system

Abstract

The system according to this embodiment aims to create an environment where children can learn in an enjoyable way and to reduce the burden on parents. [Solution] The system according to this embodiment comprises a conversation learning support unit, an emotion recognition unit, a dialogue provision unit, and a support unit. The conversation learning support unit engages in conversation on topics that interest the child. The emotion recognition unit recognizes the child's emotions. The dialogue provision unit provides dialogues corresponding to the emotions recognized by the emotion recognition unit. The support unit provides learning support based on learning goals and schedules set by the parent.

Description

Technical Field

[0004] ,

[0006] , , , , , ,

[0005] , , , , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that parents cannot take enough time to fully interact with their children and it is difficult to provide high-quality education and emotional care.

[0005] The system according to the embodiment aims to create an environment where children can learn happily and reduce the burden on parents.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a conversation learning support unit, an emotion recognition unit, a dialogue provision unit, and a support unit. The conversation learning support unit engages in conversation on topics that interest the child. The emotion recognition unit recognizes the child's emotions. The dialogue provision unit provides dialogues that correspond to the emotions recognized by the emotion recognition unit. The support unit provides learning support based on learning goals and schedules set by the parent. [Effects of the Invention]

[0007] The system according to this embodiment can create an environment where children can learn in an enjoyable way and reduce the burden on parents. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The conversational learning support system according to an embodiment of the present invention is a system that uses AI to provide a conversation partner to support a child's learning and growth. This system converses with the child on topics that interest them and helps them deepen their knowledge. It also recognizes the child's emotions and responds accordingly, providing a sense of security. This reduces the burden on parents and creates an environment where children can learn in an enjoyable way. For example, if a child is interested in dinosaurs, the AI ​​in the conversational learning support system provides knowledge about dinosaurs and helps the child deepen that knowledge through dialogue. This allows the child to learn in an enjoyable way. Next, the conversational learning support system's AI recognizes the child's emotions and responds accordingly. For example, if a child is feeling anxious, the AI ​​engages in conversation with gentle words to provide reassurance. This allows the child to learn with peace of mind. Furthermore, the conversational learning support system's AI generates stories tailored to the child's age and interests, stimulating the child's creativity. For example, if a child is interested in space, the AI ​​generates a story with a space theme, and the child can enjoy the story together with the AI. This mechanism reduces the burden on parents and creates an environment where children can learn in an enjoyable way. Parents can support their children's learning and growth without being overwhelmed by work or household chores. Furthermore, children can receive a high-quality education and appropriate emotional care. For example, in dual-income households, parents are often too busy with work and household chores to spend enough time with their children. Even in such cases, AI can support children's learning and growth, reducing the burden on parents and providing an environment where children can learn happily. AI also recognizes children's emotions and provides appropriate dialogue, thus providing emotional care. This allows children to learn with peace of mind, and parents to entrust their children to it with confidence. In this way, an AI-powered conversation partner is an effective means of supporting children's learning and growth and reducing the burden on parents. Thus, a conversational learning support system can support children's learning and growth and reduce the burden on parents.

[0029] The conversational learning support system according to this embodiment comprises a conversational learning support unit, an emotion recognition unit, a dialogue provision unit, and a support unit. The conversational learning support unit engages in conversation on themes that the child is interested in. For example, if the child is interested in dinosaurs, the conversational learning support unit provides knowledge about dinosaurs and helps the child deepen that knowledge through dialogue. The conversational learning support unit can also provide knowledge about space if the child is interested in space and help the child deepen that knowledge through dialogue. Furthermore, if the child is interested in animals, the conversational learning support unit can provide knowledge about animals and help the child deepen that knowledge through dialogue. The emotion recognition unit recognizes the child's emotions. For example, the emotion recognition unit analyzes the child's facial expressions and recognizes whether the child is happy, sad, or anxious. The emotion recognition unit can also analyze the child's tone of voice and recognize whether the child is excited or calm. Furthermore, the emotion recognition unit can analyze the child's body movements and recognize whether the child is relaxed or tense. The dialogue provision unit provides dialogue corresponding to the emotions recognized by the emotion recognition unit. For example, the dialogue provider unit can provide reassuring dialogue using gentle words when a child is feeling anxious. It can also use praise when a child is happy. Furthermore, it can use encouraging words when a child is sad. The support unit provides learning support based on the learning goals and schedule set by the parents. For example, the support unit provides appropriate learning content to the child based on the learning goals set by the parents. It can also provide appropriate study time to the child based on the schedule set by the parents. Furthermore, the support unit can monitor the child's learning progress based on the learning goals and schedule set by the parents and adjust the learning content and study time as needed. As a result, the conversational learning support system according to this embodiment can support the child's learning and growth and reduce the burden on parents.

[0030] The Conversational Learning Support Department engages in conversations on topics that interest children. For example, if a child is interested in dinosaurs, the department provides knowledge about dinosaurs and helps deepen that knowledge through dialogue. Specifically, they explain in detail the types of dinosaurs, their ecology, and their evolutionary process, and answer any questions the child may have immediately. They can also keep the child interested through dinosaur quizzes and games. Furthermore, if a child is interested in space, the department can provide knowledge about space and help deepen that knowledge through dialogue. For example, they explain planets, constellations, and the history of space exploration, and provide detailed information if the child has questions about space. This allows the child to learn deeply about the topic that interests them. Also, if a child is interested in animals, the department can provide knowledge about animals and help deepen that knowledge through dialogue. For example, they explain the ecology, habits, and conservation efforts of animals, and answer any questions the child may have with specific examples. This allows the child to deepen their understanding of animals. The Conversational Learning Support Department employs various methods to engage children's interest and make learning enjoyable. For example, by incorporating episodes and stories that capture a child's interest into the conversation, children can continue learning without getting bored. Furthermore, the content of the conversation can be flexibly modified according to the child's responses to maintain their interest. In this way, the conversational learning support department can support children's learning and help them deepen their knowledge.

[0031] The emotion recognition unit recognizes a child's emotions. For example, it analyzes a child's facial expressions to determine whether the child is happy, sad, or anxious. Specifically, it uses a camera to photograph the child's face and image analysis technology to detect changes in facial expressions. For example, it analyzes features such as smiles, tears, and frown lines to determine the child's emotions. The emotion recognition unit can also analyze the tone of a child's voice to determine whether the child is excited or calm. Using voice analysis technology, it analyzes the pitch, volume, and rhythm of the voice to determine the child's emotional state. Furthermore, the emotion recognition unit can analyze a child's physical movements to determine whether the child is relaxed or tense. For example, it analyzes the child's posture, speed of movement, and hand movements to determine their emotional state. As a result, the emotion recognition unit can recognize a child's emotions from multiple perspectives and respond appropriately. The emotion recognition unit utilizes AI technology to improve the accuracy of emotion recognition. For example, it trains a model using deep learning to learn patterns of facial expressions, voice, and movements, thereby improving the accuracy of emotion recognition. Furthermore, the emotion recognition unit can predict changes in a child's emotions based on past data and respond early. For example, it can analyze past data to predict changes in emotions under specific situations and conditions, and provide appropriate dialogue and support. This allows the emotion recognition unit to accurately recognize a child's emotions and respond appropriately.

[0032] The dialogue provider unit provides dialogue that corresponds to the emotions recognized by the emotion recognition unit. For example, if a child is feeling anxious, the dialogue provider unit provides reassuring dialogue using gentle words. Specifically, if the unit recognizes that a child is feeling anxious, it will use calming words such as, "It's okay, let's do our best together." The dialogue provider unit can also provide dialogue using praise if the child is happy. For example, if the child achieves something, it will boost the child's confidence by using praise such as, "That's amazing, you did a great job." Furthermore, if the child is sad, the dialogue provider unit can provide dialogue using words of encouragement. For example, if the child is feeling down after a failure, it will offer encouraging words such as, "I'm sure you'll do better next time, let's do our best together." The dialogue provider unit utilizes AI technology to generate optimal dialogue that corresponds to the child's emotions. For example, it uses natural language processing technology to analyze the child's statements and emotional state and generate appropriate responses. In addition, the dialogue provider unit can learn the child's preferences and reactions based on past dialogue data to provide more personalized dialogue. This allows the dialogue provider to offer appropriate dialogues that respond to the child's emotions, supporting their learning. Furthermore, the dialogue provider can monitor the child's responses in real time and flexibly modify the dialogue content. For example, if the child shows no interest in the dialogue, the dialogue provider can keep the child interested by switching to a different topic. In this way, the dialogue provider can respond flexibly to the child's emotions and support their learning.

[0033] The support department provides learning support based on the learning goals and schedules set by the parents. For example, the support department provides appropriate learning content to the child based on the learning goals set by the parents. Specifically, it suggests appropriate learning materials and programs for the child according to the goals set by the parents and monitors the child's learning progress. The support department can also provide appropriate study time for the child based on the schedule set by the parents. For example, it notifies the child of the start and end times of study according to the schedule set by the parents, helping to establish a learning rhythm. Furthermore, the support department can monitor the child's learning progress based on the learning goals and schedule set by the parents and adjust the learning content and study time as needed. For example, if the child has not reached their learning goal, the support department will suggest additional learning content and extend study time to support goal achievement. The support department utilizes AI technology to analyze the child's learning situation in real time and provide optimal learning support. For example, it analyzes learning data to identify the child's strengths and weaknesses and provides individualized support. The support department also reports the child's learning situation to the parents, enabling them to provide appropriate feedback. This allows the support department to effectively support children's learning and reduce the burden on parents. Furthermore, the support department implements measures to enhance children's motivation to learn. For example, they provide rewards and praise according to learning progress to maintain children's motivation to continue learning. In addition, the support department can flexibly adjust learning plans to suit each child's learning style and pace. In this way, the support department can comprehensively support children's learning and provide an effective learning environment.

[0034] The story generation unit can generate stories tailored to a child's age and interests. For example, if a child is interested in fantasy, the story generation unit will generate a fantasy story. It can also generate an adventure story if a child is interested in adventure. Furthermore, if a child is interested in educational stories, the story generation unit can generate an educational story. This allows for the generation of stories that are tailored to a child's age and interests, thereby stimulating their creativity. Some or all of the processes described above in the story generation unit may be performed using AI, for example, or without AI. For instance, the story generation unit can input data about the child's age and interests into a generating AI, which can then generate a story.

[0035] The support unit may include a reception unit that accepts learning goals and schedules set by parents. For example, the reception unit can accept learning goals and schedules set by parents through an input form. The reception unit can also accept learning goals and schedules set by parents through voice input. Furthermore, the reception unit can accept learning goals and schedules set by parents through a smartphone app. This allows for more effective learning support by accepting learning goals and schedules set by parents. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input the learning goals and schedule data entered by the parent into a generating AI, and have the generating AI perform data analysis.

[0036] The conversational learning support unit can provide knowledge on topics that interest children. For example, if a child is interested in dinosaurs, the conversational learning support unit can provide knowledge about dinosaurs. It can also provide knowledge about space if a child is interested in space. Furthermore, if a child is interested in animals, the conversational learning support unit can provide knowledge about animals. This allows children to deepen their learning by providing knowledge on topics that interest them. Some or all of the above-described processes in the conversational learning support unit may be performed using AI, for example, or without AI. For example, the conversational learning support unit can input data on topics that interest children into a generating AI and have the generating AI provide knowledge.

[0037] The dialogue provider can provide dialogue that provides a sense of security in accordance with the child's emotions. For example, if the child is feeling anxious, the dialogue provider can provide dialogue that provides a sense of security with gentle words. Also, if the child is happy, the dialogue provider can provide dialogue using words of praise. Furthermore, if the child is sad, the dialogue provider can provide dialogue using words of encouragement. In this way, by providing dialogue that provides a sense of security in accordance with the child's emotions, the child can learn with peace of mind. Some or all of the above processing in the dialogue provider may be performed using AI, for example, or without AI. For example, the dialogue provider can input data on the child's emotions into a generating AI and have the generating AI perform the dialogue provision.

[0038] The story generation unit can generate stories that stimulate children's creativity. For example, if a child is interested in adventure, the story generation unit can generate an adventure story. It can also generate a fantasy story if a child is interested in fantasy. Furthermore, if a child is interested in educational stories, the story generation unit can generate an educational story. This allows for the enhancement of children's creativity by generating stories that stimulate their imagination. Some or all of the above-described processes in the story generation unit may be performed using AI, for example, or without AI. For example, the story generation unit can input data about children's interests into a generation AI and have the generation AI generate a story.

[0039] The conversation learning support unit can analyze a child's past conversation history and select the most suitable conversation topics. For example, the conversation learning support unit can prioritize topics that the child has shown interest in in the past. It can also suggest new related topics based on topics the child has frequently discussed in the past. Furthermore, the conversation learning support unit can exclude topics that the child has avoided in the past and select new topics that will pique their interest. This makes it easier to select the most suitable conversation topics by analyzing the child's past conversation history. Some or all of the above processing in the conversation learning support unit may be performed using AI, for example, or without AI. For example, the conversation learning support unit can input the child's past conversation history data into a generating AI and have the generating AI select conversation topics.

[0040] The conversation learning support unit can analyze the child's responses in real time as the conversation progresses and adjust the direction of the conversation accordingly. For example, if the child shows interest, the conversation learning support unit can add questions to delve deeper into that topic. It can also change the topic and suggest a new one if the child appears bored. Furthermore, if the child seems confused, the conversation learning support unit can add simple explanations or examples to aid understanding. This allows for appropriate adjustment of the conversation's direction by analyzing the child's responses in real time as the conversation progresses. Some or all of the above processing in the conversation learning support unit may be performed using AI, for example, or without AI. For example, the conversation learning support unit can input the child's response data into a generating AI, which can then perform the adjustment of the conversation's direction.

[0041] The conversation learning support unit can select conversation topics while considering the child's learning progress. For example, the conversation learning support unit can select a topic to review what the child has recently learned. It can also select a topic to prepare for what the child will learn next. Furthermore, it can select a topic to reinforce areas where the child is struggling. By selecting topics while considering the child's learning progress, the learning effect can be enhanced. Some or all of the above processing in the conversation learning support unit may be performed using AI, for example, or without AI. For example, the conversation learning support unit can input the child's learning progress data into a generating AI and have the generating AI select conversation topics.

[0042] The conversation learning support unit can use visual content in conjunction with conversation topics to capture children's interest. For example, the conversation learning support unit can display images or videos related to topics that children are interested in. It can also provide interactive quizzes and games to keep children engaged with the topic. Furthermore, it can use diagrams and animations to explain things in a way that is easy for children to understand. This makes it easier to capture children's interest by using visual content. Some or all of the above processing in the conversation learning support unit may be performed using AI, for example, or not. For example, the conversation learning support unit can input visual content data into a generating AI and have the generating AI select the content.

[0043] The emotion recognition unit can identify emotions by analyzing a child's facial expressions and tone of voice during emotion recognition. For example, the emotion recognition unit can capture a child's facial expressions with a camera and analyze the emotions. It can also collect a child's tone of voice with a microphone and identify emotions. Furthermore, the emotion recognition unit can combine facial expressions and tone of voice to perform more accurate emotion recognition. This allows for more accurate identification of emotions by analyzing a child's facial expressions and tone of voice. Some or all of the above processing in the emotion recognition unit may be performed using AI, for example, or without AI. For example, the emotion recognition unit can input the child's facial expression data and tone of voice data into a generating AI and have the generating AI perform emotion identification.

[0044] The emotion recognition unit can improve its recognition accuracy by referring to the child's past emotional data during emotion recognition. For example, the emotion recognition unit can store and refer to the child's past emotional data in a database. It can also predict the child's current emotion based on past emotional data. Furthermore, the emotion recognition unit can train its emotion recognition algorithm using past emotional data. This allows for improved emotion recognition accuracy by referring to past emotional data. Some or all of the above processes in the emotion recognition unit may be performed using AI, for example, or without AI. For example, the emotion recognition unit can input the child's past emotional data into a generating AI and have the generating AI improve the accuracy of emotion recognition.

[0045] The emotion recognition unit can identify emotions by analyzing a child's physical movements during emotion recognition. For example, the emotion recognition unit can capture a child's physical movements with a camera and analyze the emotions. The emotion recognition unit can also identify emotions by analyzing a child's movement patterns. Furthermore, the emotion recognition unit can perform more accurate emotion recognition by combining physical movements, facial expressions, and tone of voice. This allows for more accurate identification of emotions by analyzing physical movements. Some or all of the above processing in the emotion recognition unit may be performed using AI, for example, or without AI. For example, the emotion recognition unit can input the child's physical movement data into a generating AI and have the generating AI perform emotion identification.

[0046] The emotion recognition unit can identify a child's emotions by analyzing ambient sounds around them during emotion recognition. For example, the emotion recognition unit collects ambient sounds using a microphone and analyzes the emotions. It can also identify a child's emotions by analyzing changes in ambient sounds. Furthermore, the emotion recognition unit can perform more accurate emotion recognition by combining ambient sounds with facial expressions and tone of voice. This allows for more accurate identification of emotions by analyzing ambient sounds. Some or all of the above processing in the emotion recognition unit may be performed using AI, for example, or without AI. For example, the emotion recognition unit can input ambient sound data from around the child into a generating AI and have the generating AI perform emotion identification.

[0047] The dialogue provider unit can provide optimal dialogue content by referring to the child's past dialogue history when providing dialogue. For example, the dialogue provider unit can provide dialogue content based on themes the child has shown interest in in the past. It can also exclude themes the child has avoided in the past and provide dialogue content that will interest the child. Furthermore, the dialogue provider unit can analyze the child's past dialogue history and provide optimal dialogue content. In this way, by referring to past dialogue history, it can provide dialogue content that is optimal for the child. Some or all of the above processing in the dialogue provider unit may be performed using AI, for example, or without using AI. For example, the dialogue provider unit can input the child's past dialogue history data into a generating AI and have the generating AI perform the task of providing dialogue content.

[0048] The dialogue provider can adjust the tone and language of the dialogue according to the child's age and interests when providing dialogue. For example, if the child is young, the dialogue provider will use simple language. If the child is older, the dialogue provider can also use more complex language. Furthermore, the dialogue provider can adjust the tone of the dialogue according to the child's interests. By adjusting the tone and language of the dialogue according to the child's age and interests, a more effective dialogue can be provided. Some or all of the above processing in the dialogue provider may be performed using AI, for example, or without AI. For example, the dialogue provider can input data on the child's age and interests into a generating AI and have the generating AI perform the adjustment of the tone and language of the dialogue.

[0049] The dialogue provider can customize the content of the dialogue based on the child's learning objectives when providing dialogue. For example, the dialogue provider can provide relevant dialogue content in accordance with the child's learning objectives. The dialogue provider can also adjust the dialogue content according to the child's learning progress. Furthermore, the dialogue provider can customize the dialogue content to help the child achieve their learning objectives. By customizing the dialogue content based on the child's learning objectives, the learning effect can be enhanced. Some or all of the above processing in the dialogue provider may be performed using AI, for example, or without AI. For example, the dialogue provider can input the child's learning objective data into a generating AI and have the generating AI perform the customization of the dialogue content.

[0050] The dialogue provider can use music and sound effects in conjunction with dialogue to capture a child's attention. For example, the dialogue provider can play music related to a topic that interests the child. It can also use sound effects to make the child interested in the topic. Furthermore, the dialogue provider can use music and sound effects in conjunction with explanations to make them easier for the child to understand. In this way, using music and sound effects makes it easier to capture a child's attention. Some or all of the above processing in the dialogue provider may be performed using AI, for example, or without AI. For example, the dialogue provider can input music and sound effect data into a generating AI and have the generating AI select the music and sound effects.

[0051] The support unit can select the optimal support method by referring to the child's past learning data when providing learning support. For example, the support unit selects the optimal support method based on the child's past learning data. The support unit can also adjust the support method according to the child's learning progress. Furthermore, the support unit can select a support method that matches the child's learning style. This makes it easier to select the optimal support method by referring to past learning data. Some or all of the above processing in the support unit may be performed using AI, for example, or without AI. For example, the support unit can input the child's past learning data into a generating AI and have the generating AI select a support method.

[0052] The support unit can analyze the child's learning progress in real time and adjust the support provided during learning support. For example, the support unit can monitor the child's learning progress in real time and adjust the support as needed. The support unit can also provide additional support if the child is struggling with a particular task. Furthermore, if the child achieves a goal, the support unit can set a new learning goal and update the support. This allows for the provision of appropriate support by analyzing learning progress in real time. Some or all of the above processes in the support unit may be performed using AI, for example, or not. For example, the support unit can input the child's learning progress data into a generating AI and have the generating AI adjust the support.

[0053] The support unit can customize its support methods according to the child's learning style during learning support. For example, if the child has a visual learning style, the support unit can provide support using diagrams and videos. If the child has an auditory learning style, the support unit can also provide support using audio and music. Furthermore, if the child has an experiential learning style, the support unit can provide support through interactive activities. By customizing the support methods according to the child's learning style, the support unit can provide optimal learning support. Some or all of the above processing in the support unit may be performed using AI, for example, or without AI. For example, the support unit can input the child's learning style data into a generating AI and have the generating AI customize the support methods.

[0054] The support unit can incorporate game elements to engage children during learning support. For example, the support unit can present learning content in a game format to capture children's interest. The support unit can also provide points or rewards based on learning progress. Furthermore, the support unit can present learning content in a quiz format to deepen children's understanding. This makes it easier to engage children by incorporating game elements. Some or all of the above processes in the support unit may be performed using AI, for example, or without AI. For example, the support unit can input game element data into a generating AI and have the generating AI select game elements.

[0055] The story generation unit can generate the most suitable story by referring to the child's past story history during story generation. For example, the story generation unit can generate a new story based on themes from stories the child has enjoyed in the past. It can also generate an interesting story by excluding themes the child has avoided in the past. Furthermore, the story generation unit can analyze the child's past story history and generate the most suitable story. In this way, by referring to past story history, it can generate the most suitable story for the child. Some or all of the above processes in the story generation unit may be performed using AI, for example, or without AI. For example, the story generation unit can input the child's past story history data into a generation AI and have the generation AI perform story generation.

[0056] The story generation unit can adjust the tone and theme of a story according to the child's age and interests during story generation. For example, if the child is young, the story generation unit can generate a story using simple language. Conversely, if the child is older, the story generation unit can generate a story using more complex language. Furthermore, the story generation unit can adjust the tone and theme of the story according to the child's interests. This allows the system to provide children with stories that are optimal for them by adjusting the tone and theme of the story according to their age and interests. Some or all of the above-described processes in the story generation unit may be performed using AI, for example, or not. For example, the story generation unit can input data about the child's age and interests into a generation AI and have the generation AI perform adjustments to the tone and theme of the story.

[0057] The story generation unit can customize the story content based on the child's learning objectives during story generation. For example, the story generation unit provides relevant story content in line with the child's learning objectives. The story generation unit can also adjust the story content according to the child's learning progress. Furthermore, the story generation unit can customize the story content to help the child achieve their learning objectives. This allows for enhanced learning effectiveness by customizing the story content based on learning objectives. Some or all of the above-described processes in the story generation unit may be performed using AI, for example, or without AI. For instance, the story generation unit can input the child's learning objective data into a generation AI and have the generation AI customize the story content.

[0058] The story generation unit can use visual content in conjunction with story generation to capture children's interest. For example, the story generation unit can display images or videos related to themes that children are interested in. It can also provide interactive quizzes or games to engage children's interest in the topic. Furthermore, the story generation unit can use diagrams and animations to explain things in a way that is easy for children to understand. This makes it easier to capture children's interest by using visual content. Some or all of the above processes in the story generation unit may be performed using AI, for example, or not. For example, the story generation unit can input visual content data into a generation AI and have the generation AI select the content.

[0059] The reception unit can select the optimal reception method by referring to the parent's past setting history at the time of reception. For example, the reception unit can select the optimal reception method based on the learning goals and schedules that the parent has set in the past. The reception unit can also analyze the parent's past setting history and suggest the optimal reception method. Furthermore, the reception unit can prioritize suggesting setting methods that the parent has used in the past. This makes it easier to select the optimal reception method by referring to past setting history. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input the parent's past setting history data into a generating AI and have the generating AI perform the selection of the reception method.

[0060] The reception unit can select the optimal reception method at the time of reception, taking into account the parent's device information. For example, if the parent is using a smartphone, the reception unit can provide a reception method that matches the screen size. Furthermore, if the parent is using a tablet, the reception unit can provide a reception method optimized for a larger screen. Additionally, if the parent is using a smartwatch, the reception unit can provide a concise and highly visible reception method. In this way, the reception unit can provide the optimal reception method by considering the parent's device information. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input the parent's device information into a generating AI and have the generating AI select a reception method.

[0061] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0062] The Conversational Learning Support Unit can monitor a child's learning progress in real time and provide feedback tailored to their progress. For example, when a child completes a specific task, the Conversational Learning Support Unit will offer praise and guidance for the next step. It can also provide additional hints and support if a child is struggling with a task. Furthermore, based on the child's learning progress, the Conversational Learning Support Unit can suggest what to learn next. This allows for real-time monitoring of a child's learning progress and the provision of appropriate feedback, thereby enhancing learning effectiveness.

[0063] The support system can visualize a child's learning progress based on learning goals and schedules set by parents. For example, the support system displays a child's learning progress in graphs and charts. It can also allow parents to check learning progress through a smartphone app. Furthermore, the support system can provide alerts and reminders based on learning progress. This makes it easier for parents to understand their child's learning progress and provide appropriate support.

[0064] The dialogue provider can customize the method of dialogue according to the child's learning style. For example, if the child has a visual learning style, the dialogue provider can provide dialogue using diagrams and illustrations. If the child has an auditory learning style, the dialogue provider can also provide dialogue using sound and music. Furthermore, if the child has an experiential learning style, the dialogue provider can provide interactive dialogue. By customizing the dialogue method according to the child's learning style, learning effectiveness can be enhanced.

[0065] The Conversation Learning Support Department can analyze a child's past learning data and propose an optimal learning plan. For example, it can suggest what the child should learn next based on what they have learned in the past. It can also propose a plan to reinforce areas where the child has struggled in the past. Furthermore, it can propose a plan that matches the child's learning pace. In this way, by analyzing past learning data, it can provide the optimal learning plan for each child.

[0066] The support team can report on a child's learning progress based on the learning goals and schedules set by the parents. For example, the support team can send parents regular progress reports. The support team can also allow parents to check their child's learning progress through a smartphone app. Furthermore, the support team can provide alerts and reminders based on the child's learning progress. This makes it easier for parents to understand their child's learning progress and provide appropriate support.

[0067] The following briefly describes the processing flow for example form 1.

[0068] Step 1: The Conversational Learning Support Department engages in conversations about topics that interest the child. For example, if the child is interested in dinosaurs, the department provides information about dinosaurs and helps deepen that knowledge through dialogue. Similarly, it provides information about space and animals and helps deepen that knowledge through dialogue. Step 2: The emotion recognition unit recognizes the child's emotions. For example, it analyzes the child's facial expressions, tone of voice, and body movements to recognize whether the child is happy, sad, anxious, excited, calm, relaxed, or tense. Step 3: The dialogue provider unit provides dialogue that corresponds to the emotion recognized by the emotion recognition unit. For example, if a child is feeling anxious, the dialogue provides reassurance with gentle words; if the child is happy, it provides praise; and if the child is sad, it provides words of encouragement. Step 4: The support team provides learning support based on the learning goals and schedule set by the parents. For example, they provide appropriate learning content based on the learning goals set by the parents and appropriate study time based on the schedule. They also monitor learning progress and adjust the learning content and study time as needed.

[0069] (Example of form 2) The conversational learning support system according to an embodiment of the present invention is a system that uses AI to provide a conversation partner to support a child's learning and growth. This system converses with the child on topics that interest them and helps them deepen their knowledge. It also recognizes the child's emotions and responds accordingly, providing a sense of security. This reduces the burden on parents and creates an environment where children can learn in an enjoyable way. For example, if a child is interested in dinosaurs, the AI ​​in the conversational learning support system provides knowledge about dinosaurs and helps the child deepen that knowledge through dialogue. This allows the child to learn in an enjoyable way. Next, the conversational learning support system's AI recognizes the child's emotions and responds accordingly. For example, if a child is feeling anxious, the AI ​​engages in conversation with gentle words to provide reassurance. This allows the child to learn with peace of mind. Furthermore, the conversational learning support system's AI generates stories tailored to the child's age and interests, stimulating the child's creativity. For example, if a child is interested in space, the AI ​​generates a story with a space theme, and the child can enjoy the story together with the AI. This mechanism reduces the burden on parents and creates an environment where children can learn in an enjoyable way. Parents can support their children's learning and growth without being overwhelmed by work or household chores. Furthermore, children can receive a high-quality education and appropriate emotional care. For example, in dual-income households, parents are often too busy with work and household chores to spend enough time with their children. Even in such cases, AI can support children's learning and growth, reducing the burden on parents and providing an environment where children can learn happily. AI also recognizes children's emotions and provides appropriate dialogue, thus providing emotional care. This allows children to learn with peace of mind, and parents to entrust their children to it with confidence. In this way, an AI-powered conversation partner is an effective means of supporting children's learning and growth and reducing the burden on parents. Thus, a conversational learning support system can support children's learning and growth and reduce the burden on parents.

[0070] The conversational learning support system according to this embodiment comprises a conversational learning support unit, an emotion recognition unit, a dialogue provision unit, and a support unit. The conversational learning support unit engages in conversation on themes that the child is interested in. For example, if the child is interested in dinosaurs, the conversational learning support unit provides knowledge about dinosaurs and helps the child deepen that knowledge through dialogue. The conversational learning support unit can also provide knowledge about space if the child is interested in space and help the child deepen that knowledge through dialogue. Furthermore, if the child is interested in animals, the conversational learning support unit can provide knowledge about animals and help the child deepen that knowledge through dialogue. The emotion recognition unit recognizes the child's emotions. For example, the emotion recognition unit analyzes the child's facial expressions and recognizes whether the child is happy, sad, or anxious. The emotion recognition unit can also analyze the child's tone of voice and recognize whether the child is excited or calm. Furthermore, the emotion recognition unit can analyze the child's body movements and recognize whether the child is relaxed or tense. The dialogue provision unit provides dialogue corresponding to the emotions recognized by the emotion recognition unit. For example, the dialogue provider unit can provide reassuring dialogue using gentle words when a child is feeling anxious. It can also use praise when a child is happy. Furthermore, it can use encouraging words when a child is sad. The support unit provides learning support based on the learning goals and schedule set by the parents. For example, the support unit provides appropriate learning content to the child based on the learning goals set by the parents. It can also provide appropriate study time to the child based on the schedule set by the parents. Furthermore, the support unit can monitor the child's learning progress based on the learning goals and schedule set by the parents and adjust the learning content and study time as needed. As a result, the conversational learning support system according to this embodiment can support the child's learning and growth and reduce the burden on parents.

[0071] The Conversational Learning Support Department engages in conversations on topics that interest children. For example, if a child is interested in dinosaurs, the department provides knowledge about dinosaurs and helps deepen that knowledge through dialogue. Specifically, they explain in detail the types of dinosaurs, their ecology, and their evolutionary process, and answer any questions the child may have immediately. They can also keep the child interested through dinosaur quizzes and games. Furthermore, if a child is interested in space, the department can provide knowledge about space and help deepen that knowledge through dialogue. For example, they explain planets, constellations, and the history of space exploration, and provide detailed information if the child has questions about space. This allows the child to learn deeply about the topic that interests them. Also, if a child is interested in animals, the department can provide knowledge about animals and help deepen that knowledge through dialogue. For example, they explain the ecology, habits, and conservation efforts of animals, and answer any questions the child may have with specific examples. This allows the child to deepen their understanding of animals. The Conversational Learning Support Department employs various methods to engage children's interest and make learning enjoyable. For example, by incorporating episodes and stories that capture a child's interest into the conversation, children can continue learning without getting bored. Furthermore, the content of the conversation can be flexibly modified according to the child's responses to maintain their interest. In this way, the conversational learning support department can support children's learning and help them deepen their knowledge.

[0072] The emotion recognition unit recognizes a child's emotions. For example, it analyzes a child's facial expressions to determine whether the child is happy, sad, or anxious. Specifically, it uses a camera to photograph the child's face and image analysis technology to detect changes in facial expressions. For example, it analyzes features such as smiles, tears, and frown lines to determine the child's emotions. The emotion recognition unit can also analyze the tone of a child's voice to determine whether the child is excited or calm. Using voice analysis technology, it analyzes the pitch, volume, and rhythm of the voice to determine the child's emotional state. Furthermore, the emotion recognition unit can analyze a child's physical movements to determine whether the child is relaxed or tense. For example, it analyzes the child's posture, speed of movement, and hand movements to determine their emotional state. As a result, the emotion recognition unit can recognize a child's emotions from multiple perspectives and respond appropriately. The emotion recognition unit utilizes AI technology to improve the accuracy of emotion recognition. For example, it trains a model using deep learning to learn patterns of facial expressions, voice, and movements, thereby improving the accuracy of emotion recognition. Furthermore, the emotion recognition unit can predict changes in a child's emotions based on past data and respond early. For example, it can analyze past data to predict changes in emotions under specific situations and conditions, and provide appropriate dialogue and support. This allows the emotion recognition unit to accurately recognize a child's emotions and respond appropriately.

[0073] The dialogue provider unit provides dialogue that corresponds to the emotions recognized by the emotion recognition unit. For example, if a child is feeling anxious, the dialogue provider unit provides reassuring dialogue using gentle words. Specifically, if the unit recognizes that a child is feeling anxious, it will use calming words such as, "It's okay, let's do our best together." The dialogue provider unit can also provide dialogue using praise if the child is happy. For example, if the child achieves something, it will boost the child's confidence by using praise such as, "That's amazing, you did a great job." Furthermore, if the child is sad, the dialogue provider unit can provide dialogue using words of encouragement. For example, if the child is feeling down after a failure, it will offer encouraging words such as, "I'm sure you'll do better next time, let's do our best together." The dialogue provider unit utilizes AI technology to generate optimal dialogue that corresponds to the child's emotions. For example, it uses natural language processing technology to analyze the child's statements and emotional state and generate appropriate responses. In addition, the dialogue provider unit can learn the child's preferences and reactions based on past dialogue data to provide more personalized dialogue. This allows the dialogue provider to offer appropriate dialogues that respond to the child's emotions, supporting their learning. Furthermore, the dialogue provider can monitor the child's responses in real time and flexibly modify the dialogue content. For example, if the child shows no interest in the dialogue, the dialogue provider can keep the child interested by switching to a different topic. In this way, the dialogue provider can respond flexibly to the child's emotions and support their learning.

[0074] The support department provides learning support based on the learning goals and schedules set by the parents. For example, the support department provides appropriate learning content to the child based on the learning goals set by the parents. Specifically, it suggests appropriate learning materials and programs for the child according to the goals set by the parents and monitors the child's learning progress. The support department can also provide appropriate study time for the child based on the schedule set by the parents. For example, it notifies the child of the start and end times of study according to the schedule set by the parents, helping to establish a learning rhythm. Furthermore, the support department can monitor the child's learning progress based on the learning goals and schedule set by the parents and adjust the learning content and study time as needed. For example, if the child has not reached their learning goal, the support department will suggest additional learning content and extend study time to support goal achievement. The support department utilizes AI technology to analyze the child's learning situation in real time and provide optimal learning support. For example, it analyzes learning data to identify the child's strengths and weaknesses and provides individualized support. The support department also reports the child's learning situation to the parents, enabling them to provide appropriate feedback. This allows the support department to effectively support children's learning and reduce the burden on parents. Furthermore, the support department implements measures to enhance children's motivation to learn. For example, they provide rewards and praise according to learning progress to maintain children's motivation to continue learning. In addition, the support department can flexibly adjust learning plans to suit each child's learning style and pace. In this way, the support department can comprehensively support children's learning and provide an effective learning environment.

[0075] The story generation unit can generate stories tailored to a child's age and interests. For example, if a child is interested in fantasy, the story generation unit will generate a fantasy story. It can also generate an adventure story if a child is interested in adventure. Furthermore, if a child is interested in educational stories, the story generation unit can generate an educational story. This allows for the generation of stories that are tailored to a child's age and interests, thereby stimulating their creativity. Some or all of the processes described above in the story generation unit may be performed using AI, for example, or without AI. For instance, the story generation unit can input data about the child's age and interests into a generating AI, which can then generate a story.

[0076] The support unit may include a reception unit that accepts learning goals and schedules set by parents. For example, the reception unit can accept learning goals and schedules set by parents through an input form. The reception unit can also accept learning goals and schedules set by parents through voice input. Furthermore, the reception unit can accept learning goals and schedules set by parents through a smartphone app. This allows for more effective learning support by accepting learning goals and schedules set by parents. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input the learning goals and schedule data entered by the parent into a generating AI, and have the generating AI perform data analysis.

[0077] The conversational learning support unit can provide knowledge on topics that interest children. For example, if a child is interested in dinosaurs, the conversational learning support unit can provide knowledge about dinosaurs. It can also provide knowledge about space if a child is interested in space. Furthermore, if a child is interested in animals, the conversational learning support unit can provide knowledge about animals. This allows children to deepen their learning by providing knowledge on topics that interest them. Some or all of the above-described processes in the conversational learning support unit may be performed using AI, for example, or without AI. For example, the conversational learning support unit can input data on topics that interest children into a generating AI and have the generating AI provide knowledge.

[0078] The dialogue provider can provide dialogue that provides a sense of security in accordance with the child's emotions. For example, if the child is feeling anxious, the dialogue provider can provide dialogue that provides a sense of security with gentle words. Also, if the child is happy, the dialogue provider can provide dialogue using words of praise. Furthermore, if the child is sad, the dialogue provider can provide dialogue using words of encouragement. In this way, by providing dialogue that provides a sense of security in accordance with the child's emotions, the child can learn with peace of mind. Some or all of the above processing in the dialogue provider may be performed using AI, for example, or without AI. For example, the dialogue provider can input data on the child's emotions into a generating AI and have the generating AI perform the dialogue provision.

[0079] The story generation unit can generate stories that stimulate children's creativity. For example, if a child is interested in adventure, the story generation unit can generate an adventure story. It can also generate a fantasy story if a child is interested in fantasy. Furthermore, if a child is interested in educational stories, the story generation unit can generate an educational story. This allows for the enhancement of children's creativity by generating stories that stimulate their imagination. Some or all of the above-described processes in the story generation unit may be performed using AI, for example, or without AI. For example, the story generation unit can input data about children's interests into a generation AI and have the generation AI generate a story.

[0080] The conversation learning support unit can estimate a child's emotions and select conversation topics based on those estimated emotions. For example, if the child is excited, the conversation learning support unit can select energetic topics (e.g., sports or adventure). If the child is calm, the conversation learning support unit can also select calm topics (e.g., reading or nature). Furthermore, if the child is feeling anxious, the conversation learning support unit can select reassuring topics (e.g., family or friends). By selecting conversation topics based on the child's emotions, it becomes easier to capture the child's interest. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the conversation learning support unit may be performed using AI, or not using AI. For example, the conversation learning support unit can input data about the child's emotions into a generative AI and have the generative AI select conversation topics.

[0081] The conversation learning support unit can analyze a child's past conversation history and select the most suitable conversation topics. For example, the conversation learning support unit can prioritize topics that the child has shown interest in in the past. It can also suggest new related topics based on topics the child has frequently discussed in the past. Furthermore, the conversation learning support unit can exclude topics that the child has avoided in the past and select new topics that will pique their interest. This makes it easier to select the most suitable conversation topics by analyzing the child's past conversation history. Some or all of the above processing in the conversation learning support unit may be performed using AI, for example, or without AI. For example, the conversation learning support unit can input the child's past conversation history data into a generating AI and have the generating AI select conversation topics.

[0082] The conversation learning support unit can analyze the child's responses in real time as the conversation progresses and adjust the direction of the conversation accordingly. For example, if the child shows interest, the conversation learning support unit can add questions to delve deeper into that topic. It can also change the topic and suggest a new one if the child appears bored. Furthermore, if the child seems confused, the conversation learning support unit can add simple explanations or examples to aid understanding. This allows for appropriate adjustment of the conversation's direction by analyzing the child's responses in real time as the conversation progresses. Some or all of the above processing in the conversation learning support unit may be performed using AI, for example, or without AI. For example, the conversation learning support unit can input the child's response data into a generating AI, which can then perform the adjustment of the conversation's direction.

[0083] The conversation learning support unit can estimate a child's emotions and adjust the conversation tempo based on the estimated emotions. For example, if the child is excited, the conversation learning support unit will provide a fast-paced conversation. It can also proceed at a slower pace if the child is calm. Furthermore, if the child is feeling anxious, the conversation learning support unit can conduct a reassuring conversation at a calm pace. By adjusting the conversation tempo based on the child's emotions, the child can enjoy the conversation more comfortably. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the conversation learning support unit may be performed using AI, or not. For example, the conversation learning support unit can input child emotion data into a generative AI and have the generative AI adjust the conversation tempo.

[0084] The conversation learning support unit can select conversation topics while considering the child's learning progress. For example, the conversation learning support unit can select a topic to review what the child has recently learned. It can also select a topic to prepare for what the child will learn next. Furthermore, it can select a topic to reinforce areas where the child is struggling. By selecting topics while considering the child's learning progress, the learning effect can be enhanced. Some or all of the above processing in the conversation learning support unit may be performed using AI, for example, or without AI. For example, the conversation learning support unit can input the child's learning progress data into a generating AI and have the generating AI select conversation topics.

[0085] The conversation learning support unit can use visual content in conjunction with conversation topics to capture children's interest. For example, the conversation learning support unit can display images or videos related to topics that children are interested in. It can also provide interactive quizzes and games to keep children engaged with the topic. Furthermore, it can use diagrams and animations to explain things in a way that is easy for children to understand. This makes it easier to capture children's interest by using visual content. Some or all of the above processing in the conversation learning support unit may be performed using AI, for example, or not. For example, the conversation learning support unit can input visual content data into a generating AI and have the generating AI select the content.

[0086] The emotion recognition unit can estimate a child's emotions and optimize the emotion recognition algorithm based on the estimated emotions. For example, the emotion recognition unit can collect child emotion data to improve the accuracy of the algorithm. It can also track changes in the child's emotions in real time and adjust the algorithm accordingly. Furthermore, the emotion recognition unit can provide feedback tailored to the child's emotions to facilitate algorithm learning. This allows for improved emotion recognition accuracy by optimizing the emotion recognition algorithm. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the emotion recognition unit may be performed using AI or not. For example, the emotion recognition unit can input child emotion data into a generative AI and have the generative AI optimize the algorithm.

[0087] The emotion recognition unit can identify emotions by analyzing a child's facial expressions and tone of voice during emotion recognition. For example, the emotion recognition unit can capture a child's facial expressions with a camera and analyze the emotions. It can also collect a child's tone of voice with a microphone and identify emotions. Furthermore, the emotion recognition unit can combine facial expressions and tone of voice to perform more accurate emotion recognition. This allows for more accurate identification of emotions by analyzing a child's facial expressions and tone of voice. Some or all of the above processing in the emotion recognition unit may be performed using AI, for example, or without AI. For example, the emotion recognition unit can input the child's facial expression data and tone of voice data into a generating AI and have the generating AI perform emotion identification.

[0088] The emotion recognition unit can improve its recognition accuracy by referring to the child's past emotional data during emotion recognition. For example, the emotion recognition unit can store and refer to the child's past emotional data in a database. It can also predict the child's current emotion based on past emotional data. Furthermore, the emotion recognition unit can train its emotion recognition algorithm using past emotional data. This allows for improved emotion recognition accuracy by referring to past emotional data. Some or all of the above processes in the emotion recognition unit may be performed using AI, for example, or without AI. For example, the emotion recognition unit can input the child's past emotional data into a generating AI and have the generating AI improve the accuracy of emotion recognition.

[0089] The emotion recognition unit can estimate a child's emotions and adjust the frequency of emotion recognition based on the estimated emotions. For example, if a child is excited, the emotion recognition unit will frequently recognize emotions and adjust its response accordingly. It can also reduce the frequency of emotion recognition when a child is calm to maintain a natural conversation. Furthermore, if a child is anxious, the emotion recognition unit can increase the frequency of emotion recognition to provide reassurance. This allows for appropriate responses to the child's emotions by adjusting the frequency of emotion recognition. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the emotion recognition unit may be performed using AI, or not. For example, the emotion recognition unit can input child emotion data into a generative AI and have the generative AI adjust the frequency of emotion recognition.

[0090] The emotion recognition unit can identify emotions by analyzing a child's physical movements during emotion recognition. For example, the emotion recognition unit can capture a child's physical movements with a camera and analyze the emotions. The emotion recognition unit can also identify emotions by analyzing a child's movement patterns. Furthermore, the emotion recognition unit can perform more accurate emotion recognition by combining physical movements, facial expressions, and tone of voice. This allows for more accurate identification of emotions by analyzing physical movements. Some or all of the above processing in the emotion recognition unit may be performed using AI, for example, or without AI. For example, the emotion recognition unit can input the child's physical movement data into a generating AI and have the generating AI perform emotion identification.

[0091] The emotion recognition unit can identify a child's emotions by analyzing ambient sounds around them during emotion recognition. For example, the emotion recognition unit collects ambient sounds using a microphone and analyzes the emotions. It can also identify a child's emotions by analyzing changes in ambient sounds. Furthermore, the emotion recognition unit can perform more accurate emotion recognition by combining ambient sounds with facial expressions and tone of voice. This allows for more accurate identification of emotions by analyzing ambient sounds. Some or all of the above processing in the emotion recognition unit may be performed using AI, for example, or without AI. For example, the emotion recognition unit can input ambient sound data from around the child into a generating AI and have the generating AI perform emotion identification.

[0092] The dialogue provider can estimate a child's emotions and adjust the content of the dialogue based on the estimated emotions. For example, if the child is excited, the dialogue provider can provide an energetic dialogue. It can also provide a calm dialogue if the child is calm. Furthermore, if the child is feeling anxious, the dialogue provider can provide a reassuring dialogue. This allows for the provision of the most appropriate dialogue for the child by adjusting the content based on their emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the dialogue provider may be performed using AI, or not. For example, the dialogue provider can input the child's emotion data into a generative AI and have the generative AI adjust the dialogue content.

[0093] The dialogue provider unit can provide optimal dialogue content by referring to the child's past dialogue history when providing dialogue. For example, the dialogue provider unit can provide dialogue content based on themes the child has shown interest in in the past. It can also exclude themes the child has avoided in the past and provide dialogue content that will interest the child. Furthermore, the dialogue provider unit can analyze the child's past dialogue history and provide optimal dialogue content. In this way, by referring to past dialogue history, it can provide dialogue content that is optimal for the child. Some or all of the above processing in the dialogue provider unit may be performed using AI, for example, or without using AI. For example, the dialogue provider unit can input the child's past dialogue history data into a generating AI and have the generating AI perform the task of providing dialogue content.

[0094] The dialogue provider can adjust the tone and language of the dialogue according to the child's age and interests when providing dialogue. For example, if the child is young, the dialogue provider will use simple language. If the child is older, the dialogue provider can also use more complex language. Furthermore, the dialogue provider can adjust the tone of the dialogue according to the child's interests. By adjusting the tone and language of the dialogue according to the child's age and interests, a more effective dialogue can be provided. Some or all of the above processing in the dialogue provider may be performed using AI, for example, or without AI. For example, the dialogue provider can input data on the child's age and interests into a generating AI and have the generating AI perform the adjustment of the tone and language of the dialogue.

[0095] The dialogue provider can estimate a child's emotions and adjust the length of the dialogue based on the estimated emotions. For example, if the child is excited, the dialogue provider can provide a longer dialogue. It can also provide a shorter dialogue if the child is calm. Furthermore, if the child is anxious, it can provide a dialogue of an appropriate length. This allows for the provision of an optimal dialogue length for the child by adjusting the length based on their emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the dialogue provider may be performed using AI, or not. For example, the dialogue provider can input child emotion data into a generative AI and have the generative AI adjust the length of the dialogue.

[0096] The dialogue provider can customize the content of the dialogue based on the child's learning objectives when providing dialogue. For example, the dialogue provider can provide relevant dialogue content in accordance with the child's learning objectives. The dialogue provider can also adjust the dialogue content according to the child's learning progress. Furthermore, the dialogue provider can customize the dialogue content to help the child achieve their learning objectives. By customizing the dialogue content based on the child's learning objectives, the learning effect can be enhanced. Some or all of the above processing in the dialogue provider may be performed using AI, for example, or without AI. For example, the dialogue provider can input the child's learning objective data into a generating AI and have the generating AI perform the customization of the dialogue content.

[0097] The dialogue provider can use music and sound effects in conjunction with dialogue to capture a child's attention. For example, the dialogue provider can play music related to a topic that interests the child. It can also use sound effects to make the child interested in the topic. Furthermore, the dialogue provider can use music and sound effects in conjunction with explanations to make them easier for the child to understand. In this way, using music and sound effects makes it easier to capture a child's attention. Some or all of the above processing in the dialogue provider may be performed using AI, for example, or without AI. For example, the dialogue provider can input music and sound effect data into a generating AI and have the generating AI select the music and sound effects.

[0098] The support unit can estimate a child's emotions and adjust its learning support methods based on those estimates. For example, if a child is excited, the support unit can provide energetic learning support. If a child is calm, it can provide gentle learning support. Furthermore, if a child is feeling anxious, it can provide reassuring learning support. By adjusting the learning support methods based on the child's emotions, the support unit can provide the optimal learning support for the child. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the support unit may be performed using AI, for example, or not using AI. For example, the support unit can input child emotion data into a generative AI and have the generative AI adjust the learning support methods.

[0099] The support unit can select the optimal support method by referring to the child's past learning data when providing learning support. For example, the support unit selects the optimal support method based on the child's past learning data. The support unit can also adjust the support method according to the child's learning progress. Furthermore, the support unit can select a support method that matches the child's learning style. This makes it easier to select the optimal support method by referring to past learning data. Some or all of the above processing in the support unit may be performed using AI, for example, or without AI. For example, the support unit can input the child's past learning data into a generating AI and have the generating AI select a support method.

[0100] The support unit can analyze the child's learning progress in real time and adjust the support provided during learning support. For example, the support unit can monitor the child's learning progress in real time and adjust the support as needed. The support unit can also provide additional support if the child is struggling with a particular task. Furthermore, if the child achieves a goal, the support unit can set a new learning goal and update the support. This allows for the provision of appropriate support by analyzing learning progress in real time. Some or all of the above processes in the support unit may be performed using AI, for example, or not. For example, the support unit can input the child's learning progress data into a generating AI and have the generating AI adjust the support.

[0101] The support unit can estimate the child's emotions and adjust the frequency of learning support based on the estimated emotions. For example, if the child is excited, the support unit can provide learning support more frequently. It can also provide learning support at a moderate frequency if the child is calm. Furthermore, if the child is feeling anxious, the support unit can provide learning support more frequently to reassure them. By adjusting the frequency of learning support, the system can provide optimal learning support for the child. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the support unit may be performed using AI, or not. For example, the support unit can input the child's emotion data into a generative AI and have the generative AI adjust the learning support frequency.

[0102] The support unit can customize its support methods according to the child's learning style during learning support. For example, if the child has a visual learning style, the support unit can provide support using diagrams and videos. If the child has an auditory learning style, the support unit can also provide support using audio and music. Furthermore, if the child has an experiential learning style, the support unit can provide support through interactive activities. By customizing the support methods according to the child's learning style, the support unit can provide optimal learning support. Some or all of the above processing in the support unit may be performed using AI, for example, or without AI. For example, the support unit can input the child's learning style data into a generating AI and have the generating AI customize the support methods.

[0103] The support unit can incorporate game elements to engage children during learning support. For example, the support unit can present learning content in a game format to capture children's interest. The support unit can also provide points or rewards based on learning progress. Furthermore, the support unit can present learning content in a quiz format to deepen children's understanding. This makes it easier to engage children by incorporating game elements. Some or all of the above processes in the support unit may be performed using AI, for example, or without AI. For example, the support unit can input game element data into a generating AI and have the generating AI select game elements.

[0104] The story generation unit can estimate a child's emotions and adjust the story content based on those emotions. For example, if the child is excited, the story generation unit can generate a story that includes adventure and action. It can also generate a calm story if the child is relaxed. Furthermore, if the child is anxious, the story generation unit can generate a reassuring story. This allows for the provision of a story that is optimal for the child by adjusting the story content based on their emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the story generation unit may be performed using AI, or not. For example, the story generation unit can input child emotion data into a generative AI and have the generative AI adjust the story content.

[0105] The story generation unit can generate the most suitable story by referring to the child's past story history during story generation. For example, the story generation unit can generate a new story based on themes from stories the child has enjoyed in the past. It can also generate an interesting story by excluding themes the child has avoided in the past. Furthermore, the story generation unit can analyze the child's past story history and generate the most suitable story. In this way, by referring to past story history, it can generate the most suitable story for the child. Some or all of the above processes in the story generation unit may be performed using AI, for example, or without AI. For example, the story generation unit can input the child's past story history data into a generation AI and have the generation AI perform story generation.

[0106] The story generation unit can adjust the tone and theme of a story according to the child's age and interests during story generation. For example, if the child is young, the story generation unit can generate a story using simple language. Conversely, if the child is older, the story generation unit can generate a story using more complex language. Furthermore, the story generation unit can adjust the tone and theme of the story according to the child's interests. This allows the system to provide children with stories that are optimal for them by adjusting the tone and theme of the story according to their age and interests. Some or all of the above-described processes in the story generation unit may be performed using AI, for example, or not. For example, the story generation unit can input data about the child's age and interests into a generation AI and have the generation AI perform adjustments to the tone and theme of the story.

[0107] The story generation unit can estimate a child's emotions and adjust the length of the story based on the estimated emotions. For example, if the child is excited, the story generation unit can generate a longer story. It can also generate a shorter story if the child is calm. Furthermore, if the child is anxious, the story generation unit can generate a story of appropriate length. This allows for the provision of an optimal story length for the child by adjusting the length based on their emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the story generation unit may be performed using or without AI. For example, the story generation unit can input child emotion data into a generative AI and have the generative AI adjust the story length.

[0108] The story generation unit can customize the story content based on the child's learning objectives during story generation. For example, the story generation unit provides relevant story content in line with the child's learning objectives. The story generation unit can also adjust the story content according to the child's learning progress. Furthermore, the story generation unit can customize the story content to help the child achieve their learning objectives. This allows for enhanced learning effectiveness by customizing the story content based on learning objectives. Some or all of the above-described processes in the story generation unit may be performed using AI, for example, or without AI. For instance, the story generation unit can input the child's learning objective data into a generation AI and have the generation AI customize the story content.

[0109] The story generation unit can use visual content in conjunction with story generation to capture children's interest. For example, the story generation unit can display images or videos related to themes that children are interested in. It can also provide interactive quizzes or games to engage children's interest in the topic. Furthermore, the story generation unit can use diagrams and animations to explain things in a way that is easy for children to understand. This makes it easier to capture children's interest by using visual content. Some or all of the above processes in the story generation unit may be performed using AI, for example, or not. For example, the story generation unit can input visual content data into a generation AI and have the generation AI select the content.

[0110] The reception desk can estimate a child's emotions and adjust its response based on those emotions. For example, if a child is excited, the reception desk will respond energetically. If a child is calm, the reception desk can respond gently. Furthermore, if a child is feeling anxious, the reception desk can provide reassuring support. By adjusting the reception desk's response based on the child's emotions, the system can provide the most appropriate response for the child. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI, or not. For example, the reception desk can input child emotion data into a generative AI and have the generative AI adjust the reception response.

[0111] The reception unit can select the optimal reception method by referring to the parent's past setting history at the time of reception. For example, the reception unit can select the optimal reception method based on the learning goals and schedules that the parent has set in the past. The reception unit can also analyze the parent's past setting history and suggest the optimal reception method. Furthermore, the reception unit can prioritize suggesting setting methods that the parent has used in the past. This makes it easier to select the optimal reception method by referring to past setting history. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input the parent's past setting history data into a generating AI and have the generating AI perform the selection of the reception method.

[0112] The reception unit can estimate the child's emotions and adjust the frequency of reception based on the estimated emotions. For example, the reception unit may reception more frequently if the child is excited. It may also reception at a moderate frequency if the child is calm. Furthermore, if the child is feeling anxious, the reception unit may reception more frequently to provide reassurance. By adjusting the frequency of reception based on the child's emotions, the system can provide the optimal reception frequency for the child. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception unit may be performed using AI, or not using AI. For example, the reception unit can input the child's emotion data into a generative AI and have the generative AI adjust the reception frequency.

[0113] The reception unit can select the optimal reception method at the time of reception, taking into account the parent's device information. For example, if the parent is using a smartphone, the reception unit can provide a reception method that matches the screen size. Furthermore, if the parent is using a tablet, the reception unit can provide a reception method optimized for a larger screen. Additionally, if the parent is using a smartwatch, the reception unit can provide a concise and highly visible reception method. In this way, the reception unit can provide the optimal reception method by considering the parent's device information. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input the parent's device information into a generating AI and have the generating AI select a reception method.

[0114] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0115] The Conversational Learning Support Unit can monitor a child's learning progress in real time and provide feedback tailored to their progress. For example, when a child completes a specific task, the Conversational Learning Support Unit will offer praise and guidance for the next step. It can also provide additional hints and support if a child is struggling with a task. Furthermore, based on the child's learning progress, the Conversational Learning Support Unit can suggest what to learn next. This allows for real-time monitoring of a child's learning progress and the provision of appropriate feedback, thereby enhancing learning effectiveness.

[0116] The story generation unit can estimate a child's emotions and select story characters based on those emotions. For example, if the child is excited, the story generation unit will introduce energetic characters. If the child is calm, it can introduce gentle characters. Furthermore, if the child is feeling anxious, it can introduce characters that provide a sense of security. In this way, by selecting characters based on the child's emotions, it is possible to provide a story that is optimal for the child.

[0117] The support system can visualize a child's learning progress based on learning goals and schedules set by parents. For example, the support system displays a child's learning progress in graphs and charts. It can also allow parents to check learning progress through a smartphone app. Furthermore, the support system can provide alerts and reminders based on learning progress. This makes it easier for parents to understand their child's learning progress and provide appropriate support.

[0118] The conversation learning support unit can estimate a child's emotions and adjust the tone of conversation based on those emotions. For example, if the child is excited, the unit will converse in a bright and cheerful tone. If the child is calm, the unit can converse in a gentle tone. Furthermore, if the child is feeling anxious, the unit can converse in a gentle tone to provide reassurance. By adjusting the tone of conversation based on the child's emotions, the unit can help the child enjoy conversations more comfortably.

[0119] The dialogue provider can customize the method of dialogue according to the child's learning style. For example, if the child has a visual learning style, the dialogue provider can provide dialogue using diagrams and illustrations. If the child has an auditory learning style, the dialogue provider can also provide dialogue using sound and music. Furthermore, if the child has an experiential learning style, the dialogue provider can provide interactive dialogue. By customizing the dialogue method according to the child's learning style, learning effectiveness can be enhanced.

[0120] The story generation unit can estimate a child's emotions and adjust the story's ending based on those emotions. For example, if the child is excited, the story generation unit will generate a happy ending. It can also generate a calm ending if the child is relaxed. Furthermore, if the child is feeling anxious, it can generate a reassuring ending. This allows the system to provide children with the most suitable story by adjusting the ending based on their emotions.

[0121] The Conversation Learning Support Department can analyze a child's past learning data and propose an optimal learning plan. For example, it can suggest what the child should learn next based on what they have learned in the past. It can also propose a plan to reinforce areas where the child has struggled in the past. Furthermore, it can propose a plan that matches the child's learning pace. In this way, by analyzing past learning data, it can provide the optimal learning plan for each child.

[0122] The dialogue provider can estimate a child's emotions and adjust the content of the dialogue based on those emotions. For example, if the child is excited, the dialogue provider can provide an energetic dialogue. It can also provide a calm dialogue if the child is calm. Furthermore, if the child is feeling anxious, the dialogue provider can provide a reassuring dialogue. By adjusting the dialogue content based on the child's emotions, it can provide the most appropriate dialogue for the child.

[0123] The support team can report on a child's learning progress based on the learning goals and schedules set by the parents. For example, the support team can send parents regular progress reports. The support team can also allow parents to check their child's learning progress through a smartphone app. Furthermore, the support team can provide alerts and reminders based on the child's learning progress. This makes it easier for parents to understand their child's learning progress and provide appropriate support.

[0124] The story generation unit can estimate a child's emotions and select background music for the story based on those emotions. For example, if the child is excited, the story generation unit will select energetic music. If the child is calm, it can select calming music. Furthermore, if the child is feeling anxious, it can select music that provides a sense of security. By selecting background music based on the child's emotions, the system can provide the child with the most suitable story.

[0125] The following briefly describes the processing flow for example form 2.

[0126] Step 1: The Conversational Learning Support Department engages in conversations about topics that interest the child. For example, if the child is interested in dinosaurs, the department provides information about dinosaurs and helps deepen that knowledge through dialogue. Similarly, it provides information about space and animals and helps deepen that knowledge through dialogue. Step 2: The emotion recognition unit recognizes the child's emotions. For example, it analyzes the child's facial expressions, tone of voice, and body movements to recognize whether the child is happy, sad, anxious, excited, calm, relaxed, or tense. Step 3: The dialogue provider unit provides dialogue that corresponds to the emotion recognized by the emotion recognition unit. For example, if a child is feeling anxious, the dialogue provides reassurance with gentle words; if the child is happy, it provides praise; and if the child is sad, it provides words of encouragement. Step 4: The support team provides learning support based on the learning goals and schedule set by the parents. For example, they provide appropriate learning content based on the learning goals set by the parents and appropriate study time based on the schedule. They also monitor learning progress and adjust the learning content and study time as needed.

[0127] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0128] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0129] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0130] Each of the multiple elements described above, including the conversation learning support unit, emotion recognition unit, dialogue provision unit, support unit, and story generation unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the conversation learning support unit is implemented by the control unit 46A of the smart device 14 and engages in conversation about themes that interest the child. The emotion recognition unit recognizes the child's emotions using the camera 42 and microphone 38B of the smart device 14 and analyzes them using the control unit 46A. The dialogue provision unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides dialogue corresponding to the emotions recognized by the emotion recognition unit. The support unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides learning support based on learning goals and schedules set by the parent. The story generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates stories tailored to the child's age and interests. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0131] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0132] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0133] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0134] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0135] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0137] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0138] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0139] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0140] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0141] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0142] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0143] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0144] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0145] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0146] Each of the multiple elements described above, including the conversation learning support unit, emotion recognition unit, dialogue provision unit, support unit, and story generation unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the conversation learning support unit is implemented by the control unit 46A of the smart glasses 214 and engages in conversation about themes that interest the child. The emotion recognition unit recognizes the child's emotions using the camera 42 and microphone 238 of the smart glasses 214 and analyzes them using the control unit 46A. The dialogue provision unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides dialogue corresponding to the emotions recognized by the emotion recognition unit. The support unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides learning support based on learning goals and schedules set by the parent. The story generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates stories tailored to the child's age and interests. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0147] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0148] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0149] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0150] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0151] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0153] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0154] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0155] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0156] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0157] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0158] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0159] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0160] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0161] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0162] Each of the multiple elements described above, including the conversation learning support unit, emotion recognition unit, dialogue provision unit, support unit, and story generation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the conversation learning support unit is implemented by the control unit 46A of the headset terminal 314 and engages in conversation about themes that interest the child. The emotion recognition unit recognizes the child's emotions using the camera 42 and microphone 238 of the headset terminal 314 and analyzes them using the control unit 46A. The dialogue provision unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides dialogue corresponding to the emotions recognized by the emotion recognition unit. The support unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides learning support based on learning goals and schedules set by the parent. The story generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates stories tailored to the child's age and interests. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0163] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0164] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0165] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0166] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0167] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0168] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0169] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0170] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0171] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0172] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0173] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0174] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0175] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0176] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0177] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0178] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0179] Each of the multiple elements described above, including the conversation learning support unit, emotion recognition unit, dialogue provision unit, support unit, and story generation unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the conversation learning support unit is implemented by the control unit 46A of the robot 414 and engages in conversation about themes that interest the child. The emotion recognition unit recognizes the child's emotions using the camera 42 and microphone 238 of the robot 414 and analyzes them with the control unit 46A. The dialogue provision unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides dialogue corresponding to the emotions recognized by the emotion recognition unit. The support unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides learning support based on learning goals and schedules set by the parent. The story generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates stories tailored to the child's age and interests. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0180] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0181] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0182] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0183] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0184] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0185] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0186] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0187] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0188] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0189] 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.

[0190] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0191] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0192] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0193] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0194] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0195] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0196] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0197] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0198] (Note 1) The conversation learning support department conducts conversations on topics that children are interested in, An emotion recognition unit that recognizes the child's emotions, A dialogue provision unit provides dialogue corresponding to the emotion recognized by the emotion recognition unit, It includes a support unit that provides learning support based on learning goals and schedules set by the parents. A system characterized by the following features. (Note 2) It features a story generation unit that generates stories tailored to the child's age and interests. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned support unit is It has a reception area that accepts learning goals and schedules set by parents. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned conversation learning support unit is Provide knowledge on topics that children are interested in. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned dialogue provider unit, Provide reassuring dialogue that responds to the child's emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned story generation unit, Generate stories that stimulate children's creativity. The system described in Appendix 2, characterized by the features described herein. (Note 7) The aforementioned conversation learning support unit is The system estimates the child's emotions and selects conversation topics based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned conversation learning support unit is Analyze the child's past conversation history to select the most suitable conversation topics. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned conversation learning support unit is During the conversation, the system analyzes the child's responses in real time and adjusts the direction of the conversation accordingly. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned conversation learning support unit is It estimates the child's emotions and adjusts the pace of the conversation based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned conversation learning support unit is When selecting a topic for conversation, choose one that takes into account the child's learning progress. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned conversation learning support unit is When selecting conversation topics, use visual content to capture children's interest. The system described in Appendix 1, characterized by the features described herein. (Note 13) The emotion recognition unit, The system estimates the child's emotions and optimizes the emotion recognition algorithm based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The emotion recognition unit, During emotion recognition, the child's facial expressions and tone of voice are analyzed to identify their emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The emotion recognition unit, When recognizing emotions, the child's past emotional data is referenced to improve recognition accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 16) The emotion recognition unit, It estimates the child's emotions and adjusts the frequency of emotion recognition based on the estimated emotions of the child. The system described in Appendix 1, characterized by the features described herein. (Note 17) The emotion recognition unit, During emotion recognition, the child's physical movements are analyzed to identify the emotion. The system described in Appendix 1, characterized by the features described herein. (Note 18) The emotion recognition unit, During emotion recognition, the child's surrounding environmental sounds are analyzed to identify their emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned dialogue provider unit, The system estimates the child's emotions and adjusts the content of the conversation based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned dialogue provider unit, When providing dialogue, the system refers to the child's past dialogue history to provide the most appropriate dialogue content. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned dialogue provider unit, When providing dialogues, adjust the tone and language of the dialogue according to the child's age and interests. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned dialogue provider unit, The system estimates the child's emotions and adjusts the length of the conversation based on those estimates. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned dialogue provider unit, When providing dialogues, customize the content of the dialogues based on the child's learning objectives. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned dialogue provider unit, When providing interactive content, use music and sound effects to capture children's attention. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned support unit is We estimate the child's emotions and adjust learning support methods based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned support unit is When providing learning support, we refer to the child's past learning data to select the most suitable support method. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned support unit is During learning support sessions, we analyze the child's learning progress in real time and adjust the support accordingly. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned support unit is The system estimates the child's emotions and adjusts the frequency of learning support based on those estimates. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned support unit is When providing learning support, customize the support method according to the child's learning style. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned support unit is When providing learning support, incorporate game elements to capture the child's interest. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned story generation unit, The system estimates the child's emotions and adjusts the story content based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned story generation unit, When generating a story, the system references the child's past story history to generate the most suitable story. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned story generation unit, When generating a story, adjust the tone and themes of the story according to the child's age and interests. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned story generation unit, The system estimates the child's emotions and adjusts the length of the story based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 35) The aforementioned story generation unit, When generating a story, customize the story content based on the child's learning objectives. The system described in Appendix 2, characterized by the features described herein. (Note 36) The aforementioned story generation unit, When generating stories, use visual content in conjunction to capture children's attention. The system described in Appendix 2, characterized by the features described herein. (Note 37) The aforementioned reception unit is We estimate the child's emotions and adjust the receptionist's response based on those estimates. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned reception unit is During registration, the system will refer to the parent's past settings history to select the most suitable registration method. The system described in Appendix 3, characterized by the features described herein. (Note 39) The aforementioned reception unit is The system estimates the child's emotions and adjusts the frequency of reception based on the estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 40) The aforementioned reception unit is During registration, the system will select the most suitable registration method by considering the parent's device information. The system described in Appendix 3, characterized by the features described herein. [Explanation of symbols]

[0199] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The conversation learning support department conducts conversations on topics that children are interested in, An emotion recognition unit that recognizes the child's emotions, A dialogue provision unit provides dialogue corresponding to the emotion recognized by the emotion recognition unit, It includes a support unit that provides learning support based on learning goals and schedules set by the parents. A system characterized by the following features.

2. It features a story generation unit that generates stories tailored to the child's age and interests. The system according to feature 1.

3. The aforementioned support unit is It has a reception area that accepts learning goals and schedules set by parents. The system according to feature 1.

4. The aforementioned conversation learning support unit is Provide knowledge on topics that children are interested in. The system according to feature 1.

5. The aforementioned dialogue provider unit, Provide reassuring dialogue that responds to the child's emotions. The system according to feature 1.

6. The aforementioned story generation unit, Generate stories that stimulate children's creativity. The system according to feature 2.

7. The aforementioned conversation learning support unit is The system estimates the child's emotions and selects conversation topics based on those estimated emotions. The system according to feature 1.

8. The aforementioned conversation learning support unit is Analyze the child's past conversation history to select the most suitable conversation topics. The system according to feature 1.

9. The aforementioned conversation learning support unit is During the conversation, the system analyzes the child's responses in real time and adjusts the direction of the conversation accordingly. The system according to feature 1.

Images