system

Abstract

We provide the system. [Solution] Methods for evaluating an individual's cognitive characteristics, A means for generating learning materials based on evaluation results, A means for dynamically adjusting the adaptability of the generated learning materials, A means to optimize learning effectiveness according to cognitive characteristics, 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 method for controlling a persona chatbot, which is 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 character of the chatbot, 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] Modern educational systems focus on learning different subjects such as language arts, mathematics, science, and social studies. As a result, while learning in each individual subject is carried out efficiently, there is currently insufficient consideration given to enhancing the cognitive abilities that form the basis of learning. Consequently, learners have strengths and weaknesses in their cognitive abilities, and particularly the weaker areas are limiting factors for learning efficiency. An object of the present invention is to provide a new method for efficiently strengthening such individual cognitive characteristics and improving the overall quality of learning.

Means for Solving the Problems

[0005] This invention first provides a means for evaluating the cognitive characteristics of individual learners in detail. Next, based on the evaluation results, it provides individually optimized learning materials by using a means to generate high-load tasks for the learner's strong cognitive characteristics and low-load tasks for their weaker characteristics. Furthermore, it provides a means to constantly monitor the learner's reaction time and accuracy rate in real time, to understand the progress of learning, and to dynamically adjust the difficulty level and content of the learning materials accordingly. This optimizes individual cognitive characteristics and realizes efficient learning that makes maximum use of working memory.

[0006] "Cognitive characteristics" refer to the specific features and tendencies of an individual's ability to process and understand information.

[0007] "Learning materials" refer to a collection of educational materials and assignments used by learners to acquire specific knowledge or skills.

[0008] "Generation" is the process of creating new data or objects based on evaluation results and known information.

[0009] "Dynamic adjustment" refers to the process of changing system or process parameters in response to changes in circumstances or states.

[0010] "Reaction time" is a measure of the time it takes to initiate a response to a stimulus.

[0011] "Correct answer rate" is an indicator that shows the percentage of people who answered a particular task correctly.

[0012] "Working memory" is a temporary memory system in the brain that temporarily holds, manipulates, and processes information.

[0013] "Optimization" refers to making adjustments and improvements to achieve the greatest effect or efficiency for a specific goal or condition. [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.

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

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

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

[0020] In the following embodiments, 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 is an AI system that streamlines learning according to an individual's cognitive characteristics. The system mainly consists of three entities: a server, a terminal, and a user, each playing a specific role.

[0036] First, the server provides a test to assess cognitive characteristics when a user first accesses the system. This test is designed to identify the user's cognitive strengths and weaknesses based on their input and responses. The test results are aggregated and analyzed on the server to generate individual user cognitive profiles.

[0037] Next, the server uses a generative AI to generate learning materials based on the user's cognitive profile. These materials consist of high-intensity and low-intensity tasks and are optimized according to the user's cognitive characteristics. Users with strong cognitive abilities are presented with complex problems, while those with weaker areas are presented with basic problems. For example, users with strong visual memory are given complex image recognition tasks, while users with weak logical thinking skills are presented with basic mathematical problems in a step-by-step manner.

[0038] The device functions as an interface for users to view learning materials and work on assignments. As the user progresses through the learning process, the device records reaction time and accuracy in real time and sends this data to a server. This data is collected for each user to support improvements in learning progress and assignment adaptation.

[0039] The server analyzes the received data and adjusts the content and difficulty level of the learning materials accordingly. This dynamic feedback loop makes it possible to optimize the learning experience according to the user's evolving cognitive characteristics. The feedback from the server is sent to the user's device and reflected in the next learning session.

[0040] This interactive cycle allows users to continuously receive learning tailored to their cognitive characteristics, effectively strengthening their foundational cognitive abilities.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The user accesses the system for the first time and completes the registration process. They use a terminal to enter basic information and begin an adaptive assessment test to evaluate their cognitive characteristics.

[0044] Step 2:

[0045] The terminal continuously records the user's input and test responses, and sends this information to the server. The server receives this information, analyzes the user's response data, and generates a cognitive profile.

[0046] Step 3:

[0047] The server utilizes AI generation to prepare learning materials tailored to each user. High-load tasks are designed to align with the user's cognitive strengths, while low-load tasks are configured to complement areas where the user struggles.

[0048] Step 4:

[0049] Based on server instructions, the terminal provides learning materials optimized for the user. The user works on assignments through the terminal and enters their answers to each question.

[0050] Step 5:

[0051] The device collects user reaction time and accuracy during the learning process and sends this data to the server. This collection is done in real time, ensuring accurate data is recorded.

[0052] Step 6:

[0053] The server analyzes the received data in real time to assess the user's current cognitive characteristics and limitations. Based on this, it dynamically adjusts the learning materials and workload for the next learning session.

[0054] Step 7:

[0055] Based on feedback from the server, the terminal displays a plan for the next learning session to the user. The user then proceeds to the next stage of learning.

[0056] This series of steps allows users to continuously optimize their cognitive characteristics and learn more efficiently.

[0057] (Example 1)

[0058] 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."

[0059] Traditional learning systems struggle to provide learning support that adequately considers the diverse cognitive characteristics of individuals, and therefore fail to effectively utilize each learner's strengths and weaknesses. This problem can lead to the provision of suboptimal learning methods, potentially reducing learning effectiveness.

[0060] 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.

[0061] In this invention, the server includes means for evaluating an individual's cognitive characteristics, means for generating educational content based on the evaluation results, and means for dynamically adjusting the adaptability of the generated educational content. This makes it possible to provide an optimal learning method tailored to an individual's cognitive characteristics and maximize learning effectiveness.

[0062] "Cognitive characteristics" refer to the characteristics of an individual's ability to acquire, process, and remember information.

[0063] "Evaluation" refers to the quantitative or qualitative measurement and analysis of an individual's cognitive characteristics.

[0064] "Educational content" refers to learning materials and assignments prepared to improve learners' skills and abilities.

[0065] "Dynamic adjustment" means optimizing the content and difficulty level of learning materials and assignments in real time according to the learner's progress and performance.

[0066] "Learning effectiveness" refers to the results of improved knowledge and skill development gained through learning activities.

[0067] "Means" refers to the methods, devices, or systems used to achieve a specific purpose.

[0068] This invention is designed as an artificial intelligence system for optimizing learning based on an individual's cognitive characteristics. The system mainly consists of three entities: a server, a terminal, and a user, each playing a specific role.

[0069] The server first provides a test to assess cognitive characteristics through a web application when a user accesses the system. This test is created using JavaScript® and records user input in real time. The recorded data is sent to the server, where data analysis libraries such as NumPy and Pandas are used to generate individual cognitive profiles.

[0070] The server creates educational content using a generative AI model based on the generated cognitive profile. Specifically, it prompts the AI ​​model (e.g., a natural language processing model) with the message, "Based on the user's cognitive profile, provide an image recognition task for people with strong visual memory." The generated educational content is then sent to the device in HTML or PDF format.

[0071] The device displays educational content sent from the server, allowing the user to access it. The user learns using the provided educational content, and their reaction time and accuracy are measured in real time using a JavaScript program and sent back to the server.

[0072] The server analyzes the user's learning data and uses Scikit-learn to evaluate learning progress. Based on this data, the content and difficulty level of the educational material are dynamically adjusted. The adjusted educational content is reflected on the device in the next learning session, optimizing the learning experience according to the user's evolving cognitive characteristics.

[0073] This allows users to effectively improve their skills and knowledge within a learning environment optimized for their own cognitive characteristics.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The server provides a test to assess cognitive characteristics when a user accesses the system. Users answer the test through their browser, and their input data is recorded in real time by JavaScript. This data serves as input for evaluating the user's individual cognitive characteristics. The recorded data is sent to the server, where it is analyzed using statistical methods to obtain an output result: the user's cognitive profile.

[0077] Step 2:

[0078] The server uses the cognitive profile to request the generative AI model to generate educational content. Specifically, it inputs the prompt "Based on the user's cognitive profile, please provide an image recognition task for people with strong visual memory" into the generative AI model. Based on this input, the model outputs specific educational content. In this process, data such as complex images and step-by-step problems are generated.

[0079] Step 3:

[0080] The server sends the generated educational content to the device. The device receives the content and displays it in a web browser. During this process, the content is converted to HTML or PDF format. The user works on tasks while viewing the content on the device, and the response information obtained (e.g., response time and accuracy rate) is recorded using JavaScript.

[0081] Step 4:

[0082] The learning data collected by the device is sent to the server, which analyzes the data. Progress is evaluated using tools like Scikit-learn, and learning is quantitatively assessed. Based on this input data, the content and difficulty level of the educational material are adjusted. The adjustment results are delivered to the device in the next learning session and output as new applied content.

[0083] Step 5:

[0084] The server continuously optimizes dynamically adjusted educational content for each user. This cycle is repeated to adapt to the user's evolving cognitive characteristics and continuously maximize learning effectiveness. The input is improved learning data, and the output is user-specific, optimized educational content.

[0085] (Application Example 1)

[0086] 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."

[0087] By enabling the provision of information tailored to individual cognitive characteristics, it is necessary to promote the understanding and utilization of information optimally for each user, thereby improving the effectiveness of personalized learning and product selection. Conventional systems do not adequately provide information based on individual cognitive characteristics, and there is a need to improve the quality of the user experience.

[0088] 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.

[0089] In this invention, the server includes means for evaluating an individual's cognitive characteristics, means for generating learning materials based on the evaluation results, means for dynamically adjusting the adaptability of the generated learning materials, and means for personalizing the information provided based on the individual's cognitive characteristics. This enables the provision of information optimized for the individual, supporting effective learning and product selection.

[0090] "Methods for evaluating an individual's cognitive characteristics" refer to the process of conducting tests to identify a user's cognitive strengths and weaknesses, and then generating a cognitive profile based on the results.

[0091] "Means for generating learning materials based on evaluation results" refers to a process of creating and providing optimal learning materials tailored to each user's cognitive characteristics using a generation AI.

[0092] "Means for dynamically adjusting the adaptability of generated learning materials" refers to a process that appropriately changes the content and difficulty level of the learning materials according to the learning progress, providing materials that match the user's level of understanding and progress.

[0093] "Methods for optimizing learning effectiveness according to cognitive characteristics" refer to the process of presenting learning materials in a way that is most suitable for the user's characteristics and forming a feedback loop to promote effective learning.

[0094] "Methods for personalizing information based on individual cognitive characteristics" refers to the process of providing information in a format that is optimal for each user, such as users with strong visual memory or those who excel at logical thinking, by specializing and providing information according to the user's characteristics.

[0095] The system that implements this application consists of three entities: a server, a terminal, and a user. The server provides a test to evaluate the user's cognitive characteristics and generates individual cognitive profiles by aggregating and analyzing the user's input data. Based on the evaluation results, a generative AI is used to automatically generate learning materials and information content optimized for the user. The learning materials are customized according to the user's cognitive characteristics and are delivered using a variety of media.

[0096] The device displays the learning materials and information content, functioning as an interface for the user to engage with them. It also records reaction time and accuracy as the user progresses, providing feedback to the server. This feedback data is used by the server to dynamically adjust the content and difficulty level of the learning materials.

[0097] The server optimizes information delivery according to the user's evolving cognitive characteristics, continuously providing a personalized learning experience. In this way, it supports users' effective learning and product selection through the presentation of information. For example, it can present product descriptions using images and videos to users with strong visual memory, and provide detailed data and specifications to users who excel at logical thinking.

[0098] An example of a prompt for a generating AI is: "How can product information be personalized based on the user's cognitive characteristics? In particular, consider including images and video content for users with strong visual memory, or technical specifications for users with strong logical thinking, to enhance purchasing tendencies."

[0099] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0100] Step 1:

[0101] The server provides the user with a test to assess their cognitive characteristics. The user answers this test and sends the input data to the server via the terminal. The input in this step is the user's test answers, and the output is the data necessary to generate the user's cognitive profile. The server analyzes the input data to identify the indicators that constitute the user's cognitive characteristics.

[0102] Step 2:

[0103] The server uses a generative AI model to generate learning materials and informational content based on the user's cognitive characteristics. This process generates instructions for the AI ​​model using prompts, creating materials optimized for the user. The input is the generated cognitive profile, and the output is personalized learning materials. Specifically, for users with strong visual memory, image-centric content is selected.

[0104] Step 3:

[0105] The device presents the generated learning materials to the user and provides an interface for progressing through the learning process. The user interacts with the materials through the device while working at their own pace. The input in this step is the generated learning materials, and the output is the user's learning progress (accuracy rate and reaction time). The device records this information and provides a learning experience.

[0106] Step 4:

[0107] The terminal sends feedback to the server regarding the user's learning progress. Using this data, the server adjusts the difficulty level and content of the learning materials. The input to this process is the user's learning progress data, and the output is the optimized content of the next learning material provided. The server dynamically analyzes the data and updates the learning plan to suit each individual user.

[0108] Step 5:

[0109] The server sends the updated content to the terminal and provides it to the user in the next learning session. The user receives the new materials and continues learning. The input for this step is the adjusted material data, and the output is the provision of new materials to maximize the user's learning efficiency. The server provides continuous learning support through content optimization.

[0110] 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.

[0111] This invention is an AI learning system that takes into account the user's cognitive characteristics and emotional state. This system is built using a server, a terminal, and an emotion engine, with each component playing a specific role to optimize the user's learning experience.

[0112] First, the user accesses the system and enters basic information through their device. An adaptive assessment test is then conducted, and the server generates a cognitive profile of the user based on the collected data. This profile specifically outlines the user's information processing abilities, strengths, and weaknesses.

[0113] Next, using generative AI, the server creates learning materials based on the user's cognitive profile. These materials include high-intensity tasks tailored to the user's strengths and low-intensity tasks addressing their weaknesses. Furthermore, an emotion engine analyzes the user's facial expressions and biometric information in real time to recognize their emotional state. This allows the content to be instantly adjusted according to the learning progress.

[0114] For example, if the emotion engine detects stress or frustration while a user is working on a difficult task, the server will immediately change the task to one that is easier for the user. Conversely, if the system determines that the user is relaxed, it will increase the difficulty of the task and provide appropriate stimulation to enhance their motivation to learn.

[0115] During a learning session, the device records user input data (such as reaction time and accuracy) and sentiment data, and continuously sends this data to the server. The server analyzes this data in real time, evaluates the user's learning progress, and adjusts the overall system accordingly.

[0116] This feedback loop ensures that users always receive a learning experience optimized for their own cognitive characteristics and emotional state. This system reduces user stress and improves learning efficiency, thereby enhancing learning ability.

[0117] The following describes the processing flow.

[0118] Step 1:

[0119] Users log in to the system and complete initial registration. They enter their personal information and learning objectives via their device.

[0120] Step 2:

[0121] The device administers an adaptive assessment test to the user and records their responses to the questions. The test is designed to identify the user's cognitive characteristics.

[0122] Step 3:

[0123] The server analyzes the response data sent from the terminal and generates a cognitive profile of the user. This profile clearly identifies the user's strengths and areas that need improvement.

[0124] Step 4:

[0125] The server uses generative AI to create learning materials based on the user's cognitive profile. The materials are a balanced mix of high-intensity and low-intensity tasks.

[0126] Step 5:

[0127] The emotion engine uses the device's camera and sensors to analyze the user's facial expressions and biometric data, identifying their emotional state in real time.

[0128] Step 6:

[0129] Users engage with learning materials provided by the server via their devices. Throughout the assignment, the emotion engine continuously monitors the user's emotional changes.

[0130] Step 7:

[0131] The device collects user reaction time, accuracy rate, and sentiment data, and sends this data to the server.

[0132] Step 8:

[0133] The server analyzes the collected data and dynamically adjusts the content and difficulty level of the learning materials as needed. For example, if the server determines that the user is experiencing stress, it will change the task to something more relaxing.

[0134] Step 9:

[0135] The server sends the adjustment results to the terminal and instructs the user on the next learning stage. The user continues to work on new challenges.

[0136] This series of steps allows users to receive learning tailored to their cognitive characteristics and emotional state, enabling them to effectively improve their abilities.

[0137] (Example 2)

[0138] 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".

[0139] Modern educational methods often employ a uniform learning approach that disregards individual cognitive characteristics and emotional states. As a result, learners may experience stress and reduced learning effectiveness. This invention aims to provide an optimized educational experience for each learner, thereby improving learning efficiency and effectiveness.

[0140] 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.

[0141] In this invention, the server includes means for evaluating an individual's cognitive characteristics, means for generating educational materials based on the evaluation results, and means for analyzing an individual's emotional state and adjusting the learning content accordingly. This makes it possible to provide learning materials optimized for each learner's learning characteristics in real time.

[0142] "Individual" refers to a specific learner, and the data collected includes their individual characteristics, emotional state, and other specific information.

[0143] "Cognitive characteristics" refer to the features related to intellectual activities, such as a learner's information processing ability, memory, and problem-solving ability.

[0144] "Means of evaluation" refer to methods and devices for measuring and analyzing learners' cognitive characteristics and learning outcomes.

[0145] "Educational materials" refer to teaching materials, assignments, and learning content provided to learners, and are used to achieve learning objectives.

[0146] "Emotional state" refers to the learner's psychological and physiological state, including elements such as stress, relaxation, and concentration.

[0147] "Analysis" refers to the process of understanding learners' characteristics and conditions using measured data, and then providing appropriate learning materials and support based on that information.

[0148] "Means of adjustment" refers to methods and techniques for modifying the content and difficulty level of educational materials according to the characteristics and circumstances of the learners.

[0149] This invention is a learning support system that optimizes learning content according to an individual's cognitive characteristics and emotional state. This system is mainly constructed using a server, terminals, and an emotion analysis engine.

[0150] The terminal, as the first device a user accesses, provides an interface for entering basic information. Through this terminal, users enter personal information such as their name, age, and learning objectives. Adaptive assessment tests are conducted on the terminal, collecting data to understand the user's cognitive characteristics. These tests record the user's reaction time and accuracy rate, and this data is transmitted to the server.

[0151] The server generates a user cognitive profile using a specific analysis algorithm based on data sent from the terminal. This profile includes the user's information processing ability, memory, and other cognitive characteristics. The server then utilizes a generative AI model to create educational materials based on this cognitive profile. In this process, prompts are input into the generative AI model, which selects high-intensity and low-intensity tasks tailored to the user.

[0152] The emotion analysis engine uses the device's camera and biosensors to collect and analyze the user's facial expressions and physical condition data in real time. Based on this emotion data, the server dynamically adjusts the learning content. For example, if the user shows signs of stress, the difficulty of the task is lowered, and if they are relaxed, more challenging content is provided.

[0153] As a concrete example, consider a case where a user is learning a new language. If the response time recorded by the device is long, the server prompts the generating AI with the message, "The current task is too difficult; please create and provide easier vocabulary questions." In this way, an optimized educational experience is provided for each user, improving learning efficiency.

[0154] An example of a prompt statement is as follows:

[0155] "The user's cognitive profile is as follows: Strengths are vocabulary memory, weaknesses are grammar comprehension. Please create learning materials based on this."

[0156] Thus, the present invention provides a learning environment adapted to each user, realizing educational support that meets individual learning needs.

[0157] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0158] Step 1:

[0159] Users access the system through a terminal and enter basic information. The terminal retrieves information such as the user's name, age, and learning objectives. The entered personal information is stored in a database and used for subsequent adaptive assessment tests.

[0160] Step 2:

[0161] The device presents the user with an adaptive assessment test. By answering this test, the user generates data on cognitive characteristics (e.g., reaction time and accuracy). The device receives the test results and sends the data to the server. Data processing is performed, including calculations of average reaction time and accuracy.

[0162] Step 3:

[0163] The server analyzes the received user test data and generates a cognitive profile. Inputs include reaction time and accuracy, and the output is a profile indicating the user's information processing ability. Statistical processing is performed here to clearly identify the user's strengths and weaknesses.

[0164] Step 4:

[0165] The server uses a generative AI model to create educational materials based on the user's cognitive profile. The server sends prompts to the generative AI model to generate customized tasks. The output is learning material optimized for the user's characteristics. Specifically, the prompt "Create tasks based on the user's cognitive profile" is sent, and the materials are generated.

[0166] Step 5:

[0167] The emotion analysis engine uses the device's sensors to analyze the user's biometric information and facial expressions. Based on the input data obtained (e.g., facial image, biosensor data), the emotional state is evaluated. The output is the user's emotional state (e.g., stress, relaxation), and this information is obtained using an analysis algorithm.

[0168] Step 6:

[0169] The server adapts and adjusts the learning content according to the user's emotional state. It receives emotional state data from an emotion analysis engine as input and outputs the result of adjusting the learning materials. For example, if stress is detected, the server switches to a simpler task.

[0170] Step 7:

[0171] The device continuously collects user response and sentiment data and sends it to the server. This includes data necessary to record the user's progress and adjust the learning plan. The data is analyzed in real time on the server, and feedback is provided to the user as output. The device operates according to a communication protocol to accurately transmit the acquired data to the server.

[0172] (Application Example 2)

[0173] 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".

[0174] In factory and other work environments, it is necessary to optimize both work efficiency and the psychological burden on workers simultaneously, taking into account the cognitive characteristics and emotional states of individual workers. Conventional systems only provide general instructions and procedures, making it difficult to adjust to individual characteristics and emotions, resulting in insufficient improvements in productivity and the work environment.

[0175] 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.

[0176] In this invention, the server includes means for evaluating an individual's cognitive characteristics, means for generating learning materials and work instructions based on the evaluation results, and means for detecting changes in emotional state in real time and individually adjusting work instructions. This enables efficient work instructions tailored to the worker's characteristics and dynamic adjustments to match their emotional state.

[0177] "Individual cognitive characteristics" refer to a profile that specifically shows the information processing abilities and strengths and weaknesses of each worker.

[0178] "Learning materials" refer to a collection of educational content and tasks generated based on the cognitive characteristics of the workers.

[0179] "Dynamic adjustment means" refers to a function that changes the content and difficulty level of the provided learning materials and work instructions in real time according to the work environment and learning progress.

[0180] "Optimizing learning effectiveness according to cognitive characteristics and emotional state" refers to a process for maximizing learning outcomes based on the individual characteristics and current emotional state of each worker.

[0181] "Methods for detecting changes in emotional state in real time" refers to technologies that instantly detect changes in emotions by analyzing the facial expressions and physical biometric data of workers.

[0182] "Means of individually adjusting work instructions" refers to methods for optimizing and providing work procedures and missions according to an individual's cognitive characteristics and real-time emotional state.

[0183] The system for implementing this invention is built using a server, a terminal, and an emotion engine. The server evaluates an individual's cognitive characteristics and generates optimized learning materials and work instructions based on the results. When a user inputs basic information through the terminal, an adaptive assessment test is conducted, and the server uses this data to generate a cognitive profile. This profile indicates information processing abilities and strengths and weaknesses in thinking.

[0184] The server uses a generative AI model to generate learning materials and work instructions based on this cognitive profile. This generation includes high-intensity tasks tailored to the user's strengths and low-intensity tasks addressing their weaknesses. The emotion engine analyzes the user's facial expressions and biometric information in real time to identify their emotional state. Based on this information, the server instantly adjusts the content according to the learning and work progress. For example, if the server detects that the user is stressed, it changes the task content to make it easier for the user.

[0185] The system utilizes smart glasses and emotion recognition sensors as hardware, and employs an emotion recognition model using TENSORFLOW® and a backend server powered by Flask as software. Data processing includes collecting and analyzing workers' cognitive characteristics and analyzing their emotional states in real time. The server analyzes this data in real time and dynamically adjusts work instructions.

[0186] For example, if the system detects that a worker is experiencing stress while performing specific machine maintenance, the procedure will be adjusted to be simpler and more user-friendly. An example of a prompt message might be: "Generate the following machine maintenance procedure based on worker 123's cognitive characteristics. Current emotional state: stressed."

[0187] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0188] Step 1:

[0189] The user enters basic information through the terminal. The terminal collects the entered personal information, past work data, and biometric data, and sends it to the server. This allows the server to receive the initial data necessary for evaluating cognitive characteristics.

[0190] Step 2:

[0191] The server analyzes the received data and conducts adaptive assessment tests. The analysis applies algorithms to identify information processing abilities and strengths and weaknesses in thinking. Based on this information, a cognitive profile is generated, identifying specific cognitive characteristics for each individual user.

[0192] Step 3:

[0193] The server uses a generative AI model to generate learning materials and work instructions based on cognitive profiles. Here, inputs and outputs are transformed from cognitive profiles into optimized learning materials. This prepares high-intensity and low-intensity tasks for each individual.

[0194] Step 4:

[0195] When a user begins learning or working, the emotion engine acquires the user's biometric and facial expression data in real time. Using this data, the emotion recognition model analyzes the user's current emotional state.

[0196] Step 5:

[0197] The server receives the results of the emotional state analysis and dynamically adjusts learning materials and work instructions. Based on the input emotional data and cognitive profile, the content is adjusted to be optimal for the user. For example, if stress is detected, adjustments such as lowering the difficulty of the task are made.

[0198] Step 6:

[0199] The device collects user response time, accuracy rate, and real-time sentiment data, and periodically sends it to the server. This data allows the server to monitor user progress and form a feedback loop for continuous improvement.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] [Second Embodiment]

[0204] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0205] 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.

[0206] 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).

[0207] 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.

[0208] 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.

[0209] 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).

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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".

[0216] This invention is an AI system that streamlines learning according to an individual's cognitive characteristics. The system mainly consists of three entities: a server, a terminal, and a user, each playing a specific role.

[0217] First, the server provides a test to assess cognitive characteristics when a user first accesses the system. This test is designed to identify the user's cognitive strengths and weaknesses based on their input and responses. The test results are aggregated and analyzed on the server to generate individual user cognitive profiles.

[0218] Next, the server uses a generative AI to generate learning materials based on the user's cognitive profile. These materials consist of high-intensity and low-intensity tasks and are optimized according to the user's cognitive characteristics. Users with strong cognitive abilities are presented with complex problems, while those with weaker areas are presented with basic problems. For example, users with strong visual memory are given complex image recognition tasks, while users with weak logical thinking skills are presented with basic mathematical problems in a step-by-step manner.

[0219] The device functions as an interface for users to view learning materials and work on assignments. As the user progresses through the learning process, the device records reaction time and accuracy in real time and sends this data to a server. This data is collected for each user to support improvements in learning progress and assignment adaptation.

[0220] The server analyzes the received data and adjusts the content and difficulty level of the learning materials accordingly. This dynamic feedback loop makes it possible to optimize the learning experience according to the user's evolving cognitive characteristics. The feedback from the server is sent to the user's device and reflected in the next learning session.

[0221] This interactive cycle allows users to continuously receive learning tailored to their cognitive characteristics, effectively strengthening their foundational cognitive abilities.

[0222] The following describes the processing flow.

[0223] Step 1:

[0224] The user accesses the system for the first time and completes the registration process. They use a terminal to enter basic information and begin an adaptive assessment test to evaluate their cognitive characteristics.

[0225] Step 2:

[0226] The terminal continuously records the user's input and test responses, and sends this information to the server. The server receives this information, analyzes the user's response data, and generates a cognitive profile.

[0227] Step 3:

[0228] The server utilizes AI generation to prepare learning materials tailored to each user. High-load tasks are designed to align with the user's cognitive strengths, while low-load tasks are configured to complement areas where the user struggles.

[0229] Step 4:

[0230] Based on server instructions, the terminal provides learning materials optimized for the user. The user works on assignments through the terminal and enters their answers to each question.

[0231] Step 5:

[0232] The device collects user reaction time and accuracy during the learning process and sends this data to the server. This collection is done in real time, ensuring accurate data is recorded.

[0233] Step 6:

[0234] The server analyzes the received data in real time to assess the user's current cognitive characteristics and limitations. Based on this, it dynamically adjusts the learning materials and workload for the next learning session.

[0235] Step 7:

[0236] Based on feedback from the server, the terminal displays a plan for the next learning session to the user. The user then proceeds to the next stage of learning.

[0237] This series of steps allows users to continuously optimize their cognitive characteristics and learn more efficiently.

[0238] (Example 1)

[0239] 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."

[0240] Traditional learning systems struggle to provide learning support that adequately considers the diverse cognitive characteristics of individuals, and therefore fail to effectively utilize each learner's strengths and weaknesses. This problem can lead to the provision of suboptimal learning methods, potentially reducing learning effectiveness.

[0241] 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.

[0242] In this invention, the server includes means for evaluating an individual's cognitive characteristics, means for generating educational content based on the evaluation results, and means for dynamically adjusting the adaptability of the generated educational content. This makes it possible to provide an optimal learning method tailored to an individual's cognitive characteristics and maximize learning effectiveness.

[0243] "Cognitive characteristics" refer to the characteristics of an individual's ability to acquire, process, and remember information.

[0244] "Evaluation" refers to the quantitative or qualitative measurement and analysis of an individual's cognitive characteristics.

[0245] "Educational content" refers to learning materials and assignments prepared to improve learners' skills and abilities.

[0246] "Dynamic adjustment" means optimizing the content and difficulty level of learning materials and assignments in real time according to the learner's progress and performance.

[0247] "Learning effectiveness" refers to the results of improved knowledge and skill development gained through learning activities.

[0248] "Means" refers to the methods, devices, or systems used to achieve a specific purpose.

[0249] This invention is designed as an artificial intelligence system for optimizing learning based on an individual's cognitive characteristics. The system mainly consists of three entities: a server, a terminal, and a user, each playing a specific role.

[0250] The server first provides a test to assess cognitive characteristics through a web application when a user accesses the system. This test is created using JavaScript and records user input in real time. The recorded data is sent to the server, where data analysis libraries such as NumPy and Pandas are used to generate individual cognitive profiles.

[0251] The server creates educational content using a generative AI model based on the generated cognitive profile. Specifically, it prompts the AI ​​model (e.g., a natural language processing model) with the message, "Based on the user's cognitive profile, provide an image recognition task for people with strong visual memory." The generated educational content is then sent to the device in HTML or PDF format.

[0252] The device displays educational content sent from the server, allowing the user to access it. The user learns using the provided educational content, and their reaction time and accuracy are measured in real time using a JavaScript program and sent back to the server.

[0253] The server analyzes the user's learning data and uses Scikit-learn to evaluate learning progress. Based on this data, the content and difficulty level of the educational material are dynamically adjusted. The adjusted educational content is reflected on the device in the next learning session, optimizing the learning experience according to the user's evolving cognitive characteristics.

[0254] This allows users to effectively improve their skills and knowledge within a learning environment optimized for their own cognitive characteristics.

[0255] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0256] Step 1:

[0257] The server provides a test to assess cognitive characteristics when a user accesses the system. Users answer the test through their browser, and their input data is recorded in real time by JavaScript. This data serves as input for evaluating the user's individual cognitive characteristics. The recorded data is sent to the server, where it is analyzed using statistical methods to obtain an output result: the user's cognitive profile.

[0258] Step 2:

[0259] The server uses the cognitive profile to request the generative AI model to generate educational content. Specifically, it inputs the prompt "Based on the user's cognitive profile, please provide an image recognition task for people with strong visual memory" into the generative AI model. Based on this input, the model outputs specific educational content. In this process, data such as complex images and step-by-step problems are generated.

[0260] Step 3:

[0261] The server sends the generated educational content to the device. The device receives the content and displays it in a web browser. During this process, the content is converted to HTML or PDF format. The user works on tasks while viewing the content on the device, and the response information obtained (e.g., response time and accuracy rate) is recorded using JavaScript.

[0262] Step 4:

[0263] The learning data collected by the device is sent to the server, which analyzes the data. Progress is evaluated using tools like Scikit-learn, and learning is quantitatively assessed. Based on this input data, the content and difficulty level of the educational material are adjusted. The adjustment results are delivered to the device in the next learning session and output as new applied content.

[0264] Step 5:

[0265] The server continuously optimizes dynamically adjusted educational content for each user. This cycle is repeated to adapt to the user's evolving cognitive characteristics and continuously maximize learning effectiveness. The input is improved learning data, and the output is user-specific, optimized educational content.

[0266] (Application Example 1)

[0267] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0268] By enabling the provision of information tailored to individual cognitive characteristics, it is necessary to promote the understanding and utilization of information optimally for each user, thereby improving the effectiveness of personalized learning and product selection. Conventional systems do not adequately provide information based on individual cognitive characteristics, and there is a need to improve the quality of the user experience.

[0269] 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.

[0270] In this invention, the server includes means for evaluating an individual's cognitive characteristics, means for generating learning materials based on the evaluation results, means for dynamically adjusting the adaptability of the generated learning materials, and means for personalizing the information provided based on the individual's cognitive characteristics. This enables the provision of information optimized for the individual, supporting effective learning and product selection.

[0271] "Methods for evaluating an individual's cognitive characteristics" refer to the process of conducting tests to identify a user's cognitive strengths and weaknesses, and then generating a cognitive profile based on the results.

[0272] "Means for generating learning materials based on evaluation results" refers to a process of creating and providing optimal learning materials tailored to each user's cognitive characteristics using a generation AI.

[0273] "Means for dynamically adjusting the adaptability of generated learning materials" refers to a process that appropriately changes the content and difficulty level of the learning materials according to the learning progress, providing materials that match the user's level of understanding and progress.

[0274] "Methods for optimizing learning effectiveness according to cognitive characteristics" refer to the process of presenting learning materials in a way that is most suitable for the user's characteristics and forming a feedback loop to promote effective learning.

[0275] "Methods for personalizing information based on individual cognitive characteristics" refers to the process of providing information in a format that is optimal for each user, such as users with strong visual memory or those who excel at logical thinking, by specializing and providing information according to the user's characteristics.

[0276] The system that implements this application consists of three entities: a server, a terminal, and a user. The server provides a test to evaluate the user's cognitive characteristics and generates individual cognitive profiles by aggregating and analyzing the user's input data. Based on the evaluation results, a generative AI is used to automatically generate learning materials and information content optimized for the user. The learning materials are customized according to the user's cognitive characteristics and are delivered using a variety of media.

[0277] The device displays the learning materials and information content, functioning as an interface for the user to engage with them. It also records reaction time and accuracy as the user progresses, providing feedback to the server. This feedback data is used by the server to dynamically adjust the content and difficulty level of the learning materials.

[0278] The server optimizes information delivery according to the user's evolving cognitive characteristics, continuously providing a personalized learning experience. In this way, it supports users' effective learning and product selection through the presentation of information. For example, it can present product descriptions using images and videos to users with strong visual memory, and provide detailed data and specifications to users who excel at logical thinking.

[0279] An example of a prompt for a generating AI is: "How can product information be personalized based on the user's cognitive characteristics? In particular, consider including images and video content for users with strong visual memory, or technical specifications for users with strong logical thinking, to enhance purchasing tendencies."

[0280] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0281] Step 1:

[0282] The server provides the user with a test to assess their cognitive characteristics. The user answers this test and sends the input data to the server via the terminal. The input in this step is the user's test answers, and the output is the data necessary to generate the user's cognitive profile. The server analyzes the input data to identify the indicators that constitute the user's cognitive characteristics.

[0283] Step 2:

[0284] The server uses a generative AI model to generate learning materials and information content based on the user's cognitive characteristics. In this process, prompt sentences are used to generate instructions for the AI model to create learning materials optimized for the user. The input is the generated cognitive profile, and the output is personalized learning materials. Specifically, for users with strong visual memory, image-centered content is selected.

[0285] Step 3:

[0286] The terminal presents the generated learning materials to the user and provides an interface for learning progress. The user operates the materials through the terminal while learning at their own pace. The input for this step is the generated materials, and the output is the user's learning progress (accuracy rate and reaction time). The terminal records this information and provides a learning experience.

[0287] Step 4:

[0288] The terminal sends the user's learning progress to the server as feedback. Using this data, the server adjusts the difficulty level and content of the materials. The input for this process is the user's learning progress data, and the output is the optimized content of the materials to be provided next. The server dynamically analyzes the data and updates the learning plan suitable for individual users.

[0289] Step 5:

[0290] The server sends the updated content to the terminal for the user to receive in the next learning session. The user receives the new materials and continues to learn. The input for this step is the adjusted material data, and the output is the provision of new materials to maximize the user's learning efficiency. The server provides continuous learning support through content optimization.

[0291] 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.

[0292] This invention is an AI learning system that takes into account the user's cognitive characteristics and emotional state. This system is built using a server, a terminal, and an emotion engine, with each component playing a specific role to optimize the user's learning experience.

[0293] First, the user accesses the system and enters basic information through their device. An adaptive assessment test is then conducted, and the server generates a cognitive profile of the user based on the collected data. This profile specifically outlines the user's information processing abilities, strengths, and weaknesses.

[0294] Next, using generative AI, the server creates learning materials based on the user's cognitive profile. These materials include high-intensity tasks tailored to the user's strengths and low-intensity tasks addressing their weaknesses. Furthermore, an emotion engine analyzes the user's facial expressions and biometric information in real time to recognize their emotional state. This allows the content to be instantly adjusted according to the learning progress.

[0295] For example, if the emotion engine detects stress or frustration while a user is working on a difficult task, the server will immediately change the task to one that is easier for the user. Conversely, if the system determines that the user is relaxed, it will increase the difficulty of the task and provide appropriate stimulation to enhance their motivation to learn.

[0296] During a learning session, the device records user input data (such as reaction time and accuracy) and sentiment data, and continuously sends this data to the server. The server analyzes this data in real time, evaluates the user's learning progress, and adjusts the overall system accordingly.

[0297] Through this feedback loop, users can always receive a learning experience optimized for their cognitive characteristics and emotional state. This system realizes the improvement of learning ability by reducing users' stress and improving learning efficiency.

[0298] The processing flow will be described below.

[0299] Step 1:

[0300] The user logs in to the system and performs initial registration. Personal information and learning purposes are entered through the terminal.

[0301] Step 2:

[0302] The terminal conducts an adaptive assessment test on the user and records the answers to the questions. The test is designed to identify the user's cognitive characteristics.

[0303] Step 3:

[0304] The server analyzes the answer data sent from the terminal and generates the user's cognitive profile. This profile clarifies the user's areas of strength and areas that need improvement.

[0305] Step 4:

[0306] The server uses generative AI to create learning materials based on the user's cognitive profile. The materials have a well-balanced combination of high-load tasks and low-load tasks.

[0307] Step 5:

[0308] The emotion engine analyzes the user's facial expressions and biometric data using the terminal's camera and sensors, and identifies the emotional state in real time.

[0309] Step 6:

[0310] Users engage with learning materials provided by the server via their devices. Throughout the assignment, the emotion engine continuously monitors the user's emotional changes.

[0311] Step 7:

[0312] The device collects user reaction time, accuracy rate, and sentiment data, and sends this data to the server.

[0313] Step 8:

[0314] The server analyzes the collected data and dynamically adjusts the content and difficulty level of the learning materials as needed. For example, if the server determines that the user is experiencing stress, it will change the task to something more relaxing.

[0315] Step 9:

[0316] The server sends the adjustment results to the terminal and instructs the user on the next learning stage. The user continues to work on new challenges.

[0317] This series of steps allows users to receive learning tailored to their cognitive characteristics and emotional state, enabling them to effectively improve their abilities.

[0318] (Example 2)

[0319] 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".

[0320] Modern educational methods often employ a uniform learning approach that disregards individual cognitive characteristics and emotional states. As a result, learners may experience stress and reduced learning effectiveness. This invention aims to provide an optimized educational experience for each learner, thereby improving learning efficiency and effectiveness.

[0321] 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.

[0322] In this invention, the server includes means for evaluating an individual's cognitive characteristics, means for generating educational materials based on the evaluation results, and means for analyzing an individual's emotional state and adjusting the learning content accordingly. This makes it possible to provide learning materials optimized for each learner's learning characteristics in real time.

[0323] "Individual" refers to a specific learner, and the data collected includes their individual characteristics, emotional state, and other specific information.

[0324] "Cognitive characteristics" refer to the features related to intellectual activities, such as a learner's information processing ability, memory, and problem-solving ability.

[0325] "Means of evaluation" refer to methods and devices for measuring and analyzing learners' cognitive characteristics and learning outcomes.

[0326] "Educational materials" refer to teaching materials, assignments, and learning content provided to learners, and are used to achieve learning objectives.

[0327] "Emotional state" refers to the learner's psychological and physiological state, including elements such as stress, relaxation, and concentration.

[0328] "Analysis" refers to the process of understanding learners' characteristics and conditions using measured data, and then providing appropriate learning materials and support based on that information.

[0329] "Means of adjustment" refers to methods and techniques for modifying the content and difficulty level of educational materials according to the characteristics and circumstances of the learners.

[0330] This invention is a learning support system that optimizes learning content according to an individual's cognitive characteristics and emotional state. This system is mainly constructed using a server, terminals, and an emotion analysis engine.

[0331] The terminal, as the first device a user accesses, provides an interface for entering basic information. Through this terminal, users enter personal information such as their name, age, and learning objectives. Adaptive assessment tests are conducted on the terminal, collecting data to understand the user's cognitive characteristics. These tests record the user's reaction time and accuracy rate, and this data is transmitted to the server.

[0332] The server generates a user cognitive profile using a specific analysis algorithm based on data sent from the terminal. This profile includes the user's information processing ability, memory, and other cognitive characteristics. The server then utilizes a generative AI model to create educational materials based on this cognitive profile. In this process, prompts are input into the generative AI model, which selects high-intensity and low-intensity tasks tailored to the user.

[0333] The emotion analysis engine uses the device's camera and biosensors to collect and analyze the user's facial expressions and physical condition data in real time. Based on this emotion data, the server dynamically adjusts the learning content. For example, if the user shows signs of stress, the difficulty of the task is lowered, and if they are relaxed, more challenging content is provided.

[0334] As a concrete example, consider a case where a user is learning a new language. If the response time recorded by the device is long, the server prompts the generating AI with the message, "The current task is too difficult; please create and provide easier vocabulary questions." In this way, an optimized educational experience is provided for each user, improving learning efficiency.

[0335] An example of a prompt statement is as follows:

[0336] "The user's cognitive profile is as follows: Strengths are vocabulary memory, weaknesses are grammar comprehension. Please create learning materials based on this."

[0337] Thus, the present invention provides a learning environment adapted to each user, realizing educational support that meets individual learning needs.

[0338] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0339] Step 1:

[0340] Users access the system through a terminal and enter basic information. The terminal retrieves information such as the user's name, age, and learning objectives. The entered personal information is stored in a database and used for subsequent adaptive assessment tests.

[0341] Step 2:

[0342] The device presents the user with an adaptive assessment test. By answering this test, the user generates data on cognitive characteristics (e.g., reaction time and accuracy). The device receives the test results and sends the data to the server. Data processing is performed, including calculations of average reaction time and accuracy.

[0343] Step 3:

[0344] The server analyzes the received user test data and generates a cognitive profile. Inputs include reaction time and accuracy, and the output is a profile indicating the user's information processing ability. Statistical processing is performed here to clearly identify the user's strengths and weaknesses.

[0345] Step 4:

[0346] The server uses a generative AI model to create educational materials based on the user's cognitive profile. The server sends prompts to the generative AI model to generate customized tasks. The output is learning material optimized for the user's characteristics. Specifically, the prompt "Create tasks based on the user's cognitive profile" is sent, and the materials are generated.

[0347] Step 5:

[0348] The emotion analysis engine uses the device's sensors to analyze the user's biometric information and facial expressions. Based on the input data obtained (e.g., facial image, biosensor data), the emotional state is evaluated. The output is the user's emotional state (e.g., stress, relaxation), and this information is obtained using an analysis algorithm.

[0349] Step 6:

[0350] The server adapts and adjusts the learning content according to the user's emotional state. It receives emotional state data from an emotion analysis engine as input and outputs the result of adjusting the learning materials. For example, if stress is detected, the server switches to a simpler task.

[0351] Step 7:

[0352] The device continuously collects user response and sentiment data and sends it to the server. This includes data necessary to record the user's progress and adjust the learning plan. The data is analyzed in real time on the server, and feedback is provided to the user as output. The device operates according to a communication protocol to accurately transmit the acquired data to the server.

[0353] (Application Example 2)

[0354] 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."

[0355] In factory and other work environments, it is necessary to optimize both work efficiency and the psychological burden on workers simultaneously, taking into account the cognitive characteristics and emotional states of individual workers. Conventional systems only provide general instructions and procedures, making it difficult to adjust to individual characteristics and emotions, resulting in insufficient improvements in productivity and the work environment.

[0356] 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.

[0357] In this invention, the server includes means for evaluating an individual's cognitive characteristics, means for generating learning materials and work instructions based on the evaluation results, and means for detecting changes in emotional state in real time and individually adjusting work instructions. This enables efficient work instructions tailored to the worker's characteristics and dynamic adjustments to match their emotional state.

[0358] "Individual cognitive characteristics" refer to a profile that specifically shows the information processing abilities and strengths and weaknesses of each worker.

[0359] "Learning materials" refer to a collection of educational content and tasks generated based on the cognitive characteristics of the workers.

[0360] "Dynamic adjustment means" refers to a function that changes the content and difficulty level of the provided learning materials and work instructions in real time according to the work environment and learning progress.

[0361] "Optimizing learning effectiveness according to cognitive characteristics and emotional state" refers to a process for maximizing learning outcomes based on the individual characteristics and current emotional state of each worker.

[0362] "Methods for detecting changes in emotional state in real time" refers to technologies that instantly detect changes in emotions by analyzing the facial expressions and physical biometric data of workers.

[0363] "Means of individually adjusting work instructions" refers to methods for optimizing and providing work procedures and missions according to an individual's cognitive characteristics and real-time emotional state.

[0364] The system for implementing this invention is built using a server, a terminal, and an emotion engine. The server evaluates an individual's cognitive characteristics and generates optimized learning materials and work instructions based on the results. When a user inputs basic information through the terminal, an adaptive assessment test is conducted, and the server uses this data to generate a cognitive profile. This profile indicates information processing abilities and strengths and weaknesses in thinking.

[0365] The server uses a generative AI model to generate learning materials and work instructions based on this cognitive profile. This generation includes high-intensity tasks tailored to the user's strengths and low-intensity tasks addressing their weaknesses. The emotion engine analyzes the user's facial expressions and biometric information in real time to identify their emotional state. Based on this information, the server instantly adjusts the content according to the learning and work progress. For example, if the server detects that the user is stressed, it changes the task content to make it easier for the user.

[0366] The system utilizes smart glasses and emotion recognition sensors as hardware, and employs an emotion recognition model using TensorFlow and a backend server built with Flask as software. Data processing includes collecting and analyzing workers' cognitive characteristics and analyzing their emotional states in real time. The server analyzes this data in real time and dynamically adjusts work instructions.

[0367] For example, if the system detects that a worker is experiencing stress while performing specific machine maintenance, the procedure will be adjusted to be simpler and more user-friendly. An example of a prompt message might be: "Generate the following machine maintenance procedure based on worker 123's cognitive characteristics. Current emotional state: stressed."

[0368] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0369] Step 1:

[0370] The user enters basic information through the terminal. The terminal collects the entered personal information, past work data, and biometric data, and sends it to the server. This allows the server to receive the initial data necessary for evaluating cognitive characteristics.

[0371] Step 2:

[0372] The server analyzes the received data and conducts adaptive assessment tests. The analysis applies algorithms to identify information processing abilities and strengths and weaknesses in thinking. Based on this information, a cognitive profile is generated, identifying specific cognitive characteristics for each individual user.

[0373] Step 3:

[0374] The server uses a generative AI model to generate learning materials and work instructions based on cognitive profiles. Here, inputs and outputs are transformed from cognitive profiles into optimized learning materials. This prepares high-intensity and low-intensity tasks for each individual.

[0375] Step 4:

[0376] When a user begins learning or working, the emotion engine acquires the user's biometric and facial expression data in real time. Using this data, the emotion recognition model analyzes the user's current emotional state.

[0377] Step 5:

[0378] The server receives the results of the emotional state analysis and dynamically adjusts learning materials and work instructions. Based on the input emotional data and cognitive profile, the content is adjusted to be optimal for the user. For example, if stress is detected, adjustments such as lowering the difficulty of the task are made.

[0379] Step 6:

[0380] The device collects user response time, accuracy rate, and real-time sentiment data, and periodically sends it to the server. This data allows the server to monitor user progress and form a feedback loop for continuous improvement.

[0381] 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.

[0382] 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.

[0383] 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.

[0384] [Third Embodiment]

[0385] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0386] 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.

[0387] 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).

[0388] 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.

[0389] 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.

[0390] 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).

[0391] 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.

[0392] 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.

[0393] 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.

[0394] 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.

[0395] 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.

[0396] 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".

[0397] This invention is an AI system that streamlines learning according to an individual's cognitive characteristics. The system mainly consists of three entities: a server, a terminal, and a user, each playing a specific role.

[0398] First, the server provides a test to assess cognitive characteristics when a user first accesses the system. This test is designed to identify the user's cognitive strengths and weaknesses based on their input and responses. The test results are aggregated and analyzed on the server to generate individual user cognitive profiles.

[0399] Next, the server uses a generative AI to generate learning materials based on the user's cognitive profile. These materials consist of high-intensity and low-intensity tasks and are optimized according to the user's cognitive characteristics. Users with strong cognitive abilities are presented with complex problems, while those with weaker areas are presented with basic problems. For example, users with strong visual memory are given complex image recognition tasks, while users with weak logical thinking skills are presented with basic mathematical problems in a step-by-step manner.

[0400] The device functions as an interface for users to view learning materials and work on assignments. As the user progresses through the learning process, the device records reaction time and accuracy in real time and sends this data to a server. This data is collected for each user to support improvements in learning progress and assignment adaptation.

[0401] The server analyzes the received data and adjusts the content and difficulty level of the learning materials accordingly. This dynamic feedback loop makes it possible to optimize the learning experience according to the user's evolving cognitive characteristics. The feedback from the server is sent to the user's device and reflected in the next learning session.

[0402] This interactive cycle allows users to continuously receive learning tailored to their cognitive characteristics, effectively strengthening their foundational cognitive abilities.

[0403] The following describes the processing flow.

[0404] Step 1:

[0405] The user accesses the system for the first time and completes the registration process. They use a terminal to enter basic information and begin an adaptive assessment test to evaluate their cognitive characteristics.

[0406] Step 2:

[0407] The terminal continuously records the user's input and test responses, and sends this information to the server. The server receives this information, analyzes the user's response data, and generates a cognitive profile.

[0408] Step 3:

[0409] The server utilizes AI generation to prepare learning materials tailored to each user. High-load tasks are designed to align with the user's cognitive strengths, while low-load tasks are configured to complement areas where the user struggles.

[0410] Step 4:

[0411] Based on server instructions, the terminal provides learning materials optimized for the user. The user works on assignments through the terminal and enters their answers to each question.

[0412] Step 5:

[0413] The device collects user reaction time and accuracy during the learning process and sends this data to the server. This collection is done in real time, ensuring accurate data is recorded.

[0414] Step 6:

[0415] The server analyzes the received data in real time to assess the user's current cognitive characteristics and limitations. Based on this, it dynamically adjusts the learning materials and workload for the next learning session.

[0416] Step 7:

[0417] Based on feedback from the server, the terminal displays a plan for the next learning session to the user. The user then proceeds to the next stage of learning.

[0418] This series of steps allows users to continuously optimize their cognitive characteristics and learn more efficiently.

[0419] (Example 1)

[0420] 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."

[0421] Traditional learning systems struggle to provide learning support that adequately considers the diverse cognitive characteristics of individuals, and therefore fail to effectively utilize each learner's strengths and weaknesses. This problem can lead to the provision of suboptimal learning methods, potentially reducing learning effectiveness.

[0422] 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.

[0423] In this invention, the server includes means for evaluating an individual's cognitive characteristics, means for generating educational content based on the evaluation results, and means for dynamically adjusting the adaptability of the generated educational content. This makes it possible to provide an optimal learning method tailored to an individual's cognitive characteristics and maximize learning effectiveness.

[0424] "Cognitive characteristics" refer to the characteristics of an individual's ability to acquire, process, and remember information.

[0425] "Evaluation" refers to the quantitative or qualitative measurement and analysis of an individual's cognitive characteristics.

[0426] "Educational content" refers to learning materials and assignments prepared to improve learners' skills and abilities.

[0427] "Dynamic adjustment" means optimizing the content and difficulty level of learning materials and assignments in real time according to the learner's progress and performance.

[0428] "Learning effectiveness" refers to the results of improved knowledge and skill development gained through learning activities.

[0429] "Means" refers to the methods, devices, or systems used to achieve a specific purpose.

[0430] This invention is designed as an artificial intelligence system for optimizing learning based on an individual's cognitive characteristics. The system mainly consists of three entities: a server, a terminal, and a user, each playing a specific role.

[0431] The server first provides a test to assess cognitive characteristics through a web application when a user accesses the system. This test is created using JavaScript and records user input in real time. The recorded data is sent to the server, where data analysis libraries such as NumPy and Pandas are used to generate individual cognitive profiles.

[0432] The server creates educational content using a generative AI model based on the generated cognitive profile. Specifically, it prompts the AI ​​model (e.g., a natural language processing model) with the message, "Based on the user's cognitive profile, provide an image recognition task for people with strong visual memory." The generated educational content is then sent to the device in HTML or PDF format.

[0433] The device displays educational content sent from the server, allowing the user to access it. The user learns using the provided educational content, and their reaction time and accuracy are measured in real time using a JavaScript program and sent back to the server.

[0434] The server analyzes the user's learning data and uses Scikit-learn to evaluate learning progress. Based on this data, the content and difficulty level of the educational material are dynamically adjusted. The adjusted educational content is reflected on the device in the next learning session, optimizing the learning experience according to the user's evolving cognitive characteristics.

[0435] This allows users to effectively improve their skills and knowledge within a learning environment optimized for their own cognitive characteristics.

[0436] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0437] Step 1:

[0438] The server provides a test to assess cognitive characteristics when a user accesses the system. Users answer the test through their browser, and their input data is recorded in real time by JavaScript. This data serves as input for evaluating the user's individual cognitive characteristics. The recorded data is sent to the server, where it is analyzed using statistical methods to obtain an output result: the user's cognitive profile.

[0439] Step 2:

[0440] The server uses the cognitive profile to request the generative AI model to generate educational content. Specifically, it inputs the prompt "Based on the user's cognitive profile, please provide an image recognition task for people with strong visual memory" into the generative AI model. Based on this input, the model outputs specific educational content. In this process, data such as complex images and step-by-step problems are generated.

[0441] Step 3:

[0442] The server sends the generated educational content to the device. The device receives the content and displays it in a web browser. During this process, the content is converted to HTML or PDF format. The user works on tasks while viewing the content on the device, and the response information obtained (e.g., response time and accuracy rate) is recorded using JavaScript.

[0443] Step 4:

[0444] The learning data collected by the device is sent to the server, which analyzes the data. Progress is evaluated using tools like Scikit-learn, and learning is quantitatively assessed. Based on this input data, the content and difficulty level of the educational material are adjusted. The adjustment results are delivered to the device in the next learning session and output as new applied content.

[0445] Step 5:

[0446] The server continuously optimizes dynamically adjusted educational content for each user. This cycle is repeated to adapt to the user's evolving cognitive characteristics and continuously maximize learning effectiveness. The input is improved learning data, and the output is user-specific, optimized educational content.

[0447] (Application Example 1)

[0448] 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."

[0449] By enabling the provision of information tailored to individual cognitive characteristics, it is necessary to promote the understanding and utilization of information optimally for each user, thereby improving the effectiveness of personalized learning and product selection. Conventional systems do not adequately provide information based on individual cognitive characteristics, and there is a need to improve the quality of the user experience.

[0450] 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.

[0451] In this invention, the server includes means for evaluating an individual's cognitive characteristics, means for generating learning materials based on the evaluation results, means for dynamically adjusting the adaptability of the generated learning materials, and means for personalizing the information provided based on the individual's cognitive characteristics. This enables the provision of information optimized for the individual, supporting effective learning and product selection.

[0452] "Methods for evaluating an individual's cognitive characteristics" refer to the process of conducting tests to identify a user's cognitive strengths and weaknesses, and then generating a cognitive profile based on the results.

[0453] "Means for generating learning materials based on evaluation results" refers to a process of creating and providing optimal learning materials tailored to each user's cognitive characteristics using a generation AI.

[0454] "Means for dynamically adjusting the adaptability of generated learning materials" refers to a process that appropriately changes the content and difficulty level of the learning materials according to the learning progress, providing materials that match the user's level of understanding and progress.

[0455] "Methods for optimizing learning effectiveness according to cognitive characteristics" refer to the process of presenting learning materials in a way that is most suitable for the user's characteristics and forming a feedback loop to promote effective learning.

[0456] "Methods for personalizing information based on individual cognitive characteristics" refers to the process of providing information in a format that is optimal for each user, such as users with strong visual memory or those who excel at logical thinking, by specializing and providing information according to the user's characteristics.

[0457] The system that implements this application consists of three entities: a server, a terminal, and a user. The server provides a test to evaluate the user's cognitive characteristics and generates individual cognitive profiles by aggregating and analyzing the user's input data. Based on the evaluation results, a generative AI is used to automatically generate learning materials and information content optimized for the user. The learning materials are customized according to the user's cognitive characteristics and are delivered using a variety of media.

[0458] The device displays the learning materials and information content, functioning as an interface for the user to engage with them. It also records reaction time and accuracy as the user progresses, providing feedback to the server. This feedback data is used by the server to dynamically adjust the content and difficulty level of the learning materials.

[0459] The server optimizes information delivery according to the user's evolving cognitive characteristics, continuously providing a personalized learning experience. In this way, it supports users' effective learning and product selection through the presentation of information. For example, it can present product descriptions using images and videos to users with strong visual memory, and provide detailed data and specifications to users who excel at logical thinking.

[0460] An example of a prompt for a generating AI is: "How can product information be personalized based on the user's cognitive characteristics? In particular, consider including images and video content for users with strong visual memory, or technical specifications for users with strong logical thinking, to enhance purchasing tendencies."

[0461] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0462] Step 1:

[0463] The server provides the user with a test to assess their cognitive characteristics. The user answers this test and sends the input data to the server via the terminal. The input in this step is the user's test answers, and the output is the data necessary to generate the user's cognitive profile. The server analyzes the input data to identify the indicators that constitute the user's cognitive characteristics.

[0464] Step 2:

[0465] The server uses a generative AI model to generate learning materials and informational content based on the user's cognitive characteristics. This process generates instructions for the AI ​​model using prompts, creating materials optimized for the user. The input is the generated cognitive profile, and the output is personalized learning materials. Specifically, for users with strong visual memory, image-centric content is selected.

[0466] Step 3:

[0467] The device presents the generated learning materials to the user and provides an interface for progressing through the learning process. The user interacts with the materials through the device while working at their own pace. The input in this step is the generated learning materials, and the output is the user's learning progress (accuracy rate and reaction time). The device records this information and provides a learning experience.

[0468] Step 4:

[0469] The terminal sends feedback to the server regarding the user's learning progress. Using this data, the server adjusts the difficulty level and content of the learning materials. The input to this process is the user's learning progress data, and the output is the optimized content of the next learning material provided. The server dynamically analyzes the data and updates the learning plan to suit each individual user.

[0470] Step 5:

[0471] The server sends the updated content to the terminal and provides it to the user in the next learning session. The user receives the new materials and continues learning. The input for this step is the adjusted material data, and the output is the provision of new materials to maximize the user's learning efficiency. The server provides continuous learning support through content optimization.

[0472] 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.

[0473] This invention is an AI learning system that takes into account the user's cognitive characteristics and emotional state. This system is built using a server, a terminal, and an emotion engine, with each component playing a specific role to optimize the user's learning experience.

[0474] First, the user accesses the system and enters basic information through their device. An adaptive assessment test is then conducted, and the server generates a cognitive profile of the user based on the collected data. This profile specifically outlines the user's information processing abilities, strengths, and weaknesses.

[0475] Next, using generative AI, the server creates learning materials based on the user's cognitive profile. These materials include high-intensity tasks tailored to the user's strengths and low-intensity tasks addressing their weaknesses. Furthermore, an emotion engine analyzes the user's facial expressions and biometric information in real time to recognize their emotional state. This allows the content to be instantly adjusted according to the learning progress.

[0476] For example, if the emotion engine detects stress or frustration while a user is working on a difficult task, the server will immediately change the task to one that is easier for the user. Conversely, if the system determines that the user is relaxed, it will increase the difficulty of the task and provide appropriate stimulation to enhance their motivation to learn.

[0477] During a learning session, the device records user input data (such as reaction time and accuracy) and sentiment data, and continuously sends this data to the server. The server analyzes this data in real time, evaluates the user's learning progress, and adjusts the overall system accordingly.

[0478] This feedback loop ensures that users always receive a learning experience optimized for their own cognitive characteristics and emotional state. This system reduces user stress and improves learning efficiency, thereby enhancing learning ability.

[0479] The following describes the processing flow.

[0480] Step 1:

[0481] Users log in to the system and complete initial registration. They enter their personal information and learning objectives via their device.

[0482] Step 2:

[0483] The device administers an adaptive assessment test to the user and records their responses to the questions. The test is designed to identify the user's cognitive characteristics.

[0484] Step 3:

[0485] The server analyzes the response data sent from the terminal and generates a cognitive profile of the user. This profile clearly identifies the user's strengths and areas that need improvement.

[0486] Step 4:

[0487] The server uses generative AI to create learning materials based on the user's cognitive profile. The materials are a balanced mix of high-intensity and low-intensity tasks.

[0488] Step 5:

[0489] The emotion engine uses the device's camera and sensors to analyze the user's facial expressions and biometric data, identifying their emotional state in real time.

[0490] Step 6:

[0491] Users engage with learning materials provided by the server via their devices. Throughout the assignment, the emotion engine continuously monitors the user's emotional changes.

[0492] Step 7:

[0493] The device collects user reaction time, accuracy rate, and sentiment data, and sends this data to the server.

[0494] Step 8:

[0495] The server analyzes the collected data and dynamically adjusts the content and difficulty level of the learning materials as needed. For example, if the server determines that the user is experiencing stress, it will change the task to something more relaxing.

[0496] Step 9:

[0497] The server sends the adjustment results to the terminal and instructs the user on the next learning stage. The user continues to work on new challenges.

[0498] This series of steps allows users to receive learning tailored to their cognitive characteristics and emotional state, enabling them to effectively improve their abilities.

[0499] (Example 2)

[0500] 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."

[0501] Modern educational methods often employ a uniform learning approach that disregards individual cognitive characteristics and emotional states. As a result, learners may experience stress and reduced learning effectiveness. This invention aims to provide an optimized educational experience for each learner, thereby improving learning efficiency and effectiveness.

[0502] 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.

[0503] In this invention, the server includes means for evaluating an individual's cognitive characteristics, means for generating educational materials based on the evaluation results, and means for analyzing an individual's emotional state and adjusting the learning content accordingly. This makes it possible to provide learning materials optimized for each learner's learning characteristics in real time.

[0504] "Individual" refers to a specific learner, and the data collected includes their individual characteristics, emotional state, and other specific information.

[0505] "Cognitive characteristics" refer to the features related to intellectual activities, such as a learner's information processing ability, memory, and problem-solving ability.

[0506] "Means of evaluation" refer to methods and devices for measuring and analyzing learners' cognitive characteristics and learning outcomes.

[0507] "Educational materials" refer to teaching materials, assignments, and learning content provided to learners, and are used to achieve learning objectives.

[0508] "Emotional state" refers to the learner's psychological and physiological state, including elements such as stress, relaxation, and concentration.

[0509] "Analysis" refers to the process of understanding learners' characteristics and conditions using measured data, and then providing appropriate learning materials and support based on that information.

[0510] "Means of adjustment" refers to methods and techniques for modifying the content and difficulty level of educational materials according to the characteristics and circumstances of the learners.

[0511] This invention is a learning support system that optimizes learning content according to an individual's cognitive characteristics and emotional state. This system is mainly constructed using a server, terminals, and an emotion analysis engine.

[0512] The terminal, as the first device a user accesses, provides an interface for entering basic information. Through this terminal, users enter personal information such as their name, age, and learning objectives. Adaptive assessment tests are conducted on the terminal, collecting data to understand the user's cognitive characteristics. These tests record the user's reaction time and accuracy rate, and this data is transmitted to the server.

[0513] The server generates a user cognitive profile using a specific analysis algorithm based on data sent from the terminal. This profile includes the user's information processing ability, memory, and other cognitive characteristics. The server then utilizes a generative AI model to create educational materials based on this cognitive profile. In this process, prompts are input into the generative AI model, which selects high-intensity and low-intensity tasks tailored to the user.

[0514] The emotion analysis engine uses the device's camera and biosensors to collect and analyze the user's facial expressions and physical condition data in real time. Based on this emotion data, the server dynamically adjusts the learning content. For example, if the user shows signs of stress, the difficulty of the task is lowered, and if they are relaxed, more challenging content is provided.

[0515] As a concrete example, consider a case where a user is learning a new language. If the response time recorded by the device is long, the server prompts the generating AI with the message, "The current task is too difficult; please create and provide easier vocabulary questions." In this way, an optimized educational experience is provided for each user, improving learning efficiency.

[0516] An example of a prompt statement is as follows:

[0517] "The user's cognitive profile is as follows: Strengths are vocabulary memory, weaknesses are grammar comprehension. Please create learning materials based on this."

[0518] Thus, the present invention provides a learning environment adapted to each user, realizing educational support that meets individual learning needs.

[0519] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0520] Step 1:

[0521] Users access the system through a terminal and enter basic information. The terminal retrieves information such as the user's name, age, and learning objectives. The entered personal information is stored in a database and used for subsequent adaptive assessment tests.

[0522] Step 2:

[0523] The device presents the user with an adaptive assessment test. By answering this test, the user generates data on cognitive characteristics (e.g., reaction time and accuracy). The device receives the test results and sends the data to the server. Data processing is performed, including calculations of average reaction time and accuracy.

[0524] Step 3:

[0525] The server analyzes the received user test data and generates a cognitive profile. Inputs include reaction time and accuracy, and the output is a profile indicating the user's information processing ability. Statistical processing is performed here to clearly identify the user's strengths and weaknesses.

[0526] Step 4:

[0527] The server uses a generative AI model to create educational materials based on the user's cognitive profile. The server sends prompts to the generative AI model to generate customized tasks. The output is learning material optimized for the user's characteristics. Specifically, the prompt "Create tasks based on the user's cognitive profile" is sent, and the materials are generated.

[0528] Step 5:

[0529] The emotion analysis engine uses the device's sensors to analyze the user's biometric information and facial expressions. Based on the input data obtained (e.g., facial image, biosensor data), the emotional state is evaluated. The output is the user's emotional state (e.g., stress, relaxation), and this information is obtained using an analysis algorithm.

[0530] Step 6:

[0531] The server adapts and adjusts the learning content according to the user's emotional state. It receives emotional state data from an emotion analysis engine as input and outputs the result of adjusting the learning materials. For example, if stress is detected, the server switches to a simpler task.

[0532] Step 7:

[0533] The device continuously collects user response and sentiment data and sends it to the server. This includes data necessary to record the user's progress and adjust the learning plan. The data is analyzed in real time on the server, and feedback is provided to the user as output. The device operates according to a communication protocol to accurately transmit the acquired data to the server.

[0534] (Application Example 2)

[0535] 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."

[0536] In factory and other work environments, it is necessary to optimize both work efficiency and the psychological burden on workers simultaneously, taking into account the cognitive characteristics and emotional states of individual workers. Conventional systems only provide general instructions and procedures, making it difficult to adjust to individual characteristics and emotions, resulting in insufficient improvements in productivity and the work environment.

[0537] 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.

[0538] In this invention, the server includes means for evaluating an individual's cognitive characteristics, means for generating learning materials and work instructions based on the evaluation results, and means for detecting changes in emotional state in real time and individually adjusting work instructions. This enables efficient work instructions tailored to the worker's characteristics and dynamic adjustments to match their emotional state.

[0539] "Individual cognitive characteristics" refer to a profile that specifically shows the information processing abilities and strengths and weaknesses of each worker.

[0540] "Learning materials" refer to a collection of educational content and tasks generated based on the cognitive characteristics of the workers.

[0541] "Dynamic adjustment means" refers to a function that changes the content and difficulty level of the provided learning materials and work instructions in real time according to the work environment and learning progress.

[0542] "Optimizing learning effectiveness according to cognitive characteristics and emotional state" refers to a process for maximizing learning outcomes based on the individual characteristics and current emotional state of each worker.

[0543] "Methods for detecting changes in emotional state in real time" refers to technologies that instantly detect changes in emotions by analyzing the facial expressions and physical biometric data of workers.

[0544] "Means of individually adjusting work instructions" refers to methods for optimizing and providing work procedures and missions according to an individual's cognitive characteristics and real-time emotional state.

[0545] The system for implementing this invention is built using a server, a terminal, and an emotion engine. The server evaluates an individual's cognitive characteristics and generates optimized learning materials and work instructions based on the results. When a user inputs basic information through the terminal, an adaptive assessment test is conducted, and the server uses this data to generate a cognitive profile. This profile indicates information processing abilities and strengths and weaknesses in thinking.

[0546] The server uses a generative AI model to generate learning materials and work instructions based on this cognitive profile. This generation includes high-intensity tasks tailored to the user's strengths and low-intensity tasks addressing their weaknesses. The emotion engine analyzes the user's facial expressions and biometric information in real time to identify their emotional state. Based on this information, the server instantly adjusts the content according to the learning and work progress. For example, if the server detects that the user is stressed, it changes the task content to make it easier for the user.

[0547] The system utilizes smart glasses and emotion recognition sensors as hardware, and employs an emotion recognition model using TensorFlow and a backend server built with Flask as software. Data processing includes collecting and analyzing workers' cognitive characteristics and analyzing their emotional states in real time. The server analyzes this data in real time and dynamically adjusts work instructions.

[0548] For example, if the system detects that a worker is experiencing stress while performing specific machine maintenance, the procedure will be adjusted to be simpler and more user-friendly. An example of a prompt message might be: "Generate the following machine maintenance procedure based on worker 123's cognitive characteristics. Current emotional state: stressed."

[0549] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0550] Step 1:

[0551] The user enters basic information through the terminal. The terminal collects the entered personal information, past work data, and biometric data, and sends it to the server. This allows the server to receive the initial data necessary for evaluating cognitive characteristics.

[0552] Step 2:

[0553] The server analyzes the received data and conducts adaptive assessment tests. The analysis applies algorithms to identify information processing abilities and strengths and weaknesses in thinking. Based on this information, a cognitive profile is generated, identifying specific cognitive characteristics for each individual user.

[0554] Step 3:

[0555] The server uses a generative AI model to generate learning materials and work instructions based on cognitive profiles. Here, inputs and outputs are transformed from cognitive profiles into optimized learning materials. This prepares high-intensity and low-intensity tasks for each individual.

[0556] Step 4:

[0557] When a user begins learning or working, the emotion engine acquires the user's biometric and facial expression data in real time. Using this data, the emotion recognition model analyzes the user's current emotional state.

[0558] Step 5:

[0559] The server receives the results of the emotional state analysis and dynamically adjusts learning materials and work instructions. Based on the input emotional data and cognitive profile, the content is adjusted to be optimal for the user. For example, if stress is detected, adjustments such as lowering the difficulty of the task are made.

[0560] Step 6:

[0561] The device collects user response time, accuracy rate, and real-time sentiment data, and periodically sends it to the server. This data allows the server to monitor user progress and form a feedback loop for continuous improvement.

[0562] 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.

[0563] 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.

[0564] 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.

[0565] [Fourth Embodiment]

[0566] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0567] 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.

[0568] 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).

[0569] 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.

[0570] 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.

[0571] 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).

[0572] 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.

[0573] 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.

[0574] 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.

[0575] 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.

[0576] 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.

[0577] 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.

[0578] 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".

[0579] This invention is an AI system that streamlines learning according to an individual's cognitive characteristics. The system mainly consists of three entities: a server, a terminal, and a user, each playing a specific role.

[0580] First, the server provides a test to assess cognitive characteristics when a user first accesses the system. This test is designed to identify the user's cognitive strengths and weaknesses based on their input and responses. The test results are aggregated and analyzed on the server to generate individual user cognitive profiles.

[0581] Next, the server uses a generative AI to generate learning materials based on the user's cognitive profile. These materials consist of high-intensity and low-intensity tasks and are optimized according to the user's cognitive characteristics. Users with strong cognitive abilities are presented with complex problems, while those with weaker areas are presented with basic problems. For example, users with strong visual memory are given complex image recognition tasks, while users with weak logical thinking skills are presented with basic mathematical problems in a step-by-step manner.

[0582] The device functions as an interface for users to view learning materials and work on assignments. As the user progresses through the learning process, the device records reaction time and accuracy in real time and sends this data to a server. This data is collected for each user to support improvements in learning progress and assignment adaptation.

[0583] The server analyzes the received data and adjusts the content and difficulty level of the learning materials accordingly. This dynamic feedback loop makes it possible to optimize the learning experience according to the user's evolving cognitive characteristics. The feedback from the server is sent to the user's device and reflected in the next learning session.

[0584] This interactive cycle allows users to continuously receive learning tailored to their cognitive characteristics, effectively strengthening their foundational cognitive abilities.

[0585] The following describes the processing flow.

[0586] Step 1:

[0587] The user accesses the system for the first time and completes the registration process. They use a terminal to enter basic information and begin an adaptive assessment test to evaluate their cognitive characteristics.

[0588] Step 2:

[0589] The terminal continuously records the user's input and test responses, and sends this information to the server. The server receives this information, analyzes the user's response data, and generates a cognitive profile.

[0590] Step 3:

[0591] The server utilizes AI generation to prepare learning materials tailored to each user. High-load tasks are designed to align with the user's cognitive strengths, while low-load tasks are configured to complement areas where the user struggles.

[0592] Step 4:

[0593] Based on server instructions, the terminal provides learning materials optimized for the user. The user works on assignments through the terminal and enters their answers to each question.

[0594] Step 5:

[0595] The device collects user reaction time and accuracy during the learning process and sends this data to the server. This collection is done in real time, ensuring accurate data is recorded.

[0596] Step 6:

[0597] The server analyzes the received data in real time to assess the user's current cognitive characteristics and limitations. Based on this, it dynamically adjusts the learning materials and workload for the next learning session.

[0598] Step 7:

[0599] Based on feedback from the server, the terminal displays a plan for the next learning session to the user. The user then proceeds to the next stage of learning.

[0600] This series of steps allows users to continuously optimize their cognitive characteristics and learn more efficiently.

[0601] (Example 1)

[0602] 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".

[0603] Traditional learning systems struggle to provide learning support that adequately considers the diverse cognitive characteristics of individuals, and therefore fail to effectively utilize each learner's strengths and weaknesses. This problem can lead to the provision of suboptimal learning methods, potentially reducing learning effectiveness.

[0604] 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.

[0605] In this invention, the server includes means for evaluating an individual's cognitive characteristics, means for generating educational content based on the evaluation results, and means for dynamically adjusting the adaptability of the generated educational content. This makes it possible to provide an optimal learning method tailored to an individual's cognitive characteristics and maximize learning effectiveness.

[0606] "Cognitive characteristics" refer to the characteristics of an individual's ability to acquire, process, and remember information.

[0607] "Evaluation" refers to the quantitative or qualitative measurement and analysis of an individual's cognitive characteristics.

[0608] "Educational content" refers to learning materials and assignments prepared to improve learners' skills and abilities.

[0609] "Dynamic adjustment" means optimizing the content and difficulty level of learning materials and assignments in real time according to the learner's progress and performance.

[0610] "Learning effectiveness" refers to the results of improved knowledge and skill development gained through learning activities.

[0611] "Means" refers to the methods, devices, or systems used to achieve a specific purpose.

[0612] This invention is designed as an artificial intelligence system for optimizing learning based on an individual's cognitive characteristics. The system mainly consists of three entities: a server, a terminal, and a user, each playing a specific role.

[0613] The server first provides a test to assess cognitive characteristics through a web application when a user accesses the system. This test is created using JavaScript and records user input in real time. The recorded data is sent to the server, where data analysis libraries such as NumPy and Pandas are used to generate individual cognitive profiles.

[0614] The server creates educational content using a generative AI model based on the generated cognitive profile. Specifically, it prompts the AI ​​model (e.g., a natural language processing model) with the message, "Based on the user's cognitive profile, provide an image recognition task for people with strong visual memory." The generated educational content is then sent to the device in HTML or PDF format.

[0615] The device displays educational content sent from the server, allowing the user to access it. The user learns using the provided educational content, and their reaction time and accuracy are measured in real time using a JavaScript program and sent back to the server.

[0616] The server analyzes the user's learning data and uses Scikit-learn to evaluate learning progress. Based on this data, the content and difficulty level of the educational material are dynamically adjusted. The adjusted educational content is reflected on the device in the next learning session, optimizing the learning experience according to the user's evolving cognitive characteristics.

[0617] This allows users to effectively improve their skills and knowledge within a learning environment optimized for their own cognitive characteristics.

[0618] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0619] Step 1:

[0620] The server provides a test to assess cognitive characteristics when a user accesses the system. Users answer the test through their browser, and their input data is recorded in real time by JavaScript. This data serves as input for evaluating the user's individual cognitive characteristics. The recorded data is sent to the server, where it is analyzed using statistical methods to obtain an output result: the user's cognitive profile.

[0621] Step 2:

[0622] The server uses the cognitive profile to request the generative AI model to generate educational content. Specifically, it inputs the prompt "Based on the user's cognitive profile, please provide an image recognition task for people with strong visual memory" into the generative AI model. Based on this input, the model outputs specific educational content. In this process, data such as complex images and step-by-step problems are generated.

[0623] Step 3:

[0624] The server sends the generated educational content to the device. The device receives the content and displays it in a web browser. During this process, the content is converted to HTML or PDF format. The user works on tasks while viewing the content on the device, and the response information obtained (e.g., response time and accuracy rate) is recorded using JavaScript.

[0625] Step 4:

[0626] The learning data collected by the device is sent to the server, which analyzes the data. Progress is evaluated using tools like Scikit-learn, and learning is quantitatively assessed. Based on this input data, the content and difficulty level of the educational material are adjusted. The adjustment results are delivered to the device in the next learning session and output as new applied content.

[0627] Step 5:

[0628] The server continuously optimizes dynamically adjusted educational content for each user. This cycle is repeated to adapt to the user's evolving cognitive characteristics and continuously maximize learning effectiveness. The input is improved learning data, and the output is user-specific, optimized educational content.

[0629] (Application Example 1)

[0630] 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".

[0631] By enabling the provision of information tailored to individual cognitive characteristics, it is necessary to promote the understanding and utilization of information optimally for each user, thereby improving the effectiveness of personalized learning and product selection. Conventional systems do not adequately provide information based on individual cognitive characteristics, and there is a need to improve the quality of the user experience.

[0632] 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.

[0633] In this invention, the server includes means for evaluating an individual's cognitive characteristics, means for generating learning materials based on the evaluation results, means for dynamically adjusting the adaptability of the generated learning materials, and means for personalizing the information provided based on the individual's cognitive characteristics. This enables the provision of information optimized for the individual, supporting effective learning and product selection.

[0634] "Methods for evaluating an individual's cognitive characteristics" refer to the process of conducting tests to identify a user's cognitive strengths and weaknesses, and then generating a cognitive profile based on the results.

[0635] "Means for generating learning materials based on evaluation results" refers to a process of creating and providing optimal learning materials tailored to each user's cognitive characteristics using a generation AI.

[0636] "Means for dynamically adjusting the adaptability of generated learning materials" refers to a process that appropriately changes the content and difficulty level of the learning materials according to the learning progress, providing materials that match the user's level of understanding and progress.

[0637] "Methods for optimizing learning effectiveness according to cognitive characteristics" refer to the process of presenting learning materials in a way that is most suitable for the user's characteristics and forming a feedback loop to promote effective learning.

[0638] "Methods for personalizing information based on individual cognitive characteristics" refers to the process of providing information in a format that is optimal for each user, such as users with strong visual memory or those who excel at logical thinking, by specializing and providing information according to the user's characteristics.

[0639] The system that implements this application consists of three entities: a server, a terminal, and a user. The server provides a test to evaluate the user's cognitive characteristics and generates individual cognitive profiles by aggregating and analyzing the user's input data. Based on the evaluation results, a generative AI is used to automatically generate learning materials and information content optimized for the user. The learning materials are customized according to the user's cognitive characteristics and are delivered using a variety of media.

[0640] The device displays the learning materials and information content, functioning as an interface for the user to engage with them. It also records reaction time and accuracy as the user progresses, providing feedback to the server. This feedback data is used by the server to dynamically adjust the content and difficulty level of the learning materials.

[0641] The server optimizes information delivery according to the user's evolving cognitive characteristics, continuously providing a personalized learning experience. In this way, it supports users' effective learning and product selection through the presentation of information. For example, it can present product descriptions using images and videos to users with strong visual memory, and provide detailed data and specifications to users who excel at logical thinking.

[0642] An example of a prompt for a generating AI is: "How can product information be personalized based on the user's cognitive characteristics? In particular, consider including images and video content for users with strong visual memory, or technical specifications for users with strong logical thinking, to enhance purchasing tendencies."

[0643] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0644] Step 1:

[0645] The server provides the user with a test to assess their cognitive characteristics. The user answers this test and sends the input data to the server via the terminal. The input in this step is the user's test answers, and the output is the data necessary to generate the user's cognitive profile. The server analyzes the input data to identify the indicators that constitute the user's cognitive characteristics.

[0646] Step 2:

[0647] The server uses a generative AI model to generate learning materials and informational content based on the user's cognitive characteristics. This process generates instructions for the AI ​​model using prompts, creating materials optimized for the user. The input is the generated cognitive profile, and the output is personalized learning materials. Specifically, for users with strong visual memory, image-centric content is selected.

[0648] Step 3:

[0649] The device presents the generated learning materials to the user and provides an interface for progressing through the learning process. The user interacts with the materials through the device while working at their own pace. The input in this step is the generated learning materials, and the output is the user's learning progress (accuracy rate and reaction time). The device records this information and provides a learning experience.

[0650] Step 4:

[0651] The terminal sends feedback to the server regarding the user's learning progress. Using this data, the server adjusts the difficulty level and content of the learning materials. The input to this process is the user's learning progress data, and the output is the optimized content of the next learning material provided. The server dynamically analyzes the data and updates the learning plan to suit each individual user.

[0652] Step 5:

[0653] The server sends the updated content to the terminal and provides it to the user in the next learning session. The user receives the new materials and continues learning. The input for this step is the adjusted material data, and the output is the provision of new materials to maximize the user's learning efficiency. The server provides continuous learning support through content optimization.

[0654] 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.

[0655] This invention is an AI learning system that takes into account the user's cognitive characteristics and emotional state. This system is built using a server, a terminal, and an emotion engine, with each component playing a specific role to optimize the user's learning experience.

[0656] First, the user accesses the system and enters basic information through their device. An adaptive assessment test is then conducted, and the server generates a cognitive profile of the user based on the collected data. This profile specifically outlines the user's information processing abilities, strengths, and weaknesses.

[0657] Next, using generative AI, the server creates learning materials based on the user's cognitive profile. These materials include high-intensity tasks tailored to the user's strengths and low-intensity tasks addressing their weaknesses. Furthermore, an emotion engine analyzes the user's facial expressions and biometric information in real time to recognize their emotional state. This allows the content to be instantly adjusted according to the learning progress.

[0658] For example, if the emotion engine detects stress or frustration while a user is working on a difficult task, the server will immediately change the task to one that is easier for the user. Conversely, if the system determines that the user is relaxed, it will increase the difficulty of the task and provide appropriate stimulation to enhance their motivation to learn.

[0659] During a learning session, the device records user input data (such as reaction time and accuracy) and sentiment data, and continuously sends this data to the server. The server analyzes this data in real time, evaluates the user's learning progress, and adjusts the overall system accordingly.

[0660] This feedback loop ensures that users always receive a learning experience optimized for their own cognitive characteristics and emotional state. This system reduces user stress and improves learning efficiency, thereby enhancing learning ability.

[0661] The following describes the processing flow.

[0662] Step 1:

[0663] Users log in to the system and complete initial registration. They enter their personal information and learning objectives via their device.

[0664] Step 2:

[0665] The device administers an adaptive assessment test to the user and records their responses to the questions. The test is designed to identify the user's cognitive characteristics.

[0666] Step 3:

[0667] The server analyzes the response data sent from the terminal and generates a cognitive profile of the user. This profile clearly identifies the user's strengths and areas that need improvement.

[0668] Step 4:

[0669] The server uses generative AI to create learning materials based on the user's cognitive profile. The materials are a balanced mix of high-intensity and low-intensity tasks.

[0670] Step 5:

[0671] The emotion engine uses the device's camera and sensors to analyze the user's facial expressions and biometric data, identifying their emotional state in real time.

[0672] Step 6:

[0673] Users engage with learning materials provided by the server via their devices. Throughout the assignment, the emotion engine continuously monitors the user's emotional changes.

[0674] Step 7:

[0675] The device collects user reaction time, accuracy rate, and sentiment data, and sends this data to the server.

[0676] Step 8:

[0677] The server analyzes the collected data and dynamically adjusts the content and difficulty level of the learning materials as needed. For example, if the server determines that the user is experiencing stress, it will change the task to something more relaxing.

[0678] Step 9:

[0679] The server sends the adjustment results to the terminal and instructs the user on the next learning stage. The user continues to work on new challenges.

[0680] This series of steps allows users to receive learning tailored to their cognitive characteristics and emotional state, enabling them to effectively improve their abilities.

[0681] (Example 2)

[0682] 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".

[0683] Modern educational methods often employ a uniform learning approach that disregards individual cognitive characteristics and emotional states. As a result, learners may experience stress and reduced learning effectiveness. This invention aims to provide an optimized educational experience for each learner, thereby improving learning efficiency and effectiveness.

[0684] 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.

[0685] In this invention, the server includes means for evaluating an individual's cognitive characteristics, means for generating educational materials based on the evaluation results, and means for analyzing an individual's emotional state and adjusting the learning content accordingly. This makes it possible to provide learning materials optimized for each learner's learning characteristics in real time.

[0686] "Individual" refers to a specific learner, and the data collected includes their individual characteristics, emotional state, and other specific information.

[0687] "Cognitive characteristics" refer to the features related to intellectual activities, such as a learner's information processing ability, memory, and problem-solving ability.

[0688] "Means of evaluation" refer to methods and devices for measuring and analyzing learners' cognitive characteristics and learning outcomes.

[0689] "Educational materials" refer to teaching materials, assignments, and learning content provided to learners, and are used to achieve learning objectives.

[0690] "Emotional state" refers to the learner's psychological and physiological state, including elements such as stress, relaxation, and concentration.

[0691] "Analysis" refers to the process of understanding learners' characteristics and conditions using measured data, and then providing appropriate learning materials and support based on that information.

[0692] "Means of adjustment" refers to methods and techniques for modifying the content and difficulty level of educational materials according to the characteristics and circumstances of the learners.

[0693] This invention is a learning support system that optimizes learning content according to an individual's cognitive characteristics and emotional state. This system is mainly constructed using a server, terminals, and an emotion analysis engine.

[0694] The terminal, as the first device a user accesses, provides an interface for entering basic information. Through this terminal, users enter personal information such as their name, age, and learning objectives. Adaptive assessment tests are conducted on the terminal, collecting data to understand the user's cognitive characteristics. These tests record the user's reaction time and accuracy rate, and this data is transmitted to the server.

[0695] The server generates a user cognitive profile using a specific analysis algorithm based on data sent from the terminal. This profile includes the user's information processing ability, memory, and other cognitive characteristics. The server then utilizes a generative AI model to create educational materials based on this cognitive profile. In this process, prompts are input into the generative AI model, which selects high-intensity and low-intensity tasks tailored to the user.

[0696] The emotion analysis engine uses the device's camera and biosensors to collect and analyze the user's facial expressions and physical condition data in real time. Based on this emotion data, the server dynamically adjusts the learning content. For example, if the user shows signs of stress, the difficulty of the task is lowered, and if they are relaxed, more challenging content is provided.

[0697] As a concrete example, consider a case where a user is learning a new language. If the response time recorded by the device is long, the server prompts the generating AI with the message, "The current task is too difficult; please create and provide easier vocabulary questions." In this way, an optimized educational experience is provided for each user, improving learning efficiency.

[0698] An example of a prompt statement is as follows:

[0699] "The user's cognitive profile is as follows: Strengths are vocabulary memory, weaknesses are grammar comprehension. Please create learning materials based on this."

[0700] Thus, the present invention provides a learning environment adapted to each user, realizing educational support that meets individual learning needs.

[0701] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0702] Step 1:

[0703] Users access the system through a terminal and enter basic information. The terminal retrieves information such as the user's name, age, and learning objectives. The entered personal information is stored in a database and used for subsequent adaptive assessment tests.

[0704] Step 2:

[0705] The device presents the user with an adaptive assessment test. By answering this test, the user generates data on cognitive characteristics (e.g., reaction time and accuracy). The device receives the test results and sends the data to the server. Data processing is performed, including calculations of average reaction time and accuracy.

[0706] Step 3:

[0707] The server analyzes the received user test data and generates a cognitive profile. Inputs include reaction time and accuracy, and the output is a profile indicating the user's information processing ability. Statistical processing is performed here to clearly identify the user's strengths and weaknesses.

[0708] Step 4:

[0709] The server uses a generative AI model to create educational materials based on the user's cognitive profile. The server sends prompts to the generative AI model to generate customized tasks. The output is learning material optimized for the user's characteristics. Specifically, the prompt "Create tasks based on the user's cognitive profile" is sent, and the materials are generated.

[0710] Step 5:

[0711] The emotion analysis engine uses the device's sensors to analyze the user's biometric information and facial expressions. Based on the input data obtained (e.g., facial image, biosensor data), the emotional state is evaluated. The output is the user's emotional state (e.g., stress, relaxation), and this information is obtained using an analysis algorithm.

[0712] Step 6:

[0713] The server adapts and adjusts the learning content according to the user's emotional state. It receives emotional state data from an emotion analysis engine as input and outputs the result of adjusting the learning materials. For example, if stress is detected, the server switches to a simpler task.

[0714] Step 7:

[0715] The device continuously collects user response and sentiment data and sends it to the server. This includes data necessary to record the user's progress and adjust the learning plan. The data is analyzed in real time on the server, and feedback is provided to the user as output. The device operates according to a communication protocol to accurately transmit the acquired data to the server.

[0716] (Application Example 2)

[0717] 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".

[0718] In factory and other work environments, it is necessary to optimize both work efficiency and the psychological burden on workers simultaneously, taking into account the cognitive characteristics and emotional states of individual workers. Conventional systems only provide general instructions and procedures, making it difficult to adjust to individual characteristics and emotions, resulting in insufficient improvements in productivity and the work environment.

[0719] 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.

[0720] In this invention, the server includes means for evaluating an individual's cognitive characteristics, means for generating learning materials and work instructions based on the evaluation results, and means for detecting changes in emotional state in real time and individually adjusting work instructions. This enables efficient work instructions tailored to the worker's characteristics and dynamic adjustments to match their emotional state.

[0721] "Individual cognitive characteristics" refer to a profile that specifically shows the information processing abilities and strengths and weaknesses of each worker.

[0722] "Learning materials" refer to a collection of educational content and tasks generated based on the cognitive characteristics of the workers.

[0723] "Dynamic adjustment means" refers to a function that changes the content and difficulty level of the provided learning materials and work instructions in real time according to the work environment and learning progress.

[0724] "Optimizing learning effectiveness according to cognitive characteristics and emotional state" refers to a process for maximizing learning outcomes based on the individual characteristics and current emotional state of each worker.

[0725] "Methods for detecting changes in emotional state in real time" refers to technologies that instantly detect changes in emotions by analyzing the facial expressions and physical biometric data of workers.

[0726] "Means of individually adjusting work instructions" refers to methods for optimizing and providing work procedures and missions according to an individual's cognitive characteristics and real-time emotional state.

[0727] The system for implementing this invention is built using a server, a terminal, and an emotion engine. The server evaluates an individual's cognitive characteristics and generates optimized learning materials and work instructions based on the results. When a user inputs basic information through the terminal, an adaptive assessment test is conducted, and the server uses this data to generate a cognitive profile. This profile indicates information processing abilities and strengths and weaknesses in thinking.

[0728] The server uses a generative AI model to generate learning materials and work instructions based on this cognitive profile. This generation includes high-intensity tasks tailored to the user's strengths and low-intensity tasks addressing their weaknesses. The emotion engine analyzes the user's facial expressions and biometric information in real time to identify their emotional state. Based on this information, the server instantly adjusts the content according to the learning and work progress. For example, if the server detects that the user is stressed, it changes the task content to make it easier for the user.

[0729] The system utilizes smart glasses and emotion recognition sensors as hardware, and employs an emotion recognition model using TensorFlow and a backend server built with Flask as software. Data processing includes collecting and analyzing workers' cognitive characteristics and analyzing their emotional states in real time. The server analyzes this data in real time and dynamically adjusts work instructions.

[0730] For example, if the system detects that a worker is experiencing stress while performing specific machine maintenance, the procedure will be adjusted to be simpler and more user-friendly. An example of a prompt message might be: "Generate the following machine maintenance procedure based on worker 123's cognitive characteristics. Current emotional state: stressed."

[0731] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0732] Step 1:

[0733] The user enters basic information through the terminal. The terminal collects the entered personal information, past work data, and biometric data, and sends it to the server. This allows the server to receive the initial data necessary for evaluating cognitive characteristics.

[0734] Step 2:

[0735] The server analyzes the received data and conducts adaptive assessment tests. The analysis applies algorithms to identify information processing abilities and strengths and weaknesses in thinking. Based on this information, a cognitive profile is generated, identifying specific cognitive characteristics for each individual user.

[0736] Step 3:

[0737] The server uses a generative AI model to generate learning materials and work instructions based on cognitive profiles. Here, inputs and outputs are transformed from cognitive profiles into optimized learning materials. This prepares high-intensity and low-intensity tasks for each individual.

[0738] Step 4:

[0739] When a user begins learning or working, the emotion engine acquires the user's biometric and facial expression data in real time. Using this data, the emotion recognition model analyzes the user's current emotional state.

[0740] Step 5:

[0741] The server receives the results of the emotional state analysis and dynamically adjusts learning materials and work instructions. Based on the input emotional data and cognitive profile, the content is adjusted to be optimal for the user. For example, if stress is detected, adjustments such as lowering the difficulty of the task are made.

[0742] Step 6:

[0743] The device collects user response time, accuracy rate, and real-time sentiment data, and periodically sends it to the server. This data allows the server to monitor user progress and form a feedback loop for continuous improvement.

[0744] 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.

[0745] 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.

[0746] 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.

[0747] 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.

[0748] 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.

[0749] 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.

[0750] 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.

[0751] 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.

[0752] 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."

[0753] 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.

[0754] 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.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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.

[0762] 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.

[0763] 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.

[0764] 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.

[0765] The following is further disclosed regarding the embodiments described above.

[0766] (Claim 1)

[0767] Methods for evaluating an individual's cognitive characteristics,

[0768] A means for generating learning materials based on evaluation results,

[0769] A means for dynamically adjusting the adaptability of the generated learning materials,

[0770] A means to optimize learning effectiveness according to cognitive characteristics,

[0771] A system that includes this.

[0772] (Claim 2)

[0773] The system according to claim 1, comprising means for monitoring an individual's reaction time and accuracy rate.

[0774] (Claim 3)

[0775] The system according to claim 1, comprising means for providing the generated learning materials to a user.

[0776] "Example 1"

[0777] (Claim 1)

[0778] Methods for evaluating an individual's cognitive characteristics,

[0779] A means for generating educational content based on evaluation results,

[0780] A means for dynamically adjusting the adaptability of generated educational content,

[0781] A means to optimize learning effectiveness according to cognitive characteristics,

[0782] A device for recording efforts toward educational content,

[0783] A means of adjusting educational content based on recorded data,

[0784] A system that includes this.

[0785] (Claim 2)

[0786] The system according to claim 1, comprising means for monitoring an individual's reaction time and accuracy rate.

[0787] (Claim 3)

[0788] The system according to claim 1, comprising means for providing the generated educational content to a user.

[0789] "Application Example 1"

[0790] (Claim 1)

[0791] Methods for evaluating an individual's cognitive characteristics,

[0792] A means for generating learning materials based on evaluation results,

[0793] A means for dynamically adjusting the adaptability of the generated learning materials,

[0794] A means to optimize learning effectiveness according to cognitive characteristics,

[0795] Means for personalizing the content of information provided based on individual cognitive characteristics,

[0796] A system that includes this.

[0797] (Claim 2)

[0798] The system according to claim 1, comprising means for monitoring an individual's reaction time and accuracy rate.

[0799] (Claim 3)

[0800] The system according to claim 1, comprising means for providing the generated learning materials to a user.

[0801] "Example 2 of combining an emotion engine"

[0802] (Claim 1)

[0803] Methods for evaluating an individual's cognitive characteristics,

[0804] A means for generating educational materials based on evaluation results,

[0805] A means for dynamically adjusting the adaptability of the generated educational materials,

[0806] A means to optimize learning effectiveness according to cognitive characteristics,

[0807] A means of analyzing an individual's emotional state and adjusting the learning content based on that,

[0808] A system that includes this.

[0809] (Claim 2)

[0810] The system according to claim 1, comprising means for monitoring an individual's reaction time and accuracy rate.

[0811] (Claim 3)

[0812] The system according to claim 1, comprising means for providing the generated educational materials to a user.

[0813] "Application example 2 when combining with an emotional engine"

[0814] (Claim 1)

[0815] Methods for evaluating an individual's cognitive characteristics,

[0816] A means for generating learning materials based on evaluation results,

[0817] A means for dynamically adjusting the adaptability of the generated learning materials,

[0818] A means for optimizing learning effects according to cognitive characteristics and emotional states,

[0819] A means to detect changes in emotional state in real time and adjust work instructions individually,

[0820] A system that includes this.

[0821] (Claim 2)

[0822] The system according to claim 1, comprising means for monitoring an individual's reaction time and accuracy rate, and means for analyzing their emotional state.

[0823] (Claim 3)

[0824] The system according to claim 1, comprising means for providing the user with generated learning materials and individual work instructions. [Explanation of Symbols]

[0825] 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. Methods for evaluating an individual's cognitive characteristics, A means for generating learning materials based on evaluation results, A means for dynamically adjusting the adaptability of the generated learning materials, A means to optimize learning effectiveness according to cognitive characteristics, A system that includes this.

2. The system according to claim 1, comprising means for monitoring an individual's reaction time and accuracy rate.

3. The system according to claim 1, comprising means for providing the generated learning materials to a user.

Images