system

Abstract

The system according to the embodiment aims to effectively support children's learning even when parents are busy. [Solution] A system according to an embodiment includes a reception unit, a generation unit, a provision unit, and a monitoring unit. The reception unit allows a parent to input their child's learning content. The generation unit creates a learning plan based on the information received by the reception unit. The provision unit provides learning content based on the learning plan created by the generation unit. The monitoring unit monitors the child's learning progress.

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem that it is difficult for parents to effectively support their children's learning when they are busy.

[0005] The system according to the embodiment aims to effectively support children's learning even when parents are busy. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a generation unit, a provision unit, and a monitoring unit. The reception unit allows a parent to input the learning content of their child. The generation unit creates a learning plan based on the information received by the reception unit. The provision unit provides the learning content based on the learning plan created by the generation unit. The monitoring unit monitors the child's learning progress. [Effects of the Invention]

[0007] The system according to the embodiment can effectively support children's learning even when parents are busy. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A tutoring system according to an embodiment of the present invention uses a generating AI as a tutor to teach a child about various topics and studies on behalf of a mother who is busy with housework. This tutoring system begins when a mother inputs her child's learning content and topics of interest into the generating AI. The generating AI then creates a learning plan tailored to the child based on that information. The generating AI then monitors the child's learning progress in real time and adjusts the learning content as needed. The generating AI also provides instant answers to the child's questions and provides additional information to deepen understanding. This system allows a mother to support her child's learning while focusing on housework. For example, a mother inputs her child's learning content and topics of interest into the generating AI. For example, if the child is struggling with math problems, the mother inputs that information into the generating AI. The generating AI analyzes this information and creates a learning plan tailored to the child. Next, the generating AI provides the child with learning content based on the learning plan. For example, the generating AI explains basic mathematical concepts to the child and has them solve specific problems. The generating AI then monitors the child's level of understanding in real time and adjusts the learning content as needed. Furthermore, the generative AI instantly answers any questions a child has. For example, if a child asks a question about a math problem, the generative AI provides an appropriate answer to that question. The generative AI can also provide additional information and examples to deepen the child's understanding. This system allows mothers to support their children's learning while focusing on housework. For example, while a mother is cooking, the generative AI can provide learning content for the child and answer questions, allowing the mother to do her housework with peace of mind. In this way, the tutoring system can support her children's learning while allowing the mother to focus on housework.

[0029] The tutoring system according to the embodiment includes a reception unit, a generation unit, a provision unit, and a monitoring unit. The reception unit receives input of learning content from a parent or guardian. The learning content input by the parent or guardian includes, but is not limited to, subjects, topics, and skills. For example, the reception unit receives input of the learning content from a parent or guardian in text format. The reception unit can also input the learning content using voice input. For example, the parent or guardian may explain the learning content through voice and convert it into text data. The reception unit can also provide an optimal input interface based on past input history. For example, the reception unit can automatically display learning content frequently input by the parent or guardian as candidates. The generation unit uses a generation AI to create a learning plan based on the information received by the reception unit. The generation AI creates the learning plan using, for example, a text generation AI (e.g., LLM). The generation unit can also use the generation AI to customize the learning plan to suit the child's learning style and pace. For example, the generation AI generates an optimal learning plan depending on the child's learning style, such as visual, auditory, or experiential. The provision unit provides the learning content based on the learning plan created by the generation unit. The provision unit provides learning content through, for example, online classes or face-to-face classes. The provision unit can also adjust the level of detail provided based on the child's level of understanding. For example, if the child has a high level of understanding, the provision unit can provide learning content with concise explanations. The monitoring unit monitors the child's learning progress. The monitoring unit monitors the learning progress through, for example, regular checks or real-time monitoring. The monitoring unit can also record the child's learning progress and report it to the parent. For example, the monitoring unit digitally records the learning progress and reports it to the parent via email notification or dashboard display. As a result, the tutoring system according to the embodiment can support the child's learning while the mother is able to focus on housework.

[0030] The generation unit can create a study plan using a generation AI. The generation unit creates the study plan using, for example, a generation AI. The generation AI creates the study plan using, for example, a text generation AI (e.g., LLM). The generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The generation AI generates an optimal study plan based on, for example, a child's learning content and topics of interest. For example, if a child is struggling to solve a math problem, the generation AI uses that information to create a study plan that explains basic math concepts and has the child solve specific problems. The generation AI can also customize the study plan to suit the child's learning style and pace. For example, a visual child can be provided with a study plan that includes many visual elements, while an auditory child can be provided with a study plan that includes many audio and music elements. In this way, the generation AI can efficiently create study plans. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, when creating a learning plan using the generation AI, the generation unit provides the child's learning content and topics of interest as input to the generation AI, and the generation AI generates a learning plan based on that.

[0031] The generation unit can customize the learning plan to suit a child's learning style and pace using a generation AI. The generation unit, for example, uses a generation AI to customize the learning plan to suit a child's learning style and pace. The generation AI generates an optimal learning plan depending on the child's learning style, such as visual, auditory, or experiential. For example, the generation AI provides a learning plan that includes many visual elements to a visual child. For example, the generation AI explains mathematical concepts using diagrams and graphs. The generation AI also provides a learning plan that includes many audio and music to an auditory child. For example, the generation AI explains mathematical problems using audio and uses music to promote learning rhythmically. Furthermore, the generation AI provides a learning plan that includes many practical activities to an experiential child. For example, the generation AI suggests activities such as solving mathematical problems using actual objects. This makes it possible to provide a learning plan that suits a child's individual learning style and pace. Some or all of the above-described processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, when customizing a learning plan using the generation AI, the generation unit provides information about the child's learning style and pace as input to the generation AI, and the generation AI customizes the learning plan based on that information.

[0032] The monitoring unit can record the child's learning progress and report it to the guardian. The monitoring unit, for example, digitally records the child's learning progress. Digital records include, but are not limited to, study time, test results, and assignment submission status. The monitoring unit, for example, periodically checks the learning progress and monitors it in real time. The monitoring unit also reports the child's learning progress to the guardian. Reporting methods include, for example, email notification, dashboard display, and paper report. For example, the monitoring unit digitally records the learning progress and sends an email notification to the guardian. The monitoring unit can also display the learning progress on a dashboard so that the guardian can check it at any time. Furthermore, the monitoring unit can print out the learning progress using a printer and provide it to guardians who wish to receive paper reports. This makes it easier for mothers to understand their child's learning progress. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, a generation AI. For example, the monitoring unit inputs the child's learning progress into the generation AI, which then records the learning progress based on the input and reports it to the guardian.

[0033] The tutoring system further includes an identification unit that uses a generation AI to analyze a child's learning data, identify weak points, and provide focused instruction. The identification unit uses the generation AI to analyze the child's learning data and identify weak points. The generation AI identifies weak points, for example, based on low-scoring test results or questions frequently missed. The generation AI analyzes the child's past test results and identifies questions on which the child receives low scores. The generation AI can also identify weak points based on questions frequently missed by the child. For example, the generation AI extracts questions on which the child repeatedly receives mistakes and provides focused instruction on those questions. The generation AI can also comprehensively analyze the child's learning data and identify weak points. For example, the generation AI identifies weak points based on the child's study time and assignment submission status. This identifies the child's weak points and enables effective instruction. Some or all of the above-described processing in the identification unit may be performed using, or without, the generation AI. For example, when the identification unit analyzes the child's learning data and identifies weak points using the generation AI, the identification unit provides the child's learning data as input to the generation AI, which then identifies the weak points based on that data.

[0034] The tutoring system further includes a reliability assurance unit that ensures the reliability of the information provided by the generation AI. The reliability assurance unit includes a mechanism for ensuring the reliability of the information provided by the generation AI. For example, the reliability assurance unit verifies the source of the information provided by the generation AI. For example, the reliability assurance unit verifies the source of the data used by the generation AI and uses only highly reliable data. The reliability assurance unit may also include a scoring system for evaluating the reliability of the information provided by the generation AI. For example, the reliability assurance unit calculates a reliability score for the information provided by the generation AI and prioritizes providing highly reliable information. The reliability assurance unit may also include a mechanism for continuously monitoring the reliability of the information provided by the generation AI and improving it as necessary. For example, the reliability assurance unit periodically checks the reliability of the information provided by the generation AI and eliminates unreliable information. This improves the reliability of the provided information. Some or all of the above-described processing in the reliability assurance unit may be performed using, or without, the generation AI. For example, when evaluating the reliability of the information provided by the generation AI, the reliability assurance unit provides data regarding the source and reliability of the information as input to the generation AI, and the generation AI calculates the reliability score based on that data.

[0035] The reception unit can analyze the parent's past input history and provide an optimal input interface. The reception unit uses a generation AI to analyze the parent's past input history and provide an optimal input interface. The generation AI, for example, analyzes the parent's input patterns based on past input data. For example, the reception unit automatically displays learning content that the parent has frequently input in the past as candidates. The generation AI can also prioritize suggesting input methods (voice, text, etc.) that the parent has used in the past. For example, if the parent has frequently used voice input in the past, the reception unit prioritizes voice input. Furthermore, the generation AI can predict and suggest learning content to be used during a specific time period based on the parent's past input history. For example, if the parent tends to input specific learning content during a specific time period, the reception unit suggests the learning content that is optimal for that time period. This makes it possible to provide an optimal input interface based on the parent's past input history. Some or all of the above-described processing in the reception unit may be performed using, or without, the generation AI. For example, the reception unit may analyze the parent's past input history using the generation AI and provide an optimal input interface based on the results.

[0036] When inputting learning content, the reception unit can filter the learning content based on the guardian's current living situation and areas of interest. The reception unit uses a generation AI to filter the learning content based on the guardian's current living situation and areas of interest. The generation AI analyzes the guardian's living situation based on, for example, a questionnaire survey or a behavior log. For example, if the guardian is busy, the reception unit prioritizes suggesting learning content that is quick and effective. The generation AI can also analyze the guardian's past search history and social media activity to identify the guardian's areas of interest. For example, if the guardian is interested in a particular field, the reception unit prioritizes displaying learning content related to that field. Furthermore, the generation AI can filter and suggest appropriate learning content based on the guardian's living situation. For example, if the guardian is in a particular living situation, the reception unit suggests learning content appropriate for that situation. This makes it possible to provide learning content tailored to the guardian's living situation and areas of interest. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the reception unit analyzes the guardian's living situation and areas of interest using a generation AI, and filters the learning content based on the results.

[0037] When inputting learning content, the reception unit can prioritize inputting highly relevant content by taking into account the guardian's geographical location information. The reception unit uses a generation AI to input learning content by taking into account the guardian's geographical location information. The generation AI analyzes the guardian's geographical location information based on, for example, GPS data or location information services. For example, if the guardian lives in a specific area, the reception unit prioritizes inputting learning content related to that area. Furthermore, if the guardian is traveling, the generation AI can prioritize inputting learning content related to the travel destination. For example, when the guardian inputs learning content while traveling, the reception unit provides information related to the travel destination. Furthermore, if the guardian is in a specific location, the generation AI can prioritize inputting learning content related to that location. For example, if the guardian is attending a specific facility or event, the reception unit provides learning content related to that location or event. This makes it possible to provide optimal learning content based on the guardian's geographical location information. Some or all of the above-described processing in the reception unit may be performed using, or without, the generation AI. For example, the reception unit analyzes the guardian's geographical location information using the generation AI and inputs learning content based on the results.

[0038] When inputting learning content, the reception unit can analyze the parent's social media activity and input related content. The reception unit analyzes the parent's social media activity using a generation AI and inputs related learning content. The generation AI, for example, identifies the parent's areas of interest based on an analysis of social media posts and followers. For example, the reception unit inputs learning content related to topics the parent is interested in on social media. The generation AI can also input learning content related to accounts the parent follows on social media. For example, the reception unit suggests learning content based on education-related accounts the parent follows. Furthermore, the generation AI can input learning content based on information shared by the parent on social media. For example, the reception unit provides learning content related to articles and videos shared by the parent. This makes it possible to provide optimal learning content based on the parent's social media activity. Some or all of the above-described processing in the reception unit may be performed using, or without, the generation AI. For example, the reception unit analyzes the parent's social media activity using a generation AI and inputs learning content based on the results.

[0039] When generating a study plan, the generation unit can adjust the level of detail of the plan based on the child's study history. When generating a study plan using the generation AI, the generation unit adjusts the level of detail of the plan based on the child's study history. The generation AI analyzes the study history based on, for example, past test results and study time records. For example, the generation unit generates a detailed study plan based on the content the child has learned in the past. The generation AI can also generate a study plan that prioritizes content with a high level of understanding from the child's study history. For example, the generation unit creates a study plan based on subjects and topics in which the child has previously scored highly. Furthermore, the generation AI can comprehensively analyze the child's study history to generate an optimal study plan. For example, the generation unit adjusts the level of detail of the study plan based on the child's study time and assignment submission status. This makes it possible to provide an optimal study plan based on the child's study history. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, when generating a study plan using the generation AI, the generation unit provides the child's study history as input to the generation AI, and the generation AI adjusts the level of detail of the study plan based on that.

[0040] The generation unit can apply different generation algorithms depending on the child's learning style when generating a lesson plan. The generation unit applies different generation algorithms depending on the child's learning style when generating a lesson plan using the generation AI. The generation AI uses different generation algorithms depending on the child's learning style, such as visual, auditory, or experiential. For example, the generation unit applies a generation algorithm that includes many visual elements to a visual child. For example, the generation AI explains the learning content using diagrams and graphs. The generation AI also applies a generation algorithm that includes many audio and music to an auditory child. For example, the generation AI explains the learning content using audio and uses music to advance the learning rhythmically. Furthermore, the generation AI applies a generation algorithm that includes many practical activities to an experiential child. For example, the generation AI suggests activities that allow the child to understand the learning content using actual objects. This makes it possible to provide an optimal lesson plan depending on the child's learning style. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, when generating a learning plan using the generation AI, the generation unit provides information about the child's learning style as input to the generation AI, and the generation AI applies different generation algorithms based on that information.

[0041] When generating a study plan, the generation unit can determine the priority of the plan based on the submission date of the study content. When generating a study plan using the generation AI, the generation unit determines the priority of the plan based on the submission date of the study content. The generation AI analyzes the priority of the study content based on, for example, the submission deadline or the frequency of submission. For example, the generation unit generates a study plan that prioritizes study content with an upcoming submission deadline. The generation AI can also generate a study plan that postpones study content with a distant submission deadline. For example, the generation unit generates a study plan that adjusts the priority of study content based on the submission deadline. Furthermore, the generation AI can generate an optimal study plan based on the submission date of the study content. For example, the generation unit generates a study plan that prioritizes study content with an upcoming submission deadline and postpones study content with a distant submission deadline. This makes it possible to provide an optimal study plan based on the submission date of the study content. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, when generating a learning plan using the generation AI, the generation unit provides information regarding the timing of submission of the learning content as input to the generation AI, and the generation AI determines the priority of the plan based on that information.

[0042] The generation unit can adjust the order of the plan based on the relevance of the learning content when generating the learning plan. The generation unit adjusts the order of the plan based on the relevance of the learning content when generating the learning plan using the generation AI. The generation AI analyzes the relevance of the learning content based on, for example, topic similarity or the need for prior knowledge. For example, the generation unit generates a learning plan that includes highly relevant learning content in succession. The generation AI can also generate a learning plan that includes less relevant learning content in a dispersed manner. For example, the generation unit generates a learning plan in an optimal order based on the relevance of the learning content. Furthermore, the generation AI can adjust the order of the learning plan based on the relevance of the learning content. For example, the generation unit generates a learning plan that includes highly relevant learning content in succession and includes less relevant learning content in a dispersed manner. This makes it possible to provide an optimal learning plan based on the relevance of the learning content. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, when generating a learning plan using the generation AI, the generation unit provides information regarding the relevance of the learning content as input to the generation AI, and the generation AI adjusts the order of the plan based on that information.

[0043] The provision unit can adjust the level of detail of the learning content provided based on the child's level of comprehension when providing the learning content. The provision unit adjusts the level of detail of the learning content provided based on the child's level of comprehension using the generation AI when providing the learning content. The generation AI analyzes the child's level of comprehension, for example, based on test results or the correct answer rate on quizzes. For example, the provision unit provides learning content with concise explanations if the child has a high level of comprehension. The generation AI can also provide learning content with detailed explanations if the child has a low level of comprehension. For example, if the child has a low level of comprehension on a particular topic, the provision unit provides a detailed explanation of that topic. Furthermore, the generation AI can provide learning content with an optimal level of detail based on the child's level of comprehension. For example, the provision unit adjusts the depth of the explanation and the presence or absence of supplementary materials depending on the child's level of comprehension. This allows the provision of optimal learning content based on the child's level of comprehension. Some or all of the above-described processing in the provision unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the provision unit analyzes the child's level of comprehension using the generation AI and adjusts the level of detail of the learning content based on the results.

[0044] The provision unit can apply different provision algorithms depending on the child's interests when providing learning content. The provision unit applies different provision algorithms depending on the child's interests when providing learning content using the generation AI. The generation AI analyzes the child's interests based on, for example, questionnaire surveys or behavioral logs. For example, if the child is a visual learner, the provision unit applies a provision algorithm that includes many visual elements. The generation AI can also apply a provision algorithm that includes many audio and music if the child is an auditory learner. For example, if the child is an auditory learner, the provision unit explains the learning content using audio and uses music to promote learning rhythmically. Furthermore, if the child is an experiential learner, the generation AI can apply a provision algorithm that includes many practical activities. For example, if the child is an experiential learner, the provision unit suggests activities that allow the child to understand the learning content using actual objects. This allows the provision of optimal learning content tailored to the child's interests. Some or all of the above-mentioned processing in the provision unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the provision unit analyzes the child's interests using the generation AI and applies different provision algorithms based on the results.

[0045] The provision unit can determine the priority of provision based on the child's learning history when providing learning content. The provision unit determines the priority of provision based on the child's learning history when providing learning content using the generation AI. The generation AI analyzes the learning history based on, for example, past test results and records of study time. For example, the provision unit determines the learning content to prioritize based on the content the child has learned in the past. The generation AI can also prioritize providing content that is highly understood based on the child's learning history. For example, the provision unit provides learning content based on subjects or topics in which the child has previously scored highly. Furthermore, the generation AI can comprehensively analyze the child's learning history and provide learning content with optimal priority. For example, the provision unit prioritizes content that is highly understood based on the child's learning history. This allows the provision of optimal learning content based on the child's learning history. Some or all of the above-mentioned processing in the provision unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the provision unit analyzes the child's learning history using the generation AI and determines the priority of provision based on the results.

[0046] The provision unit can improve the accuracy of the provision of learning content by referring to the child's related activities when providing learning content. The provision unit can improve the accuracy of the provision by referring to the child's related activities when providing learning content using the generation AI. The generation AI analyzes related activities based on, for example, extracurricular activities and hobbies. For example, the provision unit provides optimal learning content based on the child's past related activities. The generation AI can also prioritize providing content that is highly comprehensible based on the child's related activities. For example, the provision unit provides learning content related to the child's past extracurricular activities and hobbies. Furthermore, the generation AI can comprehensively analyze the child's related activities and provide learning content with optimal accuracy. For example, the provision unit prioritizes providing content that is highly comprehensible based on the child's related activities. This makes it possible to provide optimal learning content based on the child's related activities. Some or all of the above-mentioned processing in the provision unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the provision unit analyzes the child's related activities using the generation AI and improves the accuracy of the provision based on the results.

[0047] When monitoring learning progress, the monitoring unit can predict current progress by referring to past learning data. When monitoring learning progress using the generation AI, the monitoring unit predicts current progress by referring to past learning data. The generation AI analyzes learning data based on, for example, past test results and study time records. For example, the monitoring unit predicts current progress based on the child's past learning data. The generation AI can also prioritize monitoring content with a high level of understanding based on the child's learning history. For example, the monitoring unit predicts progress based on subjects and topics in which the child previously achieved high scores. Furthermore, the generation AI can comprehensively analyze the child's past learning data to make the most efficient progress prediction. For example, the monitoring unit predicts progress based on the child's study time and assignment submission status. This allows for an optimal progress prediction based on past learning data. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the monitoring unit analyzes past learning data using the generation AI and predicts current progress based on the results.

[0048] The monitoring unit can apply different monitoring methods to each child's learning style when monitoring learning progress. The monitoring unit uses the generating AI to apply different monitoring methods to each child's learning style when monitoring learning progress. The generating AI uses different monitoring methods depending on the learning style, such as visual, auditory, or experiential. For example, the monitoring unit applies a monitoring method that includes many visual elements to visually-oriented children. The generating AI can also apply a monitoring method that includes many audio and music to auditory-oriented children. For example, the monitoring unit monitors the learning progress of auditory-oriented children using audio and checking the progress using music to the rhythm. The generating AI can also apply a monitoring method that includes many practical activities to experiential-oriented children. For example, the monitoring unit suggests activities for experiential-oriented children that check the learning progress using actual objects. This allows optimal progress monitoring to be provided according to each child's learning style. Some or all of the above-described processing by the monitoring unit may be performed using, or without, the generating AI. For example, the monitoring unit analyzes the child's learning style using the generating AI and applies different monitoring methods based on the results.

[0049] The monitoring unit can analyze changes in progress based on the timing of submission of learning content when monitoring learning progress. The monitoring unit uses the generation AI to analyze changes in progress based on the timing of submission of learning content when monitoring learning progress. The generation AI analyzes changes in progress based on, for example, the submission deadline and submission frequency. For example, the monitoring unit prioritizes monitoring the progress of learning content with an upcoming submission deadline. The generation AI can also postpone progress of learning content with a distant submission deadline. For example, the monitoring unit analyzes progress of learning content based on the submission deadline. Furthermore, the generation AI can comprehensively analyze changes in progress based on the timing of submission of learning content. For example, the monitoring unit prioritizes monitoring the progress of learning content with an upcoming submission deadline and postpones progress of learning content with a distant submission deadline. This makes it possible to provide an optimal progress analysis based on the timing of submission of learning content. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the monitoring unit analyzes the timing of submission of learning content using the generation AI, and analyzes changes in progress based on the results.

[0050] The monitoring unit can analyze the progress by referring to the related data of the learning content when monitoring the learning progress. The monitoring unit uses the generation AI to analyze the progress by referring to the related data of the learning content when monitoring the learning progress. The generation AI analyzes the related data based on, for example, past test results and records of study time. For example, the monitoring unit analyzes the progress based on the related data of the learning content. The generation AI can also prioritize monitoring content with a high level of understanding from the related data of the learning content. For example, the monitoring unit analyzes the progress based on past test results and records of study time. The generation AI can also comprehensively analyze the related data of the learning content to perform the most efficient progress analysis. For example, the monitoring unit prioritizes monitoring content with a high level of understanding based on the related data of the learning content. This makes it possible to provide an optimal progress analysis based on the related data of the learning content. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the monitoring unit analyzes the related data of the learning content using the generation AI and analyzes the progress based on the results.

[0051] When identifying a weak point, the identification unit can predict the weak point by referring to past learning data. When identifying a weak point using the generation AI, the identification unit predicts the weak point by referring to past learning data. The generation AI analyzes learning data based on, for example, past test results and records of study time. For example, the identification unit predicts the weak point based on the child's past learning data. The generation AI can also prioritize content with low comprehension based on the child's learning history. For example, the identification unit predicts the weak point based on subjects or topics in which the child previously received low scores. Furthermore, the generation AI can comprehensively analyze the child's past learning data to make the most efficient weak point prediction. For example, the identification unit predicts the weak point based on the child's study time and assignment submission status. This allows for optimal weak point prediction based on the past learning data. Some or all of the above-mentioned processing in the identification unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the identification unit analyzes past learning data using the generation AI and predicts the weak point based on the results.

[0052] The identification unit can apply different identification techniques to each child's learning style when identifying weak points. The identification unit uses the generation AI to apply different identification techniques to each child's learning style when identifying weak points. The generation AI uses different identification techniques depending on the learning style, such as visual, auditory, or experiential. For example, the identification unit applies an identification technique that includes many visual elements to visual children. The generation AI can also apply an identification technique that includes many audio and music to auditory children. For example, the identification unit explains the learning content to auditory children using audio and uses music to promote learning rhythmically. The generation AI can also apply an identification technique that includes many practical activities to experiential children. For example, the identification unit suggests activities that allow experiential children to understand the learning content using actual objects. This allows for optimal identification of weak points according to each child's learning style. Some or all of the above-described processing in the identification unit may be performed using, or without, the generation AI. For example, the identification unit analyzes a child's learning style using the generation AI and applies different identification techniques based on the results.

[0053] When identifying weaknesses, the identification unit can analyze changes in the weaknesses based on the timing of submission of the learning content. When identifying weaknesses, the identification unit uses the generation AI to analyze changes in the weaknesses based on the timing of submission of the learning content. The generation AI analyzes changes in the weaknesses based on, for example, the submission deadline and the frequency of submission. For example, the identification unit prioritizes identifying weaknesses in learning content with an upcoming submission deadline. The generation AI can also postpone identifying weaknesses in learning content with a distant submission deadline. For example, the identification unit analyzes weaknesses in learning content based on the submission deadline. Furthermore, the generation AI can comprehensively analyze changes in weaknesses based on the timing of submission of the learning content. For example, the identification unit prioritizes identifying weaknesses in learning content with an upcoming submission deadline and postpones identifying weaknesses in learning content with a distant submission deadline. This makes it possible to provide an optimal weakness analysis based on the timing of submission of the learning content. Some or all of the above-mentioned processing in the identification unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the identification department uses the generation AI to analyze the timing of submission of learning content and analyzes changes in weaknesses based on the results.

[0054] When identifying a weakness, the identification unit can analyze the weakness by referring to the related data of the learning content. When identifying a weakness, the identification unit uses the generation AI to analyze the weakness by referring to the related data of the learning content. The generation AI analyzes the related data based on, for example, past test results and records of study time. For example, the identification unit analyzes the weakness based on the related data of the learning content. The generation AI can also prioritize identifying content with low levels of understanding from the related data of the learning content. For example, the identification unit analyzes the weakness based on past test results and records of study time. Furthermore, the generation AI can comprehensively analyze the related data of the learning content to perform the most efficient weakness analysis. For example, the identification unit prioritizes identifying content with low levels of understanding based on the related data of the learning content. This makes it possible to provide an optimal weakness analysis based on the related data of the learning content. Some or all of the above-mentioned processing in the identification unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the identification unit analyzes the related data of the learning content using the generation AI and analyzes the weaknesses based on the results.

[0055] The reliability assurance unit can predict reliability by referring to past data when ensuring the reliability of information. The reliability assurance unit predicts reliability by referring to past data when ensuring the reliability of information using the generation AI. The generation AI analyzes data based on, for example, past test results and records of study time. For example, the reliability assurance unit predicts the reliability of information based on past data. The generation AI can also prioritize providing highly reliable information from past data. For example, the reliability assurance unit predicts reliability based on past test results and records of study time. Furthermore, the generation AI can comprehensively analyze past data and provide the most reliable information. For example, the reliability assurance unit prioritizes providing highly reliable information based on past data. This makes it possible to provide an optimal reliability prediction based on past data. Some or all of the above-mentioned processing in the reliability assurance unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the reliability assurance unit analyzes past data using the generation AI and predicts reliability based on the results.

[0056] The reliability assurance unit can apply different reliability assurance methods to each information provider when ensuring the reliability of information. The reliability assurance unit applies different reliability assurance methods to each information provider when ensuring the reliability of information using the generation AI. The generation AI, for example, analyzes data based on the reliability of the provider. For example, the reliability assurance unit prioritizes providing information from highly reliable providers. The generation AI can also apply different reliability assurance methods to each information provider. For example, the reliability assurance unit applies reliability assurance methods based on the reliability of the provider. Furthermore, the generation AI can comprehensively analyze the reliability of the provider and provide the most reliable information. For example, the reliability assurance unit prioritizes providing highly reliable information based on the reliability of the provider. This makes it possible to provide the optimal reliability assurance method according to the information provider. Some or all of the above-mentioned processing in the reliability assurance unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the reliability assurance unit analyzes the reliability of the provider using the generation AI and applies a reliability assurance method based on the results.

[0057] The reliability assurance unit can analyze changes in reliability based on the time of information submission when ensuring the reliability of information. The reliability assurance unit uses the generation AI to analyze changes in reliability based on the time of information submission when ensuring the reliability of information. The generation AI analyzes changes in reliability based on, for example, the submission deadline or the frequency of submission. For example, the reliability assurance unit prioritizes analyzing the reliability of information with an upcoming submission deadline. The generation AI can also postpone analyzing the reliability of information with a distant submission deadline. For example, the reliability assurance unit analyzes the reliability of information based on the submission deadline. Furthermore, the generation AI can comprehensively analyze changes in reliability based on the time of information submission. For example, the reliability assurance unit prioritizes analyzing the reliability of information with an upcoming submission deadline and postpones analyzing the reliability of information with a distant submission deadline. This makes it possible to provide an optimal reliability analysis based on the time of information submission. Some or all of the above-mentioned processing in the reliability assurance unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the reliability assurance unit analyzes the time of information submission using the generation AI, and analyzes changes in reliability based on the results.

[0058] The reliability assurance unit can analyze reliability by referring to the related data of the information when ensuring the reliability of the information. The reliability assurance unit analyzes reliability by referring to the related data of the information when ensuring the reliability of the information using the generation AI. The generation AI analyzes the related data based on, for example, past test results and records of study time. For example, the reliability assurance unit analyzes reliability based on the related data of the information. The generation AI can also prioritize providing highly reliable information from the related data of the information. For example, the reliability assurance unit analyzes reliability based on past test results and records of study time. Furthermore, the generation AI can comprehensively analyze the related data of the information and provide the most reliable information. For example, the reliability assurance unit prioritizes providing highly reliable information based on the related data of the information. This makes it possible to provide an optimal reliability analysis based on the related data of the information. Some or all of the above-mentioned processing in the reliability assurance unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the reliability assurance unit analyzes the related data of the information using the generation AI and analyzes reliability based on the results.

[0059] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0060] The tutoring system can further include a dashboard section that visually displays a child's learning progress. The dashboard section displays a child's learning progress in graphs and charts, allowing parents to understand it at a glance. For example, it can display the progress of study time in a line graph, visually showing how much time was spent on each subject. It can also display test results in a bar graph, allowing the scores for each subject to be compared. It can also display the degree of achievement of learning progress in a pie chart, allowing parents to see at a glance how progress is made toward the goal. This makes it easier for parents to intuitively understand their child's learning situation.

[0061] The tutoring system can further include a gamification section to increase children's motivation to learn. The gamification section awards points and badges according to the progress of learning, allowing children to enjoy learning. For example, children can earn points each time they complete a specific task and use those points to purchase virtual items. In addition, they can earn badges each time they complete a certain amount of study time, providing the fun of increasing their collection. Furthermore, a system can be introduced in which children level up according to their progress in learning and new challenges are unlocked. This makes it easier for children to maintain their motivation to learn.

[0062] The tutoring system can further include an environmental adjustment unit to optimize the child's learning environment. The environmental adjustment unit monitors the child's learning environment and provides the optimal environment. For example, it can use sensors to detect the brightness and temperature of the room and adjust the brightness and temperature to an appropriate level. It can also monitor the noise level during learning and provide a noise canceling function as needed. It can also monitor posture during learning and issue alerts to help children maintain good posture. This allows the child to concentrate on their studies.

[0063] The tutoring system can also include a sharing section for sharing children's learning results. The sharing section allows children to share their learning results with family and friends, increasing their motivation to study. For example, learning progress and test results can be automatically shared in a family group chat. It can also provide a function that allows children to post their learning results on social media and compete with friends. Furthermore, learning results can be reported regularly to parents' email addresses, making it easier for parents to keep track of their children's learning status. This makes it easier for children to feel a sense of accomplishment in their studies.

[0064] The tutoring system can further include a content customization unit for providing learning content that matches a child's learning style. The content customization unit provides optimal learning content based on a child's learning style and interests. For example, a visually-oriented child can be provided with content that includes many videos and illustrations. An auditory-oriented child can also be provided with content in the form of audio commentary or podcasts. Furthermore, a hands-on child can be provided with content that includes experiments and fieldwork. This allows children to learn in a way that suits them best.

[0065] The processing flow of the first embodiment will be briefly explained below.

[0066] Step 1: The reception unit receives input from the parent or guardian about their child's learning. The learning content input by the parent or guardian includes subjects, topics, skills, etc. The reception unit can input learning content in text format or using voice input. It can also provide an optimal input interface based on past input history. Step 2: The generator creates a learning plan based on the information received by the receiver. Using AI, the generator can customize the learning plan to suit the child's learning style and pace. For example, it generates an optimal learning plan based on the child's learning style, such as visual, auditory, or experiential. Step 3: The provision unit provides learning content based on the learning plan created by the generation unit. The provision unit provides learning content through online classes or face-to-face classes, and can adjust the level of detail of the content based on the child's level of understanding. Step 4: The monitoring unit monitors the child's learning progress. The monitoring unit can monitor the child's learning progress through regular checks and real-time monitoring, record the learning progress, and report it to parents.

[0067] (Example 2) A tutoring system according to an embodiment of the present invention uses a generating AI as a tutor to teach a child about various topics and studies on behalf of a mother who is busy with housework. This tutoring system begins when a mother inputs her child's learning content and topics of interest into the generating AI. The generating AI then creates a learning plan tailored to the child based on that information. The generating AI then monitors the child's learning progress in real time and adjusts the learning content as needed. The generating AI also provides instant answers to the child's questions and provides additional information to deepen understanding. This system allows a mother to support her child's learning while focusing on housework. For example, a mother inputs her child's learning content and topics of interest into the generating AI. For example, if the child is struggling with math problems, the mother inputs that information into the generating AI. The generating AI analyzes this information and creates a learning plan tailored to the child. Next, the generating AI provides the child with learning content based on the learning plan. For example, the generating AI explains basic mathematical concepts to the child and has them solve specific problems. The generating AI then monitors the child's level of understanding in real time and adjusts the learning content as needed. Furthermore, the generative AI instantly answers any questions a child has. For example, if a child asks a question about a math problem, the generative AI provides an appropriate answer to that question. The generative AI can also provide additional information and examples to deepen the child's understanding. This system allows mothers to support their children's learning while focusing on housework. For example, while a mother is cooking, the generative AI can provide learning content for the child and answer questions, allowing the mother to do her housework with peace of mind. In this way, the tutoring system can support her children's learning while allowing the mother to focus on housework.

[0068] The tutoring system according to the embodiment includes a reception unit, a generation unit, a provision unit, and a monitoring unit. The reception unit receives input of learning content from a parent or guardian. The learning content input by the parent or guardian includes, but is not limited to, subjects, topics, and skills. For example, the reception unit receives input of the learning content from a parent or guardian in text format. The reception unit can also input the learning content using voice input. For example, the parent or guardian may explain the learning content through voice and convert it into text data. The reception unit can also provide an optimal input interface based on past input history. For example, the reception unit can automatically display learning content frequently input by the parent or guardian as candidates. The generation unit uses a generation AI to create a learning plan based on the information received by the reception unit. The generation AI creates the learning plan using, for example, a text generation AI (e.g., LLM). The generation unit can also use the generation AI to customize the learning plan to suit the child's learning style and pace. For example, the generation AI generates an optimal learning plan depending on the child's learning style, such as visual, auditory, or experiential. The provision unit provides the learning content based on the learning plan created by the generation unit. The provision unit provides learning content through, for example, online classes or face-to-face classes. The provision unit can also adjust the level of detail provided based on the child's level of understanding. For example, if the child has a high level of understanding, the provision unit can provide learning content with concise explanations. The monitoring unit monitors the child's learning progress. The monitoring unit monitors the learning progress through, for example, regular checks or real-time monitoring. The monitoring unit can also record the child's learning progress and report it to the parent. For example, the monitoring unit digitally records the learning progress and reports it to the parent via email notification or dashboard display. As a result, the tutoring system according to the embodiment can support the child's learning while the mother is able to focus on housework.

[0069] The generation unit can create a study plan using a generation AI. The generation unit creates the study plan using, for example, a generation AI. The generation AI creates the study plan using, for example, a text generation AI (e.g., LLM). The generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The generation AI generates an optimal study plan based on, for example, a child's learning content and topics of interest. For example, if a child is struggling to solve a math problem, the generation AI uses that information to create a study plan that explains basic math concepts and has the child solve specific problems. The generation AI can also customize the study plan to suit the child's learning style and pace. For example, a visual child can be provided with a study plan that includes many visual elements, while an auditory child can be provided with a study plan that includes many audio and music elements. In this way, the generation AI can efficiently create study plans. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, when creating a learning plan using the generation AI, the generation unit provides the child's learning content and topics of interest as input to the generation AI, and the generation AI generates a learning plan based on that.

[0070] The generation unit can customize the learning plan to suit a child's learning style and pace using a generation AI. The generation unit, for example, uses a generation AI to customize the learning plan to suit a child's learning style and pace. The generation AI generates an optimal learning plan depending on the child's learning style, such as visual, auditory, or experiential. For example, the generation AI provides a learning plan that includes many visual elements to a visual child. For example, the generation AI explains mathematical concepts using diagrams and graphs. The generation AI also provides a learning plan that includes many audio and music to an auditory child. For example, the generation AI explains mathematical problems using audio and uses music to promote learning rhythmically. Furthermore, the generation AI provides a learning plan that includes many practical activities to an experiential child. For example, the generation AI suggests activities such as solving mathematical problems using actual objects. This makes it possible to provide a learning plan that suits a child's individual learning style and pace. Some or all of the above-described processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, when customizing a learning plan using the generation AI, the generation unit provides information about the child's learning style and pace as input to the generation AI, and the generation AI customizes the learning plan based on that information.

[0071] The monitoring unit can record the child's learning progress and report it to the guardian. The monitoring unit, for example, digitally records the child's learning progress. Digital records include, but are not limited to, study time, test results, and assignment submission status. The monitoring unit, for example, periodically checks the learning progress and monitors it in real time. The monitoring unit also reports the child's learning progress to the guardian. Reporting methods include, for example, email notification, dashboard display, and paper report. For example, the monitoring unit digitally records the learning progress and sends an email notification to the guardian. The monitoring unit can also display the learning progress on a dashboard so that the guardian can check it at any time. Furthermore, the monitoring unit can print out the learning progress using a printer and provide it to guardians who wish to receive paper reports. This makes it easier for mothers to understand their child's learning progress. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, a generation AI. For example, the monitoring unit inputs the child's learning progress into the generation AI, which then records the learning progress based on the input and reports it to the guardian.

[0072] The tutoring system further includes an identification unit that uses a generation AI to analyze a child's learning data, identify weak points, and provide focused instruction. The identification unit uses the generation AI to analyze the child's learning data and identify weak points. The generation AI identifies weak points, for example, based on low-scoring test results or questions frequently missed. The generation AI analyzes the child's past test results and identifies questions on which the child receives low scores. The generation AI can also identify weak points based on questions frequently missed by the child. For example, the generation AI extracts questions on which the child repeatedly receives mistakes and provides focused instruction on those questions. The generation AI can also comprehensively analyze the child's learning data and identify weak points. For example, the generation AI identifies weak points based on the child's study time and assignment submission status. This identifies the child's weak points and enables effective instruction. Some or all of the above-described processing in the identification unit may be performed using, or without, the generation AI. For example, when the identification unit analyzes the child's learning data and identifies weak points using the generation AI, the identification unit provides the child's learning data as input to the generation AI, which then identifies the weak points based on that data.

[0073] The tutoring system further includes a reliability assurance unit that ensures the reliability of the information provided by the generation AI. The reliability assurance unit includes a mechanism for ensuring the reliability of the information provided by the generation AI. For example, the reliability assurance unit verifies the source of the information provided by the generation AI. For example, the reliability assurance unit verifies the source of the data used by the generation AI and uses only highly reliable data. The reliability assurance unit may also include a scoring system for evaluating the reliability of the information provided by the generation AI. For example, the reliability assurance unit calculates a reliability score for the information provided by the generation AI and prioritizes providing highly reliable information. The reliability assurance unit may also include a mechanism for continuously monitoring the reliability of the information provided by the generation AI and improving it as necessary. For example, the reliability assurance unit periodically checks the reliability of the information provided by the generation AI and eliminates unreliable information. This improves the reliability of the provided information. Some or all of the above-described processing in the reliability assurance unit may be performed using, or without, the generation AI. For example, when evaluating the reliability of the information provided by the generation AI, the reliability assurance unit provides data regarding the source and reliability of the information as input to the generation AI, and the generation AI calculates the reliability score based on that data.

[0074] The tutoring system further includes a function in which the reception unit estimates the parent's emotions and adjusts the learning content input method based on the estimated parent's emotions. The reception unit estimates the parent's emotions using a generation AI and adjusts the learning content input method based on the estimated emotions. The generation AI estimates the parent's emotions using, for example, facial expression recognition technology. For example, the reception unit captures the parent's facial expression with a camera, and the generation AI analyzes the facial expression data to estimate the parent's emotions. The generation AI can also estimate the parent's emotions using voice analysis technology. For example, the reception unit records the parent's voice, and the generation AI analyzes the voice data to estimate the parent's emotions. The generation AI can also estimate the parent's emotions using text analysis technology. For example, the reception unit provides the generation AI with text data entered by the parent, and the generation AI analyzes the text data to estimate the parent's emotions. Based on the estimated emotions, the reception unit adjusts the learning content input method. For example, if the parent is stressed, the reception unit provides a simple interface and minimizes input steps. If the parent is relaxed, the reception unit provides detailed input options and suggests a customizable input method. Furthermore, if the parent is in a hurry, the reception unit prioritizes voice input, allowing the parent to quickly input the learning content. This allows the parent to provide the optimal input method according to their emotions. Some or all of the above-described processing in the reception unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the reception unit estimates the parent's emotions using a generation AI and adjusts the input method based on the result.

[0075] The reception unit can analyze the parent's past input history and provide an optimal input interface. The reception unit uses a generation AI to analyze the parent's past input history and provide an optimal input interface. The generation AI, for example, analyzes the parent's input patterns based on past input data. For example, the reception unit automatically displays learning content that the parent has frequently input in the past as candidates. The generation AI can also prioritize suggesting input methods (voice, text, etc.) that the parent has used in the past. For example, if the parent has frequently used voice input in the past, the reception unit prioritizes voice input. Furthermore, the generation AI can predict and suggest learning content to be used during a specific time period based on the parent's past input history. For example, if the parent tends to input specific learning content during a specific time period, the reception unit suggests the learning content that is optimal for that time period. This makes it possible to provide an optimal input interface based on the parent's past input history. Some or all of the above-described processing in the reception unit may be performed using, or without, the generation AI. For example, the reception unit may analyze the parent's past input history using the generation AI and provide an optimal input interface based on the results.

[0076] When inputting learning content, the reception unit can filter the learning content based on the guardian's current living situation and areas of interest. The reception unit uses a generation AI to filter the learning content based on the guardian's current living situation and areas of interest. The generation AI analyzes the guardian's living situation based on, for example, a questionnaire survey or a behavior log. For example, if the guardian is busy, the reception unit prioritizes suggesting learning content that is quick and effective. The generation AI can also analyze the guardian's past search history and social media activity to identify the guardian's areas of interest. For example, if the guardian is interested in a particular field, the reception unit prioritizes displaying learning content related to that field. Furthermore, the generation AI can filter and suggest appropriate learning content based on the guardian's living situation. For example, if the guardian is in a particular living situation, the reception unit suggests learning content appropriate for that situation. This makes it possible to provide learning content tailored to the guardian's living situation and areas of interest. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the reception unit analyzes the guardian's living situation and areas of interest using a generation AI, and filters the learning content based on the results.

[0077] The reception unit can estimate the parent's emotions and prioritize the input content based on the estimated parent's emotions. The reception unit uses the generation AI to estimate the parent's emotions and prioritize the input content based on the estimated emotions. The generation AI estimates the parent's emotions using, for example, facial expression recognition technology. For example, the reception unit captures the parent's facial expression with a camera, and the generation AI analyzes the facial expression data to estimate the emotion. The generation AI can also estimate the parent's emotions using voice analysis technology. For example, the reception unit records the parent's voice, and the generation AI analyzes the voice data to estimate the emotion. The generation AI can also estimate the parent's emotions using text analysis technology. For example, the reception unit provides the generation AI with text data entered by the parent, and the generation AI analyzes the text data to estimate the emotion. The reception unit prioritizes the input content based on the estimated emotion. For example, if the parent is feeling stressed, the reception unit prioritizes input of important learning content. On the other hand, if the parent is relaxed, the reception unit inputs detailed learning content. Furthermore, if the parent is in a hurry, the reception unit prioritizes input of easy learning content. This allows the optimal priority of input content to be provided according to the parent's emotions. Some or all of the above-described processing in the reception unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the reception unit estimates the parent's emotions using a generation AI and determines the priority of input content based on the result.

[0078] When inputting learning content, the reception unit can prioritize inputting highly relevant content by taking into account the guardian's geographical location information. The reception unit uses a generation AI to input learning content by taking into account the guardian's geographical location information. The generation AI analyzes the guardian's geographical location information based on, for example, GPS data or location information services. For example, if the guardian lives in a specific area, the reception unit prioritizes inputting learning content related to that area. Furthermore, if the guardian is traveling, the generation AI can prioritize inputting learning content related to the travel destination. For example, when the guardian inputs learning content while traveling, the reception unit provides information related to the travel destination. Furthermore, if the guardian is in a specific location, the generation AI can prioritize inputting learning content related to that location. For example, if the guardian is attending a specific facility or event, the reception unit provides learning content related to that location or event. This makes it possible to provide optimal learning content based on the guardian's geographical location information. Some or all of the above-described processing in the reception unit may be performed using, or without, the generation AI. For example, the reception unit analyzes the guardian's geographical location information using the generation AI and inputs learning content based on the results.

[0079] When inputting learning content, the reception unit can analyze the parent's social media activity and input related content. The reception unit analyzes the parent's social media activity using a generation AI and inputs related learning content. The generation AI, for example, identifies the parent's areas of interest based on an analysis of social media posts and followers. For example, the reception unit inputs learning content related to topics the parent is interested in on social media. The generation AI can also input learning content related to accounts the parent follows on social media. For example, the reception unit suggests learning content based on education-related accounts the parent follows. Furthermore, the generation AI can input learning content based on information shared by the parent on social media. For example, the reception unit provides learning content related to articles and videos shared by the parent. This makes it possible to provide optimal learning content based on the parent's social media activity. Some or all of the above-described processing in the reception unit may be performed using, or without, the generation AI. For example, the reception unit analyzes the parent's social media activity using a generation AI and inputs learning content based on the results.

[0080] The generation unit can estimate the learner's emotions and adjust the presentation of the learning plan based on the estimated learner's emotions. The generation unit uses a generation AI to estimate the learner's emotions and adjust the presentation of the learning plan based on the estimated emotions. The generation AI estimates the learner's emotions using, for example, facial expression recognition technology. For example, the generation unit captures the learner's facial expressions with a camera, and the generation AI analyzes the facial expression data to estimate the learner's emotions. The generation AI can also estimate the learner's emotions using voice analysis technology. For example, the generation unit records the learner's voice, and the generation AI analyzes the voice data to estimate the learner's emotions. The generation AI can also estimate the learner's emotions using text analysis technology. For example, the generation unit provides the generation AI with text data entered by the learner, and the generation AI analyzes the text data to estimate the learner's emotions. The generation unit adjusts the presentation of the learning plan based on the estimated emotions. For example, if the learner is relaxed, the generation unit generates a learning plan that progresses at a leisurely pace. If the learner is excited, the generation unit generates a learning plan that adds visually stimulating effects. Furthermore, when the learner is concentrating, the generation unit generates a learning plan that includes detailed explanations. This allows for providing an optimal way to express the learning plan according to the learner's emotions. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit estimates the learner's emotions using a generation AI and adjusts the way the learning plan is expressed based on the results.

[0081] When generating a study plan, the generation unit can adjust the level of detail of the plan based on the child's study history. When generating a study plan using the generation AI, the generation unit adjusts the level of detail of the plan based on the child's study history. The generation AI analyzes the study history based on, for example, past test results and study time records. For example, the generation unit generates a detailed study plan based on the content the child has learned in the past. The generation AI can also generate a study plan that prioritizes content with a high level of understanding from the child's study history. For example, the generation unit creates a study plan based on subjects and topics in which the child has previously scored highly. Furthermore, the generation AI can comprehensively analyze the child's study history to generate an optimal study plan. For example, the generation unit adjusts the level of detail of the study plan based on the child's study time and assignment submission status. This makes it possible to provide an optimal study plan based on the child's study history. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, when generating a study plan using the generation AI, the generation unit provides the child's study history as input to the generation AI, and the generation AI adjusts the level of detail of the study plan based on that.

[0082] The generation unit can apply different generation algorithms depending on the child's learning style when generating a lesson plan. The generation unit applies different generation algorithms depending on the child's learning style when generating a lesson plan using the generation AI. The generation AI uses different generation algorithms depending on the child's learning style, such as visual, auditory, or experiential. For example, the generation unit applies a generation algorithm that includes many visual elements to a visual child. For example, the generation AI explains the learning content using diagrams and graphs. The generation AI also applies a generation algorithm that includes many audio and music to an auditory child. For example, the generation AI explains the learning content using audio and uses music to advance the learning rhythmically. Furthermore, the generation AI applies a generation algorithm that includes many practical activities to an experiential child. For example, the generation AI suggests activities that allow the child to understand the learning content using actual objects. This makes it possible to provide an optimal lesson plan depending on the child's learning style. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, when generating a learning plan using the generation AI, the generation unit provides information about the child's learning style as input to the generation AI, and the generation AI applies different generation algorithms based on that information.

[0083] The generation unit can estimate the learner's emotions and adjust the length of the lesson plan based on the estimated learner's emotions. The generation unit uses a generation AI to estimate the learner's emotions and adjust the length of the lesson plan based on the estimated emotions. The generation AI estimates the learner's emotions using, for example, facial expression recognition technology. For example, the generation unit captures the learner's facial expressions with a camera, and the generation AI analyzes the facial expression data to estimate the learner's emotions. The generation AI can also estimate the learner's emotions using voice analysis technology. For example, the generation unit records the learner's voice, and the generation AI analyzes the voice data to estimate the learner's emotions. The generation AI can also estimate the learner's emotions using text analysis technology. For example, the generation unit provides the generation AI with text data entered by the learner, and the generation AI analyzes the text data to estimate the learner's emotions. The generation unit adjusts the length of the lesson plan based on the estimated emotions. For example, if the learner is tired, the generation unit generates a short, to-the-point lesson plan. On the other hand, if the learner is relaxed, the generation unit generates a longer lesson plan with detailed explanations. Furthermore, if the learner is excited, the generation unit generates a lesson plan with visually stimulating effects. This allows the learner to be provided with a lesson plan of an optimal length according to their emotions. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit estimates the learner's emotions using a generation AI and adjusts the length of the lesson plan based on the results.

[0084] When generating a study plan, the generation unit can determine the priority of the plan based on the submission date of the study content. When generating a study plan using the generation AI, the generation unit determines the priority of the plan based on the submission date of the study content. The generation AI analyzes the priority of the study content based on, for example, the submission deadline or the frequency of submission. For example, the generation unit generates a study plan that prioritizes study content with an upcoming submission deadline. The generation AI can also generate a study plan that postpones study content with a distant submission deadline. For example, the generation unit generates a study plan that adjusts the priority of study content based on the submission deadline. Furthermore, the generation AI can generate an optimal study plan based on the submission date of the study content. For example, the generation unit generates a study plan that prioritizes study content with an upcoming submission deadline and postpones study content with a distant submission deadline. This makes it possible to provide an optimal study plan based on the submission date of the study content. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, when generating a learning plan using the generation AI, the generation unit provides information regarding the timing of submission of the learning content as input to the generation AI, and the generation AI determines the priority of the plan based on that information.

[0085] The generation unit can adjust the order of the plan based on the relevance of the learning content when generating the learning plan. The generation unit adjusts the order of the plan based on the relevance of the learning content when generating the learning plan using the generation AI. The generation AI analyzes the relevance of the learning content based on, for example, topic similarity or the need for prior knowledge. For example, the generation unit generates a learning plan that includes highly relevant learning content in succession. The generation AI can also generate a learning plan that includes less relevant learning content in a dispersed manner. For example, the generation unit generates a learning plan in an optimal order based on the relevance of the learning content. Furthermore, the generation AI can adjust the order of the learning plan based on the relevance of the learning content. For example, the generation unit generates a learning plan that includes highly relevant learning content in succession and includes less relevant learning content in a dispersed manner. This makes it possible to provide an optimal learning plan based on the relevance of the learning content. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, when generating a learning plan using the generation AI, the generation unit provides information regarding the relevance of the learning content as input to the generation AI, and the generation AI adjusts the order of the plan based on that information.

[0086] The provision unit can estimate the learner's emotions and adjust the method of providing the learning content based on the estimated learner's emotions. The provision unit estimates the learner's emotions using the generation AI and adjusts the method of providing the learning content based on the estimated emotions. The generation AI estimates the learner's emotions using, for example, facial expression recognition technology. For example, the provision unit captures the learner's facial expressions with a camera, and the generation AI analyzes the facial expression data to estimate the learner's emotions. The generation AI can also estimate the learner's emotions using voice analysis technology. For example, the provision unit records the learner's voice, and the generation AI analyzes the voice data to estimate the learner's emotions. The generation AI can also estimate the learner's emotions using text analysis technology. For example, the provision unit provides text data entered by the learner to the generation AI, and the generation AI analyzes the text data to estimate the learner's emotions. Based on the estimated emotions, the provision unit adjusts the method of providing the learning content. For example, if the learner is relaxed, the provision unit provides the learning content at a leisurely pace. Also, if the learner is excited, the provision unit provides the learning content with visually stimulating effects. Furthermore, when the learner is concentrating, the provision unit provides learning content including detailed explanations. This makes it possible to provide an optimal method of providing learning content according to the learner's emotions. Some or all of the above-mentioned processing in the provision unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the provision unit estimates the learner's emotions using a generation AI, and adjusts the method of providing learning content based on the result.

[0087] The provision unit can adjust the level of detail of the learning content provided based on the child's level of comprehension when providing the learning content. The provision unit adjusts the level of detail of the learning content provided based on the child's level of comprehension using the generation AI when providing the learning content. The generation AI analyzes the child's level of comprehension, for example, based on test results or the correct answer rate on quizzes. For example, the provision unit provides learning content with concise explanations if the child has a high level of comprehension. The generation AI can also provide learning content with detailed explanations if the child has a low level of comprehension. For example, if the child has a low level of comprehension on a particular topic, the provision unit provides a detailed explanation of that topic. Furthermore, the generation AI can provide learning content with an optimal level of detail based on the child's level of comprehension. For example, the provision unit adjusts the depth of the explanation and the presence or absence of supplementary materials depending on the child's level of comprehension. This allows the provision of optimal learning content based on the child's level of comprehension. Some or all of the above-described processing in the provision unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the provision unit analyzes the child's level of comprehension using the generation AI and adjusts the level of detail of the learning content based on the results.

[0088] The provision unit can apply different provision algorithms depending on the child's interests when providing learning content. The provision unit applies different provision algorithms depending on the child's interests when providing learning content using the generation AI. The generation AI analyzes the child's interests based on, for example, questionnaire surveys or behavioral logs. For example, if the child is a visual learner, the provision unit applies a provision algorithm that includes many visual elements. The generation AI can also apply a provision algorithm that includes many audio and music if the child is an auditory learner. For example, if the child is an auditory learner, the provision unit explains the learning content using audio and uses music to promote learning rhythmically. Furthermore, if the child is an experiential learner, the generation AI can apply a provision algorithm that includes many practical activities. For example, if the child is an experiential learner, the provision unit suggests activities that allow the child to understand the learning content using actual objects. This allows the provision of optimal learning content tailored to the child's interests. Some or all of the above-mentioned processing in the provision unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the provision unit analyzes the child's interests using the generation AI and applies different provision algorithms based on the results.

[0089] The providing unit can estimate the learner's emotions and adjust the order in which the learning content is presented based on the estimated learner's emotions. The providing unit estimates the learner's emotions using the generation AI and adjusts the order in which the learning content is presented based on the estimated emotions. The generation AI estimates the learner's emotions using, for example, facial expression recognition technology. For example, the providing unit captures the learner's facial expressions with a camera, and the generation AI analyzes the facial expression data to estimate the learner's emotions. The generation AI can also estimate the learner's emotions using voice analysis technology. For example, the providing unit records the learner's voice, and the generation AI analyzes the voice data to estimate the learner's emotions. The generation AI can also estimate the learner's emotions using text analysis technology. For example, the providing unit provides text data entered by the learner to the generation AI, and the generation AI analyzes the text data to estimate the learner's emotions. The providing unit adjusts the order in which the learning content is presented based on the estimated emotions. For example, if the learner is relaxed, the providing unit prioritizes providing more difficult learning content. Also, if the learner is excited, the providing unit prioritizes providing visually stimulating learning content. Furthermore, when a learner is concentrating, the provision unit prioritizes providing learning content that includes detailed explanations. This allows the optimal order of providing learning content to be provided according to the learner's emotions. Some or all of the above-described processing in the provision unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the provision unit estimates the learner's emotions using a generation AI, and adjusts the order of providing learning content based on the result.

[0090] The provision unit can determine the priority of provision based on the child's learning history when providing learning content. The provision unit determines the priority of provision based on the child's learning history when providing learning content using the generation AI. The generation AI analyzes the learning history based on, for example, past test results and records of study time. For example, the provision unit determines the learning content to prioritize based on the content the child has learned in the past. The generation AI can also prioritize providing content that is highly understood based on the child's learning history. For example, the provision unit provides learning content based on subjects or topics in which the child has previously scored highly. Furthermore, the generation AI can comprehensively analyze the child's learning history and provide learning content with optimal priority. For example, the provision unit prioritizes content that is highly understood based on the child's learning history. This allows the provision of optimal learning content based on the child's learning history. Some or all of the above-mentioned processing in the provision unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the provision unit analyzes the child's learning history using the generation AI and determines the priority of provision based on the results.

[0091] The provision unit can improve the accuracy of the provision of learning content by referring to the child's related activities when providing learning content. The provision unit can improve the accuracy of the provision by referring to the child's related activities when providing learning content using the generation AI. The generation AI analyzes related activities based on, for example, extracurricular activities and hobbies. For example, the provision unit provides optimal learning content based on the child's past related activities. The generation AI can also prioritize providing content that is highly comprehensible based on the child's related activities. For example, the provision unit provides learning content related to the child's past extracurricular activities and hobbies. Furthermore, the generation AI can comprehensively analyze the child's related activities and provide learning content with optimal accuracy. For example, the provision unit prioritizes providing content that is highly comprehensible based on the child's related activities. This makes it possible to provide optimal learning content based on the child's related activities. Some or all of the above-mentioned processing in the provision unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the provision unit analyzes the child's related activities using the generation AI and improves the accuracy of the provision based on the results.

[0092] The monitoring unit can estimate the learner's emotions and adjust the learning progress monitoring method based on the estimated learner's emotions. The monitoring unit estimates the learner's emotions using the generation AI and adjusts the learning progress monitoring method based on the estimated emotions. The generation AI estimates the learner's emotions using, for example, facial expression recognition technology. For example, the monitoring unit captures the learner's facial expressions with a camera, and the generation AI analyzes the facial expression data to estimate the learner's emotions. The generation AI can also estimate the learner's emotions using voice analysis technology. For example, the monitoring unit records the learner's voice, and the generation AI analyzes the voice data to estimate the learner's emotions. The generation AI can also estimate the learner's emotions using text analysis technology. For example, the monitoring unit provides the generation AI with text data entered by the learner, and the generation AI analyzes the text data to estimate the learner's emotions. The monitoring unit adjusts the learning progress monitoring method based on the estimated emotions. For example, if the learner is relaxed, the monitoring unit monitors the learner's learning progress at a leisurely pace. If the learner is excited, the monitoring unit monitors the learner's learning progress with visually stimulating effects. Furthermore, when the learner is concentrating, the monitoring unit monitors the learning progress including detailed explanations. This makes it possible to provide an optimal learning progress monitoring method according to the learner's emotions. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the monitoring unit estimates the learner's emotions using a generation AI and adjusts the learning progress monitoring method based on the result.

[0093] When monitoring learning progress, the monitoring unit can predict current progress by referring to past learning data. When monitoring learning progress using the generation AI, the monitoring unit predicts current progress by referring to past learning data. The generation AI analyzes learning data based on, for example, past test results and study time records. For example, the monitoring unit predicts current progress based on the child's past learning data. The generation AI can also prioritize monitoring content with a high level of understanding based on the child's learning history. For example, the monitoring unit predicts progress based on subjects and topics in which the child previously achieved high scores. Furthermore, the generation AI can comprehensively analyze the child's past learning data to make the most efficient progress prediction. For example, the monitoring unit predicts progress based on the child's study time and assignment submission status. This allows for an optimal progress prediction based on past learning data. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the monitoring unit analyzes past learning data using the generation AI and predicts current progress based on the results.

[0094] The monitoring unit can apply different monitoring methods to each child's learning style when monitoring learning progress. The monitoring unit uses the generating AI to apply different monitoring methods to each child's learning style when monitoring learning progress. The generating AI uses different monitoring methods depending on the learning style, such as visual, auditory, or experiential. For example, the monitoring unit applies a monitoring method that includes many visual elements to visually-oriented children. The generating AI can also apply a monitoring method that includes many audio and music to auditory-oriented children. For example, the monitoring unit monitors the learning progress of auditory-oriented children using audio and checking the progress using music to the rhythm. The generating AI can also apply a monitoring method that includes many practical activities to experiential-oriented children. For example, the monitoring unit suggests activities for experiential-oriented children that check the learning progress using actual objects. This allows optimal progress monitoring to be provided according to each child's learning style. Some or all of the above-described processing by the monitoring unit may be performed using, or without, the generating AI. For example, the monitoring unit analyzes the child's learning style using the generating AI and applies different monitoring methods based on the results.

[0095] The monitoring unit can estimate the learner's emotions and adjust the importance of progress based on the estimated learner's emotions. The monitoring unit estimates the learner's emotions using the generation AI and adjusts the importance of progress based on the estimated emotions. The generation AI estimates the learner's emotions using, for example, facial expression recognition technology. For example, the monitoring unit captures the learner's facial expressions with a camera, and the generation AI analyzes the facial expression data to estimate the learner's emotions. The generation AI can also estimate the learner's emotions using voice analysis technology. For example, the monitoring unit records the learner's voice, and the generation AI analyzes the voice data to estimate the learner's emotions. The generation AI can also estimate the learner's emotions using text analysis technology. For example, the monitoring unit provides the generation AI with text data entered by the learner, and the generation AI analyzes the text data to estimate the learner's emotions. The monitoring unit adjusts the importance of progress based on the estimated emotions. For example, if the learner is relaxed, the monitoring unit prioritizes monitoring important learning content. Also, if the learner is excited, the monitoring unit prioritizes monitoring visually stimulating learning content. Furthermore, when a learner is concentrating, the monitoring unit prioritizes monitoring of learning content that includes detailed explanations. This allows for optimal progress importance to be provided according to the learner's emotions. Some or all of the above-described processing in the monitoring unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the monitoring unit estimates the learner's emotions using a generation AI and adjusts the progress importance based on the results.

[0096] The monitoring unit can analyze changes in progress based on the timing of submission of learning content when monitoring learning progress. The monitoring unit uses the generation AI to analyze changes in progress based on the timing of submission of learning content when monitoring learning progress. The generation AI analyzes changes in progress based on, for example, the submission deadline and submission frequency. For example, the monitoring unit prioritizes monitoring the progress of learning content with an upcoming submission deadline. The generation AI can also postpone progress of learning content with a distant submission deadline. For example, the monitoring unit analyzes progress of learning content based on the submission deadline. Furthermore, the generation AI can comprehensively analyze changes in progress based on the timing of submission of learning content. For example, the monitoring unit prioritizes monitoring the progress of learning content with an upcoming submission deadline and postpones progress of learning content with a distant submission deadline. This makes it possible to provide an optimal progress analysis based on the timing of submission of learning content. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the monitoring unit analyzes the timing of submission of learning content using the generation AI, and analyzes changes in progress based on the results.

[0097] The monitoring unit can analyze the progress by referring to the related data of the learning content when monitoring the learning progress. The monitoring unit uses the generation AI to analyze the progress by referring to the related data of the learning content when monitoring the learning progress. The generation AI analyzes the related data based on, for example, past test results and records of study time. For example, the monitoring unit analyzes the progress based on the related data of the learning content. The generation AI can also prioritize monitoring content with a high level of understanding from the related data of the learning content. For example, the monitoring unit analyzes the progress based on past test results and records of study time. The generation AI can also comprehensively analyze the related data of the learning content to perform the most efficient progress analysis. For example, the monitoring unit prioritizes monitoring content with a high level of understanding based on the related data of the learning content. This makes it possible to provide an optimal progress analysis based on the related data of the learning content. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the monitoring unit analyzes the related data of the learning content using the generation AI and analyzes the progress based on the results.

[0098] The identification unit can estimate the learner's emotions and adjust the method for identifying weaknesses based on the estimated learner's emotions. The identification unit uses the generation AI to estimate the learner's emotions and adjust the method for identifying weaknesses based on the estimated emotions. The generation AI estimates the learner's emotions using, for example, facial expression recognition technology. For example, the identification unit captures the learner's facial expressions with a camera, and the generation AI analyzes the facial expression data to estimate the emotions. The generation AI can also estimate the learner's emotions using voice analysis technology. For example, the identification unit records the learner's voice, and the generation AI analyzes the voice data to estimate the emotions. The generation AI can also estimate the learner's emotions using text analysis technology. For example, the identification unit provides the generation AI with text data entered by the learner, and the generation AI analyzes the text data to estimate the emotions. Based on the estimated emotions, the identification unit adjusts the method for identifying weaknesses. For example, if the learner is relaxed, the identification unit performs a detailed analysis to identify weaknesses. Also, if the learner is excited, the identification unit performs an analysis with visually stimulating effects to identify weaknesses. Furthermore, when the learner is concentrating, the identification unit performs an analysis including a detailed explanation to identify weak points. This makes it possible to provide an optimal method for identifying weak points according to the learner's emotions. Some or all of the above-mentioned processing in the identification unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the identification unit estimates the learner's emotions using a generation AI, and adjusts the method for identifying weak points based on the result.

[0099] When identifying a weak point, the identification unit can predict the weak point by referring to past learning data. When identifying a weak point using the generation AI, the identification unit predicts the weak point by referring to past learning data. The generation AI analyzes learning data based on, for example, past test results and records of study time. For example, the identification unit predicts the weak point based on the child's past learning data. The generation AI can also prioritize content with low comprehension based on the child's learning history. For example, the identification unit predicts the weak point based on subjects or topics in which the child previously received low scores. Furthermore, the generation AI can comprehensively analyze the child's past learning data to make the most efficient weak point prediction. For example, the identification unit predicts the weak point based on the child's study time and assignment submission status. This allows for optimal weak point prediction based on the past learning data. Some or all of the above-mentioned processing in the identification unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the identification unit analyzes past learning data using the generation AI and predicts the weak point based on the results.

[0100] The identification unit can apply different identification techniques to each child's learning style when identifying weak points. The identification unit uses the generation AI to apply different identification techniques to each child's learning style when identifying weak points. The generation AI uses different identification techniques depending on the learning style, such as visual, auditory, or experiential. For example, the identification unit applies an identification technique that includes many visual elements to visual children. The generation AI can also apply an identification technique that includes many audio and music to auditory children. For example, the identification unit explains the learning content to auditory children using audio and uses music to promote learning rhythmically. The generation AI can also apply an identification technique that includes many practical activities to experiential children. For example, the identification unit suggests activities that allow experiential children to understand the learning content using actual objects. This allows for optimal identification of weak points according to each child's learning style. Some or all of the above-described processing in the identification unit may be performed using, or without, the generation AI. For example, the identification unit analyzes a child's learning style using the generation AI and applies different identification techniques based on the results.

[0101] The identification unit can estimate the learner's emotions and adjust the importance of the weaknesses based on the estimated learner's emotions. The identification unit uses the generation AI to estimate the learner's emotions and adjust the importance of the weaknesses based on the estimated emotions. The generation AI estimates the learner's emotions using, for example, facial expression recognition technology. For example, the identification unit captures the learner's facial expressions with a camera, and the generation AI analyzes the facial expression data to estimate the learner's emotions. The generation AI can also estimate the learner's emotions using voice analysis technology. For example, the identification unit records the learner's voice, and the generation AI analyzes the voice data to estimate the learner's emotions. The generation AI can also estimate the learner's emotions using text analysis technology. For example, the identification unit provides the generation AI with text data entered by the learner, and the generation AI analyzes the text data to estimate the learner's emotions. The identification unit adjusts the importance of the weaknesses based on the estimated emotions. For example, if the learner is relaxed, the identification unit prioritizes identifying important weaknesses. Also, if the learner is excited, the identification unit prioritizes identifying visually stimulating weaknesses. Furthermore, when the learner is concentrating, the identification unit prioritizes identifying weak points with detailed explanations. This allows the optimal importance of the weak points to be provided according to the learner's emotions. Some or all of the above-described processing in the identification unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the identification unit estimates the learner's emotions using a generation AI, and adjusts the importance of the weak points based on the result.

[0102] When identifying weaknesses, the identification unit can analyze changes in the weaknesses based on the timing of submission of the learning content. When identifying weaknesses, the identification unit uses the generation AI to analyze changes in the weaknesses based on the timing of submission of the learning content. The generation AI analyzes changes in the weaknesses based on, for example, the submission deadline and the frequency of submission. For example, the identification unit prioritizes identifying weaknesses in learning content with an upcoming submission deadline. The generation AI can also postpone identifying weaknesses in learning content with a distant submission deadline. For example, the identification unit analyzes weaknesses in learning content based on the submission deadline. Furthermore, the generation AI can comprehensively analyze changes in weaknesses based on the timing of submission of the learning content. For example, the identification unit prioritizes identifying weaknesses in learning content with an upcoming submission deadline and postpones identifying weaknesses in learning content with a distant submission deadline. This makes it possible to provide an optimal weakness analysis based on the timing of submission of the learning content. Some or all of the above-mentioned processing in the identification unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the identification department uses the generation AI to analyze the timing of submission of learning content and analyzes changes in weaknesses based on the results.

[0103] When identifying a weakness, the identification unit can analyze the weakness by referring to the related data of the learning content. When identifying a weakness, the identification unit uses the generation AI to analyze the weakness by referring to the related data of the learning content. The generation AI analyzes the related data based on, for example, past test results and records of study time. For example, the identification unit analyzes the weakness based on the related data of the learning content. The generation AI can also prioritize identifying content with low levels of understanding from the related data of the learning content. For example, the identification unit analyzes the weakness based on past test results and records of study time. Furthermore, the generation AI can comprehensively analyze the related data of the learning content to perform the most efficient weakness analysis. For example, the identification unit prioritizes identifying content with low levels of understanding based on the related data of the learning content. This makes it possible to provide an optimal weakness analysis based on the related data of the learning content. Some or all of the above-mentioned processing in the identification unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the identification unit analyzes the related data of the learning content using the generation AI and analyzes the weaknesses based on the results.

[0104] The reliability assurance unit can estimate the parent's emotions and adjust the method for ensuring the reliability of information based on the estimated parent's emotions. The reliability assurance unit uses a generation AI to estimate the parent's emotions and adjust the method for ensuring the reliability of information based on the estimated emotions. The generation AI estimates the parent's emotions using, for example, facial expression recognition technology. For example, the reliability assurance unit captures the parent's facial expression with a camera, and the generation AI analyzes the facial expression data to estimate the parent's emotions. The generation AI can also estimate the parent's emotions using voice analysis technology. For example, the reliability assurance unit records the parent's voice, and the generation AI analyzes the voice data to estimate the parent's emotions. The generation AI can also estimate the parent's emotions using text analysis technology. For example, the reliability assurance unit provides text data entered by the parent to the generation AI, and the generation AI analyzes the text data to estimate the parent's emotions. Based on the estimated emotions, the reliability assurance unit adjusts the method for ensuring the reliability of information. For example, if the parent is stressed, the reliability assurance unit prioritizes providing reliable information. Also, if the parent is relaxed, the reliability assurance unit provides detailed information. Furthermore, if the parent is in a hurry, the reliability assurance unit provides concise and reliable information. This makes it possible to provide an optimal method for ensuring the reliability of information according to the parent's emotions. Some or all of the above-mentioned processing in the reliability assurance unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the reliability assurance unit estimates the parent's emotions using a generation AI, and adjusts the method for ensuring the reliability of information based on the result.

[0105] The reliability assurance unit can predict reliability by referring to past data when ensuring the reliability of information. The reliability assurance unit predicts reliability by referring to past data when ensuring the reliability of information using the generation AI. The generation AI analyzes data based on, for example, past test results and records of study time. For example, the reliability assurance unit predicts the reliability of information based on past data. The generation AI can also prioritize providing highly reliable information from past data. For example, the reliability assurance unit predicts reliability based on past test results and records of study time. Furthermore, the generation AI can comprehensively analyze past data and provide the most reliable information. For example, the reliability assurance unit prioritizes providing highly reliable information based on past data. This makes it possible to provide an optimal reliability prediction based on past data. Some or all of the above-mentioned processing in the reliability assurance unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the reliability assurance unit analyzes past data using the generation AI and predicts reliability based on the results.

[0106] The reliability assurance unit can apply different reliability assurance methods to each information provider when ensuring the reliability of information. The reliability assurance unit applies different reliability assurance methods to each information provider when ensuring the reliability of information using the generation AI. The generation AI, for example, analyzes data based on the reliability of the provider. For example, the reliability assurance unit prioritizes providing information from highly reliable providers. The generation AI can also apply different reliability assurance methods to each information provider. For example, the reliability assurance unit applies reliability assurance methods based on the reliability of the provider. Furthermore, the generation AI can comprehensively analyze the reliability of the provider and provide the most reliable information. For example, the reliability assurance unit prioritizes providing highly reliable information based on the reliability of the provider. This makes it possible to provide the optimal reliability assurance method according to the information provider. Some or all of the above-mentioned processing in the reliability assurance unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the reliability assurance unit analyzes the reliability of the provider using the generation AI and applies a reliability assurance method based on the results.

[0107] The reliability assurance unit can estimate the parent's emotions and adjust the importance of the reliability of information based on the estimated parent's emotions. The reliability assurance unit estimates the parent's emotions using a generation AI and adjusts the importance of the reliability of information based on the estimated emotions. The generation AI estimates the parent's emotions using, for example, facial expression recognition technology. For example, the reliability assurance unit captures the parent's facial expression with a camera, and the generation AI analyzes the facial expression data to estimate the parent's emotions. The generation AI can also estimate the parent's emotions using voice analysis technology. For example, the reliability assurance unit records the parent's voice, and the generation AI analyzes the voice data to estimate the parent's emotions. The generation AI can also estimate the parent's emotions using text analysis technology. For example, the reliability assurance unit provides text data entered by the parent to the generation AI, and the generation AI analyzes the text data to estimate the parent's emotions. The reliability assurance unit adjusts the importance of the reliability of information based on the estimated emotions. For example, if the parent is stressed, the reliability assurance unit prioritizes providing reliable information. Also, if the parent is relaxed, the reliability assurance unit provides detailed information. Furthermore, if the parent is in a hurry, the reliability assurance unit provides concise and reliable information. This allows the parent to provide an optimal importance level for the reliability of the information according to their emotions. Some or all of the above-described processing in the reliability assurance unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the reliability assurance unit estimates the parent's emotions using a generation AI, and adjusts the importance level for the reliability of the information based on the result.

[0108] The reliability assurance unit can analyze changes in reliability based on the time of information submission when ensuring the reliability of information. The reliability assurance unit uses the generation AI to analyze changes in reliability based on the time of information submission when ensuring the reliability of information. The generation AI analyzes changes in reliability based on, for example, the submission deadline or the frequency of submission. For example, the reliability assurance unit prioritizes analyzing the reliability of information with an upcoming submission deadline. The generation AI can also postpone analyzing the reliability of information with a distant submission deadline. For example, the reliability assurance unit analyzes the reliability of information based on the submission deadline. Furthermore, the generation AI can comprehensively analyze changes in reliability based on the time of information submission. For example, the reliability assurance unit prioritizes analyzing the reliability of information with an upcoming submission deadline and postpones analyzing the reliability of information with a distant submission deadline. This makes it possible to provide an optimal reliability analysis based on the time of information submission. Some or all of the above-mentioned processing in the reliability assurance unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the reliability assurance unit analyzes the time of information submission using the generation AI, and analyzes changes in reliability based on the results.

[0109] The reliability assurance unit can analyze reliability by referring to the related data of the information when ensuring the reliability of the information. The reliability assurance unit analyzes reliability by referring to the related data of the information when ensuring the reliability of the information using the generation AI. The generation AI analyzes the related data based on, for example, past test results and records of study time. For example, the reliability assurance unit analyzes reliability based on the related data of the information. The generation AI can also prioritize providing highly reliable information from the related data of the information. For example, the reliability assurance unit analyzes reliability based on past test results and records of study time. Furthermore, the generation AI can comprehensively analyze the related data of the information and provide the most reliable information. For example, the reliability assurance unit prioritizes providing highly reliable information based on the related data of the information. This makes it possible to provide an optimal reliability analysis based on the related data of the information. Some or all of the above-mentioned processing in the reliability assurance unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the reliability assurance unit analyzes the related data of the information using the generation AI and analyzes reliability based on the results. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned reception unit, generation unit, provision unit, monitoring unit, identification unit, reliability assurance unit, and emotion estimation unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14, and a parent inputs their child's learning content. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and creates a learning plan using a generation AI. The provision unit is realized by the control unit 46A of the smart device 14, and provides the learning content to the child. The monitoring unit is realized by the specific processing unit 290 of the data processing device 12, and monitors the child's learning progress. The identification unit is realized by the specific processing unit 290 of the data processing device 12, and uses a generation AI to analyze the child's learning data and identify weaknesses. The reliability assurance unit is realized by the specific processing unit 290 of the data processing device 12, and ensures the reliability of the information provided by the generation AI. The emotion estimation unit is realized by the control unit 46A of the smart device 14, and estimates the parent's emotion and adjusts the input method. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned reception unit, generation unit, provision unit, monitoring unit, identification unit, reliability assurance unit, and emotion estimation unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214, and a parent inputs their child's learning content. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and creates a learning plan using a generation AI. The provision unit is realized by the control unit 46A of the smart glasses 214, and provides the learning content to the child. The monitoring unit is realized by the specific processing unit 290 of the data processing device 12, and monitors the child's learning progress. The identification unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the child's learning data using a generation AI and identifies weaknesses. The reliability assurance unit is realized by the specific processing unit 290 of the data processing device 12, and ensures the reliability of the information provided by the generation AI. The emotion estimation unit is realized by the control unit 46A of the smart glasses 214, and estimates the parent's emotion and adjusts the input method. === Hard Collateral 1-3 === Each of the multiple elements, including the reception unit, generation unit, provision unit, monitoring unit, identification unit, reliability assurance unit, and emotion estimation unit, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset-type terminal 314, and a parent inputs their child's learning content. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and creates a learning plan using a generation AI. The provision unit is realized by the control unit 46A of the headset-type terminal 314, and provides the learning content to the child. The monitoring unit is realized by the specific processing unit 290 of the data processing device 12, and monitors the child's learning progress. The identification unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the child's learning data using a generation AI to identify weaknesses. The reliability assurance unit is realized by the specific processing unit 290 of the data processing device 12, and ensures the reliability of the information provided by the generation AI. The emotion estimation unit is realized by the control unit 46A of the headset-type terminal 314, and estimates the parent's emotion and adjusts the input method. === Hard Collateral 1-4 === Each of the multiple elements, including the above-mentioned reception unit, generation unit, provision unit, monitoring unit, identification unit, reliability assurance unit, and emotion estimation unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414, and a parent inputs their child's learning content. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and creates a learning plan using a generation AI. The provision unit is realized by the control unit 46A of the robot 414, and provides the learning content to the child. The monitoring unit is realized by the specific processing unit 290 of the data processing device 12, and monitors the child's learning progress. The identification unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the child's learning data using a generation AI and identifies weaknesses. The reliability assurance unit is realized by the specific processing unit 290 of the data processing device 12, and ensures the reliability of the information provided by the generation AI. The emotion estimation unit is realized by the control unit 46A of the robot 414, and estimates the parent's emotion and adjusts the input method.

[0110] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0111] The tutoring system can further include a dashboard section that visually displays a child's learning progress. The dashboard section displays a child's learning progress in graphs and charts, allowing parents to understand it at a glance. For example, it can display the progress of study time in a line graph, visually showing how much time was spent on each subject. It can also display test results in a bar graph, allowing the scores for each subject to be compared. It can also display the degree of achievement of learning progress in a pie chart, allowing parents to see at a glance how progress is made toward the goal. This makes it easier for parents to intuitively understand their child's learning situation.

[0112] The tutoring system can further include a gamification section to increase children's motivation to learn. The gamification section awards points and badges according to the progress of learning, allowing children to enjoy learning. For example, children can earn points each time they complete a specific task and use those points to purchase virtual items. In addition, they can earn badges each time they complete a certain amount of study time, providing the fun of increasing their collection. Furthermore, a system can be introduced in which children level up according to their progress in learning and new challenges are unlocked. This makes it easier for children to maintain their motivation to learn.

[0113] The tutoring system can further include an environmental adjustment unit to optimize the child's learning environment. The environmental adjustment unit monitors the child's learning environment and provides the optimal environment. For example, it can use sensors to detect the brightness and temperature of the room and adjust the brightness and temperature to an appropriate level. It can also monitor the noise level during learning and provide a noise canceling function as needed. It can also monitor posture during learning and issue alerts to help children maintain good posture. This allows the child to concentrate on their studies.

[0114] The tutoring system can also include a sharing section for sharing children's learning results. The sharing section allows children to share their learning results with family and friends, increasing their motivation to study. For example, learning progress and test results can be automatically shared in a family group chat. It can also provide a function that allows children to post their learning results on social media and compete with friends. Furthermore, learning results can be reported regularly to parents' email addresses, making it easier for parents to keep track of their children's learning status. This makes it easier for children to feel a sense of accomplishment in their studies.

[0115] The tutoring system can further include a content customization unit for providing learning content that matches a child's learning style. The content customization unit provides optimal learning content based on a child's learning style and interests. For example, a visually-oriented child can be provided with content that includes many videos and illustrations. An auditory-oriented child can also be provided with content in the form of audio commentary or podcasts. Furthermore, a hands-on child can be provided with content that includes experiments and fieldwork. This allows children to learn in a way that suits them best.

[0116] The tutoring system may further include an emotion adjustment unit that estimates a child's emotions and adjusts the learning content based on the estimated emotions. The emotion adjustment unit analyzes the child's facial expressions and voice to estimate the child's emotions. For example, if the child is tired, the learning content may be lightened and relaxing content may be provided. Also, if the child is excited, a more difficult challenge may be provided to increase concentration. Furthermore, if the child is stressed, relaxing music or meditation content may be provided. This allows the child to obtain an optimal learning environment according to their emotions.

[0117] The tutoring system may further include an emotion reporting unit that estimates the child's emotions and reports the child's learning progress based on the estimated emotions. The emotion reporting unit analyzes the child's facial expressions and voice to estimate the child's emotions. For example, if the child is relaxed, the emotion reporting unit may report the child's learning progress in positive terms to increase motivation. If the child is stressed, the progress report may be simplified to reduce the child's burden. Furthermore, if the child is excited, the progress report may be provided in a visually stimulating format to keep the child interested. This allows the child to receive the most appropriate progress report according to their emotions.

[0118] The tutoring system may further include an emotion feedback unit that estimates the child's emotion and adjusts learning feedback based on the estimated emotion. The emotion feedback unit analyzes the child's facial expressions and voice to estimate the emotion. For example, if the child is relaxed, detailed feedback can be provided to deepen understanding. Also, if the child is stressed, the feedback can be made brief to reduce the burden on the child. Furthermore, if the child is excited, feedback can be provided in a visually stimulating format to maintain interest. This allows the child to receive optimal feedback according to their emotion.

[0119] The tutoring system may further include an emotional goal setting unit that estimates a child's emotions and sets learning goals based on the estimated emotions. The emotional goal setting unit analyzes the child's facial expressions and voice to estimate emotions. For example, if a child is relaxed, a challenging goal can be set to enhance a sense of accomplishment. Also, if a child is feeling stressed, a realistic and achievable goal can be set to reduce the burden. Furthermore, if a child is excited, a short-term goal can be set to maintain concentration. This allows a child to set optimal learning goals according to their emotions.

[0120] The tutoring system may further include an emotional reward unit that estimates the child's emotions and adjusts learning rewards based on the estimated emotions. The emotional reward unit analyzes the child's facial expressions and voice to estimate emotions. For example, if the child is relaxed, it provides a reward that enhances the child's sense of accomplishment. If the child is feeling stressed, it can provide a relaxing reward to reduce the child's burden. Furthermore, if the child is excited, it can provide a visually stimulating reward to keep the child interested. This allows the child to receive the optimal reward according to their emotions.

[0121] The processing flow of the second embodiment will be briefly explained below.

[0122] Step 1: The reception unit receives input from the parent or guardian about their child's learning. The learning content input by the parent or guardian includes subjects, topics, skills, etc. The reception unit can input learning content in text format or using voice input. It can also provide an optimal input interface based on past input history. Step 2: The generator creates a learning plan based on the information received by the receiver. Using AI, the generator can customize the learning plan to suit the child's learning style and pace. For example, it generates an optimal learning plan based on the child's learning style, such as visual, auditory, or experiential. Step 3: The provision unit provides learning content based on the learning plan created by the generation unit. The provision unit provides learning content through online classes or face-to-face classes, and can adjust the level of detail of the content based on the child's level of understanding. Step 4: The monitoring unit monitors the child's learning progress. The monitoring unit can monitor the child's learning progress through regular checks and real-time monitoring, record the learning progress, and report it to parents.

[0123] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0124] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0125] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0126] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0127] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0128] 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.

[0129] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0130] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0131] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0133] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0134] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0135] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0136] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0137] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0139] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0140] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0141] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0142] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0143] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0144] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0145] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0146] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0147] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0149] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0150] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0151] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0152] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0153] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0154] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0155] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0156] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0157] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0158] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0159] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0160] 7, a 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.

[0161] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0162] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0163] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0164] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0165] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0166] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0167] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0168] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0169] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0170] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0171] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0172] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0173] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0174] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0175] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0176] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0177] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0178] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0179] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0180] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0181] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0182] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0183] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0184] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0185] 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.

[0186] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0187] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0188] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0189] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0190] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0191] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0192] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0193] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0194] [Explanation of symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A reception desk where parents can input their children's learning content; a generation unit that creates a study plan based on the information received by the reception unit; a provision unit that provides learning content based on the learning plan created by the generation unit; A monitoring unit that monitors the learning progress of children. A system characterized by:

2. The generation unit Creating a learning plan using generative AI 2. The system of claim 1.

3. The generation unit Generative AI customizes learning plans to fit each child's learning style and pace 2. The system of claim 1.

4. The monitoring unit Recording children's learning progress and reporting it to parents 2. The system of claim 1.

5. Equipped with a specific section that analyzes children's learning data using generative AI, identifies weak points, and provides focused instruction.

2. The system of claim 1.

6. Equipped with a reliability assurance unit that ensures the reliability of the information provided by the generation AI 2. The system of claim 1.

7. The reception unit Estimate the parent's emotions and adjust the learning content input method based on the estimated parent's emotions 2. The system of claim 1.

8. The reception unit Analyzes the mother's past input history and provides the optimal input interface 2. The system of claim 1.

9. The reception unit Filter learning content based on the mother's current living situation and areas of interest 2. The system of claim 1.

Images