system

Abstract

The system according to this embodiment aims to provide a learning plan tailored to the child's level of understanding and interests. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a provision unit, a planning unit, and a feedback unit. The collection unit collects the child's learning data. The analysis unit analyzes the data collected by the collection unit and evaluates the child's level of understanding. The provision unit provides problems based on the evaluation results obtained by the analysis unit. The planning unit plans and executes a learning plan based on the problems provided by the provision unit. The feedback unit provides feedback on incorrect answers based on the learning plan planned by the planning unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, a learning plan tailored to the understanding level and interests of each child has not been sufficiently provided, and there is room for improvement.

[0005] The system according to the embodiment aims to provide a learning plan tailored to the understanding level and interests of children.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a data collection unit, an analysis unit, a data provision unit, a planning unit, and a feedback unit. The data collection unit collects children's learning data. The analysis unit analyzes the data collected by the data collection unit and evaluates the children's level of understanding. The data provision unit provides problems based on the evaluation results obtained by the analysis unit. The planning unit plans and executes a learning plan based on the problems provided by the data provision unit. The feedback unit provides feedback on incorrect answers based on the learning plan planned by the planning unit. [Effects of the Invention]

[0007] The system according to this embodiment can provide a learning plan tailored to the child's level of understanding and interests. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10]This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The learning support system according to an embodiment of the present invention is a learning service incorporating elements of an AI agent. This learning support system targets parents of children who need to study and provides problems tailored to each child's level of understanding and interests in tests, entrance exams, qualification exams, etc. The learning support system uses AI to grasp the child's level of understanding in real time, autonomously plan and execute a learning plan, and tune problems to match the child's interests to increase motivation. For example, the learning support system first uses AI to collect the child's learning data and grasp their level of understanding in real time. For example, it collects data such as the correct answer rate and answer time for problems the child has solved. Next, the learning support system uses AI to analyze the collected data and evaluate the child's level of understanding. For example, if the child's understanding is low in a particular area, the system adjusts to present more problems related to that area. Furthermore, the learning support system uses AI to tune problems based on the child's interests. For example, if the child is interested in a particular anime or sport, the system presents problems related to that theme. This can increase the child's motivation to learn. In addition, the learning support system uses AI to autonomously plan and execute a learning plan. For example, the system creates a daily learning schedule based on the child's understanding and interests, and presents problems at appropriate times. Furthermore, the learning support system uses AI to provide appropriate feedback on incorrect answers. For instance, it specifically points out which part of a child's answer is wrong and teaches them the correct way to answer. In this way, the learning support system can provide an optimal learning environment for each child and increase their motivation to learn. Parents can monitor their child's learning progress in real time and provide appropriate support. This maximizes the child's learning outcomes and leads to future success. In this way, the learning support system can provide an optimal learning environment for each child by collecting and analyzing the child's learning data, providing problems, planning and executing learning plans, and providing feedback.

[0029] The learning support system according to this embodiment comprises a collection unit, an analysis unit, a provision unit, a planning unit, and a feedback unit. The collection unit collects the child's learning data. For example, the collection unit collects data such as the correct answer rate and answer time for problems solved by the child. The collection unit can also collect the child's learning data in real time using AI. The analysis unit analyzes the data collected by the collection unit and evaluates the child's level of understanding. For example, if the child's understanding in a particular area is low, the analysis unit adjusts the system to present more problems related to that area. The analysis unit can also evaluate the child's level of understanding in real time using AI. The provision unit provides problems based on the evaluation results obtained by the analysis unit. For example, the provision unit tunes the problems based on the child's interests. The provision unit can also tune the problems in real time based on the child's interests using AI. The planning unit plans and executes a learning plan based on the problems provided by the provision unit. For example, the planning unit creates a daily learning schedule based on the child's level of understanding and interests, and presents problems at appropriate times. The planning unit can also use AI to plan and execute learning plans in real time. The feedback unit provides feedback on incorrect answers based on the learning plan planned by the planning unit. For example, the feedback unit will specifically point out which part of a problem a child got wrong and teach the correct way to answer it. The feedback unit can also use AI to provide feedback on incorrect answers in real time. As a result, the learning support system according to this embodiment can provide an optimal learning environment for each child by collecting and analyzing the child's learning data, providing problems, planning and executing learning plans, and providing feedback.

[0030] The data collection unit collects children's learning data. For example, it collects data such as the accuracy rate and time taken to answer problems that children have solved. Specifically, if a child is using an online learning platform, the results of each problem are automatically recorded, and the accuracy rate, time taken, and answer patterns are collected in detail. Furthermore, the data collection unit can also collect children's learning data in real time using AI. The AI ​​monitors the child's learning behavior and analyzes in real time, for example, which problems take the child the most time to solve and which problems the child makes the most mistakes on. This allows the data collection unit to understand the child's learning situation in detail and accurately. The data collection unit can also collect data about the child's learning environment. For example, it can collect information such as the time of day and location in which the child is studying and the type of device being used, and evaluate the impact of the learning environment on learning outcomes. This allows the data collection unit to collect children's learning data from multiple perspectives and build a foundation for providing more comprehensive learning support.

[0031] The analysis unit analyzes the data collected by the data collection unit and evaluates the child's level of understanding. For example, if the child's understanding is low in a particular area, the analysis unit adjusts the questions to include more problems related to that area. Specifically, it uses AI to analyze the child's answer data and evaluate their understanding in each area. The AI ​​uses machine learning algorithms to analyze the child's answer patterns, correct answer rate, and answer time to identify areas where the child's understanding is weak. For example, in the case of mathematics problems, it evaluates the child's understanding in each area such as arithmetic, algebra, and geometry, and then presents questions that focus on the areas where the child's understanding is weak. The analysis unit can also monitor the child's learning progress in real time and adjust the learning plan as needed. For example, if a child is struggling with a particular problem, it will provide additional basic problems related to that problem to help deepen their understanding. This allows the analysis unit to have a detailed understanding of the child's learning situation and provide learning support tailored to individual needs. Furthermore, the analysis unit can analyze the child's learning patterns and trends based on past learning data, which can be used to plan future learning.

[0032] The provisioning department provides problems based on evaluation results obtained by the analysis department. The provisioning department tunes the problems based on the child's interests, for example. Specifically, it can use AI to tune problems in real time based on the child's interests. The AI ​​analyzes the child's past learning history and answer patterns and selects problems in themes and formats that are likely to interest the child. For example, if a child is interested in animals, the provisioning department will present math or science problems related to animals to increase their motivation to learn. The provisioning department can also adjust the difficulty level of the problems according to the child's level of understanding. For example, it will present more difficult problems in areas where the child understands well and more basic problems in areas where the child understands less well. In this way, the provisioning department can provide problems that are optimal for each child and support effective learning. Furthermore, the provisioning department can provide flexible learning support that matches the child's learning rhythm by adjusting the frequency and timing of problem presentation. For example, it will present more difficult problems during times when the child is likely to concentrate well and review problems or easier problems during times when the child is tired. In this way, the provisioning department can maximize the child's learning efficiency and provide effective learning support.

[0033] The Planning Department plans and executes learning plans based on the problems provided by the Delivery Department. For example, the Planning Department creates a daily learning schedule based on the child's level of understanding and interests, and presents problems at appropriate times. Specifically, it can also plan and execute learning plans in real time using AI. The AI ​​analyzes the child's learning data and automatically generates an optimal learning schedule. For example, if a child is more likely to concentrate during a particular time, it will present more difficult problems during that time to deepen their understanding. The Planning Department can also monitor the child's learning progress in real time and adjust the learning plan as needed. For example, if a child is learning faster than planned, it will present additional new problems to maintain the learning pace. Also, if a child is struggling with a particular problem, it will present additional basic problems related to that problem to help deepen their understanding. In this way, the Planning Department can provide flexible learning plans tailored to the child's learning situation and provide effective learning support. Furthermore, the Planning Department can set long-term learning goals and provide a step-by-step learning plan that matches the child's growth. For example, it can set a one-year learning goal and create monthly and weekly learning plans to achieve that goal. This allows the planning department to provide long-term support for children's learning and achieve sustained learning outcomes.

[0034] The Feedback Department provides feedback on incorrect answers based on the learning plan developed by the Planning Department. For example, the Feedback Department will specifically point out which part of a problem a child answered incorrectly and teach the correct solution method. Specifically, it can also use AI to provide real-time feedback on incorrect answers. The AI ​​analyzes the child's answer data and identifies the cause of the incorrect answer. For example, it analyzes patterns of incorrect answers, such as calculation errors or misunderstandings of concepts, and provides appropriate feedback. The Feedback Department can also provide feedback using visual explanations and concrete examples to make it easier for children to understand. For example, for a math problem, it can use diagrams and graphs to visually explain the solution method and deepen understanding. The Feedback Department can also adjust the content and timing of feedback according to the child's learning progress. For example, if a child repeatedly makes mistakes on a particular problem, it will explain the basic concepts related to that problem again to help deepen understanding. In this way, the Feedback Department can maximize the child's learning effectiveness and provide effective learning support. Furthermore, the Feedback Department can monitor the child's learning progress and evaluate the effectiveness of the feedback. For example, it can analyze changes in the correct answer rate and answer time after feedback to evaluate the effectiveness of the feedback. This allows the feedback system to continuously improve the content and methods of feedback, maximizing the learning effectiveness for children.

[0035] The service provider includes a tuning unit that adjusts the questions based on the child's interests. For example, if a child is interested in a particular anime or sport, the tuning unit will present questions related to that theme. The tuning unit can also use AI to adjust the questions in real time based on the child's interests. For example, the tuning unit can present questions using characters from the child's favorite anime. It can also present questions related to sports that the child is interested in. Furthermore, the tuning unit can adjust the difficulty and format of the questions based on the child's interests. For example, by presenting questions related to themes that the child is interested in, the tuning unit can increase the child's motivation to learn. In this way, the service provider can increase the child's motivation to learn by adjusting the questions based on the child's interests.

[0036] The planning unit includes an adjustment unit that adjusts the difficulty level of problems according to the child's learning progress. The adjustment unit can, for example, raise or lower the difficulty level of problems based on the child's learning progress. The adjustment unit can also use AI to adjust the difficulty level of problems in real time based on the child's learning progress. For example, if the child's understanding of a particular subject is low, the adjustment unit can lower the difficulty level of problems related to that subject. Conversely, if the child's understanding of a particular subject is high, the adjustment unit can also raise the difficulty level of problems related to that subject. Furthermore, the adjustment unit can also adjust the format and frequency of questions based on the child's learning progress. For example, the adjustment unit can maximize the child's learning effectiveness by presenting more questions related to areas where the child has a low understanding. In this way, the planning unit can maximize the child's learning effectiveness by adjusting the difficulty level of problems according to their learning progress.

[0037] The data collection unit includes a notification unit that informs parents about their child's learning progress. The notification unit notifies parents, for example, of information regarding the child's learning progress and comprehension level. The notification unit can also use AI to notify parents of the child's learning progress in real time. For example, if the child's comprehension level is low in a particular area, the notification unit will notify the parents of that information. The notification unit can also notify parents if the child's comprehension level is high in a particular area. Furthermore, the notification unit can also suggest appropriate support to parents based on the child's learning progress. For example, the notification unit will suggest learning materials and learning methods related to areas where the child's comprehension is low. In this way, the data collection unit makes it easier for parents to support their child's learning by notifying them of the child's learning progress.

[0038] The feedback system provides specific feedback and correct solutions for incorrect answers. For example, it will specifically point out which part of a child's answer was wrong. The feedback system can also use AI to provide specific feedback and correct solutions in real time for incorrect answers. For example, it can analyze the child's answer process for a question they answered incorrectly and identify where they went wrong. It can also specifically teach the correct solution. Furthermore, the feedback system can provide children with opportunities to try the questions they answered incorrectly again. For example, it can re-present the question the child answered incorrectly and allow them to confirm the correct solution. In this way, the feedback system can deepen the child's understanding by providing specific feedback and correct solutions for incorrect answers.

[0039] The analysis unit analyzes data including the children's response times. For example, the analysis unit collects and analyzes data on the time children spend answering questions. The analysis unit can also use AI to analyze children's response times in real time. For example, the analysis unit analyzes how long a child spends on a particular problem and evaluates their level of understanding based on that data. The analysis unit can also adjust the difficulty level and frequency of questions based on the response time data. Furthermore, the analysis unit can analyze children's response times in combination with other learning data. For example, the analysis unit analyzes the relationship between response time and the accuracy rate to understand the child's learning pattern. As a result, the analysis unit can more accurately evaluate a child's level of understanding by analyzing data including their response times.

[0040] The data collection unit analyzes the child's past learning history and selects the optimal collection method. For example, the collection unit prioritizes collecting question formats in which the child has previously achieved a high correct answer rate. The collection unit can also use AI to analyze the child's past learning history in real time and select the optimal collection method. For example, the collection unit avoids collecting question formats in which the child has previously struggled. The collection unit can also prioritize collecting question formats in which the child has previously answered quickly. Furthermore, the collection unit can adjust the type and frequency of data collected based on the child's past learning history. For example, by prioritizing the collection of question formats in which the child has previously achieved a high correct answer rate, the collection unit can maximize the child's learning effectiveness. In this way, the collection unit can select the optimal collection method by analyzing the child's past learning history. Some or all of the above processing in the collection unit may be performed using AI, for example, or without using AI.

[0041] The data collection unit filters learning data based on the child's current learning environment and level of concentration. For example, if the child is learning in a quiet environment, the data collection unit will collect detailed data. The data collection unit can also use AI to evaluate the child's current learning environment and level of concentration in real time and filter the data when collecting it. For example, if the child is learning in a noisy environment, the data collection unit will collect only important data. Alternatively, if the child is focused, the data collection unit can collect all data. Furthermore, the data collection unit can adjust the type and frequency of data collected based on the child's learning environment and level of concentration. For example, by collecting detailed data when the child is learning in a quiet environment and only important data when the child is learning in a noisy environment, more accurate data collection becomes possible. This allows the data collection unit to filter learning data based on the child's current learning environment and level of concentration, enabling more accurate data collection. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI.

[0042] The data collection unit prioritizes collecting highly relevant data based on the child's geographical location when collecting learning data. For example, if the child is at school, the data collection unit prioritizes collecting data related to the school curriculum. The data collection unit can also use AI to evaluate the child's geographical location in real time and prioritize collecting highly relevant data when collecting learning data. For example, if the child is at home, the data collection unit prioritizes collecting data related to home learning. Furthermore, if the child is at the library, the data collection unit can prioritize collecting data related to library materials. In addition, the data collection unit can adjust the type and frequency of data collected based on the child's geographical location. For example, by prioritizing data related to the school curriculum when the child is at school and data related to home learning when the child is at home, more effective data collection becomes possible. This allows the data collection unit to prioritize collecting highly relevant data based on the child's geographical location, enabling more effective data collection. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI.

[0043] The data collection unit analyzes children's social media activities and collects relevant data when collecting learning data. For example, the data collection unit collects learning content that children share on social media. The data collection unit can also use AI to analyze children's social media activities in real time and collect relevant data when collecting learning data. For example, the data collection unit collects information on educational accounts that children follow on social media. The data collection unit can also collect data related to topics that children have shown interest in on social media. Furthermore, the data collection unit can adjust the type and frequency of data collected based on children's social media activities. For example, by collecting learning content that children share on social media and information on educational accounts that children follow on social media, the data collection unit can collect data more effectively. This allows the data collection unit to collect data more effectively by analyzing children's social media activities and collecting relevant data when collecting learning data. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI.

[0044] The analysis unit adjusts the level of detail of the analysis based on the importance of the training data during the analysis. For example, the analysis unit performs a detailed analysis on important data. The analysis unit can also use AI to evaluate the importance of the training data in real time and adjust the level of detail of the analysis. For example, the analysis unit performs a simplified analysis on less important data. The analysis unit can also apply multiple analysis methods to highly important data. Furthermore, the analysis unit can adjust the frequency and method of analysis based on the importance of the training data. For example, by performing a detailed analysis on highly important data and a simplified analysis on less important data, the analysis unit can perform a more effective analysis. In this way, the analysis unit can perform a more effective analysis by adjusting the level of detail of the analysis based on the importance of the training data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without using AI.

[0045] The analysis unit applies different analysis algorithms depending on the category of the training data during analysis. For example, the analysis unit applies a numerical analysis algorithm to mathematical data. The analysis unit can also use AI to evaluate the category of the training data in real time and apply different analysis algorithms during analysis. For example, the analysis unit applies a natural language processing algorithm to language data. The analysis unit can also apply a scientific analysis algorithm to science data. Furthermore, the analysis unit can adjust the method and frequency of analysis based on the category of the training data. For example, by applying a numerical analysis algorithm to mathematical data and a natural language processing algorithm to language data, the analysis unit can perform more effective analysis. Thus, the analysis unit can perform more effective analysis by applying different analysis algorithms depending on the category of the training data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI.

[0046] The analysis unit determines the priority of analysis based on the submission timing of the training data. For example, the analysis unit prioritizes the analysis of recently submitted data. The analysis unit can also use AI to evaluate the submission timing of the training data in real time and determine the priority of analysis. For example, the analysis unit prioritizes the analysis of data with an approaching submission deadline. The analysis unit can also postpone the analysis of data with an earlier submission date. Furthermore, the analysis unit can adjust the analysis method and frequency based on the submission timing of the training data. For example, by prioritizing the analysis of recently submitted data and data with an approaching submission deadline, the analysis unit can perform more effective analysis. Thus, by determining the priority of analysis based on the submission timing of the training data, the analysis unit can perform more effective analysis. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without using AI.

[0047] The analysis unit adjusts the order of analysis based on the relevance of the training data during analysis. For example, the analysis unit prioritizes analyzing highly relevant data. The analysis unit can also use AI to evaluate the relevance of the training data in real time and adjust the order of analysis. For example, the analysis unit postpones the analysis of less relevant data. The analysis unit can also perform detailed analysis on highly relevant data. Furthermore, the analysis unit can adjust the method and frequency of analysis based on the relevance of the training data. For example, by prioritizing the analysis of highly relevant data and postponing the analysis of less relevant data, the analysis unit can perform more effective analysis. Thus, the analysis unit can perform more effective analysis by adjusting the order of analysis based on the relevance of the training data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without using AI.

[0048] The provider adjusts the level of detail of the questions based on the importance of the training data when providing questions. For example, the provider provides detailed questions for important data. The provider can also use AI to evaluate the importance of the training data in real time and adjust the level of detail of the questions when providing them. For example, the provider provides simplified questions for less important data. The provider can also provide multiple questions for highly important data. Furthermore, the provider can adjust the format and difficulty of the questions based on the importance of the training data. For example, by providing detailed questions for highly important data and simplified questions for less important data, the provider can provide questions more effectively. In this way, the provider can provide questions more effectively by adjusting the level of detail of the questions based on the importance of the training data. Some or all of the above processing in the provider may be performed using AI, for example, or without using AI.

[0049] The problem provider applies different provisioning algorithms depending on the category of the training data when providing problems. For example, the provider provides numerical problems for mathematical data. The provider can also use AI to evaluate the category of the training data in real time and apply different provisioning algorithms when providing problems. For example, the provider provides word problems for language data. The provider can also provide experimental problems for science data. Furthermore, the provider can adjust the format and difficulty of the problems based on the category of the training data. For example, by providing numerical problems for mathematical data and word problems for language data, the provider can provide problems more effectively. This allows the provider to provide problems more effectively by applying different provisioning algorithms depending on the category of the training data. Some or all of the above processing in the provider may be performed using AI, for example, or without using AI.

[0050] The provisioning unit prioritizes problems based on when the training data was submitted. For example, it provides problems based on recently submitted data. The provisioning unit can also use AI to evaluate the timing of training data submissions in real time and prioritize problems when providing them. For example, it can provide problems based on data with an approaching submission deadline. It can also provide problems based on data with a past submission date. Furthermore, the provisioning unit can adjust the format and difficulty of the problems based on when the training data was submitted. For example, by providing problems based on recently submitted data and problems based on data with an approaching submission deadline, the provisioning unit can provide problems more effectively. This allows the provisioning unit to provide problems more effectively by prioritizing problems based on when the training data was submitted. Some or all of the above processing in the provisioning unit may be performed using AI, for example, or without using AI.

[0051] The provider adjusts the order of questions based on the relevance of the training data when providing questions. For example, the provider provides questions based on highly relevant data. The provider can also use AI to evaluate the relevance of the training data in real time and adjust the order of questions when providing them. For example, the provider provides questions based on less relevant data. The provider can also provide more detailed questions for highly relevant data. Furthermore, the provider can adjust the format and difficulty of the questions based on the relevance of the training data. For example, by providing questions based on highly relevant data and questions based on less relevant data, the provider can provide questions more effectively. This allows the provider to provide questions more effectively by adjusting the order of questions based on the relevance of the training data. Some or all of the above processing in the provider may be performed using AI, for example, or without using AI.

[0052] The planning unit creates an optimal learning plan by referring to past learning data when planning a learning plan. For example, the planning unit creates an optimal learning plan based on past learning data. The planning unit can also use AI to refer to past learning data in real time and create an optimal plan when planning a learning plan. For example, the planning unit creates a plan that focuses on areas where the student is weak based on past learning data. The planning unit can also analyze past learning data and create an efficient learning plan. Furthermore, the planning unit can adjust the content and schedule of the learning plan based on past learning data. For example, the planning unit can provide a more effective learning plan by creating an optimal learning plan based on past learning data and creating a plan that focuses on areas where the student is weak. In this way, the planning unit can provide a more effective learning plan by creating an optimal plan by referring to past learning data. Some or all of the above processes in the planning unit may be performed using AI, for example, or without using AI.

[0053] The planning unit customizes the learning plan based on the child's current learning situation. For example, the planning unit creates an optimal learning plan based on the child's current learning situation. The planning unit can also use AI to evaluate the child's current learning situation in real time and customize the plan when creating the learning plan. For example, the planning unit can create a plan that focuses on areas where the child is struggling, based on the child's current learning situation. The planning unit can also analyze the child's current learning situation and create an efficient learning plan. Furthermore, the planning unit can adjust the content and schedule of the learning plan based on the child's current learning situation. For example, by creating an optimal learning plan based on the child's current learning situation and creating a plan that focuses on areas where the child is struggling, the planning unit can provide a more effective learning plan. In this way, the planning unit can provide a more effective learning plan by customizing the plan based on the child's current learning situation. Some or all of the above processes in the planning unit may be performed using AI, for example, or not using AI.

[0054] The planning unit creates an optimal learning plan based on the child's geographical location. For example, if the child is at school, the planning unit creates a learning plan related to the school curriculum. The planning unit can also use AI to evaluate the child's geographical location in real time and create an optimal learning plan. For example, if the child is at home, the planning unit creates a learning plan related to home learning. Furthermore, if the child is at the library, the planning unit can create a learning plan related to library materials. In addition, the planning unit can adjust the content and schedule of the learning plan based on the child's geographical location. For example, by creating a learning plan related to the school curriculum when the child is at school and a learning plan related to home learning when the child is at home, the planning unit can provide a more effective learning plan. This allows the planning unit to provide a more effective learning plan by creating an optimal plan based on the child's geographical location. Some or all of the above processes in the planning unit may be performed using AI, for example, or without AI.

[0055] The planning department analyzes the child's social media activity and adjusts the plan when creating a learning plan. For example, the planning department adjusts the learning plan based on the learning content the child shares on social media. The planning department can also use AI to analyze the child's social media activity in real time and adjust the plan when creating a learning plan. For example, the planning department adjusts the learning plan based on information from educational accounts the child follows on social media. The planning department can also adjust the learning plan to topics the child has shown interest in on social media. Furthermore, the planning department can adjust the content and schedule of the learning plan based on the child's social media activity. For example, by adjusting the learning plan based on the learning content the child shares on social media and by adjusting the learning plan based on information from educational accounts the child follows on social media, the planning department can provide a more effective learning plan. In this way, the planning department can provide a more effective learning plan by analyzing the child's social media activity and adjusting the plan. Some or all of the above processes in the planning department may be performed using AI, for example, or not using AI.

[0056] The feedback department, when providing feedback, analyzes the cause of the incorrect answer in detail and makes specific suggestions. For example, the feedback department identifies the cause of the incorrect answer and makes specific suggestions. The feedback department can also use AI to analyze the cause of the incorrect answer in real time and make specific suggestions when providing feedback. For example, the feedback department analyzes the cause of the incorrect answer and suggests areas for improvement. The feedback department can also explain the cause of the incorrect answer in detail and provide measures to prevent recurrence. Furthermore, the feedback department can adjust the content and format of the feedback based on the cause of the incorrect answer. For example, by identifying the cause of the incorrect answer, making specific suggestions, and suggesting areas for improvement, the feedback department can provide more effective feedback. This allows the feedback department to provide more effective feedback by analyzing the cause of the incorrect answer in detail and making specific suggestions. Some or all of the above processes in the feedback department may be performed using AI, for example, or without using AI.

[0057] The feedback unit applies a method of teaching the correct solution step by step during feedback. For example, the feedback unit teaches the correct solution step by step. The feedback unit can also apply a method of teaching the correct solution step by step in real time using AI. For example, the feedback unit explains the correct solution step by step. The feedback unit can also visually represent the correct solution. Furthermore, the feedback unit can adjust the content and format of the feedback based on the method of teaching the correct solution step by step. For example, by teaching the correct solution step by step, explaining it step by step, and visually representing it, the feedback unit can provide more effective feedback. Thus, by applying a method of teaching the correct solution step by step, the feedback unit can provide more effective feedback. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without using AI.

[0058] The feedback unit adjusts the level of detail in the feedback based on the frequency of incorrect answers. For example, if the frequency of incorrect answers is high, the feedback unit provides detailed feedback. The feedback unit can also use AI to evaluate the frequency of incorrect answers in real time and adjust the level of detail in the feedback. For example, if the frequency of incorrect answers is low, the feedback unit provides simplified feedback. The feedback unit can also adjust the content and format of the feedback according to the frequency of incorrect answers. Furthermore, the feedback unit can adjust the method and frequency of feedback based on the frequency of incorrect answers. For example, by providing detailed feedback when the frequency of incorrect answers is high and simplified feedback when the frequency is low, the feedback unit can provide more effective feedback. Thus, by adjusting the level of detail in the feedback unit based on the frequency of incorrect answers, the feedback unit can provide more effective feedback. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without using AI.

[0059] The feedback unit improves the accuracy of feedback by referring to relevant learning materials during the feedback process. For example, the feedback unit improves the accuracy of feedback by referring to relevant learning materials. The feedback unit can also use AI to refer to relevant learning materials in real time and improve the accuracy of feedback during the feedback process. For example, the feedback unit provides specific feedback based on relevant learning materials. Furthermore, the feedback unit can enrich the content of the feedback by utilizing relevant learning materials. In addition, the feedback unit can adjust the content and format of the feedback based on relevant learning materials. For example, by referring to relevant learning materials, the feedback unit can improve the accuracy of feedback, provide specific feedback, and enrich the content of the feedback, thereby enabling more effective feedback. Thus, by referring to relevant learning materials and improving the accuracy of feedback, the feedback unit can enable more effective feedback. Some or all of the above-described processes in the feedback unit may be performed using AI, for example, or without AI.

[0060] The tuning unit updates the content of the questions in response to changes in the child's interests during tuning. For example, if the child's interests change, the tuning unit updates the content of the questions. The tuning unit can also use AI to evaluate changes in the child's interests in real time and update the content of the questions during tuning. For example, the tuning unit changes the theme of the questions according to the child's interests. The tuning unit can also adjust the content of the questions to reflect changes in the child's interests. Furthermore, the tuning unit can adjust the format and difficulty level of the questions based on changes in the child's interests. For example, if the child's interests change, the tuning unit can provide more effective questions by updating the content of the questions and changing the theme of the questions. In this way, the tuning unit can provide more effective questions by updating the content of the questions in response to changes in the child's interests. Some or all of the above processing in the tuning unit may be performed using AI, for example, or without using AI.

[0061] The tuning unit adjusts the difficulty level of the problems based on the child's learning progress during tuning. For example, if the child's learning progress is fast, the tuning unit increases the difficulty level of the problems. The tuning unit can also use AI to evaluate the child's learning progress in real time and adjust the difficulty level of the problems during tuning. For example, if the child's learning progress is slow, the tuning unit decreases the difficulty level of the problems. The tuning unit can also adjust the format and frequency of the problems according to the child's learning progress. Furthermore, the tuning unit can adjust the content and format of the problems based on the child's learning progress. For example, by increasing the difficulty level of the problems when the child's learning progress is fast and decreasing it when the child's learning progress is slow, the tuning unit can provide more effective problems. In this way, the tuning unit can provide more effective problems by adjusting the difficulty level of the problems based on the child's learning progress. Some or all of the above processing in the tuning unit may be performed using AI, for example, or without using AI.

[0062] The adjustment unit gradually increases the difficulty level of the problems according to the child's learning progress during the adjustment process. For example, if the child's learning progress is fast, the adjustment unit gradually increases the difficulty level of the problems. The adjustment unit can also use AI to evaluate the child's learning progress in real time and gradually increase the difficulty level of the problems during the adjustment process. For example, if the child's learning progress is slow, the adjustment unit gradually decreases the difficulty level of the problems. The adjustment unit can also adjust the format and frequency of the problems according to the child's learning progress. Furthermore, the adjustment unit can adjust the content and format of the problems based on the child's learning progress. For example, by gradually increasing the difficulty level of the problems when the child's learning progress is fast and gradually decreasing it when the child's learning progress is slow, the adjustment unit can provide more effective problems. In this way, the adjustment unit can provide more effective problems by gradually increasing the difficulty level of the problems according to the child's learning progress. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without using AI.

[0063] The adjustment unit customizes the difficulty level of problems based on the child's learning history during the adjustment process. For example, the adjustment unit provides problems of the optimal difficulty level based on the learning history. The adjustment unit can also use AI to evaluate the child's learning history in real time and customize the difficulty level of problems during the adjustment process. For example, the adjustment unit can focus on providing problems in areas where the child struggles, based on the learning history. The adjustment unit can also analyze the learning history and perform efficient difficulty level adjustments. Furthermore, the adjustment unit can adjust the content and format of the problems based on the child's learning history. For example, by providing problems of the optimal difficulty level based on the learning history and focusing on problems in areas where the child struggles, the adjustment unit can provide more effective problems. Thus, by customizing the difficulty level of problems based on the child's learning history, the adjustment unit can provide more effective problems. Some or all of the above processes in the adjustment unit may be performed using AI, for example, or without using AI.

[0064] The notification unit selects the optimal notification method by referring to the parent's past response history when sending a notification. For example, the notification unit selects the optimal notification method based on the parent's past response history. The notification unit can also use AI to refer to the parent's past response history in real time and select the optimal notification method when sending a notification. For example, the notification unit selects an effective notification method from the parent's response history. The notification unit can also analyze the parent's past responses and provide the optimal notification method. Furthermore, the notification unit can adjust the content and format of the notification based on the parent's past response history. For example, by selecting the optimal notification method based on the parent's past response history and selecting an effective notification method from the parent's response history, the notification unit can send more effective notifications. Thus, by referring to the parent's past response history and selecting the optimal notification method, the notification unit can send more effective notifications. Some or all of the above processing in the notification unit may be performed using AI, for example, or without using AI.

[0065] The notification unit selects the optimal notification method when sending a notification, taking into account the parent's device information. For example, if the parent is using a smartphone, the notification unit will send a push notification. The notification unit can also use AI to evaluate the parent's device information in real time and select the optimal notification method when sending a notification. For example, if the parent is using a tablet, the notification unit will send a notification optimized for a larger screen. Furthermore, if the parent is using a smartwatch, the notification unit can send a concise and highly visible notification. In addition, the notification unit can adjust the content and format of the notification based on the parent's device information. For example, by sending a push notification when the parent is using a smartphone and a notification optimized for a larger screen when the parent is using a tablet, the notification unit can provide more effective notifications. This allows the notification unit to provide more effective notifications by selecting the optimal notification method considering the parent's device information. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI.

[0066] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0067] The analysis unit can adjust its analysis method to take into account the child's learning style when analyzing the child's learning data. For example, it can provide analysis results using graphs and diagrams for children with a visual learning style. It can also provide audio feedback for children with an auditory learning style. Furthermore, it can provide interactive analysis results for children with a tactile learning style. In this way, the analysis unit can provide analysis methods tailored to the child's learning style, enabling more effective learning support.

[0068] The service provider can offer rewards based on the child's learning data, according to their learning progress. For example, they can award digital badges or points when certain learning goals are achieved. They can also provide in-game items or rewards for completing specific tasks. Furthermore, they can provide words of praise and encouragement from parents based on the child's learning progress. In this way, the service provider can maintain the child's motivation to learn by offering rewards that enhance their desire to learn.

[0069] The planning department can adjust the schedule when creating a learning plan, taking into account the child's daily rhythm. For example, if a child has a morning routine, the schedule can be set to allow for focused learning during the morning hours. Similarly, for children with a night owl routine, the schedule can be adjusted to allow for learning during the evening hours. Furthermore, the learning plan can be flexibly adjusted to take into account weekend and holiday schedules. In this way, the planning department can maximize the effectiveness of learning by providing a learning plan that is tailored to the child's daily rhythm.

[0070] The data collection unit can adjust its data collection method to take into account the child's learning environment when collecting children's learning data. For example, if the child is learning in a quiet environment, it can collect detailed data. Conversely, if the child is learning in a noisy environment, it can collect only the most important data. Furthermore, it can adjust the frequency and method of data collection in response to changes in the learning environment. As a result, the data collection unit can obtain more accurate learning data by collecting data according to the child's learning environment.

[0071] The feedback system can adjust the content of feedback based on the child's learning data and their progress. For example, if a child is progressing quickly, it can provide advice on how to move on to the next step. If a child is progressing slowly, it can provide supplementary explanations to deepen their understanding. Furthermore, it can adjust the frequency and format of feedback according to the child's progress. In this way, the feedback system can enhance the effectiveness of learning by providing feedback tailored to the child's learning progress.

[0072] The following briefly describes the processing flow for example form 1.

[0073] Step 1: The data collection unit collects children's learning data. For example, it collects data such as the accuracy rate and time taken to solve problems. The data collection unit can also use AI to collect children's learning data in real time. Step 2: The analysis unit analyzes the data collected by the data collection unit and evaluates the child's level of understanding. For example, if the child's understanding is low in a particular area, the analysis unit adjusts the questions to include more related problems. The analysis unit can also use AI to evaluate the child's level of understanding in real time. Step 3: The provisioning unit provides problems based on the evaluation results obtained by the analysis unit. For example, it can tune problems based on children's interests. The provisioning unit can also use AI to tune problems in real time based on children's interests. Step 4: The Planning Department plans and executes a learning plan based on the problems provided by the Delivery Department. For example, it creates a daily learning schedule based on the child's level of understanding and interests, and presents problems at appropriate times. The Planning Department can also use AI to plan and execute the learning plan in real time. Step 5: The Feedback Department provides feedback on incorrect answers based on the learning plan developed by the Planning Department. For example, it will specifically point out which part of a question a child answered incorrectly and teach them the correct way to answer it. The Feedback Department can also use AI to provide real-time feedback on incorrect answers.

[0074] (Example of form 2) The learning support system according to an embodiment of the present invention is a learning service incorporating elements of an AI agent. This learning support system targets parents of children who need to study and provides problems tailored to each child's level of understanding and interests in tests, entrance exams, qualification exams, etc. The learning support system uses AI to grasp the child's level of understanding in real time, autonomously plan and execute a learning plan, and tune problems to match the child's interests to increase motivation. For example, the learning support system first uses AI to collect the child's learning data and grasp their level of understanding in real time. For example, it collects data such as the correct answer rate and answer time for problems the child has solved. Next, the learning support system uses AI to analyze the collected data and evaluate the child's level of understanding. For example, if the child's understanding is low in a particular area, the system adjusts to present more problems related to that area. Furthermore, the learning support system uses AI to tune problems based on the child's interests. For example, if the child is interested in a particular anime or sport, the system presents problems related to that theme. This can increase the child's motivation to learn. In addition, the learning support system uses AI to autonomously plan and execute a learning plan. For example, the system creates a daily learning schedule based on the child's understanding and interests, and presents problems at appropriate times. Furthermore, the learning support system uses AI to provide appropriate feedback on incorrect answers. For instance, it specifically points out which part of a child's answer is wrong and teaches them the correct way to answer. In this way, the learning support system can provide an optimal learning environment for each child and increase their motivation to learn. Parents can monitor their child's learning progress in real time and provide appropriate support. This maximizes the child's learning outcomes and leads to future success. In this way, the learning support system can provide an optimal learning environment for each child by collecting and analyzing the child's learning data, providing problems, planning and executing learning plans, and providing feedback.

[0075] The learning support system according to this embodiment comprises a collection unit, an analysis unit, a provision unit, a planning unit, and a feedback unit. The collection unit collects the child's learning data. For example, the collection unit collects data such as the correct answer rate and answer time for problems solved by the child. The collection unit can also collect the child's learning data in real time using AI. The analysis unit analyzes the data collected by the collection unit and evaluates the child's level of understanding. For example, if the child's understanding in a particular area is low, the analysis unit adjusts the system to present more problems related to that area. The analysis unit can also evaluate the child's level of understanding in real time using AI. The provision unit provides problems based on the evaluation results obtained by the analysis unit. For example, the provision unit tunes the problems based on the child's interests. The provision unit can also tune the problems in real time based on the child's interests using AI. The planning unit plans and executes a learning plan based on the problems provided by the provision unit. For example, the planning unit creates a daily learning schedule based on the child's level of understanding and interests, and presents problems at appropriate times. The planning unit can also use AI to plan and execute learning plans in real time. The feedback unit provides feedback on incorrect answers based on the learning plan planned by the planning unit. For example, the feedback unit will specifically point out which part of a problem a child got wrong and teach the correct way to answer it. The feedback unit can also use AI to provide feedback on incorrect answers in real time. As a result, the learning support system according to this embodiment can provide an optimal learning environment for each child by collecting and analyzing the child's learning data, providing problems, planning and executing learning plans, and providing feedback.

[0076] The data collection unit collects children's learning data. For example, it collects data such as the accuracy rate and time taken to answer problems that children have solved. Specifically, if a child is using an online learning platform, the results of each problem are automatically recorded, and the accuracy rate, time taken, and answer patterns are collected in detail. Furthermore, the data collection unit can also collect children's learning data in real time using AI. The AI ​​monitors the child's learning behavior and analyzes in real time, for example, which problems take the child the most time to solve and which problems the child makes the most mistakes on. This allows the data collection unit to understand the child's learning situation in detail and accurately. The data collection unit can also collect data about the child's learning environment. For example, it can collect information such as the time of day and location in which the child is studying and the type of device being used, and evaluate the impact of the learning environment on learning outcomes. This allows the data collection unit to collect children's learning data from multiple perspectives and build a foundation for providing more comprehensive learning support.

[0077] The analysis unit analyzes the data collected by the data collection unit and evaluates the child's level of understanding. For example, if the child's understanding is low in a particular area, the analysis unit adjusts the questions to include more problems related to that area. Specifically, it uses AI to analyze the child's answer data and evaluate their understanding in each area. The AI ​​uses machine learning algorithms to analyze the child's answer patterns, correct answer rate, and answer time to identify areas where the child's understanding is weak. For example, in the case of mathematics problems, it evaluates the child's understanding in each area such as arithmetic, algebra, and geometry, and then presents questions that focus on the areas where the child's understanding is weak. The analysis unit can also monitor the child's learning progress in real time and adjust the learning plan as needed. For example, if a child is struggling with a particular problem, it will provide additional basic problems related to that problem to help deepen their understanding. This allows the analysis unit to have a detailed understanding of the child's learning situation and provide learning support tailored to individual needs. Furthermore, the analysis unit can analyze the child's learning patterns and trends based on past learning data, which can be used to plan future learning.

[0078] The provisioning department provides problems based on evaluation results obtained by the analysis department. The provisioning department tunes the problems based on the child's interests, for example. Specifically, it can use AI to tune problems in real time based on the child's interests. The AI ​​analyzes the child's past learning history and answer patterns and selects problems in themes and formats that are likely to interest the child. For example, if a child is interested in animals, the provisioning department will present math or science problems related to animals to increase their motivation to learn. The provisioning department can also adjust the difficulty level of the problems according to the child's level of understanding. For example, it will present more difficult problems in areas where the child understands well and more basic problems in areas where the child understands less well. In this way, the provisioning department can provide problems that are optimal for each child and support effective learning. Furthermore, the provisioning department can provide flexible learning support that matches the child's learning rhythm by adjusting the frequency and timing of problem presentation. For example, it will present more difficult problems during times when the child is likely to concentrate well and review problems or easier problems during times when the child is tired. In this way, the provisioning department can maximize the child's learning efficiency and provide effective learning support.

[0079] The Planning Department plans and executes learning plans based on the problems provided by the Delivery Department. For example, the Planning Department creates a daily learning schedule based on the child's level of understanding and interests, and presents problems at appropriate times. Specifically, it can also plan and execute learning plans in real time using AI. The AI ​​analyzes the child's learning data and automatically generates an optimal learning schedule. For example, if a child is more likely to concentrate during a particular time, it will present more difficult problems during that time to deepen their understanding. The Planning Department can also monitor the child's learning progress in real time and adjust the learning plan as needed. For example, if a child is learning faster than planned, it will present additional new problems to maintain the learning pace. Also, if a child is struggling with a particular problem, it will present additional basic problems related to that problem to help deepen their understanding. In this way, the Planning Department can provide flexible learning plans tailored to the child's learning situation and provide effective learning support. Furthermore, the Planning Department can set long-term learning goals and provide a step-by-step learning plan that matches the child's growth. For example, it can set a one-year learning goal and create monthly and weekly learning plans to achieve that goal. This allows the planning department to provide long-term support for children's learning and achieve sustained learning outcomes.

[0080] The Feedback Department provides feedback on incorrect answers based on the learning plan developed by the Planning Department. For example, the Feedback Department will specifically point out which part of a problem a child answered incorrectly and teach the correct solution method. Specifically, it can also use AI to provide real-time feedback on incorrect answers. The AI ​​analyzes the child's answer data and identifies the cause of the incorrect answer. For example, it analyzes patterns of incorrect answers, such as calculation errors or misunderstandings of concepts, and provides appropriate feedback. The Feedback Department can also provide feedback using visual explanations and concrete examples to make it easier for children to understand. For example, for a math problem, it can use diagrams and graphs to visually explain the solution method and deepen understanding. The Feedback Department can also adjust the content and timing of feedback according to the child's learning progress. For example, if a child repeatedly makes mistakes on a particular problem, it will explain the basic concepts related to that problem again to help deepen understanding. In this way, the Feedback Department can maximize the child's learning effectiveness and provide effective learning support. Furthermore, the Feedback Department can monitor the child's learning progress and evaluate the effectiveness of the feedback. For example, it can analyze changes in the correct answer rate and answer time after feedback to evaluate the effectiveness of the feedback. This allows the feedback system to continuously improve the content and methods of feedback, maximizing the learning effectiveness for children.

[0081] The service provider includes a tuning unit that adjusts the questions based on the child's interests. For example, if a child is interested in a particular anime or sport, the tuning unit will present questions related to that theme. The tuning unit can also use AI to adjust the questions in real time based on the child's interests. For example, the tuning unit can present questions using characters from the child's favorite anime. It can also present questions related to sports that the child is interested in. Furthermore, the tuning unit can adjust the difficulty and format of the questions based on the child's interests. For example, by presenting questions related to themes that the child is interested in, the tuning unit can increase the child's motivation to learn. In this way, the service provider can increase the child's motivation to learn by adjusting the questions based on the child's interests.

[0082] The planning unit includes an adjustment unit that adjusts the difficulty level of problems according to the child's learning progress. The adjustment unit can, for example, raise or lower the difficulty level of problems based on the child's learning progress. The adjustment unit can also use AI to adjust the difficulty level of problems in real time based on the child's learning progress. For example, if the child's understanding of a particular subject is low, the adjustment unit can lower the difficulty level of problems related to that subject. Conversely, if the child's understanding of a particular subject is high, the adjustment unit can also raise the difficulty level of problems related to that subject. Furthermore, the adjustment unit can also adjust the format and frequency of questions based on the child's learning progress. For example, the adjustment unit can maximize the child's learning effectiveness by presenting more questions related to areas where the child has a low understanding. In this way, the planning unit can maximize the child's learning effectiveness by adjusting the difficulty level of problems according to their learning progress.

[0083] The data collection unit includes a notification unit that informs parents about their child's learning progress. The notification unit notifies parents, for example, of information regarding the child's learning progress and comprehension level. The notification unit can also use AI to notify parents of the child's learning progress in real time. For example, if the child's comprehension level is low in a particular area, the notification unit will notify the parents of that information. The notification unit can also notify parents if the child's comprehension level is high in a particular area. Furthermore, the notification unit can also suggest appropriate support to parents based on the child's learning progress. For example, the notification unit will suggest learning materials and learning methods related to areas where the child's comprehension is low. In this way, the data collection unit makes it easier for parents to support their child's learning by notifying them of the child's learning progress.

[0084] The feedback system provides specific feedback and correct solutions for incorrect answers. For example, it will specifically point out which part of a child's answer was wrong. The feedback system can also use AI to provide specific feedback and correct solutions in real time for incorrect answers. For example, it can analyze the child's answer process for a question they answered incorrectly and identify where they went wrong. It can also specifically teach the correct solution. Furthermore, the feedback system can provide children with opportunities to try the questions they answered incorrectly again. For example, it can re-present the question the child answered incorrectly and allow them to confirm the correct solution. In this way, the feedback system can deepen the child's understanding by providing specific feedback and correct solutions for incorrect answers.

[0085] The analysis unit analyzes data including the children's response times. For example, the analysis unit collects and analyzes data on the time children spend answering questions. The analysis unit can also use AI to analyze children's response times in real time. For example, the analysis unit analyzes how long a child spends on a particular problem and evaluates their level of understanding based on that data. The analysis unit can also adjust the difficulty level and frequency of questions based on the response time data. Furthermore, the analysis unit can analyze children's response times in combination with other learning data. For example, the analysis unit analyzes the relationship between response time and the accuracy rate to understand the child's learning pattern. As a result, the analysis unit can more accurately evaluate a child's level of understanding by analyzing data including their response times.

[0086] The data collection unit estimates the child's emotions and adjusts the timing of data collection based on the estimated emotions. For example, the unit collects data when the child is focused and pauses collection when their concentration wavers. The data collection unit can also use AI to estimate the child's emotions in real time and adjust the timing of data collection. For example, if the unit is stressed, it will delay collection until the child is relaxed. It can also collect data when the child is having fun. Furthermore, the unit can adjust the data collection method based on the child's emotional data. For example, if the unit is relaxed, it will collect detailed data, and if the child is tired, it will collect simplified data. This allows the unit to collect data more effectively by adjusting the timing of data collection based on the child's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or without using AI.

[0087] The data collection unit analyzes the child's past learning history and selects the optimal collection method. For example, the collection unit prioritizes collecting question formats in which the child has previously achieved a high correct answer rate. The collection unit can also use AI to analyze the child's past learning history in real time and select the optimal collection method. For example, the collection unit avoids collecting question formats in which the child has previously struggled. The collection unit can also prioritize collecting question formats in which the child has previously answered quickly. Furthermore, the collection unit can adjust the type and frequency of data collected based on the child's past learning history. For example, by prioritizing the collection of question formats in which the child has previously achieved a high correct answer rate, the collection unit can maximize the child's learning effectiveness. In this way, the collection unit can select the optimal collection method by analyzing the child's past learning history. Some or all of the above processing in the collection unit may be performed using AI, for example, or without using AI.

[0088] The data collection unit filters learning data based on the child's current learning environment and level of concentration. For example, if the child is learning in a quiet environment, the data collection unit will collect detailed data. The data collection unit can also use AI to evaluate the child's current learning environment and level of concentration in real time and filter the data when collecting it. For example, if the child is learning in a noisy environment, the data collection unit will collect only important data. Alternatively, if the child is focused, the data collection unit can collect all data. Furthermore, the data collection unit can adjust the type and frequency of data collected based on the child's learning environment and level of concentration. For example, by collecting detailed data when the child is learning in a quiet environment and only important data when the child is learning in a noisy environment, more accurate data collection becomes possible. This allows the data collection unit to filter learning data based on the child's current learning environment and level of concentration, enabling more accurate data collection. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI.

[0089] The data collection unit estimates the child's emotions and prioritizes the data to collect based on the estimated emotions. For example, if the child is excited, the data collection unit prioritizes collecting data that will capture the child's interest. The data collection unit can also use AI to estimate the child's emotions in real time and prioritize the data to collect. For example, if the child is tired, the data collection unit prioritizes collecting simple data. Conversely, if the child is relaxed, the data collection unit can prioritize collecting detailed data. Furthermore, the data collection unit can adjust the type and frequency of data collected based on the child's emotional data. For example, by prioritizing data that will capture the child's interest when the child is excited and simple data when the child is tired, more effective data collection becomes possible. This allows the data collection unit to prioritize data collection based on the child's emotions, enabling more effective data collection. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or without using AI.

[0090] The data collection unit prioritizes collecting highly relevant data based on the child's geographical location when collecting learning data. For example, if the child is at school, the data collection unit prioritizes collecting data related to the school curriculum. The data collection unit can also use AI to evaluate the child's geographical location in real time and prioritize collecting highly relevant data when collecting learning data. For example, if the child is at home, the data collection unit prioritizes collecting data related to home learning. Furthermore, if the child is at the library, the data collection unit can prioritize collecting data related to library materials. In addition, the data collection unit can adjust the type and frequency of data collected based on the child's geographical location. For example, by prioritizing data related to the school curriculum when the child is at school and data related to home learning when the child is at home, more effective data collection becomes possible. This allows the data collection unit to prioritize collecting highly relevant data based on the child's geographical location, enabling more effective data collection. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI.

[0091] The data collection unit analyzes children's social media activities and collects relevant data when collecting learning data. For example, the data collection unit collects learning content that children share on social media. The data collection unit can also use AI to analyze children's social media activities in real time and collect relevant data when collecting learning data. For example, the data collection unit collects information on educational accounts that children follow on social media. The data collection unit can also collect data related to topics that children have shown interest in on social media. Furthermore, the data collection unit can adjust the type and frequency of data collected based on children's social media activities. For example, by collecting learning content that children share on social media and information on educational accounts that children follow on social media, the data collection unit can collect data more effectively. This allows the data collection unit to collect data more effectively by analyzing children's social media activities and collecting relevant data when collecting learning data. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI.

[0092] The analysis unit estimates the child's emotions and adjusts the analysis method based on the estimated emotions. For example, if the child is relaxed, the analysis unit performs a detailed analysis. The analysis unit can also use AI to estimate the child's emotions in real time and adjust the analysis method. For example, if the child is in a hurry, the analysis unit performs a simplified analysis. The analysis unit can also provide visually stimulating analysis results if the child is excited. Furthermore, the analysis unit can adjust the level of detail and frequency of the analysis based on the child's emotion data. For example, by performing a detailed analysis when the child is relaxed and a simplified analysis when the child is in a hurry, the analysis unit can perform a more effective analysis. In this way, the analysis unit can perform a more effective analysis by adjusting the analysis method based on the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI.

[0093] The analysis unit adjusts the level of detail of the analysis based on the importance of the training data during the analysis. For example, the analysis unit performs a detailed analysis on important data. The analysis unit can also use AI to evaluate the importance of the training data in real time and adjust the level of detail of the analysis. For example, the analysis unit performs a simplified analysis on less important data. The analysis unit can also apply multiple analysis methods to highly important data. Furthermore, the analysis unit can adjust the frequency and method of analysis based on the importance of the training data. For example, by performing a detailed analysis on highly important data and a simplified analysis on less important data, the analysis unit can perform a more effective analysis. In this way, the analysis unit can perform a more effective analysis by adjusting the level of detail of the analysis based on the importance of the training data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without using AI.

[0094] The analysis unit applies different analysis algorithms depending on the category of the training data during analysis. For example, the analysis unit applies a numerical analysis algorithm to mathematical data. The analysis unit can also use AI to evaluate the category of the training data in real time and apply different analysis algorithms during analysis. For example, the analysis unit applies a natural language processing algorithm to language data. The analysis unit can also apply a scientific analysis algorithm to science data. Furthermore, the analysis unit can adjust the method and frequency of analysis based on the category of the training data. For example, by applying a numerical analysis algorithm to mathematical data and a natural language processing algorithm to language data, the analysis unit can perform more effective analysis. Thus, the analysis unit can perform more effective analysis by applying different analysis algorithms depending on the category of the training data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI.

[0095] The analysis unit estimates the child's emotions and determines the analysis priority based on the estimated emotions. For example, if the child is excited, the analysis unit prioritizes analyzing data that will interest them. The analysis unit can also use AI to estimate the child's emotions in real time and determine the analysis priority. For example, if the child is tired, the analysis unit prioritizes analyzing simple data. It can also prioritize analyzing detailed data if the child is relaxed. Furthermore, the analysis unit can adjust the analysis method and frequency based on the child's emotional data. For example, by prioritizing the analysis of interesting data when the child is excited and the analysis of simple data when the child is tired, more effective analysis becomes possible. This allows the analysis unit to perform more effective analysis by determining the analysis priority based on the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or without using AI.

[0096] The analysis unit determines the priority of analysis based on the submission timing of the training data. For example, the analysis unit prioritizes the analysis of recently submitted data. The analysis unit can also use AI to evaluate the submission timing of the training data in real time and determine the priority of analysis. For example, the analysis unit prioritizes the analysis of data with an approaching submission deadline. The analysis unit can also postpone the analysis of data with an earlier submission date. Furthermore, the analysis unit can adjust the analysis method and frequency based on the submission timing of the training data. For example, by prioritizing the analysis of recently submitted data and data with an approaching submission deadline, the analysis unit can perform more effective analysis. Thus, by determining the priority of analysis based on the submission timing of the training data, the analysis unit can perform more effective analysis. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without using AI.

[0097] The analysis unit adjusts the order of analysis based on the relevance of the training data during analysis. For example, the analysis unit prioritizes analyzing highly relevant data. The analysis unit can also use AI to evaluate the relevance of the training data in real time and adjust the order of analysis. For example, the analysis unit postpones the analysis of less relevant data. The analysis unit can also perform detailed analysis on highly relevant data. Furthermore, the analysis unit can adjust the method and frequency of analysis based on the relevance of the training data. For example, by prioritizing the analysis of highly relevant data and postponing the analysis of less relevant data, the analysis unit can perform more effective analysis. Thus, the analysis unit can perform more effective analysis by adjusting the order of analysis based on the relevance of the training data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without using AI.

[0098] The service provider estimates the child's emotions and adjusts the way problems are presented based on the estimated emotions. For example, if the child is relaxed, the service provider will provide problems with detailed explanations. The service provider can also use AI to estimate the child's emotions in real time and adjust the way problems are presented. For example, if the child is in a hurry, the service provider will provide concise problems. The service provider can also provide visually stimulating problems if the child is excited. Furthermore, the service provider can adjust the format and difficulty of problems based on the child's emotion data. For example, by providing problems with detailed explanations when the child is relaxed and concise problems when the child is in a hurry, the service provider can provide problems more effectively. This allows the service provider to provide problems more effectively by adjusting the way problems are presented based on the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI.

[0099] The provider adjusts the level of detail of the questions based on the importance of the training data when providing questions. For example, the provider provides detailed questions for important data. The provider can also use AI to evaluate the importance of the training data in real time and adjust the level of detail of the questions when providing them. For example, the provider provides simplified questions for less important data. The provider can also provide multiple questions for highly important data. Furthermore, the provider can adjust the format and difficulty of the questions based on the importance of the training data. For example, by providing detailed questions for highly important data and simplified questions for less important data, the provider can provide questions more effectively. In this way, the provider can provide questions more effectively by adjusting the level of detail of the questions based on the importance of the training data. Some or all of the above processing in the provider may be performed using AI, for example, or without using AI.

[0100] The problem provider applies different provisioning algorithms depending on the category of the training data when providing problems. For example, the provider provides numerical problems for mathematical data. The provider can also use AI to evaluate the category of the training data in real time and apply different provisioning algorithms when providing problems. For example, the provider provides word problems for language data. The provider can also provide experimental problems for science data. Furthermore, the provider can adjust the format and difficulty of the problems based on the category of the training data. For example, by providing numerical problems for mathematical data and word problems for language data, the provider can provide problems more effectively. This allows the provider to provide problems more effectively by applying different provisioning algorithms depending on the category of the training data. Some or all of the above processing in the provider may be performed using AI, for example, or without using AI.

[0101] The service provider estimates the child's emotions and adjusts the order in which problems are presented based on the estimated emotions. For example, if the child is excited, the service provider prioritizes presenting problems that will pique the child's interest. The service provider can also use AI to estimate the child's emotions in real time and adjust the order in which problems are presented. For example, if the child is tired, the service provider prioritizes presenting easy problems. It can also prioritize presenting more detailed problems if the child is relaxed. Furthermore, the service provider can adjust the format and difficulty level of the problems based on the child's emotional data. For example, by prioritizing presenting problems that pique the child's interest when the child is excited and presenting easy problems when the child is tired, the service provider can provide problems more effectively. In this way, the service provider can provide problems more effectively by adjusting the order in which problems are presented based on the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI.

[0102] The provisioning unit prioritizes problems based on when the training data was submitted. For example, it provides problems based on recently submitted data. The provisioning unit can also use AI to evaluate the timing of training data submissions in real time and prioritize problems when providing them. For example, it can provide problems based on data with an approaching submission deadline. It can also provide problems based on data with a past submission date. Furthermore, the provisioning unit can adjust the format and difficulty of the problems based on when the training data was submitted. For example, by providing problems based on recently submitted data and problems based on data with an approaching submission deadline, the provisioning unit can provide problems more effectively. This allows the provisioning unit to provide problems more effectively by prioritizing problems based on when the training data was submitted. Some or all of the above processing in the provisioning unit may be performed using AI, for example, or without using AI.

[0103] The provider adjusts the order of questions based on the relevance of the training data when providing questions. For example, the provider provides questions based on highly relevant data. The provider can also use AI to evaluate the relevance of the training data in real time and adjust the order of questions when providing them. For example, the provider provides questions based on less relevant data. The provider can also provide more detailed questions for highly relevant data. Furthermore, the provider can adjust the format and difficulty of the questions based on the relevance of the training data. For example, by providing questions based on highly relevant data and questions based on less relevant data, the provider can provide questions more effectively. This allows the provider to provide questions more effectively by adjusting the order of questions based on the relevance of the training data. Some or all of the above processing in the provider may be performed using AI, for example, or without using AI.

[0104] The planning unit estimates the child's emotions and adjusts the learning plan planning method based on the estimated emotions. For example, if the child is relaxed, the planning unit provides a detailed learning plan. The planning unit can also use AI to estimate the child's emotions in real time and adjust the learning plan planning method. For example, if the child is in a hurry, the planning unit provides a concise learning plan. Furthermore, if the child is excited, the planning unit can provide a visually stimulating learning plan. In addition, the planning unit can adjust the content and schedule of the learning plan based on the child's emotional data. For example, by providing a detailed learning plan when the child is relaxed and a concise learning plan when the child is in a hurry, the planning unit can provide a more effective learning plan. This allows the planning unit to provide a more effective learning plan by adjusting the learning plan planning method based on the child's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-mentioned processes in the planning department may be performed using AI, for example, or without using AI.

[0105] The planning unit creates an optimal learning plan by referring to past learning data when planning a learning plan. For example, the planning unit creates an optimal learning plan based on past learning data. The planning unit can also use AI to refer to past learning data in real time and create an optimal plan when planning a learning plan. For example, the planning unit creates a plan that focuses on areas where the student is weak based on past learning data. The planning unit can also analyze past learning data and create an efficient learning plan. Furthermore, the planning unit can adjust the content and schedule of the learning plan based on past learning data. For example, the planning unit can provide a more effective learning plan by creating an optimal learning plan based on past learning data and creating a plan that focuses on areas where the student is weak. In this way, the planning unit can provide a more effective learning plan by creating an optimal plan by referring to past learning data. Some or all of the above processes in the planning unit may be performed using AI, for example, or without using AI.

[0106] The planning unit customizes the learning plan based on the child's current learning situation. For example, the planning unit creates an optimal learning plan based on the child's current learning situation. The planning unit can also use AI to evaluate the child's current learning situation in real time and customize the plan when creating the learning plan. For example, the planning unit can create a plan that focuses on areas where the child is struggling, based on the child's current learning situation. The planning unit can also analyze the child's current learning situation and create an efficient learning plan. Furthermore, the planning unit can adjust the content and schedule of the learning plan based on the child's current learning situation. For example, by creating an optimal learning plan based on the child's current learning situation and creating a plan that focuses on areas where the child is struggling, the planning unit can provide a more effective learning plan. In this way, the planning unit can provide a more effective learning plan by customizing the plan based on the child's current learning situation. Some or all of the above processes in the planning unit may be performed using AI, for example, or not using AI.

[0107] The planning unit estimates the child's emotions and prioritizes learning plans based on those estimates. For example, if the child is excited, the planning unit prioritizes engaging learning plans. The planning unit can also use AI to estimate the child's emotions in real time and prioritize learning plans. For example, if the child is tired, the planning unit prioritizes simple learning plans. It can also prioritize detailed learning plans if the child is relaxed. Furthermore, the planning unit can adjust the content and schedule of learning plans based on the child's emotional data. For example, by prioritizing engaging learning plans when the child is excited and simple learning plans when the child is tired, the planning unit can provide more effective learning plans. This allows the planning unit to provide more effective learning plans by prioritizing them based on the child's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-mentioned processes in the planning department may be performed using AI, for example, or without using AI.

[0108] The planning unit creates an optimal learning plan based on the child's geographical location. For example, if the child is at school, the planning unit creates a learning plan related to the school curriculum. The planning unit can also use AI to evaluate the child's geographical location in real time and create an optimal learning plan. For example, if the child is at home, the planning unit creates a learning plan related to home learning. Furthermore, if the child is at the library, the planning unit can create a learning plan related to library materials. In addition, the planning unit can adjust the content and schedule of the learning plan based on the child's geographical location. For example, by creating a learning plan related to the school curriculum when the child is at school and a learning plan related to home learning when the child is at home, the planning unit can provide a more effective learning plan. This allows the planning unit to provide a more effective learning plan by creating an optimal plan based on the child's geographical location. Some or all of the above processes in the planning unit may be performed using AI, for example, or without AI.

[0109] The planning department analyzes the child's social media activity and adjusts the plan when creating a learning plan. For example, the planning department adjusts the learning plan based on the learning content the child shares on social media. The planning department can also use AI to analyze the child's social media activity in real time and adjust the plan when creating a learning plan. For example, the planning department adjusts the learning plan based on information from educational accounts the child follows on social media. The planning department can also adjust the learning plan to topics the child has shown interest in on social media. Furthermore, the planning department can adjust the content and schedule of the learning plan based on the child's social media activity. For example, by adjusting the learning plan based on the learning content the child shares on social media and by adjusting the learning plan based on information from educational accounts the child follows on social media, the planning department can provide a more effective learning plan. In this way, the planning department can provide a more effective learning plan by analyzing the child's social media activity and adjusting the plan. Some or all of the above processes in the planning department may be performed using AI, for example, or not using AI.

[0110] The feedback unit estimates the child's emotions and adjusts the feedback method based on the estimated emotions. For example, if the child is relaxed, the feedback unit provides detailed feedback. The feedback unit can also use AI to estimate the child's emotions in real time and adjust the feedback method. For example, if the child is in a hurry, the feedback unit provides concise feedback. The feedback unit can also provide visually stimulating feedback if the child is excited. Furthermore, the feedback unit can adjust the content and format of the feedback based on the child's emotional data. For example, by providing detailed feedback when the child is relaxed and concise feedback when the child is in a hurry, the feedback unit can provide more effective feedback. This allows the feedback unit to provide more effective feedback by adjusting the feedback method based on the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI.

[0111] The feedback department, when providing feedback, analyzes the cause of the incorrect answer in detail and makes specific suggestions. For example, the feedback department identifies the cause of the incorrect answer and makes specific suggestions. The feedback department can also use AI to analyze the cause of the incorrect answer in real time and make specific suggestions when providing feedback. For example, the feedback department analyzes the cause of the incorrect answer and suggests areas for improvement. The feedback department can also explain the cause of the incorrect answer in detail and provide measures to prevent recurrence. Furthermore, the feedback department can adjust the content and format of the feedback based on the cause of the incorrect answer. For example, by identifying the cause of the incorrect answer, making specific suggestions, and suggesting areas for improvement, the feedback department can provide more effective feedback. This allows the feedback department to provide more effective feedback by analyzing the cause of the incorrect answer in detail and making specific suggestions. Some or all of the above processes in the feedback department may be performed using AI, for example, or without using AI.

[0112] The feedback unit applies a method of teaching the correct solution step by step during feedback. For example, the feedback unit teaches the correct solution step by step. The feedback unit can also apply a method of teaching the correct solution step by step in real time using AI. For example, the feedback unit explains the correct solution step by step. The feedback unit can also visually represent the correct solution. Furthermore, the feedback unit can adjust the content and format of the feedback based on the method of teaching the correct solution step by step. For example, by teaching the correct solution step by step, explaining it step by step, and visually representing it, the feedback unit can provide more effective feedback. Thus, by applying a method of teaching the correct solution step by step, the feedback unit can provide more effective feedback. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without using AI.

[0113] The feedback unit estimates the child's emotions and prioritizes feedback based on the estimated emotions. For example, if the child is excited, the feedback unit prioritizes engaging feedback. The feedback unit can also use AI to estimate the child's emotions in real time and prioritize feedback. For example, if the child is tired, the feedback unit prioritizes simple feedback. It can also prioritize detailed feedback if the child is relaxed. Furthermore, the feedback unit can adjust the content and format of feedback based on the child's emotional data. For example, by prioritizing engaging feedback when the child is excited and simple feedback when the child is tired, more effective feedback can be achieved. This allows the feedback unit to provide more effective feedback by prioritizing feedback based on the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI.

[0114] The feedback unit adjusts the level of detail in the feedback based on the frequency of incorrect answers. For example, if the frequency of incorrect answers is high, the feedback unit provides detailed feedback. The feedback unit can also use AI to evaluate the frequency of incorrect answers in real time and adjust the level of detail in the feedback. For example, if the frequency of incorrect answers is low, the feedback unit provides simplified feedback. The feedback unit can also adjust the content and format of the feedback according to the frequency of incorrect answers. Furthermore, the feedback unit can adjust the method and frequency of feedback based on the frequency of incorrect answers. For example, by providing detailed feedback when the frequency of incorrect answers is high and simplified feedback when the frequency is low, the feedback unit can provide more effective feedback. Thus, by adjusting the level of detail in the feedback unit based on the frequency of incorrect answers, the feedback unit can provide more effective feedback. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without using AI.

[0115] The feedback unit improves the accuracy of feedback by referring to relevant learning materials during the feedback process. For example, the feedback unit improves the accuracy of feedback by referring to relevant learning materials. The feedback unit can also use AI to refer to relevant learning materials in real time and improve the accuracy of feedback during the feedback process. For example, the feedback unit provides specific feedback based on relevant learning materials. Furthermore, the feedback unit can enrich the content of the feedback by utilizing relevant learning materials. In addition, the feedback unit can adjust the content and format of the feedback based on relevant learning materials. For example, by referring to relevant learning materials, the feedback unit can improve the accuracy of feedback, provide specific feedback, and enrich the content of the feedback, thereby enabling more effective feedback. Thus, by referring to relevant learning materials and improving the accuracy of feedback, the feedback unit can enable more effective feedback. Some or all of the above-described processes in the feedback unit may be performed using AI, for example, or without AI.

[0116] The tuning unit estimates the child's emotions and adjusts the problem tuning method based on the estimated emotions. For example, if the child is relaxed, the tuning unit provides a detailed problem. The tuning unit can also use AI to estimate the child's emotions in real time and adjust the problem tuning method. For example, if the child is in a hurry, the tuning unit provides a concise problem. The tuning unit can also provide a visually stimulating problem if the child is excited. Furthermore, the tuning unit can adjust the format and difficulty of the problems based on the child's emotion data. For example, by providing a detailed problem when the child is relaxed and a concise problem when the child is in a hurry, the tuning unit can provide more effective problems. In this way, the tuning unit can provide more effective problems by adjusting the problem tuning method based on the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the tuning unit may be performed using AI, for example, or without AI.

[0117] The tuning unit updates the content of the questions in response to changes in the child's interests during tuning. For example, if the child's interests change, the tuning unit updates the content of the questions. The tuning unit can also use AI to evaluate changes in the child's interests in real time and update the content of the questions during tuning. For example, the tuning unit changes the theme of the questions according to the child's interests. The tuning unit can also adjust the content of the questions to reflect changes in the child's interests. Furthermore, the tuning unit can adjust the format and difficulty level of the questions based on changes in the child's interests. For example, if the child's interests change, the tuning unit can provide more effective questions by updating the content of the questions and changing the theme of the questions. In this way, the tuning unit can provide more effective questions by updating the content of the questions in response to changes in the child's interests. Some or all of the above processing in the tuning unit may be performed using AI, for example, or without using AI.

[0118] The tuning unit estimates the child's emotions and adjusts the frequency of tuning problems based on the estimated emotions. For example, if the child is excited, the tuning unit tunes problems more frequently. The tuning unit can also use AI to estimate the child's emotions in real time and adjust the frequency of tuning problems. For example, if the child is tired, the tuning unit reduces the frequency of tuning. The tuning unit can also tune problems at a moderate frequency if the child is relaxed. Furthermore, the tuning unit can adjust the format and difficulty of problems based on the child's emotion data. For example, by tuning problems more frequently when the child is excited and reducing the frequency when the child is tired, the tuning unit can provide problems more effectively. Thus, by adjusting the frequency of tuning problems based on the child's emotions, the tuning unit can provide problems more effectively. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the tuning unit may be performed using AI, for example, or without AI.

[0119] The tuning unit adjusts the difficulty level of the problems based on the child's learning progress during tuning. For example, if the child's learning progress is fast, the tuning unit increases the difficulty level of the problems. The tuning unit can also use AI to evaluate the child's learning progress in real time and adjust the difficulty level of the problems during tuning. For example, if the child's learning progress is slow, the tuning unit decreases the difficulty level of the problems. The tuning unit can also adjust the format and frequency of the problems according to the child's learning progress. Furthermore, the tuning unit can adjust the content and format of the problems based on the child's learning progress. For example, by increasing the difficulty level of the problems when the child's learning progress is fast and decreasing it when the child's learning progress is slow, the tuning unit can provide more effective problems. In this way, the tuning unit can provide more effective problems by adjusting the difficulty level of the problems based on the child's learning progress. Some or all of the above processing in the tuning unit may be performed using AI, for example, or without using AI.

[0120] The adjustment unit estimates the child's emotions and changes the method of adjusting the difficulty of the problems based on the estimated emotions. For example, if the child is relaxed, the adjustment unit will provide more difficult problems. The adjustment unit can also use AI to estimate the child's emotions in real time and change the method of adjusting the difficulty of the problems. For example, if the child is in a hurry, the adjustment unit will provide easier problems. The adjustment unit can also provide visually stimulating problems if the child is excited. Furthermore, the adjustment unit can adjust the format and frequency of the problems based on the child's emotion data. For example, by providing more difficult problems when the child is relaxed and easier problems when the child is in a hurry, the adjustment unit can provide more effective problems. In this way, the adjustment unit can provide more effective problems by changing the method of adjusting the difficulty of the problems based on the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the adjustment unit may be performed using AI, for example, or without using AI.

[0121] The adjustment unit gradually increases the difficulty level of the problems according to the child's learning progress during the adjustment process. For example, if the child's learning progress is fast, the adjustment unit gradually increases the difficulty level of the problems. The adjustment unit can also use AI to evaluate the child's learning progress in real time and gradually increase the difficulty level of the problems during the adjustment process. For example, if the child's learning progress is slow, the adjustment unit gradually decreases the difficulty level of the problems. The adjustment unit can also adjust the format and frequency of the problems according to the child's learning progress. Furthermore, the adjustment unit can adjust the content and format of the problems based on the child's learning progress. For example, by gradually increasing the difficulty level of the problems when the child's learning progress is fast and gradually decreasing it when the child's learning progress is slow, the adjustment unit can provide more effective problems. In this way, the adjustment unit can provide more effective problems by gradually increasing the difficulty level of the problems according to the child's learning progress. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without using AI.

[0122] The adjustment unit estimates the child's emotions and changes the frequency of difficulty adjustments based on the estimated emotions. For example, if the child is excited, the adjustment unit adjusts the difficulty of the problems more frequently. The adjustment unit can also use AI to estimate the child's emotions in real time and change the frequency of difficulty adjustments. For example, if the child is tired, the adjustment unit reduces the frequency of difficulty adjustments. It can also adjust the difficulty of the problems at an appropriate frequency if the child is relaxed. Furthermore, the adjustment unit can adjust the format and frequency of questions based on the child's emotion data. For example, by frequently adjusting the difficulty of questions when the child is excited and reducing the frequency when the child is tired, the adjustment unit can provide more effective questions. In this way, the adjustment unit can provide more effective questions by changing the frequency of difficulty adjustments based on the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the adjustment unit may be performed using AI, for example, or without using AI.

[0123] The adjustment unit customizes the difficulty level of problems based on the child's learning history during the adjustment process. For example, the adjustment unit provides problems of the optimal difficulty level based on the learning history. The adjustment unit can also use AI to evaluate the child's learning history in real time and customize the difficulty level of problems during the adjustment process. For example, the adjustment unit can focus on providing problems in areas where the child struggles, based on the learning history. The adjustment unit can also analyze the learning history and perform efficient difficulty level adjustments. Furthermore, the adjustment unit can adjust the content and format of the problems based on the child's learning history. For example, by providing problems of the optimal difficulty level based on the learning history and focusing on problems in areas where the child struggles, the adjustment unit can provide more effective problems. Thus, by customizing the difficulty level of problems based on the child's learning history, the adjustment unit can provide more effective problems. Some or all of the above processes in the adjustment unit may be performed using AI, for example, or without using AI.

[0124] The notification unit estimates the child's emotions and adjusts the timing of notifications based on the estimated emotions. For example, if the child is relaxed, the notification unit provides a detailed notification. The notification unit can also use AI to estimate the child's emotions in real time and adjust the timing of notifications. For example, if the child is in a hurry, the notification unit provides a concise notification. The notification unit can also provide a visually stimulating notification if the child is excited. Furthermore, the notification unit can adjust the content and format of notifications based on the child's emotion data. For example, by providing a detailed notification when the child is relaxed and a concise notification when the child is in a hurry, more effective notifications can be made. This allows the notification unit to provide more effective notifications by adjusting the timing of notifications based on the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI.

[0125] The notification unit selects the optimal notification method by referring to the parent's past response history when sending a notification. For example, the notification unit selects the optimal notification method based on the parent's past response history. The notification unit can also use AI to refer to the parent's past response history in real time and select the optimal notification method when sending a notification. For example, the notification unit selects an effective notification method from the parent's response history. The notification unit can also analyze the parent's past responses and provide the optimal notification method. Furthermore, the notification unit can adjust the content and format of the notification based on the parent's past response history. For example, by selecting the optimal notification method based on the parent's past response history and selecting an effective notification method from the parent's response history, the notification unit can send more effective notifications. Thus, by referring to the parent's past response history and selecting the optimal notification method, the notification unit can send more effective notifications. Some or all of the above processing in the notification unit may be performed using AI, for example, or without using AI.

[0126] The notification unit estimates the child's emotions and determines notification priorities based on the estimated emotions. For example, if the child is excited, the notification unit prioritizes important notifications. The notification unit can also use AI to estimate the child's emotions in real time and determine notification priorities. For example, if the child is tired, the notification unit prioritizes simple notifications. It can also prioritize detailed notifications if the child is relaxed. Furthermore, the notification unit can adjust the content and format of notifications based on the child's emotion data. For example, by prioritizing important notifications when the child is excited and simple notifications when the child is tired, more effective notifications can be made. This allows the notification unit to make more effective notifications by determining notification priorities based on the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI.

[0127] The notification unit selects the optimal notification method when sending a notification, taking into account the parent's device information. For example, if the parent is using a smartphone, the notification unit will send a push notification. The notification unit can also use AI to evaluate the parent's device information in real time and select the optimal notification method when sending a notification. For example, if the parent is using a tablet, the notification unit will send a notification optimized for a larger screen. Furthermore, if the parent is using a smartwatch, the notification unit can send a concise and highly visible notification. In addition, the notification unit can adjust the content and format of the notification based on the parent's device information. For example, by sending a push notification when the parent is using a smartphone and a notification optimized for a larger screen when the parent is using a tablet, the notification unit can provide more effective notifications. This allows the notification unit to provide more effective notifications by selecting the optimal notification method considering the parent's device information. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI.

[0128] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0129] The analysis unit can adjust its analysis method to take into account the child's learning style when analyzing the child's learning data. For example, it can provide analysis results using graphs and diagrams for children with a visual learning style. It can also provide audio feedback for children with an auditory learning style. Furthermore, it can provide interactive analysis results for children with a tactile learning style. In this way, the analysis unit can provide analysis methods tailored to the child's learning style, enabling more effective learning support.

[0130] The service provider can offer rewards based on the child's learning data, according to their learning progress. For example, they can award digital badges or points when certain learning goals are achieved. They can also provide in-game items or rewards for completing specific tasks. Furthermore, they can provide words of praise and encouragement from parents based on the child's learning progress. In this way, the service provider can maintain the child's motivation to learn by offering rewards that enhance their desire to learn.

[0131] The planning department can adjust the schedule when creating a learning plan, taking into account the child's daily rhythm. For example, if a child has a morning routine, the schedule can be set to allow for focused learning during the morning hours. Similarly, for children with a night owl routine, the schedule can be adjusted to allow for learning during the evening hours. Furthermore, the learning plan can be flexibly adjusted to take into account weekend and holiday schedules. In this way, the planning department can maximize the effectiveness of learning by providing a learning plan that is tailored to the child's daily rhythm.

[0132] The data collection unit can adjust its data collection method to take into account the child's learning environment when collecting children's learning data. For example, if the child is learning in a quiet environment, it can collect detailed data. Conversely, if the child is learning in a noisy environment, it can collect only the most important data. Furthermore, it can adjust the frequency and method of data collection in response to changes in the learning environment. As a result, the data collection unit can obtain more accurate learning data by collecting data according to the child's learning environment.

[0133] The feedback system can adjust the content of feedback based on the child's learning data and their progress. For example, if a child is progressing quickly, it can provide advice on how to move on to the next step. If a child is progressing slowly, it can provide supplementary explanations to deepen their understanding. Furthermore, it can adjust the frequency and format of feedback according to the child's progress. In this way, the feedback system can enhance the effectiveness of learning by providing feedback tailored to the child's learning progress.

[0134] The data collection unit can estimate a child's emotions and adjust the data collection method based on the estimated emotions. For example, if the child is relaxed, it can collect detailed data. If the child is stressed, it can temporarily suspend data collection. Furthermore, it can adjust the frequency and method of data collection in response to changes in the child's emotions. This allows the data collection unit to obtain more accurate learning data by collecting data based on the child's emotions.

[0135] The analysis unit can estimate a child's emotions and adjust how the analysis results are provided based on the estimated emotions. For example, if the child is relaxed, it can provide detailed analysis results. If the child is in a hurry, it can provide concise analysis results. Furthermore, it can adjust the frequency and format of the analysis results according to changes in the child's emotions. In this way, the analysis unit can enhance the effectiveness of learning by providing analysis results based on the child's emotions.

[0136] The system can estimate a child's emotions and adjust how problems are presented based on that estimation. For example, if a child is relaxed, it can provide problems with detailed explanations. If a child is in a hurry, it can provide concise problems. Furthermore, it can adjust the frequency and format of problem presentation according to changes in the child's emotions. This allows the system to enhance learning effectiveness by providing problems based on the child's emotions.

[0137] The planning department can estimate a child's emotions and adjust the content of the learning plan based on those estimates. For example, if a child is relaxed, it can provide a detailed learning plan. If a child is in a hurry, it can provide a concise learning plan. Furthermore, it can adjust the content and schedule of the learning plan in response to changes in the child's emotions. In this way, the planning department can enhance the effectiveness of learning by providing learning plans based on the child's emotions.

[0138] The feedback unit can estimate the child's emotions and adjust the content of the feedback based on those estimates. For example, if the child is relaxed, it can provide detailed feedback. If the child is in a hurry, it can provide concise feedback. Furthermore, it can adjust the frequency and format of the feedback according to changes in the child's emotions. In this way, the feedback unit can enhance the effectiveness of learning by providing feedback based on the child's emotions.

[0139] The following briefly describes the processing flow for example form 2.

[0140] Step 1: The data collection unit collects children's learning data. For example, it collects data such as the accuracy rate and time taken to solve problems. The data collection unit can also use AI to collect children's learning data in real time. Step 2: The analysis unit analyzes the data collected by the data collection unit and evaluates the child's level of understanding. For example, if the child's understanding is low in a particular area, the analysis unit adjusts the questions to include more related problems. The analysis unit can also use AI to evaluate the child's level of understanding in real time. Step 3: The provisioning unit provides problems based on the evaluation results obtained by the analysis unit. For example, it can tune problems based on children's interests. The provisioning unit can also use AI to tune problems in real time based on children's interests. Step 4: The Planning Department plans and executes a learning plan based on the problems provided by the Delivery Department. For example, it creates a daily learning schedule based on the child's level of understanding and interests, and presents problems at appropriate times. The Planning Department can also use AI to plan and execute the learning plan in real time. Step 5: The Feedback Department provides feedback on incorrect answers based on the learning plan developed by the Planning Department. For example, it will specifically point out which part of a question a child answered incorrectly and teach them the correct way to answer it. The Feedback Department can also use AI to provide real-time feedback on incorrect answers.

[0141] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0142] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0143] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0144] Each of the multiple elements described above, including the collection unit, analysis unit, provision unit, planning unit, and feedback unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit collects the child's learning data using the camera 42 and microphone 38B of the smart device 14 and transmits it to the data processing unit 12 via the control unit 46A. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which analyzes the collected data and evaluates the child's level of understanding. The provision unit is implemented, for example, by the control unit 46A of the smart device 14, which provides problems based on the analysis results. The planning unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which plans and executes a learning plan. The feedback unit is implemented, for example, by the control unit 46A of the smart device 14, which provides feedback for incorrect answers. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0145] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0146] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0147] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0148] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0149] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0150] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0151] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0152] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0153] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0154] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0155] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0156] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0157] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0158] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0159] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0160] Each of the multiple elements described above, including the collection unit, analysis unit, provision unit, planning unit, and feedback unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit collects the child's learning data using the camera 42 and microphone 238 of the smart glasses 214 and transmits it to the data processing unit 12 via the control unit 46A. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which analyzes the collected data and evaluates the child's level of understanding. The provision unit is implemented, for example, by the control unit 46A of the smart glasses 214, which provides problems based on the analysis results. The planning unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which plans and executes a learning plan. The feedback unit is implemented, for example, by the control unit 46A of the smart glasses 214, which provides feedback for incorrect answers. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0161] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0162] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0163] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0164] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0165] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0166] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0167] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0168] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0169] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0170] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0171] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0172] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0173] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0174] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0175] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0176] Each of the multiple elements described above, including the collection unit, analysis unit, provision unit, planning unit, and feedback unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit collects the child's learning data using the camera 42 and microphone 238 of the headset terminal 314 and transmits it to the data processing unit 12 via the control unit 46A. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which analyzes the collected data and evaluates the child's level of understanding. The provision unit is implemented, for example, by the control unit 46A of the headset terminal 314, which provides problems based on the analysis results. The planning unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which plans and executes the learning plan. The feedback unit is implemented, for example, by the control unit 46A of the headset terminal 314, which provides feedback for incorrect answers. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0177] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0178] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0179] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0180] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0181] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0182] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0183] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0184] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0185] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0186] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0187] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0188] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0189] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0190] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0191] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0192] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0193] Each of the multiple elements described above, including the collection unit, analysis unit, provision unit, planning unit, and feedback unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the collection unit collects the child's learning data using the camera 42 and microphone 238 of the robot 414 and transmits it to the data processing unit 12 via the control unit 46A. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which analyzes the collected data and evaluates the child's level of understanding. The provision unit is implemented, for example, by the control unit 46A of the robot 414, which provides problems based on the analysis results. The planning unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which plans and executes the learning plan. The feedback unit is implemented, for example, by the control unit 46A of the robot 414, which provides feedback for incorrect answers. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0194] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0195] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0196] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0197] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0198] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0199] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0200] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0201] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0202] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0203] 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.

[0204] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0205] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0206] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0207] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0208] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0209] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0210] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0211] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0212] (Note 1) A data collection unit that collects children's learning data, An analysis unit analyzes the data collected by the aforementioned collection unit and evaluates the child's level of understanding, A provisioning unit that provides problems based on the evaluation results obtained by the analysis unit, A planning unit plans and executes a learning plan based on the problems provided by the aforementioned provisioning unit, The system includes a feedback unit that provides feedback on incorrect answers based on the learning plan planned by the planning unit. A system characterized by the following features. (Note 2) The aforementioned supply unit is, It features a tuning unit that adjusts problems based on children's interests and concerns. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned planning department, It features an adjustment unit that adjusts the difficulty level of the problems according to the learning progress. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned collection unit is It includes a notification unit that informs parents about their child's learning progress. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned feedback unit is Provide specific feedback on incorrect answers and explain how to answer them correctly. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit, Analyze data including the children's response times. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is The system estimates the child's emotions and adjusts the timing of data collection based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is Analyze the child's past learning history and select the optimal data collection method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is When collecting learning data, filtering is performed based on the child's current learning environment and level of concentration. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is The system estimates the child's emotions and prioritizes the data to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is When collecting learning data, prioritize the collection of highly relevant data based on the child's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is When collecting learning data, analyze children's social media activity and collect relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, We estimate the child's emotions and adjust the analysis method based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, During analysis, adjust the level of detail based on the importance of the training data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the category of the training data. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, The system estimates the child's emotions and determines the priority of analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During analysis, the priority of the analysis is determined based on when the training data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, During analysis, the order of analysis is adjusted based on the relevance of the training data. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned supply unit is, The system estimates the child's emotions and adjusts the way problems are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned supply unit is, When providing questions, adjust the level of detail of the questions based on the importance of the training data. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned supply unit is, When providing the problem, different provision algorithms are applied depending on the category of the training data. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned supply unit is, The system estimates the child's emotions and adjusts the order in which problems are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned supply unit is, When providing problems, we prioritize them based on when the training data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned supply unit is, When providing questions, adjust the order of the questions based on the relevance of the training data. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned planning department, We estimate the child's emotions and adjust the learning plan based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned planning department, When planning a learning plan, refer to past learning data to create the optimal plan. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned planning department, When planning a learning plan, customize the plan based on the child's current learning situation. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned planning department, The system estimates the child's emotions and prioritizes the learning plan based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned planning department, When planning a learning plan, create an optimal plan based on the child's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned planning department, When planning a learning plan, analyze your child's social media activity and adjust the plan accordingly. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned feedback unit is Estimate the child's emotions and adjust the feedback method based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned feedback unit is During the feedback process, we will conduct a detailed analysis of the causes of incorrect answers and provide specific feedback. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned feedback unit is During feedback, we apply a method that teaches the correct solution step by step. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned feedback unit is The system estimates the child's emotions and prioritizes feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned feedback unit is When providing feedback, adjust the level of detail based on the frequency of incorrect responses. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned feedback unit is When giving feedback, refer to relevant learning materials to improve the accuracy of the feedback. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned tuning unit is The system estimates the child's emotions and adjusts the problem-solving method based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 38) The aforementioned tuning unit is During tuning, the content of the problems is updated according to changes in the child's interests. The system described in Appendix 2, characterized by the features described herein. (Note 39) The aforementioned tuning unit is The system estimates the child's emotions and adjusts the frequency of tuning the problem based on the estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 40) The aforementioned tuning unit is During tuning, the difficulty level of the problems is adjusted based on the child's learning progress. The system described in Appendix 2, characterized by the features described herein. (Note 41) The adjustment unit is, The system estimates the child's emotions and adjusts the difficulty level of the problems based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 42) The adjustment unit is, During adjustments, the difficulty level of the problems is gradually increased according to the child's learning progress. The system described in Appendix 3, characterized by the features described herein. (Note 43) The adjustment unit is, The system estimates the child's emotions and adjusts the frequency of problem difficulty based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 44) The adjustment unit is, During adjustment, the difficulty level of the problems is customized based on the child's learning history. The system described in Appendix 3, characterized by the features described herein. (Note 45) The aforementioned notification unit, It estimates the child's emotions and adjusts the timing of notifications based on the estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 46) The aforementioned notification unit, When sending a notification, the system will refer to the parent's past response history to select the most suitable notification method. The system described in Appendix 4, characterized by the features described herein. (Note 47) The aforementioned notification unit, The system estimates the child's emotions and prioritizes notifications based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 48) The aforementioned notification unit, When sending a notification, the system will select the most suitable notification method by considering the parent's device information. The system described in Appendix 4, characterized by the features described herein. [Explanation of symbols]

[0213] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A data collection unit that collects children's learning data, An analysis unit analyzes the data collected by the aforementioned collection unit and evaluates the child's level of understanding, A provisioning unit that provides problems based on the evaluation results obtained by the analysis unit, A planning unit plans and executes a learning plan based on the problems provided by the aforementioned provisioning unit, The system includes a feedback unit that provides feedback on incorrect answers based on the learning plan planned by the planning unit. A system characterized by the following features.

2. The aforementioned supply unit is, It features a tuning unit that adjusts problems based on children's interests and concerns. The system according to feature 1.

3. The aforementioned planning department, It features an adjustment unit that adjusts the difficulty level of the problems according to the learning progress. The system according to feature 1.

4. The aforementioned collection unit is It includes a notification unit that informs parents about their child's learning progress. The system according to feature 1.

5. The aforementioned feedback unit is Provide specific feedback on incorrect answers and explain how to answer them correctly. The system according to feature 1.

6. The aforementioned analysis unit, Analyze data including the children's response times. The system according to feature 1.

7. The aforementioned collection unit is The system estimates the child's emotions and adjusts the timing of data collection based on the estimated emotions. The system according to feature 1.

8. The aforementioned collection unit is Analyze the child's past learning history and select the optimal data collection method. The system according to feature 1.

9. The aforementioned collection unit is When collecting learning data, filtering is performed based on the child's current learning environment and level of concentration. The system according to feature 1.

10. The aforementioned collection unit is The system estimates the child's emotions and prioritizes the data to collect based on those estimated emotions. The system according to feature 1.

Images