System

Abstract

An object of the system according to the embodiment is to provide support for children to efficiently solve homework and deepen their understanding.SOLUTION: A system includes a homework transmission part, a correct answer determination part, a feedback provision part, a question answer part, a progress tracking part, a tutor cooperation part, and a self-learning support part. The homework transmission unit transmits a homework. The correct answer determination unit determines a correct answer to the homework assignment transmitted by the homework assignment transmission unit. The feedback providing unit provides feedback based on the result determined by the correct answer determining unit. The question answering unit answers a question about homework. The progress tracking unit tracks the understanding level and progress of each child. The tutor collaboration unit supports collaboration with an online tutor as necessary. The self-learning facilitator provides hints and means for self-learning.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies do not provide sufficient support for children to efficiently solve homework and deepen their understanding, and there is room for improvement.

[0005] The system according to the embodiment aims to provide support for children to efficiently solve their homework and deepen their understanding. [Means for solving the problem]

[0006] The system according to the embodiment includes a homework sending unit, a correct answer determination unit, a feedback providing unit, a question and answer unit, a progress tracking unit, a tutor collaboration unit, and a self-study support unit. The homework sending unit sends homework. The correct answer determination unit determines the correct answer for the homework sent by the homework sending unit. The feedback providing unit provides feedback based on the result determined by the correct answer determination unit. The question and answering unit answers questions about the homework. The progress tracking unit tracks each child's level of understanding and progress. The tutor collaboration unit supports collaboration with online tutors as needed. The self-study support unit provides hints and tools for self-study. [Effects of the Invention]

[0007] The system according to the embodiment can provide support for children to efficiently solve their homework and deepen their understanding. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A homework support system according to an embodiment of the present invention allows children to submit their homework, and a generation AI determines the correct answers, provides feedback, answers questions, tracks comprehension and progress, supports collaboration with online tutors, and provides self-study tips, thereby providing comprehensive homework and learning support for children.

[0029] A homework assistance system according to an embodiment includes a homework sending unit, a correct answer determination unit, a feedback providing unit, a question and answer unit, a progress tracking unit, a tutor collaboration unit, and a self-study support unit. The homework sending unit allows children to submit their homework. For example, homework can be submitted in the form of a photo or text. The correct answer determination unit determines the correct answer for the homework submitted by the homework sending unit. For example, a generation AI analyzes the content of the homework and determines the correct answer. The feedback providing unit provides feedback based on the results determined by the correct answer determination unit. For example, it provides specific correction methods for incorrectly answered questions. The question and answering unit answers questions about the homework. For example, the generation AI provides appropriate answers to children's questions. The progress tracking unit tracks each child's level of understanding and progress. For example, the generation AI analyzes children's learning progress and identifies skill gaps. The tutor collaboration unit supports collaboration with online tutors as needed. For example, it suggests consulting an online tutor if a specific problem cannot be solved. The self-study support unit provides hints and methods for self-study. For example, generative AI can provide children with self-study advice, allowing the homework support system to provide comprehensive homework and learning support for children.

[0030] The homework sending unit can automatically determine the difficulty of the homework and provide feedback according to the difficulty. For example, when homework is sent, the generating AI analyzes the content of the homework and automatically determines the difficulty. For example, for a math problem, the difficulty is assessed based on the complexity of the problem and the number of calculation steps. To provide feedback according to the difficulty, the generating AI refers to past data and learns feedback for homework of similar difficulty. For example, it provides detailed explanations for difficult problems. When determining the difficulty of homework, the generating AI takes into account the child's past grades and answer history to provide an individually customized difficulty assessment. For example, if the child has struggled with similar problems in the past, it will set the difficulty higher. This makes it possible to provide appropriate feedback according to the difficulty of the homework.

[0031] The homework sending unit can automatically generate similar problems based on the content of the homework and provide additional practice problems. For example, after homework is submitted, the homework sending unit automatically generates similar problems based on the content of the submitted homework using a generation AI. For example, if it is a math problem, it will generate another problem using the same calculation method. When generating similar problems, the generation AI takes into account the child's level of understanding and provides problems of appropriate difficulty. For example, it provides problems in stages, from basic to applied problems. To automatically generate similar problems, the generation AI refers to a large problem database and selects the most appropriate problems. For example, it provides the most effective practice problems based on past homework data. This provides additional practice problems, thereby deepening children's understanding.

[0032] The homework sending unit can accept voice input, allowing children to verbally explain the contents of their homework. For example, the homework sending unit adds a function to the generation AI to accept voice input when sending homework. For example, a child verbally explains the contents of their homework using a microphone. The generation AI analyzes the voice input and converts it into text data. For example, it uses voice recognition technology to automatically transcribe the child's explanation. Based on the voice input, the generation AI understands the contents of the homework and determines the correct answer. For example, it analyzes a math problem that has been explained verbally and checks the calculation process and answer. This allows children to verbally explain the contents of their homework.

[0033] The homework sending unit can automatically suggest video tutorials related to the homework content. For example, after homework is sent, the generating AI in the homework sending unit analyzes the content of the homework and automatically suggests related video tutorials. For example, if it is a math problem, it will suggest a video that explains how to calculate it. When suggesting video tutorials, the generating AI takes into account the child's level of understanding and selects videos at an appropriate level. For example, it may suggest content in stages, from basic to applied. The generating AI references a large video database and selects the optimal video tutorial. For example, it may suggest the most effective video based on past homework data. This automatically suggests related video tutorials, deepening children's understanding.

[0034] The feedback providing unit can refer to the child's past answer history and provide individually customized feedback. For example, when providing feedback, the generation AI analyzes the child's past answer history and provides individually customized feedback. For example, it provides detailed explanations for questions that have been answered incorrectly in the past. The generation AI provides feedback to strengthen specific weaknesses based on the child's learning history. For example, if there is a lack of understanding in a particular area, it provides feedback that focuses on that area. The generation AI refers to the child's past answer history and suggests an individually customized study plan. For example, it suggests the optimal study method based on past grades. In this way, by providing individually customized feedback, children's learning effectiveness is improved.

[0035] The feedback providing unit can visually and aurally optimize the content of the feedback to suit the child's learning style. For example, to visually optimize the content of the feedback, the generation AI may use graphs and diagrams to provide explanations. For example, for a math problem, the calculation process may be illustrated. To provide auditorily optimized feedback, the generation AI may provide audio explanations. For example, the child may be able to listen to the feedback audio. The generation AI may provide a combination of visual and audio feedback to suit the child's learning style. For example, visual diagrams and audio explanations may be provided simultaneously. This improves learning effectiveness by providing feedback that suits the child's learning style.

[0036] The feedback providing unit can provide links to related reference books and websites when providing feedback. For example, when providing feedback, the generation AI provides links to related reference books. For example, if it is a math problem, it displays a link to a reference book that explains the calculation method in detail. The generation AI provides links to related websites so that children can access additional learning resources. For example, if it is a science problem, it displays a link to a website that features experiment videos. Depending on the content of the feedback, the generation AI selects the most appropriate reference book or website link. For example, it suggests the most effective resources based on past data. This expands children's learning resources by providing links to related reference books and websites.

[0037] The feedback providing unit can also share the content of the feedback with parents and teachers, thereby promoting support at home and at school. For example, the generation AI automatically generates a report to share the content of the feedback with parents and teachers. For example, a report summarizing the child's learning progress and level of understanding may be sent by email. The generation AI provides a dedicated portal site so that parents and teachers can check the content of the feedback. For example, parents and teachers can log in and check the child's learning situation. Sharing the content of the feedback promotes support at home and at school. For example, parents and teachers can identify a child's weaknesses and provide appropriate support. In this way, sharing the feedback with parents and teachers promotes support at home and at school.

[0038] The question answering unit can provide more accurate answers by referring to related past questions and answers. For example, when answering a question, the generation AI refers to a database of past questions and answers to provide the most appropriate answer. For example, an answer is generated based on past answers to similar questions. The generation AI analyzes past questions and answers to select the most effective answer. For example, it provides the answer that received the highest rating based on past data. In order to answer questions accurately, the generation AI learns from past questions and answers to improve the quality of the answers. For example, it learns answer patterns based on past data. This allows it to provide more accurate answers by referring to past questions and answers.

[0039] The question answering unit can provide answers in stages according to the child's level of understanding. In order to provide answers to questions in stages, for example, the generation AI evaluates the child's level of understanding and starts with a basic explanation. For example, if it is a math problem, the basic concept is explained first. The generation AI gradually adds detailed explanations according to the child's level of understanding. For example, after the basic explanation is understood, it explains an applied solution. In order to provide answers to questions in stages, the generation AI monitors the child's responses in real time and adjusts the level of explanation according to the child's level of understanding. For example, if the child is struggling to understand, it adds a more detailed explanation. This allows the child to deepen their understanding by providing answers in stages according to their level of understanding.

[0040] The question answering unit can provide related videos and animations to aid visual understanding. For example, when answering a question, the generating AI provides related videos. For example, if it is a math problem, it will display a video explaining how to calculate it. The generating AI will provide related animations to help children understand visually. For example, if it is a science problem, it will show an animation of the experimental process. By providing videos and animations, the generating AI will help children understand. For example, it will display videos that visually explain complex concepts. In this way, providing videos and animations will help children understand visually.

[0041] The question and answering unit can share answers to questions with other children, promoting collaborative learning. In the question and answering unit, for example, the generation AI provides a dedicated platform for sharing answers to questions with other children. For example, a forum may be created where children can post questions and answers. The generation AI then references the questions and answers of other children to promote collaborative learning. For example, children who have the same question share their answers with each other. By sharing answers to questions, the generation AI supports children's collaborative learning. For example, a function may be provided to promote group discussions. This promotes collaborative learning by sharing answers to questions.

[0042] The progress tracking unit can analyze a child's learning patterns and suggest an optimal learning schedule. For example, when tracking comprehension and progress, the generation AI analyzes the child's learning patterns and suggests an optimal learning schedule. For example, it suggests optimal study times based on past learning data. The generation AI analyzes a child's learning patterns and discovers that they are more likely to concentrate at certain times of the day. For example, it suggests a schedule that focuses on studying in the morning. When suggesting a learning schedule, the generation AI takes into account the child's level of comprehension and provides an efficient learning plan. For example, it suggests a schedule that focuses on areas where understanding is lacking. In this way, by analyzing a child's learning patterns and suggesting an optimal learning schedule, learning effectiveness is improved.

[0043] The progress tracking unit shares data on comprehension and progress with parents and teachers, enabling enhanced support at home and at school. In the progress tracking unit, for example, the generation AI automatically generates reports to share data on comprehension and progress with parents and teachers. For example, a report summarizing a child's learning progress and comprehension is sent by email. The generation AI provides a dedicated portal site so that parents and teachers can check the data on comprehension and progress. For example, parents and teachers can log in and check their child's learning situation. Sharing data on comprehension and progress strengthens support at home and at school. For example, parents and teachers can identify a child's weaknesses and provide appropriate support. In this way, sharing data on comprehension and progress strengthens support at home and at school.

[0044] The progress tracking section can stimulate a competitive spirit by comparing comprehension and progress data with other children. In the progress tracking section, for example, the generation AI provides a ranking function to compare comprehension and progress data with other children. For example, it displays rankings based on learning progress and grades. The generation AI references the data of other children and provides feedback to stimulate a competitive spirit. For example, it displays a message such as, "You're third in your class!" By comparing comprehension and progress data, the generation AI can stimulate children's competitive spirit. For example, it can set a specific goal and compare its achievement with other children's. In this way, comparing comprehension and progress data stimulates children's competitive spirit and increases their motivation to learn.

[0045] The progress tracking unit can gamify the comprehension and progress data, allowing children to learn while having fun. For example, in the progress tracking unit, the generating AI introduces a point system to gamify the comprehension and progress data. For example, points can be earned each time a homework assignment is answered correctly. The generating AI reflects learning progress in leveling up the game, allowing children to learn while having fun. For example, achieving a specific goal can increase the level. Based on the comprehension and progress data, the generating AI provides challenges to children. For example, bonus points can be earned for clearing a specific task. In this way, by gamifying the comprehension and progress data, children can learn while having fun.

[0046] The tutor collaboration unit can provide a child's past learning data, enabling the tutor to provide optimal instruction. For example, when collaborating with an online tutor, the generation AI provides the child's past learning data. For example, past grades and answer history are shared with the tutor. The generation AI analyzes the child's learning data and supports the tutor in providing optimal instruction. For example, it proposes a teaching plan to strengthen specific weak points. Based on the child's past learning data, the generation AI proposes an individually customized teaching method to the tutor. For example, it proposes the optimal teaching method based on past data. In this way, by providing past learning data, the tutor can provide optimal instruction.

[0047] The tutor collaboration unit can record sessions with online tutors so that they can be reviewed later. In the tutor collaboration unit, for example, the generation AI provides a recording function to record sessions with online tutors. For example, the content of the session can be automatically recorded so that it can be viewed later. The generation AI provides a dedicated portal site so that children can review the recorded sessions later. For example, the recording data can be saved so that children can access it at any time. By recording sessions with online tutors, the generation AI supports children's learning. For example, it can make it possible to review important points again. In this way, sessions with online tutors can be recorded so that they can be reviewed later.

[0048] The tutor collaboration unit can provide feedback in real time to improve the effectiveness of the session. In the tutor collaboration unit, for example, the generation AI provides feedback in real time when collaborating with an online tutor. For example, it evaluates the child's level of understanding during a session and suggests appropriate teaching methods to the tutor. By providing feedback in real time, the generation AI improves the effectiveness of the session. For example, if a child is struggling to understand, it suggests additional explanations. In order to provide feedback in real time, the generation AI monitors the child's reactions and gives appropriate advice to the tutor. For example, if a child is losing concentration, it suggests taking a break. In this way, by providing feedback in real time, the effectiveness of the session is improved.

[0049] The tutor collaboration unit can expand collaboration with online tutors to group sessions and promote collaborative learning. In the tutor collaboration unit, for example, to expand collaboration with online tutors to group sessions, the generation AI groups multiple children into a single session. For example, it groups children of the same grade or learning level. Through group sessions, the generation AI promotes collaborative learning. For example, it provides an environment where children can share questions and answers with each other and learn from each other. The generation AI supports the progress of group sessions, allowing tutors to provide effective instruction. For example, it monitors each child's level of understanding in real time and suggests appropriate teaching methods. This promotes collaborative learning through group sessions, thereby improving children's learning effectiveness.

[0050] The self-learning support unit can analyze a child's learning history and suggest the optimal learning method. For example, when providing self-learning hints, the generation AI analyzes the child's learning history and suggests the optimal learning method. For example, it suggests the optimal learning plan based on past grades and answer history. The generation AI analyzes the child's learning history and provides hints for strengthening specific weak points. For example, if there is a lack of understanding in a particular area, it suggests a learning method that focuses on that area. Based on the learning history, the generation AI suggests the optimal learning resources for the child. For example, it suggests the most effective reference books and websites based on past data. In this way, learning effectiveness is improved by analyzing learning history and suggesting the optimal learning method.

[0051] The self-learning support unit can provide self-learning hints customized to suit the child's interests and hobbies. In the self-learning support unit, for example, the generation AI analyzes the child's hobbies and interests in order to customize self-learning hints to suit the child's interests and hobbies. For example, it suggests learning resources related to the child's favorite topics. The generation AI provides self-learning hints based on the child's interests and hobbies. For example, if the child is interested in science, it suggests science-related learning methods. The generation AI customizes a learning plan to suit the child's interests and hobbies. For example, it suggests a learning plan that incorporates the child's favorite topics. In this way, self-learning hints tailored to the child's interests and hobbies are provided, thereby increasing motivation to learn.

[0052] The self-learning support unit can provide self-learning hints in the form of videos or animations to aid visual understanding. In the self-learning support unit, for example, the generation AI suggests related videos to provide self-learning hints in video format. For example, for a math problem, a video explaining how to calculate the problem is displayed. The generation AI provides self-learning hints in animation format to help children understand visually. For example, for a science problem, an animation is shown showing the experimental process. By providing videos and animations, the generation AI helps children understand. For example, a video that visually explains complex concepts is displayed. In this way, self-learning hints are provided in the form of videos or animations to aid visual understanding.

[0053] The self-learning support unit can share self-learning tips with other children and promote collaborative learning. For example, the self-learning support unit provides a dedicated platform for the generation AI to share self-learning tips with other children. For example, a forum may be set up where children can post learning tips. The generation AI may then refer to other children's learning tips and promote collaborative learning. For example, children who are interested in the same topic may share learning tips with each other. By sharing self-learning tips, the generation AI supports children's collaborative learning. For example, a function may be provided to promote group discussions. This promotes collaborative learning by sharing self-learning tips.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] The homework sending unit can automatically generate similar problems based on the content of the homework and provide additional practice problems. For example, after homework is submitted, the generation AI automatically generates similar problems based on the content of the submitted homework. For example, if it is a math problem, it will generate another problem using the same calculation method. When generating similar problems, the generation AI takes into account the child's level of understanding and provides problems of appropriate difficulty. For example, it provides problems in stages, from basic to applied problems. To automatically generate similar problems, the generation AI refers to a large problem database and selects the most appropriate problems. For example, it provides the most effective practice problems based on past homework data. This provides additional practice problems, deepening children's understanding.

[0056] The homework sending unit can accept voice input, allowing children to verbally explain the contents of their homework. For example, when sending homework, the generation AI can add a function to accept voice input. For example, a child can use a microphone to verbally explain the contents of their homework. The generation AI analyzes the voice input and converts it into text data. For example, it can automatically transcribe the child's explanation using voice recognition technology. Based on the voice input, the generation AI can understand the contents of the homework and determine the correct answer. For example, it can analyze a math problem that has been explained verbally and check the calculation process and answer. This allows children to verbally explain the contents of their homework.

[0057] The homework sending unit can automatically suggest video tutorials related to the homework content. For example, after homework is submitted, the generation AI analyzes the content of the homework and automatically suggests related video tutorials. For example, if it is a math problem, it will suggest a video explaining how to calculate it. When suggesting video tutorials, the generation AI takes into account the child's level of understanding and selects videos at an appropriate level. For example, it may suggest content in stages, from basic to applied. The generation AI references a large video database to select the optimal video tutorial. For example, it may suggest the most effective video based on past homework data. This automatically suggests related video tutorials, deepening children's understanding.

[0058] The feedback providing unit can refer to the child's past answer history and provide individually customized feedback. For example, when providing feedback, the generation AI analyzes the child's past answer history and provides individually customized feedback. For example, it may provide detailed explanations for questions that have been answered incorrectly in the past. The generation AI provides feedback to strengthen specific weaknesses based on the child's learning history. For example, if there is a lack of understanding in a particular area, it will provide feedback that focuses on that area. The generation AI refers to the child's past answer history and suggests an individually customized study plan. For example, it may suggest the optimal study method based on past grades. In this way, by providing individually customized feedback, children's learning effectiveness is improved.

[0059] The feedback providing unit can visually and aurally optimize the content of the feedback to suit the child's learning style. For example, to visually optimize the content of the feedback, the generation AI uses graphs and diagrams to explain. For example, for a math problem, it illustrates the calculation process. To provide auditorily optimized feedback, the generation AI provides audio explanations. For example, it allows the child to listen to the feedback audio. The generation AI provides a combination of visual and audio feedback to suit the child's learning style. For example, it provides visual diagrams and audio explanations simultaneously. This improves learning effectiveness by providing feedback that suits the child's learning style.

[0060] The feedback providing unit can provide links to related reference books and websites when providing feedback. For example, the generating AI provides links to related reference books when providing feedback. For example, for a math problem, it may display a link to a reference book that provides detailed explanations of how to calculate the problem. The generating AI may provide links to related websites so that children can access additional learning resources. For example, for a science problem, it may display a link to a website that features experiment videos. Depending on the content of the feedback, the generating AI may select the most appropriate reference book or website link. For example, it may suggest the most effective resources based on past data. This allows children to expand their learning resources by providing links to related reference books and websites.

[0061] The feedback providing unit can also share the content of the feedback with parents and teachers, thereby promoting support at home and at school. For example, the generation AI automatically generates a report to share the content of the feedback with parents and teachers. For example, a report summarizing the child's learning progress and level of understanding can be sent by email. The generation AI provides a dedicated portal site so that parents and teachers can check the content of the feedback. For example, parents and teachers can log in and check the child's learning situation. Sharing the content of the feedback promotes support at home and at school. For example, parents and teachers can identify a child's weaknesses and provide appropriate support. In this way, sharing the feedback with parents and teachers promotes support at home and at school.

[0062] The processing flow of the first embodiment will be briefly explained below.

[0063] Step 1: In the homework submission section, children submit their homework. For example, they can submit their homework in the form of a photo or text. Step 2: The correct answer determination unit determines the correct answer of the homework sent by the homework sending unit. For example, the generation AI analyzes the content of the homework and determines the correct answer. Step 3: The feedback providing unit provides feedback based on the result determined by the correct answer determining unit, for example, providing a specific correction method for a wrong question. Step 4: The question answering section answers questions about homework. For example, the generative AI provides appropriate answers to children's questions. Step 5: Progress Tracking tracks each child's understanding and progress. For example, the generative AI analyzes each child's learning progress and identifies skill gaps. Step 6: The Tutor Collaboration Department will support collaboration with online tutors as needed, for example, suggesting that students consult with an online tutor if they are unable to resolve a particular issue. Step 7: The self-learning support unit provides self-learning tips and tools. For example, the generative AI provides self-learning advice to children.

[0064] (Example 2) A homework support system according to an embodiment of the present invention allows children to submit their homework, and a generation AI determines the correct answers, provides feedback, answers questions, tracks comprehension and progress, supports collaboration with online tutors, and provides self-study tips, thereby providing comprehensive homework and learning support for children.

[0065] A homework assistance system according to an embodiment includes a homework sending unit, a correct answer determination unit, a feedback providing unit, a question and answer unit, a progress tracking unit, a tutor collaboration unit, and a self-study support unit. The homework sending unit allows children to submit their homework. For example, homework can be submitted in the form of a photo or text. The correct answer determination unit determines the correct answer for the homework submitted by the homework sending unit. For example, a generation AI analyzes the content of the homework and determines the correct answer. The feedback providing unit provides feedback based on the results determined by the correct answer determination unit. For example, it provides specific correction methods for incorrectly answered questions. The question and answering unit answers questions about the homework. For example, the generation AI provides appropriate answers to children's questions. The progress tracking unit tracks each child's level of understanding and progress. For example, the generation AI analyzes children's learning progress and identifies skill gaps. The tutor collaboration unit supports collaboration with online tutors as needed. For example, it suggests consulting an online tutor if a specific problem cannot be solved. The self-study support unit provides hints and methods for self-study. For example, generative AI can provide children with self-study advice, allowing the homework support system to provide comprehensive homework and learning support for children.

[0066] The homework sending unit can automatically determine the difficulty of the homework and provide feedback according to the difficulty. For example, when homework is sent, the generating AI analyzes the content of the homework and automatically determines the difficulty. For example, for a math problem, the difficulty is assessed based on the complexity of the problem and the number of calculation steps. To provide feedback according to the difficulty, the generating AI refers to past data and learns feedback for homework of similar difficulty. For example, it provides detailed explanations for difficult problems. When determining the difficulty of homework, the generating AI takes into account the child's past grades and answer history to provide an individually customized difficulty assessment. For example, if the child has struggled with similar problems in the past, it will set the difficulty higher. This makes it possible to provide appropriate feedback according to the difficulty of the homework.

[0067] The homework sending unit can automatically generate similar problems based on the content of the homework and provide additional practice problems. For example, after homework is submitted, the homework sending unit automatically generates similar problems based on the content of the submitted homework using a generation AI. For example, if it is a math problem, it will generate another problem using the same calculation method. When generating similar problems, the generation AI takes into account the child's level of understanding and provides problems of appropriate difficulty. For example, it provides problems in stages, from basic to applied problems. To automatically generate similar problems, the generation AI refers to a large problem database and selects the most appropriate problems. For example, it provides the most effective practice problems based on past homework data. This provides additional practice problems, thereby deepening children's understanding.

[0068] The homework sending unit can use the emotion estimation function to analyze a child's emotions when submitting homework and provide advice to reduce stress. For example, when submitting homework, the homework sending unit uses the generation AI to analyze the child's facial expressions and voice to estimate their emotions. For example, it may measure the child's stress level using a camera or microphone. Based on the emotion estimation results, the generation AI provides advice to reduce stress. For example, it may suggest breathing techniques to help them relax or a short break. The generation AI monitors the child's emotions in real time, and if stress increases, it provides encouraging messages or positive feedback. For example, it displays a message such as "You're doing a great job!" This reduces the child's stress and increases their motivation to learn.

[0069] The homework sending unit can accept voice input, allowing children to verbally explain the contents of their homework. For example, the homework sending unit adds a function to the generation AI to accept voice input when sending homework. For example, a child verbally explains the contents of their homework using a microphone. The generation AI analyzes the voice input and converts it into text data. For example, it uses voice recognition technology to automatically transcribe the child's explanation. Based on the voice input, the generation AI understands the contents of the homework and determines the correct answer. For example, it analyzes a math problem that has been explained verbally and checks the calculation process and answer. This allows children to verbally explain the contents of their homework.

[0070] The homework sending unit can automatically suggest video tutorials related to the homework content. For example, after homework is sent, the generating AI in the homework sending unit analyzes the content of the homework and automatically suggests related video tutorials. For example, if it is a math problem, it will suggest a video that explains how to calculate it. When suggesting video tutorials, the generating AI takes into account the child's level of understanding and selects videos at an appropriate level. For example, it may suggest content in stages, from basic to applied. The generating AI references a large video database and selects the optimal video tutorial. For example, it may suggest the most effective video based on past homework data. This automatically suggests related video tutorials, deepening children's understanding.

[0071] The homework sending unit can analyze a child's emotions using an emotion estimation function and emphasize positive feedback. For example, when sending homework, the homework sending unit uses the generation AI to analyze the child's facial expressions and voice to estimate their emotions. For example, it may use a camera or microphone to analyze the child's emotions in real time. Based on the emotion estimation results, the generation AI emphasizes positive feedback. For example, if a child is feeling anxious, it may display an encouraging message. It monitors a child's emotions and provides feedback to elicit positive emotions. For example, it may display a message such as "Great effort!" This analyzes a child's emotions and emphasizes positive feedback, thereby increasing their motivation to learn.

[0072] The feedback providing unit can refer to the child's past answer history and provide individually customized feedback. For example, when providing feedback, the generation AI analyzes the child's past answer history and provides individually customized feedback. For example, it provides detailed explanations for questions that have been answered incorrectly in the past. The generation AI provides feedback to strengthen specific weaknesses based on the child's learning history. For example, if there is a lack of understanding in a particular area, it provides feedback that focuses on that area. The generation AI refers to the child's past answer history and suggests an individually customized study plan. For example, it suggests the optimal study method based on past grades. In this way, by providing individually customized feedback, children's learning effectiveness is improved.

[0073] The feedback providing unit can visually and aurally optimize the content of the feedback to suit the child's learning style. For example, to visually optimize the content of the feedback, the generation AI may use graphs and diagrams to provide explanations. For example, for a math problem, the calculation process may be illustrated. To provide auditorily optimized feedback, the generation AI may provide audio explanations. For example, the child may be able to listen to the feedback audio. The generation AI may provide a combination of visual and audio feedback to suit the child's learning style. For example, visual diagrams and audio explanations may be provided simultaneously. This improves learning effectiveness by providing feedback that suits the child's learning style.

[0074] The feedback providing unit can use the emotion estimation function to analyze the child's emotions when providing feedback and add comments to increase motivation. For example, when providing feedback, the generation AI analyzes the child's facial expressions and voice to estimate their emotions. For example, a camera or microphone can be used to analyze the child's emotions in real time. Based on the emotion estimation results, the generation AI adds comments to increase motivation. For example, if the child is feeling anxious, an encouraging message can be displayed. The child's emotions can be monitored and feedback provided to elicit positive emotions can be provided. For example, a message such as "Great effort!" can be displayed. In this way, the child's emotions can be analyzed and comments to increase motivation can be added, thereby improving their motivation to learn.

[0075] The feedback providing unit can provide links to related reference books and websites when providing feedback. For example, when providing feedback, the generation AI provides links to related reference books. For example, if it is a math problem, it displays a link to a reference book that explains the calculation method in detail. The generation AI provides links to related websites so that children can access additional learning resources. For example, if it is a science problem, it displays a link to a website that features experiment videos. Depending on the content of the feedback, the generation AI selects the most appropriate reference book or website link. For example, it suggests the most effective resources based on past data. This expands children's learning resources by providing links to related reference books and websites.

[0076] The feedback providing unit can also share the content of the feedback with parents and teachers, thereby promoting support at home and at school. For example, the generation AI automatically generates a report to share the content of the feedback with parents and teachers. For example, a report summarizing the child's learning progress and level of understanding may be sent by email. The generation AI provides a dedicated portal site so that parents and teachers can check the content of the feedback. For example, parents and teachers can log in and check the child's learning situation. Sharing the content of the feedback promotes support at home and at school. For example, parents and teachers can identify a child's weaknesses and provide appropriate support. In this way, sharing the feedback with parents and teachers promotes support at home and at school.

[0077] The feedback providing unit can adjust the tone of the feedback using the emotion estimation function. For example, when providing feedback, the generation AI analyzes the child's facial expressions and voice to estimate the child's emotions. For example, a camera or microphone is used to analyze the child's emotions in real time. The generation AI adjusts the tone of the feedback based on the emotion estimation results. For example, if the child is feeling anxious, feedback is provided in a gentle tone. The child's emotions are monitored and feedback designed to elicit positive emotions is provided. For example, a message such as "Great effort!" is displayed. In this way, by adjusting the tone of the feedback using the emotion estimation function, feedback that takes into consideration the child's emotions is provided.

[0078] The question answering unit can provide more accurate answers by referring to related past questions and answers. For example, when answering a question, the generation AI refers to a database of past questions and answers to provide the most appropriate answer. For example, an answer is generated based on past answers to similar questions. The generation AI analyzes past questions and answers to select the most effective answer. For example, it provides the answer that received the highest rating based on past data. In order to answer questions accurately, the generation AI learns from past questions and answers to improve the quality of the answers. For example, it learns answer patterns based on past data. This allows it to provide more accurate answers by referring to past questions and answers.

[0079] The question answering unit can provide answers in stages according to the child's level of understanding. In order to provide answers to questions in stages, for example, the generation AI evaluates the child's level of understanding and starts with a basic explanation. For example, if it is a math problem, the basic concept is explained first. The generation AI gradually adds detailed explanations according to the child's level of understanding. For example, after the basic explanation is understood, it explains an applied solution. In order to provide answers to questions in stages, the generation AI monitors the child's responses in real time and adjusts the level of explanation according to the child's level of understanding. For example, if the child is struggling to understand, it adds a more detailed explanation. This allows the child to deepen their understanding by providing answers in stages according to their level of understanding.

[0080] The question answering unit uses the emotion estimation function to analyze a child's emotions when answering a question and can provide answers that give a sense of security. For example, when answering a question, the generation AI analyzes the child's facial expressions and voice to estimate their emotions. For example, it uses a camera or microphone to analyze the child's emotions in real time. Based on the emotion estimation results, the generation AI provides answers that give a sense of security. For example, if a child is feeling anxious, it provides answers in a gentle tone. It monitors the child's emotions and provides answers that elicit positive emotions. For example, it adds a message such as "Don't worry, you can do it!" This analyzes a child's emotions and provides answers that give a sense of security, thereby increasing their motivation to learn.

[0081] The question answering unit can provide related videos and animations to aid visual understanding. For example, when answering a question, the generating AI provides related videos. For example, if it is a math problem, it will display a video explaining how to calculate it. The generating AI will provide related animations to help children understand visually. For example, if it is a science problem, it will show an animation of the experimental process. By providing videos and animations, the generating AI will help children understand. For example, it will display videos that visually explain complex concepts. In this way, providing videos and animations will help children understand visually.

[0082] The question and answering unit can share answers to questions with other children, promoting collaborative learning. In the question and answering unit, for example, the generation AI provides a dedicated platform for sharing answers to questions with other children. For example, a forum may be created where children can post questions and answers. The generation AI then references the questions and answers of other children to promote collaborative learning. For example, children who have the same question share their answers with each other. By sharing answers to questions, the generation AI supports children's collaborative learning. For example, a function may be provided to promote group discussions. This promotes collaborative learning by sharing answers to questions.

[0083] The question answering unit can use an emotion estimation function to analyze a child's emotions and emphasize positive feedback. For example, when answering a question, the generation AI analyzes the child's facial expressions and voice to estimate their emotions. For example, it analyzes a child's emotions in real time using a camera or microphone. Based on the emotion estimation results, the generation AI emphasizes positive feedback. For example, if a child is feeling anxious, it displays an encouraging message. It monitors a child's emotions and provides feedback to elicit positive emotions. For example, it displays a message such as "Great effort!" This analyzes a child's emotions and emphasizes positive feedback, thereby increasing their motivation to learn.

[0084] The progress tracking unit can analyze a child's learning patterns and suggest an optimal learning schedule. For example, when tracking comprehension and progress, the generation AI analyzes the child's learning patterns and suggests an optimal learning schedule. For example, it suggests optimal study times based on past learning data. The generation AI analyzes a child's learning patterns and discovers that they are more likely to concentrate at certain times of the day. For example, it suggests a schedule that focuses on studying in the morning. When suggesting a learning schedule, the generation AI takes into account the child's level of comprehension and provides an efficient learning plan. For example, it suggests a schedule that focuses on areas where understanding is lacking. In this way, by analyzing a child's learning patterns and suggesting an optimal learning schedule, learning effectiveness is improved.

[0085] The progress tracking unit shares data on comprehension and progress with parents and teachers, enabling enhanced support at home and at school. In the progress tracking unit, for example, the generation AI automatically generates reports to share data on comprehension and progress with parents and teachers. For example, a report summarizing a child's learning progress and comprehension is sent by email. The generation AI provides a dedicated portal site so that parents and teachers can check the data on comprehension and progress. For example, parents and teachers can log in and check their child's learning situation. Sharing data on comprehension and progress strengthens support at home and at school. For example, parents and teachers can identify a child's weaknesses and provide appropriate support. In this way, sharing data on comprehension and progress strengthens support at home and at school.

[0086] The progress tracking unit uses the emotion estimation function to analyze a child's emotions when tracking their comprehension and progress, and can provide advice to increase their motivation to learn. For example, when tracking their comprehension and progress, the generation AI analyzes the child's facial expressions and voice to estimate their emotions. For example, a camera or microphone is used to analyze a child's emotions in real time. Based on the emotion estimation results, the generation AI provides advice to increase their motivation to learn. For example, if a child is feeling anxious, an encouraging message is displayed. The generation AI monitors a child's emotions and provides advice to elicit positive emotions. For example, a message such as "Great effort!" is displayed. This improves learning effectiveness by analyzing a child's emotions and providing advice to increase their motivation to learn.

[0087] The progress tracking section can stimulate a competitive spirit by comparing comprehension and progress data with other children. In the progress tracking section, for example, the generation AI provides a ranking function to compare comprehension and progress data with other children. For example, it displays rankings based on learning progress and grades. The generation AI references the data of other children and provides feedback to stimulate a competitive spirit. For example, it displays a message such as, "You're third in your class!" By comparing comprehension and progress data, the generation AI can stimulate children's competitive spirit. For example, it can set a specific goal and compare its achievement with other children's. In this way, comparing comprehension and progress data stimulates children's competitive spirit and increases their motivation to learn.

[0088] The progress tracking unit can gamify the comprehension and progress data, allowing children to learn while having fun. For example, in the progress tracking unit, the generating AI introduces a point system to gamify the comprehension and progress data. For example, points can be earned each time a homework assignment is answered correctly. The generating AI reflects learning progress in leveling up the game, allowing children to learn while having fun. For example, achieving a specific goal can increase the level. Based on the comprehension and progress data, the generating AI provides challenges to children. For example, bonus points can be earned for clearing a specific task. In this way, by gamifying the comprehension and progress data, children can learn while having fun.

[0089] The progress tracking unit can analyze a child's emotions using an emotion estimation function and emphasize positive feedback. For example, when tracking comprehension and progress, the generation AI analyzes the child's facial expressions and voice to estimate emotions. For example, a camera or microphone can be used to analyze a child's emotions in real time. Based on the emotion estimation results, the generation AI emphasizes positive feedback. For example, if a child is feeling anxious, an encouraging message can be displayed. The system monitors a child's emotions and provides feedback to elicit positive emotions. For example, it displays a message such as "Great effort!" This analyzes a child's emotions and emphasizes positive feedback, thereby increasing their motivation to learn.

[0090] The tutor collaboration unit can provide a child's past learning data, enabling the tutor to provide optimal instruction. For example, when collaborating with an online tutor, the generation AI provides the child's past learning data. For example, past grades and answer history are shared with the tutor. The generation AI analyzes the child's learning data and supports the tutor in providing optimal instruction. For example, it proposes a teaching plan to strengthen specific weak points. Based on the child's past learning data, the generation AI proposes an individually customized teaching method to the tutor. For example, it proposes the optimal teaching method based on past data. In this way, by providing past learning data, the tutor can provide optimal instruction.

[0091] The tutor collaboration unit can record sessions with online tutors so that they can be reviewed later. In the tutor collaboration unit, for example, the generation AI provides a recording function to record sessions with online tutors. For example, the content of the session can be automatically recorded so that it can be viewed later. The generation AI provides a dedicated portal site so that children can review the recorded sessions later. For example, the recording data can be saved so that children can access it at any time. By recording sessions with online tutors, the generation AI supports children's learning. For example, it can make it possible to review important points again. In this way, sessions with online tutors can be recorded so that they can be reviewed later.

[0092] The tutor collaboration unit uses the emotion estimation function to analyze a child's emotions when collaborating with an online tutor, allowing the tutor to respond appropriately. For example, when collaborating with an online tutor, the generation AI analyzes the child's facial expressions and voice to estimate their emotions. For example, a camera or microphone may be used to analyze the child's emotions in real time. Based on the emotion estimation results, the generation AI suggests an appropriate response to the tutor. For example, if a child is feeling anxious, it may suggest using a gentle tone to instruct the child. The generation AI monitors the child's emotions and provides feedback in real time so the tutor can respond appropriately. For example, if the child's emotions change, it may send a notification to the tutor. This improves learning effectiveness by analyzing the child's emotions and allowing the tutor to respond appropriately.

[0093] The tutor collaboration unit can provide feedback in real time to improve the effectiveness of the session. In the tutor collaboration unit, for example, the generation AI provides feedback in real time when collaborating with an online tutor. For example, it evaluates the child's level of understanding during a session and suggests appropriate teaching methods to the tutor. By providing feedback in real time, the generation AI improves the effectiveness of the session. For example, if a child is struggling to understand, it suggests additional explanations. In order to provide feedback in real time, the generation AI monitors the child's reactions and gives appropriate advice to the tutor. For example, if a child is losing concentration, it suggests taking a break. In this way, by providing feedback in real time, the effectiveness of the session is improved.

[0094] The tutor collaboration unit can expand collaboration with online tutors to group sessions and promote collaborative learning. In the tutor collaboration unit, for example, to expand collaboration with online tutors to group sessions, the generation AI groups multiple children into a single session. For example, it groups children of the same grade or learning level. Through group sessions, the generation AI promotes collaborative learning. For example, it provides an environment where children can share questions and answers with each other and learn from each other. The generation AI supports the progress of group sessions, allowing tutors to provide effective instruction. For example, it monitors each child's level of understanding in real time and suggests appropriate teaching methods. This promotes collaborative learning through group sessions, thereby improving children's learning effectiveness.

[0095] The tutor collaboration unit can use the emotion estimation function to analyze a child's emotions and emphasize positive feedback. For example, when collaborating with an online tutor, the generation AI analyzes the child's facial expressions and voice to estimate their emotions. For example, it analyzes the child's emotions in real time using a camera or microphone. Based on the emotion estimation results, the generation AI emphasizes positive feedback. For example, if a child is feeling anxious, it displays an encouraging message. It monitors the child's emotions and provides feedback to elicit positive emotions. For example, it displays a message such as "Great effort!" This analyzes the child's emotions and emphasizes positive feedback, thereby increasing their motivation to learn.

[0096] The self-learning support unit can analyze a child's learning history and suggest the optimal learning method. For example, when providing self-learning hints, the generation AI analyzes the child's learning history and suggests the optimal learning method. For example, it suggests the optimal learning plan based on past grades and answer history. The generation AI analyzes the child's learning history and provides hints for strengthening specific weak points. For example, if there is a lack of understanding in a particular area, it suggests a learning method that focuses on that area. Based on the learning history, the generation AI suggests the optimal learning resources for the child. For example, it suggests the most effective reference books and websites based on past data. In this way, learning effectiveness is improved by analyzing learning history and suggesting the optimal learning method.

[0097] The self-learning support unit can provide self-learning hints customized to suit the child's interests and hobbies. In the self-learning support unit, for example, the generation AI analyzes the child's hobbies and interests in order to customize self-learning hints to suit the child's interests and hobbies. For example, it suggests learning resources related to the child's favorite topics. The generation AI provides self-learning hints based on the child's interests and hobbies. For example, if the child is interested in science, it suggests science-related learning methods. The generation AI customizes a learning plan to suit the child's interests and hobbies. For example, it suggests a learning plan that incorporates the child's favorite topics. In this way, self-learning hints tailored to the child's interests and hobbies are provided, thereby increasing motivation to learn.

[0098] The self-learning support unit can use the emotion estimation function to analyze a child's emotions when providing self-learning hints and provide advice to increase motivation. For example, when providing self-learning hints, the self-learning support unit uses the generation AI to analyze the child's facial expressions and voice and estimate their emotions. For example, a camera or microphone may be used to analyze the child's emotions in real time. Based on the emotion estimation results, the generation AI provides advice to increase motivation. For example, if a child is feeling anxious, an encouraging message may be displayed. The child's emotions may be monitored and advice to elicit positive emotions may be provided. For example, a message such as "Great effort!" may be displayed. In this way, the child's emotions may be analyzed and advice to increase motivation may be provided, thereby improving their motivation to learn.

[0099] The self-learning support unit can provide self-learning hints in the form of videos or animations to aid visual understanding. In the self-learning support unit, for example, the generation AI suggests related videos to provide self-learning hints in video format. For example, for a math problem, a video explaining how to calculate the problem is displayed. The generation AI provides self-learning hints in animation format to help children understand visually. For example, for a science problem, an animation is shown showing the experimental process. By providing videos and animations, the generation AI helps children understand. For example, a video that visually explains complex concepts is displayed. In this way, self-learning hints are provided in the form of videos or animations to aid visual understanding.

[0100] The self-learning support unit can share self-learning tips with other children and promote collaborative learning. For example, the self-learning support unit provides a dedicated platform for the generation AI to share self-learning tips with other children. For example, a forum may be set up where children can post learning tips. The generation AI may then refer to other children's learning tips and promote collaborative learning. For example, children who are interested in the same topic may share learning tips with each other. By sharing self-learning tips, the generation AI supports children's collaborative learning. For example, a function may be provided to promote group discussions. This promotes collaborative learning by sharing self-learning tips.

[0101] The self-learning support unit can use an emotion estimation function to analyze a child's emotions and emphasize positive feedback. For example, when providing self-learning hints, the generation AI analyzes the child's facial expressions and voice to estimate their emotions. For example, it uses a camera or microphone to analyze a child's emotions in real time. Based on the emotion estimation results, the generation AI emphasizes positive feedback. For example, if a child is feeling anxious, it displays an encouraging message. It monitors a child's emotions and provides feedback to elicit positive emotions. For example, it displays a message such as "Great effort!" In this way, the child's emotions are analyzed and positive feedback is emphasized, increasing their motivation to learn.

[0102] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0103] The homework sending unit can automatically generate similar problems based on the content of the homework and provide additional practice problems. For example, after homework is submitted, the generation AI automatically generates similar problems based on the content of the submitted homework. For example, if it is a math problem, it will generate another problem using the same calculation method. When generating similar problems, the generation AI takes into account the child's level of understanding and provides problems of appropriate difficulty. For example, it provides problems in stages, from basic to applied problems. To automatically generate similar problems, the generation AI refers to a large problem database and selects the most appropriate problems. For example, it provides the most effective practice problems based on past homework data. This provides additional practice problems, deepening children's understanding.

[0104] The homework sending unit can use the emotion estimation function to analyze a child's emotions when submitting homework and provide advice to reduce stress. For example, when submitting homework, the generation AI analyzes the child's facial expressions and voice to estimate their emotions. For example, it can measure the child's stress level using a camera or microphone. Based on the emotion estimation results, the generation AI provides advice to reduce stress. For example, it can suggest breathing techniques to help them relax or take a short break. The generation AI monitors the child's emotions in real time, and if stress increases, it provides encouraging messages and positive feedback. For example, it displays a message such as "You're doing a great job!" This reduces the child's stress and increases their motivation to learn.

[0105] The homework sending unit can accept voice input, allowing children to verbally explain the contents of their homework. For example, when sending homework, the generation AI can add a function to accept voice input. For example, a child can use a microphone to verbally explain the contents of their homework. The generation AI analyzes the voice input and converts it into text data. For example, it can automatically transcribe the child's explanation using voice recognition technology. Based on the voice input, the generation AI can understand the contents of the homework and determine the correct answer. For example, it can analyze a math problem that has been explained verbally and check the calculation process and answer. This allows children to verbally explain the contents of their homework.

[0106] The homework sending unit can automatically suggest video tutorials related to the homework content. For example, after homework is submitted, the generation AI analyzes the content of the homework and automatically suggests related video tutorials. For example, if it is a math problem, it will suggest a video explaining how to calculate it. When suggesting video tutorials, the generation AI takes into account the child's level of understanding and selects videos at an appropriate level. For example, it may suggest content in stages, from basic to applied. The generation AI references a large video database to select the optimal video tutorial. For example, it may suggest the most effective video based on past homework data. This automatically suggests related video tutorials, deepening children's understanding.

[0107] The homework sending unit can use an emotion estimation function to analyze a child's emotions and emphasize positive feedback. For example, when sending homework, the generation AI analyzes the child's facial expressions and voice to estimate their emotions. For example, it can analyze a child's emotions in real time using a camera or microphone. Based on the emotion estimation results, the generation AI emphasizes positive feedback. For example, if a child is feeling anxious, it can display an encouraging message. It monitors a child's emotions and provides feedback to elicit positive emotions. For example, it can display a message such as "Great effort!" This analyzes a child's emotions and emphasizes positive feedback, thereby increasing their motivation to learn.

[0108] The feedback providing unit can refer to the child's past answer history and provide individually customized feedback. For example, when providing feedback, the generation AI analyzes the child's past answer history and provides individually customized feedback. For example, it may provide detailed explanations for questions that have been answered incorrectly in the past. The generation AI provides feedback to strengthen specific weaknesses based on the child's learning history. For example, if there is a lack of understanding in a particular area, it will provide feedback that focuses on that area. The generation AI refers to the child's past answer history and suggests an individually customized study plan. For example, it may suggest the optimal study method based on past grades. In this way, by providing individually customized feedback, children's learning effectiveness is improved.

[0109] The feedback providing unit can visually and aurally optimize the content of the feedback to suit the child's learning style. For example, to visually optimize the content of the feedback, the generation AI uses graphs and diagrams to explain. For example, for a math problem, it illustrates the calculation process. To provide auditorily optimized feedback, the generation AI provides audio explanations. For example, it allows the child to listen to the feedback audio. The generation AI provides a combination of visual and audio feedback to suit the child's learning style. For example, it provides visual diagrams and audio explanations simultaneously. This improves learning effectiveness by providing feedback that suits the child's learning style.

[0110] The feedback providing unit can use the emotion estimation function to analyze the child's emotions when providing feedback and add comments to increase motivation. For example, when providing feedback, the generation AI analyzes the child's facial expressions and voice to estimate their emotions. For example, it can analyze the child's emotions in real time using a camera or microphone. Based on the emotion estimation results, the generation AI adds comments to increase motivation. For example, if the child is feeling anxious, it can display an encouraging message. It monitors the child's emotions and provides feedback to elicit positive emotions. For example, it can display a message such as "Great effort!". In this way, analyzing the child's emotions and adding comments to increase motivation increases their motivation to learn.

[0111] The feedback providing unit can provide links to related reference books and websites when providing feedback. For example, the generating AI provides links to related reference books when providing feedback. For example, for a math problem, it may display a link to a reference book that provides detailed explanations of how to calculate the problem. The generating AI may provide links to related websites so that children can access additional learning resources. For example, for a science problem, it may display a link to a website that features experiment videos. Depending on the content of the feedback, the generating AI may select the most appropriate reference book or website link. For example, it may suggest the most effective resources based on past data. This allows children to expand their learning resources by providing links to related reference books and websites.

[0112] The feedback providing unit can also share the content of the feedback with parents and teachers, thereby promoting support at home and at school. For example, the generation AI automatically generates a report to share the content of the feedback with parents and teachers. For example, a report summarizing the child's learning progress and level of understanding can be sent by email. The generation AI provides a dedicated portal site so that parents and teachers can check the content of the feedback. For example, parents and teachers can log in and check the child's learning situation. Sharing the content of the feedback promotes support at home and at school. For example, parents and teachers can identify a child's weaknesses and provide appropriate support. In this way, sharing the feedback with parents and teachers promotes support at home and at school.

[0113] The processing flow of the second embodiment will be briefly explained below.

[0114] Step 1: In the homework submission section, children submit their homework. For example, they can submit their homework in the form of a photo or text. Step 2: The correct answer determination unit determines the correct answer of the homework sent by the homework sending unit. For example, the generation AI analyzes the content of the homework and determines the correct answer. Step 3: The feedback providing unit provides feedback based on the result determined by the correct answer determining unit, for example, providing a specific correction method for a wrong question. Step 4: The question answering section answers questions about homework. For example, the generative AI provides appropriate answers to children's questions. Step 5: Progress Tracking tracks each child's understanding and progress. For example, the generative AI analyzes each child's learning progress and identifies skill gaps. Step 6: The Tutor Collaboration Department will support collaboration with online tutors as needed, for example, suggesting that students consult with an online tutor if they are unable to resolve a particular issue. Step 7: The self-learning support unit provides self-learning tips and tools. For example, the generative AI provides self-learning advice to children.

[0115] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0116] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0117] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0118] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0119] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0120] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0121] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0122] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0123] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0124] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0125] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0126] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0127] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0128] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0129] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0130] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0131] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0132] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0133] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0134] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0135] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0136] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0137] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0139] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0140] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0141] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0142] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0143] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0144] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0145] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0146] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0147] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0148] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0149] 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.

[0150] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0151] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0152] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0153] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0154] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0155] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0156] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0157] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0158] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0159] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0160] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0161] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0162] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0163] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0164] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0165] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0166] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0167] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0168] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0169] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0170] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0171] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0172] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0173] 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.

[0174] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0175] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0176] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0177] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0178] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0179] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0180] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0181] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0182] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a homework sending unit that sends homework; a correct answer determination unit that determines the correct answer of the homework transmitted by the homework transmission unit; a feedback providing unit that provides feedback based on the result determined by the correct answer determining unit; a question answering unit that answers questions about the homework; A progress tracking section that tracks each child's understanding and progress; The Tutor Collaboration Department supports collaboration with online tutors as needed, and A self-learning support unit that provides hints and methods for self-learning. A system characterized by:

2. The homework sending unit: Automatically assess the difficulty of homework and provide feedback according to that difficulty.

2. The system of claim 1.

3. The homework sending unit: Automatically generate similar questions based on homework content and provide additional practice questions 2. The system of claim 1.

4. The homework sending unit: Analyze your child's emotions when submitting homework and offer advice to reduce stress 2. The system of claim 1.

5. The homework sending unit: Accepts voice input, allowing children to verbally explain their homework 2. The system of claim 1.

6. The homework sending unit: Automatically suggest video tutorials related to homework content 2. The system of claim 1.

7. The homework sending unit: Analyze your child's emotions and emphasize positive feedback 2. The system of claim 1.

8. The feedback providing unit: View a child's past responses and provide personalized feedback 2. The system of claim 1.

Images