system

Abstract

The system according to this embodiment aims to enable children to easily use AI to advance their learning. [Solution] The system according to the embodiment comprises a reception unit, an analysis unit, a generation unit, a camera analysis unit, and a feedback unit. The reception unit receives input of learning content. The analysis unit analyzes the information received by the reception unit. The generation unit generates prompts based on the information analyzed by the analysis unit. The camera analysis unit analyzes the content read by the camera. The feedback unit provides feedback based on the content analyzed by the camera analysis unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there was a problem that it was difficult to create an appropriate prompt and provide feedback in learning support using AI.

[0005] The system according to the embodiment aims to enable children to easily proceed with learning using AI.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, an analysis unit, a generation unit, a camera analysis unit, and a feedback unit. The reception unit receives input of learning content. The analysis unit analyzes the information received by the reception unit. The generation unit generates prompts based on the information analyzed by the analysis unit. The camera analysis unit analyzes the content read by the camera. The feedback unit provides feedback based on the content analyzed by the camera analysis unit. [Effects of the Invention]

[0007] The system according to this embodiment can enable children to easily use AI to advance their learning. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of 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), or Bluetooth (registered trademark).

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The learning support system according to an embodiment of the present invention is a system that uses AI to support children's learning. In this learning support system, the child inputs what they want to learn, and the AI ​​generates appropriate prompts based on that input and presents them to the child. Furthermore, when the child scans calculation results or handwritten notes with a camera, the AI ​​analyzes the content and provides feedback. This mechanism allows children to learn at their own pace and receive appropriate support. For example, the child inputs what they want to learn. For example, they input specific content such as "I want to solve math problems" or "I want to memorize English vocabulary." This information is input to the AI. Next, the AI ​​analyzes the input information and generates appropriate prompts. For example, if "I want to solve math problems" is input, the AI ​​presents specific problems based on that content. Also, if "I want to memorize English vocabulary" is input, the AI ​​presents a list of words based on that content. Furthermore, when the child scans calculation results or handwritten notes with a camera, the AI ​​analyzes the content. For example, when the child takes a picture of the answer to a math problem they have solved with a camera, the AI ​​analyzes the answer and determines whether it is correct or incorrect. Furthermore, when a child's handwritten English words are photographed with a camera, the AI ​​analyzes the accuracy of their writing and provides feedback. This system allows children to learn at their own pace. For example, after a child solves a problem, the AI ​​analyzes the answer and determines whether it is correct or incorrect, allowing the child to check their level of understanding. The AI ​​also generates appropriate prompts, providing children with support tailored to their learning. In addition, the AI ​​can record the child's learning history and manage their progress. For example, it can record lists of problems the child has solved and words they have memorized, which can be used to help with future learning. This allows children to check their learning progress and learn efficiently towards their goals. In this way, the AI-powered learning support system is customized to the child's age and learning content, allowing children to learn at their own pace. Moreover, the camera-based analysis function provides real-time feedback on the child's learning, enabling effective learning.This allows the learning support system to effectively assist children's learning and manage their learning progress.

[0029] The learning support system according to this embodiment comprises a reception unit, an analysis unit, a generation unit, a camera analysis unit, and a feedback unit. The reception unit receives input from the child regarding the content they wish to learn. For example, the child can input specific content such as "I want to solve math problems" or "I want to memorize English vocabulary." The analysis unit analyzes the information received by the reception unit. For example, the analysis unit performs analysis based on the input information to determine the child's learning level and goals. The generation unit generates appropriate prompts based on the information analyzed by the analysis unit. For example, if the child inputs "I want to solve math problems," the generation unit generates specific math problems. Also, if the child inputs "I want to memorize English vocabulary," the generation unit generates a list of words. The camera analysis unit analyzes the content captured by the camera. For example, the camera analysis unit photographs the child's answer to a math problem and analyzes the answer to determine if it is correct or incorrect. Also, the camera analysis unit photographs the child's written English words and analyzes the accuracy of their writing. The feedback unit provides feedback based on the content analyzed by the camera analysis unit. For example, the feedback unit provides feedback on whether a child has solved a math problem correctly, displaying a message of praise if the answer is correct and providing an explanation if it is incorrect. The feedback unit also provides feedback on the accuracy of English words written by the child, displaying a message of praise if the word is written correctly and teaching the correct way to write it if it is incorrect. In this way, the learning support system according to this embodiment can effectively support a child's learning and manage their learning progress.

[0030] The reception desk allows children to input what they want to learn. For example, children can input specific details such as "I want to solve math problems" or "I want to memorize English vocabulary." This allows children to clarify what they want to learn and provide that information to the AI. Some or all of the above processing in the reception desk may be performed using the AI, or not. For example, the reception desk can input the content entered by the child into a generating AI, which can then analyze the content and generate an appropriate prompt.

[0031] The generation unit can generate appropriate prompts using AI. For example, if a child inputs "I want to solve a math problem," the generation unit will generate a specific math problem. For example, the generation unit will generate a problem appropriate to the child's learning level and present it to the child. Also, if a child inputs "I want to memorize English words," the generation unit will generate a list of words. For example, the generation unit will select words appropriate to the child's learning goals and present them as a list. In this way, the generation unit can generate appropriate prompts that match the child's learning content. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input the content entered by the child into a generation AI, which will analyze the content and generate an appropriate prompt.

[0032] The camera analysis unit can analyze calculation results or handwritten notes captured by the camera. For example, the camera analysis unit can photograph the answer to a math problem solved by a child and analyze the answer to determine if it is correct or incorrect. For example, the camera analysis unit can use image analysis technology to extract mathematical formulas from the captured image and compare them with the correct answer. The camera analysis unit can also photograph English words written by a child and analyze the accuracy of the handwriting. For example, the camera analysis unit can use character recognition technology to extract characters from the captured image and compare them with the correct spelling. In this way, the camera analysis unit can analyze the content captured by the child and determine if it is correct or incorrect. Some or all of the above processing in the camera analysis unit may be performed using AI, for example, or without AI. For example, the camera analysis unit can input the captured image data into a generating AI, which can then analyze its content and determine if it is correct or incorrect.

[0033] The feedback unit can provide feedback based on the analysis results. For example, the feedback unit can provide feedback on whether a child has solved a math problem correctly, displaying a message of praise if the answer is correct and providing an explanation if it is incorrect. For example, the feedback unit can display messages such as "That's correct! Well done!" or "Unfortunately, that's incorrect. The correct answer is XX." The feedback unit can also provide feedback on the accuracy of English words written by the child, displaying a message of praise if they are written correctly and teaching the correct way to write them if they are written incorrectly. For example, the feedback unit can display messages such as "You wrote it correctly! Excellent!" or "That's wrong. The correct spelling is XX." In this way, the feedback unit can provide appropriate feedback based on the analysis results. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input the analysis results into a generating AI, which can then analyze the content and generate appropriate feedback.

[0034] The feedback unit can record a child's learning history and manage their progress. For example, the feedback unit can record lists of problems the child has solved and words they have memorized, to help with future learning. For instance, the feedback unit can record whether a child has solved math problems correctly or a list of English words they have memorized, to refer to during future learning. The feedback unit also manages the child's learning progress and supports them in efficiently progressing towards their goals. For example, the feedback unit can display the child's progress towards their set learning goals and check their level of achievement. This allows the feedback unit to record the child's learning history and manage their progress. Some or all of the above processes in the feedback unit may be performed using AI, for example, or not. For example, the feedback unit can input the child's learning history into a generating AI, which can then analyze the content and manage their progress.

[0035] The reception desk can analyze a child's past learning history and select the optimal input method. For example, if a child has preferred using voice input in the past, the reception desk will prioritize suggesting voice input. For example, the reception desk will display a message such as, "Let's try using voice input." The reception desk can also set text input as the default input method if a child has frequently used text input in the past. For example, the reception desk will display a message such as, "Let's try using text input." Furthermore, if a child has studied during a specific time period in the past, the reception desk can suggest an input method that matches that time period. For example, the reception desk will display a message such as, "Let's start studying during this time period." This allows the reception desk to select the optimal input method based on the child's past learning history. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input the child's past learning history data into a generating AI, which can then analyze the data and select the optimal input method.

[0036] The reception unit can filter learning content based on the child's current learning progress and areas of interest when inputting learning content. For example, the reception unit can prioritize displaying problems related to the child's current learning content. For example, the reception unit can display a message such as, "Let's solve problems related to your current learning content." The reception unit can also prioritize suggesting learning content related to areas of interest the child. For example, the reception unit can display a message such as, "Let's learn about learning content related to your areas of interest." The reception unit can also filter and display problems of appropriate difficulty according to the child's learning progress. For example, the reception unit can display a message such as, "Let's solve problems according to your current learning progress." In this way, the reception unit can filter learning content based on the child's current learning progress and areas of interest. Some or all of the above processing in the reception unit may be performed using AI, or not. For example, the reception unit can input the child's learning progress data and areas of interest data into a generating AI, which can analyze the content and filter appropriate learning content.

[0037] The reception desk can prioritize inputting highly relevant content by considering the child's geographical location when inputting learning content. For example, if the child lives in a specific region, the reception desk will prioritize displaying history and geography questions related to that region. For example, the reception desk may display a message such as, "Let's solve history questions related to your region." The reception desk can also prioritize suggesting learning content related to the travel destination if the child is traveling. For example, the reception desk may display a message such as, "Let's learn about learning content related to your travel destination." The reception desk can also prioritize displaying learning content related to the school's curriculum if the child attends a specific school. For example, the reception desk may display a message such as, "Let's learn about learning content related to your school's curriculum." In this way, the reception desk can prioritize inputting highly relevant learning content based on the child's geographical location. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the child's geographical location data into a generating AI, which can analyze the content and select highly relevant learning content.

[0038] The reception desk can analyze a child's social media activity when inputting learning content and input relevant content. For example, the reception desk can suggest learning content related to topics the child has shown interest in on social media. For example, the reception desk can display a message such as, "Let's learn about topics you're interested in on social media." The reception desk can also suggest learning content based on information from educational accounts the child follows on social media. For example, the reception desk can display a message such as, "We'll suggest learning content based on information from the educational accounts you follow." The reception desk can also display relevant problems based on learning content the child has shared on social media. For example, the reception desk can display a message such as, "Let's solve problems related to the learning content you shared." This allows the reception desk to input relevant learning content based on the child's social media activity. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the child's social media activity data into a generating AI, which can analyze the content and select relevant learning content.

[0039] The analysis unit can adjust the level of detail of the analysis based on the importance of the learning content during the analysis. For example, the analysis unit can display detailed analysis results for learning content of high importance. For example, the analysis unit can display a message such as, "This is high-importance content, so we will display detailed analysis results." The analysis unit can also display concise analysis results for learning content of low importance. For example, the analysis unit can display a message such as, "This is low-importance content, so we will display concise analysis results." The analysis unit can also adjust the display order of the analysis results according to the importance of the learning content. For example, the analysis unit can display a message such as, "High-importance content will be displayed preferentially." In this way, the analysis unit can adjust the level of detail of the analysis based on the importance of the learning content. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input learning content importance data into a generating AI, and the generating AI can analyze that content to adjust the level of detail of the analysis.

[0040] The analysis unit can apply different analysis algorithms depending on the category of the learning content during analysis. For example, for arithmetic problems, the analysis unit can apply a numerical analysis algorithm. For example, the analysis unit can display a message such as, "Applying a numerical analysis algorithm to arithmetic problems." The analysis unit can also apply a natural language processing algorithm to English words. For example, the analysis unit can display a message such as, "Applying a natural language processing algorithm to English words." The analysis unit can also apply a data analysis algorithm to science experiment results. For example, the analysis unit can display a message such as, "Applying a data analysis algorithm to science experiment results." This allows the analysis unit to apply an appropriate analysis algorithm depending on the category of the learning content. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the category data of the learning content into a generating AI, which can then analyze the content and apply an appropriate analysis algorithm.

[0041] The analysis unit can determine the priority of analysis based on the submission dates of the learning materials during the analysis process. For example, the analysis unit will prioritize the analysis of learning materials with approaching submission deadlines. For example, the analysis unit will display a message such as, "Since the submission deadline is approaching, we will prioritize the analysis." The analysis unit can also postpone the analysis of learning materials with distant submission deadlines. For example, the analysis unit will display a message such as, "Since the submission deadline is far away, we will postpone the analysis." The analysis unit can also adjust the level of detail of the analysis according to the submission date. For example, the analysis unit will display a message such as, "We will adjust the level of detail of the analysis according to the submission date." This allows the analysis unit to determine the priority of analysis based on the submission dates of the learning materials. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input learning material submission date data into a generating AI, which can then analyze the data to determine the priority of analysis.

[0042] The analysis unit can adjust the order of analysis based on the relevance of the learned content during analysis. For example, the analysis unit can prioritize the analysis of highly relevant learned content. For example, the analysis unit can display a message such as, "We will prioritize the analysis of highly relevant content." The analysis unit can also postpone the analysis of less relevant learned content. For example, the analysis unit can display a message such as, "We will postpone the analysis of less relevant content." The analysis unit can also adjust the display order of the analysis results according to the relevance of the learned content. For example, the analysis unit can display a message such as, "We will prioritize the display of highly relevant content." In this way, the analysis unit can adjust the order of analysis based on the relevance of the learned content. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input data on the relevance of the learned content into a generating AI, and the generating AI can analyze that data to adjust the order of analysis.

[0043] The generation unit can adjust the level of detail of prompts based on the importance of the learning content when generating prompts. For example, the generation unit generates detailed prompts for highly important learning content. For example, the generation unit displays a message such as, "This is highly important content, so a detailed prompt will be displayed." The generation unit can also generate concise prompts for less important learning content. For example, the generation unit displays a message such as, "This is less important content, so a concise prompt will be displayed." The generation unit can also adjust the display order of prompts according to the importance of the learning content. For example, the generation unit displays a message such as, "Highly important content will be displayed first." In this way, the generation unit can adjust the level of detail of prompts based on the importance of the learning content. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input learning content importance data into a generation AI, which can then analyze the data and adjust the level of detail of the prompts.

[0044] The generation unit can apply different generation algorithms depending on the category of learning content when generating prompts. For example, for arithmetic problems, the generation unit can apply a numerical analysis algorithm to generate prompts. For example, the generation unit can display a message such as, "Applying a numerical analysis algorithm to arithmetic problems." The generation unit can also apply a natural language processing algorithm to generate prompts for English words. For example, the generation unit can display a message such as, "Applying a natural language processing algorithm to English words." The generation unit can also apply a data analysis algorithm to generate prompts for science experiment results. For example, the generation unit can display a message such as, "Applying a data analysis algorithm to science experiment results." This allows the generation unit to apply an appropriate generation algorithm depending on the category of learning content. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input learning content category data into a generation AI, which can analyze the content and apply an appropriate generation algorithm.

[0045] The generation unit can determine the priority of prompts based on the submission timing of the learning content when generating prompts. For example, the generation unit will prioritize generating prompts for learning content with an approaching submission deadline. For example, the generation unit will display a message such as, "Since the submission deadline is approaching, we will prioritize generating a prompt." The generation unit can also postpone generating prompts for learning content with a distant submission deadline. For example, the generation unit will display a message such as, "Since the submission deadline is far away, we will postpone generating a prompt." The generation unit can also adjust the level of detail of the prompts according to the submission timing. For example, the generation unit will display a message such as, "The level of detail of the prompt will be adjusted according to the submission timing." This allows the generation unit to determine the priority of prompts based on the submission timing of the learning content. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input learning content submission timing data into a generation AI, which can then analyze the data to determine the priority of prompts.

[0046] The generation unit can adjust the order of prompts based on the relevance of the learned content when generating prompts. For example, the generation unit will prioritize generating prompts for highly relevant learned content. For example, the generation unit will display a message such as, "Prompts will be generated preferentially for highly relevant content." The generation unit can also postpone generating prompts for less relevant learned content. For example, the generation unit will display a message such as, "Prompts will be generated for less relevant content." The generation unit can also adjust the display order of prompts according to the relevance of the learned content. For example, the generation unit will display a message such as, "Highly relevant content will be displayed preferentially." In this way, the generation unit can adjust the order of prompts based on the relevance of the learned content. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input data on the relevance of the learned content into a generation AI, which can then analyze the data and adjust the order of prompts.

[0047] The camera analysis unit can improve the accuracy of its analysis by considering the interrelationships of learned content during camera analysis. For example, for arithmetic problems, the camera analysis unit performs analysis by considering the interrelationships of mathematical formulas. For example, the camera analysis unit displays a message such as, "We will analyze the arithmetic problem considering the interrelationships of mathematical formulas." The camera analysis unit can also perform analysis of English words by considering the interrelationships of context. For example, the camera analysis unit displays a message such as, "We will analyze the English words considering the interrelationships of context." The camera analysis unit can also perform analysis of science experiment results by considering the interrelationships of data. For example, the camera analysis unit displays a message such as, "We will analyze the science experiment results considering the interrelationships of data." This allows the camera analysis unit to improve the accuracy of its analysis by considering the interrelationships of learned content. Some or all of the above processing in the camera analysis unit may be performed using AI, for example, or without AI. For example, the camera analysis unit can input data on the interrelationships of learned content into a generating AI, and the generating AI can analyze that content to improve the accuracy of the analysis.

[0048] The camera analysis unit can perform analysis while considering the attribute information of the person submitting the learning content. For example, the camera analysis unit can perform analysis at an appropriate difficulty level according to the child's age. For example, the camera analysis unit can display a message such as, "Analyzing at an appropriate difficulty level according to age." The camera analysis unit can also perform analysis considering the child's level of understanding of the learning content according to their grade level. For example, the camera analysis unit can display a message such as, "Analyzing at an appropriate level of understanding according to their grade level." The camera analysis unit can also select the optimal analysis method according to the child's learning style. For example, the camera analysis unit can display a message such as, "Selecting an analysis method according to your learning style." In this way, the camera analysis unit can perform analysis while considering the attribute information of the person submitting the learning content. Some or all of the above processing in the camera analysis unit may be performed using AI, for example, or without using AI. For example, the camera analysis unit can input the submitter's attribute information data into a generating AI, and the generating AI can analyze the content and select an appropriate analysis method.

[0049] The camera analysis unit can perform camera analysis while considering the geographical distribution of learning content. For example, if a child lives in a specific area, the camera analysis unit will prioritize analyzing learning content related to that area. For example, the camera analysis unit will display a message such as, "We will prioritize analyzing learning content related to your area." The camera analysis unit can also prioritize analyzing learning content related to the travel destination if the child is traveling. For example, the camera analysis unit will display a message such as, "We will prioritize analyzing learning content related to your travel destination." The camera analysis unit can also prioritize analyzing learning content related to the curriculum of a specific school if the child attends that school. For example, the camera analysis unit will display a message such as, "We will prioritize analyzing learning content related to the school curriculum." This allows the camera analysis unit to perform analysis while considering the geographical distribution of learning content. Some or all of the above processing in the camera analysis unit may be performed using AI, for example, or without AI. For example, the camera analysis unit can input geographical distribution data into a generating AI, which can analyze the content and select an appropriate analysis method.

[0050] The camera analysis unit can improve the accuracy of its analysis by referring to relevant literature related to the learning content during camera analysis. For example, for arithmetic problems, the camera analysis unit performs analysis by referring to relevant textbooks and reference books. For example, the camera analysis unit displays a message such as, "We will analyze the arithmetic problem by referring to relevant textbooks." The camera analysis unit can also perform analysis by referring to relevant dictionaries and grammar books for English words. For example, the camera analysis unit displays a message such as, "We will analyze the English word by referring to relevant dictionaries." The camera analysis unit can also perform analysis by referring to relevant research papers and databases for science experiment results. For example, the camera analysis unit displays a message such as, "We will analyze the science experiment results by referring to relevant research papers." This allows the camera analysis unit to improve the accuracy of its analysis by referring to relevant literature related to the learning content. Some or all of the above processing in the camera analysis unit may be performed using AI, for example, or without AI. For example, the camera analysis unit can input relevant literature data into a generating AI, and the generating AI can analyze its contents to improve the accuracy of the analysis.

[0051] The feedback unit can optimize the current feedback by referring to past feedback data when providing feedback. For example, the feedback unit can provide feedback in a format that is easy for children to understand, based on past feedback data. For example, the feedback unit can display a message such as, "We will provide feedback in an easy-to-understand format based on past feedback data." The feedback unit can also provide feedback that focuses on areas where the child struggles, based on past feedback data. For example, the feedback unit can display a message such as, "We will provide feedback that focuses on areas where the child struggles, based on past feedback data." The feedback unit can also provide feedback that is tailored to the child's learning progress, based on past feedback data. For example, the feedback unit can display a message such as, "We will provide feedback tailored to the child's learning progress, based on past feedback data." This allows the feedback unit to optimize the current feedback by referring to past feedback data. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input past feedback data into a generating AI, which can then analyze its contents to optimize the current feedback.

[0052] The feedback unit can apply different feedback methods to each category of learning content during the feedback process. For example, for math problems, the feedback unit provides feedback based on numerical analysis. For instance, the feedback unit displays a message such as, "We will provide feedback based on numerical analysis for math problems." The feedback unit can also provide feedback based on grammar and pronunciation for English vocabulary. For example, the feedback unit displays a message such as, "We will provide feedback based on grammar and pronunciation for English vocabulary." The feedback unit can also provide feedback based on data analysis for science experiment results. For example, the feedback unit displays a message such as, "We will provide feedback based on data analysis for science experiment results." This allows the feedback unit to apply an appropriate feedback method to each category of learning content. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input learning content category data into a generating AI, which can then analyze the data and apply an appropriate feedback method.

[0053] The feedback unit can analyze changes in feedback based on the submission timing of the learning content. For example, the feedback unit can prioritize providing feedback for learning content with an approaching submission deadline. For example, the feedback unit can display a message such as, "Since the submission deadline is approaching, we will prioritize providing feedback." The feedback unit can also postpone providing feedback for learning content with a distant submission deadline. For example, the feedback unit can display a message such as, "Since the submission deadline is far away, we will postpone providing feedback." The feedback unit can also adjust the level of detail of the feedback according to the submission timing. For example, the feedback unit can display a message such as, "We will adjust the level of detail of the feedback according to the submission timing." This allows the feedback unit to analyze changes in feedback based on the submission timing of the learning content. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input submission timing data into a generating AI, and the generating AI can analyze the content to analyze changes in feedback.

[0054] The feedback unit can analyze feedback by referring to relevant market data related to the learning content during the feedback process. For example, for math problems, the feedback unit provides feedback based on relevant market data. For example, the feedback unit displays a message such as, "We will provide feedback on math problems based on relevant market data." The feedback unit can also provide feedback on English vocabulary based on relevant market data. For example, the feedback unit displays a message such as, "We will provide feedback on English vocabulary based on relevant market data." The feedback unit can also provide feedback on science experiment results based on relevant market data. For example, the feedback unit displays a message such as, "We will provide feedback on science experiment results based on relevant market data." This allows the feedback unit to analyze feedback by referring to relevant market data related to the learning content. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input relevant market data into a generating AI, and the generating AI can analyze its contents to analyze the feedback.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The analysis unit can analyze a child's learning history and improve the accuracy of the analysis based on past learning patterns. For example, it can analyze the types of problems a child has struggled with in the past and analyze current problems based on those types. For example, it may display a message such as, "We will analyze considering the types of problems a child has struggled with in the past." It can also analyze the types of problems a child has excelled at in the past and analyze current problems based on those types. For example, it may display a message such as, "We will analyze considering the types of problems a child has excelled at in the past." Furthermore, it can adjust the level of detail of the analysis according to the child's learning progress. For example, it may display a message such as, "We will adjust the level of detail of the analysis according to the child's learning progress." In this way, the analysis unit can improve the accuracy of the analysis based on the child's learning history.

[0057] The generation unit can generate prompts while considering the child's learning goals. For example, if a child is studying for a specific exam, it can prioritize generating questions related to that exam. For example, it might display a message such as, "Prioritizing questions related to the exam." Similarly, if a child wants to acquire a specific skill, it can prioritize generating questions related to that skill. For example, it might display a message such as, "Prioritizing questions related to skill acquisition." Furthermore, it can adjust the difficulty level of the prompts according to the child's learning pace. For example, it might display a message such as, "Adjusting the difficulty level of the prompts according to the learning pace." This allows the generation unit to generate optimal prompts based on the child's learning goals.

[0058] The camera analysis unit can improve the accuracy of its analysis by taking into account the child's learning environment. For example, if the child is learning in a quiet environment, it can perform a detailed analysis to improve accuracy. For example, it might display a message such as, "Since the child is learning in a quiet environment, a detailed analysis will be performed." If the child is learning in a noisy environment, it can perform a simplified analysis to maintain accuracy. For example, it might display a message such as, "Since the child is learning in a noisy environment, a simplified analysis will be performed." Furthermore, if the child is learning outdoors, it can perform an analysis that takes environmental fluctuations into account. For example, it might display a message such as, "Since the child is learning outdoors, the analysis will take environmental fluctuations into account." In this way, the camera analysis unit can improve the accuracy of its analysis based on the child's learning environment.

[0059] The reception desk can customize the input method for learning content based on the child's learning history. For example, if the child has preferred using voice input in the past, it can prioritize suggesting voice input. For instance, it might display a message such as, "Let's try using voice input." Similarly, if the child has frequently used text input in the past, it can set text input as the default input method. For example, it might display a message such as, "Let's try using text input." Furthermore, if the child has studied during specific time slots in the past, it can suggest an input method tailored to those times. For example, it might display a message such as, "Let's start studying during this time slot." This allows the reception desk to select the optimal input method based on the child's past learning history.

[0060] The analysis unit can monitor a child's learning progress in real time and adjust the analysis method according to that progress. For example, if a child is progressing well, it can perform a detailed analysis. For instance, it might display a message such as, "The child is progressing well, so we will perform a detailed analysis." If a child is struggling, it can perform a concise analysis. For example, it might display a message such as, "The child is struggling, so we will perform a concise analysis." Furthermore, it can adjust the frequency of analysis according to the child's learning pace. For example, it might display a message such as, "The frequency of analysis will be adjusted according to the learning pace." In this way, the analysis unit can provide the optimal analysis method based on the child's learning progress.

[0061] The generation unit can adjust the difficulty level of learning content based on the child's learning history. For example, it can set the difficulty level of the current problem based on the child's past correct answer rate. For example, it might display a message such as, "The difficulty level of the current problem will be set based on the child's past correct answer rate." It can also prioritize generating problems in areas the child has struggled with in the past. For example, it might display a message such as, "Problems in areas the child has struggled with in the past will be prioritized." Furthermore, it can adjust the difficulty level of the problems according to the child's learning goals. For example, it might display a message such as, "The difficulty level of the problems will be adjusted according to the child's learning goals." In this way, the generation unit can provide optimal learning content based on the child's learning history.

[0062] The camera analysis unit can improve the accuracy of its analysis based on the child's learning history. For example, it can analyze the trends in problems the child has solved in the past and analyze the current problem based on those trends. For example, it may display a message such as, "We will analyze considering the trends in past problems." It can also analyze the trends in problems the child has excelled at in the past and analyze the current problem based on those trends. For example, it may display a message such as, "We will analyze considering the trends in problems the child has excelled at in the past." Furthermore, it can adjust the level of detail of the analysis according to the child's learning progress. For example, it may display a message such as, "We will adjust the level of detail of the analysis according to the child's learning progress." In this way, the camera analysis unit can improve the accuracy of its analysis based on the child's learning history.

[0063] The feedback system can customize the content of feedback based on the child's learning history. For example, it can provide feedback that focuses on areas the child has struggled with in the past. For instance, it might display a message such as, "We will provide feedback that focuses on areas the child has struggled with in the past." It can also provide feedback that praises areas the child has excelled at in the past. For example, it might display a message such as, "We will provide feedback that praises areas the child has excelled at in the past." Furthermore, it can adjust the level of detail of the feedback according to the child's learning progress. For example, it might display a message such as, "We will adjust the level of detail of the feedback according to the child's learning progress." This allows the feedback system to provide optimal feedback based on the child's learning history.

[0064] The following briefly describes the processing flow for example form 1.

[0065] Step 1: The reception desk inputs what the child wants to learn. For example, the child can input specific details such as "I want to solve math problems" or "I want to memorize English vocabulary." Step 2: The analysis unit analyzes the information received by the reception unit. For example, the analysis unit performs an analysis based on the input information, tailored to the child's learning level and goals. Step 3: The generation unit generates appropriate prompts based on the information analyzed by the analysis unit. For example, if the child inputs "I want to solve a math problem," the generation unit will generate a specific math problem. Also, if the child inputs "I want to memorize English words," the generation unit will generate a list of words. Step 4: The camera analysis unit analyzes the content captured by the camera. For example, the camera analysis unit takes a picture of a child's answer to a math problem and analyzes the answer to determine if it is correct or incorrect. The camera analysis unit also takes a picture of an English word written by a child and analyzes the accuracy of the writing. Step 5: The feedback unit provides feedback based on the analysis performed by the camera analysis unit. For example, the feedback unit provides feedback on whether the child's math problems were correct or incorrect, displaying a message of praise if correct and providing an explanation if incorrect. The feedback unit also provides feedback on the accuracy of the English words the child has written, displaying a message of praise if they are written correctly and teaching the correct way to write them if they are written incorrectly.

[0066] (Example of form 2) The learning support system according to an embodiment of the present invention is a system that uses AI to support children's learning. In this learning support system, the child inputs what they want to learn, and the AI ​​generates appropriate prompts based on that input and presents them to the child. Furthermore, when the child scans calculation results or handwritten notes with a camera, the AI ​​analyzes the content and provides feedback. This mechanism allows children to learn at their own pace and receive appropriate support. For example, the child inputs what they want to learn. For example, they input specific content such as "I want to solve math problems" or "I want to memorize English vocabulary." This information is input to the AI. Next, the AI ​​analyzes the input information and generates appropriate prompts. For example, if "I want to solve math problems" is input, the AI ​​presents specific problems based on that content. Also, if "I want to memorize English vocabulary" is input, the AI ​​presents a list of words based on that content. Furthermore, when the child scans calculation results or handwritten notes with a camera, the AI ​​analyzes the content. For example, when the child takes a picture of the answer to a math problem they have solved with a camera, the AI ​​analyzes the answer and determines whether it is correct or incorrect. Furthermore, when a child's handwritten English words are photographed with a camera, the AI ​​analyzes the accuracy of their writing and provides feedback. This system allows children to learn at their own pace. For example, after a child solves a problem, the AI ​​analyzes the answer and determines whether it is correct or incorrect, allowing the child to check their level of understanding. The AI ​​also generates appropriate prompts, providing children with support tailored to their learning. In addition, the AI ​​can record the child's learning history and manage their progress. For example, it can record lists of problems the child has solved and words they have memorized, which can be used to help with future learning. This allows children to check their learning progress and learn efficiently towards their goals. In this way, the AI-powered learning support system is customized to the child's age and learning content, allowing children to learn at their own pace. Moreover, the camera-based analysis function provides real-time feedback on the child's learning, enabling effective learning.This allows the learning support system to effectively assist children's learning and manage their learning progress.

[0067] The learning support system according to this embodiment comprises a reception unit, an analysis unit, a generation unit, a camera analysis unit, and a feedback unit. The reception unit receives input from the child regarding the content they wish to learn. For example, the child can input specific content such as "I want to solve math problems" or "I want to memorize English vocabulary." The analysis unit analyzes the information received by the reception unit. For example, the analysis unit performs analysis based on the input information to determine the child's learning level and goals. The generation unit generates appropriate prompts based on the information analyzed by the analysis unit. For example, if the child inputs "I want to solve math problems," the generation unit generates specific math problems. Also, if the child inputs "I want to memorize English vocabulary," the generation unit generates a list of words. The camera analysis unit analyzes the content captured by the camera. For example, the camera analysis unit photographs the child's answer to a math problem and analyzes the answer to determine if it is correct or incorrect. Also, the camera analysis unit photographs the child's written English words and analyzes the accuracy of their writing. The feedback unit provides feedback based on the content analyzed by the camera analysis unit. For example, the feedback unit provides feedback on whether a child has solved a math problem correctly, displaying a message of praise if the answer is correct and providing an explanation if it is incorrect. The feedback unit also provides feedback on the accuracy of English words written by the child, displaying a message of praise if the word is written correctly and teaching the correct way to write it if it is incorrect. In this way, the learning support system according to this embodiment can effectively support a child's learning and manage their learning progress.

[0068] The reception desk allows children to input what they want to learn. For example, children can input specific details such as "I want to solve math problems" or "I want to memorize English vocabulary." This allows children to clarify what they want to learn and provide that information to the AI. Some or all of the above processing in the reception desk may be performed using the AI, or not. For example, the reception desk can input the content entered by the child into a generating AI, which can then analyze the content and generate an appropriate prompt.

[0069] The generation unit can generate appropriate prompts using AI. For example, if a child inputs "I want to solve a math problem," the generation unit will generate a specific math problem. For example, the generation unit will generate a problem appropriate to the child's learning level and present it to the child. Also, if a child inputs "I want to memorize English words," the generation unit will generate a list of words. For example, the generation unit will select words appropriate to the child's learning goals and present them as a list. In this way, the generation unit can generate appropriate prompts that match the child's learning content. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input the content entered by the child into a generation AI, which will analyze the content and generate an appropriate prompt.

[0070] The camera analysis unit can analyze calculation results or handwritten notes captured by the camera. For example, the camera analysis unit can photograph the answer to a math problem solved by a child and analyze the answer to determine if it is correct or incorrect. For example, the camera analysis unit can use image analysis technology to extract mathematical formulas from the captured image and compare them with the correct answer. The camera analysis unit can also photograph English words written by a child and analyze the accuracy of the handwriting. For example, the camera analysis unit can use character recognition technology to extract characters from the captured image and compare them with the correct spelling. In this way, the camera analysis unit can analyze the content captured by the child and determine if it is correct or incorrect. Some or all of the above processing in the camera analysis unit may be performed using AI, for example, or without AI. For example, the camera analysis unit can input the captured image data into a generating AI, which can then analyze its content and determine if it is correct or incorrect.

[0071] The feedback unit can provide feedback based on the analysis results. For example, the feedback unit can provide feedback on whether a child has solved a math problem correctly, displaying a message of praise if the answer is correct and providing an explanation if it is incorrect. For example, the feedback unit can display messages such as "That's correct! Well done!" or "Unfortunately, that's incorrect. The correct answer is XX." The feedback unit can also provide feedback on the accuracy of English words written by the child, displaying a message of praise if they are written correctly and teaching the correct way to write them if they are written incorrectly. For example, the feedback unit can display messages such as "You wrote it correctly! Excellent!" or "That's wrong. The correct spelling is XX." In this way, the feedback unit can provide appropriate feedback based on the analysis results. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input the analysis results into a generating AI, which can then analyze the content and generate appropriate feedback.

[0072] The feedback unit can record a child's learning history and manage their progress. For example, the feedback unit can record lists of problems the child has solved and words they have memorized, to help with future learning. For instance, the feedback unit can record whether a child has solved math problems correctly or a list of English words they have memorized, to refer to during future learning. The feedback unit also manages the child's learning progress and supports them in efficiently progressing towards their goals. For example, the feedback unit can display the child's progress towards their set learning goals and check their level of achievement. This allows the feedback unit to record the child's learning history and manage their progress. Some or all of the above processes in the feedback unit may be performed using AI, for example, or not. For example, the feedback unit can input the child's learning history into a generating AI, which can then analyze the content and manage their progress.

[0073] The reception system can estimate a child's emotions and adjust the timing of learning content input based on the estimated emotions. For example, if the child is tired, the reception system can display a message encouraging a break and temporarily delay the input of learning content. For example, the reception system might display a message such as, "Let's take a short break. Let's refresh ourselves before continuing." The reception system can also adjust the input of learning content if the child is excited, playing relaxing music to improve concentration. For example, the reception system might play relaxing music and wait for the child to calm down. Furthermore, if the child is stressed, the reception system can adjust the timing of learning content input by starting with easy questions and gradually increasing the difficulty. For example, the reception system might display a message such as, "Let's start with easy questions," and gradually increase the difficulty. In this way, the reception system can adjust the timing of learning content input based on the child's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the reception area may be performed using AI, for example, or without AI. For example, the reception area can input child emotional data into a generating AI, which can then analyze the data and adjust the timing of inputting learning content.

[0074] The reception desk can analyze a child's past learning history and select the optimal input method. For example, if a child has preferred using voice input in the past, the reception desk will prioritize suggesting voice input. For example, the reception desk will display a message such as, "Let's try using voice input." The reception desk can also set text input as the default input method if a child has frequently used text input in the past. For example, the reception desk will display a message such as, "Let's try using text input." Furthermore, if a child has studied during a specific time period in the past, the reception desk can suggest an input method that matches that time period. For example, the reception desk will display a message such as, "Let's start studying during this time period." This allows the reception desk to select the optimal input method based on the child's past learning history. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input the child's past learning history data into a generating AI, which can then analyze the data and select the optimal input method.

[0075] The reception unit can filter learning content based on the child's current learning progress and areas of interest when inputting learning content. For example, the reception unit can prioritize displaying problems related to the child's current learning content. For example, the reception unit can display a message such as, "Let's solve problems related to your current learning content." The reception unit can also prioritize suggesting learning content related to areas of interest the child. For example, the reception unit can display a message such as, "Let's learn about learning content related to your areas of interest." The reception unit can also filter and display problems of appropriate difficulty according to the child's learning progress. For example, the reception unit can display a message such as, "Let's solve problems according to your current learning progress." In this way, the reception unit can filter learning content based on the child's current learning progress and areas of interest. Some or all of the above processing in the reception unit may be performed using AI, or not. For example, the reception unit can input the child's learning progress data and areas of interest data into a generating AI, which can analyze the content and filter appropriate learning content.

[0076] The reception unit can estimate the child's emotions and determine the priority of the learning content to be input based on the estimated emotions. For example, if the child is tired, the reception unit may prioritize displaying easy problems. For example, the reception unit may display a message such as, "Let's start with easy problems." The reception unit may also prioritize displaying more difficult problems to improve the child's concentration if the child is excited. For example, the reception unit may display a message such as, "Let's try some difficult problems." The reception unit may also display balanced problems if the child is relaxed. For example, the reception unit may display a message such as, "Let's solve some balanced problems." In this way, the reception unit can determine the priority of learning content based on the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception desk can input children's emotional data into a generating AI, which can then analyze the data to determine the priority of learning content.

[0077] The reception desk can prioritize inputting highly relevant content by considering the child's geographical location when inputting learning content. For example, if the child lives in a specific region, the reception desk will prioritize displaying history and geography questions related to that region. For example, the reception desk may display a message such as, "Let's solve history questions related to your region." The reception desk can also prioritize suggesting learning content related to the travel destination if the child is traveling. For example, the reception desk may display a message such as, "Let's learn about learning content related to your travel destination." The reception desk can also prioritize displaying learning content related to the school's curriculum if the child attends a specific school. For example, the reception desk may display a message such as, "Let's learn about learning content related to your school's curriculum." In this way, the reception desk can prioritize inputting highly relevant learning content based on the child's geographical location. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the child's geographical location data into a generating AI, which can analyze the content and select highly relevant learning content.

[0078] The reception desk can analyze a child's social media activity when inputting learning content and input relevant content. For example, the reception desk can suggest learning content related to topics the child has shown interest in on social media. For example, the reception desk can display a message such as, "Let's learn about topics you're interested in on social media." The reception desk can also suggest learning content based on information from educational accounts the child follows on social media. For example, the reception desk can display a message such as, "We'll suggest learning content based on information from the educational accounts you follow." The reception desk can also display relevant problems based on learning content the child has shared on social media. For example, the reception desk can display a message such as, "Let's solve problems related to the learning content you shared." This allows the reception desk to input relevant learning content based on the child's social media activity. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the child's social media activity data into a generating AI, which can analyze the content and select relevant learning content.

[0079] The analysis unit can estimate the child's emotions and adjust the presentation of the analysis based on the estimated emotions. For example, if the child is nervous, the analysis unit displays a simple and visually easy-to-understand analysis result. For example, the analysis unit may display a message such as, "You seem nervous. We will display a simple analysis result." The analysis unit can also display a detailed analysis result if the child is relaxed. For example, the analysis unit may display a message such as, "You seem relaxed. We will display a detailed analysis result." The analysis unit can also display an analysis result with a visually stimulating effect if the child is excited. For example, the analysis unit may display a message such as, "You seem excited. We will display a visually stimulating analysis result." In this way, the analysis unit can adjust the presentation of the analysis based on the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input child emotional data into a generating AI, which can then analyze the data and adjust the way the analysis is presented.

[0080] The analysis unit can adjust the level of detail of the analysis based on the importance of the learning content during the analysis. For example, the analysis unit can display detailed analysis results for learning content of high importance. For example, the analysis unit can display a message such as, "This is high-importance content, so we will display detailed analysis results." The analysis unit can also display concise analysis results for learning content of low importance. For example, the analysis unit can display a message such as, "This is low-importance content, so we will display concise analysis results." The analysis unit can also adjust the display order of the analysis results according to the importance of the learning content. For example, the analysis unit can display a message such as, "High-importance content will be displayed preferentially." In this way, the analysis unit can adjust the level of detail of the analysis based on the importance of the learning content. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input learning content importance data into a generating AI, and the generating AI can analyze that content to adjust the level of detail of the analysis.

[0081] The analysis unit can apply different analysis algorithms depending on the category of the learning content during analysis. For example, for arithmetic problems, the analysis unit can apply a numerical analysis algorithm. For example, the analysis unit can display a message such as, "Applying a numerical analysis algorithm to arithmetic problems." The analysis unit can also apply a natural language processing algorithm to English words. For example, the analysis unit can display a message such as, "Applying a natural language processing algorithm to English words." The analysis unit can also apply a data analysis algorithm to science experiment results. For example, the analysis unit can display a message such as, "Applying a data analysis algorithm to science experiment results." This allows the analysis unit to apply an appropriate analysis algorithm depending on the category of the learning content. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the category data of the learning content into a generating AI, which can then analyze the content and apply an appropriate analysis algorithm.

[0082] The analysis unit can estimate the child's emotions and adjust the length of the analysis based on the estimated emotions. For example, if the child is in a hurry, the analysis unit will display a short, concise analysis result. For example, the analysis unit will display a message such as, "You seem to be in a hurry. Here is a short, concise analysis result." The analysis unit can also display a detailed analysis result if the child is relaxed. For example, the analysis unit will display a message such as, "You seem to be relaxed. Here is a detailed analysis result." The analysis unit can also display an analysis result with visually stimulating effects if the child is excited. For example, the analysis unit will display a message such as, "You seem to be excited. Here is a visually stimulating analysis result." This allows the analysis unit to adjust the length of the analysis based on the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input child emotional data into a generating AI, which can then analyze the data and adjust the length of the analysis.

[0083] The analysis unit can determine the priority of analysis based on the submission dates of the learning materials during the analysis process. For example, the analysis unit will prioritize the analysis of learning materials with approaching submission deadlines. For example, the analysis unit will display a message such as, "Since the submission deadline is approaching, we will prioritize the analysis." The analysis unit can also postpone the analysis of learning materials with distant submission deadlines. For example, the analysis unit will display a message such as, "Since the submission deadline is far away, we will postpone the analysis." The analysis unit can also adjust the level of detail of the analysis according to the submission date. For example, the analysis unit will display a message such as, "We will adjust the level of detail of the analysis according to the submission date." This allows the analysis unit to determine the priority of analysis based on the submission dates of the learning materials. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input learning material submission date data into a generating AI, which can then analyze the data to determine the priority of analysis.

[0084] The analysis unit can adjust the order of analysis based on the relevance of the learned content during analysis. For example, the analysis unit can prioritize the analysis of highly relevant learned content. For example, the analysis unit can display a message such as, "We will prioritize the analysis of highly relevant content." The analysis unit can also postpone the analysis of less relevant learned content. For example, the analysis unit can display a message such as, "We will postpone the analysis of less relevant content." The analysis unit can also adjust the display order of the analysis results according to the relevance of the learned content. For example, the analysis unit can display a message such as, "We will prioritize the display of highly relevant content." In this way, the analysis unit can adjust the order of analysis based on the relevance of the learned content. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input data on the relevance of the learned content into a generating AI, and the generating AI can analyze that data to adjust the order of analysis.

[0085] The generation unit can estimate a child's emotions and adjust the way it presents the generated prompts based on the estimated emotions. For example, if the child is nervous, the generation unit can generate a simple and visually clear prompt. For example, it might display a message such as, "You seem nervous. Here's a simple prompt." The generation unit can also generate a detailed prompt if the child is relaxed. For example, it might display a message such as, "You seem relaxed. Here's a detailed prompt." The generation unit can also generate a prompt with visually stimulating effects if the child is excited. For example, it might display a message such as, "You seem excited. Here's a visually stimulating prompt." This allows the generation unit to adjust the way it presents prompts based on the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input child emotional data into the generation AI, which can then analyze the data and adjust how the prompts are expressed.

[0086] The generation unit can adjust the level of detail of prompts based on the importance of the learning content when generating prompts. For example, the generation unit generates detailed prompts for highly important learning content. For example, the generation unit displays a message such as, "This is highly important content, so a detailed prompt will be displayed." The generation unit can also generate concise prompts for less important learning content. For example, the generation unit displays a message such as, "This is less important content, so a concise prompt will be displayed." The generation unit can also adjust the display order of prompts according to the importance of the learning content. For example, the generation unit displays a message such as, "Highly important content will be displayed first." In this way, the generation unit can adjust the level of detail of prompts based on the importance of the learning content. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input learning content importance data into a generation AI, which can then analyze the data and adjust the level of detail of the prompts.

[0087] The generation unit can apply different generation algorithms depending on the category of learning content when generating prompts. For example, for arithmetic problems, the generation unit can apply a numerical analysis algorithm to generate prompts. For example, the generation unit can display a message such as, "Applying a numerical analysis algorithm to arithmetic problems." The generation unit can also apply a natural language processing algorithm to generate prompts for English words. For example, the generation unit can display a message such as, "Applying a natural language processing algorithm to English words." The generation unit can also apply a data analysis algorithm to generate prompts for science experiment results. For example, the generation unit can display a message such as, "Applying a data analysis algorithm to science experiment results." This allows the generation unit to apply an appropriate generation algorithm depending on the category of learning content. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input learning content category data into a generation AI, which can analyze the content and apply an appropriate generation algorithm.

[0088] The generation unit can estimate the child's emotions and adjust the length of the prompt based on the estimated emotions. For example, if the child is in a hurry, the generation unit will generate a short, concise prompt. For example, the generation unit will display a message such as, "You seem to be in a hurry. Here is a short, concise prompt." The generation unit can also generate a detailed prompt if the child is relaxed. For example, the generation unit will display a message such as, "You seem to be relaxed. Here is a detailed prompt." The generation unit can also generate a prompt with a visually stimulating effect if the child is excited. For example, the generation unit will display a message such as, "You seem to be excited. Here is a visually stimulating prompt." This allows the generation unit to adjust the length of the prompt based on the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input child emotional data into the generation AI, which can then analyze the data and adjust the length of the prompt.

[0089] The generation unit can determine the priority of prompts based on the submission timing of the learning content when generating prompts. For example, the generation unit will prioritize generating prompts for learning content with an approaching submission deadline. For example, the generation unit will display a message such as, "Since the submission deadline is approaching, we will prioritize generating a prompt." The generation unit can also postpone generating prompts for learning content with a distant submission deadline. For example, the generation unit will display a message such as, "Since the submission deadline is far away, we will postpone generating a prompt." The generation unit can also adjust the level of detail of the prompts according to the submission timing. For example, the generation unit will display a message such as, "The level of detail of the prompt will be adjusted according to the submission timing." This allows the generation unit to determine the priority of prompts based on the submission timing of the learning content. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input learning content submission timing data into a generation AI, which can then analyze the data to determine the priority of prompts.

[0090] The generation unit can adjust the order of prompts based on the relevance of the learned content when generating prompts. For example, the generation unit will prioritize generating prompts for highly relevant learned content. For example, the generation unit will display a message such as, "Prompts will be generated preferentially for highly relevant content." The generation unit can also postpone generating prompts for less relevant learned content. For example, the generation unit will display a message such as, "Prompts will be generated for less relevant content." The generation unit can also adjust the display order of prompts according to the relevance of the learned content. For example, the generation unit will display a message such as, "Highly relevant content will be displayed preferentially." In this way, the generation unit can adjust the order of prompts based on the relevance of the learned content. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input data on the relevance of the learned content into a generation AI, which can then analyze the data and adjust the order of prompts.

[0091] The camera analysis unit can estimate the child's emotions and adjust the camera analysis criteria based on the estimated emotions. For example, if the child is nervous, the camera analysis unit displays a simple and visually easy-to-understand analysis result. For example, the camera analysis unit may display a message such as, "You seem nervous. We will display a simple analysis result." The camera analysis unit can also display a detailed analysis result if the child is relaxed. For example, the camera analysis unit may display a message such as, "You seem relaxed. We will display a detailed analysis result." The camera analysis unit can also display an analysis result with a visually stimulating effect if the child is excited. For example, the camera analysis unit may display a message such as, "You seem excited. We will display a visually stimulating analysis result." This allows the camera analysis unit to adjust the camera analysis criteria based on the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the camera analysis unit may be performed using AI, for example, or without AI. For example, the camera analysis unit can input child emotional data into a generating AI, which can then analyze the data and adjust the criteria for camera analysis.

[0092] The camera analysis unit can improve the accuracy of its analysis by considering the interrelationships of learned content during camera analysis. For example, for arithmetic problems, the camera analysis unit performs analysis by considering the interrelationships of mathematical formulas. For example, the camera analysis unit displays a message such as, "We will analyze the arithmetic problem considering the interrelationships of mathematical formulas." The camera analysis unit can also perform analysis of English words by considering the interrelationships of context. For example, the camera analysis unit displays a message such as, "We will analyze the English words considering the interrelationships of context." The camera analysis unit can also perform analysis of science experiment results by considering the interrelationships of data. For example, the camera analysis unit displays a message such as, "We will analyze the science experiment results considering the interrelationships of data." This allows the camera analysis unit to improve the accuracy of its analysis by considering the interrelationships of learned content. Some or all of the above processing in the camera analysis unit may be performed using AI, for example, or without AI. For example, the camera analysis unit can input data on the interrelationships of learned content into a generating AI, and the generating AI can analyze that content to improve the accuracy of the analysis.

[0093] The camera analysis unit can perform analysis while considering the attribute information of the person submitting the learning content. For example, the camera analysis unit can perform analysis at an appropriate difficulty level according to the child's age. For example, the camera analysis unit can display a message such as, "Analyzing at an appropriate difficulty level according to age." The camera analysis unit can also perform analysis considering the child's level of understanding of the learning content according to their grade level. For example, the camera analysis unit can display a message such as, "Analyzing at an appropriate level of understanding according to their grade level." The camera analysis unit can also select the optimal analysis method according to the child's learning style. For example, the camera analysis unit can display a message such as, "Selecting an analysis method according to your learning style." In this way, the camera analysis unit can perform analysis while considering the attribute information of the person submitting the learning content. Some or all of the above processing in the camera analysis unit may be performed using AI, for example, or without using AI. For example, the camera analysis unit can input the submitter's attribute information data into a generating AI, and the generating AI can analyze the content and select an appropriate analysis method.

[0094] The camera analysis unit can estimate a child's emotions and adjust the order in which it displays the camera analysis results based on the estimated emotions. For example, if a child is nervous, the camera analysis unit will prioritize displaying simple and visually easy-to-understand analysis results. For example, the camera analysis unit may display a message such as, "You seem nervous. We will prioritize displaying simple analysis results." The camera analysis unit can also prioritize displaying detailed analysis results if the child is relaxed. For example, the camera analysis unit may display a message such as, "You seem relaxed. We will prioritize displaying detailed analysis results." The camera analysis unit can also prioritize displaying analysis results with visually stimulating effects if the child is excited. For example, the camera analysis unit may display a message such as, "You seem excited. We will prioritize displaying visually stimulating analysis results." In this way, the camera analysis unit can adjust the order in which it displays the camera analysis results based on the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the camera analysis unit may be performed using AI, for example, or without AI. For example, the camera analysis unit can input child emotion data into a generating AI, which can then analyze the data and adjust the display order of the analysis results.

[0095] The camera analysis unit can perform camera analysis while considering the geographical distribution of learning content. For example, if a child lives in a specific area, the camera analysis unit will prioritize analyzing learning content related to that area. For example, the camera analysis unit will display a message such as, "We will prioritize analyzing learning content related to your area." The camera analysis unit can also prioritize analyzing learning content related to the travel destination if the child is traveling. For example, the camera analysis unit will display a message such as, "We will prioritize analyzing learning content related to your travel destination." The camera analysis unit can also prioritize analyzing learning content related to the curriculum of a specific school if the child attends that school. For example, the camera analysis unit will display a message such as, "We will prioritize analyzing learning content related to the school curriculum." This allows the camera analysis unit to perform analysis while considering the geographical distribution of learning content. Some or all of the above processing in the camera analysis unit may be performed using AI, for example, or without AI. For example, the camera analysis unit can input geographical distribution data into a generating AI, which can analyze the content and select an appropriate analysis method.

[0096] The camera analysis unit can improve the accuracy of its analysis by referring to relevant literature related to the learning content during camera analysis. For example, for arithmetic problems, the camera analysis unit performs analysis by referring to relevant textbooks and reference books. For example, the camera analysis unit displays a message such as, "We will analyze the arithmetic problem by referring to relevant textbooks." The camera analysis unit can also perform analysis by referring to relevant dictionaries and grammar books for English words. For example, the camera analysis unit displays a message such as, "We will analyze the English word by referring to relevant dictionaries." The camera analysis unit can also perform analysis by referring to relevant research papers and databases for science experiment results. For example, the camera analysis unit displays a message such as, "We will analyze the science experiment results by referring to relevant research papers." This allows the camera analysis unit to improve the accuracy of its analysis by referring to relevant literature related to the learning content. Some or all of the above processing in the camera analysis unit may be performed using AI, for example, or without AI. For example, the camera analysis unit can input relevant literature data into a generating AI, and the generating AI can analyze its contents to improve the accuracy of the analysis.

[0097] The feedback unit can estimate the child's emotions and adjust how the feedback is displayed based on the estimated emotions. For example, if the child is nervous, the feedback unit can display simple and visually easy-to-understand feedback. For example, the feedback unit can display a message such as, "You seem nervous. Here is some simple feedback." The feedback unit can also display detailed feedback if the child is relaxed. For example, the feedback unit can display a message such as, "You seem relaxed. Here is some detailed feedback." The feedback unit can also display feedback with visually stimulating effects if the child is excited. For example, the feedback unit can display a message such as, "You seem excited. Here is some visually stimulating feedback." In this way, the feedback unit can adjust how the feedback is displayed based on the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input child emotional data into a generating AI, which can then analyze the data and adjust how the feedback is displayed.

[0098] The feedback unit can optimize the current feedback by referring to past feedback data when providing feedback. For example, the feedback unit can provide feedback in a format that is easy for children to understand, based on past feedback data. For example, the feedback unit can display a message such as, "We will provide feedback in an easy-to-understand format based on past feedback data." The feedback unit can also provide feedback that focuses on areas where the child struggles, based on past feedback data. For example, the feedback unit can display a message such as, "We will provide feedback that focuses on areas where the child struggles, based on past feedback data." The feedback unit can also provide feedback that is tailored to the child's learning progress, based on past feedback data. For example, the feedback unit can display a message such as, "We will provide feedback tailored to the child's learning progress, based on past feedback data." This allows the feedback unit to optimize the current feedback by referring to past feedback data. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input past feedback data into a generating AI, which can then analyze its contents to optimize the current feedback.

[0099] The feedback unit can apply different feedback methods to each category of learning content during the feedback process. For example, for math problems, the feedback unit provides feedback based on numerical analysis. For instance, the feedback unit displays a message such as, "We will provide feedback based on numerical analysis for math problems." The feedback unit can also provide feedback based on grammar and pronunciation for English vocabulary. For example, the feedback unit displays a message such as, "We will provide feedback based on grammar and pronunciation for English vocabulary." The feedback unit can also provide feedback based on data analysis for science experiment results. For example, the feedback unit displays a message such as, "We will provide feedback based on data analysis for science experiment results." This allows the feedback unit to apply an appropriate feedback method to each category of learning content. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input learning content category data into a generating AI, which can then analyze the data and apply an appropriate feedback method.

[0100] The feedback unit can estimate the child's emotions and adjust the importance of feedback based on the estimated emotions. For example, if the child is nervous, the feedback unit will prioritize displaying high-importance feedback. For instance, it might display a message such as, "You seem nervous. We will prioritize displaying high-importance feedback." The feedback unit can also prioritize displaying detailed feedback if the child is relaxed. For example, it might display a message such as, "You seem relaxed. We will prioritize displaying detailed feedback." The feedback unit can also prioritize displaying feedback with visually stimulating effects if the child is excited. For example, it might display a message such as, "You seem excited. We will prioritize displaying visually stimulating feedback." In this way, the feedback unit can adjust the importance of feedback based on the child's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input the child's emotional data into a generating AI, which can then analyze the data and adjust the importance of the feedback.

[0101] The feedback unit can analyze changes in feedback based on the submission timing of the learning content. For example, the feedback unit can prioritize providing feedback for learning content with an approaching submission deadline. For example, the feedback unit can display a message such as, "Since the submission deadline is approaching, we will prioritize providing feedback." The feedback unit can also postpone providing feedback for learning content with a distant submission deadline. For example, the feedback unit can display a message such as, "Since the submission deadline is far away, we will postpone providing feedback." The feedback unit can also adjust the level of detail of the feedback according to the submission timing. For example, the feedback unit can display a message such as, "We will adjust the level of detail of the feedback according to the submission timing." This allows the feedback unit to analyze changes in feedback based on the submission timing of the learning content. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input submission timing data into a generating AI, and the generating AI can analyze the content to analyze changes in feedback.

[0102] The feedback unit can analyze feedback by referring to relevant market data related to the learning content during the feedback process. For example, for math problems, the feedback unit provides feedback based on relevant market data. For example, the feedback unit displays a message such as, "We will provide feedback on math problems based on relevant market data." The feedback unit can also provide feedback on English vocabulary based on relevant market data. For example, the feedback unit displays a message such as, "We will provide feedback on English vocabulary based on relevant market data." The feedback unit can also provide feedback on science experiment results based on relevant market data. For example, the feedback unit displays a message such as, "We will provide feedback on science experiment results based on relevant market data." This allows the feedback unit to analyze feedback by referring to relevant market data related to the learning content. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input relevant market data into a generating AI, and the generating AI can analyze its contents to analyze the feedback. === Hard Collateral 1-1 === Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, camera analysis unit, and feedback unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit receives input from the child using the touch panel 38A or microphone 38B of the smart device 14. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the input information. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates appropriate prompts based on the analysis results. The camera analysis unit uses the camera 42 of the smart device 14 to photograph the child's notebook or calculation results and analyze their contents. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides feedback based on the analysis results. === Hard Collateral 1-2 === Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, camera analysis unit, and feedback unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit receives input from a child using the microphone 238 of the smart glasses 214. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the input information. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates appropriate prompts based on the analysis results. The camera analysis unit uses the camera 42 of the smart glasses 214 to photograph the child's notebook or calculation results and analyze their contents. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides feedback based on the analysis results. === Hard Collateral 1-3 === Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, camera analysis unit, and feedback unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit receives input from the child using the microphone 238 of the headset terminal 314. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the input information. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates appropriate prompts based on the analysis results. The camera analysis unit uses the camera 42 of the headset terminal 314 to photograph the child's notebook or calculation results and analyze their contents. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides feedback based on the analysis results. === Hard Collateral 1-4 === Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, camera analysis unit, and feedback unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the reception unit receives input from a child using the microphone 238 of the robot 414. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the input information. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates appropriate prompts based on the analysis results. The camera analysis unit uses the camera 42 of the robot 414 to photograph the child's notebook or calculation results and analyze their contents. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides feedback based on the analysis results.

[0103] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0104] The reception desk can estimate a child's learning style and adjust the input method of learning content based on that estimate. For example, if a child is a visual learner, the reception desk can prioritize presenting learning content that uses images and videos. For example, it might display a message such as, "For visual learners, let's use video materials." If a child is an auditory learner, it can prioritize presenting learning content that uses audio and music. For example, it might display a message such as, "For auditory learners, let's use audio materials." Furthermore, if a child is an experiential learner, it can suggest activities that involve hands-on learning. For example, it might display a message such as, "For experiential learners, let's learn by actually doing." In this way, the reception desk can provide the optimal input method of learning content based on the child's learning style.

[0105] The analysis unit can analyze a child's learning history and improve the accuracy of the analysis based on past learning patterns. For example, it can analyze the types of problems a child has struggled with in the past and analyze current problems based on those types. For example, it may display a message such as, "We will analyze considering the types of problems a child has struggled with in the past." It can also analyze the types of problems a child has excelled at in the past and analyze current problems based on those types. For example, it may display a message such as, "We will analyze considering the types of problems a child has excelled at in the past." Furthermore, it can adjust the level of detail of the analysis according to the child's learning progress. For example, it may display a message such as, "We will adjust the level of detail of the analysis according to the child's learning progress." In this way, the analysis unit can improve the accuracy of the analysis based on the child's learning history.

[0106] The generation unit can generate prompts while considering the child's learning goals. For example, if a child is studying for a specific exam, it can prioritize generating questions related to that exam. For example, it might display a message such as, "Prioritizing questions related to the exam." Similarly, if a child wants to acquire a specific skill, it can prioritize generating questions related to that skill. For example, it might display a message such as, "Prioritizing questions related to skill acquisition." Furthermore, it can adjust the difficulty level of the prompts according to the child's learning pace. For example, it might display a message such as, "Adjusting the difficulty level of the prompts according to the learning pace." This allows the generation unit to generate optimal prompts based on the child's learning goals.

[0107] The camera analysis unit can improve the accuracy of its analysis by taking into account the child's learning environment. For example, if the child is learning in a quiet environment, it can perform a detailed analysis to improve accuracy. For example, it might display a message such as, "Since the child is learning in a quiet environment, a detailed analysis will be performed." If the child is learning in a noisy environment, it can perform a simplified analysis to maintain accuracy. For example, it might display a message such as, "Since the child is learning in a noisy environment, a simplified analysis will be performed." Furthermore, if the child is learning outdoors, it can perform an analysis that takes environmental fluctuations into account. For example, it might display a message such as, "Since the child is learning outdoors, the analysis will take environmental fluctuations into account." In this way, the camera analysis unit can improve the accuracy of its analysis based on the child's learning environment.

[0108] The feedback unit can estimate a child's learning motivation and adjust the content of the feedback based on that estimate. For example, if a child is highly motivated, it can provide challenging feedback. For instance, it might display a message such as, "You are highly motivated, so we will provide challenging feedback." If a child is less motivated, it can provide encouraging feedback. For example, it might display a message such as, "You are less motivated, so we will provide encouraging feedback." Furthermore, if a child is moderately motivated, it can provide balanced feedback. For example, it might display a message such as, "Your motivation is moderate, so we will provide balanced feedback." In this way, the feedback unit can provide optimal feedback based on the child's learning motivation.

[0109] The reception desk can customize the input method for learning content based on the child's learning history. For example, if the child has preferred using voice input in the past, it can prioritize suggesting voice input. For instance, it might display a message such as, "Let's try using voice input." Similarly, if the child has frequently used text input in the past, it can set text input as the default input method. For example, it might display a message such as, "Let's try using text input." Furthermore, if the child has studied during specific time slots in the past, it can suggest an input method tailored to those times. For example, it might display a message such as, "Let's start studying during this time slot." This allows the reception desk to select the optimal input method based on the child's past learning history.

[0110] The analysis unit can monitor a child's learning progress in real time and adjust the analysis method according to that progress. For example, if a child is progressing well, it can perform a detailed analysis. For instance, it might display a message such as, "The child is progressing well, so we will perform a detailed analysis." If a child is struggling, it can perform a concise analysis. For example, it might display a message such as, "The child is struggling, so we will perform a concise analysis." Furthermore, it can adjust the frequency of analysis according to the child's learning pace. For example, it might display a message such as, "The frequency of analysis will be adjusted according to the learning pace." In this way, the analysis unit can provide the optimal analysis method based on the child's learning progress.

[0111] The generation unit can adjust the difficulty level of learning content based on the child's learning history. For example, it can set the difficulty level of the current problem based on the child's past correct answer rate. For example, it might display a message such as, "The difficulty level of the current problem will be set based on the child's past correct answer rate." It can also prioritize generating problems in areas the child has struggled with in the past. For example, it might display a message such as, "Problems in areas the child has struggled with in the past will be prioritized." Furthermore, it can adjust the difficulty level of the problems according to the child's learning goals. For example, it might display a message such as, "The difficulty level of the problems will be adjusted according to the child's learning goals." In this way, the generation unit can provide optimal learning content based on the child's learning history.

[0112] The camera analysis unit can improve the accuracy of its analysis based on the child's learning history. For example, it can analyze the trends in problems the child has solved in the past and analyze the current problem based on those trends. For example, it may display a message such as, "We will analyze considering the trends in past problems." It can also analyze the trends in problems the child has excelled at in the past and analyze the current problem based on those trends. For example, it may display a message such as, "We will analyze considering the trends in problems the child has excelled at in the past." Furthermore, it can adjust the level of detail of the analysis according to the child's learning progress. For example, it may display a message such as, "We will adjust the level of detail of the analysis according to the child's learning progress." In this way, the camera analysis unit can improve the accuracy of its analysis based on the child's learning history.

[0113] The feedback system can customize the content of feedback based on the child's learning history. For example, it can provide feedback that focuses on areas the child has struggled with in the past. For instance, it might display a message such as, "We will provide feedback that focuses on areas the child has struggled with in the past." It can also provide feedback that praises areas the child has excelled at in the past. For example, it might display a message such as, "We will provide feedback that praises areas the child has excelled at in the past." Furthermore, it can adjust the level of detail of the feedback according to the child's learning progress. For example, it might display a message such as, "We will adjust the level of detail of the feedback according to the child's learning progress." This allows the feedback system to provide optimal feedback based on the child's learning history.

[0114] The following briefly describes the processing flow for example form 2.

[0115] Step 1: The reception desk inputs what the child wants to learn. For example, the child can input specific details such as "I want to solve math problems" or "I want to memorize English vocabulary." Step 2: The analysis unit analyzes the information received by the reception unit. For example, the analysis unit performs an analysis based on the input information, tailored to the child's learning level and goals. Step 3: The generation unit generates appropriate prompts based on the information analyzed by the analysis unit. For example, if the child inputs "I want to solve a math problem," the generation unit will generate a specific math problem. Also, if the child inputs "I want to memorize English words," the generation unit will generate a list of words. Step 4: The camera analysis unit analyzes the content captured by the camera. For example, the camera analysis unit takes a picture of a child's answer to a math problem and analyzes the answer to determine if it is correct or incorrect. The camera analysis unit also takes a picture of an English word written by a child and analyzes the accuracy of the writing. Step 5: The feedback unit provides feedback based on the analysis performed by the camera analysis unit. For example, the feedback unit provides feedback on whether the child's math problems were correct or incorrect, displaying a message of praise if correct and providing an explanation if incorrect. The feedback unit also provides feedback on the accuracy of the English words the child has written, displaying a message of praise if they are written correctly and teaching the correct way to write them if they are written incorrectly.

[0116] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0117] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (for example, still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or Naive Bayes, and can perform a variety of operations, but is not limited to these examples. Furthermore, AI may also be an AI agent. Also, when the operations described above are performed by AI, the operations may be performed partially or entirely by AI, but is not limited to these examples. Additionally, operations performed by AI, including generative AI, may be replaced by rule-based operations, and rule-based operations may be replaced by operations performed by AI, including generative AI.

[0118] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0119] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0120] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0121] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0122] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0123] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0124] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0125] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0126] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0127] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0128] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0129] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0130] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0131] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0132] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0133] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0134] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0135] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0136] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0137] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0138] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0139] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0140] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0141] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0142] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0143] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0144] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0145] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0146] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0147] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0148] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0149] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0150] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0151] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0152] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0153] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0154] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0155] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0156] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0157] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0158] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0159] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0160] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0161] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0162] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0163] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0164] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0165] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0166] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0167] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0168] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0169] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0170] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0171] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0172] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0173] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0174] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0175] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0176] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0177] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0178] 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.

[0179] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0180] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0181] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0182] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0183] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0184] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0185] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0186] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0187] [Explanation of Symbols]

[0188] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception area that accepts input of learning content, An analysis unit that analyzes the information received by the reception unit, A generation unit that generates a prompt based on the information analyzed by the analysis unit, The camera analysis unit analyzes the content read by the camera, The camera analysis unit provides feedback based on the analysis performed by the camera analysis unit. A system characterized by the following features.

2. The aforementioned reception unit is Enter the content your child wants to learn. The system according to feature 1.

3. The generating unit is AI generates appropriate prompts. The system according to feature 1.

4. The camera analysis unit, Analyze calculation results scanned by a camera or handwritten notes. The system according to feature 1.

5. The aforementioned feedback unit is Provide feedback based on the analysis results. The system according to feature 1.

6. The aforementioned feedback unit is Record your child's learning history and manage their progress. The system according to feature 1.

7. The aforementioned reception unit is The system estimates the child's emotions and adjusts the timing of inputting learning content based on those estimated emotions. The system according to feature 1.

8. The aforementioned reception unit is Analyze the child's past learning history and select an input method. The system according to feature 1.

9. The aforementioned reception unit is When inputting learning content, filtering is performed based on the child's current learning progress and areas of interest. The system according to feature 1.

10. The aforementioned reception unit is The system estimates the child's emotions and determines the priority of the learning content to be input based on the estimated emotions. The system according to feature 1.

Images