system

Abstract

Provide a system. 【Solution means】 A device for collecting the learning history and achievement data of users, A device for analyzing the collected data to identify the cognitive ability and learning method of users, A device for generating an optimal education plan based on the identified learning method and cognitive ability, A device for automatically creating training tasks focused on the weak areas of users, A connection device for providing the generated education plan and training tasks to users, A device for collecting the learning results from users as regression information, analyzing the regression information, and reflecting it in the next education plan, A device for selecting teaching materials for enhancing and improving learning using AI technology and providing knowledge suitable for users, A system including the above.

Description

Technical Field

[0004] , , , ,

[0005] , , , , ,

[0003] , ,

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional learning method, it is difficult to provide a personalized learning plan tailored to individual learners, and it is impossible to accurately grasp individual academic abilities and learning styles. As a result, there has been a problem that the learning effect is often not maximized. In addition, since it is costly to receive individual guidance, such services have been difficult to use for many learners. There is a need to solve these problems and widely provide effective and economical learning support.

Means for Solving the Problems

[0005] This invention provides an analytical means for collecting a user's past learning data and identifying their academic ability and learning style based on that data. Furthermore, by generating an optimal learning plan based on the analysis results, it is possible to show each user an appropriate learning path. In addition, it automatically generates practice problems to focus on improving the user's weak areas, thereby supporting an overall improvement in their abilities. Moreover, it has a means to provide a continuous and effective learning environment by reflecting feedback on learning results in real time and utilizing it in the next learning plan. As a result, high-quality learning support can be realized at a low cost without relying on individual tutoring.

[0006] A "user" is an individual who uses a learning system to improve their academic abilities.

[0007] "Learning history" refers to a collection of data about the learning content, achievements, and time spent by a user in the past.

[0008] "Performance data" refers to information that shows the user's performance and level of understanding during the learning process.

[0009] "Analysis" refers to the process of analyzing collected data to identify user characteristics, learning styles, strengths, and weaknesses.

[0010] "Academic ability" refers to a comprehensive evaluation of a user's knowledge and understanding in a specific academic field.

[0011] A "learning plan" is a plan that outlines specific learning content and sequence, designed to contribute to improving the user's academic performance.

[0012] "Practice exercises" are a collection of specific tasks and problems provided to check the user's learning progress and improve their skills.

[0013] "Interface means" refers to mechanisms and elements related to the user interface that allow a user to access and operate a learning system.

[0014] "Feedback" refers to information and responses used to evaluate a user's learning results and to modify their next learning method or plan based on those results. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] 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.

[0019] 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.

[0020] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention is implemented within an integrated system that includes a user terminal, a server for processing information, and an interface. Users access the learning system using a terminal such as a smartphone or tablet and begin their individual learning experience. The program's processing is described below in natural language.

[0037] First, the user inputs their learning history and performance data into their device, and this information is sent to the server. The device formats the data appropriately and transmits it using a secure communication protocol to ensure data consistency and security.

[0038] The server analyzes the received data and visualizes the user's academic ability and learning style. The analytical techniques used here include machine learning algorithms and data mining methods. This clearly identifies the user's strengths and weaknesses.

[0039] Based on the analysis results, the server generates a learning plan that best suits the user's learning goals. This plan is designed to leverage the user's strengths while overcoming their weaknesses and includes specific learning materials and practice exercises.

[0040] The server also automatically generates practice problems that focus on areas where the user struggles. These problems are structured to gradually increase in complexity and are provided with explanations. By working through them, users can gradually improve their skills.

[0041] The generated learning plans and practice exercises are provided to the user via the device. Users access these through the interface and use them for daily learning. The interface is designed to be intuitive and enhance the user experience.

[0042] Learning progress and results are periodically sent from the device to the server. The server analyzes this data and generates feedback tailored to the user's situation. This feedback is then incorporated into the next learning plan, enabling continuous learning improvement.

[0043] This invention enables a specific operational model in which users can enjoy a learning experience that is optimal for them, without needing individualized instruction.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The user uses the device to input their past learning history and current learning goals. The device receives this data, formats it, and prepares it for processing.

[0047] Step 2:

[0048] The terminal sends the data entered by the user to the server. A secure communication protocol is used for transmission, ensuring the security and integrity of the data.

[0049] Step 3:

[0050] The server analyzes the user's past learning history and academic ability based on the received data. It uses machine learning algorithms to identify the user's strengths and weaknesses and evaluate their learning style.

[0051] Step 4:

[0052] Based on the analysis results, the server generates a learning plan optimized for the user's current learning needs. The plan includes specific learning materials and exercises, customized to match the user's learning objectives.

[0053] Step 5:

[0054] The server automatically generates practice problems to address the user's areas of weakness. These problems include gradual difficulty adjustments and detailed explanations, designed to make it easier for users to understand the material.

[0055] Step 6:

[0056] The terminal presents the user with a learning plan and practice problems received from the server. The user can then use the provided information to carry out their daily studies.

[0057] Step 7:

[0058] As users progress through their learning, they input their learning progress and practice problem results into their device. The device collects this information and continuously transmits it to the server.

[0059] Step 8:

[0060] The server analyzes the submitted learning results and generates feedback for the user. This feedback is incorporated into the next learning plan and used to continuously improve the user's learning.

[0061] (Example 1)

[0062] 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."

[0063] Traditional learning systems suffer from a lack of adequate mechanisms for efficiently collecting individual users' learning history and performance data, and for providing optimal learning plans based on that data. Furthermore, the difficulty in automatically generating and providing practice problems tailored to users' weak areas in real time makes personalized learning optimization challenging. Additionally, there is a lack of mechanisms for appropriately reflecting feedback based on learning progress.

[0064] 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.

[0065] In this invention, the server includes means for collecting user history information and performance information, means for analyzing the collected information to identify the user's abilities and learning tendencies, and means for generating an optimal plan based on the identified learning tendencies and abilities. As a result, users can receive an optimal learning plan based on their individual learning history, practice problems that focus on areas of weakness, and feedback that is tailored to their learning progress.

[0066] "User" refers to an individual who uses the system to learn.

[0067] "History information" refers to records of learning activities that users have engaged in in the past.

[0068] "Performance information" refers to data that shows the user's learning outcomes and evaluations.

[0069] "Collection" refers to the process of gathering information, with the aim of storing it in a database.

[0070] "Analysis" refers to the process of analyzing collected information using appropriate methods to obtain useful insights.

[0071] "Ability" refers to an indicator that shows the user's academic capabilities.

[0072] "Learning tendencies" refer to the characteristics and behavioral patterns of users in their learning.

[0073] A "plan" refers to a series of learning activities designed to achieve the user's learning goals.

[0074] A "weakness area" refers to a learning area in which a user is relatively less proficient compared to other areas.

[0075] "Assignments" refer to problems and practical activities that users should engage in during their learning process.

[0076] "Display means" refers to an interface that allows users to visually confirm the generated information.

[0077] "Results information" refers to report data that shows the results of the user's learning activities.

[0078] "Correction" refers to the process of implementing improvements for the user's next learning activity.

[0079] A "communication protocol" refers to the procedures and rules necessary for sending and receiving digital information.

[0080] "Information device" refers to electronic equipment used for storing, processing, and transferring data.

[0081] "Notification" refers to the act of transmitting generated information to the user.

[0082] This invention provides a system for offering personalized learning experiences, in which a user-facing terminal and a server that processes information work in conjunction. Users input their history and performance information into the terminal. This is done using a dedicated application for smartphones and tablets, allowing users to easily input information through devices they use on a daily basis.

[0083] The terminal formats the entered information into an appropriate format and securely transmits it to the server using the SSL protocol. The server analyzes the entered data using an analysis system built with a programming language such as Python. Here, machine learning algorithms and data mining techniques are utilized to identify the user's abilities and learning tendencies, and to understand their strengths and weaknesses.

[0084] Based on the analysis results, the server uses a generative AI model to create an optimal learning plan for the user. Additionally, practice problems tailored to the user's weak areas are automatically generated. These generation processes utilize reinforcement learning algorithms, enabling step-by-step task setting according to the user's progress.

[0085] For example, for a user who struggles with differential and integral calculus, the server provides practice problems and explanations specifically tailored to that area. This makes it easier for the user to overcome their specific weaknesses.

[0086] These learning plans and exercises are presented to the user visually through the device's interface. The intuitively designed interface allows users to easily progress through their learning. Learning results and progress data are periodically sent to the server and incorporated as feedback for the next learning plan.

[0087] As described above, the present invention provides an individualized learning experience that maximizes the user's learning performance.

[0088] Example of a prompt:

[0089] "Use a generative AI model to create a learning plan for students who struggle with differential and integral calculus. Include specific practice problems and explanatory materials."

[0090] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0091] Step 1:

[0092] The user enters history information and performance information.

[0093] Users input data such as past test results, study time, and self-assessments using a dedicated smartphone application. The input data is converted into an appropriate data format, such as JSON. This prepares the input data for transmission to the server.

[0094] Step 2:

[0095] The device sends data to the server.

[0096] The terminal sends the converted data to the server using the SSL communication protocol. This step ensures data consistency and security. The data sent by the terminal is stored in the server's database.

[0097] Step 3:

[0098] The server analyzes the data.

[0099] The server uses a Python®-based machine learning library to analyze the received data. Specifically, it employs clustering techniques to understand learning trends and classification algorithms to identify strengths and weaknesses. The analysis results clarify the learning characteristics of each user, which then forms the basis for the next step.

[0100] Step 4:

[0101] The server generates a training plan.

[0102] Based on the analysis results, the server uses a generated AI model to create an optimal learning plan for the user. In this step, reinforcement learning algorithms are used to select learning materials and tasks that match the user's goals. As a result, an individualized learning plan is output.

[0103] Step 5:

[0104] The server automatically generates practice problems.

[0105] The server automatically generates practice problem sets that focus on areas of particular difficulty. Hints and explanations are added sequentially to the problems to help resolve any questions. This output is then provided to the user in the next step.

[0106] Step 6:

[0107] The device provides information to the user.

[0108] The device displays the generated learning plan and practice problems in the user interface. A notification function informs the user when new learning materials are available. The user can progress through the learning process based on the provided information via an intuitively operable app.

[0109] Step 7:

[0110] The user inputs the learning results, and the device sends them to the server.

[0111] Users input the results and progress of their learning activities into their terminal. The entered information is formatted and sent to the server. This data transmission allows the server to receive important information that can be used to plan the next learning session.

[0112] Step 8:

[0113] The server evaluates the progress and provides feedback.

[0114] The server evaluates progress based on the received learning results. This process includes data analysis and comparison. The evaluation results are used as material for adjustments in the next learning plan and are displayed as feedback on the device. This continuous process allows users to feel the effects of their learning and continuously improve themselves.

[0115] (Application Example 1)

[0116] 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."

[0117] In modern education, it is necessary to provide learning experiences tailored to each individual learner, but this is difficult to achieve with traditional methods. Furthermore, it is essential to accurately identify learners' strengths and weaknesses and quickly provide optimal educational plans based on that information. Providing flexible, real-time feedback that matches learning progress is also a crucial challenge.

[0118] 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.

[0119] In this invention, the server includes means for collecting and analyzing the user's learning history and performance data, means for generating an educational plan based on identified learning methods and cognitive abilities, and means for providing knowledge tailored to the user using AI technology. This enables the provision of a learning experience optimized for each individual learner and effective feedback.

[0120] "Learning history" refers to the learning activities a user has undertaken and the records thereof.

[0121] "Performance data" refers to information that shows the results and performance obtained through user learning.

[0122] "Cognitive ability" refers to a user's ability and tendencies regarding understanding and problem-solving.

[0123] "Learning method" refers to the techniques and styles that users employ when progressing through their learning process.

[0124] An "educational plan" is a lesson plan designed to streamline the user's learning process and bring them closer to achieving their goals.

[0125] A "weakness area" refers to an academic field or topic that the user finds difficult to understand.

[0126] "Training exercises" are exercises or problem sets designed to improve specific skills or knowledge.

[0127] A "connection device" is a device that provides an interface for users to access digital learning content.

[0128] "Return information" refers to the results and feedback collected after a user's learning session, which are then incorporated into their next learning plan.

[0129] "AI technology" refers to technologies that use artificial intelligence methods to perform data analysis and problem solving.

[0130] "Knowledge provision" refers to the act of providing users with the information and learning materials they need for their studies.

[0131] A "generative AI model" is a model that uses AI to generate new data and information.

[0132] A "prompt statement" is a phrase used to give instructions to an AI or training model.

[0133] In the system implementing this invention, an integrated platform is constructed by fusing the user's terminal, a server, and an AI-based interface. Users access the learning support platform via a smartphone or tablet and input their learning history and achievement data. This data is transmitted to the server via a secure protocol.

[0134] The server uses AI technology to analyze the user's cognitive abilities and learning methods based on the received data. This involves a generative AI model, performing advanced calculations and data processing to generate the most suitable educational plan for the user. The educational plan includes training tasks designed to improve specific skills. These training tasks are automatically generated by AI technology based on the user's weak areas, and their difficulty level is adjusted in stages.

[0135] The generated educational plan and training tasks are provided to the user's device, and the learning activity progresses. Through the connected device, the user intuitively interacts with this content and continues learning. At the end of learning or periodically thereafter, the user's learning results are sent to the server as feedback information. The server re-analyzes this feedback information, generates feedback tailored to the user, and incorporates it into the next learning plan.

[0136] As a concrete example, a student aiming for university entrance exams uses this system to receive personalized learning materials to further strengthen their strong point, mathematics, and improve their weak point, English. The feedback provided by the server includes the message, "You are on track towards your next goal." An example of a prompt used in the generating AI model is, "Generate an optimal learning plan based on the user's learning history. Identify strengths and weaknesses and suggest appropriate learning materials and practice problems."

[0137] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0138] Step 1:

[0139] Users input their learning history and achievement data using their own devices. This input data is formatted appropriately by the device and sent to the server using a secure communication protocol.

[0140] Step 2:

[0141] The server analyzes the received data. Using a generative AI model, it processes the data to identify cognitive abilities and learning methods. Specifically, it analyzes each data point and applies statistical methods to identify the user's strengths and weaknesses.

[0142] Step 3:

[0143] The server generates an educational plan based on identified cognitive abilities and learning methods. It designs training tasks optimized for each user and outputs them as a properly formatted educational plan. In this process, machine learning algorithms are used to select tasks that focus on reinforcing the user's weak areas.

[0144] Step 4:

[0145] The server sends the generated educational plan and training assignments to the terminal. The terminal receives them and displays them intuitively through the user interface. The user then proceeds with their daily learning based on this.

[0146] Step 5:

[0147] When a user finishes learning or a specified period has elapsed, the learning results are sent from the device to the server as recovery information. The server re-analyzes this recovery information and identifies elements that should be reflected in the next educational plan.

[0148] Step 6:

[0149] The server utilizes a generative AI model based on the analyzed recovery information to create new feedback. This generated feedback includes instructions on the direction and level of achievement for the next learning session, prompting the user to prepare for the next learning session.

[0150] Step 7:

[0151] The server continuously facilitates user learning improvement by repeating the above process. The prompt used is: "Generate an optimal learning plan based on the user's learning history. Identify strengths and weaknesses and suggest appropriate learning materials and practice problems."

[0152] 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.

[0153] This invention is a system that analyzes a user's emotional state and appropriately adjusts learning content in order to improve the user's learning experience. The system consists of a terminal that includes means for collecting the user's learning history and performance data, an emotion engine that performs emotion analysis, and a server that processes this data and provides an optimal learning plan. The specific operational form of this system is shown below.

[0154] When a user begins learning through their device, the device collects data such as the user's voice, facial expressions, and input patterns, and sends this data to a server. The emotion engine analyzes the received data to identify the user's emotional state. For example, voice analysis can detect emotions such as stress, concentration, and joy.

[0155] The server integrates and evaluates the analysis results from the emotion engine with the user's learning data. If the user is focused, it presents problems of appropriate difficulty level; conversely, if the user is stressed, it can lower the difficulty level or suggest a plan to simplify the learning process.

[0156] The learning plans provided to users incorporate dynamic adjustments based on emotion analysis. For example, if stress is detected while a user is solving a differential calculus problem, the server can temporarily lower the difficulty of the problem or change the subject area to approach it from there. These adjustments reduce the burden on the user, allowing them to continue learning while maintaining motivation.

[0157] Furthermore, once a learning session ends, the device sends emotional feedback along with the results data to the server. The server then uses this feedback to inform the next learning plan, enabling continuous curriculum improvement. This feedback, tailored to emotional changes, enhances the quality of the learning experience.

[0158] Thus, the present invention makes it possible to integrate and process user emotions and learning outcomes, and to provide an optimal learning environment tailored to individual needs. Through this system, an efficient and stress-free learning experience is realized.

[0159] The following describes the processing flow.

[0160] Step 1:

[0161] The user accesses the designated learning platform using their device. The device then performs the necessary authentication and prepares to retrieve the user's learning history and past performance data.

[0162] Step 2:

[0163] Once the user begins learning, the device detects facial expressions and voice tone through video and audio analysis, collecting emotional data. This process utilizes devices such as cameras and microphones as needed.

[0164] Step 3:

[0165] The emotional data collected by the device is sent to a server and analyzed by an emotion engine. The emotion engine uses machine learning models to identify stress levels, concentration levels, happiness levels, and other factors.

[0166] Step 4:

[0167] The server generates an optimal learning plan based on the analysis results of the emotion engine and the user's learning history data. The plan includes the selection of learning materials and the adjustment of the difficulty level of practice problems, with the content determined according to the user's current emotional state.

[0168] Step 5:

[0169] The terminal provides the user with a learning plan received from the server. The user can then review and work through the recommended learning content via the interface.

[0170] Step 6:

[0171] Users progress through their learning according to the provided learning plan, while the device continuously collects emotional data and transmits it to the server in real time. This process allows for dynamic adjustment of the content in response to changes in emotions during learning.

[0172] Step 7:

[0173] After the learning session ends, the device sends data on the final learning results and emotional changes to the server. The server analyzes this data and generates feedback for the user.

[0174] Step 8:

[0175] The server uses the analysis results to make adjustments to the next learning plan. This feedback, along with the sentiment engine results, is recorded in the user's account and applied when the next learning session begins.

[0176] (Example 2)

[0177] 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".

[0178] Traditional learning systems lack dynamic adjustments to learning based on the user's emotional state, resulting in insufficient learning effectiveness. Furthermore, they lack features to adequately address situations where users are stressed or their concentration is waning. This leads to decreased user motivation and difficulty in sustained learning.

[0179] 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.

[0180] In this invention, the server includes means for collecting the user's learning history, mental state, and work data; means for analyzing the collected data to identify the user's emotional state; and means for dynamically adjusting the learning plan based on the identified emotional state. This makes it possible to provide an optimal learning experience that is tailored to the user's emotional state and level of concentration during learning.

[0181] "User learning history" refers to data about the learning activities a user has engaged in in the past, including the content, results, and duration of those activities.

[0182] "Mental state" refers to information that indicates the user's internal health and emotional state, and includes elements such as stress, concentration level, and excitement.

[0183] "Work data" refers to a record of specific operations and inputs performed by a user during a learning activity, including information such as keyboard input, mouse movements, and time.

[0184] "Emotional state" refers to information that indicates the user's current emotional state, identifying psychological elements such as joy, surprise, and stress.

[0185] A "learning plan" is a plan or curriculum created to optimize a user's learning progress, and it includes elements such as goals, methods, and learning materials.

[0186] "Means of dynamic adjustment" refers to methods or algorithms that allow the system to automatically change the learning content and difficulty level in real time in response to changes in the user's situation and conditions.

[0187] A "communication device" is a device or interface that exchanges information between a server and a user's terminal, and has the function of sending and receiving data.

[0188] "Means of analyzing feedback" refer to methods and processes for evaluating information about learning outcomes and emotional changes obtained from users and incorporating them into subsequent learning plans.

[0189] This invention is an advanced system for improving the user's learning experience, and consists of a terminal, a server, and an emotion engine. The following describes how this system is specifically implemented.

[0190] As soon as the user begins learning, the device uses its built-in camera and microphone to collect voice, facial expressions, and user input data in real time. This data is transmitted to the server via a secure communication protocol (e.g., SSL / TLS).

[0191] The server passes this received data to the emotion engine for analysis. The emotion engine uses emotion analysis software, such as "EmotionAPI," to identify the user's emotional state, including stress levels, concentration, and joy. Based on this analysis, the server dynamically adjusts the learning plan.

[0192] For example, if high stress is detected while a user is learning a calculus problem, the server can immediately change the plan, lowering the difficulty level or taking a different approach to reduce the burden on the user. This process allows the user to learn enthusiastically and efficiently.

[0193] Furthermore, once the learning session is complete, the device sends the user's learning results and emotional feedback to the server. The server then incorporates this information into the next learning plan, continuously improving the learning curriculum.

[0194] In this way, the server and terminal work together to create an advanced system that provides the optimal learning experience for the user. This technology reduces stress during learning and enables a flexible learning process that is tailored to each individual's learning pace.

[0195] Example prompt: "We have detected that the user's stress level is increasing while working on differential calculus problems. Please suggest adjustments to improve the quality of the learning experience."

[0196] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0197] Step 1:

[0198] The user begins learning, and the device collects voice, facial expressions, and input patterns in real time. The user's actions and reactions during learning serve as input for this step. The device uses its camera and microphone to capture the user's facial expressions and voice data, and also senses keyboard and touch input. This collected data is processed and temporarily stored for use in the next step.

[0199] Step 2:

[0200] The terminal transmits the collected data to the server via a secure communication protocol. Voice data, facial expression data, and input data are the specific inputs in this step. Communication security is maintained because the data is transmitted to the server using protocols such as SSL / TLS. The output of this step is the raw data that was transmitted.

[0201] Step 3:

[0202] The server analyzes the received data using an emotion engine. Voice and facial expression data are input, and based on this, the emotional state is obtained as output. Using "EmotionAPI" and other tools, the server extracts the user's stress level, concentration level, and feelings of joy. These analysis results are then used in the next step.

[0203] Step 4:

[0204] The server adjusts the learning plan to best suit the user's current learning progress based on the analyzed emotional data. Emotional state and learning history are used as input for this step. If the user is experiencing stress, the server uses a generative AI model to create a plan with adjusted difficulty. The generated learning plan is the output, providing a dynamic means to enhance the user's motivation to learn.

[0205] Step 5:

[0206] The generated plan is sent back from the server to the terminal and presented to the user. The input for this step is the generated learning plan, and the output is the information presented to the user visually or audibly. The terminal displays the tasks and explanations on the application using a user interface.

[0207] Step 6:

[0208] Once the learning process is complete, the device sends the learning results and feedback to the server. The user's learning progress and feedback data are inputs for this step. The transmitted feedback information is the output and will be used to improve future learning sessions.

[0209] Step 7:

[0210] The server analyzes the feedback information and incorporates it into the next learning plan. User feedback is the input, and revised learning plans and improvement suggestions are the output. This makes it possible to provide individualized support tailored to the user's learning progress, optimizing the long-term learning experience.

[0211] (Application Example 2)

[0212] 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".

[0213] In educational settings, providing learners with efficient and individualized learning experiences is crucial. However, uniform learning plans make it difficult to provide appropriate guidance to all learners with diverse learning styles and emotional states. Furthermore, dynamically adjusting learning plans according to learners' emotional states would improve the quality of learning, but such a system has not yet been established.

[0214] 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.

[0215] In this invention, the server includes means for collecting the user's learning history and work efficiency data, an emotion analysis device for analyzing the user's emotional state, and means for generating an optimal learning plan based on the identified learning style and emotional state. This makes it possible to provide dynamic learning plans tailored to each learner's emotional state and learning style.

[0216] "Learning history" refers to a record of the learning activities a user has undertaken in the past.

[0217] "Work efficiency data" refers to data that shows how efficiently users performed tasks during their learning process.

[0218] "Comprehension" refers to a user's ability to accurately understand the information they are given.

[0219] "Learning style" refers to the learning methods or styles that users prefer or find effective.

[0220] An "emotion analysis device" is a device that analyzes a user's voice and facial expressions to identify their emotional state.

[0221] A "learning plan" is a plan that outlines the learning steps and schedule necessary for a user to achieve their ultimate goal.

[0222] An "unfamiliar area" refers to a subject or area that the user does not fully understand or struggles with.

[0223] "Practice exercises" are problems or exercises that users work on to deepen their understanding.

[0224] "Communication means" refers to interface means used to provide information and content to users.

[0225] "Emotional feedback" refers to evaluations and metrics that reflect the user's emotional changes and states during the learning process.

[0226] The system that implements this application example begins by collecting the user's learning history and work efficiency data via a terminal and sending it to a server. The server processes the data obtained from audio and video using an emotion analysis device to identify the user's emotional state. Emotion analysis software can be used for this processing. Furthermore, by using algorithms to analyze the user's comprehension and learning style, this data is comprehensively evaluated and an optimal learning plan is generated. The generated learning plan is provided to the user via communication and practice tasks are presented as needed. Emotional feedback from the user during the learning process is collected by the terminal and sent back to the server. This feedback is used to improve the next learning plan. For example, if an elementary school student is learning math at home with a robot, and the robot detects a decrease in the user's concentration, it can provide problems with adjusted difficulty levels to create a better learning experience. Prompt sentences such as, "Based on this text, please think of specific ways a robot that provides help to middle school students can adjust the learning content while analyzing emotions," can be used in the generating AI model.

[0227] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0228] Step 1:

[0229] The terminal collects user voice, facial expressions, and input data in real time. Input includes data from a voice input device, camera, and keyboard. This data is then prepared for transfer to a server via communication. This step involves data collection and initial processing.

[0230] Step 2:

[0231] The server receives data transmitted from the terminal and performs analysis using an emotion analysis device. The received audio and video data is passed to emotion analysis software for processing to identify the user's emotional state (e.g., stress, excitement, concentration level). The output is information about the user's emotional state. This step involves determining the emotional state and analyzing the data.

[0232] Step 3:

[0233] The server integrates the obtained emotional state information with past learning history and work efficiency data, and uses a learning style analysis program to evaluate the user's academic ability. Inputs include emotional state information, learning history, and work efficiency data, and the output is the user's academic ability and learning style. This step establishes the user profile.

[0234] Step 4:

[0235] The server generates an optimal learning plan based on the user's academic ability and learning style. Using an adaptive learning algorithm, it creates learning steps tailored to the user, incorporating sentiment analysis information. Inputs include academic ability, learning style, and emotional state information, and the output is a customized learning plan. This step involves creating the learning plan.

[0236] Step 5:

[0237] The generated learning plan and appropriate practice tasks are transmitted to the terminal via communication means. The user proceeds with learning on the terminal according to the learning plan. As output, the learning content displayed to the user is provided. In this step, the learning content is provided and feedback is presented to the user.

[0238] Step 6:

[0239] After completing a learning session, the user enters feedback information into the device. This input includes the user's learning outcomes and emotional feedback. This information is prepared to be sent to the server to be used in the next session. This step involves collecting feedback information.

[0240] Step 7:

[0241] The server analyzes the feedback information received from the terminal and applies it to adjusting the next learning plan. It takes feedback information as input and incorporates it into the next improved learning plan. The output is the improved learning plan. This step involves continuous optimization of the learning plan.

[0242] 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.

[0243] 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.

[0244] 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.

[0245] [Second Embodiment]

[0246] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0247] 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.

[0248] 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).

[0249] 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.

[0250] 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.

[0251] 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).

[0252] 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.

[0253] 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.

[0254] 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.

[0255] 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.

[0256] 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.

[0257] 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".

[0258] This invention is implemented within an integrated system that includes a user terminal, a server for processing information, and an interface. Users access the learning system using a terminal such as a smartphone or tablet and begin their individual learning experience. The program's processing is described below in natural language.

[0259] First, the user inputs their learning history and performance data into their device, and this information is sent to the server. The device formats the data appropriately and transmits it using a secure communication protocol to ensure data consistency and security.

[0260] The server analyzes the received data and visualizes the user's academic ability and learning style. The analytical techniques used here include machine learning algorithms and data mining methods. This clearly identifies the user's strengths and weaknesses.

[0261] Based on the analysis results, the server generates a learning plan that best suits the user's learning goals. This plan is designed to leverage the user's strengths while overcoming their weaknesses and includes specific learning materials and practice exercises.

[0262] The server also automatically generates practice problems that focus on areas where the user struggles. These problems are structured to gradually increase in complexity and are provided with explanations. By working through them, users can gradually improve their skills.

[0263] The generated learning plans and practice exercises are provided to the user via the device. Users access these through the interface and use them for daily learning. The interface is designed to be intuitive and enhance the user experience.

[0264] Learning progress and results are periodically sent from the device to the server. The server analyzes this data and generates feedback tailored to the user's situation. This feedback is then incorporated into the next learning plan, enabling continuous learning improvement.

[0265] This invention enables a specific operational model in which users can enjoy a learning experience that is optimal for them, without needing individualized instruction.

[0266] The following describes the processing flow.

[0267] Step 1:

[0268] The user uses the device to input their past learning history and current learning goals. The device receives this data, formats it, and prepares it for processing.

[0269] Step 2:

[0270] The terminal sends the data entered by the user to the server. A secure communication protocol is used for transmission, ensuring the security and integrity of the data.

[0271] Step 3:

[0272] The server analyzes the user's past learning history and academic ability based on the received data. It uses machine learning algorithms to identify the user's strengths and weaknesses and evaluate their learning style.

[0273] Step 4:

[0274] Based on the analysis results, the server generates a learning plan optimized for the user's current learning needs. The plan includes specific learning materials and exercises, customized to match the user's learning objectives.

[0275] Step 5:

[0276] The server automatically generates practice problems to address the user's areas of weakness. These problems include gradual difficulty adjustments and detailed explanations, designed to make it easier for users to understand the material.

[0277] Step 6:

[0278] The terminal presents the user with a learning plan and practice problems received from the server. The user can then use the provided information to carry out their daily studies.

[0279] Step 7:

[0280] As the user progresses in learning, they input information such as the progress of learning and the results of practice problems into the terminal. The terminal collects this information and continuously sends it to the server.

[0281] Step 8:

[0282] The server analyzes the transmitted learning results and generates feedback for the user. The feedback is reflected in the next learning plan and is used to continuously improve the user's learning.

[0283] (Example 1)

[0284] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0285] Conventional learning systems have the problem that there is no well-established mechanism for efficiently collecting the learning histories and performance data of individual users and providing an optimal learning plan based on them. Also, it is difficult to automatically generate and provide practice problems specialized for the user's weak areas in real time, making it difficult to optimize individualized learning. Furthermore, there is also a lack of a mechanism to appropriately reflect feedback according to the progress of learning.

[0286] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0287] In this invention, the server includes means for collecting the user's history information and performance information, means for analyzing the collected information to identify the user's abilities and learning tendencies, and means for generating an optimal plan based on the identified learning tendencies and abilities. As a result, the user can receive an optimal learning plan based on their individual learning history and practice problems focused on their weak areas, and furthermore, feedback according to the progress of learning becomes possible.

[0288] The "user" refers to an individual who conducts learning using the system.

[0289] "History information" refers to records of learning activities that users have engaged in in the past.

[0290] "Performance information" refers to data that shows the user's learning outcomes and evaluations.

[0291] "Collection" refers to the process of gathering information, with the aim of storing it in a database.

[0292] "Analysis" refers to the process of analyzing collected information using appropriate methods to obtain useful insights.

[0293] "Ability" refers to an indicator that shows the user's academic capabilities.

[0294] "Learning tendencies" refer to the characteristics and behavioral patterns of users in their learning.

[0295] A "plan" refers to a series of learning activities designed to achieve the user's learning goals.

[0296] A "weakness area" refers to a learning area in which a user is relatively less proficient compared to other areas.

[0297] "Assignments" refer to problems and practical activities that users should engage in during their learning process.

[0298] "Display means" refers to an interface that allows users to visually confirm the generated information.

[0299] "Results information" refers to report data that shows the results of the user's learning activities.

[0300] "Correction" refers to the process of implementing improvements for the user's next learning activity.

[0301] A "communication protocol" refers to the procedures and rules necessary for sending and receiving digital information.

[0302] The "information device" refers to an electronic device for storing, processing, and transferring data.

[0303] "Notification" refers to the act of transmitting the generated information to the user.

[0304] The present invention is a system for providing individualized learning experiences, which operates in cooperation with a terminal used by a user and a server that processes information. The user inputs their history information and performance information into the terminal. For this, dedicated applications for smartphones and tablets are used, enabling the user to easily input information through the devices they use daily.

[0305] The terminal arranges the input information into an appropriate format and securely transmits it to the server using the SSL protocol. The server uses an analysis system built with a programming language such as Python to analyze the input data. Here, machine learning algorithms and data mining techniques are utilized to identify the user's capabilities and learning tendencies, and to grasp the user's strong and weak areas.

[0306] Based on the analysis results, the server uses a generative AI model to create an optimal learning plan for the user. Also, practice problems specialized in the user's weak areas are automatically generated. These generations use algorithms such as reinforcement learning algorithms, enabling step-by-step task settings according to the user's progress.

[0307] As an example, for a user who has a lack of confidence in differential and integral calculus in mathematics, the server provides practice problems and explanations specialized in that field. This makes it easier for the user to overcome specific weak areas.

[0308] These learning plans and problems are visually provided to the user through the interface of the terminal. With an interface designed to be intuitively operable, the user can easily proceed with learning. The results and progress data of learning are periodically transmitted to the server and reflected as feedback in the next plan.

[0309] As described above, the present invention provides an individualized learning experience that maximizes the user's learning performance.

[0310] Example of a prompt:

[0311] "Use a generative AI model to create a learning plan for students who struggle with differential and integral calculus. Include specific practice problems and explanatory materials."

[0312] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0313] Step 1:

[0314] The user enters history information and performance information.

[0315] Users input data such as past test results, study time, and self-assessments using a dedicated smartphone application. The input data is converted into an appropriate data format, such as JSON. This prepares the input data for transmission to the server.

[0316] Step 2:

[0317] The device sends data to the server.

[0318] The terminal sends the converted data to the server using the SSL communication protocol. This step ensures data consistency and security. The data sent by the terminal is stored in the server's database.

[0319] Step 3:

[0320] The server analyzes the data.

[0321] The server uses a Python-based machine learning library to analyze the received data. Specifically, it employs clustering techniques to understand learning trends and classification algorithms to identify strengths and weaknesses. The analysis clarifies the learning characteristics of each user, which then forms the basis for the next step.

[0322] Step 4:

[0323] The server generates a training plan.

[0324] Based on the analysis results, the server uses a generated AI model to create an optimal learning plan for the user. In this step, reinforcement learning algorithms are used to select learning materials and tasks that match the user's goals. As a result, an individualized learning plan is output.

[0325] Step 5:

[0326] The server automatically generates practice problems.

[0327] The server automatically generates practice problem sets that focus on areas of particular difficulty. Hints and explanations are added sequentially to the problems to help resolve any questions. This output is then provided to the user in the next step.

[0328] Step 6:

[0329] The device provides information to the user.

[0330] The device displays the generated learning plan and practice problems in the user interface. A notification function informs the user when new learning materials are available. The user can progress through the learning process based on the provided information via an intuitively operable app.

[0331] Step 7:

[0332] The user inputs the learning results, and the device sends them to the server.

[0333] Users input the results and progress of their learning activities into their terminal. The entered information is formatted and sent to the server. This data transmission allows the server to receive important information that can be used to plan the next learning session.

[0334] Step 8:

[0335] The server evaluates the progress and provides feedback.

[0336] The server evaluates progress based on the received learning results. This process includes data analysis and comparison. The evaluation results are used as material for adjustments in the next learning plan and are displayed as feedback on the device. This continuous process allows users to feel the effects of their learning and continuously improve themselves.

[0337] (Application Example 1)

[0338] 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."

[0339] In modern education, it is necessary to provide learning experiences tailored to each individual learner, but this is difficult to achieve with traditional methods. Furthermore, it is essential to accurately identify learners' strengths and weaknesses and quickly provide optimal educational plans based on that information. Providing flexible, real-time feedback that matches learning progress is also a crucial challenge.

[0340] 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.

[0341] In this invention, the server includes means for collecting and analyzing the user's learning history and performance data, means for generating an educational plan based on identified learning methods and cognitive abilities, and means for providing knowledge tailored to the user using AI technology. This enables the provision of a learning experience optimized for each individual learner and effective feedback.

[0342] "Learning history" refers to the learning activities a user has undertaken and the records thereof.

[0343] "Performance data" refers to information that shows the results and performance obtained through user learning.

[0344] "Cognitive ability" refers to a user's ability and tendencies regarding understanding and problem-solving.

[0345] "Learning method" refers to the techniques and styles that users employ when progressing through their learning process.

[0346] An "educational plan" is a lesson plan designed to streamline the user's learning process and bring them closer to achieving their goals.

[0347] A "weakness area" refers to an academic field or topic that the user finds difficult to understand.

[0348] "Training exercises" are exercises or problem sets designed to improve specific skills or knowledge.

[0349] A "connection device" is a device that provides an interface for users to access digital learning content.

[0350] "Return information" refers to the results and feedback collected after a user's learning session, which are then incorporated into their next learning plan.

[0351] "AI technology" refers to technologies that use artificial intelligence methods to perform data analysis and problem solving.

[0352] "Knowledge provision" refers to the act of providing users with the information and learning materials they need for their studies.

[0353] A "generative AI model" is a model that uses AI to generate new data and information.

[0354] A "prompt statement" is a phrase used to give instructions to an AI or training model.

[0355] In the system implementing this invention, an integrated platform is constructed by fusing the user's terminal, a server, and an AI-based interface. Users access the learning support platform via a smartphone or tablet and input their learning history and achievement data. This data is transmitted to the server via a secure protocol.

[0356] The server uses AI technology to analyze the user's cognitive abilities and learning methods based on the received data. This involves a generative AI model, performing advanced calculations and data processing to generate the most suitable educational plan for the user. The educational plan includes training tasks designed to improve specific skills. These training tasks are automatically generated by AI technology based on the user's weak areas, and their difficulty level is adjusted in stages.

[0357] The generated educational plan and training tasks are provided to the user's device, and the learning activity progresses. Through the connected device, the user intuitively interacts with this content and continues learning. At the end of learning or periodically thereafter, the user's learning results are sent to the server as feedback information. The server re-analyzes this feedback information, generates feedback tailored to the user, and incorporates it into the next learning plan.

[0358] As a concrete example, a student aiming for university entrance exams uses this system to receive personalized learning materials to further strengthen their strong point, mathematics, and improve their weak point, English. The feedback provided by the server includes the message, "You are on track towards your next goal." An example of a prompt used in the generating AI model is, "Generate an optimal learning plan based on the user's learning history. Identify strengths and weaknesses and suggest appropriate learning materials and practice problems."

[0359] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0360] Step 1:

[0361] Users input their learning history and achievement data using their own devices. This input data is formatted appropriately by the device and sent to the server using a secure communication protocol.

[0362] Step 2:

[0363] The server analyzes the received data. Using a generative AI model, it processes the data to identify cognitive abilities and learning methods. Specifically, it analyzes each data point and applies statistical methods to identify the user's strengths and weaknesses.

[0364] Step 3:

[0365] The server generates an educational plan based on identified cognitive abilities and learning methods. It designs training tasks optimized for each user and outputs them as a properly formatted educational plan. In this process, machine learning algorithms are used to select tasks that focus on reinforcing the user's weak areas.

[0366] Step 4:

[0367] The server sends the generated educational plan and training assignments to the terminal. The terminal receives them and displays them intuitively through the user interface. The user then proceeds with their daily learning based on this.

[0368] Step 5:

[0369] When a user finishes learning or a specified period has elapsed, the learning results are sent from the device to the server as recovery information. The server re-analyzes this recovery information and identifies elements that should be reflected in the next educational plan.

[0370] Step 6:

[0371] The server utilizes a generative AI model based on the analyzed recovery information to create new feedback. This generated feedback includes instructions on the direction and level of achievement for the next learning session, prompting the user to prepare for the next learning session.

[0372] Step 7:

[0373] The server continuously facilitates user learning improvement by repeating the above process. The prompt used is: "Generate an optimal learning plan based on the user's learning history. Identify strengths and weaknesses and suggest appropriate learning materials and practice problems."

[0374] 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.

[0375] This invention is a system that analyzes a user's emotional state and appropriately adjusts learning content in order to improve the user's learning experience. The system consists of a terminal that includes means for collecting the user's learning history and performance data, an emotion engine that performs emotion analysis, and a server that processes this data and provides an optimal learning plan. The specific operational form of this system is shown below.

[0376] When a user begins learning through their device, the device collects data such as the user's voice, facial expressions, and input patterns, and sends this data to a server. The emotion engine analyzes the received data to identify the user's emotional state. For example, voice analysis can detect emotions such as stress, concentration, and joy.

[0377] The server integrates and evaluates the analysis results from the emotion engine with the user's learning data. If the user is focused, it presents problems of appropriate difficulty level; conversely, if the user is stressed, it can lower the difficulty level or suggest a plan to simplify the learning process.

[0378] The learning plans provided to users incorporate dynamic adjustments based on emotion analysis. For example, if stress is detected while a user is solving a differential calculus problem, the server can temporarily lower the difficulty of the problem or change the subject area to approach it from there. These adjustments reduce the burden on the user, allowing them to continue learning while maintaining motivation.

[0379] Furthermore, once a learning session ends, the device sends emotional feedback along with the results data to the server. The server then uses this feedback to inform the next learning plan, enabling continuous curriculum improvement. This feedback, tailored to emotional changes, enhances the quality of the learning experience.

[0380] Thus, the present invention makes it possible to integrate and process user emotions and learning outcomes, and to provide an optimal learning environment tailored to individual needs. Through this system, an efficient and stress-free learning experience is realized.

[0381] The following describes the processing flow.

[0382] Step 1:

[0383] The user accesses the designated learning platform using their device. The device then performs the necessary authentication and prepares to retrieve the user's learning history and past performance data.

[0384] Step 2:

[0385] Once the user begins learning, the device detects facial expressions and voice tone through video and audio analysis, collecting emotional data. This process utilizes devices such as cameras and microphones as needed.

[0386] Step 3:

[0387] The emotional data collected by the device is sent to a server and analyzed by an emotion engine. The emotion engine uses machine learning models to identify stress levels, concentration levels, happiness levels, and other factors.

[0388] Step 4:

[0389] The server generates an optimal learning plan based on the analysis results of the emotion engine and the user's learning history data. The plan includes the selection of learning materials and the adjustment of the difficulty level of practice problems, with the content determined according to the user's current emotional state.

[0390] Step 5:

[0391] The terminal provides the user with a learning plan received from the server. The user can then review and work through the recommended learning content via the interface.

[0392] Step 6:

[0393] Users progress through their learning according to the provided learning plan, while the device continuously collects emotional data and transmits it to the server in real time. This process allows for dynamic adjustment of the content in response to changes in emotions during learning.

[0394] Step 7:

[0395] After the learning session ends, the device sends data on the final learning results and emotional changes to the server. The server analyzes this data and generates feedback for the user.

[0396] Step 8:

[0397] The server uses the analysis results to make adjustments to the next learning plan. This feedback, along with the sentiment engine results, is recorded in the user's account and applied when the next learning session begins.

[0398] (Example 2)

[0399] 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".

[0400] Traditional learning systems lack dynamic adjustments to learning based on the user's emotional state, resulting in insufficient learning effectiveness. Furthermore, they lack features to adequately address situations where users are stressed or their concentration is waning. This leads to decreased user motivation and difficulty in sustained learning.

[0401] 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.

[0402] In this invention, the server includes means for collecting the user's learning history, mental state, and work data; means for analyzing the collected data to identify the user's emotional state; and means for dynamically adjusting the learning plan based on the identified emotional state. This makes it possible to provide an optimal learning experience that is tailored to the user's emotional state and level of concentration during learning.

[0403] "User learning history" refers to data about the learning activities a user has engaged in in the past, including the content, results, and duration of those activities.

[0404] "Mental state" refers to information that indicates the user's internal health and emotional state, and includes elements such as stress, concentration level, and excitement.

[0405] "Work data" refers to a record of specific operations and inputs performed by a user during a learning activity, including information such as keyboard input, mouse movements, and time.

[0406] "Emotional state" refers to information that indicates the user's current emotional state, identifying psychological elements such as joy, surprise, and stress.

[0407] A "learning plan" is a plan or curriculum created to optimize a user's learning progress, and it includes elements such as goals, methods, and learning materials.

[0408] "Means of dynamic adjustment" refers to methods or algorithms that allow the system to automatically change the learning content and difficulty level in real time in response to changes in the user's situation and conditions.

[0409] A "communication device" is a device or interface that exchanges information between a server and a user's terminal, and has the function of sending and receiving data.

[0410] "Means of analyzing feedback" refer to methods and processes for evaluating information about learning outcomes and emotional changes obtained from users and incorporating them into subsequent learning plans.

[0411] This invention is an advanced system for improving the user's learning experience, and consists of a terminal, a server, and an emotion engine. The following describes how this system is specifically implemented.

[0412] As soon as the user begins learning, the device uses its built-in camera and microphone to collect voice, facial expressions, and user input data in real time. This data is transmitted to the server via a secure communication protocol (e.g., SSL / TLS).

[0413] The server passes this received data to the emotion engine for analysis. The emotion engine uses emotion analysis software, such as "EmotionAPI," to identify the user's emotional state, including stress levels, concentration, and joy. Based on this analysis, the server dynamically adjusts the learning plan.

[0414] For example, if high stress is detected while a user is learning a calculus problem, the server can immediately change the plan, lowering the difficulty level or taking a different approach to reduce the burden on the user. This process allows the user to learn enthusiastically and efficiently.

[0415] Furthermore, once the learning session is complete, the device sends the user's learning results and emotional feedback to the server. The server then incorporates this information into the next learning plan, continuously improving the learning curriculum.

[0416] In this way, the server and terminal work together to create an advanced system that provides the optimal learning experience for the user. This technology reduces stress during learning and enables a flexible learning process that is tailored to each individual's learning pace.

[0417] Example prompt: "We have detected that the user's stress level is increasing while working on differential calculus problems. Please suggest adjustments to improve the quality of the learning experience."

[0418] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0419] Step 1:

[0420] The user begins learning, and the device collects voice, facial expressions, and input patterns in real time. The user's actions and reactions during learning serve as input for this step. The device uses its camera and microphone to capture the user's facial expressions and voice data, and also senses keyboard and touch input. This collected data is processed and temporarily stored for use in the next step.

[0421] Step 2:

[0422] The terminal transmits the collected data to the server via a secure communication protocol. Voice data, facial expression data, and input data are the specific inputs in this step. Communication security is maintained because the data is transmitted to the server using protocols such as SSL / TLS. The output of this step is the raw data that was transmitted.

[0423] Step 3:

[0424] The server analyzes the received data using an emotion engine. Voice and facial expression data are input, and based on this, the emotional state is obtained as output. Using "EmotionAPI" and other tools, the server extracts the user's stress level, concentration level, and feelings of joy. These analysis results are then used in the next step.

[0425] Step 4:

[0426] The server adjusts the learning plan to best suit the user's current learning progress based on the analyzed emotional data. Emotional state and learning history are used as input for this step. If the user is experiencing stress, the server uses a generative AI model to create a plan with adjusted difficulty. The generated learning plan is the output, providing a dynamic means to enhance the user's motivation to learn.

[0427] Step 5:

[0428] The generated plan is sent back from the server to the terminal and presented to the user. The input for this step is the generated learning plan, and the output is the information presented to the user visually or audibly. The terminal displays the tasks and explanations on the application using a user interface.

[0429] Step 6:

[0430] Once the learning process is complete, the device sends the learning results and feedback to the server. The user's learning progress and feedback data are inputs for this step. The transmitted feedback information is the output and will be used to improve future learning sessions.

[0431] Step 7:

[0432] The server analyzes the feedback information and incorporates it into the next learning plan. User feedback is the input, and revised learning plans and improvement suggestions are the output. This makes it possible to provide individualized support tailored to the user's learning progress, optimizing the long-term learning experience.

[0433] (Application Example 2)

[0434] 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."

[0435] In educational settings, providing learners with efficient and individualized learning experiences is crucial. However, uniform learning plans make it difficult to provide appropriate guidance to all learners with diverse learning styles and emotional states. Furthermore, dynamically adjusting learning plans according to learners' emotional states would improve the quality of learning, but such a system has not yet been established.

[0436] 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.

[0437] In this invention, the server includes means for collecting the user's learning history and work efficiency data, an emotion analysis device for analyzing the user's emotional state, and means for generating an optimal learning plan based on the identified learning style and emotional state. This makes it possible to provide dynamic learning plans tailored to each learner's emotional state and learning style.

[0438] "Learning history" refers to a record of the learning activities a user has undertaken in the past.

[0439] "Work efficiency data" refers to data that shows how efficiently users performed tasks during their learning process.

[0440] "Comprehension" refers to a user's ability to accurately understand the information they are given.

[0441] "Learning style" refers to the learning methods or styles that users prefer or find effective.

[0442] An "emotion analysis device" is a device that analyzes a user's voice and facial expressions to identify their emotional state.

[0443] A "learning plan" is a plan that outlines the learning steps and schedule necessary for a user to achieve their ultimate goal.

[0444] An "unfamiliar area" refers to a subject or area that the user does not fully understand or struggles with.

[0445] "Practice exercises" are problems or exercises that users work on to deepen their understanding.

[0446] "Communication means" refers to interface means used to provide information and content to users.

[0447] "Emotional feedback" refers to evaluations and metrics that reflect the user's emotional changes and states during the learning process.

[0448] The system that implements this application example begins by collecting the user's learning history and work efficiency data via a terminal and sending it to a server. The server processes the data obtained from audio and video using an emotion analysis device to identify the user's emotional state. Emotion analysis software can be used for this processing. Furthermore, by using algorithms to analyze the user's comprehension and learning style, this data is comprehensively evaluated and an optimal learning plan is generated. The generated learning plan is provided to the user via communication and practice tasks are presented as needed. Emotional feedback from the user during the learning process is collected by the terminal and sent back to the server. This feedback is used to improve the next learning plan. For example, if an elementary school student is learning math at home with a robot, and the robot detects a decrease in the user's concentration, it can provide problems with adjusted difficulty levels to create a better learning experience. Prompt sentences such as, "Based on this text, please think of specific ways a robot that provides help to middle school students can adjust the learning content while analyzing emotions," can be used in the generating AI model.

[0449] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0450] Step 1:

[0451] The terminal collects user voice, facial expressions, and input data in real time. Input includes data from a voice input device, camera, and keyboard. This data is then prepared for transfer to a server via communication. This step involves data collection and initial processing.

[0452] Step 2:

[0453] The server receives data transmitted from the terminal and performs analysis using an emotion analysis device. The received audio and video data is passed to emotion analysis software for processing to identify the user's emotional state (e.g., stress, excitement, concentration level). The output is information about the user's emotional state. This step involves determining the emotional state and analyzing the data.

[0454] Step 3:

[0455] The server integrates the obtained emotional state information with past learning history and work efficiency data, and uses a learning style analysis program to evaluate the user's academic ability. Inputs include emotional state information, learning history, and work efficiency data, and the output is the user's academic ability and learning style. This step establishes the user profile.

[0456] Step 4:

[0457] The server generates an optimal learning plan based on the user's academic ability and learning style. Using an adaptive learning algorithm, it creates learning steps tailored to the user, incorporating sentiment analysis information. Inputs include academic ability, learning style, and emotional state information, and the output is a customized learning plan. This step involves creating the learning plan.

[0458] Step 5:

[0459] The generated learning plan and appropriate practice tasks are transmitted to the terminal via communication means. The user proceeds with learning on the terminal according to the learning plan. As output, the learning content displayed to the user is provided. In this step, the learning content is provided and feedback is presented to the user.

[0460] Step 6:

[0461] After completing a learning session, the user enters feedback information into the device. This input includes the user's learning outcomes and emotional feedback. This information is prepared to be sent to the server to be used in the next session. This step involves collecting feedback information.

[0462] Step 7:

[0463] The server analyzes the feedback information received from the terminal and applies it to adjusting the next learning plan. It takes feedback information as input and incorporates it into the next improved learning plan. The output is the improved learning plan. This step involves continuous optimization of the learning plan.

[0464] 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.

[0465] 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.

[0466] 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.

[0467] [Third Embodiment]

[0468] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0469] 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.

[0470] 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).

[0471] 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.

[0472] 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.

[0473] 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).

[0474] 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.

[0475] 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.

[0476] 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.

[0477] 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.

[0478] 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.

[0479] 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".

[0480] This invention is implemented within an integrated system that includes a user terminal, a server for processing information, and an interface. Users access the learning system using a terminal such as a smartphone or tablet and begin their individual learning experience. The program's processing is described below in natural language.

[0481] First, the user inputs their learning history and performance data into their device, and this information is sent to the server. The device formats the data appropriately and transmits it using a secure communication protocol to ensure data consistency and security.

[0482] The server analyzes the received data and visualizes the user's academic ability and learning style. The analytical techniques used here include machine learning algorithms and data mining methods. This clearly identifies the user's strengths and weaknesses.

[0483] Based on the analysis results, the server generates a learning plan that best suits the user's learning goals. This plan is designed to leverage the user's strengths while overcoming their weaknesses and includes specific learning materials and practice exercises.

[0484] The server also automatically generates practice problems that focus on areas where the user struggles. These problems are structured to gradually increase in complexity and are provided with explanations. By working through them, users can gradually improve their skills.

[0485] The generated learning plans and practice exercises are provided to the user via the device. Users access these through the interface and use them for daily learning. The interface is designed to be intuitive and enhance the user experience.

[0486] Learning progress and results are periodically sent from the device to the server. The server analyzes this data and generates feedback tailored to the user's situation. This feedback is then incorporated into the next learning plan, enabling continuous learning improvement.

[0487] This invention enables a specific operational model in which users can enjoy a learning experience that is optimal for them, without needing individualized instruction.

[0488] The following describes the processing flow.

[0489] Step 1:

[0490] The user uses the device to input their past learning history and current learning goals. The device receives this data, formats it, and prepares it for processing.

[0491] Step 2:

[0492] The terminal sends the data entered by the user to the server. A secure communication protocol is used for transmission, ensuring the security and integrity of the data.

[0493] Step 3:

[0494] The server analyzes the user's past learning history and academic ability based on the received data. It uses machine learning algorithms to identify the user's strengths and weaknesses and evaluate their learning style.

[0495] Step 4:

[0496] Based on the analysis results, the server generates a learning plan optimized for the user's current learning needs. The plan includes specific learning materials and exercises, customized to match the user's learning objectives.

[0497] Step 5:

[0498] The server automatically generates practice problems to address the user's areas of weakness. These problems include gradual difficulty adjustments and detailed explanations, designed to make it easier for users to understand the material.

[0499] Step 6:

[0500] The terminal presents the user with a learning plan and practice problems received from the server. The user can then use the provided information to carry out their daily studies.

[0501] Step 7:

[0502] As users progress through their learning, they input their learning progress and practice problem results into their device. The device collects this information and continuously transmits it to the server.

[0503] Step 8:

[0504] The server analyzes the submitted learning results and generates feedback for the user. This feedback is incorporated into the next learning plan and used to continuously improve the user's learning.

[0505] (Example 1)

[0506] 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."

[0507] Traditional learning systems suffer from a lack of adequate mechanisms for efficiently collecting individual users' learning history and performance data, and for providing optimal learning plans based on that data. Furthermore, the difficulty in automatically generating and providing practice problems tailored to users' weak areas in real time makes personalized learning optimization challenging. Additionally, there is a lack of mechanisms for appropriately reflecting feedback based on learning progress.

[0508] 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.

[0509] In this invention, the server includes means for collecting user history information and performance information, means for analyzing the collected information to identify the user's abilities and learning tendencies, and means for generating an optimal plan based on the identified learning tendencies and abilities. As a result, users can receive an optimal learning plan based on their individual learning history, practice problems that focus on areas of weakness, and feedback that is tailored to their learning progress.

[0510] "User" refers to an individual who uses the system to learn.

[0511] "History information" refers to records of learning activities that users have engaged in in the past.

[0512] "Performance information" refers to data that shows the user's learning outcomes and evaluations.

[0513] "Collection" refers to the process of gathering information, with the aim of storing it in a database.

[0514] "Analysis" refers to the process of analyzing collected information using appropriate methods to obtain useful insights.

[0515] "Ability" refers to an indicator that shows the user's academic capabilities.

[0516] "Learning tendencies" refer to the characteristics and behavioral patterns of users in their learning.

[0517] A "plan" refers to a series of learning activities designed to achieve the user's learning goals.

[0518] A "weakness area" refers to a learning area in which a user is relatively less proficient compared to other areas.

[0519] "Assignments" refer to problems and practical activities that users should engage in during their learning process.

[0520] "Display means" refers to an interface that allows users to visually confirm the generated information.

[0521] "Results information" refers to report data that shows the results of the user's learning activities.

[0522] "Correction" refers to the process of implementing improvements for the user's next learning activity.

[0523] A "communication protocol" refers to the procedures and rules necessary for sending and receiving digital information.

[0524] "Information device" refers to electronic equipment used for storing, processing, and transferring data.

[0525] "Notification" refers to the act of transmitting generated information to the user.

[0526] This invention provides a system for offering personalized learning experiences, in which a user-facing terminal and a server that processes information work in conjunction. Users input their history and performance information into the terminal. This is done using a dedicated application for smartphones and tablets, allowing users to easily input information through devices they use on a daily basis.

[0527] The terminal formats the entered information into an appropriate format and securely transmits it to the server using the SSL protocol. The server analyzes the entered data using an analysis system built with a programming language such as Python. Here, machine learning algorithms and data mining techniques are utilized to identify the user's abilities and learning tendencies, and to understand their strengths and weaknesses.

[0528] Based on the analysis results, the server uses a generative AI model to create an optimal learning plan for the user. Additionally, practice problems tailored to the user's weak areas are automatically generated. These generation processes utilize reinforcement learning algorithms, enabling step-by-step task setting according to the user's progress.

[0529] For example, for a user who struggles with differential and integral calculus, the server provides practice problems and explanations specifically tailored to that area. This makes it easier for the user to overcome their specific weaknesses.

[0530] These learning plans and exercises are presented to the user visually through the device's interface. The intuitively designed interface allows users to easily progress through their learning. Learning results and progress data are periodically sent to the server and incorporated as feedback for the next learning plan.

[0531] As described above, the present invention provides an individualized learning experience that maximizes the user's learning performance.

[0532] Example of a prompt:

[0533] "Use a generative AI model to create a learning plan for students who struggle with differential and integral calculus. Include specific practice problems and explanatory materials."

[0534] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0535] Step 1:

[0536] The user enters history information and performance information.

[0537] Users input data such as past test results, study time, and self-assessments using a dedicated smartphone application. The input data is converted into an appropriate data format, such as JSON. This prepares the input data for transmission to the server.

[0538] Step 2:

[0539] The device sends data to the server.

[0540] The terminal sends the converted data to the server using the SSL communication protocol. This step ensures data consistency and security. The data sent by the terminal is stored in the server's database.

[0541] Step 3:

[0542] The server analyzes the data.

[0543] The server uses a Python-based machine learning library to analyze the received data. Specifically, it employs clustering techniques to understand learning trends and classification algorithms to identify strengths and weaknesses. The analysis clarifies the learning characteristics of each user, which then forms the basis for the next step.

[0544] Step 4:

[0545] The server generates a training plan.

[0546] Based on the analysis results, the server uses a generated AI model to create an optimal learning plan for the user. In this step, reinforcement learning algorithms are used to select learning materials and tasks that match the user's goals. As a result, an individualized learning plan is output.

[0547] Step 5:

[0548] The server automatically generates practice problems.

[0549] The server automatically generates practice problem sets that focus on areas of particular difficulty. Hints and explanations are added sequentially to the problems to help resolve any questions. This output is then provided to the user in the next step.

[0550] Step 6:

[0551] The device provides information to the user.

[0552] The device displays the generated learning plan and practice problems in the user interface. A notification function informs the user when new learning materials are available. The user can progress through the learning process based on the provided information via an intuitively operable app.

[0553] Step 7:

[0554] The user inputs the learning results, and the device sends them to the server.

[0555] Users input the results and progress of their learning activities into their terminal. The entered information is formatted and sent to the server. This data transmission allows the server to receive important information that can be used to plan the next learning session.

[0556] Step 8:

[0557] The server evaluates the progress and provides feedback.

[0558] The server evaluates progress based on the received learning results. This process includes data analysis and comparison. The evaluation results are used as material for adjustments in the next learning plan and are displayed as feedback on the device. This continuous process allows users to feel the effects of their learning and continuously improve themselves.

[0559] (Application Example 1)

[0560] 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."

[0561] In modern education, it is necessary to provide learning experiences tailored to each individual learner, but this is difficult to achieve with traditional methods. Furthermore, it is essential to accurately identify learners' strengths and weaknesses and quickly provide optimal educational plans based on that information. Providing flexible, real-time feedback that matches learning progress is also a crucial challenge.

[0562] 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.

[0563] In this invention, the server includes means for collecting and analyzing the user's learning history and performance data, means for generating an educational plan based on identified learning methods and cognitive abilities, and means for providing knowledge tailored to the user using AI technology. This enables the provision of a learning experience optimized for each individual learner and effective feedback.

[0564] "Learning history" refers to the learning activities a user has undertaken and the records thereof.

[0565] "Performance data" refers to information that shows the results and performance obtained through user learning.

[0566] "Cognitive ability" refers to a user's ability and tendencies regarding understanding and problem-solving.

[0567] "Learning method" refers to the techniques and styles that users employ when progressing through their learning process.

[0568] An "educational plan" is a lesson plan designed to streamline the user's learning process and bring them closer to achieving their goals.

[0569] A "weakness area" refers to an academic field or topic that the user finds difficult to understand.

[0570] "Training exercises" are exercises or problem sets designed to improve specific skills or knowledge.

[0571] A "connection device" is a device that provides an interface for users to access digital learning content.

[0572] "Return information" refers to the results and feedback collected after a user's learning session, which are then incorporated into their next learning plan.

[0573] "AI technology" refers to technologies that use artificial intelligence methods to perform data analysis and problem solving.

[0574] "Knowledge provision" refers to the act of providing users with the information and learning materials they need for their studies.

[0575] A "generative AI model" is a model that uses AI to generate new data and information.

[0576] A "prompt statement" is a phrase used to give instructions to an AI or training model.

[0577] In the system implementing this invention, an integrated platform is constructed by fusing the user's terminal, a server, and an AI-based interface. Users access the learning support platform via a smartphone or tablet and input their learning history and achievement data. This data is transmitted to the server via a secure protocol.

[0578] The server uses AI technology to analyze the user's cognitive abilities and learning methods based on the received data. This involves a generative AI model, performing advanced calculations and data processing to generate the most suitable educational plan for the user. The educational plan includes training tasks designed to improve specific skills. These training tasks are automatically generated by AI technology based on the user's weak areas, and their difficulty level is adjusted in stages.

[0579] The generated educational plan and training tasks are provided to the user's device, and the learning activity progresses. Through the connected device, the user intuitively interacts with this content and continues learning. At the end of learning or periodically thereafter, the user's learning results are sent to the server as feedback information. The server re-analyzes this feedback information, generates feedback tailored to the user, and incorporates it into the next learning plan.

[0580] As a concrete example, a student aiming for university entrance exams uses this system to receive personalized learning materials to further strengthen their strong point, mathematics, and improve their weak point, English. The feedback provided by the server includes the message, "You are on track towards your next goal." An example of a prompt used in the generating AI model is, "Generate an optimal learning plan based on the user's learning history. Identify strengths and weaknesses and suggest appropriate learning materials and practice problems."

[0581] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0582] Step 1:

[0583] Users input their learning history and achievement data using their own devices. This input data is formatted appropriately by the device and sent to the server using a secure communication protocol.

[0584] Step 2:

[0585] The server analyzes the received data. Using a generative AI model, it processes the data to identify cognitive abilities and learning methods. Specifically, it analyzes each data point and applies statistical methods to identify the user's strengths and weaknesses.

[0586] Step 3:

[0587] The server generates an educational plan based on identified cognitive abilities and learning methods. It designs training tasks optimized for each user and outputs them as a properly formatted educational plan. In this process, machine learning algorithms are used to select tasks that focus on reinforcing the user's weak areas.

[0588] Step 4:

[0589] The server sends the generated educational plan and training assignments to the terminal. The terminal receives them and displays them intuitively through the user interface. The user then proceeds with their daily learning based on this.

[0590] Step 5:

[0591] When a user finishes learning or a specified period has elapsed, the learning results are sent from the device to the server as recovery information. The server re-analyzes this recovery information and identifies elements that should be reflected in the next educational plan.

[0592] Step 6:

[0593] The server utilizes a generative AI model based on the analyzed recovery information to create new feedback. This generated feedback includes instructions on the direction and level of achievement for the next learning session, prompting the user to prepare for the next learning session.

[0594] Step 7:

[0595] The server continuously facilitates user learning improvement by repeating the above process. The prompt used is: "Generate an optimal learning plan based on the user's learning history. Identify strengths and weaknesses and suggest appropriate learning materials and practice problems."

[0596] 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.

[0597] This invention is a system that analyzes a user's emotional state and appropriately adjusts learning content in order to improve the user's learning experience. The system consists of a terminal that includes means for collecting the user's learning history and performance data, an emotion engine that performs emotion analysis, and a server that processes this data and provides an optimal learning plan. The specific operational form of this system is shown below.

[0598] When a user begins learning through their device, the device collects data such as the user's voice, facial expressions, and input patterns, and sends this data to a server. The emotion engine analyzes the received data to identify the user's emotional state. For example, voice analysis can detect emotions such as stress, concentration, and joy.

[0599] The server integrates and evaluates the analysis results from the emotion engine with the user's learning data. If the user is focused, it presents problems of appropriate difficulty level; conversely, if the user is stressed, it can lower the difficulty level or suggest a plan to simplify the learning process.

[0600] The learning plans provided to users incorporate dynamic adjustments based on emotion analysis. For example, if stress is detected while a user is solving a differential calculus problem, the server can temporarily lower the difficulty of the problem or change the subject area to approach it from there. These adjustments reduce the burden on the user, allowing them to continue learning while maintaining motivation.

[0601] Furthermore, once a learning session ends, the device sends emotional feedback along with the results data to the server. The server then uses this feedback to inform the next learning plan, enabling continuous curriculum improvement. This feedback, tailored to emotional changes, enhances the quality of the learning experience.

[0602] Thus, the present invention makes it possible to integrate and process user emotions and learning outcomes, and to provide an optimal learning environment tailored to individual needs. Through this system, an efficient and stress-free learning experience is realized.

[0603] The following describes the processing flow.

[0604] Step 1:

[0605] The user accesses the designated learning platform using their device. The device then performs the necessary authentication and prepares to retrieve the user's learning history and past performance data.

[0606] Step 2:

[0607] Once the user begins learning, the device detects facial expressions and voice tone through video and audio analysis, collecting emotional data. This process utilizes devices such as cameras and microphones as needed.

[0608] Step 3:

[0609] The emotional data collected by the device is sent to a server and analyzed by an emotion engine. The emotion engine uses machine learning models to identify stress levels, concentration levels, happiness levels, and other factors.

[0610] Step 4:

[0611] The server generates an optimal learning plan based on the analysis results of the emotion engine and the user's learning history data. The plan includes the selection of learning materials and the adjustment of the difficulty level of practice problems, with the content determined according to the user's current emotional state.

[0612] Step 5:

[0613] The terminal provides the user with a learning plan received from the server. The user can then review and work through the recommended learning content via the interface.

[0614] Step 6:

[0615] Users progress through their learning according to the provided learning plan, while the device continuously collects emotional data and transmits it to the server in real time. This process allows for dynamic adjustment of the content in response to changes in emotions during learning.

[0616] Step 7:

[0617] After the learning session ends, the device sends data on the final learning results and emotional changes to the server. The server analyzes this data and generates feedback for the user.

[0618] Step 8:

[0619] The server uses the analysis results to make adjustments to the next learning plan. This feedback, along with the sentiment engine results, is recorded in the user's account and applied when the next learning session begins.

[0620] (Example 2)

[0621] 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."

[0622] Traditional learning systems lack dynamic adjustments to learning based on the user's emotional state, resulting in insufficient learning effectiveness. Furthermore, they lack features to adequately address situations where users are stressed or their concentration is waning. This leads to decreased user motivation and difficulty in sustained learning.

[0623] 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.

[0624] In this invention, the server includes means for collecting the user's learning history, mental state, and work data; means for analyzing the collected data to identify the user's emotional state; and means for dynamically adjusting the learning plan based on the identified emotional state. This makes it possible to provide an optimal learning experience that is tailored to the user's emotional state and level of concentration during learning.

[0625] "User learning history" refers to data about the learning activities a user has engaged in in the past, including the content, results, and duration of those activities.

[0626] "Mental state" refers to information that indicates the user's internal health and emotional state, and includes elements such as stress, concentration level, and excitement.

[0627] "Work data" refers to a record of specific operations and inputs performed by a user during a learning activity, including information such as keyboard input, mouse movements, and time.

[0628] "Emotional state" refers to information that indicates the user's current emotional state, identifying psychological elements such as joy, surprise, and stress.

[0629] A "learning plan" is a plan or curriculum created to optimize a user's learning progress, and it includes elements such as goals, methods, and learning materials.

[0630] "Means of dynamic adjustment" refers to methods or algorithms that allow the system to automatically change the learning content and difficulty level in real time in response to changes in the user's situation and conditions.

[0631] A "communication device" is a device or interface that exchanges information between a server and a user's terminal, and has the function of sending and receiving data.

[0632] "Means of analyzing feedback" refer to methods and processes for evaluating information about learning outcomes and emotional changes obtained from users and incorporating them into subsequent learning plans.

[0633] This invention is an advanced system for improving the user's learning experience, and consists of a terminal, a server, and an emotion engine. The following describes how this system is specifically implemented.

[0634] As soon as the user begins learning, the device uses its built-in camera and microphone to collect voice, facial expressions, and user input data in real time. This data is transmitted to the server via a secure communication protocol (e.g., SSL / TLS).

[0635] The server passes this received data to the emotion engine for analysis. The emotion engine uses emotion analysis software, such as "EmotionAPI," to identify the user's emotional state, including stress levels, concentration, and joy. Based on this analysis, the server dynamically adjusts the learning plan.

[0636] For example, if high stress is detected while a user is learning a calculus problem, the server can immediately change the plan, lowering the difficulty level or taking a different approach to reduce the burden on the user. This process allows the user to learn enthusiastically and efficiently.

[0637] Furthermore, once the learning session is complete, the device sends the user's learning results and emotional feedback to the server. The server then incorporates this information into the next learning plan, continuously improving the learning curriculum.

[0638] In this way, the server and terminal work together to create an advanced system that provides the optimal learning experience for the user. This technology reduces stress during learning and enables a flexible learning process that is tailored to each individual's learning pace.

[0639] Example prompt: "We have detected that the user's stress level is increasing while working on differential calculus problems. Please suggest adjustments to improve the quality of the learning experience."

[0640] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0641] Step 1:

[0642] The user begins learning, and the device collects voice, facial expressions, and input patterns in real time. The user's actions and reactions during learning serve as input for this step. The device uses its camera and microphone to capture the user's facial expressions and voice data, and also senses keyboard and touch input. This collected data is processed and temporarily stored for use in the next step.

[0643] Step 2:

[0644] The terminal transmits the collected data to the server via a secure communication protocol. Voice data, facial expression data, and input data are the specific inputs in this step. Communication security is maintained because the data is transmitted to the server using protocols such as SSL / TLS. The output of this step is the raw data that was transmitted.

[0645] Step 3:

[0646] The server analyzes the received data using an emotion engine. Voice and facial expression data are input, and based on this, the emotional state is obtained as output. Using "EmotionAPI" and other tools, the server extracts the user's stress level, concentration level, and feelings of joy. These analysis results are then used in the next step.

[0647] Step 4:

[0648] The server adjusts the learning plan to best suit the user's current learning progress based on the analyzed emotional data. Emotional state and learning history are used as input for this step. If the user is experiencing stress, the server uses a generative AI model to create a plan with adjusted difficulty. The generated learning plan is the output, providing a dynamic means to enhance the user's motivation to learn.

[0649] Step 5:

[0650] The generated plan is sent back from the server to the terminal and presented to the user. The input for this step is the generated learning plan, and the output is the information presented to the user visually or audibly. The terminal displays the tasks and explanations on the application using a user interface.

[0651] Step 6:

[0652] Once the learning process is complete, the device sends the learning results and feedback to the server. The user's learning progress and feedback data are inputs for this step. The transmitted feedback information is the output and will be used to improve future learning sessions.

[0653] Step 7:

[0654] The server analyzes the feedback information and incorporates it into the next learning plan. User feedback is the input, and revised learning plans and improvement suggestions are the output. This makes it possible to provide individualized support tailored to the user's learning progress, optimizing the long-term learning experience.

[0655] (Application Example 2)

[0656] 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."

[0657] In educational settings, providing learners with efficient and individualized learning experiences is crucial. However, uniform learning plans make it difficult to provide appropriate guidance to all learners with diverse learning styles and emotional states. Furthermore, dynamically adjusting learning plans according to learners' emotional states would improve the quality of learning, but such a system has not yet been established.

[0658] 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.

[0659] In this invention, the server includes means for collecting the user's learning history and work efficiency data, an emotion analysis device for analyzing the user's emotional state, and means for generating an optimal learning plan based on the identified learning style and emotional state. This makes it possible to provide dynamic learning plans tailored to each learner's emotional state and learning style.

[0660] "Learning history" refers to a record of the learning activities a user has undertaken in the past.

[0661] "Work efficiency data" refers to data that shows how efficiently users performed tasks during their learning process.

[0662] "Comprehension" refers to a user's ability to accurately understand the information they are given.

[0663] "Learning style" refers to the learning methods or styles that users prefer or find effective.

[0664] An "emotion analysis device" is a device that analyzes a user's voice and facial expressions to identify their emotional state.

[0665] A "learning plan" is a plan that outlines the learning steps and schedule necessary for a user to achieve their ultimate goal.

[0666] An "unfamiliar area" refers to a subject or area that the user does not fully understand or struggles with.

[0667] "Practice exercises" are problems or exercises that users work on to deepen their understanding.

[0668] "Communication means" refers to interface means used to provide information and content to users.

[0669] "Emotional feedback" refers to evaluations and metrics that reflect the user's emotional changes and states during the learning process.

[0670] The system that implements this application example begins by collecting the user's learning history and work efficiency data via a terminal and sending it to a server. The server processes the data obtained from audio and video using an emotion analysis device to identify the user's emotional state. Emotion analysis software can be used for this processing. Furthermore, by using algorithms to analyze the user's comprehension and learning style, this data is comprehensively evaluated and an optimal learning plan is generated. The generated learning plan is provided to the user via communication and practice tasks are presented as needed. Emotional feedback from the user during the learning process is collected by the terminal and sent back to the server. This feedback is used to improve the next learning plan. For example, if an elementary school student is learning math at home with a robot, and the robot detects a decrease in the user's concentration, it can provide problems with adjusted difficulty levels to create a better learning experience. Prompt sentences such as, "Based on this text, please think of specific ways a robot that provides help to middle school students can adjust the learning content while analyzing emotions," can be used in the generating AI model.

[0671] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0672] Step 1:

[0673] The terminal collects user voice, facial expressions, and input data in real time. Input includes data from a voice input device, camera, and keyboard. This data is then prepared for transfer to a server via communication. This step involves data collection and initial processing.

[0674] Step 2:

[0675] The server receives data transmitted from the terminal and performs analysis using an emotion analysis device. The received audio and video data is passed to emotion analysis software for processing to identify the user's emotional state (e.g., stress, excitement, concentration level). The output is information about the user's emotional state. This step involves determining the emotional state and analyzing the data.

[0676] Step 3:

[0677] The server integrates the obtained emotional state information with past learning history and work efficiency data, and uses a learning style analysis program to evaluate the user's academic ability. Inputs include emotional state information, learning history, and work efficiency data, and the output is the user's academic ability and learning style. This step establishes the user profile.

[0678] Step 4:

[0679] The server generates an optimal learning plan based on the user's academic ability and learning style. Using an adaptive learning algorithm, it creates learning steps tailored to the user, incorporating sentiment analysis information. Inputs include academic ability, learning style, and emotional state information, and the output is a customized learning plan. This step involves creating the learning plan.

[0680] Step 5:

[0681] The generated learning plan and appropriate practice tasks are transmitted to the terminal via communication means. The user proceeds with learning on the terminal according to the learning plan. As output, the learning content displayed to the user is provided. In this step, the learning content is provided and feedback is presented to the user.

[0682] Step 6:

[0683] After completing a learning session, the user enters feedback information into the device. This input includes the user's learning outcomes and emotional feedback. This information is prepared to be sent to the server to be used in the next session. This step involves collecting feedback information.

[0684] Step 7:

[0685] The server analyzes the feedback information received from the terminal and applies it to adjusting the next learning plan. It takes feedback information as input and incorporates it into the next improved learning plan. The output is the improved learning plan. This step involves continuous optimization of the learning plan.

[0686] 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.

[0687] 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.

[0688] 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.

[0689] [Fourth Embodiment]

[0690] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0691] 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.

[0692] 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).

[0693] 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.

[0694] 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.

[0695] 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).

[0696] 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.

[0697] 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.

[0698] 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.

[0699] 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.

[0700] 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.

[0701] 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.

[0702] 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".

[0703] This invention is implemented within an integrated system that includes a user terminal, a server for processing information, and an interface. Users access the learning system using a terminal such as a smartphone or tablet and begin their individual learning experience. The program's processing is described below in natural language.

[0704] First, the user inputs their learning history and performance data into their device, and this information is sent to the server. The device formats the data appropriately and transmits it using a secure communication protocol to ensure data consistency and security.

[0705] The server analyzes the received data and visualizes the user's academic ability and learning style. The analytical techniques used here include machine learning algorithms and data mining methods. This clearly identifies the user's strengths and weaknesses.

[0706] Based on the analysis results, the server generates a learning plan that best suits the user's learning goals. This plan is designed to leverage the user's strengths while overcoming their weaknesses and includes specific learning materials and practice exercises.

[0707] The server also automatically generates practice problems that focus on areas where the user struggles. These problems are structured to gradually increase in complexity and are provided with explanations. By working through them, users can gradually improve their skills.

[0708] The generated learning plans and practice exercises are provided to the user via the device. Users access these through the interface and use them for daily learning. The interface is designed to be intuitive and enhance the user experience.

[0709] Learning progress and results are periodically sent from the device to the server. The server analyzes this data and generates feedback tailored to the user's situation. This feedback is then incorporated into the next learning plan, enabling continuous learning improvement.

[0710] This invention enables a specific operational model in which users can enjoy a learning experience that is optimal for them, without needing individualized instruction.

[0711] The following describes the processing flow.

[0712] Step 1:

[0713] The user uses the device to input their past learning history and current learning goals. The device receives this data, formats it, and prepares it for processing.

[0714] Step 2:

[0715] The terminal sends the data entered by the user to the server. A secure communication protocol is used for transmission, ensuring the security and integrity of the data.

[0716] Step 3:

[0717] The server analyzes the user's past learning history and academic ability based on the received data. It uses machine learning algorithms to identify the user's strengths and weaknesses and evaluate their learning style.

[0718] Step 4:

[0719] Based on the analysis results, the server generates a learning plan optimized for the user's current learning needs. The plan includes specific learning materials and exercises, customized to match the user's learning objectives.

[0720] Step 5:

[0721] The server automatically generates practice problems to address the user's areas of weakness. These problems include gradual difficulty adjustments and detailed explanations, designed to make it easier for users to understand the material.

[0722] Step 6:

[0723] The terminal presents the user with a learning plan and practice problems received from the server. The user can then use the provided information to carry out their daily studies.

[0724] Step 7:

[0725] As users progress through their learning, they input their learning progress and practice problem results into their device. The device collects this information and continuously transmits it to the server.

[0726] Step 8:

[0727] The server analyzes the submitted learning results and generates feedback for the user. This feedback is incorporated into the next learning plan and used to continuously improve the user's learning.

[0728] (Example 1)

[0729] 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".

[0730] Traditional learning systems suffer from a lack of adequate mechanisms for efficiently collecting individual users' learning history and performance data, and for providing optimal learning plans based on that data. Furthermore, the difficulty in automatically generating and providing practice problems tailored to users' weak areas in real time makes personalized learning optimization challenging. Additionally, there is a lack of mechanisms for appropriately reflecting feedback based on learning progress.

[0731] 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.

[0732] In this invention, the server includes means for collecting user history information and performance information, means for analyzing the collected information to identify the user's abilities and learning tendencies, and means for generating an optimal plan based on the identified learning tendencies and abilities. As a result, users can receive an optimal learning plan based on their individual learning history, practice problems that focus on areas of weakness, and feedback that is tailored to their learning progress.

[0733] "User" refers to an individual who uses the system to learn.

[0734] "History information" refers to records of learning activities that users have engaged in in the past.

[0735] "Performance information" refers to data that shows the user's learning outcomes and evaluations.

[0736] "Collection" refers to the process of gathering information, with the aim of storing it in a database.

[0737] "Analysis" refers to the process of analyzing collected information using appropriate methods to obtain useful insights.

[0738] "Ability" refers to an indicator that shows the user's academic capabilities.

[0739] "Learning tendencies" refer to the characteristics and behavioral patterns of users in their learning.

[0740] A "plan" refers to a series of learning activities designed to achieve the user's learning goals.

[0741] A "weakness area" refers to a learning area in which a user is relatively less proficient compared to other areas.

[0742] "Assignments" refer to problems and practical activities that users should engage in during their learning process.

[0743] "Display means" refers to an interface that allows users to visually confirm the generated information.

[0744] "Results information" refers to report data that shows the results of the user's learning activities.

[0745] "Correction" refers to the process of implementing improvements for the user's next learning activity.

[0746] A "communication protocol" refers to the procedures and rules necessary for sending and receiving digital information.

[0747] "Information device" refers to electronic equipment used for storing, processing, and transferring data.

[0748] "Notification" refers to the act of transmitting generated information to the user.

[0749] This invention provides a system for offering personalized learning experiences, in which a user-facing terminal and a server that processes information work in conjunction. Users input their history and performance information into the terminal. This is done using a dedicated application for smartphones and tablets, allowing users to easily input information through devices they use on a daily basis.

[0750] The terminal formats the entered information into an appropriate format and securely transmits it to the server using the SSL protocol. The server analyzes the entered data using an analysis system built with a programming language such as Python. Here, machine learning algorithms and data mining techniques are utilized to identify the user's abilities and learning tendencies, and to understand their strengths and weaknesses.

[0751] Based on the analysis results, the server uses a generative AI model to create an optimal learning plan for the user. Additionally, practice problems tailored to the user's weak areas are automatically generated. These generation processes utilize reinforcement learning algorithms, enabling step-by-step task setting according to the user's progress.

[0752] For example, for a user who struggles with differential and integral calculus, the server provides practice problems and explanations specifically tailored to that area. This makes it easier for the user to overcome their specific weaknesses.

[0753] These learning plans and exercises are presented to the user visually through the device's interface. The intuitively designed interface allows users to easily progress through their learning. Learning results and progress data are periodically sent to the server and incorporated as feedback for the next learning plan.

[0754] As described above, the present invention provides an individualized learning experience that maximizes the user's learning performance.

[0755] Example of a prompt:

[0756] "Use a generative AI model to create a learning plan for students who struggle with differential and integral calculus. Include specific practice problems and explanatory materials."

[0757] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0758] Step 1:

[0759] The user enters history information and performance information.

[0760] Users input data such as past test results, study time, and self-assessments using a dedicated smartphone application. The input data is converted into an appropriate data format, such as JSON. This prepares the input data for transmission to the server.

[0761] Step 2:

[0762] The device sends data to the server.

[0763] The terminal sends the converted data to the server using the SSL communication protocol. This step ensures data consistency and security. The data sent by the terminal is stored in the server's database.

[0764] Step 3:

[0765] The server analyzes the data.

[0766] The server uses a Python-based machine learning library to analyze the received data. Specifically, it employs clustering techniques to understand learning trends and classification algorithms to identify strengths and weaknesses. The analysis clarifies the learning characteristics of each user, which then forms the basis for the next step.

[0767] Step 4:

[0768] The server generates a training plan.

[0769] Based on the analysis results, the server uses a generated AI model to create an optimal learning plan for the user. In this step, reinforcement learning algorithms are used to select learning materials and tasks that match the user's goals. As a result, an individualized learning plan is output.

[0770] Step 5:

[0771] The server automatically generates practice problems.

[0772] The server automatically generates practice problem sets that focus on areas of particular difficulty. Hints and explanations are added sequentially to the problems to help resolve any questions. This output is then provided to the user in the next step.

[0773] Step 6:

[0774] The device provides information to the user.

[0775] The device displays the generated learning plan and practice problems in the user interface. A notification function informs the user when new learning materials are available. The user can progress through the learning process based on the provided information via an intuitively operable app.

[0776] Step 7:

[0777] The user inputs the learning results, and the device sends them to the server.

[0778] Users input the results and progress of their learning activities into their terminal. The entered information is formatted and sent to the server. This data transmission allows the server to receive important information that can be used to plan the next learning session.

[0779] Step 8:

[0780] The server evaluates the progress and provides feedback.

[0781] The server evaluates progress based on the received learning results. This process includes data analysis and comparison. The evaluation results are used as material for adjustments in the next learning plan and are displayed as feedback on the device. This continuous process allows users to feel the effects of their learning and continuously improve themselves.

[0782] (Application Example 1)

[0783] 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".

[0784] In modern education, it is necessary to provide learning experiences tailored to each individual learner, but this is difficult to achieve with traditional methods. Furthermore, it is essential to accurately identify learners' strengths and weaknesses and quickly provide optimal educational plans based on that information. Providing flexible, real-time feedback that matches learning progress is also a crucial challenge.

[0785] 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.

[0786] In this invention, the server includes means for collecting and analyzing the user's learning history and performance data, means for generating an educational plan based on identified learning methods and cognitive abilities, and means for providing knowledge tailored to the user using AI technology. This enables the provision of a learning experience optimized for each individual learner and effective feedback.

[0787] "Learning history" refers to the learning activities a user has undertaken and the records thereof.

[0788] "Performance data" refers to information that shows the results and performance obtained through user learning.

[0789] "Cognitive ability" refers to a user's ability and tendencies regarding understanding and problem-solving.

[0790] "Learning method" refers to the techniques and styles that users employ when progressing through their learning process.

[0791] An "educational plan" is a lesson plan designed to streamline the user's learning process and bring them closer to achieving their goals.

[0792] A "weakness area" refers to an academic field or topic that the user finds difficult to understand.

[0793] "Training exercises" are exercises or problem sets designed to improve specific skills or knowledge.

[0794] A "connection device" is a device that provides an interface for users to access digital learning content.

[0795] "Return information" refers to the results and feedback collected after a user's learning session, which are then incorporated into their next learning plan.

[0796] "AI technology" refers to technologies that use artificial intelligence methods to perform data analysis and problem solving.

[0797] "Knowledge provision" refers to the act of providing users with the information and learning materials they need for their studies.

[0798] A "generative AI model" is a model that uses AI to generate new data and information.

[0799] A "prompt statement" is a phrase used to give instructions to an AI or training model.

[0800] In the system implementing this invention, an integrated platform is constructed by fusing the user's terminal, a server, and an AI-based interface. Users access the learning support platform via a smartphone or tablet and input their learning history and achievement data. This data is transmitted to the server via a secure protocol.

[0801] The server uses AI technology to analyze the user's cognitive abilities and learning methods based on the received data. This involves a generative AI model, performing advanced calculations and data processing to generate the most suitable educational plan for the user. The educational plan includes training tasks designed to improve specific skills. These training tasks are automatically generated by AI technology based on the user's weak areas, and their difficulty level is adjusted in stages.

[0802] The generated educational plan and training tasks are provided to the user's device, and the learning activity progresses. Through the connected device, the user intuitively interacts with this content and continues learning. At the end of learning or periodically thereafter, the user's learning results are sent to the server as feedback information. The server re-analyzes this feedback information, generates feedback tailored to the user, and incorporates it into the next learning plan.

[0803] As a concrete example, a student aiming for university entrance exams uses this system to receive personalized learning materials to further strengthen their strong point, mathematics, and improve their weak point, English. The feedback provided by the server includes the message, "You are on track towards your next goal." An example of a prompt used in the generating AI model is, "Generate an optimal learning plan based on the user's learning history. Identify strengths and weaknesses and suggest appropriate learning materials and practice problems."

[0804] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0805] Step 1:

[0806] Users input their learning history and achievement data using their own devices. This input data is formatted appropriately by the device and sent to the server using a secure communication protocol.

[0807] Step 2:

[0808] The server analyzes the received data. Using a generative AI model, it processes the data to identify cognitive abilities and learning methods. Specifically, it analyzes each data point and applies statistical methods to identify the user's strengths and weaknesses.

[0809] Step 3:

[0810] The server generates an educational plan based on identified cognitive abilities and learning methods. It designs training tasks optimized for each user and outputs them as a properly formatted educational plan. In this process, machine learning algorithms are used to select tasks that focus on reinforcing the user's weak areas.

[0811] Step 4:

[0812] The server sends the generated educational plan and training assignments to the terminal. The terminal receives them and displays them intuitively through the user interface. The user then proceeds with their daily learning based on this.

[0813] Step 5:

[0814] When a user finishes learning or a specified period has elapsed, the learning results are sent from the device to the server as recovery information. The server re-analyzes this recovery information and identifies elements that should be reflected in the next educational plan.

[0815] Step 6:

[0816] The server utilizes a generative AI model based on the analyzed recovery information to create new feedback. This generated feedback includes instructions on the direction and level of achievement for the next learning session, prompting the user to prepare for the next learning session.

[0817] Step 7:

[0818] The server continuously facilitates user learning improvement by repeating the above process. The prompt used is: "Generate an optimal learning plan based on the user's learning history. Identify strengths and weaknesses and suggest appropriate learning materials and practice problems."

[0819] 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.

[0820] This invention is a system that analyzes a user's emotional state and appropriately adjusts learning content in order to improve the user's learning experience. The system consists of a terminal that includes means for collecting the user's learning history and performance data, an emotion engine that performs emotion analysis, and a server that processes this data and provides an optimal learning plan. The specific operational form of this system is shown below.

[0821] When a user begins learning through their device, the device collects data such as the user's voice, facial expressions, and input patterns, and sends this data to a server. The emotion engine analyzes the received data to identify the user's emotional state. For example, voice analysis can detect emotions such as stress, concentration, and joy.

[0822] The server integrates and evaluates the analysis results from the emotion engine with the user's learning data. If the user is focused, it presents problems of appropriate difficulty level; conversely, if the user is stressed, it can lower the difficulty level or suggest a plan to simplify the learning process.

[0823] The learning plans provided to users incorporate dynamic adjustments based on emotion analysis. For example, if stress is detected while a user is solving a differential calculus problem, the server can temporarily lower the difficulty of the problem or change the subject area to approach it from there. These adjustments reduce the burden on the user, allowing them to continue learning while maintaining motivation.

[0824] Furthermore, once a learning session ends, the device sends emotional feedback along with the results data to the server. The server then uses this feedback to inform the next learning plan, enabling continuous curriculum improvement. This feedback, tailored to emotional changes, enhances the quality of the learning experience.

[0825] Thus, the present invention makes it possible to integrate and process user emotions and learning outcomes, and to provide an optimal learning environment tailored to individual needs. Through this system, an efficient and stress-free learning experience is realized.

[0826] The following describes the processing flow.

[0827] Step 1:

[0828] The user accesses the designated learning platform using their device. The device then performs the necessary authentication and prepares to retrieve the user's learning history and past performance data.

[0829] Step 2:

[0830] Once the user begins learning, the device detects facial expressions and voice tone through video and audio analysis, collecting emotional data. This process utilizes devices such as cameras and microphones as needed.

[0831] Step 3:

[0832] The emotional data collected by the device is sent to a server and analyzed by an emotion engine. The emotion engine uses machine learning models to identify stress levels, concentration levels, happiness levels, and other factors.

[0833] Step 4:

[0834] The server generates an optimal learning plan based on the analysis results of the emotion engine and the user's learning history data. The plan includes the selection of learning materials and the adjustment of the difficulty level of practice problems, with the content determined according to the user's current emotional state.

[0835] Step 5:

[0836] The terminal provides the user with a learning plan received from the server. The user can then review and work through the recommended learning content via the interface.

[0837] Step 6:

[0838] Users progress through their learning according to the provided learning plan, while the device continuously collects emotional data and transmits it to the server in real time. This process allows for dynamic adjustment of the content in response to changes in emotions during learning.

[0839] Step 7:

[0840] After the learning session ends, the device sends data on the final learning results and emotional changes to the server. The server analyzes this data and generates feedback for the user.

[0841] Step 8:

[0842] The server uses the analysis results to make adjustments to the next learning plan. This feedback, along with the sentiment engine results, is recorded in the user's account and applied when the next learning session begins.

[0843] (Example 2)

[0844] 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".

[0845] Traditional learning systems lack dynamic adjustments to learning based on the user's emotional state, resulting in insufficient learning effectiveness. Furthermore, they lack features to adequately address situations where users are stressed or their concentration is waning. This leads to decreased user motivation and difficulty in sustained learning.

[0846] 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.

[0847] In this invention, the server includes means for collecting the user's learning history, mental state, and work data; means for analyzing the collected data to identify the user's emotional state; and means for dynamically adjusting the learning plan based on the identified emotional state. This makes it possible to provide an optimal learning experience that is tailored to the user's emotional state and level of concentration during learning.

[0848] "User learning history" refers to data about the learning activities a user has engaged in in the past, including the content, results, and duration of those activities.

[0849] "Mental state" refers to information that indicates the user's internal health and emotional state, and includes elements such as stress, concentration level, and excitement.

[0850] "Work data" refers to a record of specific operations and inputs performed by a user during a learning activity, including information such as keyboard input, mouse movements, and time.

[0851] "Emotional state" refers to information that indicates the user's current emotional state, identifying psychological elements such as joy, surprise, and stress.

[0852] A "learning plan" is a plan or curriculum created to optimize a user's learning progress, and it includes elements such as goals, methods, and learning materials.

[0853] "Means of dynamic adjustment" refers to methods or algorithms that allow the system to automatically change the learning content and difficulty level in real time in response to changes in the user's situation and conditions.

[0854] A "communication device" is a device or interface that exchanges information between a server and a user's terminal, and has the function of sending and receiving data.

[0855] "Means of analyzing feedback" refer to methods and processes for evaluating information about learning outcomes and emotional changes obtained from users and incorporating them into subsequent learning plans.

[0856] This invention is an advanced system for improving the user's learning experience, and consists of a terminal, a server, and an emotion engine. The following describes how this system is specifically implemented.

[0857] As soon as the user begins learning, the device uses its built-in camera and microphone to collect voice, facial expressions, and user input data in real time. This data is transmitted to the server via a secure communication protocol (e.g., SSL / TLS).

[0858] The server passes this received data to the emotion engine for analysis. The emotion engine uses emotion analysis software, such as "EmotionAPI," to identify the user's emotional state, including stress levels, concentration, and joy. Based on this analysis, the server dynamically adjusts the learning plan.

[0859] For example, if high stress is detected while a user is learning a calculus problem, the server can immediately change the plan, lowering the difficulty level or taking a different approach to reduce the burden on the user. This process allows the user to learn enthusiastically and efficiently.

[0860] Furthermore, once the learning session is complete, the device sends the user's learning results and emotional feedback to the server. The server then incorporates this information into the next learning plan, continuously improving the learning curriculum.

[0861] In this way, the server and terminal work together to create an advanced system that provides the optimal learning experience for the user. This technology reduces stress during learning and enables a flexible learning process that is tailored to each individual's learning pace.

[0862] Example prompt: "We have detected that the user's stress level is increasing while working on differential calculus problems. Please suggest adjustments to improve the quality of the learning experience."

[0863] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0864] Step 1:

[0865] The user begins learning, and the device collects voice, facial expressions, and input patterns in real time. The user's actions and reactions during learning serve as input for this step. The device uses its camera and microphone to capture the user's facial expressions and voice data, and also senses keyboard and touch input. This collected data is processed and temporarily stored for use in the next step.

[0866] Step 2:

[0867] The terminal transmits the collected data to the server via a secure communication protocol. Voice data, facial expression data, and input data are the specific inputs in this step. Communication security is maintained because the data is transmitted to the server using protocols such as SSL / TLS. The output of this step is the raw data that was transmitted.

[0868] Step 3:

[0869] The server analyzes the received data using an emotion engine. Voice and facial expression data are input, and based on this, the emotional state is obtained as output. Using "EmotionAPI" and other tools, the server extracts the user's stress level, concentration level, and feelings of joy. These analysis results are then used in the next step.

[0870] Step 4:

[0871] The server adjusts the learning plan to best suit the user's current learning progress based on the analyzed emotional data. Emotional state and learning history are used as input for this step. If the user is experiencing stress, the server uses a generative AI model to create a plan with adjusted difficulty. The generated learning plan is the output, providing a dynamic means to enhance the user's motivation to learn.

[0872] Step 5:

[0873] The generated plan is sent back from the server to the terminal and presented to the user. The input for this step is the generated learning plan, and the output is the information presented to the user visually or audibly. The terminal displays the tasks and explanations on the application using a user interface.

[0874] Step 6:

[0875] Once the learning process is complete, the device sends the learning results and feedback to the server. The user's learning progress and feedback data are inputs for this step. The transmitted feedback information is the output and will be used to improve future learning sessions.

[0876] Step 7:

[0877] The server analyzes the feedback information and incorporates it into the next learning plan. User feedback is the input, and revised learning plans and improvement suggestions are the output. This makes it possible to provide individualized support tailored to the user's learning progress, optimizing the long-term learning experience.

[0878] (Application Example 2)

[0879] 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".

[0880] In educational settings, providing learners with efficient and individualized learning experiences is crucial. However, uniform learning plans make it difficult to provide appropriate guidance to all learners with diverse learning styles and emotional states. Furthermore, dynamically adjusting learning plans according to learners' emotional states would improve the quality of learning, but such a system has not yet been established.

[0881] 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.

[0882] In this invention, the server includes means for collecting the user's learning history and work efficiency data, an emotion analysis device for analyzing the user's emotional state, and means for generating an optimal learning plan based on the identified learning style and emotional state. This makes it possible to provide dynamic learning plans tailored to each learner's emotional state and learning style.

[0883] "Learning history" refers to a record of the learning activities a user has undertaken in the past.

[0884] "Work efficiency data" refers to data that shows how efficiently users performed tasks during their learning process.

[0885] "Comprehension" refers to a user's ability to accurately understand the information they are given.

[0886] "Learning style" refers to the learning methods or styles that users prefer or find effective.

[0887] An "emotion analysis device" is a device that analyzes a user's voice and facial expressions to identify their emotional state.

[0888] A "learning plan" is a plan that outlines the learning steps and schedule necessary for a user to achieve their ultimate goal.

[0889] An "unfamiliar area" refers to a subject or area that the user does not fully understand or struggles with.

[0890] "Practice exercises" are problems or exercises that users work on to deepen their understanding.

[0891] "Communication means" refers to interface means used to provide information and content to users.

[0892] "Emotional feedback" refers to evaluations and metrics that reflect the user's emotional changes and states during the learning process.

[0893] The system that implements this application example begins by collecting the user's learning history and work efficiency data via a terminal and sending it to a server. The server processes the data obtained from audio and video using an emotion analysis device to identify the user's emotional state. Emotion analysis software can be used for this processing. Furthermore, by using algorithms to analyze the user's comprehension and learning style, this data is comprehensively evaluated and an optimal learning plan is generated. The generated learning plan is provided to the user via communication and practice tasks are presented as needed. Emotional feedback from the user during the learning process is collected by the terminal and sent back to the server. This feedback is used to improve the next learning plan. For example, if an elementary school student is learning math at home with a robot, and the robot detects a decrease in the user's concentration, it can provide problems with adjusted difficulty levels to create a better learning experience. Prompt sentences such as, "Based on this text, please think of specific ways a robot that provides help to middle school students can adjust the learning content while analyzing emotions," can be used in the generating AI model.

[0894] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0895] Step 1:

[0896] The terminal collects user voice, facial expressions, and input data in real time. Input includes data from a voice input device, camera, and keyboard. This data is then prepared for transfer to a server via communication. This step involves data collection and initial processing.

[0897] Step 2:

[0898] The server receives data transmitted from the terminal and performs analysis using an emotion analysis device. The received audio and video data is passed to emotion analysis software for processing to identify the user's emotional state (e.g., stress, excitement, concentration level). The output is information about the user's emotional state. This step involves determining the emotional state and analyzing the data.

[0899] Step 3:

[0900] The server integrates the obtained emotional state information with past learning history and work efficiency data, and uses a learning style analysis program to evaluate the user's academic ability. Inputs include emotional state information, learning history, and work efficiency data, and the output is the user's academic ability and learning style. This step establishes the user profile.

[0901] Step 4:

[0902] The server generates an optimal learning plan based on the user's academic ability and learning style. Using an adaptive learning algorithm, it creates learning steps tailored to the user, incorporating sentiment analysis information. Inputs include academic ability, learning style, and emotional state information, and the output is a customized learning plan. This step involves creating the learning plan.

[0903] Step 5:

[0904] The generated learning plan and appropriate practice tasks are transmitted to the terminal via communication means. The user proceeds with learning on the terminal according to the learning plan. As output, the learning content displayed to the user is provided. In this step, the learning content is provided and feedback is presented to the user.

[0905] Step 6:

[0906] After completing a learning session, the user enters feedback information into the device. This input includes the user's learning outcomes and emotional feedback. This information is prepared to be sent to the server to be used in the next session. This step involves collecting feedback information.

[0907] Step 7:

[0908] The server analyzes the feedback information received from the terminal and applies it to adjusting the next learning plan. It takes feedback information as input and incorporates it into the next improved learning plan. The output is the improved learning plan. This step involves continuous optimization of the learning plan.

[0909] 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.

[0910] 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.

[0911] 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.

[0912] 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.

[0913] 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.

[0914] 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.

[0915] 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.

[0916] 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.

[0917] 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."

[0918] 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.

[0919] 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.

[0920] 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.

[0921] 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.

[0922] 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.

[0923] 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.

[0924] 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.

[0925] 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.

[0926] 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.

[0927] 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.

[0928] 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.

[0929] 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 as being incorporated by reference.

[0930] The following is further disclosed regarding the embodiments described above.

[0931] (Claim 1)

[0932] A means of collecting user learning history and performance data,

[0933] A means for analyzing the collected data to identify the user's academic ability and learning style,

[0934] A means for generating an optimal learning plan based on the identified learning style and academic ability,

[0935] A method for automatically generating practice problems that focus on the user's weak areas,

[0936] An interface means for providing the user with a generated learning plan and practice problems,

[0937] A means for collecting learning results from users as feedback, analyzing the feedback, and reflecting it in the next learning plan,

[0938] A system that includes this.

[0939] (Claim 2)

[0940] The system according to claim 1, wherein the learning plan generation means includes an algorithm that, based on the analyzed data, selects a plurality of learning materials and combines them to create a learning curriculum optimized for the user.

[0941] (Claim 3)

[0942] The system according to claim 1, wherein the feedback collection means includes means for automatically analyzing the results of the learning content at the end of the user's learning session and making corrections to the results for the next learning method.

[0943] "Example 1"

[0944] (Claim 1)

[0945] A means of collecting user history information and performance information,

[0946] A means for analyzing the collected information to identify the user's abilities and learning tendencies,

[0947] Means for generating an optimal plan based on the identified learning tendencies and abilities,

[0948] A means of automatically generating tasks that focus on the user's weak areas,

[0949] A display means for providing the generated plans and tasks to the user,

[0950] A means for collecting learning results from users as result information, analyzing said result information, and reflecting it in the next plan,

[0951] A means for formatting user input information and transmitting it to an information device using a secure communication protocol,

[0952] The aforementioned information device provides means for notifying the user of the plan and issues generated by the analysis,

[0953] A system that includes this.

[0954] (Claim 2)

[0955] The system according to claim 1, wherein the plan generation means performs a process of selecting multiple learning materials based on the analyzed information and combining them to create a curriculum optimized for the user.

[0956] (Claim 3)

[0957] The system according to claim 1, wherein the results information collection means includes a process that automatically analyzes the results of the learning content at the end of the user's learning period and makes modifications to the results for use in the next learning method.

[0958] "Application Example 1"

[0959] (Claim 1)

[0960] A device for collecting user learning history and performance data,

[0961] A device that analyzes the collected data to identify the user's cognitive abilities and learning methods,

[0962] An apparatus for generating an optimal educational plan based on the identified learning methods and cognitive abilities,

[0963] A device that automatically creates training tasks that focus on the user's weak areas,

[0964] A connection device for providing the generated educational plan and training tasks to the user,

[0965] A device that collects learning results from users as recovery information, analyzes the recovery information, and reflects it in the next educational plan,

[0966] A device that uses AI technology to select learning materials for enhancing and improving learning, and provides knowledge tailored to the user,

[0967] A system that includes this.

[0968] (Claim 2)

[0969] The system according to claim 1, comprising a method for creating an optimized lesson plan for a user by selecting multiple educational materials and combining them based on the analyzed data of the educational plan generation device.

[0970] (Claim 3)

[0971] The system according to claim 1, wherein the recovery information collection device includes a device that automatically analyzes the results of the user's learning activity at the end of the user's learning activity and makes corrections to the results for use in the next learning method, and a device that outputs the results obtained using a generated AI model as a prompt message.

[0972] "Example 2 of combining an emotion engine"

[0973] (Claim 1)

[0974] A means for collecting the user's learning history, mental state, and work data,

[0975] A means for analyzing the collected data to identify the user's emotional state,

[0976] A means for dynamically adjusting the learning plan based on the identified emotional state,

[0977] A means to automatically change the difficulty level of practice problems according to the user's mental state,

[0978] A communication device for providing the user with a generated learning plan and adjusted practice problems,

[0979] A means for collecting user feedback on learning results and mental state, analyzing the feedback, and reflecting it in the next learning plan,

[0980] A system that includes this.

[0981] (Claim 2)

[0982] The system according to claim 1, comprising an algorithm for providing to the user an optimized combination of multiple learning materials based on the analyzed data, according to the user's emotional state.

[0983] (Claim 3)

[0984] The system according to claim 1, comprising means for analyzing emotional feedback at the end of a user's learning session and making corrections to the results for use in the next learning method.

[0985] "Application example 2 when combining with an emotional engine"

[0986] (Claim 1)

[0987] A means of collecting user learning history and work efficiency data,

[0988] A means for analyzing the collected information to identify the user's comprehension level and learning style,

[0989] An emotion analysis device for analyzing the emotional state of a user,

[0990] A means for generating an optimal learning plan based on the identified learning style and emotional state,

[0991] A means of automatically generating practice tasks that focus on the user's weak areas,

[0992] A communication means for providing the user with the generated learning plan and practice assignments,

[0993] A means for collecting emotional feedback from users, analyzing the feedback, and reflecting it in the next learning plan,

[0994] A system that includes this.

[0995] (Claim 2)

[0996] The system according to claim 1, wherein the learning plan generation means includes an algorithm that, based on the analyzed information, selects a plurality of learning materials and combines them to create a learning course optimized for the user.

[0997] (Claim 3)

[0998] The system according to claim 1, wherein the feedback collection means includes means for automatically analyzing the results of the user's learning at the end of the learning period and making modifications based on the results for the next learning method. [Explanation of Symbols]

[0999] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A device for collecting user learning history and performance data, A device that analyzes the collected data to identify the user's cognitive abilities and learning methods, An apparatus for generating an optimal educational plan based on the identified learning methods and cognitive abilities, A device that automatically creates training tasks that focus on the user's weak areas, A connection device for providing the generated educational plan and training tasks to the user, A device that collects learning results from users as recovery information, analyzes the recovery information, and reflects it in the next educational plan, A device that uses AI technology to select learning materials for enhancing and improving learning, and provides knowledge tailored to the user, A system that includes this.

2. The system according to claim 1, wherein the device for generating educational plans includes a method for selecting multiple educational materials based on the analyzed data and combining them to create an educational lesson plan optimized for the user.

3. The system according to claim 1, comprising a device for collecting recovery information, a device for automatically analyzing the results of the user's learning activity at the end of the user's learning activity and making corrections to the results for use in the next learning method, and a device for outputting the results obtained using a generated AI model as a prompt message.

Images