficulty of problems as needed.

[0414] (Application Example 2)

[0415] 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."

[0416] Traditional learning systems have struggled to accurately identify individual proficiency levels and weaknesses, and to provide support that takes into account the learner's mental state. Furthermore, the fixed learning environment and lack of flexibility to adapt to individual users prevented efficient training support.

[0417] 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.

[0418] In this invention, the server includes means for storing analyzed information in a database, means for generating new test questions using a generation device, means for identifying weak areas based on individual answer information, means for analyzing emotions and monitoring psychological state, and means for providing user support based on monitored emotions. This enables personalized training support for learners.

[0419] "Analyzed information" refers to data obtained by analyzing user learning history, answer data, and other similar information.

[0420] A "database" is a data management system for systematically storing analyzed information and generated test questions.

[0421] A "generation device" is a device that automatically creates new examination questions from existing educational information.

[0422] A "weakness area" refers to an area in which a learner's proficiency particularly needs improvement.

[0423] "Means of identification" refers to methods and devices for analyzing data such as learners' answer patterns to identify areas of weakness.

[0424] A "plan" is an instructional schedule created to help learners effectively progress in their studies, based on identified areas of weakness.

[0425] "Analyzing emotions" refers to assessing a user's psychological state by analyzing their facial expressions and voice data.

[0426] "Means of monitoring psychological state" refers to technologies that monitor a user's emotions in real time and track changes in those emotions.

[0427] "Means of providing support" refers to methods of providing appropriate advice, such as encouragement or solutions, according to the learner's psychological state.

[0428] The system for implementing this invention uses a server, an emotion analysis engine, a generation device, and a database, etc. First, the server analyzes educational information and generates new test questions. These questions are stored in the database and can be accessed from the user's terminal.

[0429] Learners can use their devices to answer the provided test questions. Once a user answers, the data is sent to a server, which uses machine learning techniques to analyze the answer patterns. This analysis identifies the individual learner's weak areas. This identified information is then fed back into the next learning plan, and individually tailored questions are prepared.

[0430] Furthermore, the emotion analysis engine works in conjunction with the device to collect the user's facial expressions and voice data. This allows the server to analyze emotions in real time and monitor their psychological state. As a result, if the learner shows signs of stress or decreased concentration, encouraging messages and appropriate advice are provided through the device.

[0431] As a concrete example, consider a scenario in assembly training where, as a user learns a new process, the system checks their learning progress and sends reassuring comments in real time. For example, a message like, "This part is a little difficult, but let's take it slow," might be displayed.

[0432] An example of a prompt is: "Design a system that uses TensorFlow and sentiment analysis tools to analyze the emotions and learning progress of factory staff working in real time and provide advice."

[0433] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0434] Step 1:

[0435] The server collects and analyzes educational information. Educational information is taken in as input, and the data is processed to extract necessary items. A new learning dataset is formed as output. This dataset is stored in a database and forms the basis for generating exam questions.

[0436] Step 2:

[0437] The server generates new test questions using a generator. An educational dataset is input, and questions are generated by an algorithm. These generated questions are stored in a database and output to learners as a set of questions provided via terminals.

[0438] Step 3:

[0439] The user answers the provided test questions using a terminal. The learner's answer information is sent to the server as input from the terminal. The answer information is then analyzed by the server, and the correctness of each answer is determined. An answer pattern is formed as output.

[0440] Step 4:

[0441] The server uses a machine learning model to analyze answer patterns and identify individual learners' weak areas. The input is answer patterns, and the learners' weaknesses are identified through data calculation and analysis. The identified weak areas become the output used to generate the next learning plan.

[0442] Step 5:

[0443] The device works in conjunction with an emotion analysis engine to collect the user's facial expressions and voice data. The input consists of voice and video data being trained. This data is analyzed in real time, and the user's psychological state is evaluated. As output, the user's emotional state is sent to a server and recorded.

[0444] Step 6:

[0445] The server analyzes the user's psychological state based on collected emotional data. Based on the analysis results, it evaluates the user's stress and concentration levels. Based on this evaluation, it determines actions regarding the next learning step. Encouraging messages and advice are generated as output.

[0446] Step 7:

[0447] The terminal provides appropriate feedback to the user based on instructions from the server. It receives output information from the server as input and displays messages to the user on the terminal. The messages are intended to adjust the learner's psychological state and improve their motivation to learn, thereby optimizing the learning environment.

[0448] 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.

[0449] 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.

[0450] 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.

[0451] [Third Embodiment]

[0452] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0453] 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.

[0454] 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).

[0455] 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.

[0456] 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.

[0457] 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).

[0458] 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.

[0459] 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.

[0460] 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.

[0461] 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.

[0462] 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.

[0463] 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".

[0464] This invention provides a system that analyzes educational information and generates new test questions. This system operates based on the interaction between a server, a terminal, and a user, and provides learners with individually optimized learning plans.

[0465] The server first collects educational information and stores it in a database in a standardized format. This includes educational materials such as past exam questions and textbooks. The collected data is analyzed, and features based on question trends and learning themes are extracted. This analyzed data is then used to generate questions.

[0466] The server uses a generation device to generate new test questions based on the analysis results. The generated questions reflect the characteristics of the educational information and include a variety of question formats. Each generated question has attributes such as difficulty level and theme, and is stored in the database.

[0467] When a user begins learning, the device sends data to the server based on the user's learning goals and current level, requesting appropriate problems. The server selects the most suitable problems from the user's learning history and analysis results and sends them to the device. The user then works on these problems and enters their answers on the device.

[0468] The device provides immediate feedback upon receiving an answer. This feedback includes information on whether the answer is correct or incorrect, as well as detailed explanations. The answer information is sent to a server, which analyzes the answer patterns of individual learners. The analysis identifies the learner's weak areas, and a customized learning plan is created based on the results.

[0469] For example, if a user is preparing for an English exam, the server analyzes past English exam questions and generates new reading comprehension and grammar exercises. As the user works through these exercises, the device provides feedback tailored to the user's characteristics, and the server identifies grammar points the user struggles with. Subsequently, the server presents the user with a revised learning plan focusing on specific grammar points or themes. In this way, the user can use their time efficiently to progress with their studies.

[0470] The following describes the processing flow.

[0471] Step 1:

[0472] The server collects educational information from textbooks and past exam questions and stores it in a database in a standardized format. During this process, data organization and duplicate removal are performed to ensure the information is accurate and uncluttered.

[0473] Step 2:

[0474] The server uses machine learning algorithms to analyze educational information stored in the database. This extracts characteristics of question trends, important themes, and related knowledge, and assigns them as attribute information.

[0475] Step 3:

[0476] The server uses a generator to create new test questions based on the analysis results. These questions have a set difficulty level and theme, and the generated questions are added to the database.

[0477] Step 4:

[0478] When users initiate a learning session via their device, they input information about their learning goals, areas of interest, and current level. This provides the data that forms the basis of their individualized learning plan.

[0479] Step 5:

[0480] The device sends a request for a set of questions to the server based on the collected user information. The server selects appropriate questions based on past learning history and current input and sends them to the device.

[0481] Step 6:

[0482] Users work on problems displayed on their devices and enter their answers into the device. The answers serve as an important indicator of the user's learning progress.

[0483] Step 7:

[0484] The device generates and presents immediate feedback to the user based on the entered answer. This feedback includes the accuracy rate and a detailed explanation.

[0485] Step 8:

[0486] The device sends the answer information to the server. The server analyzes this data to understand the user's answer patterns and areas of weakness.

[0487] Step 9:

[0488] The server builds a learning plan optimized for the user based on identified areas of weakness. This plan indicates the areas of focus for the next learning session.

[0489] Step 10:

[0490] The device presents the user with a customized learning plan and initiates the next practice cycle. The user continues learning according to this plan and improves their skills.

[0491] (Example 1)

[0492] 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."

[0493] In today's educational environment, there is a demand for efficient, individually optimized learning that can address the diverse needs of learners. However, traditional methods struggle to accommodate this individualization, with significant challenges particularly in analyzing learners' weaknesses and customizing learning plans. Furthermore, providing new test questions quickly and in diverse formats has also been difficult.

[0494] 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.

[0495] In this invention, the server includes means for collecting educational information and storing it in a database; means for analyzing the collected educational information to analyze question trends; means for generating new test questions using a generative AI model; means for providing optimal test questions based on individual learners' answer information and learning history; means for providing immediate feedback using learners' answer information; means for identifying weak areas based on answer patterns; and means for generating a learning plan based on the identified weak areas. This enables individually optimized and efficient learning support for learners.

[0496] "Educational information" refers to data related to learners' education, including past exam questions, textbooks, and reference materials.

[0497] "Means of storing information in a database" refers to technologies that store information in a structured format, enabling efficient searching and management.

[0498] "Means for analyzing collected educational information" refers to methods that use machine learning and data mining techniques to extract useful features and patterns from collected educational data.

[0499] A "generative AI model" is a computational model that uses artificial intelligence to generate new data and content, and is applied to areas such as natural language processing and image generation.

[0500] "Means for generating new test questions" refers to technology that automatically creates test questions based on educational information, and can dynamically adjust the difficulty level and format.

[0501] "Individual learner answer information" refers to data about the answers a specific learner gave to an exam or exercise, including their accuracy and answer patterns.

[0502] "Learning history" refers to information that records the learning activities and achievements a learner has experienced to date.

[0503] "Means of providing optimal test questions" refers to the technology of selecting and presenting appropriate test questions according to the learner's abilities and progress.

[0504] "Means of providing immediate feedback" refers to techniques that evaluate learners' answers on the spot and quickly provide information on correctness and explanations.

[0505] "Methods for identifying weak areas based on answer patterns" are techniques for analyzing learners' answer tendencies and revealing areas where they struggle and the frequency of their errors.

[0506] "Means for generating learning plans based on identified weak areas" refers to methods for automatically creating learning guidelines and materials that reflect areas for improvement in learners.

[0507] This invention provides a system that analyzes educational information, generates new test questions, and provides learners with individually optimized learning plans. Embodiments of this system are described below.

[0508] The server collects diverse educational information via the internet and internal networks. This includes past exam questions, textbooks, and reference materials, which are retrieved using web crawling technologies and APIs. This collected data undergoes a data cleaning process and is then stored in a standardized format in relational database management systems such as SQL.

[0509] Subsequently, the server proceeds to the data analysis stage, where it analyzes the collected information. This analysis uses a generative AI model, applying machine learning techniques to extract features related to the solicited question trends and learning themes. The analyzed data serves as the basis for creating questions.

[0510] By using a generative AI model, new test questions are generated. This model utilizes natural language processing technology to automatically create test questions with various themes and difficulty levels. For example, the server can use the OpenAI API to generate new English reading comprehension questions based on a specified theme.

[0511] When a user begins learning, their device sends their learning goals and current level to the server. The server then selects the most suitable test questions based on the user's accumulated learning history and analytical data, and sends them to the user's device. This allows the user to work on questions that match their level and goals.

[0512] Once a user completes an answer, the device evaluates the answer and provides immediate feedback. This feedback includes not only correctness information but also a detailed explanation of the answer. This answer data is then sent back to the server, which analyzes the answer patterns to identify the learner's weaknesses.

[0513] The server generates and presents a personalized learning plan to the user based on identified weaknesses. This allows the user to efficiently overcome their weaknesses and progress in their learning.

[0514] For example, if a user is preparing for the TOEFL exam, the server generates new reading comprehension and multiple-choice questions based on data from previous English exams. By providing these questions to the user and offering feedback, the system can identify grammatical weaknesses and vocabulary deficiencies, and present a focused learning plan. This allows the user to prepare for the exam efficiently.

[0515] An example of a prompt message is "Analyze the question trends based on the past 10 years of nationwide mock exams," which instructs the user to analyze question trends based on the past 10 years of nationwide mock exams. This enables the system using the generative AI model to generate appropriate questions and provide learning support tailored to the user.

[0516] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0517] Step 1:

[0518] The server collects educational data from educational institutions and the internet. Specifically, it obtains textbooks, past exam questions, reference materials, etc., through web crawling technology and APIs. This data is processed using a text analysis library and converted into a standardized format. The converted data is then stored in an SQL database. The collected inputs are educational information in various forms, and the output is standardized data stored in the database.

[0519] Step 2:

[0520] The server analyzes the stored educational data. Using a generative AI model, it applies machine learning techniques to the data to extract characteristics of question trends and learning themes. This analysis primarily involves feature extraction from text data, performed through scoring and clustering. The input is the educational data in the database, and the output is the analysis result with extracted features. Specific operations include text classification and feature extraction using the Scikit-learn library.

[0521] Step 3:

[0522] The server generates new test questions using a generative AI model based on the analyzed data. The generative AI model uses natural language processing techniques to generate questions on various themes and formats. This generation process utilizes the generative AI model's API, taking the analysis results as input and producing new test questions as output. An example involves using the OpenAI API to create English reading comprehension questions.

[0523] Step 4:

[0524] The terminal sends the user's learning goals and current level to the server and requests appropriate problems. The server selects the most suitable problems based on the user's learning history and analysis results and sends them to the terminal. The input is the user's learning goals and current learning level information, and the output is the most suitable test questions provided to the user. This process involves data retrieval and filtering operations using SQL queries.

[0525] Step 5:

[0526] The user works on the test questions and enters their answers on a terminal. The terminal sends the answer data to the server, which evaluates the data. The server immediately determines whether the answers are correct or incorrect and provides feedback, including detailed explanations. The user's answer information is used as input, and feedback is provided as output. Specifically, this includes automated evaluation and generation of correct answer explanations using a Python script.

[0527] Step 6:

[0528] The server analyzes the user's past answer data and identifies weak areas from answer patterns. Machine learning techniques are used to analyze the learner's patterns and extract points that need improvement. The input to this process is the user's cumulative answer data, and the output is the identified weak areas. Specific processing includes pattern analysis based on decision trees and random forests.

[0529] Step 7:

[0530] The server generates a customized learning plan based on identified weakness areas. This plan serves as a guide for the user to efficiently overcome weaknesses and achieve their goals. Data on weakness areas is used as input, and the output is an individualized learning plan. Specific operations include programmatic control to send the generated learning plan to the terminal.

[0531] (Application Example 1)

[0532] 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."

[0533] In modern education systems, accurately understanding each learner's level of comprehension and weaknesses, and providing efficient, individually optimized learning plans, is a challenge. Furthermore, general, standardized tests and materials are often inadequate to suit the characteristics and goals of individual learners. Moreover, in online learning environments, it is difficult for learners to receive appropriate feedback tailored to their own progress.

[0534] 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.

[0535] In this invention, the server includes means for storing analyzed educational information in a database, means for generating new assessment questions using a generation device, means for identifying areas of weakness based on individual learners' answer information, means for using a smart device that proposes assessment questions to learners in a standardized format, and means for supplying personalized educational content based on learners' goals. This enables learners to receive individually optimized learning plans and feedback.

[0536] "Educational information" refers to information about learning materials, including past exam questions and textbooks.

[0537] A "database" is a system for efficiently storing and managing information and data.

[0538] A "generator" is a computerized unit used to create new evaluation problems.

[0539] An "assessment question" is a task created to measure a learner's level of understanding and proficiency.

[0540] An "individual learner" refers to a specific individual learner who is the subject of education.

[0541] A "weakness area" refers to learning content or topics that a learner is particularly unsure of.

[0542] A "learning strategy" is a learning plan designed to help learners achieve their goals efficiently.

[0543] A "smart device" is a digital device with internet connectivity used to present information to learners.

[0544] "Personalized educational content" refers to learning materials that are customized according to the learner's characteristics and goals.

[0545] The system for implementing this invention is designed to efficiently analyze educational information and provide learners with an individually optimized learning experience. The following describes each component of the system and its role.

[0546] The server first stores educational information in a database. This educational information includes past exam questions and learning materials, which are converted into a standardized format and stored. The server analyzes this accumulated data to extract question trends and learning themes. A generative AI model (e.g., OpenAI's GPT-4) is used for this analysis to generate new assessment questions. This results in a variety of question formats, enabling the provision of personalized educational content to individual learners.

[0547] The system consists of smart devices such as smartphones and tablets, which present evaluation questions to users in a standardized format. Users can work on these questions and enter their answers to receive immediate feedback. This feedback includes correct / incorrect information and detailed explanations. When a user starts learning, they send their learning goals to the server, which then returns the most suitable questions based on the user's learning history.

[0548] The server identifies learners' weak areas based on the collected answer data. Machine learning techniques are used in this process to design learning strategies tailored to each learner's characteristics. Finally, the server provides personalized educational content to support learners in efficiently deepening their understanding and achieving their goals.

[0549] As a concrete example, when a server generates grammar and listening assessment questions for TOEIC exam preparation, it can send the following prompt to its AI model in response to a user requesting to "strengthen grammar and listening skills":

[0550] "Generate a new set of grammar and listening questions for a TOEIC exam preparation. Focus on these specific grammar points: conditional sentences and verb tenses."

[0551] This approach allows the system to provide learners with an efficient and fulfilling learning experience, enabling them to use their time effectively.

[0552] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0553] Step 1:

[0554] The server collects educational information and stores it in a database in a standardized format. Input includes past exam questions and teaching materials. This information is converted into a format that is easy to analyze and stored in a database that enables efficient searching and management.

[0555] Step 2:

[0556] The server analyzes educational information stored in the database to extract question trends and learning themes. The input is standardized educational information within the database. It analyzes this information and creates prompts to send to the AI ​​model. The output consists of characteristics and trends necessary for question generation.

[0557] Step 3:

[0558] The server generates new evaluation problems using a generative AI model. The inputs for this step are the analysis results and the generated prompt sentences. The AI ​​model generates problems based on these inputs and outputs evaluation problems in various formats.

[0559] Step 4:

[0560] The terminal sends the user's learning goals and learning history to the server and requests the provision of the most suitable problems. The input requires the user's learning-related information (learning goals, history). Based on this, the server selects appropriate problems and sends them back to the terminal.

[0561] Step 5:

[0562] The terminal presents the received evaluation questions to the user, who then works on the questions and enters their answers. The input is the evaluation questions sent from the server. The output is the user's answer information.

[0563] Step 6:

[0564] The device provides immediate feedback based on the user's answer. The input is the user's answer, and the output is feedback (correctness information and detailed explanations). This feedback helps deepen the user's understanding.

[0565] Step 7:

[0566] The server analyzes the answer information received from the user to identify the learner's weak areas. The input for this step is the user's answer information. Machine learning techniques are used for the analysis, and the output is the identified weak areas.

[0567] Step 8:

[0568] The server designs and delivers personalized learning strategies and educational content to the user based on identified areas of weakness. The input is the identified areas of weakness, and the output is the personalized educational content. This allows the user to learn efficiently.

[0569] 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.

[0570] This invention provides a system that generates new test questions based on educational information and analyzes individual learners' answer patterns to identify areas of weakness. This system achieves more effective learning support by combining it with an emotion engine that recognizes the user's emotions. The following describes specific embodiments for carrying out this invention.

[0571] The server first analyzes educational information and generates new test questions based on this analysis. These generated questions are stored in a database and provided to users when they attempt them. The server also collects and analyzes answer information from users to identify areas of weakness in learners. This identification is performed using machine learning techniques to improve accuracy.

[0572] The emotion engine analyzes the user's facial expressions and voice data during learning to monitor their psychological state. This emotion data is sent to the server in real time and used to optimize the learning environment. For example, if the user is feeling anxious or frustrated, the system will adjust the difficulty level of the problems or provide messages to boost their motivation.

[0573] As a concrete example, consider a user learning English. When the user enters their set goal into the device, the server selects and provides English problems that are suitable for that goal. As the user works on the problems, the emotion engine monitors the user's facial expressions, and if it determines that their concentration is waning, the server sends an encouraging message. Furthermore, if the user's weaknesses are identified from their answers, this information is reflected in the learning plan, and specialized problems are selected in the next learning session to help them overcome those weaknesses. In this way, users can learn at their own pace with more effective and individually tailored support.

[0574] The following describes the processing flow.

[0575] Step 1:

[0576] The server analyzes educational information stored in the database. This includes past exam questions and textbook content, and machine learning algorithms are used to identify exam trends and important themes.

[0577] Step 2:

[0578] The server uses a generator to create new test questions based on the analyzed information. The format and content of the questions vary, and they are categorized by difficulty level and theme, and stored in a database in a reusable format.

[0579] Step 3:

[0580] Users begin learning through their device, entering information about their goals and current knowledge level. This input data is sent to the server as the basis for a personalized learning experience.

[0581] Step 4:

[0582] The terminal requests the server to provide problems. The server selects a suitable set of problems based on individualized criteria and sends them to the terminal.

[0583] Step 5:

[0584] The user answers the questions presented on the device. The answers are entered into the device, and feedback is provided immediately. This feedback includes the accuracy rate and a detailed explanation of the answer.

[0585] Step 6:

[0586] The emotion engine analyzes the user's facial expressions and voice in real time during the learning process to measure their emotional state. It determines states such as anxiety, excitement, and calmness, and sends this information to the server.

[0587] Step 7:

[0588] The server analyzes emotional information and answer results in combination to evaluate the user's level of understanding and emotional state. Based on this evaluation, it adjusts the learning environment.

[0589] Step 8:

[0590] The server creates a new learning plan based on the evaluation results. This plan not only includes problems that address the user's weak areas, but also incorporates difficulty adjustments and messages that respond to the user's emotional state.

[0591] Step 9:

[0592] The device presents the user with a customized learning plan. The user then proceeds with the next learning session according to the updated plan. This ensures more effective and personalized learning over time.

[0593] (Example 2)

[0594] 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."

[0595] Traditional learning systems have struggled to systematically identify individual learners' weaknesses and provide optimized learning plans based on those weaknesses. Furthermore, they fail to consider learners' emotions, resulting in ineffective learning support.

[0596] 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.

[0597] In this invention, the server includes means for storing analyzed educational information, means for producing new test items using a generator, means for clarifying weak areas based on individual learners' answer information, means for presenting a learning plan based on the clarified weak areas, and means for recognizing learners' emotions and adaptively adjusting the learning environment. This makes it possible to enhance learning effectiveness and provide an individually optimized learning experience.

[0598] "Educational information" refers to information about knowledge and skills used for the purpose of improving learners' abilities.

[0599] A "generator" is a device or software that generates new content or data based on input information.

[0600] "Test items" refer to a collection of questions and tasks designed to assess a learner's understanding and knowledge.

[0601] An "individual learner" refers to an individual who learns independently using specific educational content or programs.

[0602] "Answer information" refers to the content of the answers provided by learners to the test items, and is data used to evaluate learning outcomes.

[0603] A "weakness area" refers to an area of ​​knowledge or skill that a learner is not considered to have fully understood or mastered.

[0604] "Clarification" refers to making unclear or ambiguous points specific and clearly stating them.

[0605] A "learning plan" refers to a schedule and content of learning designed to help learners efficiently achieve their goals.

[0606] "Emotion" is a general term for a learner's feelings and psychological state, and changes in these can affect learning performance.

[0607] "Adjustment" refers to changing settings or conditions to achieve the optimal state depending on the situation.

[0608] This invention is a system that provides a customized learning experience to individual learners based on educational information. The server analyzes educational information collected from an educational database. This analysis utilizes natural language processing technology to identify important concepts from the educational content. Next, a generative AI model is used to generate new test items based on the identified concepts. This generation process creates test items tailored to individual learners. The generated test items are stored in a database and provided to learners as needed.

[0609] The terminal receives access from a learner and requests the server to provide test items. The server selects pre-generated test items, taking into account the logged-in learner's learning history and set goals, and sends them to the terminal. The terminal presents these test items to the learner through its user interface. When the learner answers a question, the answer information is fed back from the terminal to the server.

[0610] The server analyzes the collected answer data and uses machine learning algorithms to identify the learner's weak areas. Based on the analysis, the server develops a personalized learning plan for the next lesson. This plan is designed to help learners progress more effectively. Furthermore, the system incorporates an emotion engine that analyzes the learner's emotions and has the ability to adjust the learning environment in real time. Emotional data is sent to the server, optimizing the learning experience based on the learner's concentration level and stress level.

[0611] As a concrete example, consider a case where an English learner sets the goal of "achieving a TOEIC score of 700 or higher." Based on this goal, the server selects TOEIC-related questions. The emotion engine monitors the learner's facial expressions, and if it detects a decline in concentration, the server sends an encouraging message.

[0612] An example of a prompt message is: "Describe how to select problems based on the learning objectives set by the user, and how to optimize learning support based on the user's emotional data during learning."

[0613] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0614] Step 1:

[0615] The server collects educational information from an educational database and uses natural language processing techniques to analyze important concepts and topics. The input is educational information, and the output is data categorized into important concepts. Based on this data, a generative AI model prepares to generate test items.

[0616] Step 2:

[0617] The server uses a generative AI model to generate new test items. The input is the conceptual data analyzed in step 1, and the output is the new test items. The generated test items are stored in the test item database. In this process, prompts are used to instruct the generative AI model on the format in which to create the questions.

[0618] Step 3:

[0619] The user logs into the terminal and sets specific learning objectives. The terminal sends this information to the server. The input is the user's learning objectives, and the output is personalized question request information. The server receives this information and selects questions from the test item database that match the user's objectives.

[0620] Step 4:

[0621] The server sends the selected test items to the user's terminal. The input is the requested test items, and the output is the questions presented on the user's terminal. The terminal displays the questions to the learner via the user interface and initiates the learning process.

[0622] Step 5:

[0623] When a user answers a question, that answer information is sent from the terminal to the server. The input is the user's answer data, and the output is the stored answer information. The server collects this answer information and evaluates the performance of individual learners.

[0624] Step 6:

[0625] The server analyzes the collected answer data using a machine learning algorithm to identify the user's weak areas. The input is the answer data, and the output is data on the identified weak areas. Based on this data, a learning plan for the next session is formulated.

[0626] Step 7:

[0627] The device uses its built-in emotion engine to collect emotional data from the user during learning. Input consists of the user's facial expressions and voice data, while output is analyzed emotional data. This emotional data is sent to a server and used to optimize the learning environment.

[0628] Step 8:

[0629] The server adjusts the learning environment based on emotional data, according to the learner's psychological state. The input is emotional data, and the output is the adjusted learning environment. It maintains learner motivation by providing encouraging messages and adjusting the difficulty of problems as needed.

[0630] (Application Example 2)

[0631] 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."

[0632] Traditional learning systems have struggled to accurately identify individual proficiency levels and weaknesses, and to provide support that takes into account the learner's mental state. Furthermore, the fixed learning environment and lack of flexibility to adapt to individual users prevented efficient training support.

[0633] 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.

[0634] In this invention, the server includes means for storing analyzed information in a database, means for generating new test questions using a generation device, means for identifying weak areas based on individual answer information, means for analyzing emotions and monitoring psychological state, and means for providing user support based on monitored emotions. This enables personalized training support for learners.

[0635] "Analyzed information" refers to data obtained by analyzing user learning history, answer data, and other similar information.

[0636] A "database" is a data management system for systematically storing analyzed information and generated test questions.

[0637] A "generation device" is a device that automatically creates new examination questions from existing educational information.

[0638] A "weakness area" refers to an area in which a learner's proficiency particularly needs improvement.

[0639] "Means of identification" refers to methods and devices for analyzing data such as learners' answer patterns to identify areas of weakness.

[0640] A "plan" is an instructional schedule created to help learners effectively progress in their studies, based on identified areas of weakness.

[0641] "Analyzing emotions" refers to assessing a user's psychological state by analyzing their facial expressions and voice data.

[0642] "Means of monitoring psychological state" refers to technologies that monitor a user's emotions in real time and track changes in those emotions.

[0643] "Means of providing support" refers to methods of providing appropriate advice, such as encouragement or solutions, according to the learner's psychological state.

[0644] The system for implementing this invention uses a server, an emotion analysis engine, a generation device, and a database, etc. First, the server analyzes educational information and generates new test questions. These questions are stored in the database and can be accessed from the user's terminal.

[0645] Learners can use their devices to answer the provided test questions. Once a user answers, the data is sent to a server, which uses machine learning techniques to analyze the answer patterns. This analysis identifies the individual learner's weak areas. This identified information is then fed back into the next learning plan, and individually tailored questions are prepared.

[0646] Furthermore, the emotion analysis engine works in conjunction with the device to collect the user's facial expressions and voice data. This allows the server to analyze emotions in real time and monitor their psychological state. As a result, if the learner shows signs of stress or decreased concentration, encouraging messages and appropriate advice are provided through the device.

[0647] As a concrete example, consider a scenario in assembly training where, as a user learns a new process, the system checks their learning progress and sends reassuring comments in real time. For example, a message like, "This part is a little difficult, but let's take it slow," might be displayed.

[0648] An example of a prompt is: "Design a system that uses TensorFlow and sentiment analysis tools to analyze the emotions and learning progress of factory staff working in real time and provide advice."

[0649] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0650] Step 1:

[0651] The server collects and analyzes educational information. Educational information is taken in as input, and the data is processed to extract necessary items. A new learning dataset is formed as output. This dataset is stored in a database and forms the basis for generating exam questions.

[0652] Step 2:

[0653] The server generates new test questions using a generator. An educational dataset is input, and questions are generated by an algorithm. These generated questions are stored in a database and output to learners as a set of questions provided via terminals.

[0654] Step 3:

[0655] The user answers the provided test questions using a terminal. The learner's answer information is sent to the server as input from the terminal. The answer information is then analyzed by the server, and the correctness of each answer is determined. An answer pattern is formed as output.

[0656] Step 4:

[0657] The server uses a machine learning model to analyze answer patterns and identify individual learners' weak areas. The input is answer patterns, and the learners' weaknesses are identified through data calculation and analysis. The identified weak areas become the output used to generate the next learning plan.

[0658] Step 5:

[0659] The device works in conjunction with an emotion analysis engine to collect the user's facial expressions and voice data. The input consists of voice and video data being trained. This data is analyzed in real time, and the user's psychological state is evaluated. As output, the user's emotional state is sent to a server and recorded.

[0660] Step 6:

[0661] The server analyzes the user's psychological state based on collected emotional data. Based on the analysis results, it evaluates the user's stress and concentration levels. Based on this evaluation, it determines actions regarding the next learning step. Encouraging messages and advice are generated as output.

[0662] Step 7:

[0663] The terminal provides appropriate feedback to the user based on instructions from the server. It receives output information from the server as input and displays messages to the user on the terminal. The messages are intended to adjust the learner's psychological state and improve their motivation to learn, thereby optimizing the learning environment.

[0664] 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.

[0665] 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.

[0666] 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.

[0667] [Fourth Embodiment]

[0668] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0669] 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.

[0670] 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).

[0671] 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.

[0672] 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.

[0673] 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).

[0674] 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.

[0675] 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.

[0676] 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.

[0677] 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.

[0678] 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.

[0679] 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.

[0680] 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".

[0681] This invention provides a system that analyzes educational information and generates new test questions. This system operates based on the interaction between a server, a terminal, and a user, and provides learners with individually optimized learning plans.

[0682] The server first collects educational information and stores it in a database in a standardized format. This includes educational materials such as past exam questions and textbooks. The collected data is analyzed, and features based on question trends and learning themes are extracted. This analyzed data is then used to generate questions.

[0683] The server uses a generation device to generate new test questions based on the analysis results. The generated questions reflect the characteristics of the educational information and include a variety of question formats. Each generated question has attributes such as difficulty level and theme, and is stored in the database.

[0684] When a user begins learning, the device sends data to the server based on the user's learning goals and current level, requesting appropriate problems. The server selects the most suitable problems from the user's learning history and analysis results and sends them to the device. The user then works on these problems and enters their answers on the device.

[0685] The device provides immediate feedback upon receiving an answer. This feedback includes information on whether the answer is correct or incorrect, as well as detailed explanations. The answer information is sent to a server, which analyzes the answer patterns of individual learners. The analysis identifies the learner's weak areas, and a customized learning plan is created based on the results.

[0686] For example, if a user is preparing for an English exam, the server analyzes past English exam questions and generates new reading comprehension and grammar exercises. As the user works through these exercises, the device provides feedback tailored to the user's characteristics, and the server identifies grammar points the user struggles with. Subsequently, the server presents the user with a revised learning plan focusing on specific grammar points or themes. In this way, the user can use their time efficiently to progress with their studies.

[0687] The following describes the processing flow.

[0688] Step 1:

[0689] The server collects educational information from textbooks and past exam questions and stores it in a database in a standardized format. During this process, data organization and duplicate removal are performed to ensure the information is accurate and uncluttered.

[0690] Step 2:

[0691] The server uses machine learning algorithms to analyze educational information stored in the database. This extracts characteristics of question trends, important themes, and related knowledge, and assigns them as attribute information.

[0692] Step 3:

[0693] The server uses a generator to create new test questions based on the analysis results. These questions have a set difficulty level and theme, and the generated questions are added to the database.

[0694] Step 4:

[0695] When users initiate a learning session via their device, they input information about their learning goals, areas of interest, and current level. This provides the data that forms the basis of their individualized learning plan.

[0696] Step 5:

[0697] The device sends a request for a set of questions to the server based on the collected user information. The server selects appropriate questions based on past learning history and current input and sends them to the device.

[0698] Step 6:

[0699] Users work on problems displayed on their devices and enter their answers into the device. The answers serve as an important indicator of the user's learning progress.

[0700] Step 7:

[0701] The device generates and presents immediate feedback to the user based on the entered answer. This feedback includes the accuracy rate and a detailed explanation.

[0702] Step 8:

[0703] The device sends the answer information to the server. The server analyzes this data to understand the user's answer patterns and areas of weakness.

[0704] Step 9:

[0705] The server builds a learning plan optimized for the user based on identified areas of weakness. This plan indicates the areas of focus for the next learning session.

[0706] Step 10:

[0707] The device presents the user with a customized learning plan and initiates the next practice cycle. The user continues learning according to this plan and improves their skills.

[0708] (Example 1)

[0709] 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".

[0710] In today's educational environment, there is a demand for efficient, individually optimized learning that can address the diverse needs of learners. However, traditional methods struggle to accommodate this individualization, with significant challenges particularly in analyzing learners' weaknesses and customizing learning plans. Furthermore, providing new test questions quickly and in diverse formats has also been difficult.

[0711] 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.

[0712] In this invention, the server includes means for collecting educational information and storing it in a database; means for analyzing the collected educational information to analyze question trends; means for generating new test questions using a generative AI model; means for providing optimal test questions based on individual learners' answer information and learning history; means for providing immediate feedback using learners' answer information; means for identifying weak areas based on answer patterns; and means for generating a learning plan based on the identified weak areas. This enables individually optimized and efficient learning support for learners.

[0713] "Educational information" refers to data related to learners' education, including past exam questions, textbooks, and reference materials.

[0714] "Means of storing information in a database" refers to technologies that store information in a structured format, enabling efficient searching and management.

[0715] "Means for analyzing collected educational information" refers to methods that use machine learning and data mining techniques to extract useful features and patterns from collected educational data.

[0716] A "generative AI model" is a computational model that uses artificial intelligence to generate new data and content, and is applied to areas such as natural language processing and image generation.

[0717] "Means for generating new test questions" refers to technology that automatically creates test questions based on educational information, and can dynamically adjust the difficulty level and format.

[0718] "Individual learner answer information" refers to data about the answers a specific learner gave to an exam or exercise, including their accuracy and answer patterns.

[0719] "Learning history" refers to information that records the learning activities and achievements a learner has experienced to date.

[0720] "Means of providing optimal test questions" refers to the technology of selecting and presenting appropriate test questions according to the learner's abilities and progress.

[0721] "Means of providing immediate feedback" refers to techniques that evaluate learners' answers on the spot and quickly provide information on correctness and explanations.

[0722] "Methods for identifying weak areas based on answer patterns" are techniques for analyzing learners' answer tendencies and revealing areas where they struggle and the frequency of their errors.

[0723] "Means for generating learning plans based on identified weak areas" refers to methods for automatically creating learning guidelines and materials that reflect areas for improvement in learners.

[0724] This invention provides a system that analyzes educational information, generates new test questions, and provides learners with individually optimized learning plans. Embodiments of this system are described below.

[0725] The server collects diverse educational information via the internet and internal networks. This includes past exam questions, textbooks, and reference materials, which are retrieved using web crawling technologies and APIs. This collected data undergoes a data cleaning process and is then stored in a standardized format in relational database management systems such as SQL.

[0726] Subsequently, the server proceeds to the data analysis stage, where it analyzes the collected information. This analysis uses a generative AI model, applying machine learning techniques to extract features related to the solicited question trends and learning themes. The analyzed data serves as the basis for creating questions.

[0727] By using a generative AI model, new test questions are generated. This model utilizes natural language processing technology to automatically create test questions with various themes and difficulty levels. For example, the server can use the OpenAI API to generate new English reading comprehension questions based on a specified theme.

[0728] When a user begins learning, their device sends their learning goals and current level to the server. The server then selects the most suitable test questions based on the user's accumulated learning history and analytical data, and sends them to the user's device. This allows the user to work on questions that match their level and goals.

[0729] Once a user completes an answer, the device evaluates the answer and provides immediate feedback. This feedback includes not only correctness information but also a detailed explanation of the answer. This answer data is then sent back to the server, which analyzes the answer patterns to identify the learner's weaknesses.

[0730] The server generates and presents a personalized learning plan to the user based on identified weaknesses. This allows the user to efficiently overcome their weaknesses and progress in their learning.

[0731] For example, if a user is preparing for the TOEFL exam, the server generates new reading comprehension and multiple-choice questions based on data from previous English exams. By providing these questions to the user and offering feedback, the system can identify grammatical weaknesses and vocabulary deficiencies, and present a focused learning plan. This allows the user to prepare for the exam efficiently.

[0732] An example of a prompt message is "Analyze the question trends based on the past 10 years of nationwide mock exams," which instructs the user to analyze question trends based on the past 10 years of nationwide mock exams. This enables the system using the generative AI model to generate appropriate questions and provide learning support tailored to the user.

[0733] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0734] Step 1:

[0735] The server collects educational data from educational institutions and the internet. Specifically, it obtains textbooks, past exam questions, reference materials, etc., through web crawling technology and APIs. This data is processed using a text analysis library and converted into a standardized format. The converted data is then stored in an SQL database. The collected inputs are educational information in various forms, and the output is standardized data stored in the database.

[0736] Step 2:

[0737] The server analyzes the stored educational data. Using a generative AI model, it applies machine learning techniques to the data to extract characteristics of question trends and learning themes. This analysis primarily involves feature extraction from text data, performed through scoring and clustering. The input is the educational data in the database, and the output is the analysis result with extracted features. Specific operations include text classification and feature extraction using the Scikit-learn library.

[0738] Step 3:

[0739] The server generates new test questions using a generative AI model based on the analyzed data. The generative AI model uses natural language processing techniques to generate questions on various themes and formats. This generation process utilizes the generative AI model's API, taking the analysis results as input and producing new test questions as output. An example involves using the OpenAI API to create English reading comprehension questions.

[0740] Step 4:

[0741] The terminal sends the user's learning goals and current level to the server and requests appropriate problems. The server selects the most suitable problems based on the user's learning history and analysis results and sends them to the terminal. The input is the user's learning goals and current learning level information, and the output is the most suitable test questions provided to the user. This process involves data retrieval and filtering operations using SQL queries.

[0742] Step 5:

[0743] The user works on the test questions and enters their answers on a terminal. The terminal sends the answer data to the server, which evaluates the data. The server immediately determines whether the answers are correct or incorrect and provides feedback, including detailed explanations. The user's answer information is used as input, and feedback is provided as output. Specifically, this includes automated evaluation and generation of correct answer explanations using a Python script.

[0744] Step 6:

[0745] The server analyzes the user's past answer data and identifies weak areas from answer patterns. Machine learning techniques are used to analyze the learner's patterns and extract points that need improvement. The input to this process is the user's cumulative answer data, and the output is the identified weak areas. Specific processing includes pattern analysis based on decision trees and random forests.

[0746] Step 7:

[0747] The server generates a customized learning plan based on identified weakness areas. This plan serves as a guide for the user to efficiently overcome weaknesses and achieve their goals. Data on weakness areas is used as input, and the output is an individualized learning plan. Specific operations include programmatic control to send the generated learning plan to the terminal.

[0748] (Application Example 1)

[0749] 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".

[0750] In modern education systems, accurately understanding each learner's level of comprehension and weaknesses, and providing efficient, individually optimized learning plans, is a challenge. Furthermore, general, standardized tests and materials are often inadequate to suit the characteristics and goals of individual learners. Moreover, in online learning environments, it is difficult for learners to receive appropriate feedback tailored to their own progress.

[0751] 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.

[0752] In this invention, the server includes means for storing analyzed educational information in a database, means for generating new assessment questions using a generation device, means for identifying areas of weakness based on individual learners' answer information, means for using a smart device that proposes assessment questions to learners in a standardized format, and means for supplying personalized educational content based on learners' goals. This enables learners to receive individually optimized learning plans and feedback.

[0753] "Educational information" refers to information about learning materials, including past exam questions and textbooks.

[0754] A "database" is a system for efficiently storing and managing information and data.

[0755] A "generator" is a computerized unit used to create new evaluation problems.

[0756] An "assessment question" is a task created to measure a learner's level of understanding and proficiency.

[0757] An "individual learner" refers to a specific individual learner who is the subject of education.

[0758] A "weakness area" refers to learning content or topics that a learner is particularly unsure of.

[0759] A "learning strategy" is a learning plan designed to help learners achieve their goals efficiently.

[0760] A "smart device" is a digital device with internet connectivity used to present information to learners.

[0761] "Personalized educational content" refers to learning materials that are customized according to the learner's characteristics and goals.

[0762] The system for implementing this invention is designed to efficiently analyze educational information and provide learners with an individually optimized learning experience. The following describes each component of the system and its role.

[0763] The server first stores educational information in a database. This educational information includes past exam questions and learning materials, which are converted into a standardized format and stored. The server analyzes this accumulated data to extract question trends and learning themes. A generative AI model (e.g., OpenAI's GPT-4) is used for this analysis to generate new assessment questions. This results in a variety of question formats, enabling the provision of personalized educational content to individual learners.

[0764] The system consists of smart devices such as smartphones and tablets, which present evaluation questions to users in a standardized format. Users can work on these questions and enter their answers to receive immediate feedback. This feedback includes correct / incorrect information and detailed explanations. When a user starts learning, they send their learning goals to the server, which then returns the most suitable questions based on the user's learning history.

[0765] The server identifies learners' weak areas based on the collected answer data. Machine learning techniques are used in this process to design learning strategies tailored to each learner's characteristics. Finally, the server provides personalized educational content to support learners in efficiently deepening their understanding and achieving their goals.

[0766] As a concrete example, when a server generates grammar and listening assessment questions for TOEIC exam preparation, it can send the following prompt to its AI model in response to a user requesting to "strengthen grammar and listening skills":

[0767] "Generate a new set of grammar and listening questions for a TOEIC exam preparation. Focus on these specific grammar points: conditional sentences and verb tenses."

[0768] This approach allows the system to provide learners with an efficient and fulfilling learning experience, enabling them to use their time effectively.

[0769] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0770] Step 1:

[0771] The server collects educational information and stores it in a database in a standardized format. Input includes past exam questions and teaching materials. This information is converted into a format that is easy to analyze and stored in a database that enables efficient searching and management.

[0772] Step 2:

[0773] The server analyzes educational information stored in the database to extract question trends and learning themes. The input is standardized educational information within the database. It analyzes this information and creates prompts to send to the AI ​​model. The output consists of characteristics and trends necessary for question generation.

[0774] Step 3:

[0775] The server generates new evaluation problems using a generative AI model. The inputs for this step are the analysis results and the generated prompt sentences. The AI ​​model generates problems based on these inputs and outputs evaluation problems in various formats.

[0776] Step 4:

[0777] The terminal sends the user's learning goals and learning history to the server and requests the provision of the most suitable problems. The input requires the user's learning-related information (learning goals, history). Based on this, the server selects appropriate problems and sends them back to the terminal.

[0778] Step 5:

[0779] The terminal presents the received evaluation questions to the user, who then works on the questions and enters their answers. The input is the evaluation questions sent from the server. The output is the user's answer information.

[0780] Step 6:

[0781] The device provides immediate feedback based on the user's answer. The input is the user's answer, and the output is feedback (correctness information and detailed explanations). This feedback helps deepen the user's understanding.

[0782] Step 7:

[0783] The server analyzes the answer information received from the user to identify the learner's weak areas. The input for this step is the user's answer information. Machine learning techniques are used for the analysis, and the output is the identified weak areas.

[0784] Step 8:

[0785] The server designs and delivers personalized learning strategies and educational content to the user based on identified areas of weakness. The input is the identified areas of weakness, and the output is the personalized educational content. This allows the user to learn efficiently.

[0786] 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.

[0787] This invention provides a system that generates new test questions based on educational information and analyzes individual learners' answer patterns to identify areas of weakness. This system achieves more effective learning support by combining it with an emotion engine that recognizes the user's emotions. The following describes specific embodiments for carrying out this invention.

[0788] The server first analyzes educational information and generates new test questions based on this analysis. These generated questions are stored in a database and provided to users when they attempt them. The server also collects and analyzes answer information from users to identify areas of weakness in learners. This identification is performed using machine learning techniques to improve accuracy.

[0789] The emotion engine analyzes the user's facial expressions and voice data during learning to monitor their psychological state. This emotion data is sent to the server in real time and used to optimize the learning environment. For example, if the user is feeling anxious or frustrated, the system will adjust the difficulty level of the problems or provide messages to boost their motivation.

[0790] As a concrete example, consider a user learning English. When the user enters their set goal into the device, the server selects and provides English problems that are suitable for that goal. As the user works on the problems, the emotion engine monitors the user's facial expressions, and if it determines that their concentration is waning, the server sends an encouraging message. Furthermore, if the user's weaknesses are identified from their answers, this information is reflected in the learning plan, and specialized problems are selected in the next learning session to help them overcome those weaknesses. In this way, users can learn at their own pace with more effective and individually tailored support.

[0791] The following describes the processing flow.

[0792] Step 1:

[0793] The server analyzes educational information stored in the database. This includes past exam questions and textbook content, and machine learning algorithms are used to identify exam trends and important themes.

[0794] Step 2:

[0795] The server uses a generator to create new test questions based on the analyzed information. The format and content of the questions vary, and they are categorized by difficulty level and theme, and stored in a database in a reusable format.

[0796] Step 3:

[0797] Users begin learning through their device, entering information about their goals and current knowledge level. This input data is sent to the server as the basis for a personalized learning experience.

[0798] Step 4:

[0799] The terminal requests the server to provide problems. The server selects a suitable set of problems based on individualized criteria and sends them to the terminal.

[0800] Step 5:

[0801] The user answers the questions presented on the device. The answers are entered into the device, and feedback is provided immediately. This feedback includes the accuracy rate and a detailed explanation of the answer.

[0802] Step 6:

[0803] The emotion engine analyzes the user's facial expressions and voice in real time during the learning process to measure their emotional state. It determines states such as anxiety, excitement, and calmness, and sends this information to the server.

[0804] Step 7:

[0805] The server analyzes emotional information and answer results in combination to evaluate the user's level of understanding and emotional state. Based on this evaluation, it adjusts the learning environment.

[0806] Step 8:

[0807] The server creates a new learning plan based on the evaluation results. This plan not only includes problems that address the user's weak areas, but also incorporates difficulty adjustments and messages that respond to the user's emotional state.

[0808] Step 9:

[0809] The device presents the user with a customized learning plan. The user then proceeds with the next learning session according to the updated plan. This ensures more effective and personalized learning over time.

[0810] (Example 2)

[0811] 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".

[0812] Traditional learning systems have struggled to systematically identify individual learners' weaknesses and provide optimized learning plans based on those weaknesses. Furthermore, they fail to consider learners' emotions, resulting in ineffective learning support.

[0813] 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.

[0814] In this invention, the server includes means for storing analyzed educational information, means for producing new test items using a generator, means for clarifying weak areas based on individual learners' answer information, means for presenting a learning plan based on the clarified weak areas, and means for recognizing learners' emotions and adaptively adjusting the learning environment. This makes it possible to enhance learning effectiveness and provide an individually optimized learning experience.

[0815] "Educational information" refers to information about knowledge and skills used for the purpose of improving learners' abilities.

[0816] A "generator" is a device or software that generates new content or data based on input information.

[0817] "Test items" refer to a collection of questions and tasks designed to assess a learner's understanding and knowledge.

[0818] An "individual learner" refers to an individual who learns independently using specific educational content or programs.

[0819] "Answer information" refers to the content of the answers provided by learners to the test items, and is data used to evaluate learning outcomes.

[0820] A "weakness area" refers to an area of ​​knowledge or skill that a learner is not considered to have fully understood or mastered.

[0821] "Clarification" refers to making unclear or ambiguous points specific and clearly stating them.

[0822] A "learning plan" refers to a schedule and content of learning designed to help learners efficiently achieve their goals.

[0823] "Emotion" is a general term for a learner's feelings and psychological state, and changes in these can affect learning performance.

[0824] "Adjustment" refers to changing settings or conditions to achieve the optimal state depending on the situation.

[0825] This invention is a system that provides a customized learning experience to individual learners based on educational information. The server analyzes educational information collected from an educational database. This analysis utilizes natural language processing technology to identify important concepts from the educational content. Next, a generative AI model is used to generate new test items based on the identified concepts. This generation process creates test items tailored to individual learners. The generated test items are stored in a database and provided to learners as needed.

[0826] The terminal receives access from a learner and requests the server to provide test items. The server selects pre-generated test items, taking into account the logged-in learner's learning history and set goals, and sends them to the terminal. The terminal presents these test items to the learner through its user interface. When the learner answers a question, the answer information is fed back from the terminal to the server.

[0827] The server analyzes the collected answer data and uses machine learning algorithms to identify the learner's weak areas. Based on the analysis, the server develops a personalized learning plan for the next lesson. This plan is designed to help learners progress more effectively. Furthermore, the system incorporates an emotion engine that analyzes the learner's emotions and has the ability to adjust the learning environment in real time. Emotional data is sent to the server, optimizing the learning experience based on the learner's concentration level and stress level.

[0828] As a concrete example, consider a case where an English learner sets the goal of "achieving a TOEIC score of 700 or higher." Based on this goal, the server selects TOEIC-related questions. The emotion engine monitors the learner's facial expressions, and if it detects a decline in concentration, the server sends an encouraging message.

[0829] An example of a prompt message is: "Describe how to select problems based on the learning objectives set by the user, and how to optimize learning support based on the user's emotional data during learning."

[0830] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0831] Step 1:

[0832] The server collects educational information from an educational database and uses natural language processing techniques to analyze important concepts and topics. The input is educational information, and the output is data categorized into important concepts. Based on this data, a generative AI model prepares to generate test items.

[0833] Step 2:

[0834] The server uses a generative AI model to generate new test items. The input is the conceptual data analyzed in step 1, and the output is the new test items. The generated test items are stored in the test item database. In this process, prompts are used to instruct the generative AI model on the format in which to create the questions.

[0835] Step 3:

[0836] The user logs into the terminal and sets specific learning objectives. The terminal sends this information to the server. The input is the user's learning objectives, and the output is personalized question request information. The server receives this information and selects questions from the test item database that match the user's objectives.

[0837] Step 4:

[0838] The server sends the selected test items to the user's terminal. The input is the requested test items, and the output is the questions presented on the user's terminal. The terminal displays the questions to the learner via the user interface and initiates the learning process.

[0839] Step 5:

[0840] When a user answers a question, that answer information is sent from the terminal to the server. The input is the user's answer data, and the output is the stored answer information. The server collects this answer information and evaluates the performance of individual learners.

[0841] Step 6:

[0842] The server analyzes the collected answer data using a machine learning algorithm to identify the user's weak areas. The input is the answer data, and the output is data on the identified weak areas. Based on this data, a learning plan for the next session is formulated.

[0843] Step 7:

[0844] The device uses its built-in emotion engine to collect emotional data from the user during learning. Input consists of the user's facial expressions and voice data, while output is analyzed emotional data. This emotional data is sent to a server and used to optimize the learning environment.

[0845] Step 8:

[0846] The server adjusts the learning environment based on emotional data, according to the learner's psychological state. The input is emotional data, and the output is the adjusted learning environment. It maintains learner motivation by providing encouraging messages and adjusting the difficulty of problems as needed.

[0847] (Application Example 2)

[0848] 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".

[0849] Traditional learning systems have struggled to accurately identify individual proficiency levels and weaknesses, and to provide support that takes into account the learner's mental state. Furthermore, the fixed learning environment and lack of flexibility to adapt to individual users prevented efficient training support.

[0850] 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.

[0851] In this invention, the server includes means for storing analyzed information in a database, means for generating new test questions using a generation device, means for identifying weak areas based on individual answer information, means for analyzing emotions and monitoring psychological state, and means for providing user support based on monitored emotions. This enables personalized training support for learners.

[0852] "Analyzed information" refers to data obtained by analyzing user learning history, answer data, and other similar information.

[0853] A "database" is a data management system for systematically storing analyzed information and generated test questions.

[0854] A "generation device" is a device that automatically creates new examination questions from existing educational information.

[0855] A "weakness area" refers to an area in which a learner's proficiency particularly needs improvement.

[0856] "Means of identification" refers to methods and devices for analyzing data such as learners' answer patterns to identify areas of weakness.

[0857] A "plan" is an instructional schedule created to help learners effectively progress in their studies, based on identified areas of weakness.

[0858] "Analyzing emotions" refers to assessing a user's psychological state by analyzing their facial expressions and voice data.

[0859] "Means of monitoring psychological state" refers to technologies that monitor a user's emotions in real time and track changes in those emotions.

[0860] "Means of providing support" refers to methods of providing appropriate advice, such as encouragement or solutions, according to the learner's psychological state.

[0861] The system for implementing this invention uses a server, an emotion analysis engine, a generation device, and a database, etc. First, the server analyzes educational information and generates new test questions. These questions are stored in the database and can be accessed from the user's terminal.

[0862] Learners can use their devices to answer the provided test questions. Once a user answers, the data is sent to a server, which uses machine learning techniques to analyze the answer patterns. This analysis identifies the individual learner's weak areas. This identified information is then fed back into the next learning plan, and individually tailored questions are prepared.

[0863] Furthermore, the emotion analysis engine works in conjunction with the device to collect the user's facial expressions and voice data. This allows the server to analyze emotions in real time and monitor their psychological state. As a result, if the learner shows signs of stress or decreased concentration, encouraging messages and appropriate advice are provided through the device.

[0864] As a concrete example, consider a scenario in assembly training where, as a user learns a new process, the system checks their learning progress and sends reassuring comments in real time. For example, a message like, "This part is a little difficult, but let's take it slow," might be displayed.

[0865] An example of a prompt is: "Design a system that uses TensorFlow and sentiment analysis tools to analyze the emotions and learning progress of factory staff working in real time and provide advice."

[0866] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0867] Step 1:

[0868] The server collects and analyzes educational information. Educational information is taken in as input, and the data is processed to extract necessary items. A new learning dataset is formed as output. This dataset is stored in a database and forms the basis for generating exam questions.

[0869] Step 2:

[0870] The server generates new test questions using a generator. An educational dataset is input, and questions are generated by an algorithm. These generated questions are stored in a database and output to learners as a set of questions provided via terminals.

[0871] Step 3:

[0872] The user answers the provided test questions using a terminal. The learner's answer information is sent to the server as input from the terminal. The answer information is then analyzed by the server, and the correctness of each answer is determined. An answer pattern is formed as output.

[0873] Step 4:

[0874] The server uses a machine learning model to analyze answer patterns and identify individual learners' weak areas. The input is answer patterns, and the learners' weaknesses are identified through data calculation and analysis. The identified weak areas become the output used to generate the next learning plan.

[0875] Step 5:

[0876] The device works in conjunction with an emotion analysis engine to collect the user's facial expressions and voice data. The input consists of voice and video data being trained. This data is analyzed in real time, and the user's psychological state is evaluated. As output, the user's emotional state is sent to a server and recorded.

[0877] Step 6:

[0878] The server analyzes the user's psychological state based on collected emotional data. Based on the analysis results, it evaluates the user's stress and concentration levels. Based on this evaluation, it determines actions regarding the next learning step. Encouraging messages and advice are generated as output.

[0879] Step 7:

[0880] The terminal provides appropriate feedback to the user based on instructions from the server. It receives output information from the server as input and displays messages to the user on the terminal. The messages are intended to adjust the learner's psychological state and improve their motivation to learn, thereby optimizing the learning environment.

[0881] 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.

[0882] 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.

[0883] 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.

[0884] 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.

[0885] 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. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, 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.

[0886] 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.

[0887] 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.

[0888] 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.

[0889] 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."

[0890] 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.

[0891] 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.

[0892] 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.

[0893] 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.

[0894] 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.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] 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.

[0899] 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.

[0900] 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.

[0901] 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.

[0902] The following is further disclosed regarding the embodiments described above.

[0903] (Claim 1)

[0904] A means of storing the analyzed educational information in a database,

[0905] A means for generating new test questions using a generation device,

[0906] A means of identifying areas of weakness based on the answer information of individual learners,

[0907] A means of providing a learning plan based on identified areas of weakness,

[0908] A system that includes this.

[0909] (Claim 2)

[0910] The system according to claim 1, which provides the generated problems in a standardized format.

[0911] (Claim 3)

[0912] The system according to claim 1, which uses machine learning techniques to identify weak areas.

[0913] "Example 1"

[0914] (Claim 1)

[0915] Means for collecting educational information and storing it in a database,

[0916] A method for analyzing question trends by analyzing collected educational information,

[0917] A means of generating new test questions using a generative AI model,

[0918] A means of providing optimal test questions based on individual learners' answer information and learning history,

[0919] A means of providing immediate feedback using learners' answer information,

[0920] A means of identifying weak areas based on answer patterns,

[0921] A means for generating a learning plan based on identified weak areas,

[0922] A system that includes this.

[0923] (Claim 2)

[0924] The system according to claim 1, which provides the generated problems in various formats.

[0925] (Claim 3)

[0926] The system according to claim 1, which uses a generative AI model to identify weak areas.

[0927] "Application Example 1"

[0928] (Claim 1)

[0929] A means of storing the analyzed educational information in a database,

[0930] A means for generating a new evaluation problem using a generation device,

[0931] A means of identifying areas of weakness based on the answer information of individual learners,

[0932] A means of providing learning strategies based on identified weak areas,

[0933] A means of using smart devices to propose assessment questions to learners in a standardized format,

[0934] Means for providing personalized educational content based on learners' goals,

[0935] A system that includes this.

[0936] (Claim 2)

[0937] The system according to claim 1, which provides the generated problems in a standardized format.

[0938] (Claim 3)

[0939] The system according to claim 1, which uses machine learning techniques to identify weak areas.

[0940] "Example 2 of combining an emotion engine"

[0941] (Claim 1)

[0942] Means for accumulating analyzed educational information,

[0943] A means of producing new test items using a generator,

[0944] A means of clarifying weak areas based on the answer information of individual learners,

[0945] A means of presenting a learning plan based on clearly identified areas of weakness,

[0946] A means of recognizing learners' emotions and adaptively adjusting the learning environment,

[0947] A system that includes this.

[0948] (Claim 2)

[0949] The system according to claim 1, which presents the generated items in a standardized format.

[0950] (Claim 3)

[0951] The system according to claim 1, which utilizes machine learning technology to clarify areas of weakness.

[0952] "Application example 2 when combining with an emotional engine"

[0953] (Claim 1)

[0954] A means of storing the analyzed information in a database,

[0955] A means for generating new test questions using a generation device,

[0956] A means of identifying weak areas based on individual answer information,

[0957] Means for providing a plan based on a specified area,

[0958] A means of analyzing emotions and monitoring psychological states,

[0959] A means of providing user support based on monitored emotions,

[0960] A system that includes this.

[0961] (Claim 2)

[0962] The system according to claim 1, which provides generated problems in a standardized format and combines them with information to assist in training.

[0963] (Claim 3)

[0964] The system according to claim 1, which uses machine learning techniques for domain identification and sentiment analysis. [Explanation of Symbols]

[0965] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of storing the analyzed educational information in a database, A means for generating new test questions using a generation device, A means of identifying areas of weakness based on the answer information of individual learners, A means of providing a learning plan based on identified areas of weakness, A system that includes this.

2. The system according to claim 1, which provides the generated problems in a standardized format.

3. The system according to claim 1, which uses machine learning techniques to identify weak areas.

Images