System

Abstract

An object of a system according to an embodiment is to provide optimal learning contents corresponding to individual learning needs of learners.SOLUTION: A system according to an embodiment includes a learning need analysis unit, a customized instructor generation unit, and a learning contents providing unit. The learning needs analysis unit analyzes the learning needs of the learner. The customized instructor generation unit generates a customized instructor based on the learning needs analyzed by the learning needs analysis unit. The learning contents providing unit provides optimum learning contents to the learner by using the customized instructor generated by the customized instructor generation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technologies have not adequately provided optimal learning content that meets the individual learning needs of learners, and there is room for improvement.

[0005] The system according to the embodiment aims to provide optimal learning content that meets the individual learning needs of each learner. [Means for solving the problem]

[0006] The system according to the embodiment includes a learning needs analysis unit, a customized instructor generation unit, and a learning content provision unit. The learning needs analysis unit analyzes the learning needs of a learner. The customized instructor generation unit generates a customized instructor based on the learning needs analyzed by the learning needs analysis unit. The learning content provision unit provides optimal learning content to the learner using the customized instructor generated by the customized instructor generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can provide optimal learning content that meets the individual learning needs of each learner. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices 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), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The enhanced tutor creator system according to an embodiment of the present invention provides a learning environment in which learners can use their own enhanced tutor creator. This system uses a generation AI to generate a customized tutor tailored to each learner's individual learning needs, and the tutor provides optimal learning content to the learner. This allows the enhanced tutor creator system to generate a customized tutor tailored to each learner's individual learning needs and provide optimal learning content.

[0029] An enhanced instructor creator system according to an embodiment includes a learning needs analysis unit, a customized instructor generation unit, and a learning content provision unit. The learning needs analysis unit analyzes the learning needs of a learner. For example, the learning needs analysis unit analyzes the learner's learning goals and learning style. The learning needs analysis unit can also collect and analyze background information of the learner. For example, the learning needs analysis unit analyzes the learner's past learning history and performance data to identify the learner's learning needs. The customized instructor generation unit generates a customized instructor based on the learning needs analyzed by the learning needs analysis unit. For example, the customized instructor generation unit uses a generation AI to generate an instructor based on the learner's learning needs. The customized instructor generation unit can also use the generation AI to generate an optimal instructor based on the learner's level of understanding and goals. For example, the generation AI receives the learner's learning needs as prompts and generates a customized instructor based on the prompts. The learning content provision unit provides optimal learning content to the learner using the customized instructor generated by the customized instructor generation unit. For example, the learning content provision unit uses the customized instructor generated by the generation AI to pose questions based on the learner's level of understanding and provide explanations. The learning content provider can also adjust the learning content according to the learner's progress to support effective learning. For example, the learning content provider uses a generation AI to monitor the learner's progress and suggest the next learning content. This allows the enhanced instructor creator system according to the embodiment to generate a customized instructor according to the learner's individual learning needs and provide optimal learning content.

[0030] The learning needs analysis unit can analyze a learner's past learning history and performance data and generate a customized tutor based on their long-term learning trends. For example, the learning needs analysis unit analyzes a learner's past test results and assignment submission status to understand their long-term learning trends. For example, if a learner's grades in a particular area of ​​mathematics are consistently low, a customized tutor specialized in that area is generated. The learning needs analysis unit also analyzes the learner's activity history on the online learning platform to identify the time of day when the learner can best concentrate on studying. For example, a customized tutor that suggests an optimal study schedule is generated. The learning needs analysis unit also sets future learning goals based on the learner's past learning performance data and generates a customized tutor accordingly. For example, for a learner aiming to take a university entrance exam, a tutor specialized in entrance exam preparation is generated. This makes it possible to generate more sophisticated customized tutors based on the learner's past learning history and performance data.

[0031] The learning needs analysis unit analyzes the learner's non-verbal behavior to more precisely grasp their learning needs. For example, the learning needs analysis unit analyzes the learner's facial expressions using a camera to determine whether they are concentrating. For example, if they are not concentrating, a customized instructor is generated that suggests taking a break. The learning needs analysis unit also analyzes the learner's posture using a sensor to measure their level of fatigue. For example, if they have been sitting for a long time, a customized instructor is generated that suggests stretching. The learning needs analysis unit also analyzes the learner's eye movements to identify where their attention is focused. For example, if their gaze is fixed on a particular problem for a long time, a customized instructor is generated that provides additional explanation for that problem. In this way, by analyzing the learner's non-verbal behavior, it is possible to more precisely grasp their learning needs.

[0032] The learning needs analysis unit can analyze a learner's hobbies and interests and, based on that, generate a customized tutor that combines learning content with entertainment elements. The learning needs analysis unit, for example, collects a learner's hobbies and interests from questionnaires or profile information and customizes learning content based on that. For example, for a learner who likes music, a customized tutor that provides music-related math problems is generated. The learning needs analysis unit also analyzes the learner's social media and online activities to identify topics of interest. For example, for a learner who is interested in sports, a customized tutor that provides data analysis problems using sports statistics is generated. The learning needs analysis unit also analyzes the learner's past learning history to identify learning content that is likely to interest them. For example, for a learner who is interested in history, a customized tutor that provides English reading comprehension questions based on historical events is generated. In this way, a customized tutor that combines learning content with entertainment elements can be generated based on the learner's hobbies and interests.

[0033] The learning needs analysis unit can generate customized instructors corresponding to different learning styles, allowing learners to select an instructor based on their preferences. The learning needs analysis unit, for example, collects learners' learning styles from questionnaires or profile information and generates a customized instructor based on that information. For example, for visual learners, it generates an instructor that makes extensive use of visual content. The learning needs analysis unit also analyzes the learner's past learning history and identifies which learning style is most effective. For example, for auditory learners, it generates an instructor that focuses on audio commentary. The learning needs analysis unit also provides an interface that allows learners to select their own learning style, and generates a customized instructor based on that. For example, for tactile learners, it generates an instructor that provides interactive experiments and simulations. In this way, customized instructors corresponding to different learning styles can be generated, allowing learners to select an instructor based on their preferences.

[0034] The learning content providing unit can analyze the learner's real-time reactions and instantly adjust the learning content based on those reactions. For example, the learning content providing unit analyzes the learner's facial expressions and voice in real time to determine the learner's level of comprehension and concentration. For example, if the learner's understanding is not progressing, the learning content providing unit provides additional explanation. The learning content providing unit also analyzes the learner's physiological data (for example, heart rate and electrodermal activity) in real time to determine the learner's stress level. For example, if the learner is highly stressed, the learning content providing unit provides questions with a lower level of difficulty. The learning content providing unit also analyzes the learner's operation history in real time to identify where the learner is having difficulty. For example, if the learner is taking a long time to solve a particular problem, the learning content providing unit provides a hint. This makes it possible to instantly adjust the learning content based on the learner's real-time reactions.

[0035] The learning content providing unit enables instructors generated by the generation AI to explain the same content from multiple perspectives in order to deepen the learner's understanding. For example, the learning content providing unit generates instructors who use multiple approaches to explain the same content from different perspectives. For example, a mathematics problem may be explained using both an algebraic approach and a geometric approach. The learning content providing unit also generates instructors who use different media (e.g., text, video, audio) in order to deepen the learner's understanding. For example, in addition to text explanations, it may provide video explanations. The learning content providing unit also generates instructors who provide explanations from multiple perspectives so that the learner can choose the explanation method that suits them best. For example, it generates an instructor that combines theoretical explanations with practical examples. This allows the same content to be explained from multiple perspectives in order to deepen the learner's understanding.

[0036] The learning content providing unit can gamify the learning content, allowing learners to learn while having fun. The learning content providing unit, for example, converts the learning content into a game format, allowing learners to learn while having fun. For example, it provides a game in which learners earn points by solving math problems and level up. The learning content providing unit also adjusts the learning content according to the progress in the game, allowing learners to learn at their own pace. For example, it gradually increases the difficulty level to maintain learners' motivation. Furthermore, by gamifying the learning content, the learning content providing unit allows learners to learn with a competitive spirit. For example, it provides a ranking function that allows learners to compete with other learners for the highest score. In this way, the learning content is gamified, allowing learners to learn while having fun.

[0037] The learning content providing unit can provide learning content on-demand so that learners can learn at their own pace. For example, the learning content providing unit builds a system that provides learning content on-demand so that learners can learn at their own pace. For example, it provides video lectures that learners can access at any time they like. The learning content providing unit also develops a system that automatically suggests the next content to be learned according to the learner's progress. For example, it suggests the next unit after a specific unit has been cleared. The learning content providing unit also builds a system that provides learning content in stages so that learners can learn at their own pace. For example, it provides a step-by-step learning plan from basic to advanced. This makes it possible to provide learning content on-demand so that learners can learn at their own pace.

[0038] The learning progress monitoring unit can analyze a learner's progress data, identify long-term learning patterns, and provide feedback. For example, the learning progress monitoring unit collects a learner's progress data over a long period of time and analyzes their learning patterns. For example, if a learner's grades in a particular unit are consistently low, additional learning resources for that unit are provided. The learning progress monitoring unit can also identify areas where learning needs to be strengthened based on the learner's progress data and provide individualized feedback. For example, if a particular skill is lacking, it can provide practice questions to strengthen that skill. The learning progress monitoring unit can also analyze a learner's progress data and propose a study plan to maximize the effectiveness of learning. For example, it can propose an optimal study schedule based on past data. In this way, it is possible to analyze a learner's progress data, identify long-term learning patterns, and provide feedback.

[0039] The learning progress monitoring unit can visualize the learner's progress and make it intuitively understandable using graphs and charts. The learning progress monitoring unit, for example, visualizes the learner's progress data using graphs and charts to make it intuitively understandable. For example, it displays the learning progress status using a line graph. The learning progress monitoring unit also provides a dashboard that visualizes the learning results based on the learner's progress data. For example, it displays the grades for each unit using a bar graph. The learning progress monitoring unit also updates the learner's progress data in real time to visualize the latest learning status. For example, it displays the learning progress using a pie chart to show the degree of achievement. In this way, the learner's progress is visualized and can be intuitively understood using graphs and charts.

[0040] The learning progress monitoring unit can compare a learner's progress with other learners and provide feedback that stimulates a competitive spirit. For example, the learning progress monitoring unit compares a learner's progress data with other learners and provides feedback that stimulates a competitive spirit. For example, it displays the performance ranking within a class. The learning progress monitoring unit also compares the learner's progress data with other learners and provides messages that stimulate a competitive spirit. For example, it displays the difference between the learner and a higher-ranked learner. The learning progress monitoring unit also updates the learner's progress data in real time and displays the comparison results with other learners. For example, it compares the learner's performance in a specific unit with other learners. In this way, the learner's progress is compared with other learners and feedback that stimulates a competitive spirit is provided.

[0041] The learning progress monitoring unit can provide rewards and badges according to the learner's progress, thereby enhancing the learner's sense of accomplishment. For example, the learning progress monitoring unit provides rewards and badges when a specific goal is achieved based on the learner's progress data. For example, a badge is earned when a specific unit is cleared. The learning progress monitoring unit also updates the learner's progress data in real time, and provides rewards and badges according to the level of achievement. For example, a reward is provided when continuous learning is performed. The learning progress monitoring unit also builds a reward system based on the learner's progress data to enhance the learner's sense of accomplishment. For example, a badge is earned when a specific skill is mastered. In this way, rewards and badges are provided according to the learner's progress, enhancing the learner's sense of accomplishment.

[0042] The learning environment optimization unit can customize and provide environmental sounds and music to improve the learner's concentration. The learning environment optimization unit, for example, customizes and provides environmental sounds and music to improve the learner's concentration. For example, it provides a learning environment with the sounds of nature or classical music as a background. The learning environment optimization unit also analyzes the learner's physiological data (e.g., heart rate and electrodermal activity) and provides music to improve concentration. For example, it selects music that stabilizes the heart rate. The learning environment optimization unit also analyzes the learner's past learning history and provides environmental sounds and music to improve concentration. For example, if a particular piece of music improves concentration, it provides that music. In this way, environmental sounds and music are customized and provided to improve the learner's concentration.

[0043] The learning environment optimization unit can analyze the learner's physiological data and propose the optimal learning environment. The learning environment optimization unit, for example, analyzes the learner's heart rate in real time and proposes the optimal learning environment. For example, it proposes an environment that stabilizes the heart rate. The learning environment optimization unit also analyzes the learner's brain waves and proposes the optimal learning environment. For example, it proposes an environment that improves concentration. The learning environment optimization unit also builds a system that proposes the optimal learning environment based on the learner's physiological data. For example, it adjusts the environment based on heart rate and brain wave data. In this way, the learner's physiological data is analyzed and the optimal learning environment is proposed.

[0044] The learning environment optimization unit can customize the learning environment by providing digital art and background images according to the learner's preferences. The learning environment optimization unit, for example, provides digital art and background images according to the learner's preferences and customizes the learning environment. For example, a natural landscape or abstract art may be set as the background. The learning environment optimization unit also analyzes the learner's past learning history and provides digital art and background images according to the learner's preferences. For example, if a particular background image improves concentration, it provides that image. The learning environment optimization unit also provides an interface that allows the learner to select digital art and background images according to their preferences. For example, the learner may upload an image they like and set it as the background. In this way, digital art and background images according to the learner's preferences are provided and the learning environment is customized.

[0045] The learning environment optimization unit can analyze the time periods when a learner can best concentrate and recommend studying during those time periods. The learning environment optimization unit, for example, analyzes the learner's past learning history to identify the time periods when the learner can best concentrate. For example, if learning is most effective during a particular time period, it recommends studying during that time period. The learning environment optimization unit also analyzes the learner's physiological data (e.g., heart rate and electrodermal activity) to identify the time periods when the learner can best concentrate. For example, it recommends studying during times when the heart rate is stable. The learning environment optimization unit also analyzes the learner's emotional state in real time to identify the time periods when the learner can best concentrate. For example, it recommends studying during times when the learner is relaxed. In this way, it analyzes the time periods when the learner can best concentrate and recommends studying during those times.

[0046] The learning community building unit can match optimal learning partners based on the learner's interests and goals. For example, the learning community building unit collects learners' interests and goals from questionnaires or profile information and matches optimal learning partners based on that. For example, it matches learners with the same goals. The learning community building unit also analyzes the learner's past learning history to match optimal learning partners. For example, it matches learners who have learning experience in the same field. The learning community building unit also analyzes the learner's physiological data (for example, heart rate or electrodermal activity) to match optimal learning partners. For example, it matches learners who can study at the same rhythm. In this way, the optimal learning partners are matched based on the learner's interests and goals.

[0047] The learning community building unit can provide a virtual classroom where learners can interact with each other in real time. The learning community building unit, for example, provides a virtual classroom where learners can interact with each other in real time. For example, learners communicate with each other through video chat or text chat. The learning community building unit also provides a virtual classroom where learners can learn together and promotes real-time discussions and group work. For example, learners can work together using an online whiteboard. The learning community building unit also provides a virtual classroom where learners can interact with each other in real time and ask questions and exchange opinions about the learning content. For example, the learning community building unit holds sessions where instructors provide feedback in real time. In this way, a virtual classroom where learners can interact with each other in real time is provided.

[0048] The learning community construction unit can match learners from different regions and cultural areas and provide learning from a global perspective. The learning community construction unit, for example, matches learners from different regions and cultural areas and provides learning from a global perspective. For example, learning diverse perspectives through intercultural exchange. The learning community construction unit also matches learners from different regions and cultural areas based on learner profile information. For example, it matches learners who are learning different languages. The learning community construction unit also analyzes learners' past learning history and matches learners from different regions and cultural areas. For example, it matches learners with different cultural backgrounds. In this way, learners from different regions and cultural areas are matched and learning from a global perspective is provided.

[0049] The learning community building unit can provide collaboration tools that allow learners to work together on a project. The learning community building unit provides, for example, collaboration tools that allow learners to work together on a project. For example, it provides an online whiteboard and document sharing function. The learning community building unit also provides collaboration tools that allow learners to work together in real time. For example, it provides a platform that integrates video conferencing and chat functions. The learning community building unit also provides collaboration tools that allow learners to manage the progress of a project. For example, it provides task management and progress reporting functions. In this way, collaboration tools are provided that allow learners to work together on a project.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The learning needs analysis unit analyzes the learning needs of the learner. For example, the learning needs analysis unit analyzes the learner's learning goals and learning style. The learning needs analysis unit can also collect and analyze background information of the learner. For example, the learning needs analysis unit analyzes the learner's past learning history and performance data to identify the learning needs. The customized instructor generation unit generates a customized instructor based on the learning needs analyzed by the learning needs analysis unit. For example, the customized instructor generation unit uses a generation AI to generate an instructor that meets the learner's learning needs. The customized instructor generation unit can also use the generation AI to generate an optimal instructor based on the learner's level of understanding and goals. For example, the customized instructor generation unit receives the learner's learning needs as prompts and generates a customized instructor based on the prompts. The learning content provision unit provides optimal learning content to the learner using the customized instructor generated by the customized instructor generation unit. For example, the learning content provision unit uses the customized instructor generated by the generation AI to pose questions that meet the learner's level of understanding and provide explanations. The learning content provision unit can also adjust the learning content according to the learner's progress to support effective learning. For example, the learning content providing unit uses a generation AI to monitor the learner's progress and suggest the next learning content. As a result, the enhanced instructor creator system according to the embodiment can generate a customized instructor according to the individual learning needs of the learner and provide optimal learning content.

[0052] The learning needs analysis unit can analyze a learner's past learning history and performance data and generate a customized tutor based on their long-term learning trends. For example, the learning needs analysis unit analyzes a learner's past test results and assignment submission status to understand their long-term learning trends. For example, if a learner's grades in a particular area of ​​mathematics are consistently low, a customized tutor specialized in that area is generated. The learning needs analysis unit also analyzes the learner's activity history on the online learning platform to identify the time of day when the learner can best concentrate on studying. For example, a customized tutor that suggests an optimal study schedule is generated. The learning needs analysis unit also sets future learning goals based on the learner's past learning performance data and generates a customized tutor accordingly. For example, for a learner aiming to take a university entrance exam, a tutor specialized in entrance exam preparation is generated. This makes it possible to generate more sophisticated customized tutors based on the learner's past learning history and performance data.

[0053] The learning needs analysis unit analyzes the learner's non-verbal behavior to more precisely grasp their learning needs. For example, the learning needs analysis unit analyzes the learner's facial expressions using a camera to determine whether they are concentrating. For example, if they are not concentrating, a customized instructor is generated that suggests taking a break. The learning needs analysis unit also analyzes the learner's posture using a sensor to measure their level of fatigue. For example, if they have been sitting for a long time, a customized instructor is generated that suggests stretching. The learning needs analysis unit also analyzes the learner's eye movements to identify where their attention is focused. For example, if their gaze is fixed on a particular problem for a long time, a customized instructor is generated that provides additional explanation for that problem. In this way, by analyzing the learner's non-verbal behavior, it is possible to more precisely grasp their learning needs.

[0054] The learning needs analysis unit can analyze a learner's hobbies and interests and, based on that, generate a customized tutor that combines learning content with entertainment elements. The learning needs analysis unit, for example, collects a learner's hobbies and interests from questionnaires or profile information and customizes learning content based on that. For example, for a learner who likes music, a customized tutor that provides music-related math problems is generated. The learning needs analysis unit also analyzes the learner's social media and online activities to identify topics of interest. For example, for a learner who is interested in sports, a customized tutor that provides data analysis problems using sports statistics is generated. The learning needs analysis unit also analyzes the learner's past learning history to identify learning content that is likely to interest them. For example, for a learner who is interested in history, a customized tutor that provides English reading comprehension questions based on historical events is generated. In this way, a customized tutor that combines learning content with entertainment elements can be generated based on the learner's hobbies and interests.

[0055] The learning needs analysis unit can generate customized instructors corresponding to different learning styles, allowing learners to select an instructor based on their preferences. The learning needs analysis unit, for example, collects learners' learning styles from questionnaires or profile information and generates a customized instructor based on that information. For example, for visual learners, it generates an instructor that makes extensive use of visual content. The learning needs analysis unit also analyzes the learner's past learning history and identifies which learning style is most effective. For example, for auditory learners, it generates an instructor that focuses on audio commentary. The learning needs analysis unit also provides an interface that allows learners to select their own learning style, and generates a customized instructor based on that. For example, for tactile learners, it generates an instructor that provides interactive experiments and simulations. In this way, customized instructors corresponding to different learning styles can be generated, allowing learners to select an instructor based on their preferences.

[0056] The learning content providing unit can analyze the learner's real-time reactions and instantly adjust the learning content based on those reactions. For example, the learning content providing unit analyzes the learner's facial expressions and voice in real time to determine the learner's level of comprehension and concentration. For example, if the learner's understanding is not progressing, the learning content providing unit provides additional explanation. The learning content providing unit also analyzes the learner's physiological data (for example, heart rate and electrodermal activity) in real time to determine the learner's stress level. For example, if the learner is highly stressed, the learning content providing unit provides questions with a lower level of difficulty. The learning content providing unit also analyzes the learner's operation history in real time to identify where the learner is having difficulty. For example, if the learner is taking a long time to solve a particular problem, the learning content providing unit provides a hint. This makes it possible to instantly adjust the learning content based on the learner's real-time reactions.

[0057] The learning content providing unit enables instructors generated by the generation AI to explain the same content from multiple perspectives in order to deepen the learner's understanding. For example, the learning content providing unit generates instructors who use multiple approaches to explain the same content from different perspectives. For example, a mathematics problem may be explained using both an algebraic approach and a geometric approach. The learning content providing unit also generates instructors who use different media (e.g., text, video, audio) in order to deepen the learner's understanding. For example, in addition to text explanations, it may provide video explanations. The learning content providing unit also generates instructors who provide explanations from multiple perspectives so that the learner can choose the explanation method that suits them best. For example, it generates an instructor that combines theoretical explanations with practical examples. This allows the same content to be explained from multiple perspectives in order to deepen the learner's understanding.

[0058] The processing flow of the first embodiment will be briefly explained below.

[0059] Step 1: The learning needs analysis unit analyzes the learner's learning needs. For example, the learning needs analysis unit analyzes the learner's learning goals and learning style, and can also collect and analyze the learner's background information. Specifically, the learning needs are identified by analyzing the learner's past learning history and performance data. Step 2: The customized instructor generation unit generates a customized instructor based on the learning needs analyzed by the learning needs analysis unit. For example, the customized instructor generation unit uses a generation AI to generate an instructor that meets the learner's learning needs. It can also generate an optimal instructor based on the learner's level of understanding and goals. Specifically, the generation AI receives the learner's learning needs as a prompt and generates a customized instructor based on that. Step 3: The learning content provider uses the customized tutor generated by the customized tutor generator to provide optimal learning content to the learner. For example, the learning content provider uses the customized tutor generated by the generation AI to pose questions based on the learner's level of understanding and provide explanations. It can also adjust the learning content according to the learner's progress to support effective learning. Specifically, the generation AI monitors the learner's progress and suggests what content to study next.

[0060] (Example 2) The enhanced tutor creator system according to an embodiment of the present invention provides a learning environment in which learners can use their own enhanced tutor creator. This system uses a generation AI to generate a customized tutor tailored to each learner's individual learning needs, and the tutor provides optimal learning content to the learner. This allows the enhanced tutor creator system to generate a customized tutor tailored to each learner's individual learning needs and provide optimal learning content.

[0061] An enhanced instructor creator system according to an embodiment includes a learning needs analysis unit, a customized instructor generation unit, and a learning content provision unit. The learning needs analysis unit analyzes the learning needs of a learner. For example, the learning needs analysis unit analyzes the learner's learning goals and learning style. The learning needs analysis unit can also collect and analyze background information of the learner. For example, the learning needs analysis unit analyzes the learner's past learning history and performance data to identify the learner's learning needs. The customized instructor generation unit generates a customized instructor based on the learning needs analyzed by the learning needs analysis unit. For example, the customized instructor generation unit uses a generation AI to generate an instructor based on the learner's learning needs. The customized instructor generation unit can also use the generation AI to generate an optimal instructor based on the learner's level of understanding and goals. For example, the generation AI receives the learner's learning needs as prompts and generates a customized instructor based on the prompts. The learning content provision unit provides optimal learning content to the learner using the customized instructor generated by the customized instructor generation unit. For example, the learning content provision unit uses the customized instructor generated by the generation AI to pose questions based on the learner's level of understanding and provide explanations. The learning content provider can also adjust the learning content according to the learner's progress to support effective learning. For example, the learning content provider uses a generation AI to monitor the learner's progress and suggest the next learning content. This allows the enhanced instructor creator system according to the embodiment to generate a customized instructor according to the learner's individual learning needs and provide optimal learning content.

[0062] The learning needs analysis unit can analyze a learner's past learning history and performance data and generate a customized tutor based on their long-term learning trends. For example, the learning needs analysis unit analyzes a learner's past test results and assignment submission status to understand their long-term learning trends. For example, if a learner's grades in a particular area of ​​mathematics are consistently low, a customized tutor specialized in that area is generated. The learning needs analysis unit also analyzes the learner's activity history on the online learning platform to identify the time of day when the learner can best concentrate on studying. For example, a customized tutor that suggests an optimal study schedule is generated. The learning needs analysis unit also sets future learning goals based on the learner's past learning performance data and generates a customized tutor accordingly. For example, for a learner aiming to take a university entrance exam, a tutor specialized in entrance exam preparation is generated. This makes it possible to generate more sophisticated customized tutors based on the learner's past learning history and performance data.

[0063] The learning needs analysis unit analyzes the learner's non-verbal behavior to more precisely grasp their learning needs. For example, the learning needs analysis unit analyzes the learner's facial expressions using a camera to determine whether they are concentrating. For example, if they are not concentrating, a customized instructor is generated that suggests taking a break. The learning needs analysis unit also analyzes the learner's posture using a sensor to measure their level of fatigue. For example, if they have been sitting for a long time, a customized instructor is generated that suggests stretching. The learning needs analysis unit also analyzes the learner's eye movements to identify where their attention is focused. For example, if their gaze is fixed on a particular problem for a long time, a customized instructor is generated that provides additional explanation for that problem. In this way, by analyzing the learner's non-verbal behavior, it is possible to more precisely grasp their learning needs.

[0064] The learning needs analysis unit can use the emotion estimation function to analyze the emotional state of a learner in real time and generate a customized instructor according to that emotion. The learning needs analysis unit, for example, analyzes the learner's facial expression to estimate the emotional state in real time. For example, if the learner is feeling stressed, a customized instructor is generated that suggests a learning method that will help the learner relax. The learning needs analysis unit also analyzes the learner's tone of voice to estimate the emotional state. For example, if the learner is excited, a customized instructor is generated that provides advice on how to improve concentration. The learning needs analysis unit also analyzes the learner's physiological data (for example, heart rate and electrodermal activity) to estimate the emotional state. For example, if the learner is relaxed, a customized instructor is generated that suggests the learner try more difficult problems. In this way, the emotional state of a learner can be analyzed in real time and a customized instructor according to that emotion can be generated.

[0065] The learning needs analysis unit can analyze a learner's hobbies and interests and, based on that, generate a customized tutor that combines learning content with entertainment elements. The learning needs analysis unit, for example, collects a learner's hobbies and interests from questionnaires or profile information and customizes learning content based on that. For example, for a learner who likes music, a customized tutor that provides music-related math problems is generated. The learning needs analysis unit also analyzes the learner's social media and online activities to identify topics of interest. For example, for a learner who is interested in sports, a customized tutor that provides data analysis problems using sports statistics is generated. The learning needs analysis unit also analyzes the learner's past learning history to identify learning content that is likely to interest them. For example, for a learner who is interested in history, a customized tutor that provides English reading comprehension questions based on historical events is generated. In this way, a customized tutor that combines learning content with entertainment elements can be generated based on the learner's hobbies and interests.

[0066] The learning needs analysis unit can generate customized instructors corresponding to different learning styles, allowing learners to select an instructor based on their preferences. The learning needs analysis unit, for example, collects learners' learning styles from questionnaires or profile information and generates a customized instructor based on that information. For example, for visual learners, it generates an instructor that makes extensive use of visual content. The learning needs analysis unit also analyzes the learner's past learning history and identifies which learning style is most effective. For example, for auditory learners, it generates an instructor that focuses on audio commentary. The learning needs analysis unit also provides an interface that allows learners to select their own learning style, and generates a customized instructor based on that. For example, for tactile learners, it generates an instructor that provides interactive experiments and simulations. In this way, customized instructors corresponding to different learning styles can be generated, allowing learners to select an instructor based on their preferences.

[0067] The learning needs analysis unit uses the emotion estimation function to analyze the environment in which the learner finds the most relaxing, and can generate a customized tutor that is optimal for that environment. The learning needs analysis unit, for example, analyzes the learner's emotional state in real time to identify a relaxing environment. For example, if learning in a quiet environment is effective, a customized tutor that is optimal for that environment is generated. The learning needs analysis unit also analyzes the learner's physiological data (e.g., heart rate and electrodermal activity) to identify a relaxing environment. For example, a tutor is generated with natural sounds or relaxing music as the background. The learning needs analysis unit also analyzes the learner's past learning history to identify a relaxing environment. For example, if learning is effective at a specific time of day or place, a customized tutor that is optimal for that environment is generated. In this way, the environment in which the learner finds the most relaxing can be analyzed, and a customized tutor that is optimal for that environment can be generated.

[0068] The learning content providing unit can analyze the learner's real-time reactions and instantly adjust the learning content based on those reactions. For example, the learning content providing unit analyzes the learner's facial expressions and voice in real time to determine the learner's level of comprehension and concentration. For example, if the learner's understanding is not progressing, the learning content providing unit provides additional explanation. The learning content providing unit also analyzes the learner's physiological data (for example, heart rate and electrodermal activity) in real time to determine the learner's stress level. For example, if the learner is highly stressed, the learning content providing unit provides questions with a lower level of difficulty. The learning content providing unit also analyzes the learner's operation history in real time to identify where the learner is having difficulty. For example, if the learner is taking a long time to solve a particular problem, the learning content providing unit provides a hint. This makes it possible to instantly adjust the learning content based on the learner's real-time reactions.

[0069] The learning content providing unit enables instructors generated by the generation AI to explain the same content from multiple perspectives in order to deepen the learner's understanding. For example, the learning content providing unit generates instructors who use multiple approaches to explain the same content from different perspectives. For example, a mathematics problem may be explained using both an algebraic approach and a geometric approach. The learning content providing unit also generates instructors who use different media (e.g., text, video, audio) in order to deepen the learner's understanding. For example, in addition to text explanations, it may provide video explanations. The learning content providing unit also generates instructors who provide explanations from multiple perspectives so that the learner can choose the explanation method that suits them best. For example, it generates an instructor that combines theoretical explanations with practical examples. This allows the same content to be explained from multiple perspectives in order to deepen the learner's understanding.

[0070] The learning content providing unit can use the emotion estimation function to provide messages to improve motivation according to the emotional state of the learner. The learning content providing unit, for example, analyzes the emotional state of the learner in real time and provides messages to improve motivation. For example, if the learner is tired, it displays an encouraging message. The learning content providing unit also analyzes the learner's physiological data (for example, heart rate or electrodermal activity) and provides messages to improve motivation. For example, if the learner is under high stress, it provides advice on how to relax. The learning content providing unit also analyzes the learner's past learning history and provides messages to improve motivation. For example, it displays a message looking back on past successful experiences. In this way, it is possible to provide messages to improve motivation according to the learner's emotional state.

[0071] The learning content providing unit can gamify the learning content, allowing learners to learn while having fun. The learning content providing unit, for example, converts the learning content into a game format, allowing learners to learn while having fun. For example, it provides a game in which learners earn points by solving math problems and level up. The learning content providing unit also adjusts the learning content according to the progress in the game, allowing learners to learn at their own pace. For example, it gradually increases the difficulty level to maintain learners' motivation. Furthermore, by gamifying the learning content, the learning content providing unit allows learners to learn with a competitive spirit. For example, it provides a ranking function that allows learners to compete with other learners for the highest score. In this way, the learning content is gamified, allowing learners to learn while having fun.

[0072] The learning content providing unit can provide learning content on-demand so that learners can learn at their own pace. For example, the learning content providing unit builds a system that provides learning content on-demand so that learners can learn at their own pace. For example, it provides video lectures that learners can access at any time they like. The learning content providing unit also develops a system that automatically suggests the next content to be learned according to the learner's progress. For example, it suggests the next unit after a specific unit has been cleared. The learning content providing unit also builds a system that provides learning content in stages so that learners can learn at their own pace. For example, it provides a step-by-step learning plan from basic to advanced. This makes it possible to provide learning content on-demand so that learners can learn at their own pace.

[0073] The learning content providing unit can use the emotion estimation function to provide learning content at times when the learner can best concentrate. The learning content providing unit, for example, analyzes the learner's emotional state in real time to identify times when the learner can best concentrate. For example, it provides learning content at times when the learner is relaxed. The learning content providing unit also analyzes the learner's physiological data (for example, heart rate or electrodermal activity) to identify times when the learner can best concentrate. For example, it provides learning content at times when the heart rate is stable. The learning content providing unit also analyzes the learner's past learning history to identify times when the learner can best concentrate. For example, if learning is most effective at a particular time of day, it provides learning content at that time of day. This allows learning content to be provided at times when the learner can best concentrate.

[0074] The learning progress monitoring unit can analyze a learner's progress data, identify long-term learning patterns, and provide feedback. For example, the learning progress monitoring unit collects a learner's progress data over a long period of time and analyzes their learning patterns. For example, if a learner's grades in a particular unit are consistently low, additional learning resources for that unit are provided. The learning progress monitoring unit can also identify areas where learning needs to be strengthened based on the learner's progress data and provide individualized feedback. For example, if a particular skill is lacking, it can provide practice questions to strengthen that skill. The learning progress monitoring unit can also analyze a learner's progress data and propose a study plan to maximize the effectiveness of learning. For example, it can propose an optimal study schedule based on past data. In this way, it is possible to analyze a learner's progress data, identify long-term learning patterns, and provide feedback.

[0075] The learning progress monitoring unit can visualize the learner's progress and make it intuitively understandable using graphs and charts. The learning progress monitoring unit, for example, visualizes the learner's progress data using graphs and charts to make it intuitively understandable. For example, it displays the learning progress status using a line graph. The learning progress monitoring unit also provides a dashboard that visualizes the learning results based on the learner's progress data. For example, it displays the grades for each unit using a bar graph. The learning progress monitoring unit also updates the learner's progress data in real time to visualize the latest learning status. For example, it displays the learning progress using a pie chart to show the degree of achievement. In this way, the learner's progress is visualized and can be intuitively understood using graphs and charts.

[0076] The learning progress monitoring unit can use the emotion estimation function to provide feedback according to the learner's emotional state and maintain motivation. The learning progress monitoring unit, for example, analyzes the learner's emotional state in real time and provides feedback to maintain motivation. For example, if the learner is tired, it displays an encouraging message. The learning progress monitoring unit also analyzes the learner's physiological data (for example, heart rate or electrodermal activity) and provides feedback to maintain motivation. For example, if the learner is under high stress, it provides advice on how to relax. The learning progress monitoring unit also analyzes the learner's past learning history and provides feedback to maintain motivation. For example, it displays a message looking back on past successful experiences. In this way, feedback according to the learner's emotional state is provided and motivation is maintained.

[0077] The learning progress monitoring unit can compare a learner's progress with other learners and provide feedback that stimulates a competitive spirit. For example, the learning progress monitoring unit compares a learner's progress data with other learners and provides feedback that stimulates a competitive spirit. For example, it displays the performance ranking within a class. The learning progress monitoring unit also compares the learner's progress data with other learners and provides messages that stimulate a competitive spirit. For example, it displays the difference between the learner and a higher-ranked learner. The learning progress monitoring unit also updates the learner's progress data in real time and displays the comparison results with other learners. For example, it compares the learner's performance in a specific unit with other learners. In this way, the learner's progress is compared with other learners and feedback that stimulates a competitive spirit is provided.

[0078] The learning progress monitoring unit can provide rewards and badges according to the learner's progress, thereby enhancing the learner's sense of accomplishment. For example, the learning progress monitoring unit provides rewards and badges when a specific goal is achieved based on the learner's progress data. For example, a badge is earned when a specific unit is cleared. The learning progress monitoring unit also updates the learner's progress data in real time, and provides rewards and badges according to the level of achievement. For example, a reward is provided when continuous learning is performed. The learning progress monitoring unit also builds a reward system based on the learner's progress data to enhance the learner's sense of accomplishment. For example, a badge is earned when a specific skill is mastered. In this way, rewards and badges are provided according to the learner's progress, enhancing the learner's sense of accomplishment.

[0079] The learning progress monitoring unit can use the emotion estimation function to provide feedback that evokes the most positive emotions in the learner. For example, the learning progress monitoring unit analyzes the emotional state of the learner in real time and provides feedback that evokes the most positive emotions. For example, it displays a message that makes the learner feel happy. The learning progress monitoring unit also analyzes the learner's physiological data (for example, heart rate or electrodermal activity) and provides feedback that evokes the most positive emotions. For example, it displays a message that makes the learner feel relaxed. The learning progress monitoring unit also analyzes the learner's past learning history and provides feedback that evokes the most positive emotions. For example, it displays a message that reflects on past successful experiences. In this way, it provides feedback that evokes the most positive emotions in the learner.

[0080] The learning environment optimization unit can customize and provide environmental sounds and music to improve the learner's concentration. The learning environment optimization unit, for example, customizes and provides environmental sounds and music to improve the learner's concentration. For example, it provides a learning environment with the sounds of nature or classical music as a background. The learning environment optimization unit also analyzes the learner's physiological data (e.g., heart rate and electrodermal activity) and provides music to improve concentration. For example, it selects music that stabilizes the heart rate. The learning environment optimization unit also analyzes the learner's past learning history and provides environmental sounds and music to improve concentration. For example, if a particular piece of music improves concentration, it provides that music. In this way, environmental sounds and music are customized and provided to improve the learner's concentration.

[0081] The learning environment optimization unit can analyze the learner's physiological data and propose the optimal learning environment. The learning environment optimization unit, for example, analyzes the learner's heart rate in real time and proposes the optimal learning environment. For example, it proposes an environment that stabilizes the heart rate. The learning environment optimization unit also analyzes the learner's brain waves and proposes the optimal learning environment. For example, it proposes an environment that improves concentration. The learning environment optimization unit also builds a system that proposes the optimal learning environment based on the learner's physiological data. For example, it adjusts the environment based on heart rate and brain wave data. In this way, the learner's physiological data is analyzed and the optimal learning environment is proposed.

[0082] The learning environment optimization unit can use the emotion estimation function to adjust environmental settings in real time according to the emotional state of the learner. The learning environment optimization unit, for example, analyzes the emotional state of the learner in real time and adjusts the environmental settings. For example, if the learner is feeling stressed, it provides a relaxing environment. The learning environment optimization unit also analyzes physiological data of the learner (e.g., heart rate and electrodermal activity) and adjusts the environmental settings. For example, if the heart rate is high, it provides a quiet environment. The learning environment optimization unit also analyzes the learner's past learning history and adjusts the environmental settings according to the emotional state. For example, if a particular environment produces a high learning effect, it provides that environment. In this way, the environmental settings are adjusted in real time according to the learner's emotional state.

[0083] The learning environment optimization unit can customize the learning environment by providing digital art and background images according to the learner's preferences. The learning environment optimization unit, for example, provides digital art and background images according to the learner's preferences and customizes the learning environment. For example, a natural landscape or abstract art may be set as the background. The learning environment optimization unit also analyzes the learner's past learning history and provides digital art and background images according to the learner's preferences. For example, if a particular background image improves concentration, it provides that image. The learning environment optimization unit also provides an interface that allows the learner to select digital art and background images according to their preferences. For example, the learner may upload an image they like and set it as the background. In this way, digital art and background images according to the learner's preferences are provided and the learning environment is customized.

[0084] The learning environment optimization unit can analyze the time periods when a learner can best concentrate and recommend studying during those time periods. The learning environment optimization unit, for example, analyzes the learner's past learning history to identify the time periods when the learner can best concentrate. For example, if learning is most effective during a particular time period, it recommends studying during that time period. The learning environment optimization unit also analyzes the learner's physiological data (e.g., heart rate and electrodermal activity) to identify the time periods when the learner can best concentrate. For example, it recommends studying during times when the heart rate is stable. The learning environment optimization unit also analyzes the learner's emotional state in real time to identify the time periods when the learner can best concentrate. For example, it recommends studying during times when the learner is relaxed. In this way, it analyzes the time periods when the learner can best concentrate and recommends studying during those times.

[0085] The learning environment optimization unit can use the emotion estimation function to suggest an environment in which the learner can be most relaxed. The learning environment optimization unit, for example, analyzes the learner's emotional state in real time and suggests the most relaxing environment. For example, if the learner is feeling stressed, it provides a relaxing environment. The learning environment optimization unit also analyzes the learner's physiological data (e.g., heart rate and electrodermal activity) and suggests the most relaxing environment. For example, it provides an environment in which the heart rate is stable. The learning environment optimization unit also analyzes the learner's past learning history and suggests the most relaxing environment. For example, if a particular environment is highly effective for learning, it provides that environment. In this way, it suggests an environment in which the learner can be most relaxed.

[0086] The learning community building unit can match optimal learning partners based on the learner's interests and goals. For example, the learning community building unit collects learners' interests and goals from questionnaires or profile information and matches optimal learning partners based on that. For example, it matches learners with the same goals. The learning community building unit also analyzes the learner's past learning history to match optimal learning partners. For example, it matches learners who have learning experience in the same field. The learning community building unit also analyzes the learner's physiological data (for example, heart rate or electrodermal activity) to match optimal learning partners. For example, it matches learners who can study at the same rhythm. In this way, the optimal learning partners are matched based on the learner's interests and goals.

[0087] The learning community building unit can provide a virtual classroom where learners can interact with each other in real time. The learning community building unit, for example, provides a virtual classroom where learners can interact with each other in real time. For example, learners communicate with each other through video chat or text chat. The learning community building unit also provides a virtual classroom where learners can learn together and promotes real-time discussions and group work. For example, learners can work together using an online whiteboard. The learning community building unit also provides a virtual classroom where learners can interact with each other in real time and ask questions and exchange opinions about the learning content. For example, the learning community building unit holds sessions where instructors provide feedback in real time. In this way, a virtual classroom where learners can interact with each other in real time is provided.

[0088] The learning community building unit can use the emotion estimation function to suggest community activities according to the emotional state of the learner. The learning community building unit, for example, analyzes the emotional state of the learner in real time and suggests community activities according to the emotional state. For example, if the learner is feeling stressed, it suggests activities that will help them relax. The learning community building unit also analyzes the learner's physiological data (e.g., heart rate and electrodermal activity) and suggests community activities according to their emotional state. For example, if the heart rate is high, it suggests activities that will help them relax. The learning community building unit also analyzes the learner's past learning history and suggests community activities according to their emotional state. For example, if a particular activity has a relaxing effect, it suggests that activity. In this way, community activities according to the learner's emotional state are suggested.

[0089] The learning community construction unit can match learners from different regions and cultural areas and provide learning from a global perspective. The learning community construction unit, for example, matches learners from different regions and cultural areas and provides learning from a global perspective. For example, learning diverse perspectives through intercultural exchange. The learning community construction unit also matches learners from different regions and cultural areas based on learner profile information. For example, it matches learners who are learning different languages. The learning community construction unit also analyzes learners' past learning history and matches learners from different regions and cultural areas. For example, it matches learners with different cultural backgrounds. In this way, learners from different regions and cultural areas are matched and learning from a global perspective is provided.

[0090] The learning community building unit can provide collaboration tools that allow learners to work together on a project. The learning community building unit provides, for example, collaboration tools that allow learners to work together on a project. For example, it provides an online whiteboard and document sharing function. The learning community building unit also provides collaboration tools that allow learners to work together in real time. For example, it provides a platform that integrates video conferencing and chat functions. The learning community building unit also provides collaboration tools that allow learners to manage the progress of a project. For example, it provides task management and progress reporting functions. In this way, collaboration tools are provided that allow learners to work together on a project.

[0091] The learning community building unit can use the emotion estimation function to suggest community activities that will evoke the most positive emotions in the learner. For example, the learning community building unit analyzes the emotional state of the learner in real time and suggests community activities that will evoke the most positive emotions. For example, it suggests activities that make the learner feel happy. The learning community building unit also analyzes the learner's physiological data (for example, heart rate or electrodermal activity) and suggests community activities that will evoke the most positive emotions. For example, it suggests activities that stabilize the heart rate. The learning community building unit also analyzes the learner's past learning history and suggests community activities that will evoke the most positive emotions. For example, if a specific activity evokes positive emotions, it suggests that activity. In this way, it suggests community activities that will evoke the most positive emotions in the learner.

[0092] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0093] The learning needs analysis unit analyzes the learning needs of the learner. For example, the learning needs analysis unit analyzes the learner's learning goals and learning style. The learning needs analysis unit can also collect and analyze background information of the learner. For example, the learning needs analysis unit analyzes the learner's past learning history and performance data to identify the learning needs. The customized instructor generation unit generates a customized instructor based on the learning needs analyzed by the learning needs analysis unit. For example, the customized instructor generation unit uses a generation AI to generate an instructor that meets the learner's learning needs. The customized instructor generation unit can also use the generation AI to generate an optimal instructor based on the learner's level of understanding and goals. For example, the customized instructor generation unit receives the learner's learning needs as prompts and generates a customized instructor based on the prompts. The learning content provision unit provides optimal learning content to the learner using the customized instructor generated by the customized instructor generation unit. For example, the learning content provision unit uses the customized instructor generated by the generation AI to pose questions that meet the learner's level of understanding and provide explanations. The learning content provision unit can also adjust the learning content according to the learner's progress to support effective learning. For example, the learning content providing unit uses a generation AI to monitor the learner's progress and suggest the next learning content. As a result, the enhanced instructor creator system according to the embodiment can generate a customized instructor according to the individual learning needs of the learner and provide optimal learning content.

[0094] The learning needs analysis unit can analyze a learner's past learning history and performance data and generate a customized tutor based on their long-term learning trends. For example, the learning needs analysis unit analyzes a learner's past test results and assignment submission status to understand their long-term learning trends. For example, if a learner's grades in a particular area of ​​mathematics are consistently low, a customized tutor specialized in that area is generated. The learning needs analysis unit also analyzes the learner's activity history on the online learning platform to identify the time of day when the learner can best concentrate on studying. For example, a customized tutor that suggests an optimal study schedule is generated. The learning needs analysis unit also sets future learning goals based on the learner's past learning performance data and generates a customized tutor accordingly. For example, for a learner aiming to take a university entrance exam, a tutor specialized in entrance exam preparation is generated. This makes it possible to generate more sophisticated customized tutors based on the learner's past learning history and performance data.

[0095] The learning needs analysis unit analyzes the learner's non-verbal behavior to more precisely grasp their learning needs. For example, the learning needs analysis unit analyzes the learner's facial expressions using a camera to determine whether they are concentrating. For example, if they are not concentrating, a customized instructor is generated that suggests taking a break. The learning needs analysis unit also analyzes the learner's posture using a sensor to measure their level of fatigue. For example, if they have been sitting for a long time, a customized instructor is generated that suggests stretching. The learning needs analysis unit also analyzes the learner's eye movements to identify where their attention is focused. For example, if their gaze is fixed on a particular problem for a long time, a customized instructor is generated that provides additional explanation for that problem. In this way, by analyzing the learner's non-verbal behavior, it is possible to more precisely grasp their learning needs.

[0096] The learning needs analysis unit can use the emotion estimation function to analyze the emotional state of a learner in real time and generate a customized instructor according to that emotion. The learning needs analysis unit, for example, analyzes the learner's facial expression to estimate the emotional state in real time. For example, if the learner is feeling stressed, a customized instructor is generated that suggests a learning method that will help the learner relax. The learning needs analysis unit also analyzes the learner's tone of voice to estimate the emotional state. For example, if the learner is excited, a customized instructor is generated that provides advice on how to improve concentration. The learning needs analysis unit also analyzes the learner's physiological data (for example, heart rate and electrodermal activity) to estimate the emotional state. For example, if the learner is relaxed, a customized instructor is generated that suggests the learner try more difficult problems. In this way, the emotional state of a learner can be analyzed in real time and a customized instructor according to that emotion can be generated.

[0097] The learning needs analysis unit can analyze a learner's hobbies and interests and, based on that, generate a customized tutor that combines learning content with entertainment elements. The learning needs analysis unit, for example, collects a learner's hobbies and interests from questionnaires or profile information and customizes learning content based on that. For example, for a learner who likes music, a customized tutor that provides music-related math problems is generated. The learning needs analysis unit also analyzes the learner's social media and online activities to identify topics of interest. For example, for a learner who is interested in sports, a customized tutor that provides data analysis problems using sports statistics is generated. The learning needs analysis unit also analyzes the learner's past learning history to identify learning content that is likely to interest them. For example, for a learner who is interested in history, a customized tutor that provides English reading comprehension questions based on historical events is generated. In this way, a customized tutor that combines learning content with entertainment elements can be generated based on the learner's hobbies and interests.

[0098] The learning needs analysis unit can generate customized instructors corresponding to different learning styles, allowing learners to select an instructor based on their preferences. The learning needs analysis unit, for example, collects learners' learning styles from questionnaires or profile information and generates a customized instructor based on that information. For example, for visual learners, it generates an instructor that makes extensive use of visual content. The learning needs analysis unit also analyzes the learner's past learning history and identifies which learning style is most effective. For example, for auditory learners, it generates an instructor that focuses on audio commentary. The learning needs analysis unit also provides an interface that allows learners to select their own learning style, and generates a customized instructor based on that. For example, for tactile learners, it generates an instructor that provides interactive experiments and simulations. In this way, customized instructors corresponding to different learning styles can be generated, allowing learners to select an instructor based on their preferences.

[0099] The learning needs analysis unit uses the emotion estimation function to analyze the environment in which the learner finds the most relaxing, and can generate a customized tutor that is optimal for that environment. The learning needs analysis unit, for example, analyzes the learner's emotional state in real time to identify a relaxing environment. For example, if learning in a quiet environment is effective, a customized tutor that is optimal for that environment is generated. The learning needs analysis unit also analyzes the learner's physiological data (e.g., heart rate and electrodermal activity) to identify a relaxing environment. For example, a tutor is generated with natural sounds or relaxing music as the background. The learning needs analysis unit also analyzes the learner's past learning history to identify a relaxing environment. For example, if learning is effective at a specific time of day or place, a customized tutor that is optimal for that environment is generated. In this way, the environment in which the learner finds the most relaxing can be analyzed, and a customized tutor that is optimal for that environment can be generated.

[0100] The learning content providing unit can analyze the learner's real-time reactions and instantly adjust the learning content based on those reactions. For example, the learning content providing unit analyzes the learner's facial expressions and voice in real time to determine the learner's level of comprehension and concentration. For example, if the learner's understanding is not progressing, the learning content providing unit provides additional explanation. The learning content providing unit also analyzes the learner's physiological data (for example, heart rate and electrodermal activity) in real time to determine the learner's stress level. For example, if the learner is highly stressed, the learning content providing unit provides questions with a lower level of difficulty. The learning content providing unit also analyzes the learner's operation history in real time to identify where the learner is having difficulty. For example, if the learner is taking a long time to solve a particular problem, the learning content providing unit provides a hint. This makes it possible to instantly adjust the learning content based on the learner's real-time reactions.

[0101] The learning content providing unit enables instructors generated by the generation AI to explain the same content from multiple perspectives in order to deepen the learner's understanding. For example, the learning content providing unit generates instructors who use multiple approaches to explain the same content from different perspectives. For example, a mathematics problem may be explained using both an algebraic approach and a geometric approach. The learning content providing unit also generates instructors who use different media (e.g., text, video, audio) in order to deepen the learner's understanding. For example, in addition to text explanations, it may provide video explanations. The learning content providing unit also generates instructors who provide explanations from multiple perspectives so that the learner can choose the explanation method that suits them best. For example, it generates an instructor that combines theoretical explanations with practical examples. This allows the same content to be explained from multiple perspectives in order to deepen the learner's understanding.

[0102] The learning content providing unit can use the emotion estimation function to provide messages to improve motivation according to the emotional state of the learner. The learning content providing unit, for example, analyzes the emotional state of the learner in real time and provides messages to improve motivation. For example, if the learner is tired, it displays an encouraging message. The learning content providing unit also analyzes the learner's physiological data (for example, heart rate or electrodermal activity) and provides messages to improve motivation. For example, if the learner is under high stress, it provides advice on how to relax. The learning content providing unit also analyzes the learner's past learning history and provides messages to improve motivation. For example, it displays a message looking back on past successful experiences. In this way, it is possible to provide messages to improve motivation according to the learner's emotional state.

[0103] The processing flow of the second embodiment will be briefly explained below.

[0104] Step 1: The learning needs analysis unit analyzes the learner's learning needs. For example, the learning needs analysis unit analyzes the learner's learning goals and learning style, and can also collect and analyze the learner's background information. Specifically, the learning needs are identified by analyzing the learner's past learning history and performance data. Step 2: The customized instructor generation unit generates a customized instructor based on the learning needs analyzed by the learning needs analysis unit. For example, the customized instructor generation unit uses a generation AI to generate an instructor that meets the learner's learning needs. It can also generate an optimal instructor based on the learner's level of understanding and goals. Specifically, the generation AI receives the learner's learning needs as a prompt and generates a customized instructor based on that. Step 3: The learning content provider uses the customized tutor generated by the customized tutor generator to provide optimal learning content to the learner. For example, the learning content provider uses the customized tutor generated by the generation AI to pose questions based on the learner's level of understanding and provide explanations. It can also adjust the learning content according to the learner's progress to support effective learning. Specifically, the generation AI monitors the learner's progress and suggests what content to study next.

[0105] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0106] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0107] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0108] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0109] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0110] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0111] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0112] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0113] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0114] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0115] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0116] 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.

[0117] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0118] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0119] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0120] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0121] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0122] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0123] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0124] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0125] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0126] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0127] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0128] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0129] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0130] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0131] 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.

[0132] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0133] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0134] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0135] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0136] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0137] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0138] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0139] 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.

[0140] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0141] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0142] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0143] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0144] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0145] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0146] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0147] 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.

[0148] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0149] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0150] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0151] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0152] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0153] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0154] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0155] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0156] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0157] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0158] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0159] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0160] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0161] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0162] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0163] 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.

[0164] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0165] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0166] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific process may be a single processor.

[0167] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0168] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0169] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0170] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0171] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0172] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a learning needs analysis unit that analyzes the learning needs of a learner; a customized instructor generation unit that generates a customized instructor based on the learning needs analyzed by the learning needs analysis unit; a learning content providing unit that provides optimal learning content to a learner using the customized instructor generated by the customized instructor generating unit. A system characterized by:

2. The learning needs analysis unit Analyze learners' past learning history and performance data to generate customized instructors based on long-term learning trends 2. The system of claim 1.

3. The learning needs analysis unit Analyzing learners' non-verbal behavior to more precisely understand their learning needs 2. The system of claim 1.

4. The learning needs analysis unit Analyzing learners' emotional states in real time and generating customized instructors based on those emotions 2. The system of claim 1.

5. The learning needs analysis unit Analyze learners' hobbies and interests and generate customized instructors that combine learning content with entertainment elements.

2. The system of claim 1.

6. The learning needs analysis unit Generate customized instructors for different learning styles, allowing learners to choose according to their preferences 2. The system of claim 1.

7. The learning needs analysis unit Analyzes the environment in which a learner finds themselves most relaxed and generates a customized instructor that is optimal for that environment 2. The system of claim 1.

8. The learning content providing unit Analyze learners' real-time responses and instantly adjust learning content based on those responses 2. The system of claim 1.

Images