system

Abstract

We provide the system. [Solution] A means of inputting the applicant's current academic ability information, Means of obtaining entrance examination information for the educational institution you wish to attend, A means for using a generative model to generate an individualized learning plan based on the aforementioned academic ability information and entrance examination information, A means of presenting the aforementioned learning plan to the test taker, A means of generating feedback on the learning content, Means of providing a learning experience in a virtual environment, 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, the method 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] Conventional exam preparation measures generally rely on guidance from cram schools or private tutors, resulting in high costs and limited teaching resources as problems. Also, it is difficult to achieve effective learning according to the academic ability of individual examinees with a uniform curriculum, and it is also difficult to maintain motivation. There is a need for a method to solve such problems and promote exam preparation efficiently and economically.

Means for Solving the Problems

[0005] This invention provides a system that uses a generative model to generate personalized learning plans based on the applicant's academic ability information and entrance examination information of the educational institution they wish to attend. Specifically, it includes means for dynamically updating the learning plan using the applicant's mock exam results, and further includes a motivation maintenance method to improve the applicant's motivation to learn by providing a learning experience in a virtual environment. This enables the applicant to learn efficiently at their own pace.

[0006] "Examinee" refers to a learner whose purpose is to take an examination.

[0007] "Academic ability information" refers to data that indicates the current level of knowledge and skills of test takers regarding the subjects being tested.

[0008] "Desired educational institution" refers to the school or university that the applicant wishes to attend.

[0009] "Entrance examination information" refers to detailed data and criteria regarding the entrance examinations conducted by the educational institution you wish to attend.

[0010] An "individualized learning plan" refers to a plan of education and learning activities created specifically for a particular test-taker.

[0011] A "generative model" refers to an artificial intelligence algorithm that learns from large amounts of data and generates new information.

[0012] A "study plan" refers to an educational plan designed to help test-takers study efficiently.

[0013] "Dynamic updating" refers to the process of quickly modifying plans and content in response to changes in the test takers' situations and data.

[0014] A "virtual environment" refers to a simulated space or scene created through a computer.

[0015] The "motivation maintenance method" refers to methods and means for sustaining and improving the learning motivation of the examinee.

Brief Explanation of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiment for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0019] In the following embodiments, a numbered 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.

[0020] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, a numbered 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, etc.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] 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."

[0024] [First Embodiment]

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

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0031] 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.

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

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] This invention is an educational support system aimed at improving the efficiency of learning and maintaining motivation for students preparing for exams. The system provides individualized learning plans to a large number of users (students preparing for exams), thereby enabling efficient exam preparation.

[0038] System Overview

[0039] 1. Enter applicant information

[0040] Users access the system and input their academic ability information and information about the educational institutions they wish to attend. Users can also input their past mock exam results and their current level of understanding of the subjects they are studying.

[0041] 2. Data Processing

[0042] The server receives academic ability information and entrance exam information for desired schools from the user and stores this information in a database. Based on this data, the server uses an AI generative model to construct a different learning plan for each user.

[0043] 3. Presentation and adjustment of the learning plan

[0044] The server sends the generated learning plan to the device. The learning plan includes recommended learning content, learning frequency, and required review items. The AI ​​continuously evaluates the user's learning progress and dynamically adjusts the plan's content.

[0045] 4. Learning in a virtual environment

[0046] The terminal provides users with a virtual environment. Within this environment, users can interact with other test-takers and converse with virtual tutors. This is a measure taken to improve motivation.

[0047] Specific example

[0048] For example, when a user is preparing for a mathematics entrance exam, the system analyzes the user's weaknesses based on their past mathematics practice test data. Based on this analysis, the server adjusts the learning content for each topic, such as "functions" or "geometry," and generates interactive assignments. The terminal promptly presents the user with the assignments to be solved and detailed explanations. This allows the user to focus their learning at their own pace.

[0049] This system allows users to efficiently prepare for entrance exams at their desired educational institutions while monitoring their daily learning progress. Furthermore, by utilizing a virtual environment, it reduces the isolation of studying and alleviates the mental burden of exam preparation.

[0050] The following describes the processing flow.

[0051] Step 1:

[0052] The user logs into the device and enters their basic information, academic information, and data on the educational institution they wish to attend. This allows the system to collect the user's individual data.

[0053] Step 2:

[0054] The terminal sends user input information to the server. This includes past mock exam results and current school preference information. The terminal confirms that the transmission was successful and notifies the user of the progress.

[0055] Step 3:

[0056] The server stores the data received from the terminal in a database. Furthermore, it applies an AI-generated model to the stored data to create a personalized learning plan tailored to the user's academic ability. This plan includes recommended learning content for each subject and items that require high review.

[0057] Step 4:

[0058] The server sends the created learning plan to the user's device. At that time, it prioritizes the recommended learning content included in the plan according to each user's progress.

[0059] Step 5:

[0060] The device presents the received learning plan to the user. It guides the user through the learning process by displaying necessary learning materials, video explanations, and practice problems step by step.

[0061] Step 6:

[0062] Users progress through their daily studies based on the learning plan displayed on their device. They learn efficiently at their own pace by solving problems and watching video explanations.

[0063] Step 7:

[0064] The device continuously records the user's learning progress. For example, it reports the time taken to answer each problem and the correct answer rate to the server, accumulating progress data.

[0065] Step 8:

[0066] The server analyzes the collected study progress data and incorporates it into new learning plans. In particular, it prioritizes areas where the user struggles and their current learning progress, dynamically updating the plan accordingly.

[0067] Step 9:

[0068] In the virtual environment provided by the device, users can participate in study rooms and receive support from virtual characters, thereby maintaining their motivation to learn and reducing mental burden.

[0069] (Example 1)

[0070] 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."

[0071] The challenge lies in efficiently supporting test-takers' learning and realizing optimal learning tailored to each individual's academic ability and aspirations. In particular, it is necessary to provide personalized learning plans that address the unique circumstances of each test-taker, maintain their motivation to learn, and reduce feelings of isolation.

[0072] 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.

[0073] In this invention, the server includes means for inputting the examinee's current ability information, means for obtaining examination information from the educational institution they wish to attend, and means for using a generative model to generate an individualized learning plan. As a result, examinees receive an effective learning plan based on their academic ability and aspirations, and the learning experience through a virtual space can improve their motivation to learn and reduce feelings of isolation.

[0074] An "examinee" is a learner whose purpose is to take an examination.

[0075] "Ability information" refers to a collection of data that indicates the academic ability and level of understanding of the test taker.

[0076] "Desired educational institution" refers to the educational institution that the applicant aims to enroll in.

[0077] "Examination information" refers to data and requirements related to entrance examinations.

[0078] An "educational plan" is a set of teaching guidelines formulated to effectively guide the learning of test-takers.

[0079] A "generative model" is an algorithm that automatically creates an educational plan based on the applicant's ability information and test information.

[0080] A "virtual space" refers to a virtual learning environment created using digital technology.

[0081] "Motivation maintenance techniques" refer to a set of techniques that include various approaches to enhance and maintain the learning motivation of test-takers.

[0082] This invention is a learning support system for test takers, aiming to provide an individualized educational plan. The system is configured and operates as follows:

[0083] Users first access the system using a web browser. They input their own information, such as past exam results and their current level of understanding of subjects. The interface used for this is a web application utilizing HTML and JavaScript (registered trademark).

[0084] The server stores the ability information submitted by the user and the examination information of the educational institution the user wishes to attend in a database. A database management system such as MySQL (registered trademark) is used for this database. The server uses a generative AI model to generate a personalized educational plan for each user. Here, the AI ​​model is given the prompt statement, "Create a personalized educational plan based on the user's academic ability information."

[0085] The generated lesson plan is sent from the server to the terminal. The terminal displays the plan on its screen to make it easy for the user to understand. At this stage, the user can communicate with other test-takers in a virtual space and interact with a virtual tutor. This environment is built using virtual reality technologies such as Unity or Unreal Engine.

[0086] For example, when a user is preparing for an English exam, the system analyzes their weaknesses based on past practice test data and generates a focused study plan for frequently appearing questions. The server generates assignments to improve skills such as listening and speaking. The terminal presents these assignments to the user, provides explanations, and feeds back the progress to the server.

[0087] This system allows users to obtain an educational plan optimized for them and an environment that enables them to learn at their own pace.

[0088] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0089] Step 1:

[0090] Users access the system using a web browser and enter their own ability information and exam information for their desired educational institution. This information includes past mock exam scores and current study status. This data is sent to the server when the submit button is pressed.

[0091] Step 2:

[0092] The server parses the input data received from the user and stores it in a database. A data management system such as MySQL is used for this database. The input data undergoes format checks and is stored in a normalized state. The stored data then serves as the foundational information for generating educational plans in subsequent processing.

[0093] Step 3:

[0094] The server runs a generative AI model using stored user data. Specifically, it provides the AI ​​model with the prompt, "Create an individualized educational plan based on the user's academic ability information." The generative AI model then performs data analysis based on this prompt and outputs an individualized educational plan adapted to the user.

[0095] Step 4:

[0096] The generated learning plan is sent from the server to the terminal. The terminal receives this plan and displays it in an easy-to-understand format for the user. The specific output includes the learning content for each subject and a recommended learning timeline. The user can then proceed with their learning based on this information.

[0097] Step 5:

[0098] The terminal provides users with a virtual space that allows them to interact with other test-takers. This virtual space is built using tools such as Unity and Unreal Engine. Users can confirm learning content and get answers to their questions through a dialogue function with a virtual tutor. Learning progress data obtained through information exchange is periodically sent to the server and used to revise the educational plan.

[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 exam preparation, there is a need for individualized learning that caters to the diverse needs of students. Furthermore, new methods are required to maintain motivation while efficiently advancing learning. However, the current education system makes it difficult to provide each student with an optimized learning plan and a rich learning experience. Maintaining sustained motivation is a major challenge, especially in a learning environment that tends to be isolated.

[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 inputting the applicant's current academic ability information, means for obtaining entrance examination information of the educational institution the applicant wishes to attend, and means for using a generative model to generate an individualized learning plan. This makes it possible to provide applicants with an individualized learning plan and to realize an interactive learning experience through a visual device.

[0104] "Means for inputting the applicant's current academic ability information" refers to the technical means for incorporating the applicant's academic status into the system, and designing an individualized learning plan based on the input information.

[0105] "Means of obtaining entrance examination information for desired educational institutions" refers to technical means of obtaining information on the examination content and standards of the target school for applicants, and using that information to help construct a study plan.

[0106] "Methods using generative models" refer to methods that utilize AI models to generate personalized learning plans for each student taking the exam.

[0107] "Means for generating feedback on learning content" refers to methods for evaluating the level of understanding and progress of test-takers and providing information on areas for improvement and achievement.

[0108] "Means of providing a learning experience in a virtual environment" refers to providing an environment in which examinees can study in a virtual space and gain a richer learning experience.

[0109] "Means using visual devices" refers to devices or technologies used to provide students with visual learning materials and to enable them to intuitively understand the content.

[0110] "A means of supporting learning through real-time interaction with a virtual instructor" refers to a technological means of supporting learning by enabling immediate communication between a virtual instructor and a student.

[0111] "Motivation maintenance techniques" refer to psychological or technical methods used to enhance and maintain students' motivation to learn.

[0112] This invention is designed to effectively provide learning support to students preparing for exams. The main hardware used includes smart devices, such as smart glasses. The system also features a cloud server and AI platform, and the software utilizes Unity, TENSORFLOW®, and Azure® Cloud Services.

[0113] The server is responsible for acquiring the applicant's current academic ability information and collecting entrance examination information for their desired educational institutions from a database. This makes it possible to design a learning plan optimized for each applicant. The server applies an AI generative model to integrate the applicant's past performance data with expected goals and generates a personalized learning plan.

[0114] The terminal, or smart device, visualizes the generated learning plan for the test-taker. An interactive virtual environment built with Unity is provided, allowing the test-taker to view the necessary learning materials and assignments through the visual device. These processes are centrally managed, and the test-taker can interact with a virtual instructor in real time.

[0115] Users can enjoy a visual and interactive learning experience through modules provided within a virtual environment. Learning plans are dynamically updated to allow learners to focus on areas where they struggle.

[0116] For example, if a user needs to deepen their understanding of mathematics, the server analyzes the student's past practice test results and creates assignments tailored to their weak areas in mathematics. Then, through a visual device, the user is presented with application problems involving functions and geometry. A virtual instructor responds to the user's questions in real time, facilitating learning.

[0117] An example of a prompt would be, "Suggest an efficient study plan for a student who struggles with function differentiation." This prompt serves as a guide for the generative AI model in constructing the optimal study plan for the student.

[0118] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0119] Step 1:

[0120] The server receives academic ability information of applicants and entrance examination information of their desired educational institutions as input from the user. This data is formatted according to a template and stored in a database. Based on the input information, data processing is performed to evaluate the applicant's academic ability and target level.

[0121] Step 2:

[0122] The server uses a generative AI model to generate personalized learning plans based on the applicant's current academic ability and the entrance exam information of their desired school. Following prompts, data calculations are performed to extract the applicant's weak areas from past mock exam results and set learning priorities based on that. The output is a learning plan tailored to each applicant.

[0123] Step 3:

[0124] The terminal presents the learning plan received from the server to the user through the smart device interface. Based on the learning plan received as input, it displays visual learning materials using a 3D graphics engine. The output is an interactive virtual learning environment.

[0125] Step 4:

[0126] Users wear visual devices and use learning materials provided within a virtual environment. In response to user input (e.g., gaze and gestures), the device generates feedback on the learning content and enables interaction with a virtual instructor. The output is a learning experience that progresses at the student's own pace.

[0127] Step 5:

[0128] The server dynamically updates the learning plan using the generative AI model again, based on the learning progress and user feedback. The input data consists of the user's learning outcomes and feedback, and the output is a newly generated learning plan, which is then provided to the user again.

[0129] 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.

[0130] This invention incorporates an emotion engine into a system that provides personalized learning plans for test-takers. It enables real-time recognition of the test-taker's emotional and motivational state, and dynamically adjusts the learning plan and feedback content based on this information. This helps maintain the test-taker's motivation to learn and reduces their mental burden.

[0131] System Overview

[0132] 1. Obtaining and entering applicant information

[0133] Users access the system and input their academic performance information, information about their desired educational institutions, and emotional data. The emotional data is analyzed by a dedicated emotional engine.

[0134] 2. Data processing and training plan generation

[0135] The server receives and stores data sent by the user. It then uses an AI-generated model to create a personalized learning plan for each test-taker. Furthermore, it optimizes the plan by taking into account the user's emotional state, as provided by the emotion engine.

[0136] 3. Real-time feedback via an emotion engine

[0137] The server monitors the test-taker's emotions and learning progress in real time and constantly updates the feedback. The emotion engine determines the user's emotional state from their facial expressions and tone of voice, and adjusts the difficulty level of the learning tasks and the question format based on that data.

[0138] 4. Presentation of a tailored learning plan

[0139] The device presents the user with an optimized learning plan provided by the server. This allows the user to learn at their own pace.

[0140] 5. Maintaining motivation in a virtual environment

[0141] The device provides users with a virtual environment, enabling test-takers to continue learning while enjoying the process. The emotional engine also helps in selecting music and videos to reduce learning stress.

[0142] Specific example

[0143] For example, suppose the emotion engine detects that a user is feeling confused or stressed while working on an English reading comprehension problem. In that case, the server immediately changes the plan to provide a slightly easier problem and include a short break. The device displays this plan and switches to an interface that helps the user relax. In this way, an environment is created that allows the user to learn comfortably and continuously.

[0144] The following describes the processing flow.

[0145] Step 1:

[0146] Users log in to the system via their device and input academic information, information about their desired educational institutions, past mock exam results, and emotional data. Emotional data is acquired using the camera and microphone.

[0147] Step 2:

[0148] The terminal sends all information entered by the user to the server. This data includes emotional information such as facial expression analysis results and voice analysis results.

[0149] Step 3:

[0150] The server uses an AI-generated model to create personalized learning plans for each user based on the received academic ability and entrance exam information. Furthermore, it incorporates emotional data provided by the emotion engine to adjust the learning difficulty level and add specific feedback content.

[0151] Step 4:

[0152] The server sends the generated learning plan to the device. The sent plan includes adjustments that take emotions into account.

[0153] Step 5:

[0154] The device displays the learning plan received from the server to the user. It provides an interface that includes emotionally responsive animations and voice guidance.

[0155] Step 6:

[0156] The user progresses through the learning process according to the provided learning plan. If a change in the user's emotions is detected during the learning process, this change is reflected in the feedback displayed on the device.

[0157] Step 7:

[0158] The device periodically uses an emotion engine to recognize the user's emotional state and reports the results to the server. It also suggests relaxation options to the user as needed.

[0159] Step 8:

[0160] The server analyzes the collected emotional data and makes further adjustments to the learning plan. For example, if the user is experiencing stress, it adjusts the pace of the plan to make learning more comfortable for the user.

[0161] Step 9:

[0162] In the virtual environment provided through the device, users can maintain their motivation to learn by interacting with other test-takers and experiencing relaxation content recommended by the emotion engine.

[0163] (Example 2)

[0164] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0165] Conventional learning support systems have a problem in that they provide a uniform learning plan for all test-takers, making it difficult to consider individual academic abilities and emotional states, which can lead to decreased motivation and increased stress. Furthermore, the lack of dynamically tailored feedback and support for enjoying learning has prevented them from providing an efficient and effective learning environment for test-takers.

[0166] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0167] In this invention, the server includes means for collecting information on the academic ability of test takers, means for obtaining information on educational institutions related to the test taker, means for using a generative model to create an individualized learning plan using the above information, means for analyzing the emotional state of the test taker, means for adjusting the learning plan while considering the academic ability information and emotional data, means for visually presenting the adjusted learning plan, means for generating feedback according to the progress of learning, and means for providing a learning experience through a virtual space. This makes it possible to provide a learning plan optimized for the individual state of the test taker and to realize an efficient and less stressful learning environment.

[0168] "Examinee" refers to a learner or student taking an examination who provides academic ability and emotional information to the system.

[0169] "Academic ability information" refers to data about the knowledge and abilities that test-takers currently possess, and it forms the basis for creating individualized learning plans.

[0170] "Information acquisition methods" refer to the functions and methods for collecting entrance examination information related to educational institutions, and are used to consider which institutions applicants are interested in.

[0171] "Emotional state" refers to the emotional reactions that test-takers experience during their studies, and it is an element that the system analyzes in real time and incorporates into the study plan.

[0172] A "generative model" refers to an algorithm or process that uses AI to automatically generate the optimal learning plan based on the academic ability and emotional data of test takers.

[0173] A "virtual space" is an environment constructed using digital technology, providing an interactive space where test-takers can learn in a relaxed environment.

[0174] "Feedback" refers to information and advice provided by the system according to the test-taker's learning progress, and is an indicator designed to improve the efficiency and effectiveness of learning.

[0175] This invention is a system for providing test takers with an individualized learning experience. The system consists of a server, a terminal, and user interaction.

[0176] Users input their academic performance information and emotional state through the device. The device captures facial expressions and voice tone using its camera and microphone, and an emotion engine analyzes this information. This information is sent to a server for storage and supplied to an AI-generated model for analysis.

[0177] The server receives this data and uses a generative AI model to create individualized learning plans for each test-taker. This model takes into account the user's unique academic ability and emotional data to provide an optimized plan. The server also monitors the test-taker's emotions in real time and dynamically adjusts the plan as needed.

[0178] The device, following instructions from the server, presents the user with an optimized learning plan. This allows the user to learn at their own pace. The device also plays a role in providing a virtual environment, creating an immersive learning experience. Relaxing music and visual effects are used in the virtual environment, which are also selected by the emotion engine.

[0179] As a concrete example, let's assume a user is solving a math problem. If the emotion engine detects that the user is experiencing frustration, the server immediately adjusts the difficulty level of the learning task, and the device displays a problem accordingly. In this way, the system reduces the user's stress and provides an environment that makes it easier to continue learning.

[0180] An example of a prompt is: "Analyze the emotions the test-taker feels about a particular subject, and adjust the study plan based on those emotions."

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

[0182] Step 1:

[0183] Users input their academic performance and emotional state using a device. This includes inputting academic performance information as text data through an interface, and recording facial expressions and voice tone in real time using a camera and microphone. The input data is sent directly to the server.

[0184] Step 2:

[0185] The server stores the received academic performance information and emotional data in a database. This database storage process creates the foundation for subsequent analysis. The output of this step is the information stored in the database.

[0186] Step 3:

[0187] The server uses an emotion engine to analyze the received emotion data. The analysis uses facial recognition algorithms and voice analysis technology to identify the test-taker's emotional state, and generates an emotion score based on the results. This score is output and passed on to the next step.

[0188] Step 4:

[0189] The server utilizes a generative AI model to generate personalized learning plans tailored to each test-taker, using academic performance information and emotional scores as arguments. The AI ​​analyzes this data and automatically combines the most suitable learning materials and assignments for each test-taker's abilities and condition, outputting a new learning plan.

[0190] Step 5:

[0191] The server updates the generated learning plan in real time. It dynamically adjusts the learning plan by taking into account the test-taker's progress and emotional changes, and providing feedback as needed. This adjusted plan is output and sent to the terminal.

[0192] Step 6:

[0193] The terminal visually presents the adjusted learning plan sent from the server to the test-taker. This includes clearly displaying the plan on the user interface and providing visual feedback to support learning progress.

[0194] Step 7:

[0195] The device provides test-takers with a relaxing learning environment through a virtual environment. It uses music and videos to reduce stress and help maintain motivation. Content is selected and changed according to the instructions of the emotion engine, resulting in an effective learning environment.

[0196] (Application Example 2)

[0197] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0198] In current examination and educational settings, there is a lack of flexible learning plans that cater to the emotional state and individual needs of test-takers. Furthermore, in real-world consumer experiences, there is a lack of methods for providing personalized suggestions based on customer emotions. This leads to problems such as decreased motivation to learn and reduced purchasing intent.

[0199] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0200] In this invention, the server includes means for analyzing the emotional state of the test taker in real time, means for dynamically adjusting the learning plan and feedback according to the emotional state, and means for emotional analysis and suggestion adjustment for providing personalized product suggestions in the real world. This makes it possible to optimize the learning experience to meet individual needs and provide product suggestions based on the consumer's emotions.

[0201] An "examinee" is an individual who prepares for and studies to take an exam.

[0202] "Academic ability information" refers to data that indicates the current level of knowledge and skills of the test taker.

[0203] "Desired educational institution" refers to the specific educational institution that the applicant wishes to attend or enroll in.

[0204] "Entrance examination information" refers to all data related to the entrance examinations administered by the educational institution you wish to attend.

[0205] A "generative model" is an algorithm used to create personalized learning plans based on input information.

[0206] A "study plan" is a plan outlining the time allocation and content of study, designed to effectively guide a test-taker's learning.

[0207] "Feedback" refers to evaluations and suggestions for improvement provided regarding learning content and progress.

[0208] A "virtual environment" is a simulated space recreated on a computer, where test-takers can experience learning.

[0209] "Emotional state" refers to the psychological sensations and emotional conditions that a test-taker experiences at a specific time.

[0210] "Dynamic adjustment" refers to making adjustments or changes in real time in response to changes in the situation or data.

[0211] A "product suggestion" is a recommendation of a specific product or service presented in response to consumer needs and emotions.

[0212] This invention is a system that analyzes the emotional state of test takers in real time and dynamically adjusts learning plans and feedback. Furthermore, it also has a function to provide personalized product recommendations in the real world.

[0213] In this system, the server plays a central role and performs the main processing. The server receives academic ability information and entrance examination information for desired educational institutions from the user, and uses this data to create a personalized learning plan using a generative AI model. The generative model uses AI algorithms to design an optimized plan. The server also uses an emotion engine (e.g., Microsoft® Azure Emotion API) that analyzes the user's facial image and voice tone to determine their emotional state. Based on the emotional data, it is possible to adjust feedback and learning plans in real time.

[0214] The device plays the role of presenting the user with generated learning plans and feedback. Examples include smart glasses or smartphones with learning applications installed. This allows the user to continuously receive an optimized learning experience.

[0215] Meanwhile, in physical stores, customer emotions are analyzed by an emotion engine via specific robots or smart glasses, and this data is processed on a server. The server then presents emotion-based product suggestions to actual store staff, providing real-time recommendations for the most suitable products and services.

[0216] For example, if the emotion engine detects stress in a user while they are learning English reading online, the server will adjust the learning plan and suggest easier problems or breaks. Another possible application is in a physical store, where if a customer shows interest in a product but appears somewhat tense, the system could suggest products with relaxing effects.

[0217] Example prompt for a generative AI model: "Based on this customer's emotional state, please tell me the best way to suggest products that have a relaxing effect."

[0218] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0219] Step 1:

[0220] The server receives academic ability information and entrance examination information for the educational institutions the user is applying to. The input data includes the applicant's past grades, study progress, and desired passing criteria. This information is stored in a database and used in subsequent processing.

[0221] Step 2:

[0222] The server uses the terminal's emotion detection function to capture the test-taker's facial expressions and voice tone in real time and analyzes their emotional state. The input includes raw data collected from the camera and microphone, which is processed using an emotion engine. The output is the test-taker's current emotional state (e.g., stress, relaxation).

[0223] Step 3:

[0224] The server integrates the applicant's academic ability information, entrance exam information, and emotional state to create a personalized learning plan using a generative AI model. The input is the data obtained in Step 1 and Step 2, which is used to generate an optimized learning plan. The output is a customized learning plan to be presented to the user.

[0225] Step 4:

[0226] The terminal presents the user with a personalized learning plan provided by the server. The input here is learning plan data received from the server, and the output provides learning guidelines and study schedules that the user can easily understand. Specifically, the information is displayed on the terminal's screen.

[0227] Step 5:

[0228] The user progresses through the learning process based on the provided learning plan. The user's progress and responses are recorded on the device, and feedback is sent to the server. The input is the user's learning progress, and the output is feedback data regarding the user's learning.

[0229] Step 6:

[0230] When analyzing customer emotions in a physical store and making product recommendations, the server processes video and audio data from within the store. Input is emotion data from cameras and audio devices, which is evaluated by an emotion engine. Output is personalized product recommendations based on those emotions.

[0231] This series of steps provides test takers with an optimized learning experience and customers with emotion-based product recommendations.

[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 is an educational support system aimed at improving the efficiency of learning and maintaining motivation for students preparing for exams. The system provides individualized learning plans to a large number of users (students preparing for exams), thereby enabling efficient exam preparation.

[0249] System Overview

[0250] 1. Enter applicant information

[0251] Users access the system and input their academic ability information and information about the educational institutions they wish to attend. Users can also input their past mock exam results and their current level of understanding of the subjects they are studying.

[0252] 2. Data Processing

[0253] The server receives academic ability information and entrance exam information for desired schools from the user and stores this information in a database. Based on this data, the server uses an AI generative model to construct a different learning plan for each user.

[0254] 3. Presentation and adjustment of the learning plan

[0255] The server sends the generated learning plan to the device. The learning plan includes recommended learning content, learning frequency, and required review items. The AI ​​continuously evaluates the user's learning progress and dynamically adjusts the plan's content.

[0256] 4. Learning in a virtual environment

[0257] The terminal provides users with a virtual environment. Within this environment, users can interact with other test-takers and converse with virtual tutors. This is a measure taken to improve motivation.

[0258] Specific example

[0259] For example, when a user is preparing for a mathematics entrance exam, the system analyzes the user's weaknesses based on their past mathematics practice test data. Based on this analysis, the server adjusts the learning content for each topic, such as "functions" or "geometry," and generates interactive assignments. The terminal promptly presents the user with the assignments to be solved and detailed explanations. This allows the user to focus their learning at their own pace.

[0260] This system allows users to efficiently prepare for entrance exams at their desired educational institutions while monitoring their daily learning progress. Furthermore, by utilizing a virtual environment, it reduces the isolation of studying and alleviates the mental burden of exam preparation.

[0261] The following describes the processing flow.

[0262] Step 1:

[0263] The user logs into the device and enters their basic information, academic information, and data on the educational institution they wish to attend. This allows the system to collect the user's individual data.

[0264] Step 2:

[0265] The terminal sends user input information to the server. This includes past mock exam results and current school preference information. The terminal confirms that the transmission was successful and notifies the user of the progress.

[0266] Step 3:

[0267] The server stores the data received from the terminal in a database. Furthermore, it applies an AI-generated model to the stored data to create a personalized learning plan tailored to the user's academic ability. This plan includes recommended learning content for each subject and items that require high review.

[0268] Step 4:

[0269] The server sends the created learning plan to the user's device. At that time, it prioritizes the recommended learning content included in the plan according to each user's progress.

[0270] Step 5:

[0271] The device presents the received learning plan to the user. It guides the user through the learning process by displaying necessary learning materials, video explanations, and practice problems step by step.

[0272] Step 6:

[0273] Users progress through their daily studies based on the learning plan displayed on their device. They learn efficiently at their own pace by solving problems and watching video explanations.

[0274] Step 7:

[0275] The device continuously records the user's learning progress. For example, it reports the time taken to answer each problem and the correct answer rate to the server, accumulating progress data.

[0276] Step 8:

[0277] The server analyzes the collected study progress data and incorporates it into new learning plans. In particular, it prioritizes areas where the user struggles and their current learning progress, dynamically updating the plan accordingly.

[0278] Step 9:

[0279] In the virtual environment provided by the device, users can participate in study rooms and receive support from virtual characters, thereby maintaining their motivation to learn and reducing mental burden.

[0280] (Example 1)

[0281] 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."

[0282] The challenge lies in efficiently supporting test-takers' learning and realizing optimal learning tailored to each individual's academic ability and aspirations. In particular, it is necessary to provide personalized learning plans that address the unique circumstances of each test-taker, maintain their motivation to learn, and reduce feelings of isolation.

[0283] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in the first embodiment is realized by the following means.

[0284] In this invention, the server includes means for inputting the current ability information of the examinee, means for acquiring the test information of the educational institution the examinee wishes to enter, and means for using a generation model for generating an individualized educational plan. As a result, the examinee can receive an effective learning plan based on their academic ability and aspirations, and it becomes possible to improve learning motivation and reduce feelings of loneliness through the learning experience in the virtual space.

[0285] An "examinee" refers to a learner who aims to take an exam.

[0286] "Ability information" is a set of data indicating the academic ability and comprehension level of the examinee.

[0287] [[ID=No.18]]"Educational institution the examinee wishes to enter" refers to an educational facility that the examinee aims to enroll in.

[0288] "Test information" is information referring to data and requirements related to the entrance examination.

[0289] An "educational plan" is a guiding guideline formulated to effectively promote the learning of the examinee.

[0290] A "generation model" is an algorithm that automatically creates an educational plan based on the ability information and test information of the examinee.

[0291] A "virtual space" refers to a virtual learning environment created using digital technology.

[0292] A "motivation maintenance method" is a technology that includes various approaches for enhancing and maintaining the learning motivation of the examinee.

[0293] This invention is a learning support system for test takers, aiming to provide an individualized educational plan. The system is configured and operates as follows:

[0294] Users first access the system using a web browser. They input their own information, such as past exam results and their current level of understanding of subjects. The interface used for this is a web application utilizing HTML and JavaScript.

[0295] The server stores the ability information submitted by the user and the examination information of the educational institution the user wishes to attend in a database. A database management system such as MySQL is used for this database. The server uses a generative AI model to generate a personalized educational plan for each user. Here, the AI ​​model is given the prompt statement, "Create a personalized educational plan based on the user's academic ability information."

[0296] The generated lesson plan is sent from the server to the terminal. The terminal displays the plan on its screen to make it easy for the user to understand. At this stage, the user can communicate with other test-takers in a virtual space and interact with a virtual tutor. This environment is built using virtual reality technologies such as Unity or Unreal Engine.

[0297] For example, when a user is preparing for an English exam, the system analyzes their weaknesses based on past practice test data and generates a focused study plan for frequently appearing questions. The server generates assignments to improve skills such as listening and speaking. The terminal presents these assignments to the user, provides explanations, and feeds back the progress to the server.

[0298] This system allows users to obtain an educational plan optimized for them and an environment that enables them to learn at their own pace.

[0299] The flow of the specific process in Example 1 will be described using FIG. 11.

[0300] Step 1:

[0301] The user accesses the system using a web browser and enters their own ability information and the exam information of the educational institution they aspire to. The information entered includes past mock exam results and the current learning situation. These input data are sent to the server when the send button is pressed.

[0302] Step 2:

[0303] The server analyzes the input data received from the user and saves it in the database. Here, a data management system such as MySQL is used for the database. The input data undergoes format checking and is saved in a normalized state. The saved data serves as the basic information for generating an educational plan in subsequent processing.

[0304] Step 3:

[0305] The server executes the generated AI model using the saved user data. Specifically, a prompt sentence such as "Create an individualized educational plan based on the user's academic ability information" is given as an input to the AI model. The generated AI model performs data analysis based on this and outputs an individualized educational plan adapted to the user.

[0306] Step 4:

[0307] The generated educational plan is sent from the server to the terminal. The terminal receives this plan as a recipient and displays it in an easy-to-understand manner for the user. The specific output includes the learning content of each subject and the recommended learning timeline. The user can proceed with learning based on this.

[0308] Step 5:

[0309] The terminal provides users with a virtual space that allows them to interact with other test-takers. This virtual space is built using tools such as Unity and Unreal Engine. Users can confirm learning content and get answers to their questions through a dialogue function with a virtual tutor. Learning progress data obtained through information exchange is periodically sent to the server and used to revise the educational plan.

[0310] (Application Example 1)

[0311] 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."

[0312] In exam preparation, there is a need for individualized learning that caters to the diverse needs of students. Furthermore, new methods are required to maintain motivation while efficiently advancing learning. However, the current education system makes it difficult to provide each student with an optimized learning plan and a rich learning experience. Maintaining sustained motivation is a major challenge, especially in a learning environment that tends to be isolated.

[0313] 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.

[0314] In this invention, the server includes means for inputting the applicant's current academic ability information, means for obtaining entrance examination information of the educational institution the applicant wishes to attend, and means for using a generative model to generate an individualized learning plan. This makes it possible to provide applicants with an individualized learning plan and to realize an interactive learning experience through a visual device.

[0315] "Means for inputting the applicant's current academic ability information" refers to the technical means for incorporating the applicant's academic status into the system, and designing an individualized learning plan based on the input information.

[0316] "Means of obtaining entrance examination information for desired educational institutions" refers to technical means of obtaining information on the examination content and standards of the target school for applicants, and using that information to help construct a study plan.

[0317] "Methods using generative models" refer to methods that utilize AI models to generate personalized learning plans for each student taking the exam.

[0318] "Means for generating feedback on learning content" refers to methods for evaluating the level of understanding and progress of test-takers and providing information on areas for improvement and achievement.

[0319] "Means of providing a learning experience in a virtual environment" refers to providing an environment in which examinees can study in a virtual space and gain a richer learning experience.

[0320] "Means using visual devices" refers to devices or technologies used to provide students with visual learning materials and to enable them to intuitively understand the content.

[0321] "A means of supporting learning through real-time interaction with a virtual instructor" refers to a technological means of supporting learning by enabling immediate communication between a virtual instructor and a student.

[0322] "Motivation maintenance techniques" refer to psychological or technical methods used to enhance and maintain students' motivation to learn.

[0323] This invention is designed to effectively provide learning support for students preparing for exams. The main hardware used includes smart devices, such as smart glasses. The system also features a cloud server and AI platform, and the software utilizes Unity, TensorFlow, and Azure Cloud Services.

[0324] The server is responsible for acquiring the applicant's current academic ability information and collecting entrance examination information for their desired educational institutions from a database. This makes it possible to design a learning plan optimized for each applicant. The server applies an AI generative model to integrate the applicant's past performance data with expected goals and generates a personalized learning plan.

[0325] The terminal, or smart device, visualizes the generated learning plan for the test-taker. An interactive virtual environment built with Unity is provided, allowing the test-taker to view the necessary learning materials and assignments through the visual device. These processes are centrally managed, and the test-taker can interact with a virtual instructor in real time.

[0326] Users can enjoy a visual and interactive learning experience through modules provided within a virtual environment. Learning plans are dynamically updated to allow learners to focus on areas where they struggle.

[0327] For example, if a user needs to deepen their understanding of mathematics, the server analyzes the student's past practice test results and creates assignments tailored to their weak areas in mathematics. Then, through a visual device, the user is presented with application problems involving functions and geometry. A virtual instructor responds to the user's questions in real time, facilitating learning.

[0328] An example of a prompt would be, "Suggest an efficient study plan for a student who struggles with function differentiation." This prompt serves as a guide for the generative AI model in constructing the optimal study plan for the student.

[0329] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0330] Step 1:

[0331] The server receives academic ability information of applicants and entrance examination information of their desired educational institutions as input from the user. This data is formatted according to a template and stored in a database. Based on the input information, data processing is performed to evaluate the applicant's academic ability and target level.

[0332] Step 2:

[0333] The server uses a generative AI model to generate personalized learning plans based on the applicant's current academic ability and the entrance exam information of their desired school. Following prompts, data calculations are performed to extract the applicant's weak areas from past mock exam results and set learning priorities based on that. The output is a learning plan tailored to each applicant.

[0334] Step 3:

[0335] The terminal presents the learning plan received from the server to the user through the smart device interface. Based on the learning plan received as input, it displays visual learning materials using a 3D graphics engine. The output is an interactive virtual learning environment.

[0336] Step 4:

[0337] Users wear visual devices and use learning materials provided within a virtual environment. In response to user input (e.g., gaze and gestures), the device generates feedback on the learning content and enables interaction with a virtual instructor. The output is a learning experience that progresses at the student's own pace.

[0338] Step 5:

[0339] The server dynamically updates the learning plan using the generative AI model again, based on the learning progress and user feedback. The input data consists of the user's learning outcomes and feedback, and the output is a newly generated learning plan, which is then provided to the user again.

[0340] 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.

[0341] This invention incorporates an emotion engine into a system that provides personalized learning plans for test-takers. It enables real-time recognition of the test-taker's emotional and motivational state, and dynamically adjusts the learning plan and feedback content based on this information. This helps maintain the test-taker's motivation to learn and reduces their mental burden.

[0342] System Overview

[0343] 1. Obtaining and entering applicant information

[0344] Users access the system and input their academic performance information, information about their desired educational institutions, and emotional data. The emotional data is analyzed by a dedicated emotional engine.

[0345] 2. Data processing and training plan generation

[0346] The server receives and stores data sent by the user. It then uses an AI-generated model to create a personalized learning plan for each test-taker. Furthermore, it optimizes the plan by taking into account the user's emotional state, as provided by the emotion engine.

[0347] 3. Real-time feedback via an emotion engine

[0348] The server monitors the test-taker's emotions and learning progress in real time and constantly updates the feedback. The emotion engine determines the user's emotional state from their facial expressions and tone of voice, and adjusts the difficulty level of the learning tasks and the question format based on that data.

[0349] 4. Presentation of a tailored learning plan

[0350] The device presents the user with an optimized learning plan provided by the server. This allows the user to learn at their own pace.

[0351] 5. Maintaining motivation in a virtual environment

[0352] The device provides users with a virtual environment, enabling test-takers to continue learning while enjoying the process. The emotional engine also helps in selecting music and videos to reduce learning stress.

[0353] Specific example

[0354] For example, suppose the emotion engine detects that a user is feeling confused or stressed while working on an English reading comprehension problem. In that case, the server immediately changes the plan to provide a slightly easier problem and include a short break. The device displays this plan and switches to an interface that helps the user relax. In this way, an environment is created that allows the user to learn comfortably and continuously.

[0355] The following describes the processing flow.

[0356] Step 1:

[0357] Users log in to the system via their device and input academic information, information about their desired educational institutions, past mock exam results, and emotional data. Emotional data is acquired using the camera and microphone.

[0358] Step 2:

[0359] The terminal sends all information entered by the user to the server. This data includes emotional information such as facial expression analysis results and voice analysis results.

[0360] Step 3:

[0361] The server uses an AI-generated model to create personalized learning plans for each user based on the received academic ability and entrance exam information. Furthermore, it incorporates emotional data provided by the emotion engine to adjust the learning difficulty level and add specific feedback content.

[0362] Step 4:

[0363] The server sends the generated learning plan to the device. The sent plan includes adjustments that take emotions into account.

[0364] Step 5:

[0365] The device displays the learning plan received from the server to the user. It provides an interface that includes emotionally responsive animations and voice guidance.

[0366] Step 6:

[0367] The user progresses through the learning process according to the provided learning plan. If a change in the user's emotions is detected during the learning process, this change is reflected in the feedback displayed on the device.

[0368] Step 7:

[0369] The device periodically uses an emotion engine to recognize the user's emotional state and reports the results to the server. It also suggests relaxation options to the user as needed.

[0370] Step 8:

[0371] The server analyzes the collected emotional data and makes further adjustments to the learning plan. For example, if the user is experiencing stress, it adjusts the pace of the plan to make learning more comfortable for the user.

[0372] Step 9:

[0373] In the virtual environment provided through the device, users can maintain their motivation to learn by interacting with other test-takers and experiencing relaxation content recommended by the emotion engine.

[0374] (Example 2)

[0375] 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".

[0376] Conventional learning support systems have a problem in that they provide a uniform learning plan for all test-takers, making it difficult to consider individual academic abilities and emotional states, which can lead to decreased motivation and increased stress. Furthermore, the lack of dynamically tailored feedback and support for enjoying learning has prevented them from providing an efficient and effective learning environment for test-takers.

[0377] 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.

[0378] In this invention, the server includes means for collecting information on the academic ability of test takers, means for obtaining information on educational institutions related to the test taker, means for using a generative model to create an individualized learning plan using the above information, means for analyzing the emotional state of the test taker, means for adjusting the learning plan while considering the academic ability information and emotional data, means for visually presenting the adjusted learning plan, means for generating feedback according to the progress of learning, and means for providing a learning experience through a virtual space. This makes it possible to provide a learning plan optimized for the individual state of the test taker and to realize an efficient and less stressful learning environment.

[0379] "Examinee" refers to a learner or student taking an examination who provides academic ability and emotional information to the system.

[0380] "Academic ability information" refers to data about the knowledge and abilities that test-takers currently possess, and it forms the basis for creating individualized learning plans.

[0381] "Information acquisition methods" refer to the functions and methods for collecting entrance examination information related to educational institutions, and are used to consider which institutions applicants are interested in.

[0382] "Emotional state" refers to the emotional reactions that test-takers experience during their studies, and it is an element that the system analyzes in real time and incorporates into the study plan.

[0383] A "generative model" refers to an algorithm or process that uses AI to automatically generate the optimal learning plan based on the academic ability and emotional data of test takers.

[0384] A "virtual space" is an environment constructed using digital technology, providing an interactive space where test-takers can learn in a relaxed environment.

[0385] "Feedback" refers to information and advice provided by the system according to the test-taker's learning progress, and is an indicator designed to improve the efficiency and effectiveness of learning.

[0386] This invention is a system for providing test takers with an individualized learning experience. The system consists of a server, a terminal, and user interaction.

[0387] Users input their academic performance information and emotional state through the device. The device captures facial expressions and voice tone using its camera and microphone, and an emotion engine analyzes this information. This information is sent to a server for storage and supplied to an AI-generated model for analysis.

[0388] The server receives this data and uses a generative AI model to create individualized learning plans for each test-taker. This model takes into account the user's unique academic ability and emotional data to provide an optimized plan. The server also monitors the test-taker's emotions in real time and dynamically adjusts the plan as needed.

[0389] The device, following instructions from the server, presents the user with an optimized learning plan. This allows the user to learn at their own pace. The device also plays a role in providing a virtual environment, creating an immersive learning experience. Relaxing music and visual effects are used in the virtual environment, which are also selected by the emotion engine.

[0390] As a concrete example, let's assume a user is solving a math problem. If the emotion engine detects that the user is experiencing frustration, the server immediately adjusts the difficulty level of the learning task, and the device displays a problem accordingly. In this way, the system reduces the user's stress and provides an environment that makes it easier to continue learning.

[0391] An example of a prompt is: "Analyze the emotions the test-taker feels about a particular subject, and adjust the study plan based on those emotions."

[0392] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0393] Step 1:

[0394] Users input their academic performance and emotional state using a device. This includes inputting academic performance information as text data through an interface, and recording facial expressions and voice tone in real time using a camera and microphone. The input data is sent directly to the server.

[0395] Step 2:

[0396] The server stores the received academic performance information and emotional data in a database. This database storage process creates the foundation for subsequent analysis. The output of this step is the information stored in the database.

[0397] Step 3:

[0398] The server uses an emotion engine to analyze the received emotion data. The analysis uses facial recognition algorithms and voice analysis technology to identify the test-taker's emotional state, and generates an emotion score based on the results. This score is output and passed on to the next step.

[0399] Step 4:

[0400] The server utilizes a generative AI model to generate personalized learning plans tailored to each test-taker, using academic performance information and emotional scores as arguments. The AI ​​analyzes this data and automatically combines the most suitable learning materials and assignments for each test-taker's abilities and condition, outputting a new learning plan.

[0401] Step 5:

[0402] The server updates the generated learning plan in real time. It dynamically adjusts the learning plan by taking into account the test-taker's progress and emotional changes, and providing feedback as needed. This adjusted plan is output and sent to the terminal.

[0403] Step 6:

[0404] The terminal visually presents the adjusted learning plan sent from the server to the test-taker. This includes clearly displaying the plan on the user interface and providing visual feedback to support learning progress.

[0405] Step 7:

[0406] The device provides test-takers with a relaxing learning environment through a virtual environment. It uses music and videos to reduce stress and help maintain motivation. Content is selected and changed according to the instructions of the emotion engine, resulting in an effective learning environment.

[0407] (Application Example 2)

[0408] 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."

[0409] In current examination and educational settings, there is a lack of flexible learning plans that cater to the emotional state and individual needs of test-takers. Furthermore, in real-world consumer experiences, there is a lack of methods for providing personalized suggestions based on customer emotions. This leads to problems such as decreased motivation to learn and reduced purchasing intent.

[0410] 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.

[0411] In this invention, the server includes means for analyzing the emotional state of the test taker in real time, means for dynamically adjusting the learning plan and feedback according to the emotional state, and means for emotional analysis and suggestion adjustment for providing personalized product suggestions in the real world. This makes it possible to optimize the learning experience to meet individual needs and provide product suggestions based on the consumer's emotions.

[0412] An "examinee" is an individual who prepares for and studies to take an exam.

[0413] "Academic ability information" refers to data that indicates the current level of knowledge and skills of the test taker.

[0414] "Desired educational institution" refers to the specific educational institution that the applicant wishes to attend or enroll in.

[0415] "Entrance examination information" refers to all data related to the entrance examinations administered by the educational institution you wish to attend.

[0416] A "generative model" is an algorithm used to create personalized learning plans based on input information.

[0417] A "study plan" is a plan outlining the time allocation and content of study, designed to effectively guide a test-taker's learning.

[0418] "Feedback" refers to evaluations and suggestions for improvement provided regarding learning content and progress.

[0419] A "virtual environment" is a simulated space recreated on a computer, where test-takers can experience learning.

[0420] "Emotional state" refers to the psychological sensations and emotional conditions that a test-taker experiences at a specific time.

[0421] "Dynamic adjustment" refers to making adjustments or changes in real time in response to changes in the situation or data.

[0422] A "product suggestion" is a recommendation of a specific product or service presented in response to consumer needs and emotions.

[0423] This invention is a system that analyzes the emotional state of test takers in real time and dynamically adjusts learning plans and feedback. Furthermore, it also has a function to provide personalized product recommendations in the real world.

[0424] In this system, the server plays a central role and performs the main processing. The server receives academic ability information and entrance examination information for desired educational institutions from the user, and uses this data to create a personalized learning plan using a generative AI model. The generative model uses AI algorithms to design an optimized plan. The server also uses an emotion engine (e.g., Microsoft Azure Emotion API) that analyzes the user's facial image and voice tone to determine their emotional state. Based on the emotional data, it is possible to adjust feedback and learning plans in real time.

[0425] The device plays the role of presenting the user with generated learning plans and feedback. Examples include smart glasses or smartphones with learning applications installed. This allows the user to continuously receive an optimized learning experience.

[0426] Meanwhile, in physical stores, customer emotions are analyzed by an emotion engine via specific robots or smart glasses, and this data is processed on a server. The server then presents emotion-based product suggestions to actual store staff, providing real-time recommendations for the most suitable products and services.

[0427] For example, if the emotion engine detects stress in a user while they are learning English reading online, the server will adjust the learning plan and suggest easier problems or breaks. Another possible application is in a physical store, where if a customer shows interest in a product but appears somewhat tense, the system could suggest products with relaxing effects.

[0428] Example prompt for a generative AI model: "Based on this customer's emotional state, please tell me the best way to suggest products that have a relaxing effect."

[0429] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0430] Step 1:

[0431] The server receives academic ability information and entrance examination information for the educational institutions the user is applying to. The input data includes the applicant's past grades, study progress, and desired passing criteria. This information is stored in a database and used in subsequent processing.

[0432] Step 2:

[0433] The server uses the terminal's emotion detection function to capture the test-taker's facial expressions and voice tone in real time and analyzes their emotional state. The input includes raw data collected from the camera and microphone, which is processed using an emotion engine. The output is the test-taker's current emotional state (e.g., stress, relaxation).

[0434] Step 3:

[0435] The server integrates the applicant's academic ability information, entrance exam information, and emotional state to create a personalized learning plan using a generative AI model. The input is the data obtained in Step 1 and Step 2, which is used to generate an optimized learning plan. The output is a customized learning plan to be presented to the user.

[0436] Step 4:

[0437] The terminal presents the user with a personalized learning plan provided by the server. The input here is learning plan data received from the server, and the output provides learning guidelines and study schedules that the user can easily understand. Specifically, the information is displayed on the terminal's screen.

[0438] Step 5:

[0439] The user progresses through the learning process based on the provided learning plan. The user's progress and responses are recorded on the device, and feedback is sent to the server. The input is the user's learning progress, and the output is feedback data regarding the user's learning.

[0440] Step 6:

[0441] When analyzing customer emotions in a physical store and making product recommendations, the server processes video and audio data from within the store. Input is emotion data from cameras and audio devices, which is evaluated by an emotion engine. Output is personalized product recommendations based on those emotions.

[0442] This series of steps provides test takers with an optimized learning experience and customers with emotion-based product recommendations.

[0443] 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.

[0444] 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.

[0445] 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.

[0446] [Third Embodiment]

[0447] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0448] 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.

[0449] 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).

[0450] 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.

[0451] 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.

[0452] 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).

[0453] 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.

[0454] 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.

[0455] 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.

[0456] 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.

[0457] 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.

[0458] 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".

[0459] This invention is an educational support system aimed at improving the efficiency of learning and maintaining motivation for students preparing for exams. The system provides individualized learning plans to a large number of users (students preparing for exams), thereby enabling efficient exam preparation.

[0460] System Overview

[0461] 1. Enter applicant information

[0462] Users access the system and input their academic ability information and information about the educational institutions they wish to attend. Users can also input their past mock exam results and their current level of understanding of the subjects they are studying.

[0463] 2. Data Processing

[0464] The server receives academic ability information and entrance exam information for desired schools from the user and stores this information in a database. Based on this data, the server uses an AI generative model to construct a different learning plan for each user.

[0465] 3. Presentation and adjustment of the learning plan

[0466] The server sends the generated learning plan to the device. The learning plan includes recommended learning content, learning frequency, and required review items. The AI ​​continuously evaluates the user's learning progress and dynamically adjusts the plan's content.

[0467] 4. Learning in a virtual environment

[0468] The terminal provides users with a virtual environment. Within this environment, users can interact with other test-takers and converse with virtual tutors. This is a measure taken to improve motivation.

[0469] Specific example

[0470] For example, when a user is preparing for a mathematics entrance exam, the system analyzes the user's weaknesses based on their past mathematics practice test data. Based on this analysis, the server adjusts the learning content for each topic, such as "functions" or "geometry," and generates interactive assignments. The terminal promptly presents the user with the assignments to be solved and detailed explanations. This allows the user to focus their learning at their own pace.

[0471] This system allows users to efficiently prepare for entrance exams at their desired educational institutions while monitoring their daily learning progress. Furthermore, by utilizing a virtual environment, it reduces the isolation of studying and alleviates the mental burden of exam preparation.

[0472] The following describes the processing flow.

[0473] Step 1:

[0474] The user logs into the device and enters their basic information, academic information, and data on the educational institution they wish to attend. This allows the system to collect the user's individual data.

[0475] Step 2:

[0476] The terminal sends user input information to the server. This includes past mock exam results and current school preference information. The terminal confirms that the transmission was successful and notifies the user of the progress.

[0477] Step 3:

[0478] The server stores the data received from the terminal in a database. Furthermore, it applies an AI-generated model to the stored data to create a personalized learning plan tailored to the user's academic ability. This plan includes recommended learning content for each subject and items that require high review.

[0479] Step 4:

[0480] The server sends the created learning plan to the user's device. At that time, it prioritizes the recommended learning content included in the plan according to each user's progress.

[0481] Step 5:

[0482] The device presents the received learning plan to the user. It guides the user through the learning process by displaying necessary learning materials, video explanations, and practice problems step by step.

[0483] Step 6:

[0484] Users progress through their daily studies based on the learning plan displayed on their device. They learn efficiently at their own pace by solving problems and watching video explanations.

[0485] Step 7:

[0486] The device continuously records the user's learning progress. For example, it reports the time taken to answer each problem and the correct answer rate to the server, accumulating progress data.

[0487] Step 8:

[0488] The server analyzes the collected study progress data and incorporates it into new learning plans. In particular, it prioritizes areas where the user struggles and their current learning progress, dynamically updating the plan accordingly.

[0489] Step 9:

[0490] In the virtual environment provided by the device, users can participate in study rooms and receive support from virtual characters, thereby maintaining their motivation to learn and reducing mental burden.

[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] The challenge lies in efficiently supporting test-takers' learning and realizing optimal learning tailored to each individual's academic ability and aspirations. In particular, it is necessary to provide personalized learning plans that address the unique circumstances of each test-taker, maintain their motivation to learn, and reduce feelings of isolation.

[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 inputting the examinee's current ability information, means for obtaining examination information from the educational institution they wish to attend, and means for using a generative model to generate an individualized learning plan. As a result, examinees receive an effective learning plan based on their academic ability and aspirations, and the learning experience through a virtual space can improve their motivation to learn and reduce feelings of isolation.

[0496] An "examinee" is a learner whose purpose is to take an examination.

[0497] "Ability information" refers to a collection of data that indicates the academic ability and level of understanding of the test taker.

[0498] "Desired educational institution" refers to the educational institution that the applicant aims to enroll in.

[0499] "Examination information" refers to data and requirements related to entrance examinations.

[0500] An "educational plan" is a set of teaching guidelines formulated to effectively guide the learning of test-takers.

[0501] A "generative model" is an algorithm that automatically creates an educational plan based on the applicant's ability information and test information.

[0502] A "virtual space" refers to a virtual learning environment created using digital technology.

[0503] "Motivation maintenance techniques" refer to a set of techniques that include various approaches to enhance and maintain the learning motivation of test-takers.

[0504] This invention is a learning support system for test takers, aiming to provide an individualized educational plan. The system is configured and operates as follows:

[0505] Users first access the system using a web browser. They input their own information, such as past exam results and their current level of understanding of subjects. The interface used for this is a web application utilizing HTML and JavaScript.

[0506] The server stores the ability information submitted by the user and the examination information of the educational institution the user wishes to attend in a database. A database management system such as MySQL is used for this database. The server uses a generative AI model to generate a personalized educational plan for each user. Here, the AI ​​model is given the prompt statement, "Create a personalized educational plan based on the user's academic ability information."

[0507] The generated lesson plan is sent from the server to the terminal. The terminal displays the plan on its screen to make it easy for the user to understand. At this stage, the user can communicate with other test-takers in a virtual space and interact with a virtual tutor. This environment is built using virtual reality technologies such as Unity or Unreal Engine.

[0508] For example, when a user is preparing for an English exam, the system analyzes their weaknesses based on past practice test data and generates a focused study plan for frequently appearing questions. The server generates assignments to improve skills such as listening and speaking. The terminal presents these assignments to the user, provides explanations, and feeds back the progress to the server.

[0509] This system allows users to obtain an educational plan optimized for them and an environment that enables them to learn at their own pace.

[0510] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0511] Step 1:

[0512] Users access the system using a web browser and enter their own ability information and exam information for their desired educational institution. This information includes past mock exam scores and current study status. This data is sent to the server when the submit button is pressed.

[0513] Step 2:

[0514] The server parses the input data received from the user and stores it in a database. A data management system such as MySQL is used for this database. The input data undergoes format checks and is stored in a normalized state. The stored data then serves as the foundational information for generating educational plans in subsequent processing.

[0515] Step 3:

[0516] The server runs a generative AI model using stored user data. Specifically, it provides the AI ​​model with the prompt, "Create an individualized educational plan based on the user's academic ability information." The generative AI model then performs data analysis based on this prompt and outputs an individualized educational plan adapted to the user.

[0517] Step 4:

[0518] The generated learning plan is sent from the server to the terminal. The terminal receives this plan and displays it in an easy-to-understand format for the user. The specific output includes the learning content for each subject and a recommended learning timeline. The user can then proceed with their learning based on this information.

[0519] Step 5:

[0520] The terminal provides users with a virtual space that allows them to interact with other test-takers. This virtual space is built using tools such as Unity and Unreal Engine. Users can confirm learning content and get answers to their questions through a dialogue function with a virtual tutor. Learning progress data obtained through information exchange is periodically sent to the server and used to revise the educational plan.

[0521] (Application Example 1)

[0522] 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."

[0523] In exam preparation, there is a need for individualized learning that caters to the diverse needs of students. Furthermore, new methods are required to maintain motivation while efficiently advancing learning. However, the current education system makes it difficult to provide each student with an optimized learning plan and a rich learning experience. Maintaining sustained motivation is a major challenge, especially in a learning environment that tends to be isolated.

[0524] 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.

[0525] In this invention, the server includes means for inputting the applicant's current academic ability information, means for obtaining entrance examination information of the educational institution the applicant wishes to attend, and means for using a generative model to generate an individualized learning plan. This makes it possible to provide applicants with an individualized learning plan and to realize an interactive learning experience through a visual device.

[0526] "Means for inputting the applicant's current academic ability information" refers to the technical means for incorporating the applicant's academic status into the system, and designing an individualized learning plan based on the input information.

[0527] "Means of obtaining entrance examination information for desired educational institutions" refers to technical means of obtaining information on the examination content and standards of the target school for applicants, and using that information to help construct a study plan.

[0528] "Methods using generative models" refer to methods that utilize AI models to generate personalized learning plans for each student taking the exam.

[0529] "Means for generating feedback on learning content" refers to methods for evaluating the level of understanding and progress of test-takers and providing information on areas for improvement and achievement.

[0530] "Means of providing a learning experience in a virtual environment" refers to providing an environment in which examinees can study in a virtual space and gain a richer learning experience.

[0531] "Means using visual devices" refers to devices or technologies used to provide students with visual learning materials and to enable them to intuitively understand the content.

[0532] "A means of supporting learning through real-time interaction with a virtual instructor" refers to a technological means of supporting learning by enabling immediate communication between a virtual instructor and a student.

[0533] "Motivation maintenance techniques" refer to psychological or technical methods used to enhance and maintain students' motivation to learn.

[0534] This invention is designed to effectively provide learning support for students preparing for exams. The main hardware used includes smart devices, such as smart glasses. The system also features a cloud server and AI platform, and the software utilizes Unity, TensorFlow, and Azure Cloud Services.

[0535] The server is responsible for acquiring the applicant's current academic ability information and collecting entrance examination information for their desired educational institutions from a database. This makes it possible to design a learning plan optimized for each applicant. The server applies an AI generative model to integrate the applicant's past performance data with expected goals and generates a personalized learning plan.

[0536] The terminal, or smart device, visualizes the generated learning plan for the test-taker. An interactive virtual environment built with Unity is provided, allowing the test-taker to view the necessary learning materials and assignments through the visual device. These processes are centrally managed, and the test-taker can interact with a virtual instructor in real time.

[0537] Users can enjoy a visual and interactive learning experience through modules provided within a virtual environment. Learning plans are dynamically updated to allow learners to focus on areas where they struggle.

[0538] For example, if a user needs to deepen their understanding of mathematics, the server analyzes the student's past practice test results and creates assignments tailored to their weak areas in mathematics. Then, through a visual device, the user is presented with application problems involving functions and geometry. A virtual instructor responds to the user's questions in real time, facilitating learning.

[0539] An example of a prompt would be, "Suggest an efficient study plan for a student who struggles with function differentiation." This prompt serves as a guide for the generative AI model in constructing the optimal study plan for the student.

[0540] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0541] Step 1:

[0542] The server receives academic ability information of applicants and entrance examination information of their desired educational institutions as input from the user. This data is formatted according to a template and stored in a database. Based on the input information, data processing is performed to evaluate the applicant's academic ability and target level.

[0543] Step 2:

[0544] The server uses a generative AI model to generate personalized learning plans based on the applicant's current academic ability and the entrance exam information of their desired school. Following prompts, data calculations are performed to extract the applicant's weak areas from past mock exam results and set learning priorities based on that. The output is a learning plan tailored to each applicant.

[0545] Step 3:

[0546] The terminal presents the learning plan received from the server to the user through the smart device interface. Based on the learning plan received as input, it displays visual learning materials using a 3D graphics engine. The output is an interactive virtual learning environment.

[0547] Step 4:

[0548] Users wear visual devices and use learning materials provided within a virtual environment. In response to user input (e.g., gaze and gestures), the device generates feedback on the learning content and enables interaction with a virtual instructor. The output is a learning experience that progresses at the student's own pace.

[0549] Step 5:

[0550] The server dynamically updates the learning plan using the generative AI model again, based on the learning progress and user feedback. The input data consists of the user's learning outcomes and feedback, and the output is a newly generated learning plan, which is then provided to the user again.

[0551] 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.

[0552] This invention incorporates an emotion engine into a system that provides personalized learning plans for test-takers. It enables real-time recognition of the test-taker's emotional and motivational state, and dynamically adjusts the learning plan and feedback content based on this information. This helps maintain the test-taker's motivation to learn and reduces their mental burden.

[0553] System Overview

[0554] 1. Obtaining and entering applicant information

[0555] Users access the system and input their academic performance information, information about their desired educational institutions, and emotional data. The emotional data is analyzed by a dedicated emotional engine.

[0556] 2. Data processing and training plan generation

[0557] The server receives and stores data sent by the user. It then uses an AI-generated model to create a personalized learning plan for each test-taker. Furthermore, it optimizes the plan by taking into account the user's emotional state, as provided by the emotion engine.

[0558] 3. Real-time feedback via an emotion engine

[0559] The server monitors the test-taker's emotions and learning progress in real time and constantly updates the feedback. The emotion engine determines the user's emotional state from their facial expressions and tone of voice, and adjusts the difficulty level of the learning tasks and the question format based on that data.

[0560] 4. Presentation of a tailored learning plan

[0561] The device presents the user with an optimized learning plan provided by the server. This allows the user to learn at their own pace.

[0562] 5. Maintaining motivation in a virtual environment

[0563] The device provides users with a virtual environment, enabling test-takers to continue learning while enjoying the process. The emotional engine also helps in selecting music and videos to reduce learning stress.

[0564] Specific example

[0565] For example, suppose the emotion engine detects that a user is feeling confused or stressed while working on an English reading comprehension problem. In that case, the server immediately changes the plan to provide a slightly easier problem and include a short break. The device displays this plan and switches to an interface that helps the user relax. In this way, an environment is created that allows the user to learn comfortably and continuously.

[0566] The following describes the processing flow.

[0567] Step 1:

[0568] Users log in to the system via their device and input academic information, information about their desired educational institutions, past mock exam results, and emotional data. Emotional data is acquired using the camera and microphone.

[0569] Step 2:

[0570] The terminal sends all information entered by the user to the server. This data includes emotional information such as facial expression analysis results and voice analysis results.

[0571] Step 3:

[0572] The server uses an AI-generated model to create personalized learning plans for each user based on the received academic ability and entrance exam information. Furthermore, it incorporates emotional data provided by the emotion engine to adjust the learning difficulty level and add specific feedback content.

[0573] Step 4:

[0574] The server sends the generated learning plan to the device. The sent plan includes adjustments that take emotions into account.

[0575] Step 5:

[0576] The device displays the learning plan received from the server to the user. It provides an interface that includes emotionally responsive animations and voice guidance.

[0577] Step 6:

[0578] The user progresses through the learning process according to the provided learning plan. If a change in the user's emotions is detected during the learning process, this change is reflected in the feedback displayed on the device.

[0579] Step 7:

[0580] The device periodically uses an emotion engine to recognize the user's emotional state and reports the results to the server. It also suggests relaxation options to the user as needed.

[0581] Step 8:

[0582] The server analyzes the collected emotional data and makes further adjustments to the learning plan. For example, if the user is experiencing stress, it adjusts the pace of the plan to make learning more comfortable for the user.

[0583] Step 9:

[0584] In the virtual environment provided through the device, users can maintain their motivation to learn by interacting with other test-takers and experiencing relaxation content recommended by the emotion engine.

[0585] (Example 2)

[0586] 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."

[0587] Conventional learning support systems have a problem in that they provide a uniform learning plan for all test-takers, making it difficult to consider individual academic abilities and emotional states, which can lead to decreased motivation and increased stress. Furthermore, the lack of dynamically tailored feedback and support for enjoying learning has prevented them from providing an efficient and effective learning environment for test-takers.

[0588] 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.

[0589] In this invention, the server includes means for collecting information on the academic ability of test takers, means for obtaining information on educational institutions related to the test taker, means for using a generative model to create an individualized learning plan using the above information, means for analyzing the emotional state of the test taker, means for adjusting the learning plan while considering the academic ability information and emotional data, means for visually presenting the adjusted learning plan, means for generating feedback according to the progress of learning, and means for providing a learning experience through a virtual space. This makes it possible to provide a learning plan optimized for the individual state of the test taker and to realize an efficient and less stressful learning environment.

[0590] "Examinee" refers to a learner or student taking an examination who provides academic ability and emotional information to the system.

[0591] "Academic ability information" refers to data about the knowledge and abilities that test-takers currently possess, and it forms the basis for creating individualized learning plans.

[0592] "Information acquisition methods" refer to the functions and methods for collecting entrance examination information related to educational institutions, and are used to consider which institutions applicants are interested in.

[0593] "Emotional state" refers to the emotional reactions that test-takers experience during their studies, and it is an element that the system analyzes in real time and incorporates into the study plan.

[0594] A "generative model" refers to an algorithm or process that uses AI to automatically generate the optimal learning plan based on the academic ability and emotional data of test takers.

[0595] A "virtual space" is an environment constructed using digital technology, providing an interactive space where test-takers can learn in a relaxed environment.

[0596] "Feedback" refers to information and advice provided by the system according to the test-taker's learning progress, and is an indicator designed to improve the efficiency and effectiveness of learning.

[0597] This invention is a system for providing test takers with an individualized learning experience. The system consists of a server, a terminal, and user interaction.

[0598] Users input their academic performance information and emotional state through the device. The device captures facial expressions and voice tone using its camera and microphone, and an emotion engine analyzes this information. This information is sent to a server for storage and supplied to an AI-generated model for analysis.

[0599] The server receives this data and uses a generative AI model to create individualized learning plans for each test-taker. This model takes into account the user's unique academic ability and emotional data to provide an optimized plan. The server also monitors the test-taker's emotions in real time and dynamically adjusts the plan as needed.

[0600] The device, following instructions from the server, presents the user with an optimized learning plan. This allows the user to learn at their own pace. The device also plays a role in providing a virtual environment, creating an immersive learning experience. Relaxing music and visual effects are used in the virtual environment, which are also selected by the emotion engine.

[0601] As a concrete example, let's assume a user is solving a math problem. If the emotion engine detects that the user is experiencing frustration, the server immediately adjusts the difficulty level of the learning task, and the device displays a problem accordingly. In this way, the system reduces the user's stress and provides an environment that makes it easier to continue learning.

[0602] An example of a prompt is: "Analyze the emotions the test-taker feels about a particular subject, and adjust the study plan based on those emotions."

[0603] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0604] Step 1:

[0605] Users input their academic performance and emotional state using a device. This includes inputting academic performance information as text data through an interface, and recording facial expressions and voice tone in real time using a camera and microphone. The input data is sent directly to the server.

[0606] Step 2:

[0607] The server stores the received academic performance information and emotional data in a database. This database storage process creates the foundation for subsequent analysis. The output of this step is the information stored in the database.

[0608] Step 3:

[0609] The server uses an emotion engine to analyze the received emotion data. The analysis uses facial recognition algorithms and voice analysis technology to identify the test-taker's emotional state, and generates an emotion score based on the results. This score is output and passed on to the next step.

[0610] Step 4:

[0611] The server utilizes a generative AI model to generate personalized learning plans tailored to each test-taker, using academic performance information and emotional scores as arguments. The AI ​​analyzes this data and automatically combines the most suitable learning materials and assignments for each test-taker's abilities and condition, outputting a new learning plan.

[0612] Step 5:

[0613] The server updates the generated learning plan in real time. It dynamically adjusts the learning plan by taking into account the test-taker's progress and emotional changes, and providing feedback as needed. This adjusted plan is output and sent to the terminal.

[0614] Step 6:

[0615] The terminal visually presents the adjusted learning plan sent from the server to the test-taker. This includes clearly displaying the plan on the user interface and providing visual feedback to support learning progress.

[0616] Step 7:

[0617] The device provides test-takers with a relaxing learning environment through a virtual environment. It uses music and videos to reduce stress and help maintain motivation. Content is selected and changed according to the instructions of the emotion engine, resulting in an effective learning environment.

[0618] (Application Example 2)

[0619] 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."

[0620] In current examination and educational settings, there is a lack of flexible learning plans that cater to the emotional state and individual needs of test-takers. Furthermore, in real-world consumer experiences, there is a lack of methods for providing personalized suggestions based on customer emotions. This leads to problems such as decreased motivation to learn and reduced purchasing intent.

[0621] 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.

[0622] In this invention, the server includes means for analyzing the emotional state of the test taker in real time, means for dynamically adjusting the learning plan and feedback according to the emotional state, and means for emotional analysis and suggestion adjustment for providing personalized product suggestions in the real world. This makes it possible to optimize the learning experience to meet individual needs and provide product suggestions based on the consumer's emotions.

[0623] An "examinee" is an individual who prepares for and studies to take an exam.

[0624] "Academic ability information" refers to data that indicates the current level of knowledge and skills of the test taker.

[0625] "Desired educational institution" refers to the specific educational institution that the applicant wishes to attend or enroll in.

[0626] "Entrance examination information" refers to all data related to the entrance examinations administered by the educational institution you wish to attend.

[0627] A "generative model" is an algorithm used to create personalized learning plans based on input information.

[0628] A "study plan" is a plan outlining the time allocation and content of study, designed to effectively guide a test-taker's learning.

[0629] "Feedback" refers to evaluations and suggestions for improvement provided regarding learning content and progress.

[0630] A "virtual environment" is a simulated space recreated on a computer, where test-takers can experience learning.

[0631] "Emotional state" refers to the psychological sensations and emotional conditions that a test-taker experiences at a specific time.

[0632] "Dynamic adjustment" refers to making adjustments or changes in real time in response to changes in the situation or data.

[0633] A "product suggestion" is a recommendation of a specific product or service presented in response to consumer needs and emotions.

[0634] This invention is a system that analyzes the emotional state of test takers in real time and dynamically adjusts learning plans and feedback. Furthermore, it also has a function to provide personalized product recommendations in the real world.

[0635] In this system, the server plays a central role and performs the main processing. The server receives academic ability information and entrance examination information for desired educational institutions from the user, and uses this data to create a personalized learning plan using a generative AI model. The generative model uses AI algorithms to design an optimized plan. The server also uses an emotion engine (e.g., Microsoft Azure Emotion API) that analyzes the user's facial image and voice tone to determine their emotional state. Based on the emotional data, it is possible to adjust feedback and learning plans in real time.

[0636] The device plays the role of presenting the user with generated learning plans and feedback. Examples include smart glasses or smartphones with learning applications installed. This allows the user to continuously receive an optimized learning experience.

[0637] Meanwhile, in physical stores, customer emotions are analyzed by an emotion engine via specific robots or smart glasses, and this data is processed on a server. The server then presents emotion-based product suggestions to actual store staff, providing real-time recommendations for the most suitable products and services.

[0638] For example, if the emotion engine detects stress in a user while they are learning English reading online, the server will adjust the learning plan and suggest easier problems or breaks. Another possible application is in a physical store, where if a customer shows interest in a product but appears somewhat tense, the system could suggest products with relaxing effects.

[0639] Example prompt for a generative AI model: "Based on this customer's emotional state, please tell me the best way to suggest products that have a relaxing effect."

[0640] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0641] Step 1:

[0642] The server receives academic ability information and entrance examination information for the educational institutions the user is applying to. The input data includes the applicant's past grades, study progress, and desired passing criteria. This information is stored in a database and used in subsequent processing.

[0643] Step 2:

[0644] The server uses the terminal's emotion detection function to capture the test-taker's facial expressions and voice tone in real time and analyzes their emotional state. The input includes raw data collected from the camera and microphone, which is processed using an emotion engine. The output is the test-taker's current emotional state (e.g., stress, relaxation).

[0645] Step 3:

[0646] The server integrates the applicant's academic ability information, entrance exam information, and emotional state to create a personalized learning plan using a generative AI model. The input is the data obtained in Step 1 and Step 2, which is used to generate an optimized learning plan. The output is a customized learning plan to be presented to the user.

[0647] Step 4:

[0648] The terminal presents the user with a personalized learning plan provided by the server. The input here is learning plan data received from the server, and the output provides learning guidelines and study schedules that the user can easily understand. Specifically, the information is displayed on the terminal's screen.

[0649] Step 5:

[0650] The user progresses through the learning process based on the provided learning plan. The user's progress and responses are recorded on the device, and feedback is sent to the server. The input is the user's learning progress, and the output is feedback data regarding the user's learning.

[0651] Step 6:

[0652] When analyzing customer emotions in a physical store and making product recommendations, the server processes video and audio data from within the store. Input is emotion data from cameras and audio devices, which is evaluated by an emotion engine. Output is personalized product recommendations based on those emotions.

[0653] This series of steps provides test takers with an optimized learning experience and customers with emotion-based product recommendations.

[0654] 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.

[0655] 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.

[0656] 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.

[0657] [Fourth Embodiment]

[0658] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0659] 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.

[0660] 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).

[0661] 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.

[0662] 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.

[0663] 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).

[0664] 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.

[0665] 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.

[0666] 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.

[0667] 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.

[0668] 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.

[0669] 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.

[0670] 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".

[0671] This invention is an educational support system aimed at improving the efficiency of learning and maintaining motivation for students preparing for exams. The system provides individualized learning plans to a large number of users (students preparing for exams), thereby enabling efficient exam preparation.

[0672] System Overview

[0673] 1. Enter applicant information

[0674] Users access the system and input their academic ability information and information about the educational institutions they wish to attend. Users can also input their past mock exam results and their current level of understanding of the subjects they are studying.

[0675] 2. Data Processing

[0676] The server receives academic ability information and entrance exam information for desired schools from the user and stores this information in a database. Based on this data, the server uses an AI generative model to construct a different learning plan for each user.

[0677] 3. Presentation and adjustment of the learning plan

[0678] The server sends the generated learning plan to the device. The learning plan includes recommended learning content, learning frequency, and required review items. The AI ​​continuously evaluates the user's learning progress and dynamically adjusts the plan's content.

[0679] 4. Learning in a virtual environment

[0680] The terminal provides users with a virtual environment. Within this environment, users can interact with other test-takers and converse with virtual tutors. This is a measure taken to improve motivation.

[0681] Specific example

[0682] For example, when a user is preparing for a mathematics entrance exam, the system analyzes the user's weaknesses based on their past mathematics practice test data. Based on this analysis, the server adjusts the learning content for each topic, such as "functions" or "geometry," and generates interactive assignments. The terminal promptly presents the user with the assignments to be solved and detailed explanations. This allows the user to focus their learning at their own pace.

[0683] This system allows users to efficiently prepare for entrance exams at their desired educational institutions while monitoring their daily learning progress. Furthermore, by utilizing a virtual environment, it reduces the isolation of studying and alleviates the mental burden of exam preparation.

[0684] The following describes the processing flow.

[0685] Step 1:

[0686] The user logs into the device and enters their basic information, academic information, and data on the educational institution they wish to attend. This allows the system to collect the user's individual data.

[0687] Step 2:

[0688] The terminal sends user input information to the server. This includes past mock exam results and current school preference information. The terminal confirms that the transmission was successful and notifies the user of the progress.

[0689] Step 3:

[0690] The server stores the data received from the terminal in a database. Furthermore, it applies an AI-generated model to the stored data to create a personalized learning plan tailored to the user's academic ability. This plan includes recommended learning content for each subject and items that require high review.

[0691] Step 4:

[0692] The server sends the created learning plan to the user's device. At that time, it prioritizes the recommended learning content included in the plan according to each user's progress.

[0693] Step 5:

[0694] The device presents the received learning plan to the user. It guides the user through the learning process by displaying necessary learning materials, video explanations, and practice problems step by step.

[0695] Step 6:

[0696] Users progress through their daily studies based on the learning plan displayed on their device. They learn efficiently at their own pace by solving problems and watching video explanations.

[0697] Step 7:

[0698] The device continuously records the user's learning progress. For example, it reports the time taken to answer each problem and the correct answer rate to the server, accumulating progress data.

[0699] Step 8:

[0700] The server analyzes the collected study progress data and incorporates it into new learning plans. In particular, it prioritizes areas where the user struggles and their current learning progress, dynamically updating the plan accordingly.

[0701] Step 9:

[0702] In the virtual environment provided by the device, users can participate in study rooms and receive support from virtual characters, thereby maintaining their motivation to learn and reducing mental burden.

[0703] (Example 1)

[0704] 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".

[0705] The challenge lies in efficiently supporting test-takers' learning and realizing optimal learning tailored to each individual's academic ability and aspirations. In particular, it is necessary to provide personalized learning plans that address the unique circumstances of each test-taker, maintain their motivation to learn, and reduce feelings of isolation.

[0706] 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.

[0707] In this invention, the server includes means for inputting the examinee's current ability information, means for obtaining examination information from the educational institution they wish to attend, and means for using a generative model to generate an individualized learning plan. As a result, examinees receive an effective learning plan based on their academic ability and aspirations, and the learning experience through a virtual space can improve their motivation to learn and reduce feelings of isolation.

[0708] An "examinee" is a learner whose purpose is to take an examination.

[0709] "Ability information" refers to a collection of data that indicates the academic ability and level of understanding of the test taker.

[0710] "Desired educational institution" refers to the educational institution that the applicant aims to enroll in.

[0711] "Examination information" refers to data and requirements related to entrance examinations.

[0712] An "educational plan" is a set of teaching guidelines formulated to effectively guide the learning of test-takers.

[0713] A "generative model" is an algorithm that automatically creates an educational plan based on the applicant's ability information and test information.

[0714] A "virtual space" refers to a virtual learning environment created using digital technology.

[0715] "Motivation maintenance techniques" refer to a set of techniques that include various approaches to enhance and maintain the learning motivation of test-takers.

[0716] This invention is a learning support system for test takers, aiming to provide an individualized educational plan. The system is configured and operates as follows:

[0717] Users first access the system using a web browser. They input their own information, such as past exam results and their current level of understanding of subjects. The interface used for this is a web application utilizing HTML and JavaScript.

[0718] The server stores the ability information submitted by the user and the examination information of the educational institution the user wishes to attend in a database. A database management system such as MySQL is used for this database. The server uses a generative AI model to generate a personalized educational plan for each user. Here, the AI ​​model is given the prompt statement, "Create a personalized educational plan based on the user's academic ability information."

[0719] The generated lesson plan is sent from the server to the terminal. The terminal displays the plan on its screen to make it easy for the user to understand. At this stage, the user can communicate with other test-takers in a virtual space and interact with a virtual tutor. This environment is built using virtual reality technologies such as Unity or Unreal Engine.

[0720] For example, when a user is preparing for an English exam, the system analyzes their weaknesses based on past practice test data and generates a focused study plan for frequently appearing questions. The server generates assignments to improve skills such as listening and speaking. The terminal presents these assignments to the user, provides explanations, and feeds back the progress to the server.

[0721] This system allows users to obtain an educational plan optimized for them and an environment that enables them to learn at their own pace.

[0722] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0723] Step 1:

[0724] Users access the system using a web browser and enter their own ability information and exam information for their desired educational institution. This information includes past mock exam scores and current study status. This data is sent to the server when the submit button is pressed.

[0725] Step 2:

[0726] The server parses the input data received from the user and stores it in a database. A data management system such as MySQL is used for this database. The input data undergoes format checks and is stored in a normalized state. The stored data then serves as the foundational information for generating educational plans in subsequent processing.

[0727] Step 3:

[0728] The server runs a generative AI model using stored user data. Specifically, it provides the AI ​​model with the prompt, "Create an individualized educational plan based on the user's academic ability information." The generative AI model then performs data analysis based on this prompt and outputs an individualized educational plan adapted to the user.

[0729] Step 4:

[0730] The generated learning plan is sent from the server to the terminal. The terminal receives this plan and displays it in an easy-to-understand format for the user. The specific output includes the learning content for each subject and a recommended learning timeline. The user can then proceed with their learning based on this information.

[0731] Step 5:

[0732] The terminal provides users with a virtual space that allows them to interact with other test-takers. This virtual space is built using tools such as Unity and Unreal Engine. Users can confirm learning content and get answers to their questions through a dialogue function with a virtual tutor. Learning progress data obtained through information exchange is periodically sent to the server and used to revise the educational plan.

[0733] (Application Example 1)

[0734] 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".

[0735] In exam preparation, there is a need for individualized learning that caters to the diverse needs of students. Furthermore, new methods are required to maintain motivation while efficiently advancing learning. However, the current education system makes it difficult to provide each student with an optimized learning plan and a rich learning experience. Maintaining sustained motivation is a major challenge, especially in a learning environment that tends to be isolated.

[0736] 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.

[0737] In this invention, the server includes means for inputting the applicant's current academic ability information, means for obtaining entrance examination information of the educational institution the applicant wishes to attend, and means for using a generative model to generate an individualized learning plan. This makes it possible to provide applicants with an individualized learning plan and to realize an interactive learning experience through a visual device.

[0738] "Means for inputting the applicant's current academic ability information" refers to the technical means for incorporating the applicant's academic status into the system, and designing an individualized learning plan based on the input information.

[0739] "Means of obtaining entrance examination information for desired educational institutions" refers to technical means of obtaining information on the examination content and standards of the target school for applicants, and using that information to help construct a study plan.

[0740] "Methods using generative models" refer to methods that utilize AI models to generate personalized learning plans for each student taking the exam.

[0741] "Means for generating feedback on learning content" refers to methods for evaluating the level of understanding and progress of test-takers and providing information on areas for improvement and achievement.

[0742] "Means of providing a learning experience in a virtual environment" refers to providing an environment in which examinees can study in a virtual space and gain a richer learning experience.

[0743] "Means using visual devices" refers to devices or technologies used to provide students with visual learning materials and to enable them to intuitively understand the content.

[0744] "A means of supporting learning through real-time interaction with a virtual instructor" refers to a technological means of supporting learning by enabling immediate communication between a virtual instructor and a student.

[0745] "Motivation maintenance techniques" refer to psychological or technical methods used to enhance and maintain students' motivation to learn.

[0746] This invention is designed to effectively provide learning support for students preparing for exams. The main hardware used includes smart devices, such as smart glasses. The system also features a cloud server and AI platform, and the software utilizes Unity, TensorFlow, and Azure Cloud Services.

[0747] The server is responsible for acquiring the applicant's current academic ability information and collecting entrance examination information for their desired educational institutions from a database. This makes it possible to design a learning plan optimized for each applicant. The server applies an AI generative model to integrate the applicant's past performance data with expected goals and generates a personalized learning plan.

[0748] The terminal, or smart device, visualizes the generated learning plan for the test-taker. An interactive virtual environment built with Unity is provided, allowing the test-taker to view the necessary learning materials and assignments through the visual device. These processes are centrally managed, and the test-taker can interact with a virtual instructor in real time.

[0749] Users can enjoy a visual and interactive learning experience through modules provided within a virtual environment. Learning plans are dynamically updated to allow learners to focus on areas where they struggle.

[0750] For example, if a user needs to deepen their understanding of mathematics, the server analyzes the student's past practice test results and creates assignments tailored to their weak areas in mathematics. Then, through a visual device, the user is presented with application problems involving functions and geometry. A virtual instructor responds to the user's questions in real time, facilitating learning.

[0751] An example of a prompt would be, "Suggest an efficient study plan for a student who struggles with function differentiation." This prompt serves as a guide for the generative AI model in constructing the optimal study plan for the student.

[0752] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0753] Step 1:

[0754] The server receives academic ability information of applicants and entrance examination information of their desired educational institutions as input from the user. This data is formatted according to a template and stored in a database. Based on the input information, data processing is performed to evaluate the applicant's academic ability and target level.

[0755] Step 2:

[0756] The server uses a generative AI model to generate personalized learning plans based on the applicant's current academic ability and the entrance exam information of their desired school. Following prompts, data calculations are performed to extract the applicant's weak areas from past mock exam results and set learning priorities based on that. The output is a learning plan tailored to each applicant.

[0757] Step 3:

[0758] The terminal presents the learning plan received from the server to the user through the smart device interface. Based on the learning plan received as input, it displays visual learning materials using a 3D graphics engine. The output is an interactive virtual learning environment.

[0759] Step 4:

[0760] Users wear visual devices and use learning materials provided within a virtual environment. In response to user input (e.g., gaze and gestures), the device generates feedback on the learning content and enables interaction with a virtual instructor. The output is a learning experience that progresses at the student's own pace.

[0761] Step 5:

[0762] The server dynamically updates the learning plan using the generative AI model again, based on the learning progress and user feedback. The input data consists of the user's learning outcomes and feedback, and the output is a newly generated learning plan, which is then provided to the user again.

[0763] 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.

[0764] This invention incorporates an emotion engine into a system that provides personalized learning plans for test-takers. It enables real-time recognition of the test-taker's emotional and motivational state, and dynamically adjusts the learning plan and feedback content based on this information. This helps maintain the test-taker's motivation to learn and reduces their mental burden.

[0765] System Overview

[0766] 1. Obtaining and entering applicant information

[0767] Users access the system and input their academic performance information, information about their desired educational institutions, and emotional data. The emotional data is analyzed by a dedicated emotional engine.

[0768] 2. Data processing and training plan generation

[0769] The server receives and stores data sent by the user. It then uses an AI-generated model to create a personalized learning plan for each test-taker. Furthermore, it optimizes the plan by taking into account the user's emotional state, as provided by the emotion engine.

[0770] 3. Real-time feedback via an emotion engine

[0771] The server monitors the test-taker's emotions and learning progress in real time and constantly updates the feedback. The emotion engine determines the user's emotional state from their facial expressions and tone of voice, and adjusts the difficulty level of the learning tasks and the question format based on that data.

[0772] 4. Presentation of a tailored learning plan

[0773] The device presents the user with an optimized learning plan provided by the server. This allows the user to learn at their own pace.

[0774] 5. Maintaining motivation in a virtual environment

[0775] The device provides users with a virtual environment, enabling test-takers to continue learning while enjoying the process. The emotional engine also helps in selecting music and videos to reduce learning stress.

[0776] Specific example

[0777] For example, suppose the emotion engine detects that a user is feeling confused or stressed while working on an English reading comprehension problem. In that case, the server immediately changes the plan to provide a slightly easier problem and include a short break. The device displays this plan and switches to an interface that helps the user relax. In this way, an environment is created that allows the user to learn comfortably and continuously.

[0778] The following describes the processing flow.

[0779] Step 1:

[0780] Users log in to the system via their device and input academic information, information about their desired educational institutions, past mock exam results, and emotional data. Emotional data is acquired using the camera and microphone.

[0781] Step 2:

[0782] The terminal sends all information entered by the user to the server. This data includes emotional information such as facial expression analysis results and voice analysis results.

[0783] Step 3:

[0784] The server uses an AI-generated model to create personalized learning plans for each user based on the received academic ability and entrance exam information. Furthermore, it incorporates emotional data provided by the emotion engine to adjust the learning difficulty level and add specific feedback content.

[0785] Step 4:

[0786] The server sends the generated learning plan to the device. The sent plan includes adjustments that take emotions into account.

[0787] Step 5:

[0788] The device displays the learning plan received from the server to the user. It provides an interface that includes emotionally responsive animations and voice guidance.

[0789] Step 6:

[0790] The user progresses through the learning process according to the provided learning plan. If a change in the user's emotions is detected during the learning process, this change is reflected in the feedback displayed on the device.

[0791] Step 7:

[0792] The device periodically uses an emotion engine to recognize the user's emotional state and reports the results to the server. It also suggests relaxation options to the user as needed.

[0793] Step 8:

[0794] The server analyzes the collected emotional data and makes further adjustments to the learning plan. For example, if the user is experiencing stress, it adjusts the pace of the plan to make learning more comfortable for the user.

[0795] Step 9:

[0796] In the virtual environment provided through the device, users can maintain their motivation to learn by interacting with other test-takers and experiencing relaxation content recommended by the emotion engine.

[0797] (Example 2)

[0798] 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".

[0799] Conventional learning support systems have a problem in that they provide a uniform learning plan for all test-takers, making it difficult to consider individual academic abilities and emotional states, which can lead to decreased motivation and increased stress. Furthermore, the lack of dynamically tailored feedback and support for enjoying learning has prevented them from providing an efficient and effective learning environment for test-takers.

[0800] 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.

[0801] In this invention, the server includes means for collecting information on the academic ability of test takers, means for obtaining information on educational institutions related to the test taker, means for using a generative model to create an individualized learning plan using the above information, means for analyzing the emotional state of the test taker, means for adjusting the learning plan while considering the academic ability information and emotional data, means for visually presenting the adjusted learning plan, means for generating feedback according to the progress of learning, and means for providing a learning experience through a virtual space. This makes it possible to provide a learning plan optimized for the individual state of the test taker and to realize an efficient and less stressful learning environment.

[0802] "Examinee" refers to a learner or student taking an examination who provides academic ability and emotional information to the system.

[0803] "Academic ability information" refers to data about the knowledge and abilities that test-takers currently possess, and it forms the basis for creating individualized learning plans.

[0804] "Information acquisition methods" refer to the functions and methods for collecting entrance examination information related to educational institutions, and are used to consider which institutions applicants are interested in.

[0805] "Emotional state" refers to the emotional reactions that test-takers experience during their studies, and it is an element that the system analyzes in real time and incorporates into the study plan.

[0806] A "generative model" refers to an algorithm or process that uses AI to automatically generate the optimal learning plan based on the academic ability and emotional data of test takers.

[0807] A "virtual space" is an environment constructed using digital technology, providing an interactive space where test-takers can learn in a relaxed environment.

[0808] "Feedback" refers to information and advice provided by the system according to the test-taker's learning progress, and is an indicator designed to improve the efficiency and effectiveness of learning.

[0809] This invention is a system for providing test takers with an individualized learning experience. The system consists of a server, a terminal, and user interaction.

[0810] Users input their academic performance information and emotional state through the device. The device captures facial expressions and voice tone using its camera and microphone, and an emotion engine analyzes this information. This information is sent to a server for storage and supplied to an AI-generated model for analysis.

[0811] The server receives this data and uses a generative AI model to create individualized learning plans for each test-taker. This model takes into account the user's unique academic ability and emotional data to provide an optimized plan. The server also monitors the test-taker's emotions in real time and dynamically adjusts the plan as needed.

[0812] The device, following instructions from the server, presents the user with an optimized learning plan. This allows the user to learn at their own pace. The device also plays a role in providing a virtual environment, creating an immersive learning experience. Relaxing music and visual effects are used in the virtual environment, which are also selected by the emotion engine.

[0813] As a concrete example, let's assume a user is solving a math problem. If the emotion engine detects that the user is experiencing frustration, the server immediately adjusts the difficulty level of the learning task, and the device displays a problem accordingly. In this way, the system reduces the user's stress and provides an environment that makes it easier to continue learning.

[0814] An example of a prompt is: "Analyze the emotions the test-taker feels about a particular subject, and adjust the study plan based on those emotions."

[0815] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0816] Step 1:

[0817] Users input their academic performance and emotional state using a device. This includes inputting academic performance information as text data through an interface, and recording facial expressions and voice tone in real time using a camera and microphone. The input data is sent directly to the server.

[0818] Step 2:

[0819] The server stores the received academic performance information and emotional data in a database. This database storage process creates the foundation for subsequent analysis. The output of this step is the information stored in the database.

[0820] Step 3:

[0821] The server uses an emotion engine to analyze the received emotion data. The analysis uses facial recognition algorithms and voice analysis technology to identify the test-taker's emotional state, and generates an emotion score based on the results. This score is output and passed on to the next step.

[0822] Step 4:

[0823] The server utilizes a generative AI model to generate personalized learning plans tailored to each test-taker, using academic performance information and emotional scores as arguments. The AI ​​analyzes this data and automatically combines the most suitable learning materials and assignments for each test-taker's abilities and condition, outputting a new learning plan.

[0824] Step 5:

[0825] The server updates the generated learning plan in real time. It dynamically adjusts the learning plan by taking into account the test-taker's progress and emotional changes, and providing feedback as needed. This adjusted plan is output and sent to the terminal.

[0826] Step 6:

[0827] The terminal visually presents the adjusted learning plan sent from the server to the test-taker. This includes clearly displaying the plan on the user interface and providing visual feedback to support learning progress.

[0828] Step 7:

[0829] The device provides test-takers with a relaxing learning environment through a virtual environment. It uses music and videos to reduce stress and help maintain motivation. Content is selected and changed according to the instructions of the emotion engine, resulting in an effective learning environment.

[0830] (Application Example 2)

[0831] 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".

[0832] In current examination and educational settings, there is a lack of flexible learning plans that cater to the emotional state and individual needs of test-takers. Furthermore, in real-world consumer experiences, there is a lack of methods for providing personalized suggestions based on customer emotions. This leads to problems such as decreased motivation to learn and reduced purchasing intent.

[0833] 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.

[0834] In this invention, the server includes means for analyzing the emotional state of the test taker in real time, means for dynamically adjusting the learning plan and feedback according to the emotional state, and means for emotional analysis and suggestion adjustment for providing personalized product suggestions in the real world. This makes it possible to optimize the learning experience to meet individual needs and provide product suggestions based on the consumer's emotions.

[0835] An "examinee" is an individual who prepares for and studies to take an exam.

[0836] "Academic ability information" refers to data that indicates the current level of knowledge and skills of the test taker.

[0837] "Desired educational institution" refers to the specific educational institution that the applicant wishes to attend or enroll in.

[0838] "Entrance examination information" refers to all data related to the entrance examinations administered by the educational institution you wish to attend.

[0839] A "generative model" is an algorithm used to create personalized learning plans based on input information.

[0840] A "study plan" is a plan outlining the time allocation and content of study, designed to effectively guide a test-taker's learning.

[0841] "Feedback" refers to evaluations and suggestions for improvement provided regarding learning content and progress.

[0842] A "virtual environment" is a simulated space recreated on a computer, where test-takers can experience learning.

[0843] "Emotional state" refers to the psychological sensations and emotional conditions that a test-taker experiences at a specific time.

[0844] "Dynamic adjustment" refers to making adjustments or changes in real time in response to changes in the situation or data.

[0845] A "product suggestion" is a recommendation of a specific product or service presented in response to consumer needs and emotions.

[0846] This invention is a system that analyzes the emotional state of test takers in real time and dynamically adjusts learning plans and feedback. Furthermore, it also has a function to provide personalized product recommendations in the real world.

[0847] In this system, the server plays a central role and performs the main processing. The server receives academic ability information and entrance examination information for desired educational institutions from the user, and uses this data to create a personalized learning plan using a generative AI model. The generative model uses AI algorithms to design an optimized plan. The server also uses an emotion engine (e.g., Microsoft Azure Emotion API) that analyzes the user's facial image and voice tone to determine their emotional state. Based on the emotional data, it is possible to adjust feedback and learning plans in real time.

[0848] The device plays the role of presenting the user with generated learning plans and feedback. Examples include smart glasses or smartphones with learning applications installed. This allows the user to continuously receive an optimized learning experience.

[0849] Meanwhile, in physical stores, customer emotions are analyzed by an emotion engine via specific robots or smart glasses, and this data is processed on a server. The server then presents emotion-based product suggestions to actual store staff, providing real-time recommendations for the most suitable products and services.

[0850] For example, if the emotion engine detects stress in a user while they are learning English reading online, the server will adjust the learning plan and suggest easier problems or breaks. Another possible application is in a physical store, where if a customer shows interest in a product but appears somewhat tense, the system could suggest products with relaxing effects.

[0851] Example prompt for a generative AI model: "Based on this customer's emotional state, please tell me the best way to suggest products that have a relaxing effect."

[0852] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0853] Step 1:

[0854] The server receives academic ability information and entrance examination information for the educational institutions the user is applying to. The input data includes the applicant's past grades, study progress, and desired passing criteria. This information is stored in a database and used in subsequent processing.

[0855] Step 2:

[0856] The server uses the terminal's emotion detection function to capture the test-taker's facial expressions and voice tone in real time and analyzes their emotional state. The input includes raw data collected from the camera and microphone, which is processed using an emotion engine. The output is the test-taker's current emotional state (e.g., stress, relaxation).

[0857] Step 3:

[0858] The server integrates the applicant's academic ability information, entrance exam information, and emotional state to create a personalized learning plan using a generative AI model. The input is the data obtained in Step 1 and Step 2, which is used to generate an optimized learning plan. The output is a customized learning plan to be presented to the user.

[0859] Step 4:

[0860] The terminal presents the user with a personalized learning plan provided by the server. The input here is learning plan data received from the server, and the output provides learning guidelines and study schedules that the user can easily understand. Specifically, the information is displayed on the terminal's screen.

[0861] Step 5:

[0862] The user progresses through the learning process based on the provided learning plan. The user's progress and responses are recorded on the device, and feedback is sent to the server. The input is the user's learning progress, and the output is feedback data regarding the user's learning.

[0863] Step 6:

[0864] When analyzing customer emotions in a physical store and making product recommendations, the server processes video and audio data from within the store. Input is emotion data from cameras and audio devices, which is evaluated by an emotion engine. Output is personalized product recommendations based on those emotions.

[0865] This series of steps provides test takers with an optimized learning experience and customers with emotion-based product recommendations.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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.

[0870] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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."

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] 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.

[0882] 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.

[0883] 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.

[0884] 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.

[0885] 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.

[0886] 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.

[0887] The following is further disclosed regarding the embodiments described above.

[0888] (Claim 1)

[0889] A means of inputting the applicant's current academic ability information,

[0890] Means of obtaining entrance examination information for the educational institution you wish to attend,

[0891] A means for using a generative model to generate an individualized learning plan based on the aforementioned academic ability information and entrance examination information,

[0892] A means of presenting the aforementioned learning plan to the test taker,

[0893] A means of generating feedback on the learning content,

[0894] Means of providing a learning experience in a virtual environment,

[0895] A system that includes this.

[0896] (Claim 2)

[0897] The system according to claim 1, wherein the generative model dynamically updates the learning plan using the test taker's mock exam results.

[0898] (Claim 3)

[0899] The system according to claim 1, wherein the virtual environment includes a method for maintaining motivation to improve the examinee's motivation to learn.

[0900] "Example 1"

[0901] (Claim 1)

[0902] A means of inputting the applicant's current ability information,

[0903] Means of obtaining exam information for the educational institution you wish to attend,

[0904] A means for using a generative model to generate an individualized educational plan based on the aforementioned competency information and the aforementioned test information,

[0905] A means of presenting the aforementioned educational plan to the applicants,

[0906] A means of generating responses to educational content,

[0907] Means of providing a learning experience in a virtual space,

[0908] Means for dynamically adjusting the plan,

[0909] A means to facilitate interaction with other test takers,

[0910] A system that includes this.

[0911] (Claim 2)

[0912] The system according to claim 1, wherein the generative model dynamically updates the educational plan using the results of the examinee's mock exam.

[0913] (Claim 3)

[0914] The system according to claim 1, wherein the virtual space includes a method for maintaining motivation to improve the examinee's motivation to learn.

[0915] "Application Example 1"

[0916] (Claim 1)

[0917] A means of inputting the applicant's current academic ability information,

[0918] Means of obtaining entrance examination information for the educational institution you wish to attend,

[0919] A means for using a generative model to generate an individualized learning plan based on the aforementioned academic ability information and the aforementioned entrance examination information,

[0920] A means of presenting the aforementioned learning plan to the test taker,

[0921] A means of generating feedback on the learning content,

[0922] Means of providing a learning experience in a virtual environment,

[0923] A means of using a visual device to present learning materials through visual elements in a virtual environment,

[0924] A means of supporting learning through real-time interaction with a virtual instructor,

[0925] A system that includes this.

[0926] (Claim 2)

[0927] The system according to claim 1, wherein the generative model dynamically updates the learning plan using the test taker's mock exam results.

[0928] (Claim 3)

[0929] The system according to claim 1, wherein the virtual environment includes a motivation maintenance method for improving the examinee's motivation to learn, and provides an interactive learning experience through a visual device.

[0930] "Example 2 of combining an emotion engine"

[0931] (Claim 1)

[0932] Means of collecting information on the academic ability of test takers,

[0933] Means of obtaining information about educational institutions related to entrance examinations,

[0934] A means of using a generative model to create individual learning plans using the above information,

[0935] Methods for analyzing the emotional state of test takers,

[0936] A means for adjusting the learning plan while taking into account the aforementioned academic ability information and emotional data,

[0937] A means of visually presenting the above-mentioned adjusted learning plan,

[0938] A means of generating feedback according to learning progress,

[0939] A means of providing a learning experience through virtual space,

[0940] A system that includes this.

[0941] (Claim 2)

[0942] The system according to claim 1, wherein the generative model dynamically optimizes the learning plan using the test taker's mock exam results and emotional data.

[0943] (Claim 3)

[0944] The system according to claim 1, wherein the virtual environment incorporates methods for maintaining the examinee's motivation and adjusts the content based on emotional data.

[0945] "Application example 2 when combining with an emotional engine"

[0946] (Claim 1)

[0947] A means of inputting the applicant's current academic ability information,

[0948] Means of obtaining entrance examination information for the educational institution you wish to attend,

[0949] A means for using a generative model to generate an individualized learning plan based on the aforementioned academic ability information and the aforementioned entrance examination information,

[0950] A means of presenting the aforementioned study plan to the test taker,

[0951] A means of generating feedback on the learning content,

[0952] Means of providing a learning experience in a virtual environment,

[0953] A means of analyzing the emotional state of test takers in real time,

[0954] Means for dynamically adjusting the learning plan and feedback according to the aforementioned emotional state,

[0955] A means of sentiment analysis and proposal adjustment for making personalized product suggestions in the real world,

[0956] A system that includes this.

[0957] (Claim 2)

[0958] The system according to claim 1, wherein the generative model dynamically updates the learning plan using the test taker's mock exam results.

[0959] (Claim 3)

[0960] The system according to claim 1, wherein the virtual environment includes a method for maintaining motivation to improve the examinee's motivation to learn. [Explanation of Symbols]

[0961] 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 inputting the applicant's current academic ability information, Means of obtaining entrance examination information for the educational institution you wish to attend, A means for using a generative model to generate an individualized learning plan based on the aforementioned academic ability information and entrance examination information, A means of presenting the aforementioned learning plan to the test taker, A means of generating feedback on the learning content, Means of providing a learning experience in a virtual environment, A system that includes this.

2. The system according to claim 1, wherein the generative model dynamically updates the learning plan using the test taker's mock exam results.

3. The system according to claim 1, wherein the virtual environment includes a method for maintaining motivation to improve the examinee's motivation to learn.

Images