system

Abstract

We provide the system. [Solution] A means for acquiring the user's learning results and automatically generating personalized learning content based on those learning results, Means for organizing the individualized learning content by referring to past learning information and external information sources, A means of presenting the compiled learning content to the user, A knowledge system that provides knowledge including the features of a new product, and means for automatically generating personalized educational materials based on the user's identified weaknesses, 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 as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional learning and training systems, it has been difficult to efficiently provide learning content focusing on the individual weaknesses and incorrect answer items of users, so it has been impossible to ensure an optimized learning experience for each user. In addition, there has been a problem that real-time correction and improvement according to the learning progress of each user are not performed, leading to a decrease in learning efficiency and loss of motivation.

Means for Solving the Problems

[0005] This invention provides a system that collects users' learning results, analyzes incorrect answers using artificial intelligence, and automatically generates supplementary learning materials for the relevant areas. This system can organize personalized learning content based on the user's past learning information and reliable external sources, and present it to the user's device. This enables a learning experience that allows users to efficiently and effectively overcome their weaknesses.

[0006] The term "user" refers to an individual or group that uses a learning system to engage in learning activities.

[0007] "Learning results" refer to information such as grades and correct / incorrect answers obtained by users through specific learning activities or tests.

[0008] "Personalized learning content" refers to educational materials and information that are designed or tailored specifically for a user, reflecting their particular learning needs and weaknesses.

[0009] "Methods for automatic generation" refers to technical methods that use artificial intelligence or algorithms to automatically create and structure learning content without human intervention.

[0010] "Past learning information" refers to historical information such as learning activities, acquired knowledge, and grades that a user has experienced in the past.

[0011] "External information sources" refer to educational materials, databases, or resources accessible via the internet or other networks.

[0012] "Means of organization" refers to methods and techniques for compiling, structuring, and organizing information in a way that is beneficial to the user.

[0013] "Means of presentation" refers to technologies and mechanisms that present generated or compiled information in an easily understandable way to users. [Brief explanation of the drawing]

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

MODE FOR CARRYING OUT THE INVENTION

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

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

[0017] In the following embodiments, the 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.

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

[0019] In the following embodiments, the 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.

[0020] 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).

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

[0022] [First Embodiment]

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

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

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

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

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

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

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

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0035] This invention comprises a learning-based training system that utilizes artificial intelligence to provide a personalized learning experience in order to enhance the user's learning efficiency. The system primarily consists of a server, terminals, and users.

[0036] Server Role

[0037] The server receives test results submitted by users and records the data in a database. The server then analyzes the collected test results for each user. Using artificial intelligence technology, it identifies the user's weaknesses by pinpointing incorrect answers and related learning topics. Based on this, it automatically generates personalized learning slides, referencing past learning content and external information sources. These generated slides are structured to meet each user's learning needs.

[0038] Terminal role

[0039] The device receives personalized learning slides sent from the server and presents them to the user. The device is designed to allow users to comfortably view the slides through a graphical user interface. Furthermore, as the user progresses through the learning process, the device records their progress and saves the data for use in the next learning step.

[0040] User roles

[0041] Users can use this system to improve their learning efficiency. They can view learning slides displayed on their device and use them to deepen their understanding of topics they answered incorrectly. The personalized content provided by the system allows users to learn at their own pace.

[0042] For example, if a user makes multiple incorrect answers on the topic of "data structures" in a particular test, the server generates learning slides containing content related to that topic and sends them to the user's device. Through these slides, the user can deepen their understanding of the questions and aim for better results in their next attempt. In this way, the present invention efficiently provides personalized learning support and creates an environment in which users can learn more effectively.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server receives the user's test results. After the test is completed, the user's device sends correct / incorrect answer data for each question to the server. This data is structured as question number and result (correct or incorrect).

[0046] Step 2:

[0047] The server records the received test results in a database. The results are stored along with each user's identification information, preparing them for subsequent analysis.

[0048] Step 3:

[0049] The server executes a process to analyze the recorded test results. Using artificial intelligence, it identifies incorrect answers and related topics, extracting the user's weaknesses. For example, if a group of questions with many incorrect answers are concentrated on a particular topic, that topic is recognized as the user's weakness.

[0050] Step 4:

[0051] The server generates personalized learning slides based on identified weaknesses. It automatically generates slides by referencing past learning databases and reliable information sources on the internet, and combining relevant content.

[0052] Step 5:

[0053] The server sends the generated learning slides to the user's device. It links them with the user's identification information to quickly deliver personalized content.

[0054] Step 6:

[0055] The device opens the received learning slides and makes them available for viewing to the user. The device provides a graphical user interface to help the user smoothly progress through the slide learning process.

[0056] Step 7:

[0057] Users view learning slides displayed on their device and begin learning based on personalized content. Users can learn at their own pace and record their progress on their device.

[0058] This processing flow allows users to efficiently address their weaknesses and maximize their learning effectiveness.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] In conventional learning systems, it was difficult to quickly and accurately provide personalized educational content based on the learning results submitted by users. This resulted in the challenge of maximizing the learning efficiency of each user. Furthermore, there was insufficient mechanism for identifying users' weaknesses and providing appropriate learning materials accordingly.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes means for registering learning results obtained from the user in a recording device, means for analyzing the learning results to identify the user's incorrect answers, and means for creating personalized educational materials based on the incorrect answers using a generation algorithm. This enables the rapid generation and provision of optimal educational content tailored to each individual user.

[0064] "User" refers to an individual who uses this system to learn through educational materials.

[0065] "Learning results" refers to the collective performance and answer information from tests and exercises taken by users.

[0066] A "recording device" is a mechanism for storing and managing data, and may include a database.

[0067] "Analysis" refers to data processing procedures that involve processing information based on data to obtain useful insights.

[0068] An "incorrect answer" refers to an item that a user answered incorrectly during the learning process, and is identified to provide further learning opportunities.

[0069] A "generative algorithm" encompasses a set of techniques used to create a new output based on input data.

[0070] "Educational materials" refer to content such as slides and documents provided to assist users in their learning.

[0071] "Personalization" means that adjustments are made to suit the different requirements and needs of each user.

[0072] This invention specifically demonstrates a method for providing a personalized learning experience by utilizing artificial intelligence in the learning process. This system mainly consists of a server, terminals, and users.

[0073] The server receives learning result data transmitted from users via the internet and stores this data using a recording device. This data includes the user's scores and error information from tests and exercises. General database software is used for database management.

[0074] Next, the server uses machine learning libraries for data analysis to identify the user's incorrect answers. Based on this analysis, it leverages a generative algorithm to create personalized training materials. Common generative techniques can be used as the generative AI model, using the prompt "How do I create training slides based on the user's incorrect topics?".

[0075] Learning materials generated on the server are sent to the terminal. The terminal presents these materials to the user through a graphical user interface, designed to allow for smooth viewing. The terminal also records the user's learning progress and saves that data to local storage for the next learning session.

[0076] Users use the learning materials presented on this device to deepen their understanding of topics they previously answered incorrectly. Based on the personalized content provided by the system, users can learn at their own pace and progress effectively. For example, if a user answers multiple questions related to "data structures" incorrectly, the server generates and provides learning materials related to those topics to help the user achieve better results in their next attempt.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The server receives learning result data from users via the internet. The input is the user's test results, and this data is stored in a recording device. The server prepares the data for subsequent analysis by standardizing the data format and storing it in a database. The output is the learning result data stored in the database.

[0080] Step 2:

[0081] The server analyzes the stored training data. This analysis uses machine learning libraries, primarily to extract patterns and frequencies of incorrect answers. The input is the training data in the database, and the server identifies each user's incorrect answers and lists the topics most likely to cause those errors. The output is a list of incorrect answers for each user.

[0082] Step 3:

[0083] The server uses a generation algorithm to create personalized training materials based on incorrect answers. The prompt "How do I create training slides based on the user's incorrect topics?" is used to guide the generation AI model. The input is a list of identified incorrect questions, and the server compiles personalized training materials in slide format based on the information obtained from the AI ​​model. The output is the personalized training material.

[0084] Step 4:

[0085] The server sends the generated learning materials to the terminal. The input is the learning materials created on the server, which the server pushes to a specific application on the terminal via the internet. The output is the learning materials delivered to the terminal.

[0086] Step 5:

[0087] The terminal presents the user with the individual learning materials it has received. The input is the learning materials sent from the server, and the terminal displays the materials in a user-friendly format. The output is a visually organized slide designed to facilitate user understanding.

[0088] Step 6:

[0089] The device records the user's progress as they learn. The input is the user's browsing activity; the device logs which slides were viewed and for how long. The output is data used to improve the next learning session.

[0090] Step 7:

[0091] Users deepen their understanding of topics they answered incorrectly through the provided learning materials. The input is the learning materials presented on the device; users view the slides and acquire knowledge. The output is improved understanding, aimed at achieving better results in the next test.

[0092] (Application Example 1)

[0093] 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."

[0094] Acquiring product knowledge in retail stores often depends on the experience and background of individual employees, making it difficult to provide uniform knowledge. Furthermore, in today's world where new products frequently appear, efficiently acquiring the latest product information is a crucial challenge. Traditional methods have been inefficient in employee learning because they have struggled to provide knowledge tailored to individual weaknesses.

[0095] 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.

[0096] In this invention, the server includes means for acquiring the user's learning results and automatically generating personalized learning content based on those learning results; means for organizing the personalized learning content by referring to past learning information and external information sources; means for presenting the organized learning content to the user; and a knowledge system that provides knowledge including the features of new products, and means for automatically generating personalized educational materials based on the user's identified weaknesses. This makes it possible for store employees to efficiently acquire the necessary knowledge based on their individual weaknesses and to promote product understanding in commercial stores.

[0097] "Users" refer to individual store employees who receive learning content through the knowledge system with the aim of deepening their understanding of the products.

[0098] "Learning results" refer to the outcomes obtained by users using the knowledge system, and are data that influences subsequent learning content based on whether the answers are correct or incorrect.

[0099] "Personalized learning content" refers to educational materials specifically created for a user, based on their specific weaknesses and past learning history, using artificial intelligence.

[0100] "External information sources" refer to external databases and publicly available resources that knowledge systems refer to when organizing personalized learning content.

[0101] "Identified weaknesses" refer to areas where the user's knowledge is lacking or understanding is incomplete, as revealed during their learning process.

[0102] "Educational materials" refer to information and content created to improve users' knowledge and address specific areas of weakness.

[0103] A "commercial store" refers to a physical facility that provides goods and services to the general public, and is a place where store employees engage in activities to deepen their understanding of the products.

[0104] This invention comprises a server, terminals, and users to realize an employee training system for stores. The server receives the results of tests taken by users and records them in a database. Subsequently, artificial intelligence technology is used to identify the user's weak points and generate personalized learning slides based on those points. This helps users efficiently overcome their shortcomings.

[0105] The server uses MongoDB as its database for processing, and a Python-based machine learning framework is employed for generating individual training content. The generated training slides are sent to the device via AWS® or Google® Cloud Platform.

[0106] The device receives materials sent from the server and displays them visually to the user. The smartphone app, developed using React Native, provides a user-friendly interface and offers features for viewing learning slides and managing progress.

[0107] Users acquire product knowledge by viewing personalized learning slides through a smartphone app. For example, when a new product is introduced, users can refer to individual learning slides containing its features to deepen their understanding. This allows for the rapid provision of accurate and useful information when explaining products to customers.

[0108] Examples of prompts include "Generate learning slides to address misunderstandings about the new fall collection" and "Create slides highlighting the features of this product." By using these prompts, the generative AI model can provide optimal learning content tailored to the user's needs.

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] The server receives the results of the tests taken by the user. These results include information on whether each question was answered correctly or incorrectly. The received data is stored in MongoDB, allowing for tracking of individual learning progress.

[0112] Step 2:

[0113] The server uses artificial intelligence technology to identify the user's weak points based on the received test result data. This process utilizes a Python machine learning framework, performing data analysis and calculations to efficiently identify areas with frequent errors. The identified weaknesses are then used as important data for generating subsequent learning slides.

[0114] Step 3:

[0115] The server automatically generates relevant learning content based on identified weaknesses. This generation utilizes a generative AI model to create personalized slides tailored to the user's needs. By analyzing input data and selecting appropriate topics and content, it generates learning slides as output.

[0116] Step 4:

[0117] The server sends the generated learning slides to the device via AWS or Google Cloud Platform, making them accessible to the user. The slides are output in an appropriate format so that they can be visually displayed on the user's device.

[0118] Step 5:

[0119] The device receives learning slides sent from the server and presents them to the user. A user interface built with React Native allows users to visually review the slides as they progress through the learning process. Progress data is recorded based on user interactions, enabling the provision of additional information during subsequent access.

[0120] Step 6:

[0121] Users deepen their knowledge of identified weaknesses by using slides displayed on their devices. This increased knowledge acquisition allows for effective preparation for the next test. A concrete example would be learning about relevant product specifications and sales methods to accurately understand the features of a newly released product.

[0122] 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.

[0123] This invention is a system that provides an individualized learning experience to improve the user's learning efficiency, and in particular incorporates technology that recognizes the user's emotional state and adapts the learning content accordingly. This system mainly consists of a combination of a server, a terminal, a user, and an emotion engine.

[0124] Server Role

[0125] The server receives test results and sentiment data submitted by the user and records them in a database. Based on this data, the server analyzes the user's learning tendencies and emotional changes, and generates personalized learning content and learning plans. In particular, it uses sentiment data obtained from the sentiment engine to understand the user's level of concentration and stress, and adjusts the order and difficulty level of the learning content presented based on this.

[0126] Terminal role

[0127] The device receives personalized learning slides and instructions based on emotion data sent from the server. As the user views the slides, the device activates an emotion engine in real time, analyzing the user's emotions from their facial expressions and voice. The collected emotion information is then sent to the server, and the learning content is continuously optimized.

[0128] The role of the emotional engine

[0129] The emotion engine is embedded in the user's device and recognizes the user's emotions in real time. Specifically, it analyzes the user's facial expressions and voice characteristics through the camera and microphone to identify emotions such as joy, sadness, stress, and concentration levels. This data is sent to a server as key information to improve learning efficiency and is used to dynamically adjust the learning content.

[0130] User roles

[0131] Users view learning slides delivered by the system via their devices and receive a learning experience tailored to their emotional state, as recognized by the emotion engine. If a user experiences stress or a decrease in concentration, the system immediately adjusts the learning content and pace to provide an optimal learning environment.

[0132] For example, if the emotion engine determines that a user's concentration is waning, the server will temporarily reduce the amount of learning content presented and suggest short quizzes or motivational content to refresh the user. In this way, support is provided to help users continue learning efficiently.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] The user logs in via their device when starting a learning session. The device sends the user's identification information to the server and prepares to start the learning session.

[0136] Step 2:

[0137] The server retrieves the user's past learning results and history data from the database. Based on this data, the server identifies the relevant learning content and generates a learning plan for the user.

[0138] Step 3:

[0139] The device begins displaying the learning content provided by the server. Simultaneously, the emotion engine starts up and begins collecting emotion data through the user's facial expressions and voice.

[0140] Step 4:

[0141] The emotion engine analyzes the user's emotional state in real time and sends that data to the server. Specifically, it determines concentration levels, stress levels, and other factors based on the user's eye movements and tone of voice.

[0142] Step 5:

[0143] The server evaluates the user's emotional state based on emotional data and dynamically adjusts the learning content accordingly. If the emotional state is detected as unsuitable for learning, it presents simpler content or break content.

[0144] Step 6:

[0145] The device presents the user with the latest learning content provided by the server. Based on the user's emotional state, the device appropriately adjusts the learning pace and the difficulty level of the content.

[0146] Step 7:

[0147] The user continuously views the adjusted learning content. Because the content is updated in real time based on the user's emotional state, the user can learn in the best possible environment.

[0148] Step 8:

[0149] When a learning session ends, the device sends the final learning results to the server. The server saves these results to a database and prepares for subsequent learning sessions.

[0150] Through this processing flow, the system can provide users with a highly personalized learning experience using emotion recognition.

[0151] (Example 2)

[0152] 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".

[0153] A problem exists where learners' learning efficiency suffers because they are not provided with learning content appropriate to their individual emotional states. Furthermore, current learning systems have difficulty reflecting changes in users' emotions in real time and providing personalized learning experiences. In addition, there is a lack of feedback and break suggestions based on users' emotions, making it difficult to optimize the learning pace.

[0154] 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.

[0155] In this invention, the server includes means for recognizing the user's emotional state and dynamically adjusting the display order and difficulty level of learning content based on that emotional state; means for collecting the emotional data and learning progress information and transmitting it to a communication device; and means for analyzing the emotional data and learning progress information collected by the communication device and generating an individualized learning plan. This makes it possible to optimize the learning content and learning pace to suit the user's emotions.

[0156] "Emotional state" refers to a specific emotional state exhibited by a learner, including the type and intensity of emotions such as joy, sadness, stress, and concentration.

[0157] "Dynamic adjustment" means instantly changing the order and difficulty level of learning content in response to real-time feedback from users.

[0158] "Communication device" refers to hardware or a platform that communicates with a user's terminal to support data collection and transmission.

[0159] A "learning plan" refers to a plan that includes detailed learning content and schedules tailored to the user's learning needs and emotional state.

[0160] A "generative AI model" refers to an algorithm that generates and analyzes data based on artificial intelligence technology to provide users with optimal learning materials and feedback.

[0161] The system of this invention is composed of a server, terminal, user, and emotion engine at its core to realize emotion recognition and personalized learning. Details of each component are as follows.

[0162] Server Configuration and Roles

[0163] The server manages user sentiment data and learning progress information in conjunction with the database. Using this data, the server leverages generative AI models to analyze the user's learning state. It then generates personalized learning plans and sends them to the user's device. To efficiently process large amounts of data, the server needs a high-performance processor and ample memory.

[0164] Device configuration and role

[0165] The terminal functions as an interface connecting the user and the server. It is primarily equipped with a camera and microphone, which are used by an emotion engine to analyze the user's facial expressions and voice characteristics. The resulting emotion data is transmitted to the server in real time. The terminal includes a display for showing learning slides and an input device for detecting user actions.

[0166] User roles

[0167] Users view and utilize learning slides. During learning, emotional information collected by the camera and microphone is analyzed in the background and sent to the server. If the user experiences stress or their concentration decreases, the learning content and pace are automatically adjusted based on instructions sent from the server.

[0168] The structure and role of the emotional engine

[0169] The emotion engine is software that analyzes a user's emotions in real time. It implements machine learning algorithms and recognizes emotions such as joy, sadness, stress, and concentration levels based on data obtained from the camera and microphone. The recognized emotion data is then used to generate learning plans on the server side.

[0170] Specific example

[0171] For example, if the emotion engine determines that a user's concentration is waning, the server inserts suggestions for refreshing quizzes or light exercises into the learning plan. In this process, the generative AI model receives prompts such as "Please provide content that will help the user refresh" and suggests appropriate content. In this way, it becomes possible to dynamically optimize the user's learning experience according to their individual state.

[0172] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0173] Step 1:

[0174] The user starts a learning session and interacts with the device to view learning slides. The user's facial expressions and voice are collected as input via the camera and microphone. This data is sent to the emotion engine on the device.

[0175] Step 2:

[0176] The device analyzes facial and voice data collected using an emotion engine. The emotion engine utilizes machine learning algorithms to identify the user's emotional state (e.g., concentration level, stress) based on the input data. The analysis results are generated as output and sent to the server.

[0177] Step 3:

[0178] The server receives emotional state data sent from the terminal and records it in a database. Using the emotional state as input and past training data, the server utilizes a generative AI model to generate an optimal learning plan for the user. As output, personalized learning slides and supplementary materials are generated.

[0179] Step 4:

[0180] The server sends the generated learning plan and slides to the terminal. The terminal then uses this to prepare the learning content to display to the user. The input is the learning slides from the server, and the output is the content to be displayed to the user.

[0181] Step 5:

[0182] The user continues to view the displayed learning slides and provides feedback via the device as needed. The device collects facial expressions and audio again in real time, and the process returns to step 2 to monitor changes in emotional state. This cycle optimizes the learning content for continuous improvement.

[0183] Step 6:

[0184] The server, based on the received sentiment data and additional learning outcomes, sends a prompt message to the AI ​​model, which then generates additional learning materials or rest content as needed. This process may include using the prompt message, "Your concentration is low. Please generate refreshment content."

[0185] Step 7:

[0186] The optimized learning content and supplementary materials are sent back to the device and presented to the user. This creates an environment that supports the user in continuing to learn efficiently.

[0187] (Application Example 2)

[0188] 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".

[0189] Conventional learning support systems provide individualization based on the user's learning progress, but they cannot dynamically adjust learning content while considering the user's emotional state, and therefore fail to adequately improve learning efficiency and motivation. For this reason, there is a need for technology that can recognize the user's emotional state in real time and appropriately adapt learning content.

[0190] 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.

[0191] In this invention, the server includes means for acquiring the user's learning results and emotional state, and automatically generating personalized learning information based on said learning results and emotional state; means for organizing said personalized learning information by referring to past learning data and external information sources; and means for recognizing the user's emotions in real time and dynamically adjusting the learning information according to that state. This makes it possible to improve the user's learning efficiency and provide an effective learning experience while reducing the burden on the user.

[0192] A "user" is a person who uses the system and is the recipient of personalized learning content.

[0193] "Learning results" refer to data that shows the knowledge and skills acquired by the user during the learning process, and serve as the basis for the system to generate personalized learning information.

[0194] "Emotional state" refers to the user's current psychological and emotional condition, and is important information for the system to dynamically adjust the learning content.

[0195] "Personalized learning information" refers to information that indicates learning content and pace optimized for a specific user, based on the user's learning results and emotional state.

[0196] "Past learning data" refers to records of learning that users have done in the past, and is referenced when organizing the current learning content.

[0197] "External information sources" refer to information outside the system that is referenced when organizing learning content, and include encyclopedias and specialized databases.

[0198] "Recognizing user emotions in real time" means analyzing the user's emotional state without any time delay and understanding their psychological state while they are learning.

[0199] "Dynamic adjustment" means appropriately changing learning content and methods in response to the passage of time and changes in circumstances, and is a process for realizing education that is tailored to the user's situation.

[0200] A "generative AI model" is an artificial intelligence model that uses machine learning techniques to generate new data or information.

[0201] A "prompt statement" is an instruction given to an AI model to guide it to produce an appropriate response or output, and it provides relevant information for the user in learning support.

[0202] In this invention, the server acquires the user's learning results and emotional state and automatically generates personalized learning information. The hardware used is a general cloud server or database server, and machine learning libraries such as TENSORFLOW® and PyTorch are utilized for emotion recognition. This allows the server to generate organized learning information by referencing past learning data and external information sources. The server also uses a generative AI model to create prompt statements, providing a learning experience tailored to the user.

[0203] The terminal acts as the interface with the user, using a camera and microphone to recognize the user's emotional state in real time. This uses OpenCV for facial recognition and librosa for speech analysis. The terminal sends this data to a server, and the server presents personalized learning information to the user. The learning content and pace are dynamically adjusted based on the user's learning progress and real-time emotional feedback.

[0204] Users can utilize personalized learning information provided via devices such as smartphones to facilitate efficient learning. For example, elementary school students working on a summer vacation project can use this system to efficiently understand experimental procedures and necessary background knowledge, enabling them to smoothly complete their project.

[0205] An example of a prompt statement in this invention is: "The user's facial expression is {facial expression data}, and their voice is {voice data}. Based on this data, evaluate the user's emotions and recommend appropriate learning content." Such specific prompts enable the generative AI model to provide learning information tailored to the user.

[0206] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0207] Step 1:

[0208] The device uses the smartphone's camera and microphone to acquire the user's facial expressions and audio data in real time. The input to the device is video and audio data, which is used to analyze facial and audio features using OpenCV and librosa. The output is analyzed emotional state data. Through this process, the user's emotions are determined, such as "concentrating" or "feeling stressed."

[0209] Step 2:

[0210] The device sends the emotional state data acquired in Step 1 to the server. The server receives this emotional state data and analyzes it against its past learning database. It receives emotional state data and past learning history data as input and uses a generative AI model to create prompt sentences based on this. As output, learning information optimized for the user is generated.

[0211] Step 3:

[0212] The server sends the learning information generated in step 2 to the terminal. The terminal receives this learning information and presents it to the user. Specifically, it displays personalized learning content on the learning application screen based on the user's emotional state and learning history. The user can then use this content to smoothly progress through their learning.

[0213] Step 4:

[0214] The user uses the presented learning information to tackle problems. By answering specific questions or digesting learning content, they gain further learning results and new emotional states. This serves as input when returning to step 1 of the next cycle.

[0215] Through this entire process, users can continuously receive learning support adapted to their emotional state, maximizing their learning effectiveness.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] [Second Embodiment]

[0220] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0221] 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.

[0222] 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).

[0223] 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.

[0224] 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.

[0225] 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).

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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".

[0232] This invention comprises a learning-based training system that utilizes artificial intelligence to provide a personalized learning experience in order to enhance the user's learning efficiency. The system primarily consists of a server, terminals, and users.

[0233] Server Role

[0234] The server receives test results submitted by users and records the data in a database. The server then analyzes the collected test results for each user. Using artificial intelligence technology, it identifies the user's weaknesses by pinpointing incorrect answers and related learning topics. Based on this, it automatically generates personalized learning slides, referencing past learning content and external information sources. These generated slides are structured to meet each user's learning needs.

[0235] Terminal role

[0236] The device receives personalized learning slides sent from the server and presents them to the user. The device is designed to allow users to comfortably view the slides through a graphical user interface. Furthermore, as the user progresses through the learning process, the device records their progress and saves the data for use in the next learning step.

[0237] User roles

[0238] Users can use this system to improve their learning efficiency. They can view learning slides displayed on their device and use them to deepen their understanding of topics they answered incorrectly. The personalized content provided by the system allows users to learn at their own pace.

[0239] For example, if a user makes multiple incorrect answers on the topic of "data structures" in a particular test, the server generates learning slides containing content related to that topic and sends them to the user's device. Through these slides, the user can deepen their understanding of the questions and aim for better results in their next attempt. In this way, the present invention efficiently provides personalized learning support and creates an environment in which users can learn more effectively.

[0240] The following describes the processing flow.

[0241] Step 1:

[0242] The server receives the user's test results. After the test is completed, the user's device sends correct / incorrect answer data for each question to the server. This data is structured as question number and result (correct or incorrect).

[0243] Step 2:

[0244] The server records the received test results in a database. The results are stored along with each user's identification information, preparing them for subsequent analysis.

[0245] Step 3:

[0246] The server executes a process to analyze the recorded test results. Using artificial intelligence, it identifies incorrect answers and related topics, extracting the user's weaknesses. For example, if a group of questions with many incorrect answers are concentrated on a particular topic, that topic is recognized as the user's weakness.

[0247] Step 4:

[0248] The server generates personalized learning slides based on identified weaknesses. It automatically generates slides by referencing past learning databases and reliable information sources on the internet, and combining relevant content.

[0249] Step 5:

[0250] The server sends the generated learning slides to the user's device. It links them with the user's identification information to quickly deliver personalized content.

[0251] Step 6:

[0252] The device opens the received learning slides and makes them available for viewing to the user. The device provides a graphical user interface to help the user smoothly progress through the slide learning process.

[0253] Step 7:

[0254] Users view learning slides displayed on their device and begin learning based on personalized content. Users can learn at their own pace and record their progress on their device.

[0255] This processing flow allows users to efficiently address their weaknesses and maximize their learning effectiveness.

[0256] (Example 1)

[0257] 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".

[0258] In conventional learning systems, it was difficult to quickly and accurately provide personalized educational content based on the learning results submitted by users. This resulted in the challenge of maximizing the learning efficiency of each user. Furthermore, there was insufficient mechanism for identifying users' weaknesses and providing appropriate learning materials accordingly.

[0259] 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.

[0260] In this invention, the server includes means for registering learning results obtained from the user in a recording device, means for analyzing the learning results to identify the user's incorrect answers, and means for creating personalized educational materials based on the incorrect answers using a generation algorithm. This enables the rapid generation and provision of optimal educational content tailored to each individual user.

[0261] "User" refers to an individual who uses this system to learn through educational materials.

[0262] "Learning results" refers to the collective performance and answer information from tests and exercises taken by users.

[0263] A "recording device" is a mechanism for storing and managing data, and may include a database.

[0264] "Analysis" refers to data processing procedures that involve processing information based on data to obtain useful insights.

[0265] An "incorrect answer" refers to an item that a user answered incorrectly during the learning process, and is identified to provide further learning opportunities.

[0266] A "generative algorithm" encompasses a set of techniques used to create a new output based on input data.

[0267] "Educational materials" refer to content such as slides and documents provided to assist users in their learning.

[0268] "Personalization" means that adjustments are made to suit the different requirements and needs of each user.

[0269] This invention specifically demonstrates a method for providing a personalized learning experience by utilizing artificial intelligence in the learning process. This system mainly consists of a server, terminals, and users.

[0270] The server receives learning result data transmitted from users via the internet and stores this data using a recording device. This data includes the user's scores and error information from tests and exercises. General database software is used for database management.

[0271] Next, the server uses machine learning libraries for data analysis to identify the user's incorrect answers. Based on this analysis, it leverages a generative algorithm to create personalized training materials. Common generative techniques can be used as the generative AI model, using the prompt "How do I create training slides based on the user's incorrect topics?".

[0272] Learning materials generated on the server are sent to the terminal. The terminal presents these materials to the user through a graphical user interface, designed to allow for smooth viewing. The terminal also records the user's learning progress and saves that data to local storage for the next learning session.

[0273] Users use the learning materials presented on this device to deepen their understanding of topics they previously answered incorrectly. Based on the personalized content provided by the system, users can learn at their own pace and progress effectively. For example, if a user answers multiple questions related to "data structures" incorrectly, the server generates and provides learning materials related to those topics to help the user achieve better results in their next attempt.

[0274] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0275] Step 1:

[0276] The server receives learning result data from users via the internet. The input is the user's test results, and this data is stored in a recording device. The server prepares the data for subsequent analysis by standardizing the data format and storing it in a database. The output is the learning result data stored in the database.

[0277] Step 2:

[0278] The server analyzes the saved learning result data. For this analysis, a machine learning library is used to mainly extract the patterns and frequencies of incorrect answers. The input is the learning results in the database, and the server identifies the incorrect answer questions of each user and lists the topics that are likely to be the causes. The output is a list of incorrect answer questions for each user.

[0279] Step 3:

[0280] The server creates personalized learning materials based on the incorrect answers using a generation algorithm. At this time, the prompt sentence "Please teach me how to create learning slides based on the user's incorrect answer topics" is used for the generation AI model. The input is the identified list of incorrect answer questions, and the server compiles individual learning materials in slide format based on the information obtained from the AI model. The output is personalized learning materials.

[0281] Step 4:

[0282] The server sends the generated learning materials to the terminal. The input is the learning materials created by the server, and the server pushes this to a specific application on the terminal via the Internet. The output is the learning materials distributed to the terminal.

[0283] Step 5:

[0284] The terminal presents the received individual learning materials to the user. The input is the learning materials sent from the server, and the terminal displays the materials in a format that is easy for the user to use. The output is visually organized slides to facilitate the user's understanding.

[0285] Step 6:

[0286] The terminal records the progress of the user's learning. The input is the user's browsing activities, and the terminal records in the log how much each slide has been viewed. The output is data that can be used to improve for the next learning session.

[0287] Step 7:

[0288] The user deepens the understanding of the topics with incorrect answers through the provided learning materials. The input is the learning materials presented on the terminal, and the user browses the slides and acquires knowledge. The output is an improved comprehension ability aiming for better results in the next test.

[0289] (Application Example 1)

[0290] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0291] The acquisition of product knowledge in commercial stores often depends on the experience and background of individual store employees, and it is difficult to provide knowledge uniformly. Also, in modern times when new products frequently appear, it is an important issue for store employees to efficiently acquire the latest product information. In the conventional method, it was difficult to provide knowledge tailored to individual weaknesses, so inefficiency was seen in the learning of store employees.

[0292] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0293] In this invention, the server includes means for acquiring the learning results of the user and automatically generating individualized learning content based on the learning results, means for compiling the individualized learning content by referring to past learning information and external information sources, means for presenting the compiled learning content to the user, and a knowledge system that provides knowledge including the features of new products, and means for automatically generating individualized educational materials based on the identified weak items of the user. Thereby, it becomes possible for store employees to efficiently acquire the necessary knowledge based on individual weaknesses and promote product understanding in commercial stores.

[0294] The "user" refers to individual store employees within the store who receive learning content through the knowledge system for the purpose of deepening product understanding.

[0295] "Learning results" refer to the outcomes obtained by users using the knowledge system, and are data that influences subsequent learning content based on whether the answers are correct or incorrect.

[0296] "Personalized learning content" refers to educational materials specifically created for a user, based on their specific weaknesses and past learning history, using artificial intelligence.

[0297] "External information sources" refer to external databases and publicly available resources that knowledge systems refer to when organizing personalized learning content.

[0298] "Identified weaknesses" refer to areas where the user's knowledge is lacking or understanding is incomplete, as revealed during their learning process.

[0299] "Educational materials" refer to information and content created to improve users' knowledge and address specific areas of weakness.

[0300] A "commercial store" refers to a physical facility that provides goods and services to the general public, and is a place where store employees engage in activities to deepen their understanding of the products.

[0301] This invention comprises a server, terminals, and users to realize an employee training system for stores. The server receives the results of tests taken by users and records them in a database. Subsequently, artificial intelligence technology is used to identify the user's weak points and generate personalized learning slides based on those points. This helps users efficiently overcome their shortcomings.

[0302] The server uses MongoDB as its database for processing, and a Python-based machine learning framework is employed for the individual generation of training content. The generated training slides are sent to the device via AWS or Google Cloud Platform.

[0303] The terminal receives the materials sent from the server and has the role of visually displaying them to the user. A smartphone app developed using React Native provides an easy-to-use interface and functions for viewing learning slides and progress management.

[0304] Users can view individualized learning slides through the smartphone app and acquire product knowledge. As a specific example, when a new sales product is introduced, users can refer to individual learning slides containing its features to deepen their understanding. This enables the rapid provision of accurate and useful information when explaining the product to customers.

[0305] Examples of prompt sentences include "Generate learning slides in case of misunderstandings about the new autumn collection" and "Create slides highlighting the features of this product". By using these prompt sentences, the generative AI model can provide optimal learning content tailored to the needs of the user.

[0306] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0307] Step 1:

[0308] The server receives the results of the test conducted by the user. This result includes information on correct and incorrect answers for each question. The received data is stored in MongoDB. This makes it possible to track individual learning progress.

[0309] Step 2:

[0310] The server uses artificial intelligence technology to identify the user's weak points based on the received test result data. This process utilizes a Python machine learning framework, performing data analysis and calculations to efficiently identify areas with frequent errors. The identified weaknesses are then used as important data for generating subsequent learning slides.

[0311] Step 3:

[0312] The server automatically generates relevant learning content based on identified weaknesses. This generation utilizes a generative AI model to create personalized slides tailored to the user's needs. By analyzing input data and selecting appropriate topics and content, it generates learning slides as output.

[0313] Step 4:

[0314] The server sends the generated learning slides to the device via AWS or Google Cloud Platform, making them accessible to the user. The slides are output in an appropriate format so that they can be visually displayed on the user's device.

[0315] Step 5:

[0316] The device receives learning slides sent from the server and presents them to the user. A user interface built with React Native allows users to visually review the slides as they progress through the learning process. Progress data is recorded based on user interactions, enabling the provision of additional information during subsequent access.

[0317] Step 6:

[0318] Users deepen their knowledge of identified weaknesses by using slides displayed on their devices. This increased knowledge acquisition allows for effective preparation for the next test. A concrete example would be learning about relevant product specifications and sales methods to accurately understand the features of a newly released product.

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

[0320] This invention is a system that provides an individualized learning experience to improve the user's learning efficiency, and in particular incorporates technology that recognizes the user's emotional state and adapts the learning content accordingly. This system mainly consists of a combination of a server, a terminal, a user, and an emotion engine.

[0321] Server Role

[0322] The server receives test results and sentiment data submitted by the user and records them in a database. Based on this data, the server analyzes the user's learning tendencies and emotional changes, and generates personalized learning content and learning plans. In particular, it uses sentiment data obtained from the sentiment engine to understand the user's level of concentration and stress, and adjusts the order and difficulty level of the learning content presented based on this.

[0323] Terminal role

[0324] The device receives personalized learning slides and instructions based on emotion data sent from the server. As the user views the slides, the device activates an emotion engine in real time, analyzing the user's emotions from their facial expressions and voice. The collected emotion information is then sent to the server, and the learning content is continuously optimized.

[0325] The role of the emotional engine

[0326] The emotion engine is embedded in the user's device and recognizes the user's emotions in real time. Specifically, it analyzes the user's facial expressions and voice characteristics through the camera and microphone to identify emotions such as joy, sadness, stress, and concentration levels. This data is sent to a server as key information to improve learning efficiency and is used to dynamically adjust the learning content.

[0327] User roles

[0328] Users view learning slides delivered by the system via their devices and receive a learning experience tailored to their emotional state, as recognized by the emotion engine. If a user experiences stress or a decrease in concentration, the system immediately adjusts the learning content and pace to provide an optimal learning environment.

[0329] For example, if the emotion engine determines that a user's concentration is waning, the server will temporarily reduce the amount of learning content presented and suggest short quizzes or motivational content to refresh the user. In this way, support is provided to help users continue learning efficiently.

[0330] The following describes the processing flow.

[0331] Step 1:

[0332] The user logs in via their device when starting a learning session. The device sends the user's identification information to the server and prepares to start the learning session.

[0333] Step 2:

[0334] The server retrieves the user's past learning results and history data from the database. Based on this data, the server identifies the relevant learning content and generates a learning plan for the user.

[0335] Step 3:

[0336] The device begins displaying the learning content provided by the server. Simultaneously, the emotion engine starts up and begins collecting emotion data through the user's facial expressions and voice.

[0337] Step 4:

[0338] The emotion engine analyzes the user's emotional state in real time and sends that data to the server. Specifically, it determines concentration levels, stress levels, and other factors based on the user's eye movements and tone of voice.

[0339] Step 5:

[0340] The server evaluates the user's emotional state based on emotional data and dynamically adjusts the learning content accordingly. If the emotional state is detected as unsuitable for learning, it presents simpler content or break content.

[0341] Step 6:

[0342] The device presents the user with the latest learning content provided by the server. Based on the user's emotional state, the device appropriately adjusts the learning pace and the difficulty level of the content.

[0343] Step 7:

[0344] The user continuously views the adjusted learning content. Because the content is updated in real time based on the user's emotional state, the user can learn in the best possible environment.

[0345] Step 8:

[0346] When a learning session ends, the device sends the final learning results to the server. The server saves these results to a database and prepares for subsequent learning sessions.

[0347] Through this processing flow, the system can provide users with a highly personalized learning experience using emotion recognition.

[0348] (Example 2)

[0349] 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".

[0350] A problem exists where learners' learning efficiency suffers because they are not provided with learning content appropriate to their individual emotional states. Furthermore, current learning systems have difficulty reflecting changes in users' emotions in real time and providing personalized learning experiences. In addition, there is a lack of feedback and break suggestions based on users' emotions, making it difficult to optimize the learning pace.

[0351] 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.

[0352] In this invention, the server includes means for recognizing the user's emotional state and dynamically adjusting the display order and difficulty level of learning content based on that emotional state; means for collecting the emotional data and learning progress information and transmitting it to a communication device; and means for analyzing the emotional data and learning progress information collected by the communication device and generating an individualized learning plan. This makes it possible to optimize the learning content and learning pace to suit the user's emotions.

[0353] "Emotional state" refers to a specific emotional state exhibited by a learner, including the type and intensity of emotions such as joy, sadness, stress, and concentration.

[0354] "Dynamic adjustment" means instantly changing the order and difficulty level of learning content in response to real-time feedback from users.

[0355] "Communication device" refers to hardware or a platform that communicates with a user's terminal to support data collection and transmission.

[0356] A "learning plan" refers to a plan that includes detailed learning content and schedules tailored to the user's learning needs and emotional state.

[0357] A "generative AI model" refers to an algorithm that generates and analyzes data based on artificial intelligence technology to provide users with optimal learning materials and feedback.

[0358] The system of this invention is composed of a server, terminal, user, and emotion engine at its core to realize emotion recognition and personalized learning. Details of each component are as follows.

[0359] Server Configuration and Roles

[0360] The server manages user sentiment data and learning progress information in conjunction with the database. Using this data, the server leverages generative AI models to analyze the user's learning state. It then generates personalized learning plans and sends them to the user's device. To efficiently process large amounts of data, the server needs a high-performance processor and ample memory.

[0361] Device configuration and role

[0362] The terminal functions as an interface connecting the user and the server. It is primarily equipped with a camera and microphone, which are used by an emotion engine to analyze the user's facial expressions and voice characteristics. The resulting emotion data is transmitted to the server in real time. The terminal includes a display for showing learning slides and an input device for detecting user actions.

[0363] User roles

[0364] Users view and utilize learning slides. During learning, emotional information collected by the camera and microphone is analyzed in the background and sent to the server. If the user experiences stress or their concentration decreases, the learning content and pace are automatically adjusted based on instructions sent from the server.

[0365] The structure and role of the emotional engine

[0366] The emotion engine is software that analyzes a user's emotions in real time. It implements machine learning algorithms and recognizes emotions such as joy, sadness, stress, and concentration levels based on data obtained from the camera and microphone. The recognized emotion data is then used to generate learning plans on the server side.

[0367] Specific example

[0368] For example, if the emotion engine determines that a user's concentration is waning, the server inserts suggestions for refreshing quizzes or light exercises into the learning plan. In this process, the generative AI model receives prompts such as "Please provide content that will help the user refresh" and suggests appropriate content. In this way, it becomes possible to dynamically optimize the user's learning experience according to their individual state.

[0369] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0370] Step 1:

[0371] The user starts a learning session and interacts with the device to view learning slides. The user's facial expressions and voice are collected as input via the camera and microphone. This data is sent to the emotion engine on the device.

[0372] Step 2:

[0373] The device analyzes facial and voice data collected using an emotion engine. The emotion engine utilizes machine learning algorithms to identify the user's emotional state (e.g., concentration level, stress) based on the input data. The analysis results are generated as output and sent to the server.

[0374] Step 3:

[0375] The server receives emotional state data sent from the terminal and records it in a database. Using the emotional state as input and past training data, the server utilizes a generative AI model to generate an optimal learning plan for the user. As output, personalized learning slides and supplementary materials are generated.

[0376] Step 4:

[0377] The server sends the generated learning plan and slides to the terminal. The terminal then uses this to prepare the learning content to display to the user. The input is the learning slides from the server, and the output is the content to be displayed to the user.

[0378] Step 5:

[0379] The user continues to view the displayed learning slides and provides feedback via the device as needed. The device collects facial expressions and audio again in real time, and the process returns to step 2 to monitor changes in emotional state. This cycle optimizes the learning content for continuous improvement.

[0380] Step 6:

[0381] The server, based on the received sentiment data and additional learning outcomes, sends a prompt message to the AI ​​model, which then generates additional learning materials or rest content as needed. This process may include using the prompt message, "Your concentration is low. Please generate refreshment content."

[0382] Step 7:

[0383] The optimized learning content and supplementary materials are sent back to the device and presented to the user. This creates an environment that supports the user in continuing to learn efficiently.

[0384] (Application Example 2)

[0385] 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."

[0386] Conventional learning support systems provide individualization based on the user's learning progress, but they cannot dynamically adjust learning content while considering the user's emotional state, and therefore fail to adequately improve learning efficiency and motivation. For this reason, there is a need for technology that can recognize the user's emotional state in real time and appropriately adapt learning content.

[0387] 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.

[0388] In this invention, the server includes means for acquiring the user's learning results and emotional state, and automatically generating personalized learning information based on said learning results and emotional state; means for organizing said personalized learning information by referring to past learning data and external information sources; and means for recognizing the user's emotions in real time and dynamically adjusting the learning information according to that state. This makes it possible to improve the user's learning efficiency and provide an effective learning experience while reducing the burden on the user.

[0389] A "user" is a person who uses the system and is the recipient of personalized learning content.

[0390] "Learning results" refer to data that shows the knowledge and skills acquired by the user during the learning process, and serve as the basis for the system to generate personalized learning information.

[0391] "Emotional state" refers to the user's current psychological and emotional condition, and is important information for the system to dynamically adjust the learning content.

[0392] "Personalized learning information" refers to information that indicates learning content and pace optimized for a specific user, based on the user's learning results and emotional state.

[0393] "Past learning data" refers to records of learning that users have done in the past, and is referenced when organizing the current learning content.

[0394] "External information sources" refer to information outside the system that is referenced when organizing learning content, and include encyclopedias and specialized databases.

[0395] "Recognizing user emotions in real time" means analyzing the user's emotional state without any time delay and understanding their psychological state while they are learning.

[0396] "Dynamic adjustment" means appropriately changing learning content and methods in response to the passage of time and changes in circumstances, and is a process for realizing education that is tailored to the user's situation.

[0397] A "generative AI model" is an artificial intelligence model that uses machine learning techniques to generate new data or information.

[0398] A "prompt statement" is an instruction given to an AI model to guide it to produce an appropriate response or output, and it provides relevant information for the user in learning support.

[0399] In this invention, the server acquires the user's learning results and emotional state, and automatically generates personalized learning information. The hardware used is a general cloud server or database server, and machine learning libraries such as TensorFlow and PyTorch are utilized for emotion recognition. This allows the server to generate organized learning information by referencing past learning data and external information sources. The server also uses a generative AI model to create prompt statements, providing a learning experience tailored to the user.

[0400] The terminal acts as the interface with the user, using a camera and microphone to recognize the user's emotional state in real time. This uses OpenCV for facial recognition and librosa for speech analysis. The terminal sends this data to a server, and the server presents personalized learning information to the user. The learning content and pace are dynamically adjusted based on the user's learning progress and real-time emotional feedback.

[0401] Users can utilize personalized learning information provided via devices such as smartphones to facilitate efficient learning. For example, elementary school students working on a summer vacation project can use this system to efficiently understand experimental procedures and necessary background knowledge, enabling them to smoothly complete their project.

[0402] An example of a prompt statement in this invention is: "The user's facial expression is {facial expression data}, and their voice is {voice data}. Based on this data, evaluate the user's emotions and recommend appropriate learning content." Such specific prompts enable the generative AI model to provide learning information tailored to the user.

[0403] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0404] Step 1:

[0405] The device uses the smartphone's camera and microphone to acquire the user's facial expressions and audio data in real time. The input to the device is video and audio data, which is used to analyze facial and audio features using OpenCV and librosa. The output is analyzed emotional state data. Through this process, the user's emotions are determined, such as "concentrating" or "feeling stressed."

[0406] Step 2:

[0407] The device sends the emotional state data acquired in Step 1 to the server. The server receives this emotional state data and analyzes it against its past learning database. It receives emotional state data and past learning history data as input and uses a generative AI model to create prompt sentences based on this. As output, learning information optimized for the user is generated.

[0408] Step 3:

[0409] The server sends the learning information generated in step 2 to the terminal. The terminal receives this learning information and presents it to the user. Specifically, it displays personalized learning content on the learning application screen based on the user's emotional state and learning history. The user can then use this content to smoothly progress through their learning.

[0410] Step 4:

[0411] The user uses the presented learning information to tackle problems. By answering specific questions or digesting learning content, they gain further learning results and new emotional states. This serves as input when returning to step 1 of the next cycle.

[0412] Through this entire process, users can continuously receive learning support adapted to their emotional state, maximizing their learning effectiveness.

[0413] 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.

[0414] 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.

[0415] 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.

[0416] [Third Embodiment]

[0417] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0418] 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.

[0419] 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).

[0420] 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.

[0421] 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.

[0422] 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).

[0423] 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.

[0424] 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.

[0425] 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.

[0426] 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.

[0427] 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.

[0428] 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".

[0429] This invention comprises a learning-based training system that utilizes artificial intelligence to provide a personalized learning experience in order to enhance the user's learning efficiency. The system primarily consists of a server, terminals, and users.

[0430] Server Role

[0431] The server receives test results submitted by users and records the data in a database. The server then analyzes the collected test results for each user. Using artificial intelligence technology, it identifies the user's weaknesses by pinpointing incorrect answers and related learning topics. Based on this, it automatically generates personalized learning slides, referencing past learning content and external information sources. These generated slides are structured to meet each user's learning needs.

[0432] Terminal role

[0433] The device receives personalized learning slides sent from the server and presents them to the user. The device is designed to allow users to comfortably view the slides through a graphical user interface. Furthermore, as the user progresses through the learning process, the device records their progress and saves the data for use in the next learning step.

[0434] User roles

[0435] Users can use this system to improve their learning efficiency. They can view learning slides displayed on their device and use them to deepen their understanding of topics they answered incorrectly. The personalized content provided by the system allows users to learn at their own pace.

[0436] For example, if a user makes multiple incorrect answers on the topic of "data structures" in a particular test, the server generates learning slides containing content related to that topic and sends them to the user's device. Through these slides, the user can deepen their understanding of the questions and aim for better results in their next attempt. In this way, the present invention efficiently provides personalized learning support and creates an environment in which users can learn more effectively.

[0437] The following describes the processing flow.

[0438] Step 1:

[0439] The server receives the user's test results. After the test is completed, the user's device sends correct / incorrect answer data for each question to the server. This data is structured as question number and result (correct or incorrect).

[0440] Step 2:

[0441] The server records the received test results in a database. The results are stored along with each user's identification information, preparing them for subsequent analysis.

[0442] Step 3:

[0443] The server executes a process to analyze the recorded test results. Using artificial intelligence, it identifies incorrect answers and related topics, extracting the user's weaknesses. For example, if a group of questions with many incorrect answers are concentrated on a particular topic, that topic is recognized as the user's weakness.

[0444] Step 4:

[0445] The server generates personalized learning slides based on identified weaknesses. It automatically generates slides by referencing past learning databases and reliable information sources on the internet, and combining relevant content.

[0446] Step 5:

[0447] The server sends the generated learning slides to the user's device. It links them with the user's identification information to quickly deliver personalized content.

[0448] Step 6:

[0449] The device opens the received learning slides and makes them available for viewing to the user. The device provides a graphical user interface to help the user smoothly progress through the slide learning process.

[0450] Step 7:

[0451] Users view learning slides displayed on their device and begin learning based on personalized content. Users can learn at their own pace and record their progress on their device.

[0452] This processing flow allows users to efficiently address their weaknesses and maximize their learning effectiveness.

[0453] (Example 1)

[0454] 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."

[0455] In conventional learning systems, it was difficult to quickly and accurately provide personalized educational content based on the learning results submitted by users. This resulted in the challenge of maximizing the learning efficiency of each user. Furthermore, there was insufficient mechanism for identifying users' weaknesses and providing appropriate learning materials accordingly.

[0456] 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.

[0457] In this invention, the server includes means for registering learning results obtained from the user in a recording device, means for analyzing the learning results to identify the user's incorrect answers, and means for creating personalized educational materials based on the incorrect answers using a generation algorithm. This enables the rapid generation and provision of optimal educational content tailored to each individual user.

[0458] "User" refers to an individual who uses this system to learn through educational materials.

[0459] "Learning results" refers to the collective performance and answer information from tests and exercises taken by users.

[0460] A "recording device" is a mechanism for storing and managing data, and may include a database.

[0461] "Analysis" refers to data processing procedures that involve processing information based on data to obtain useful insights.

[0462] An "incorrect answer" refers to an item that a user answered incorrectly during the learning process, and is identified to provide further learning opportunities.

[0463] A "generative algorithm" encompasses a set of techniques used to create a new output based on input data.

[0464] "Educational materials" refer to content such as slides and documents provided to assist users in their learning.

[0465] "Personalization" means that adjustments are made to suit the different requirements and needs of each user.

[0466] This invention specifically demonstrates a method for providing a personalized learning experience by utilizing artificial intelligence in the learning process. This system mainly consists of a server, terminals, and users.

[0467] The server receives learning result data transmitted from users via the internet and stores this data using a recording device. This data includes the user's scores and error information from tests and exercises. General database software is used for database management.

[0468] Next, the server uses machine learning libraries for data analysis to identify the user's incorrect answers. Based on this analysis, it leverages a generative algorithm to create personalized training materials. Common generative techniques can be used as the generative AI model, using the prompt "How do I create training slides based on the user's incorrect topics?".

[0469] Learning materials generated on the server are sent to the terminal. The terminal presents these materials to the user through a graphical user interface, designed to allow for smooth viewing. The terminal also records the user's learning progress and saves that data to local storage for the next learning session.

[0470] Users use the learning materials presented on this device to deepen their understanding of topics they previously answered incorrectly. Based on the personalized content provided by the system, users can learn at their own pace and progress effectively. For example, if a user answers multiple questions related to "data structures" incorrectly, the server generates and provides learning materials related to those topics to help the user achieve better results in their next attempt.

[0471] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0472] Step 1:

[0473] The server receives learning result data from users via the internet. The input is the user's test results, and this data is stored in a recording device. The server prepares the data for subsequent analysis by standardizing the data format and storing it in a database. The output is the learning result data stored in the database.

[0474] Step 2:

[0475] The server analyzes the stored training data. This analysis uses machine learning libraries, primarily to extract patterns and frequencies of incorrect answers. The input is the training data in the database, and the server identifies each user's incorrect answers and lists the topics most likely to cause those errors. The output is a list of incorrect answers for each user.

[0476] Step 3:

[0477] The server uses a generation algorithm to create personalized training materials based on incorrect answers. The prompt "How do I create training slides based on the user's incorrect topics?" is used to guide the generation AI model. The input is a list of identified incorrect questions, and the server compiles personalized training materials in slide format based on the information obtained from the AI ​​model. The output is the personalized training material.

[0478] Step 4:

[0479] The server sends the generated learning materials to the terminal. The input is the learning materials created on the server, which the server pushes to a specific application on the terminal via the internet. The output is the learning materials delivered to the terminal.

[0480] Step 5:

[0481] The terminal presents the user with the individual learning materials it has received. The input is the learning materials sent from the server, and the terminal displays the materials in a user-friendly format. The output is a visually organized slide designed to facilitate user understanding.

[0482] Step 6:

[0483] The device records the user's progress as they learn. The input is the user's browsing activity; the device logs which slides were viewed and for how long. The output is data used to improve the next learning session.

[0484] Step 7:

[0485] Users deepen their understanding of topics they answered incorrectly through the provided learning materials. The input is the learning materials presented on the device; users view the slides and acquire knowledge. The output is improved understanding, aimed at achieving better results in the next test.

[0486] (Application Example 1)

[0487] 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."

[0488] Acquiring product knowledge in retail stores often depends on the experience and background of individual employees, making it difficult to provide uniform knowledge. Furthermore, in today's world where new products frequently appear, efficiently acquiring the latest product information is a crucial challenge. Traditional methods have been inefficient in employee learning because they have struggled to provide knowledge tailored to individual weaknesses.

[0489] 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.

[0490] In this invention, the server includes means for acquiring the user's learning results and automatically generating personalized learning content based on those learning results; means for organizing the personalized learning content by referring to past learning information and external information sources; means for presenting the organized learning content to the user; and a knowledge system that provides knowledge including the features of new products, and means for automatically generating personalized educational materials based on the user's identified weaknesses. This makes it possible for store employees to efficiently acquire the necessary knowledge based on their individual weaknesses and to promote product understanding in commercial stores.

[0491] "Users" refer to individual store employees who receive learning content through the knowledge system with the aim of deepening their understanding of the products.

[0492] "Learning results" refer to the outcomes obtained by users using the knowledge system, and are data that influences subsequent learning content based on whether the answers are correct or incorrect.

[0493] "Personalized learning content" refers to educational materials specifically created for a user, based on their specific weaknesses and past learning history, using artificial intelligence.

[0494] "External information sources" refer to external databases and publicly available resources that knowledge systems refer to when organizing personalized learning content.

[0495] "Identified weaknesses" refer to areas where the user's knowledge is lacking or understanding is incomplete, as revealed during their learning process.

[0496] "Educational materials" refer to information and content created to improve users' knowledge and address specific areas of weakness.

[0497] A "commercial store" refers to a physical facility that provides goods and services to the general public, and is a place where store employees engage in activities to deepen their understanding of the products.

[0498] This invention comprises a server, terminals, and users to realize an employee training system for stores. The server receives the results of tests taken by users and records them in a database. Subsequently, artificial intelligence technology is used to identify the user's weak points and generate personalized learning slides based on those points. This helps users efficiently overcome their shortcomings.

[0499] The server uses MongoDB as its database for processing, and a Python-based machine learning framework is employed for the individual generation of training content. The generated training slides are sent to the device via AWS or Google Cloud Platform.

[0500] The device receives materials sent from the server and displays them visually to the user. The smartphone app, developed using React Native, provides a user-friendly interface and offers features for viewing learning slides and managing progress.

[0501] Users acquire product knowledge by viewing personalized learning slides through a smartphone app. For example, when a new product is introduced, users can refer to individual learning slides containing its features to deepen their understanding. This allows for the rapid provision of accurate and useful information when explaining products to customers.

[0502] Examples of prompts include "Generate learning slides to address misunderstandings about the new fall collection" and "Create slides highlighting the features of this product." By using these prompts, the generative AI model can provide optimal learning content tailored to the user's needs.

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

[0504] Step 1:

[0505] The server receives the results of the tests taken by the user. These results include information on whether each question was answered correctly or incorrectly. The received data is stored in MongoDB, allowing for tracking of individual learning progress.

[0506] Step 2:

[0507] The server uses artificial intelligence technology to identify the user's weak points based on the received test result data. This process utilizes a Python machine learning framework, performing data analysis and calculations to efficiently identify areas with frequent errors. The identified weaknesses are then used as important data for generating subsequent learning slides.

[0508] Step 3:

[0509] The server automatically generates relevant learning content based on identified weaknesses. This generation utilizes a generative AI model to create personalized slides tailored to the user's needs. By analyzing input data and selecting appropriate topics and content, it generates learning slides as output.

[0510] Step 4:

[0511] The server sends the generated learning slides to the device via AWS or Google Cloud Platform, making them accessible to the user. The slides are output in an appropriate format so that they can be visually displayed on the user's device.

[0512] Step 5:

[0513] The device receives learning slides sent from the server and presents them to the user. A user interface built with React Native allows users to visually review the slides as they progress through the learning process. Progress data is recorded based on user interactions, enabling the provision of additional information during subsequent access.

[0514] Step 6:

[0515] Users deepen their knowledge of identified weaknesses by using slides displayed on their devices. This increased knowledge acquisition allows for effective preparation for the next test. A concrete example would be learning about relevant product specifications and sales methods to accurately understand the features of a newly released product.

[0516] 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.

[0517] This invention is a system that provides an individualized learning experience to improve the user's learning efficiency, and in particular incorporates technology that recognizes the user's emotional state and adapts the learning content accordingly. This system mainly consists of a combination of a server, a terminal, a user, and an emotion engine.

[0518] Server Role

[0519] The server receives test results and sentiment data submitted by the user and records them in a database. Based on this data, the server analyzes the user's learning tendencies and emotional changes, and generates personalized learning content and learning plans. In particular, it uses sentiment data obtained from the sentiment engine to understand the user's level of concentration and stress, and adjusts the order and difficulty level of the learning content presented based on this.

[0520] Terminal role

[0521] The device receives personalized learning slides and instructions based on emotion data sent from the server. As the user views the slides, the device activates an emotion engine in real time, analyzing the user's emotions from their facial expressions and voice. The collected emotion information is then sent to the server, and the learning content is continuously optimized.

[0522] The role of the emotional engine

[0523] The emotion engine is embedded in the user's device and recognizes the user's emotions in real time. Specifically, it analyzes the user's facial expressions and voice characteristics through the camera and microphone to identify emotions such as joy, sadness, stress, and concentration levels. This data is sent to a server as key information to improve learning efficiency and is used to dynamically adjust the learning content.

[0524] User roles

[0525] Users view learning slides delivered by the system via their devices and receive a learning experience tailored to their emotional state, as recognized by the emotion engine. If a user experiences stress or a decrease in concentration, the system immediately adjusts the learning content and pace to provide an optimal learning environment.

[0526] For example, if the emotion engine determines that a user's concentration is waning, the server will temporarily reduce the amount of learning content presented and suggest short quizzes or motivational content to refresh the user. In this way, support is provided to help users continue learning efficiently.

[0527] The following describes the processing flow.

[0528] Step 1:

[0529] The user logs in via their device when starting a learning session. The device sends the user's identification information to the server and prepares to start the learning session.

[0530] Step 2:

[0531] The server retrieves the user's past learning results and history data from the database. Based on this data, the server identifies the relevant learning content and generates a learning plan for the user.

[0532] Step 3:

[0533] The device begins displaying the learning content provided by the server. Simultaneously, the emotion engine starts up and begins collecting emotion data through the user's facial expressions and voice.

[0534] Step 4:

[0535] The emotion engine analyzes the user's emotional state in real time and sends that data to the server. Specifically, it determines concentration levels, stress levels, and other factors based on the user's eye movements and tone of voice.

[0536] Step 5:

[0537] The server evaluates the user's emotional state based on emotional data and dynamically adjusts the learning content accordingly. If the emotional state is detected as unsuitable for learning, it presents simpler content or break content.

[0538] Step 6:

[0539] The device presents the user with the latest learning content provided by the server. Based on the user's emotional state, the device appropriately adjusts the learning pace and the difficulty level of the content.

[0540] Step 7:

[0541] The user continuously views the adjusted learning content. Because the content is updated in real time based on the user's emotional state, the user can learn in the best possible environment.

[0542] Step 8:

[0543] When a learning session ends, the device sends the final learning results to the server. The server saves these results to a database and prepares for subsequent learning sessions.

[0544] Through this processing flow, the system can provide users with a highly personalized learning experience using emotion recognition.

[0545] (Example 2)

[0546] 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."

[0547] A problem exists where learners' learning efficiency suffers because they are not provided with learning content appropriate to their individual emotional states. Furthermore, current learning systems have difficulty reflecting changes in users' emotions in real time and providing personalized learning experiences. In addition, there is a lack of feedback and break suggestions based on users' emotions, making it difficult to optimize the learning pace.

[0548] 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.

[0549] In this invention, the server includes means for recognizing the user's emotional state and dynamically adjusting the display order and difficulty level of learning content based on that emotional state; means for collecting the emotional data and learning progress information and transmitting it to a communication device; and means for analyzing the emotional data and learning progress information collected by the communication device and generating an individualized learning plan. This makes it possible to optimize the learning content and learning pace to suit the user's emotions.

[0550] "Emotional state" refers to a specific emotional state exhibited by a learner, including the type and intensity of emotions such as joy, sadness, stress, and concentration.

[0551] "Dynamic adjustment" means instantly changing the order and difficulty level of learning content in response to real-time feedback from users.

[0552] "Communication device" refers to hardware or a platform that communicates with a user's terminal to support data collection and transmission.

[0553] A "learning plan" refers to a plan that includes detailed learning content and schedules tailored to the user's learning needs and emotional state.

[0554] A "generative AI model" refers to an algorithm that generates and analyzes data based on artificial intelligence technology to provide users with optimal learning materials and feedback.

[0555] The system of this invention is composed of a server, terminal, user, and emotion engine at its core to realize emotion recognition and personalized learning. Details of each component are as follows.

[0556] Server Configuration and Roles

[0557] The server manages user sentiment data and learning progress information in conjunction with the database. Using this data, the server leverages generative AI models to analyze the user's learning state. It then generates personalized learning plans and sends them to the user's device. To efficiently process large amounts of data, the server needs a high-performance processor and ample memory.

[0558] Device configuration and role

[0559] The terminal functions as an interface connecting the user and the server. It is primarily equipped with a camera and microphone, which are used by an emotion engine to analyze the user's facial expressions and voice characteristics. The resulting emotion data is transmitted to the server in real time. The terminal includes a display for showing learning slides and an input device for detecting user actions.

[0560] User roles

[0561] Users view and utilize learning slides. During learning, emotional information collected by the camera and microphone is analyzed in the background and sent to the server. If the user experiences stress or their concentration decreases, the learning content and pace are automatically adjusted based on instructions sent from the server.

[0562] The structure and role of the emotional engine

[0563] The emotion engine is software that analyzes a user's emotions in real time. It implements machine learning algorithms and recognizes emotions such as joy, sadness, stress, and concentration levels based on data obtained from the camera and microphone. The recognized emotion data is then used to generate learning plans on the server side.

[0564] Specific example

[0565] For example, if the emotion engine determines that a user's concentration is waning, the server inserts suggestions for refreshing quizzes or light exercises into the learning plan. In this process, the generative AI model receives prompts such as "Please provide content that will help the user refresh" and suggests appropriate content. In this way, it becomes possible to dynamically optimize the user's learning experience according to their individual state.

[0566] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0567] Step 1:

[0568] The user starts a learning session and interacts with the device to view learning slides. The user's facial expressions and voice are collected as input via the camera and microphone. This data is sent to the emotion engine on the device.

[0569] Step 2:

[0570] The device analyzes facial and voice data collected using an emotion engine. The emotion engine utilizes machine learning algorithms to identify the user's emotional state (e.g., concentration level, stress) based on the input data. The analysis results are generated as output and sent to the server.

[0571] Step 3:

[0572] The server receives emotional state data sent from the terminal and records it in a database. Using the emotional state as input and past training data, the server utilizes a generative AI model to generate an optimal learning plan for the user. As output, personalized learning slides and supplementary materials are generated.

[0573] Step 4:

[0574] The server sends the generated learning plan and slides to the terminal. The terminal then uses this to prepare the learning content to display to the user. The input is the learning slides from the server, and the output is the content to be displayed to the user.

[0575] Step 5:

[0576] The user continues to view the displayed learning slides and provides feedback via the device as needed. The device collects facial expressions and audio again in real time, and the process returns to step 2 to monitor changes in emotional state. This cycle optimizes the learning content for continuous improvement.

[0577] Step 6:

[0578] The server, based on the received sentiment data and additional learning outcomes, sends a prompt message to the AI ​​model, which then generates additional learning materials or rest content as needed. This process may include using the prompt message, "Your concentration is low. Please generate refreshment content."

[0579] Step 7:

[0580] The optimized learning content and supplementary materials are sent back to the device and presented to the user. This creates an environment that supports the user in continuing to learn efficiently.

[0581] (Application Example 2)

[0582] 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."

[0583] Conventional learning support systems provide individualization based on the user's learning progress, but they cannot dynamically adjust learning content while considering the user's emotional state, and therefore fail to adequately improve learning efficiency and motivation. For this reason, there is a need for technology that can recognize the user's emotional state in real time and appropriately adapt learning content.

[0584] 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.

[0585] In this invention, the server includes means for acquiring the user's learning results and emotional state, and automatically generating personalized learning information based on said learning results and emotional state; means for organizing said personalized learning information by referring to past learning data and external information sources; and means for recognizing the user's emotions in real time and dynamically adjusting the learning information according to that state. This makes it possible to improve the user's learning efficiency and provide an effective learning experience while reducing the burden on the user.

[0586] A "user" is a person who uses the system and is the recipient of personalized learning content.

[0587] "Learning results" refer to data that shows the knowledge and skills acquired by the user during the learning process, and serve as the basis for the system to generate personalized learning information.

[0588] "Emotional state" refers to the user's current psychological and emotional condition, and is important information for the system to dynamically adjust the learning content.

[0589] "Personalized learning information" refers to information that indicates learning content and pace optimized for a specific user, based on the user's learning results and emotional state.

[0590] "Past learning data" refers to records of learning that users have done in the past, and is referenced when organizing the current learning content.

[0591] "External information sources" refer to information outside the system that is referenced when organizing learning content, and include encyclopedias and specialized databases.

[0592] "Recognizing user emotions in real time" means analyzing the user's emotional state without any time delay and understanding their psychological state while they are learning.

[0593] "Dynamic adjustment" means appropriately changing learning content and methods in response to the passage of time and changes in circumstances, and is a process for realizing education that is tailored to the user's situation.

[0594] A "generative AI model" is an artificial intelligence model that uses machine learning techniques to generate new data or information.

[0595] A "prompt statement" is an instruction given to an AI model to guide it to produce an appropriate response or output, and it provides relevant information for the user in learning support.

[0596] In this invention, the server acquires the user's learning results and emotional state, and automatically generates personalized learning information. The hardware used is a general cloud server or database server, and machine learning libraries such as TensorFlow and PyTorch are utilized for emotion recognition. This allows the server to generate organized learning information by referencing past learning data and external information sources. The server also uses a generative AI model to create prompt statements, providing a learning experience tailored to the user.

[0597] The terminal acts as the interface with the user, using a camera and microphone to recognize the user's emotional state in real time. This uses OpenCV for facial recognition and librosa for speech analysis. The terminal sends this data to a server, and the server presents personalized learning information to the user. The learning content and pace are dynamically adjusted based on the user's learning progress and real-time emotional feedback.

[0598] Users can utilize personalized learning information provided via devices such as smartphones to facilitate efficient learning. For example, elementary school students working on a summer vacation project can use this system to efficiently understand experimental procedures and necessary background knowledge, enabling them to smoothly complete their project.

[0599] An example of a prompt statement in this invention is: "The user's facial expression is {facial expression data}, and their voice is {voice data}. Based on this data, evaluate the user's emotions and recommend appropriate learning content." Such specific prompts enable the generative AI model to provide learning information tailored to the user.

[0600] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0601] Step 1:

[0602] The device uses the smartphone's camera and microphone to acquire the user's facial expressions and audio data in real time. The input to the device is video and audio data, which is used to analyze facial and audio features using OpenCV and librosa. The output is analyzed emotional state data. Through this process, the user's emotions are determined, such as "concentrating" or "feeling stressed."

[0603] Step 2:

[0604] The device sends the emotional state data acquired in Step 1 to the server. The server receives this emotional state data and analyzes it against its past learning database. It receives emotional state data and past learning history data as input and uses a generative AI model to create prompt sentences based on this. As output, learning information optimized for the user is generated.

[0605] Step 3:

[0606] The server sends the learning information generated in step 2 to the terminal. The terminal receives this learning information and presents it to the user. Specifically, it displays personalized learning content on the learning application screen based on the user's emotional state and learning history. The user can then use this content to smoothly progress through their learning.

[0607] Step 4:

[0608] The user uses the presented learning information to tackle problems. By answering specific questions or digesting learning content, they gain further learning results and new emotional states. This serves as input when returning to step 1 of the next cycle.

[0609] Through this entire process, users can continuously receive learning support adapted to their emotional state, maximizing their learning effectiveness.

[0610] 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.

[0611] 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.

[0612] 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.

[0613] [Fourth Embodiment]

[0614] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0615] 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.

[0616] 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).

[0617] 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.

[0618] 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.

[0619] 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).

[0620] 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.

[0621] 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.

[0622] 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.

[0623] 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.

[0624] 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.

[0625] 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.

[0626] 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".

[0627] This invention comprises a learning-based training system that utilizes artificial intelligence to provide a personalized learning experience in order to enhance the user's learning efficiency. The system primarily consists of a server, terminals, and users.

[0628] Server Role

[0629] The server receives test results submitted by users and records the data in a database. The server then analyzes the collected test results for each user. Using artificial intelligence technology, it identifies the user's weaknesses by pinpointing incorrect answers and related learning topics. Based on this, it automatically generates personalized learning slides, referencing past learning content and external information sources. These generated slides are structured to meet each user's learning needs.

[0630] Terminal role

[0631] The device receives personalized learning slides sent from the server and presents them to the user. The device is designed to allow users to comfortably view the slides through a graphical user interface. Furthermore, as the user progresses through the learning process, the device records their progress and saves the data for use in the next learning step.

[0632] User roles

[0633] Users can use this system to improve their learning efficiency. They can view learning slides displayed on their device and use them to deepen their understanding of topics they answered incorrectly. The personalized content provided by the system allows users to learn at their own pace.

[0634] For example, if a user makes multiple incorrect answers on the topic of "data structures" in a particular test, the server generates learning slides containing content related to that topic and sends them to the user's device. Through these slides, the user can deepen their understanding of the questions and aim for better results in their next attempt. In this way, the present invention efficiently provides personalized learning support and creates an environment in which users can learn more effectively.

[0635] The following describes the processing flow.

[0636] Step 1:

[0637] The server receives the user's test results. After the test is completed, the user's device sends correct / incorrect answer data for each question to the server. This data is structured as question number and result (correct or incorrect).

[0638] Step 2:

[0639] The server records the received test results in a database. The results are stored along with each user's identification information, preparing them for subsequent analysis.

[0640] Step 3:

[0641] The server executes a process to analyze the recorded test results. Using artificial intelligence, it identifies incorrect answers and related topics, extracting the user's weaknesses. For example, if a group of questions with many incorrect answers are concentrated on a particular topic, that topic is recognized as the user's weakness.

[0642] Step 4:

[0643] The server generates personalized learning slides based on identified weaknesses. It automatically generates slides by referencing past learning databases and reliable information sources on the internet, and combining relevant content.

[0644] Step 5:

[0645] The server sends the generated learning slides to the user's device. It links them with the user's identification information to quickly deliver personalized content.

[0646] Step 6:

[0647] The device opens the received learning slides and makes them available for viewing to the user. The device provides a graphical user interface to help the user smoothly progress through the slide learning process.

[0648] Step 7:

[0649] Users view learning slides displayed on their device and begin learning based on personalized content. Users can learn at their own pace and record their progress on their device.

[0650] This processing flow allows users to efficiently address their weaknesses and maximize their learning effectiveness.

[0651] (Example 1)

[0652] 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".

[0653] In conventional learning systems, it was difficult to quickly and accurately provide personalized educational content based on the learning results submitted by users. This resulted in the challenge of maximizing the learning efficiency of each user. Furthermore, there was insufficient mechanism for identifying users' weaknesses and providing appropriate learning materials accordingly.

[0654] 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.

[0655] In this invention, the server includes means for registering learning results obtained from the user in a recording device, means for analyzing the learning results to identify the user's incorrect answers, and means for creating personalized educational materials based on the incorrect answers using a generation algorithm. This enables the rapid generation and provision of optimal educational content tailored to each individual user.

[0656] "User" refers to an individual who uses this system to learn through educational materials.

[0657] "Learning results" refers to the collective performance and answer information from tests and exercises taken by users.

[0658] A "recording device" is a mechanism for storing and managing data, and may include a database.

[0659] "Analysis" refers to data processing procedures that involve processing information based on data to obtain useful insights.

[0660] An "incorrect answer" refers to an item that a user answered incorrectly during the learning process, and is identified to provide further learning opportunities.

[0661] A "generative algorithm" encompasses a set of techniques used to create a new output based on input data.

[0662] "Educational materials" refer to content such as slides and documents provided to assist users in their learning.

[0663] "Personalization" means that adjustments are made to suit the different requirements and needs of each user.

[0664] This invention specifically demonstrates a method for providing a personalized learning experience by utilizing artificial intelligence in the learning process. This system mainly consists of a server, terminals, and users.

[0665] The server receives learning result data transmitted from users via the internet and stores this data using a recording device. This data includes the user's scores and error information from tests and exercises. General database software is used for database management.

[0666] Next, the server uses machine learning libraries for data analysis to identify the user's incorrect answers. Based on this analysis, it leverages a generative algorithm to create personalized training materials. Common generative techniques can be used as the generative AI model, using the prompt "How do I create training slides based on the user's incorrect topics?".

[0667] Learning materials generated on the server are sent to the terminal. The terminal presents these materials to the user through a graphical user interface, designed to allow for smooth viewing. The terminal also records the user's learning progress and saves that data to local storage for the next learning session.

[0668] Users use the learning materials presented on this device to deepen their understanding of topics they previously answered incorrectly. Based on the personalized content provided by the system, users can learn at their own pace and progress effectively. For example, if a user answers multiple questions related to "data structures" incorrectly, the server generates and provides learning materials related to those topics to help the user achieve better results in their next attempt.

[0669] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0670] Step 1:

[0671] The server receives learning result data from users via the internet. The input is the user's test results, and this data is stored in a recording device. The server prepares the data for subsequent analysis by standardizing the data format and storing it in a database. The output is the learning result data stored in the database.

[0672] Step 2:

[0673] The server analyzes the stored training data. This analysis uses machine learning libraries, primarily to extract patterns and frequencies of incorrect answers. The input is the training data in the database, and the server identifies each user's incorrect answers and lists the topics most likely to cause those errors. The output is a list of incorrect answers for each user.

[0674] Step 3:

[0675] The server uses a generation algorithm to create personalized training materials based on incorrect answers. The prompt "How do I create training slides based on the user's incorrect topics?" is used to guide the generation AI model. The input is a list of identified incorrect questions, and the server compiles personalized training materials in slide format based on the information obtained from the AI ​​model. The output is the personalized training material.

[0676] Step 4:

[0677] The server sends the generated learning materials to the terminal. The input is the learning materials created on the server, which the server pushes to a specific application on the terminal via the internet. The output is the learning materials delivered to the terminal.

[0678] Step 5:

[0679] The terminal presents the user with the individual learning materials it has received. The input is the learning materials sent from the server, and the terminal displays the materials in a user-friendly format. The output is a visually organized slide designed to facilitate user understanding.

[0680] Step 6:

[0681] The device records the user's progress as they learn. The input is the user's browsing activity; the device logs which slides were viewed and for how long. The output is data used to improve the next learning session.

[0682] Step 7:

[0683] Users deepen their understanding of topics they answered incorrectly through the provided learning materials. The input is the learning materials presented on the device; users view the slides and acquire knowledge. The output is improved understanding, aimed at achieving better results in the next test.

[0684] (Application Example 1)

[0685] 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".

[0686] Acquiring product knowledge in retail stores often depends on the experience and background of individual employees, making it difficult to provide uniform knowledge. Furthermore, in today's world where new products frequently appear, efficiently acquiring the latest product information is a crucial challenge. Traditional methods have been inefficient in employee learning because they have struggled to provide knowledge tailored to individual weaknesses.

[0687] 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.

[0688] In this invention, the server includes means for acquiring the user's learning results and automatically generating personalized learning content based on those learning results; means for organizing the personalized learning content by referring to past learning information and external information sources; means for presenting the organized learning content to the user; and a knowledge system that provides knowledge including the features of new products, and means for automatically generating personalized educational materials based on the user's identified weaknesses. This makes it possible for store employees to efficiently acquire the necessary knowledge based on their individual weaknesses and to promote product understanding in commercial stores.

[0689] "Users" refer to individual store employees who receive learning content through the knowledge system with the aim of deepening their understanding of the products.

[0690] "Learning results" refer to the outcomes obtained by users using the knowledge system, and are data that influences subsequent learning content based on whether the answers are correct or incorrect.

[0691] "Personalized learning content" refers to educational materials specifically created for a user, based on their specific weaknesses and past learning history, using artificial intelligence.

[0692] "External information sources" refer to external databases and publicly available resources that knowledge systems refer to when organizing personalized learning content.

[0693] "Identified weaknesses" refer to areas where the user's knowledge is lacking or understanding is incomplete, as revealed during their learning process.

[0694] "Educational materials" refer to information and content created to improve users' knowledge and address specific areas of weakness.

[0695] A "commercial store" refers to a physical facility that provides goods and services to the general public, and is a place where store employees engage in activities to deepen their understanding of the products.

[0696] This invention comprises a server, terminals, and users to realize an employee training system for stores. The server receives the results of tests taken by users and records them in a database. Subsequently, artificial intelligence technology is used to identify the user's weak points and generate personalized learning slides based on those points. This helps users efficiently overcome their shortcomings.

[0697] The server uses MongoDB as its database for processing, and a Python-based machine learning framework is employed for the individual generation of training content. The generated training slides are sent to the device via AWS or Google Cloud Platform.

[0698] The device receives materials sent from the server and displays them visually to the user. The smartphone app, developed using React Native, provides a user-friendly interface and offers features for viewing learning slides and managing progress.

[0699] Users acquire product knowledge by viewing personalized learning slides through a smartphone app. For example, when a new product is introduced, users can refer to individual learning slides containing its features to deepen their understanding. This allows for the rapid provision of accurate and useful information when explaining products to customers.

[0700] Examples of prompts include "Generate learning slides to address misunderstandings about the new fall collection" and "Create slides highlighting the features of this product." By using these prompts, the generative AI model can provide optimal learning content tailored to the user's needs.

[0701] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0702] Step 1:

[0703] The server receives the results of the tests taken by the user. These results include information on whether each question was answered correctly or incorrectly. The received data is stored in MongoDB, allowing for tracking of individual learning progress.

[0704] Step 2:

[0705] The server uses artificial intelligence technology to identify the user's weak points based on the received test result data. This process utilizes a Python machine learning framework, performing data analysis and calculations to efficiently identify areas with frequent errors. The identified weaknesses are then used as important data for generating subsequent learning slides.

[0706] Step 3:

[0707] The server automatically generates relevant learning content based on identified weaknesses. This generation utilizes a generative AI model to create personalized slides tailored to the user's needs. By analyzing input data and selecting appropriate topics and content, it generates learning slides as output.

[0708] Step 4:

[0709] The server sends the generated learning slides to the device via AWS or Google Cloud Platform, making them accessible to the user. The slides are output in an appropriate format so that they can be visually displayed on the user's device.

[0710] Step 5:

[0711] The device receives learning slides sent from the server and presents them to the user. A user interface built with React Native allows users to visually review the slides as they progress through the learning process. Progress data is recorded based on user interactions, enabling the provision of additional information during subsequent access.

[0712] Step 6:

[0713] Users deepen their knowledge of identified weaknesses by using slides displayed on their devices. This increased knowledge acquisition allows for effective preparation for the next test. A concrete example would be learning about relevant product specifications and sales methods to accurately understand the features of a newly released product.

[0714] 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.

[0715] This invention is a system that provides an individualized learning experience to improve the user's learning efficiency, and in particular incorporates technology that recognizes the user's emotional state and adapts the learning content accordingly. This system mainly consists of a combination of a server, a terminal, a user, and an emotion engine.

[0716] Server Role

[0717] The server receives test results and sentiment data submitted by the user and records them in a database. Based on this data, the server analyzes the user's learning tendencies and emotional changes, and generates personalized learning content and learning plans. In particular, it uses sentiment data obtained from the sentiment engine to understand the user's level of concentration and stress, and adjusts the order and difficulty level of the learning content presented based on this.

[0718] Terminal role

[0719] The device receives personalized learning slides and instructions based on emotion data sent from the server. As the user views the slides, the device activates an emotion engine in real time, analyzing the user's emotions from their facial expressions and voice. The collected emotion information is then sent to the server, and the learning content is continuously optimized.

[0720] The role of the emotional engine

[0721] The emotion engine is embedded in the user's device and recognizes the user's emotions in real time. Specifically, it analyzes the user's facial expressions and voice characteristics through the camera and microphone to identify emotions such as joy, sadness, stress, and concentration levels. This data is sent to a server as key information to improve learning efficiency and is used to dynamically adjust the learning content.

[0722] User roles

[0723] Users view learning slides delivered by the system via their devices and receive a learning experience tailored to their emotional state, as recognized by the emotion engine. If a user experiences stress or a decrease in concentration, the system immediately adjusts the learning content and pace to provide an optimal learning environment.

[0724] For example, if the emotion engine determines that a user's concentration is waning, the server will temporarily reduce the amount of learning content presented and suggest short quizzes or motivational content to refresh the user. In this way, support is provided to help users continue learning efficiently.

[0725] The following describes the processing flow.

[0726] Step 1:

[0727] The user logs in via their device when starting a learning session. The device sends the user's identification information to the server and prepares to start the learning session.

[0728] Step 2:

[0729] The server retrieves the user's past learning results and history data from the database. Based on this data, the server identifies the relevant learning content and generates a learning plan for the user.

[0730] Step 3:

[0731] The device begins displaying the learning content provided by the server. Simultaneously, the emotion engine starts up and begins collecting emotion data through the user's facial expressions and voice.

[0732] Step 4:

[0733] The emotion engine analyzes the user's emotional state in real time and sends that data to the server. Specifically, it determines concentration levels, stress levels, and other factors based on the user's eye movements and tone of voice.

[0734] Step 5:

[0735] The server evaluates the user's emotional state based on emotional data and dynamically adjusts the learning content accordingly. If the emotional state is detected as unsuitable for learning, it presents simpler content or break content.

[0736] Step 6:

[0737] The device presents the user with the latest learning content provided by the server. Based on the user's emotional state, the device appropriately adjusts the learning pace and the difficulty level of the content.

[0738] Step 7:

[0739] The user continuously views the adjusted learning content. Because the content is updated in real time based on the user's emotional state, the user can learn in the best possible environment.

[0740] Step 8:

[0741] When a learning session ends, the device sends the final learning results to the server. The server saves these results to a database and prepares for subsequent learning sessions.

[0742] Through this processing flow, the system can provide users with a highly personalized learning experience using emotion recognition.

[0743] (Example 2)

[0744] 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".

[0745] A problem exists where learners' learning efficiency suffers because they are not provided with learning content appropriate to their individual emotional states. Furthermore, current learning systems have difficulty reflecting changes in users' emotions in real time and providing personalized learning experiences. In addition, there is a lack of feedback and break suggestions based on users' emotions, making it difficult to optimize the learning pace.

[0746] 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.

[0747] In this invention, the server includes means for recognizing the user's emotional state and dynamically adjusting the display order and difficulty level of learning content based on that emotional state; means for collecting the emotional data and learning progress information and transmitting it to a communication device; and means for analyzing the emotional data and learning progress information collected by the communication device and generating an individualized learning plan. This makes it possible to optimize the learning content and learning pace to suit the user's emotions.

[0748] "Emotional state" refers to a specific emotional state exhibited by a learner, including the type and intensity of emotions such as joy, sadness, stress, and concentration.

[0749] "Dynamic adjustment" means instantly changing the order and difficulty level of learning content in response to real-time feedback from users.

[0750] "Communication device" refers to hardware or a platform that communicates with a user's terminal to support data collection and transmission.

[0751] A "learning plan" refers to a plan that includes detailed learning content and schedules tailored to the user's learning needs and emotional state.

[0752] A "generative AI model" refers to an algorithm that generates and analyzes data based on artificial intelligence technology to provide users with optimal learning materials and feedback.

[0753] The system of this invention is composed of a server, terminal, user, and emotion engine at its core to realize emotion recognition and personalized learning. Details of each component are as follows.

[0754] Server Configuration and Roles

[0755] The server manages user sentiment data and learning progress information in conjunction with the database. Using this data, the server leverages generative AI models to analyze the user's learning state. It then generates personalized learning plans and sends them to the user's device. To efficiently process large amounts of data, the server needs a high-performance processor and ample memory.

[0756] Device configuration and role

[0757] The terminal functions as an interface connecting the user and the server. It is primarily equipped with a camera and microphone, which are used by an emotion engine to analyze the user's facial expressions and voice characteristics. The resulting emotion data is transmitted to the server in real time. The terminal includes a display for showing learning slides and an input device for detecting user actions.

[0758] User roles

[0759] Users view and utilize learning slides. During learning, emotional information collected by the camera and microphone is analyzed in the background and sent to the server. If the user experiences stress or their concentration decreases, the learning content and pace are automatically adjusted based on instructions sent from the server.

[0760] The structure and role of the emotional engine

[0761] The emotion engine is software that analyzes a user's emotions in real time. It implements machine learning algorithms and recognizes emotions such as joy, sadness, stress, and concentration levels based on data obtained from the camera and microphone. The recognized emotion data is then used to generate learning plans on the server side.

[0762] Specific example

[0763] For example, if the emotion engine determines that a user's concentration is waning, the server inserts suggestions for refreshing quizzes or light exercises into the learning plan. In this process, the generative AI model receives prompts such as "Please provide content that will help the user refresh" and suggests appropriate content. In this way, it becomes possible to dynamically optimize the user's learning experience according to their individual state.

[0764] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0765] Step 1:

[0766] The user starts a learning session and interacts with the device to view learning slides. The user's facial expressions and voice are collected as input via the camera and microphone. This data is sent to the emotion engine on the device.

[0767] Step 2:

[0768] The device analyzes facial and voice data collected using an emotion engine. The emotion engine utilizes machine learning algorithms to identify the user's emotional state (e.g., concentration level, stress) based on the input data. The analysis results are generated as output and sent to the server.

[0769] Step 3:

[0770] The server receives emotional state data sent from the terminal and records it in a database. Using the emotional state as input and past training data, the server utilizes a generative AI model to generate an optimal learning plan for the user. As output, personalized learning slides and supplementary materials are generated.

[0771] Step 4:

[0772] The server sends the generated learning plan and slides to the terminal. The terminal then uses this to prepare the learning content to display to the user. The input is the learning slides from the server, and the output is the content to be displayed to the user.

[0773] Step 5:

[0774] The user continues to view the displayed learning slides and provides feedback via the device as needed. The device collects facial expressions and audio again in real time, and the process returns to step 2 to monitor changes in emotional state. This cycle optimizes the learning content for continuous improvement.

[0775] Step 6:

[0776] The server, based on the received sentiment data and additional learning outcomes, sends a prompt message to the AI ​​model, which then generates additional learning materials or rest content as needed. This process may include using the prompt message, "Your concentration is low. Please generate refreshment content."

[0777] Step 7:

[0778] The optimized learning content and supplementary materials are sent back to the device and presented to the user. This creates an environment that supports the user in continuing to learn efficiently.

[0779] (Application Example 2)

[0780] 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".

[0781] Conventional learning support systems provide individualization based on the user's learning progress, but they cannot dynamically adjust learning content while considering the user's emotional state, and therefore fail to adequately improve learning efficiency and motivation. For this reason, there is a need for technology that can recognize the user's emotional state in real time and appropriately adapt learning content.

[0782] 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.

[0783] In this invention, the server includes means for acquiring the user's learning results and emotional state, and automatically generating personalized learning information based on said learning results and emotional state; means for organizing said personalized learning information by referring to past learning data and external information sources; and means for recognizing the user's emotions in real time and dynamically adjusting the learning information according to that state. This makes it possible to improve the user's learning efficiency and provide an effective learning experience while reducing the burden on the user.

[0784] A "user" is a person who uses the system and is the recipient of personalized learning content.

[0785] "Learning results" refer to data that shows the knowledge and skills acquired by the user during the learning process, and serve as the basis for the system to generate personalized learning information.

[0786] "Emotional state" refers to the user's current psychological and emotional condition, and is important information for the system to dynamically adjust the learning content.

[0787] "Personalized learning information" refers to information that indicates learning content and pace optimized for a specific user, based on the user's learning results and emotional state.

[0788] "Past learning data" refers to records of learning that users have done in the past, and is referenced when organizing the current learning content.

[0789] "External information sources" refer to information outside the system that is referenced when organizing learning content, and include encyclopedias and specialized databases.

[0790] "Recognizing user emotions in real time" means analyzing the user's emotional state without any time delay and understanding their psychological state while they are learning.

[0791] "Dynamic adjustment" means appropriately changing learning content and methods in response to the passage of time and changes in circumstances, and is a process for realizing education that is tailored to the user's situation.

[0792] A "generative AI model" is an artificial intelligence model that uses machine learning techniques to generate new data or information.

[0793] A "prompt statement" is an instruction given to an AI model to guide it to produce an appropriate response or output, and it provides relevant information for the user in learning support.

[0794] In this invention, the server acquires the user's learning results and emotional state, and automatically generates personalized learning information. The hardware used is a general cloud server or database server, and machine learning libraries such as TensorFlow and PyTorch are utilized for emotion recognition. This allows the server to generate organized learning information by referencing past learning data and external information sources. The server also uses a generative AI model to create prompt statements, providing a learning experience tailored to the user.

[0795] The terminal acts as the interface with the user, using a camera and microphone to recognize the user's emotional state in real time. This uses OpenCV for facial recognition and librosa for speech analysis. The terminal sends this data to a server, and the server presents personalized learning information to the user. The learning content and pace are dynamically adjusted based on the user's learning progress and real-time emotional feedback.

[0796] Users can utilize personalized learning information provided via devices such as smartphones to facilitate efficient learning. For example, elementary school students working on a summer vacation project can use this system to efficiently understand experimental procedures and necessary background knowledge, enabling them to smoothly complete their project.

[0797] An example of a prompt statement in this invention is: "The user's facial expression is {facial expression data}, and their voice is {voice data}. Based on this data, evaluate the user's emotions and recommend appropriate learning content." Such specific prompts enable the generative AI model to provide learning information tailored to the user.

[0798] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0799] Step 1:

[0800] The device uses the smartphone's camera and microphone to acquire the user's facial expressions and audio data in real time. The input to the device is video and audio data, which is used to analyze facial and audio features using OpenCV and librosa. The output is analyzed emotional state data. Through this process, the user's emotions are determined, such as "concentrating" or "feeling stressed."

[0801] Step 2:

[0802] The device sends the emotional state data acquired in Step 1 to the server. The server receives this emotional state data and analyzes it against its past learning database. It receives emotional state data and past learning history data as input and uses a generative AI model to create prompt sentences based on this. As output, learning information optimized for the user is generated.

[0803] Step 3:

[0804] The server sends the learning information generated in step 2 to the terminal. The terminal receives this learning information and presents it to the user. Specifically, it displays personalized learning content on the learning application screen based on the user's emotional state and learning history. The user can then use this content to smoothly progress through their learning.

[0805] Step 4:

[0806] The user uses the presented learning information to tackle problems. By answering specific questions or digesting learning content, they gain further learning results and new emotional states. This serves as input when returning to step 1 of the next cycle.

[0807] Through this entire process, users can continuously receive learning support adapted to their emotional state, maximizing their learning effectiveness.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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."

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] The following is further disclosed regarding the embodiments described above.

[0830] (Claim 1)

[0831] A means for acquiring the user's learning results and automatically generating personalized learning content based on those learning results,

[0832] Means for organizing the individualized learning content by referring to past learning information and external information sources,

[0833] A means of presenting the compiled learning content to the user,

[0834] A system that includes this.

[0835] (Claim 2)

[0836] The system according to claim 1, further comprising means for analyzing the user's incorrectly answered learning items and extracting information related to the incorrectly answered items.

[0837] (Claim 3)

[0838] The system according to claim 1, further comprising means for using artificial intelligence to identify areas of weakness based on the user's learning results and for generating supplementary learning materials targeting the identified areas of weakness.

[0839] "Example 1"

[0840] (Claim 1)

[0841] A means for registering learning results obtained from users into a recording device,

[0842] A means for analyzing the learning results to identify the user's incorrect answers,

[0843] A means for creating personalized educational materials based on the incorrectly answered problem using a generation algorithm,

[0844] A means of compiling educational materials by referring to past educational data and external information,

[0845] A means for outputting the compiled educational materials to the user,

[0846] A system that includes this.

[0847] (Claim 2)

[0848] The system according to claim 1, further comprising means for analyzing the user's incorrect answers using information processing technology and extracting supplementary information related to the incorrect answers.

[0849] (Claim 3)

[0850] The system according to claim 1, further comprising means for using an intelligent system to identify problem areas based on the user's learning results and for generating support materials for the identified problem areas.

[0851] "Application Example 1"

[0852] (Claim 1)

[0853] A means for acquiring the user's learning results and automatically generating personalized learning content based on those learning results,

[0854] Means for organizing the individualized learning content by referring to past learning information and external information sources,

[0855] A means of presenting the compiled learning content to the user,

[0856] A knowledge system that provides knowledge including the features of a new product, and means for automatically generating personalized educational materials based on the user's identified weaknesses,

[0857] A system that includes this.

[0858] (Claim 2)

[0859] The system according to claim 1, further comprising means for analyzing the learning items that the user answered incorrectly, extracting information related to the incorrect items, and presenting knowledge levels to enable the user to expand their knowledge.

[0860] (Claim 3)

[0861] The system according to claim 1, further comprising means for using artificial intelligence to identify areas of weakness based on the user's learning results, generating supplementary learning materials targeting the identified areas of weakness, and providing educational support to promote product understanding in commercial stores.

[0862] "Example 2 of combining an emotion engine"

[0863] (Claim 1)

[0864] A means for recognizing the user's emotional state and dynamically adjusting the display order and difficulty level of learning content based on that emotional state,

[0865] Means for collecting the emotion data and learning progress information and transmitting it to a communication device,

[0866] A means for analyzing emotional data and learning progress information collected by the communication device and generating an individualized learning plan,

[0867] A means of presenting the generated learning plan to the user and continuously optimizing it,

[0868] A system that includes this.

[0869] (Claim 2)

[0870] The system according to claim 1, which analyzes data based on the user's emotions and provides appropriate feedback and breaks according to the analysis results.

[0871] (Claim 3)

[0872] The system according to claim 1, which uses a generative AI model to generate supplementary learning materials for improving learning efficiency based on the user's emotions and learning results.

[0873] "Application example 2 when combining with an emotional engine"

[0874] (Claim 1)

[0875] A means for acquiring the user's learning results and emotional state, and for automatically generating personalized learning information based on said learning results and emotional state,

[0876] A means for compiling the individualized learning information by referring to past learning data and external information sources,

[0877] A means of recognizing the user's emotions in real time and dynamically adjusting the learning information according to that state,

[0878] Means for presenting the compiled learning information to the user through visual and auditory means,

[0879] A system that includes this.

[0880] (Claim 2)

[0881] The system according to claim 1, further comprising means for analyzing a user's incorrectly answered learning tasks, extracting information related to the incorrectly answered tasks, and generating supplementary learning materials corresponding to the user's emotional state.

[0882] (Claim 3)

[0883] The system according to claim 1, further comprising means for using artificial intelligence to identify weak areas based on the user's learning results and emotional state, generating supplementary learning content targeting the identified weak areas, and constructing appropriate prompt sentences using a generating AI model. [Explanation of symbols]

[0884] 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 for acquiring the user's learning results and automatically generating personalized learning content based on those learning results, Means for organizing the individualized learning content by referring to past learning information and external information sources, A means of presenting the compiled learning content to the user, A knowledge system that provides knowledge including the features of a new product, and means for automatically generating personalized educational materials based on the user's identified weaknesses, A system that includes this.

2. The system according to claim 1, further comprising means for analyzing the learning items that the user answered incorrectly, extracting information related to the incorrect items, and presenting knowledge levels to enable the user to expand their knowledge.

3. The system according to claim 1, further comprising means for using artificial intelligence to identify areas of weakness based on the user's learning results, generating supplementary learning materials targeting the identified areas of weakness, and providing educational support to promote product understanding in commercial stores.

Images