system

Abstract

The system according to this embodiment aims to provide children with immediate and appropriate answers to their questions and to create learning opportunities. [Solution] The system according to the embodiment comprises a reception unit, a generation unit, a reading unit, a storage unit, and an access unit. The reception unit inputs a child's question using voice recognition. The generation unit generates a picture book containing the answer to the question input by the reception unit. The reading unit reads aloud the picture book generated by the generation unit. The storage unit stores the picture book generated by the generation unit. The access unit accesses questions from other children.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance 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 it is difficult to immediately provide an appropriate answer to a child's question and create an opportunity for learning.

[0005] The system according to the embodiment aims to immediately provide an appropriate answer to a child's question and create an opportunity for learning.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a generation unit, a reading unit, a storage unit, and an access unit. The reception unit inputs a child's question using voice recognition. The generation unit generates a picture book containing the answer to the question input by the reception unit. The reading unit reads aloud the picture book generated by the generation unit. The storage unit stores the picture book generated by the generation unit. The access unit accesses questions from other children. [Effects of the Invention]

[0007] The system according to this embodiment can provide children with immediate and appropriate answers to their questions and create learning opportunities. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards 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) An educational app according to an embodiment of the present invention is a system that generates original picture books that answer children's "why?" questions. In this educational app, children input their questions using voice recognition, and an image generation AI generates a picture book that includes the answer to that question. The generated picture book has content that is easy to understand according to the child's age and developmental stage, and by including the child's name and siblings, it becomes more familiar and approachable. Furthermore, by utilizing the voice generation AI, the picture book can be read aloud in the voices of family members. The generated picture books are saved as a personal knowledge bookshelf, allowing the child to review what they have learned. In addition, the child can access questions from other children, creating learning opportunities and providing a chance to cultivate intellectual curiosity. For example, a child inputs a question such as "Why is the sky blue?" by voice. This question is converted into text by the voice recognition AI. Next, the image generation AI generates a picture book that includes the answer to the input question. For example, in response to the question "Why is the sky blue?", a picture book explaining why the sky is blue is generated. This picture book is designed to be easy to understand, tailored to the child's age and developmental stage, and becomes more relatable and engaging by including the child's name and siblings. Furthermore, it utilizes voice-generating AI to allow the picture book to be read aloud in the voices of family members. For example, having the picture book read aloud in the mother's voice can make the child feel more connected to it. The generated picture books are saved as a personal knowledge library, allowing the child to review their learning. For example, they can reread previously generated picture books to review what they have learned. In addition, they can access questions from other children, creating learning opportunities and providing a chance to cultivate intellectual curiosity. For example, if another child has a question such as "Why do rainbows appear?", they can gain new knowledge by reading a picture book that answers that question. In this way, the educational app can generate, read aloud, save, and access original picture books in response to children's questions.

[0029] The educational app according to this embodiment comprises a reception unit, a generation unit, a reading unit, a storage unit, and an access unit. The reception unit receives a child's question via voice recognition. For example, a child might voice a question such as, "Why is the sky blue?" This question is converted into text by a voice recognition AI. The generation unit generates a picture book containing the answer to the question entered by the reception unit. For example, an image generation AI generates a picture book explaining why the sky is blue in response to the question, "Why is the sky blue?" The generated picture book is easy to understand according to the child's age and developmental stage, and becomes more familiar and relatable by including the child's name and siblings. The reading unit reads aloud the picture book generated by the generation unit. For example, it can use a voice generation AI to read the picture book in a mother's voice. The storage unit saves the picture book generated by the generation unit. For example, the generated picture book is saved as a personal knowledge bookshelf, allowing the user to review their learning. The access unit accesses questions from other children. For example, if another child has a question such as "Why do rainbows appear?", they can gain new knowledge by reading a picture book that answers that question. Thus, the educational app according to this embodiment can generate, read aloud, save, and access original picture books that address children's questions.

[0030] The reception desk uses voice recognition to input children's questions. For example, a child might voice a question like, "Why is the sky blue?" This question is then converted into text by a voice recognition AI. Specifically, the voice recognition AI uses advanced algorithms to analyze the child's pronunciation and tone of voice and accurately convert it into text data. The voice recognition AI uses noise cancellation technology to remove ambient noise and capture the child's voice clearly. The voice recognition AI can also provide appropriate feedback based on the child's pronunciation characteristics and language proficiency. For example, if the pronunciation is unclear, it will display a message prompting the child to pronounce it again. Furthermore, the voice recognition AI supports multiple languages ​​and can handle questions in different languages. This allows the reception desk to provide an environment where children can input questions naturally and support their first steps in learning.

[0031] The generation unit generates picture books that include answers to questions entered by the reception unit. For example, if the image generation AI answers the question "Why is the sky blue?", it will generate a picture book explaining why the sky is blue. The generated picture books will have content that is easy to understand according to the child's age and developmental stage, and will be more relatable and familiar by including the child's name and siblings. Specifically, the image generation AI uses natural language processing technology to analyze the entered question and generate an appropriate answer. Next, it generates relevant illustrations and characters based on the answer. For example, to explain why the sky is blue, it creates illustrations that visually represent the changes in the sky's color and the phenomenon of light scattering. The generation unit also customizes the content of the picture book by taking into account the child's individual information. For example, it will make the content more relatable by including the child's name and favorite characters in the picture book. Furthermore, the generation unit regularly updates its database and incorporates new information and technologies to improve the quality of the picture book's story and illustrations. In this way, the generation unit can provide children with engaging and educational picture books and enhance their motivation to learn.

[0032] The reading unit reads aloud the picture book generated by the generation unit. For example, it can use voice generation AI to read a picture book in a mother's voice. Specifically, the voice generation AI generates natural and emotionally rich voices based on pre-recorded samples of a mother's voice. The voice generation AI analyzes the text data and reads it aloud with appropriate intonation and rhythm. The reading unit can also adjust the reading speed and volume according to the child's reactions and level of understanding. For example, it will read slowly and carefully in parts that the child shows interest in, while reading smoothly in parts that the child understands better. Furthermore, the reading unit offers multiple voice options, allowing children to enjoy the picture book in their favorite voice. For example, it can read in various voices, such as a father's voice or a character's voice. In this way, the reading unit can provide children with a fun and educational read-aloud experience, enhancing their learning effectiveness.

[0033] The storage unit stores the picture books generated by the generation unit. For example, the generated picture books are stored as a personal knowledge bookshelf, allowing users to review their learning. Specifically, the storage unit saves the generated picture books to cloud storage, making them accessible at any time. The storage unit manages the picture book metadata (title, creation date, content summary, etc.), enabling efficient searching and organization. The storage unit also manages version control of picture books, allowing comparison between past and latest versions. Furthermore, the storage unit provides a picture book sharing function, allowing users to share picture books with family and friends. For example, a picture book created by a child can be sent to grandparents, allowing the whole family to enjoy the results of their learning. In this way, the storage unit can centrally manage children's learning history and support reflection on and sharing of their learning.

[0034] The Access Unit provides access to other children's questions. For example, if another child has a question like, "Why do rainbows form?", they can gain new knowledge by reading a picture book that addresses that question. Specifically, the Access Unit provides a function to access a database of picture books created by other children and search for relevant books. The Access Unit uses an algorithm to recommend the most suitable picture book based on keywords and categories of questions. For example, searching with the keyword "rainbow" will display picture books that explain the formation process of rainbows and the breakdown of colors. The Access Unit also provides picture book rating and comment functions, allowing children to share their opinions and impressions. In this way, the Access Unit provides children with opportunities to encounter other children's questions and learning, promoting mutual learning. Furthermore, the Access Unit can maintain children's motivation to learn by regularly adding new picture books and always providing the latest information.

[0035] The generation unit includes a customization unit that customizes the content of the picture book to suit the child's age and developmental stage. For example, the generation unit adjusts the content of the picture book according to the child's age. For instance, it generates picture books for toddlers that use simple language and colorful illustrations, and picture books for elementary school children that include detailed explanations and concrete examples. The generation unit can also customize the content of the picture book according to the child's developmental stage. For example, it provides information on content that is easy to understand and of an appropriate difficulty level according to the developmental stage. This makes it possible to generate customized picture books that are tailored to the child's age and developmental stage. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation AI automatically selects appropriate content based on the child's age and developmental stage and generates a picture book.

[0036] The reading unit includes a voice setting unit for reading picture books in the voices of family members. For example, the reading unit can read picture books in the voice of a mother. The voice setting unit records the voices of family members and sets the unit to use those voices to read picture books. For example, it can record the voice of a mother and set the unit to use that voice to read picture books. The voice setting unit can also set the unit to use the voices of a father or sibling to read picture books. This allows picture books to be read in the voices of family members, making them more familiar to children. Some or all of the above processing in the reading unit may be performed using AI or not. For example, the voice setting unit can perform voice settings using an AI model that records the voices of family members and sets the unit to use those voices to read picture books.

[0037] The storage unit saves the generated picture books as a personal bookshelf of knowledge. The storage unit can, for example, save the generated picture books as a digital library. For example, the generated picture books are saved in digital format and can be accessed at any time. The storage unit can also save the picture books as physical bookshelves. For example, the generated picture books can be printed and stored on a physical bookshelf. This allows the generated picture books to be saved as a personal bookshelf of knowledge. Some or all of the above processes in the storage unit may be performed using AI or not. For example, the storage unit can perform saving using an AI model that saves the generated picture books as a digital library.

[0038] The access unit accesses picture books that answer questions from other children. For example, if another child has a question such as "Why do rainbows appear?", the access unit can access a picture book that answers that question. The access unit can access picture books that answer questions from other children through online access. For example, it can browse picture books that answer questions from other children via the internet. The access unit can also access picture books that answer questions from other children through offline access. For example, it can browse downloaded picture books offline. This allows access to picture books that answer questions from other children and provides learning opportunities. Some or all of the above processing in the access unit may be performed using AI or not. For example, the access unit can use an AI model to access picture books that answer questions from other children.

[0039] The customization section generates more relatable and engaging picture books by incorporating the child's name and siblings. For example, the customization section can feature the child's name as a character in the picture book. By naming the main character of the picture book after the child, the child can feel like they are part of the story. The customization section can also include the names of siblings and other family members in the picture book. For example, siblings and other family members can appear as characters who go on adventures together in the picture book. In this way, by including the child's name and siblings, it is possible to generate more relatable and engaging picture books. Some or all of the above processes in the customization section are performed using a generation AI. For example, the generation AI automatically generates characters for the picture book based on the child's name and information about siblings, and incorporates them into the story.

[0040] The reception desk analyzes the child's past question history and selects the optimal input method. For example, the reception desk prioritizes suggesting input methods that the child has frequently used in the past (voice, text, etc.). For instance, if the child prefers voice input, it will prioritize suggesting voice input. The reception desk can also suggest input methods related to specific themes based on the child's past question history. For example, if the child has many questions about science, it will suggest science-related input methods. Furthermore, the reception desk can analyze the child's past question history and suggest the most efficient input method. For example, based on past question history, it will suggest the method that allows for the shortest input time. In this way, the optimal input method can be selected by analyzing the child's past question history. Some or all of the above processing in the reception desk is performed using AI. For example, the AI ​​analyzes the child's past question history and automatically selects the optimal input method.

[0041] The input system filters questions based on the child's current interests. For example, it prioritizes questions related to the child's current interests. If the child is interested in dinosaurs, it prioritizes questions related to dinosaurs. The input system can also filter relevant questions based on the child's current interests and prompt for input. For example, if the child is interested in space, it filters and prompts for questions related to space. Furthermore, the input system can analyze the child's current interests and prompt for the most relevant questions. For example, if the child is interested in animals, it prioritizes questions related to animals. This allows for the input of more relevant questions by filtering them based on the child's current interests. Some or all of the above processing in the input system is performed using AI. For example, the AI ​​analyzes the child's current interests and automatically filters for the most relevant questions.

[0042] The reception desk prioritizes the input of highly relevant questions by considering the child's geographical location when a question is entered. For example, if the child is in a specific location, the reception desk will prioritize questions related to that location. For example, if the child is in a zoo, it will prioritize questions related to animals. The reception desk can also filter and prompt for highly relevant questions based on the child's current location. For example, if the child is in a museum, it will filter and prompt for questions related to museums. Furthermore, the reception desk can analyze the child's geographical location and prompt for the input of the most relevant questions. For example, if the child is in a park, it will prioritize questions related to parks. In this way, highly relevant questions can be prioritized by considering the child's geographical location. Some or all of the above processing in the reception desk is performed using AI. For example, the AI ​​analyzes the child's geographical location and automatically filters for the most relevant questions.

[0043] The reception desk analyzes the child's social media activity when a question is entered and prompts for relevant questions. For example, the reception desk prioritizes questions related to themes the child shows interest in on social media. For instance, if the child shows interest in dinosaurs on social media, it will prioritize questions related to dinosaurs. The reception desk can also analyze the child's social media activity and prompt for the most relevant questions. For example, if the child shows interest in space on social media, it will prompt for questions related to space. Furthermore, the reception desk can filter relevant questions and prompt for input based on the child's social media activity history. For example, if the child shows interest in animals on social media, it will prompt for questions related to animals. This allows for the input of relevant questions by analyzing the child's social media activity. Some or all of the above processing in the reception desk is performed using AI. For example, the AI ​​analyzes the child's social media activity and automatically filters for the most relevant questions.

[0044] The generation unit adjusts the level of detail in the picture book based on the importance of the question during the generation process. For example, for highly important questions, the generation unit generates a picture book with detailed explanations and many illustrations. For example, for scientific questions, it generates a picture book with detailed explanations and specific examples. The generation unit can also generate a picture book with concise explanations and few illustrations for less important questions. For example, for everyday questions, it generates a picture book with concise explanations and few illustrations. Furthermore, the generation unit can adjust the number of pages and the depth of content in the picture book according to the importance of the question. For example, for highly important questions, it increases the number of pages and delves deeper into the content. In this way, by adjusting the level of detail in the picture book based on the importance of the question, a more appropriate picture book can be generated. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation AI analyzes the importance of the question and automatically adjusts the level of detail in the picture book based on that.

[0045] The generation unit applies different generation algorithms depending on the category of the question when generating picture books. For example, for questions about science, the generation unit applies a generation algorithm that includes scientific explanations. For example, for scientific questions, it applies a generation algorithm based on scientific theories and experimental results. The generation unit can also apply a generation algorithm that includes historical background for questions about history. For example, for historical questions, it applies a generation algorithm based on historical events and people. Furthermore, for questions about nature, the generation unit can apply a generation algorithm that emphasizes the beauty of nature. For example, for questions about nature, it applies a generation algorithm based on beautiful landscapes and flora and fauna. In this way, by applying different generation algorithms depending on the category of the question, a more appropriate picture book can be generated. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation AI analyzes the category of the question and automatically applies the optimal generation algorithm based on it.

[0046] The generation unit determines the priority of picture books based on when the questions were submitted. For example, the generation unit prioritizes generating picture books for recently submitted questions. For instance, it prioritizes generating picture books for the latest questions to provide quick answers. The generation unit can also prioritize generating newer questions and postpone older questions. For example, it prioritizes generating picture books for newer questions over older ones. Furthermore, the generation unit can adjust the order in which picture books are generated based on the submission date. For example, it determines the order in which picture books are generated according to the submission date to generate picture books efficiently. This allows for the generation of more appropriate picture books by determining the priority of picture books based on when the questions were submitted. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation AI analyzes when the questions were submitted and automatically determines the priority of picture books based on that.

[0047] The generation unit adjusts the order of picture books based on the relevance of the questions during the picture book generation process. For example, the generation unit prioritizes generating picture books for highly relevant questions. For instance, it prioritizes generating picture books for highly relevant questions to provide quick answers. The generation unit can also prioritize generating highly relevant questions while delaying less relevant questions. For example, it prioritizes generating picture books for highly relevant questions over less relevant ones. Furthermore, the generation unit can adjust the generation order of picture books based on the relevance of the questions. For example, it determines the generation order of picture books according to their relevance to efficiently generate them. This allows for the generation of more appropriate picture books by adjusting the order of picture books based on the relevance of the questions. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation AI analyzes the relevance of the questions and automatically adjusts the order of picture books based on that analysis.

[0048] The reading unit adjusts the reading speed and tone based on the content of the picture book during reading. For example, in action scenes, the reading unit reads at a fast speed and in a high tone. The reading unit can also read at a slow speed and in a low tone in explanatory scenes. Furthermore, the reading unit can read in an emotional tone in emotional scenes. By adjusting the reading speed and tone based on the content of the picture book, a more appropriate reading can be achieved. Some or all of the above processing in the reading unit may be performed using AI, or not. For example, the reading unit can perform reading using an AI model that analyzes the content of the picture book and automatically adjusts the reading speed and tone based on that analysis.

[0049] The reading unit selects the optimal reading method by referring to the child's past responses during reading. For example, the reading unit may prioritize reading methods that the child has preferred in the past. For example, it may select the optimal reading method based on the child's past preferred reading methods. The reading unit can also analyze the child's past responses and select the most effective reading method. For example, it may select the most effective reading method based on the child's past responses. Furthermore, the reading unit can adjust the reading speed and tone based on the child's past responses. For example, it may adjust the reading speed and tone based on the child's past responses. This allows the optimal reading method to be selected by referring to the child's past responses. Some or all of the above processing in the reading unit may be performed using AI or not. For example, the reading unit can perform reading using an AI model that analyzes the child's past responses and automatically selects the optimal reading method based on them.

[0050] The reading unit selects the optimal reading method when reading aloud, taking into account the child's geographical location. For example, if the child is in a specific location, the reading unit will prioritize reading content related to that location. For example, if the child is in a zoo, it will prioritize reading content related to animals. The reading unit can also read content that is highly relevant based on the child's current location. For example, if the child is in a museum, it will read content related to museums. Furthermore, the reading unit can analyze the child's geographical location and read the most relevant content. For example, if the child is in a park, it will prioritize reading content related to parks. In this way, the optimal reading method can be selected by considering the child's geographical location. Some or all of the above processing in the reading unit may be performed using AI, or not. For example, the reading unit can perform reading using an AI model that analyzes the child's geographical location and automatically selects the optimal reading method based on that analysis.

[0051] The reading unit analyzes the child's social media activity during reading and suggests a reading method. For example, the reading unit prioritizes reading content related to themes the child shows interest in on social media. For example, if the child shows interest in dinosaurs on social media, it will prioritize reading content related to dinosaurs. The reading unit can also analyze the child's social media activity and read the most relevant content. For example, if the child shows interest in space on social media, it will read content related to space. Furthermore, the reading unit can read relevant content based on the child's social media activity history. For example, if the child shows interest in animals on social media, it will read content related to animals. In this way, by analyzing the child's social media activity, the optimal reading method can be suggested. Some or all of the above processing in the reading unit may be performed using AI or not. For example, the reading unit can perform reading using an AI model that analyzes the child's social media activity and automatically suggests the optimal reading method based on that analysis.

[0052] The storage unit adjusts the save format based on the content of the picture book during saving. For example, if a picture book has many illustrations, the storage unit will save it in a high-resolution image format. For example, if a picture book has many illustrations, it will save it in a high-resolution JPEG format. The storage unit can also save picture books with a lot of text in a text format. For example, if a picture book has a lot of text, it will save it in PDF format. Furthermore, if a picture book contains videos, the storage unit can save it in a video format. For example, if a picture book contains videos, it will save it in MP4 format. In this way, by adjusting the save format based on the content of the picture book, the optimal format can be used for saving. Some or all of the above processing in the storage unit may be performed using AI, or it may be performed without AI. For example, the storage unit can perform saving using an AI model that analyzes the content of the picture book and automatically selects the optimal save format based on that analysis.

[0053] The storage unit, when saving, selects the optimal saving method by referring to the child's past saving history. For example, the storage unit may prioritize the format that the child has preferred to save in the past. For example, it may select the optimal saving method based on the format that the child has preferred to save in the past. The storage unit can also analyze the child's past saving history and select the most efficient saving method. For example, it may select the most efficient saving method based on the child's past saving history. Furthermore, the storage unit may adjust the saving format based on the child's past saving history. For example, it may adjust the saving format based on the child's past saving history. This allows the optimal saving method to be selected by referring to the child's past saving history. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit can perform saving using an AI model that analyzes the child's past saving history and automatically selects the optimal saving method based on it.

[0054] The preservation unit selects the optimal preservation method when preserving a child, taking into account the child's geographical location. For example, if the child is in a specific location, the preservation unit provides a preservation method related to that location. For example, if the child is in a zoo, it provides a preservation method related to animals. The preservation unit can also select the optimal preservation method based on the child's current location. For example, if the child is in a museum, it selects a preservation method related to the museum. Furthermore, the preservation unit can analyze the child's geographical location and select the most efficient preservation method. For example, if the child is in a park, it selects a preservation method related to the park. In this way, the optimal preservation method can be selected by considering the child's geographical location. Some or all of the above processing in the preservation unit may be performed using AI, or not. For example, the preservation unit can perform preservation using an AI model that analyzes the child's geographical location and automatically selects the optimal preservation method based on that analysis.

[0055] The storage unit analyzes the child's social media activity during storage and proposes a storage method. For example, the storage unit prioritizes saving picture books that the child wants to share on social media. For example, it proposes the optimal storage method based on the picture books the child wants to share on social media. The storage unit can also analyze the child's social media activity and propose the most relevant storage method. For example, it proposes the most relevant storage method based on the child's social media activity. Furthermore, the storage unit can adjust the storage format based on the child's social media activity history. For example, it adjusts the storage format based on the child's social media activity history. This allows the storage unit to propose the optimal storage method by analyzing the child's social media activity. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit can perform storage using an AI model that analyzes the child's social media activity and automatically proposes the optimal storage method based on that analysis.

[0056] The access unit adjusts the access method based on the content of other children's questions when accessing content. For example, the access unit prioritizes access to picture books related to questions that other children are interested in. For example, it adjusts the optimal access method based on picture books related to questions that other children are interested in. The access unit can also analyze the content of other children's questions and access the most relevant picture books. For example, it accesses the most relevant picture books based on the content of other children's questions. Furthermore, the access unit can adjust the access method based on the content of other children's questions. For example, it adjusts the optimal access method based on the content of other children's questions. This allows access to more relevant picture books by adjusting the access method based on the content of other children's questions. Some or all of the above processing in the access unit may be performed using AI or not. For example, the access unit can perform access using an AI model that analyzes the content of other children's questions and automatically adjusts the optimal access method based on that analysis.

[0057] The access unit, upon access, selects the optimal access method by referring to the child's past access history. For example, the access unit may prioritize accessing picture books that the child has previously enjoyed accessing. For example, it may select the optimal access method based on the picture books the child has previously enjoyed accessing. The access unit can also analyze the child's past access history and select the most efficient access method. For example, it may select the most efficient access method based on the child's past access history. Furthermore, the access unit can adjust the access method based on the child's past access history. For example, it may adjust the access method based on the child's past access history. This allows the optimal access method to be selected by referring to the child's past access history. Some or all of the above processing in the access unit may be performed using AI or not. For example, the access unit can perform access using an AI model that analyzes the child's past access history and automatically selects the optimal access method based on it.

[0058] The access unit selects the optimal access method when accessing content, taking into account the child's geographical location. For example, if the child is in a specific location, the access unit prioritizes accessing picture books related to that location. For example, if the child is in a zoo, it prioritizes accessing picture books related to animals. The access unit can also select the optimal access method based on the child's current location. For example, if the child is in a museum, it selects picture books related to museums. Furthermore, the access unit can analyze the child's geographical location and select the most efficient access method. For example, if the child is in a park, it selects picture books related to parks. In this way, the optimal access method can be selected by considering the child's geographical location. Some or all of the above processing in the access unit may be performed using AI, or not. For example, the access unit can perform access using an AI model that analyzes the child's geographical location and automatically selects the optimal access method based on that analysis.

[0059] The access unit analyzes the child's social media activity and suggests access methods when accessing content. For example, the access unit prioritizes access to picture books related to themes the child shows interest in on social media. For instance, if the child shows interest in dinosaurs on social media, it prioritizes access to picture books related to dinosaurs. The access unit can also analyze the child's social media activity and access the most relevant picture books. For example, if the child shows interest in space on social media, it will access picture books related to space. Furthermore, the access unit can access relevant picture books based on the child's social media activity history. For example, if the child shows interest in animals on social media, it will access picture books related to animals. In this way, by analyzing the child's social media activity, the optimal access method can be suggested. Some or all of the above processing in the access unit may be performed using AI or not. For example, the access unit can perform access using an AI model that analyzes the child's social media activity and automatically suggests the optimal access method based on that analysis.

[0060] The customization unit selects the optimal customization method by referring to the child's past question history during the customization process. For example, the customization unit may prioritize customization methods that the child has preferred in the past. For example, it may select the optimal customization method based on the child's past preferred customization methods. The customization unit can also analyze the child's past question history and select the most effective customization method. For example, it may select the most effective customization method based on the child's past question history. Furthermore, the customization unit can adjust the customization method based on the child's past question history. For example, it may adjust the customization method based on the child's past question history. This allows the optimal customization method to be selected by referring to the child's past question history. Some or all of the above processing in the customization unit is performed using a generative AI. For example, the generative AI analyzes the child's past question history and automatically selects the optimal customization method based on it.

[0061] The customization unit performs customization based on the child's current interests and concerns. For example, the customization unit will perform customizations related to themes the child is currently interested in. For instance, if the child is interested in dinosaurs, it will perform customizations related to dinosaurs. The customization unit can also perform customizations related to the child's current interests. For example, if the child is interested in space, it will perform customizations related to space. Furthermore, the customization unit can analyze the child's current interests and concerns and perform the most relevant customizations. For example, if the child is interested in animals, it will perform customizations related to animals. This allows for the generation of more appropriate picture books by customizing based on the child's current interests and concerns. Some or all of the above processing in the customization unit is performed using a generative AI. For example, the generative AI analyzes the child's current interests and concerns and automatically performs the optimal customizations based on that.

[0062] The customization unit selects the optimal customization method by considering the child's geographical location during the customization process. For example, if the child is in a specific location, the customization unit will perform customizations related to that location. For example, if the child is in a zoo, it will perform customizations related to animals. The customization unit can also select the optimal customization method based on the child's current location. For example, if the child is in a museum, it will select customizations related to the museum. Furthermore, the customization unit can analyze the child's geographical location and select the most relevant customization method. For example, if the child is in a park, it will select customizations related to the park. In this way, the optimal customization method can be selected by considering the child's geographical location. Some or all of the above processing in the customization unit is performed using generative AI. For example, the generative AI analyzes the child's geographical location and automatically selects the optimal customization method based on that analysis.

[0063] The customization unit analyzes the child's social media activity during the customization process and proposes customization methods. For example, the customization unit performs customizations related to themes the child shows interest in on social media. For instance, if the child shows interest in dinosaurs on social media, it will perform dinosaur-related customizations. The customization unit can also analyze the child's social media activity and perform the most relevant customizations. For example, if the child shows interest in space on social media, it will perform space-related customizations. Furthermore, the customization unit can perform relevant customizations based on the child's social media activity history. For example, if the child shows interest in animals on social media, it will perform animal-related customizations. In this way, by analyzing the child's social media activity, the optimal customization method can be proposed. Some or all of the above processing in the customization unit is performed using generative AI. For example, the generative AI analyzes the child's social media activity and automatically proposes the optimal customization method based on that analysis.

[0064] The voice setting unit selects the optimal voice setting based on the characteristics of each family member's voice during the voice setting process. For example, the voice setting unit can analyze the characteristics of the mother's voice and set a voice setting that is similar to the mother's voice. For example, it can select the optimal voice setting based on the characteristics of the mother's voice. The voice setting unit can also analyze the characteristics of the father's voice and set a voice setting that is similar to the father's voice. For example, it can select the optimal voice setting based on the characteristics of the father's voice. Furthermore, the voice setting unit can analyze the characteristics of siblings' voices and set a voice setting that is similar to their voices. For example, it can select the optimal voice setting based on the characteristics of each family member's voice. This allows for a more user-friendly voice setting by selecting the optimal voice setting based on the characteristics of each family member's voice. Some or all of the above-described processes in the voice setting unit may be performed using AI or not. For example, the voice setting unit can perform voice setting using an AI model that analyzes the characteristics of each family member's voice and automatically selects the optimal voice setting based on that analysis.

[0065] The voice setting unit selects the optimal voice setting method by referring to the child's past responses when setting the voice. For example, the voice setting unit may prioritize selecting voice settings that the child has preferred in the past. For example, it may select the optimal voice setting method based on the child's past preferred voice settings. The voice setting unit can also analyze the child's past responses and select the most effective voice setting method. For example, it may select the most effective voice setting method based on the child's past responses. Furthermore, the voice setting unit may adjust the speed and tone of the voice setting based on the child's past responses. For example, it may adjust the speed and tone of the voice setting based on the child's past responses. This allows the optimal voice setting method to be selected by referring to the child's past responses. Some or all of the above processing in the voice setting unit may be performed using AI or not. For example, the voice setting unit can perform voice setting using an AI model that analyzes the child's past responses and automatically selects the optimal voice setting method based on that analysis.

[0066] The voice setting unit selects the optimal voice setting method when setting voices, taking into account the child's geographical location. For example, if the child is in a specific location, the voice setting unit will set voices related to that location. For example, if the child is in a zoo, it will set voices related to animals. The voice setting unit can also select the optimal voice setting method based on the child's current location. For example, if the child is in a museum, it will select voices related to the museum. Furthermore, the voice setting unit can analyze the child's geographical location and select the most relevant voice setting method. For example, if the child is in a park, it will select voices related to the park. In this way, the optimal voice setting method can be selected by considering the child's geographical location. Some or all of the above processing in the voice setting unit may be performed using AI or not. For example, the voice setting unit can perform voice settings using an AI model that analyzes the child's geographical location and automatically selects the optimal voice setting method based on that analysis.

[0067] The voice setting unit analyzes the child's social media activity and proposes voice setting methods during voice setting. For example, the voice setting unit sets voice settings related to themes the child shows interest in on social media. For example, if the child shows interest in dinosaurs on social media, it sets voice settings related to dinosaurs. The voice setting unit can also analyze the child's social media activity and set the most relevant voice settings. For example, if the child shows interest in space on social media, it sets voice settings related to space. Furthermore, the voice setting unit can set relevant voice settings based on the child's social media activity history. For example, if the child shows interest in animals on social media, it sets voice settings related to animals. In this way, by analyzing the child's social media activity, the optimal voice setting method can be proposed. Some or all of the above processing in the voice setting unit may be performed using AI or not. For example, the voice setting unit can perform voice setting using an AI model that analyzes the child's social media activity and automatically proposes the optimal voice setting method based on that analysis.

[0068] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0069] The reception desk can analyze a child's past question history and select the most suitable input method. For example, it can prioritize suggesting input methods that the child has frequently used in the past (voice, text, etc.). It can also suggest input methods related to specific topics based on the child's past question history. Furthermore, it can analyze the child's past question history and suggest the most efficient input method. In this way, the optimal input method can be selected by analyzing the child's past question history. Some or all of the above processes in the reception desk are performed using AI. For example, the AI ​​can analyze the child's past question history and automatically select the most suitable input method.

[0070] The reception desk can filter questions based on the child's current interests and concerns when they are entered. For example, it can prioritize questions related to topics the child is currently interested in. It can also filter relevant questions based on the child's current interests and prompt for input. Furthermore, it can analyze the child's current interests and concerns and prompt for the most relevant questions. This allows for the input of more relevant questions by filtering questions based on the child's current interests. Some or all of the above processing in the reception desk is performed using AI. For example, the AI ​​can analyze the child's current interests and concerns and automatically filter for the most relevant questions.

[0071] The generation unit can adjust the level of detail in a picture book based on the importance of the question during the book generation process. For example, for highly important questions, it can generate a picture book with detailed explanations and many illustrations. Conversely, for less important questions, it can generate a picture book with concise explanations and fewer illustrations. Furthermore, it can adjust the number of pages and the depth of content of the picture book according to the importance of the question. This allows for the generation of more appropriate picture books by adjusting the level of detail based on the importance of the question. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation AI can analyze the importance of the question and automatically adjust the level of detail of the picture book based on that analysis.

[0072] The generation unit can apply different generation algorithms depending on the category of the question when generating a picture book. For example, a generation algorithm that includes scientific explanations can be applied to questions about science. Similarly, a generation algorithm that includes historical background can be applied to questions about history. Furthermore, a generation algorithm that emphasizes the beauty of nature can be applied to questions about nature. By applying different generation algorithms depending on the category of the question, a more appropriate picture book can be generated. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation AI can analyze the category of the question and automatically apply the most suitable generation algorithm based on that.

[0073] The access unit can adjust its access method based on the content of other children's questions when accessing content. For example, it can prioritize accessing picture books related to questions that other children are interested in. It can also analyze the content of other children's questions and access the most relevant picture books. Furthermore, it can adjust its access method based on the content of other children's questions. This allows access to more relevant picture books by adjusting the access method based on the content of other children's questions. Some or all of the above processing in the access unit is performed using AI. For example, the access unit can analyze the content of other children's questions and automatically adjust the optimal access method based on that analysis.

[0074] The following briefly describes the processing flow for example form 1.

[0075] Step 1: The reception desk inputs the child's question using voice recognition. For example, the child might voice a question like, "Why is the sky blue?", and this question is converted into text by the voice recognition AI. Step 2: The generation unit generates a picture book containing answers to the questions entered by the reception unit. For example, if the image generation AI answers the question "Why is the sky blue?", it will generate a picture book explaining why the sky is blue. The generated picture book will have content that is easy to understand according to the child's age and developmental stage, and will be more relatable and familiar by including the child's name and siblings. Step 3: The reading unit reads aloud the picture book generated by the generation unit. For example, by utilizing voice generation AI, the picture book can be read aloud in a mother's voice. Step 4: The storage unit saves the picture books generated by the generation unit. For example, the generated picture books are saved as a personal bookshelf of knowledge, allowing the user to review their learning. Step 5: The access section accesses other children's questions. For example, if another child has a question like, "Why do rainbows appear?", they can gain new knowledge by reading a picture book that addresses that question.

[0076] (Example of form 2) An educational app according to an embodiment of the present invention is a system that generates original picture books that answer children's "why?" questions. In this educational app, children input their questions using voice recognition, and an image generation AI generates a picture book that includes the answer to that question. The generated picture book has content that is easy to understand according to the child's age and developmental stage, and by including the child's name and siblings, it becomes more familiar and approachable. Furthermore, by utilizing the voice generation AI, the picture book can be read aloud in the voices of family members. The generated picture books are saved as a personal knowledge bookshelf, allowing the child to review what they have learned. In addition, the child can access questions from other children, creating learning opportunities and providing a chance to cultivate intellectual curiosity. For example, a child inputs a question such as "Why is the sky blue?" by voice. This question is converted into text by the voice recognition AI. Next, the image generation AI generates a picture book that includes the answer to the input question. For example, in response to the question "Why is the sky blue?", a picture book explaining why the sky is blue is generated. This picture book is designed to be easy to understand, tailored to the child's age and developmental stage, and becomes more relatable and engaging by including the child's name and siblings. Furthermore, it utilizes voice-generating AI to allow the picture book to be read aloud in the voices of family members. For example, having the picture book read aloud in the mother's voice can make the child feel more connected to it. The generated picture books are saved as a personal knowledge library, allowing the child to review their learning. For example, they can reread previously generated picture books to review what they have learned. In addition, they can access questions from other children, creating learning opportunities and providing a chance to cultivate intellectual curiosity. For example, if another child has a question such as "Why do rainbows appear?", they can gain new knowledge by reading a picture book that answers that question. In this way, the educational app can generate, read aloud, save, and access original picture books in response to children's questions.

[0077] The educational app according to this embodiment comprises a reception unit, a generation unit, a reading unit, a storage unit, and an access unit. The reception unit receives a child's question via voice recognition. For example, a child might voice a question such as, "Why is the sky blue?" This question is converted into text by a voice recognition AI. The generation unit generates a picture book containing the answer to the question entered by the reception unit. For example, an image generation AI generates a picture book explaining why the sky is blue in response to the question, "Why is the sky blue?" The generated picture book is easy to understand according to the child's age and developmental stage, and becomes more familiar and relatable by including the child's name and siblings. The reading unit reads aloud the picture book generated by the generation unit. For example, it can use a voice generation AI to read the picture book in a mother's voice. The storage unit saves the picture book generated by the generation unit. For example, the generated picture book is saved as a personal knowledge bookshelf, allowing the user to review their learning. The access unit accesses questions from other children. For example, if another child has a question such as "Why do rainbows appear?", they can gain new knowledge by reading a picture book that answers that question. Thus, the educational app according to this embodiment can generate, read aloud, save, and access original picture books that address children's questions.

[0078] The reception desk uses voice recognition to input children's questions. For example, a child might voice a question like, "Why is the sky blue?" This question is then converted into text by a voice recognition AI. Specifically, the voice recognition AI uses advanced algorithms to analyze the child's pronunciation and tone of voice and accurately convert it into text data. The voice recognition AI uses noise cancellation technology to remove ambient noise and capture the child's voice clearly. The voice recognition AI can also provide appropriate feedback based on the child's pronunciation characteristics and language proficiency. For example, if the pronunciation is unclear, it will display a message prompting the child to pronounce it again. Furthermore, the voice recognition AI supports multiple languages ​​and can handle questions in different languages. This allows the reception desk to provide an environment where children can input questions naturally and support their first steps in learning.

[0079] The generation unit generates picture books that include answers to questions entered by the reception unit. For example, if the image generation AI answers the question "Why is the sky blue?", it will generate a picture book explaining why the sky is blue. The generated picture books will have content that is easy to understand according to the child's age and developmental stage, and will be more relatable and familiar by including the child's name and siblings. Specifically, the image generation AI uses natural language processing technology to analyze the entered question and generate an appropriate answer. Next, it generates relevant illustrations and characters based on the answer. For example, to explain why the sky is blue, it creates illustrations that visually represent the changes in the sky's color and the phenomenon of light scattering. The generation unit also customizes the content of the picture book by taking into account the child's individual information. For example, it will make the content more relatable by including the child's name and favorite characters in the picture book. Furthermore, the generation unit regularly updates its database and incorporates new information and technologies to improve the quality of the picture book's story and illustrations. In this way, the generation unit can provide children with engaging and educational picture books and enhance their motivation to learn.

[0080] The reading unit reads aloud the picture book generated by the generation unit. For example, it can use voice generation AI to read a picture book in a mother's voice. Specifically, the voice generation AI generates natural and emotionally rich voices based on pre-recorded samples of a mother's voice. The voice generation AI analyzes the text data and reads it aloud with appropriate intonation and rhythm. The reading unit can also adjust the reading speed and volume according to the child's reactions and level of understanding. For example, it will read slowly and carefully in parts that the child shows interest in, while reading smoothly in parts that the child understands better. Furthermore, the reading unit offers multiple voice options, allowing children to enjoy the picture book in their favorite voice. For example, it can read in various voices, such as a father's voice or a character's voice. In this way, the reading unit can provide children with a fun and educational read-aloud experience, enhancing their learning effectiveness.

[0081] The storage unit stores the picture books generated by the generation unit. For example, the generated picture books are stored as a personal knowledge bookshelf, allowing users to review their learning. Specifically, the storage unit saves the generated picture books to cloud storage, making them accessible at any time. The storage unit manages the picture book metadata (title, creation date, content summary, etc.), enabling efficient searching and organization. The storage unit also manages version control of picture books, allowing comparison between past and latest versions. Furthermore, the storage unit provides a picture book sharing function, allowing users to share picture books with family and friends. For example, a picture book created by a child can be sent to grandparents, allowing the whole family to enjoy the results of their learning. In this way, the storage unit can centrally manage children's learning history and support reflection on and sharing of their learning.

[0082] The Access Unit provides access to other children's questions. For example, if another child has a question like, "Why do rainbows form?", they can gain new knowledge by reading a picture book that addresses that question. Specifically, the Access Unit provides a function to access a database of picture books created by other children and search for relevant books. The Access Unit uses an algorithm to recommend the most suitable picture book based on keywords and categories of questions. For example, searching with the keyword "rainbow" will display picture books that explain the formation process of rainbows and the breakdown of colors. The Access Unit also provides picture book rating and comment functions, allowing children to share their opinions and impressions. In this way, the Access Unit provides children with opportunities to encounter other children's questions and learning, promoting mutual learning. Furthermore, the Access Unit can maintain children's motivation to learn by regularly adding new picture books and always providing the latest information.

[0083] The generation unit includes a customization unit that customizes the content of the picture book to suit the child's age and developmental stage. For example, the generation unit adjusts the content of the picture book according to the child's age. For instance, it generates picture books for toddlers that use simple language and colorful illustrations, and picture books for elementary school children that include detailed explanations and concrete examples. The generation unit can also customize the content of the picture book according to the child's developmental stage. For example, it provides information on content that is easy to understand and of an appropriate difficulty level according to the developmental stage. This makes it possible to generate customized picture books that are tailored to the child's age and developmental stage. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation AI automatically selects appropriate content based on the child's age and developmental stage and generates a picture book.

[0084] The reading unit includes a voice setting unit for reading picture books in the voices of family members. For example, the reading unit can read picture books in the voice of a mother. The voice setting unit records the voices of family members and sets the unit to use those voices to read picture books. For example, it can record the voice of a mother and set the unit to use that voice to read picture books. The voice setting unit can also set the unit to use the voices of a father or sibling to read picture books. This allows picture books to be read in the voices of family members, making them more familiar to children. Some or all of the above processing in the reading unit may be performed using AI or not. For example, the voice setting unit can perform voice settings using an AI model that records the voices of family members and sets the unit to use those voices to read picture books.

[0085] The storage unit saves the generated picture books as a personal bookshelf of knowledge. The storage unit can, for example, save the generated picture books as a digital library. For example, the generated picture books are saved in digital format and can be accessed at any time. The storage unit can also save the picture books as physical bookshelves. For example, the generated picture books can be printed and stored on a physical bookshelf. This allows the generated picture books to be saved as a personal bookshelf of knowledge. Some or all of the above processes in the storage unit may be performed using AI or not. For example, the storage unit can perform saving using an AI model that saves the generated picture books as a digital library.

[0086] The access unit accesses picture books that answer questions from other children. For example, if another child has a question such as "Why do rainbows appear?", the access unit can access a picture book that answers that question. The access unit can access picture books that answer questions from other children through online access. For example, it can browse picture books that answer questions from other children via the internet. The access unit can also access picture books that answer questions from other children through offline access. For example, it can browse downloaded picture books offline. This allows access to picture books that answer questions from other children and provides learning opportunities. Some or all of the above processing in the access unit may be performed using AI or not. For example, the access unit can use an AI model to access picture books that answer questions from other children.

[0087] The customization section generates more relatable and engaging picture books by incorporating the child's name and siblings. For example, the customization section can feature the child's name as a character in the picture book. By naming the main character of the picture book after the child, the child can feel like they are part of the story. The customization section can also include the names of siblings and other family members in the picture book. For example, siblings and other family members can appear as characters who go on adventures together in the picture book. In this way, by including the child's name and siblings, it is possible to generate more relatable and engaging picture books. Some or all of the above processes in the customization section are performed using a generation AI. For example, the generation AI automatically generates characters for the picture book based on the child's name and information about siblings, and incorporates them into the story.

[0088] The reception desk estimates the child's emotions and adjusts the timing of question input based on the estimated emotions. For example, if the child is excited, the reception desk delays prompting for question input, allowing the child to enter the question when they are calm. For example, when the child is excited, it prompts for question input after a short delay. Also, if the child is tired, the reception desk simplifies question input, allowing for quick input. For example, when the child is tired, it prompts for question input in a simple question format. Furthermore, if the child is focused, the reception desk prompts for question input immediately, allowing the child to enter the question while maintaining their concentration. For example, when the child is focused, it prompts for question input immediately. In this way, by adjusting the timing of question input according to the child's emotions, questions can be entered at a more appropriate time. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI estimates the child's emotions using, for example, facial recognition or voice analysis, and adjusts the input timing based on the results.

[0089] The reception desk analyzes the child's past question history and selects the optimal input method. For example, the reception desk prioritizes suggesting input methods that the child has frequently used in the past (voice, text, etc.). For instance, if the child prefers voice input, it will prioritize suggesting voice input. The reception desk can also suggest input methods related to specific themes based on the child's past question history. For example, if the child has many questions about science, it will suggest science-related input methods. Furthermore, the reception desk can analyze the child's past question history and suggest the most efficient input method. For example, based on past question history, it will suggest the method that allows for the shortest input time. In this way, the optimal input method can be selected by analyzing the child's past question history. Some or all of the above processing in the reception desk is performed using AI. For example, the AI ​​analyzes the child's past question history and automatically selects the optimal input method.

[0090] The input system filters questions based on the child's current interests. For example, it prioritizes questions related to the child's current interests. If the child is interested in dinosaurs, it prioritizes questions related to dinosaurs. The input system can also filter relevant questions based on the child's current interests and prompt for input. For example, if the child is interested in space, it filters and prompts for questions related to space. Furthermore, the input system can analyze the child's current interests and prompt for the most relevant questions. For example, if the child is interested in animals, it prioritizes questions related to animals. This allows for the input of more relevant questions by filtering them based on the child's current interests. Some or all of the above processing in the input system is performed using AI. For example, the AI ​​analyzes the child's current interests and automatically filters for the most relevant questions.

[0091] The reception desk estimates the child's emotions and prioritizes the questions to be entered based on the estimated emotions. For example, if the child is excited, the reception desk will prioritize simple and intuitive questions. For instance, when the child is excited, it will ask questions in the form of simple questions. The reception desk can also prioritize detailed questions if the child is relaxed. For example, when the child is relaxed, it will ask questions that require detailed explanations. Furthermore, if the child is tired, the reception desk can prioritize questions that can be answered quickly. For example, when the child is tired, it will ask simple questions that can be answered quickly. By prioritizing questions according to the child's emotions, more appropriate questions can be entered. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI estimates the child's emotions using, for example, facial recognition or voice analysis, and prioritizes questions based on the results.

[0092] The reception desk prioritizes the input of highly relevant questions by considering the child's geographical location when a question is entered. For example, if the child is in a specific location, the reception desk will prioritize questions related to that location. For example, if the child is in a zoo, it will prioritize questions related to animals. The reception desk can also filter and prompt for highly relevant questions based on the child's current location. For example, if the child is in a museum, it will filter and prompt for questions related to museums. Furthermore, the reception desk can analyze the child's geographical location and prompt for the input of the most relevant questions. For example, if the child is in a park, it will prioritize questions related to parks. In this way, highly relevant questions can be prioritized by considering the child's geographical location. Some or all of the above processing in the reception desk is performed using AI. For example, the AI ​​analyzes the child's geographical location and automatically filters for the most relevant questions.

[0093] The reception desk analyzes the child's social media activity when a question is entered and prompts for relevant questions. For example, the reception desk prioritizes questions related to themes the child shows interest in on social media. For instance, if the child shows interest in dinosaurs on social media, it will prioritize questions related to dinosaurs. The reception desk can also analyze the child's social media activity and prompt for the most relevant questions. For example, if the child shows interest in space on social media, it will prompt for questions related to space. Furthermore, the reception desk can filter relevant questions and prompt for input based on the child's social media activity history. For example, if the child shows interest in animals on social media, it will prompt for questions related to animals. This allows for the input of relevant questions by analyzing the child's social media activity. Some or all of the above processing in the reception desk is performed using AI. For example, the AI ​​analyzes the child's social media activity and automatically filters for the most relevant questions.

[0094] The generation unit estimates the child's emotions and adjusts the picture book's presentation based on the estimated emotions. For example, if the child is excited, the generation unit generates a picture book with visually stimulating effects. For instance, when the child is excited, it generates a picture book that makes extensive use of colorful and dynamic illustrations. The generation unit can also generate a picture book with calm colors and design if the child is relaxed. For example, when the child is relaxed, it generates a picture book with soft colors and a simple design. Furthermore, if the child is tired, the generation unit can generate a simple and highly visible picture book. For example, when the child is tired, it generates a short and concise picture book. In this way, by adjusting the presentation of the picture book according to the child's emotions, a more appropriate picture book can be generated. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI estimates the child's emotions using, for example, facial recognition or voice analysis, and adjusts the presentation of the picture book based on the results.

[0095] The generation unit adjusts the level of detail in the picture book based on the importance of the question during the generation process. For example, for highly important questions, the generation unit generates a picture book with detailed explanations and many illustrations. For example, for scientific questions, it generates a picture book with detailed explanations and specific examples. The generation unit can also generate a picture book with concise explanations and few illustrations for less important questions. For example, for everyday questions, it generates a picture book with concise explanations and few illustrations. Furthermore, the generation unit can adjust the number of pages and the depth of content in the picture book according to the importance of the question. For example, for highly important questions, it increases the number of pages and delves deeper into the content. In this way, by adjusting the level of detail in the picture book based on the importance of the question, a more appropriate picture book can be generated. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation AI analyzes the importance of the question and automatically adjusts the level of detail in the picture book based on that.

[0096] The generation unit applies different generation algorithms depending on the category of the question when generating picture books. For example, for questions about science, the generation unit applies a generation algorithm that includes scientific explanations. For example, for scientific questions, it applies a generation algorithm based on scientific theories and experimental results. The generation unit can also apply a generation algorithm that includes historical background for questions about history. For example, for historical questions, it applies a generation algorithm based on historical events and people. Furthermore, for questions about nature, the generation unit can apply a generation algorithm that emphasizes the beauty of nature. For example, for questions about nature, it applies a generation algorithm based on beautiful landscapes and flora and fauna. In this way, by applying different generation algorithms depending on the category of the question, a more appropriate picture book can be generated. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation AI analyzes the category of the question and automatically applies the optimal generation algorithm based on it.

[0097] The generation unit estimates the child's emotions and adjusts the length of the picture book based on the estimated emotions. For example, if the child is excited, the generation unit generates a short, visually stimulating picture book. For instance, when the child is excited, it generates a picture book with a short number of pages and many colorful illustrations. The generation unit can also generate a long, detailed picture book if the child is relaxed. For example, when the child is relaxed, it generates a picture book with a long number of pages and detailed explanations. Furthermore, if the child is tired, the generation unit can generate a short, concise picture book. For example, when the child is tired, it generates a picture book with a short number of pages and concise explanations. In this way, by adjusting the length of the picture book according to the child's emotions, a more appropriate picture book can be generated. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI estimates the child's emotions using, for example, facial recognition or voice analysis, and adjusts the length of the picture book based on the results.

[0098] The generation unit determines the priority of picture books based on when the questions were submitted. For example, the generation unit prioritizes generating picture books for recently submitted questions. For instance, it prioritizes generating picture books for the latest questions to provide quick answers. The generation unit can also prioritize generating newer questions and postpone older questions. For example, it prioritizes generating picture books for newer questions over older ones. Furthermore, the generation unit can adjust the order in which picture books are generated based on the submission date. For example, it determines the order in which picture books are generated according to the submission date to generate picture books efficiently. This allows for the generation of more appropriate picture books by determining the priority of picture books based on when the questions were submitted. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation AI analyzes when the questions were submitted and automatically determines the priority of picture books based on that.

[0099] The generation unit adjusts the order of picture books based on the relevance of the questions during the picture book generation process. For example, the generation unit prioritizes generating picture books for highly relevant questions. For instance, it prioritizes generating picture books for highly relevant questions to provide quick answers. The generation unit can also prioritize generating highly relevant questions while delaying less relevant questions. For example, it prioritizes generating picture books for highly relevant questions over less relevant ones. Furthermore, the generation unit can adjust the generation order of picture books based on the relevance of the questions. For example, it determines the generation order of picture books according to their relevance to efficiently generate them. This allows for the generation of more appropriate picture books by adjusting the order of picture books based on the relevance of the questions. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation AI analyzes the relevance of the questions and automatically adjusts the order of picture books based on that analysis.

[0100] The reading unit estimates the child's emotions and adjusts the reading style based on the estimated emotions. For example, if the child is excited, the reading unit will read in a cheerful and bright voice. For example, when the child is excited, the reading unit will read the picture book in a cheerful and bright voice. The reading unit can also read in a calm voice if the child is relaxed. For example, when the child is relaxed, the reading unit will read the picture book in a calm voice. Furthermore, if the child is tired, the reading unit can read in a gentle voice. For example, when the child is tired, the reading unit will read the picture book in a gentle voice. In this way, by adjusting the reading style according to the child's emotions, a more appropriate reading can be achieved. Emotion estimation is achieved using an emotion estimation function that utilizes an emotion engine or generative AI. The generative AI estimates the child's emotions using, for example, facial recognition or voice analysis, and adjusts the reading style based on the results.

[0101] The reading unit adjusts the reading speed and tone based on the content of the picture book during reading. For example, in action scenes, the reading unit reads at a fast speed and in a high tone. The reading unit can also read at a slow speed and in a low tone in explanatory scenes. Furthermore, the reading unit can read in an emotional tone in emotional scenes. By adjusting the reading speed and tone based on the content of the picture book, a more appropriate reading can be achieved. Some or all of the above processing in the reading unit may be performed using AI, or not. For example, the reading unit can perform reading using an AI model that analyzes the content of the picture book and automatically adjusts the reading speed and tone based on that analysis.

[0102] The reading unit selects the optimal reading method by referring to the child's past responses during reading. For example, the reading unit may prioritize reading methods that the child has preferred in the past. For example, it may select the optimal reading method based on the child's past preferred reading methods. The reading unit can also analyze the child's past responses and select the most effective reading method. For example, it may select the most effective reading method based on the child's past responses. Furthermore, the reading unit can adjust the reading speed and tone based on the child's past responses. For example, it may adjust the reading speed and tone based on the child's past responses. This allows the optimal reading method to be selected by referring to the child's past responses. Some or all of the above processing in the reading unit may be performed using AI or not. For example, the reading unit can perform reading using an AI model that analyzes the child's past responses and automatically selects the optimal reading method based on them.

[0103] The reading unit estimates the child's emotions and adjusts the reading order based on the estimated emotions. For example, if the child is excited, the reading unit will read the scenes that interest them first. The reading unit can also read the story in order if the child is relaxed. Furthermore, if the child is tired, the reading unit can prioritize reading important scenes. This allows for more appropriate reading by adjusting the reading order according to the child's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI estimates the child's emotions using, for example, facial recognition or voice analysis, and adjusts the reading order based on the results.

[0104] The reading unit selects the optimal reading method when reading aloud, taking into account the child's geographical location. For example, if the child is in a specific location, the reading unit will prioritize reading content related to that location. For example, if the child is in a zoo, it will prioritize reading content related to animals. The reading unit can also read content that is highly relevant based on the child's current location. For example, if the child is in a museum, it will read content related to museums. Furthermore, the reading unit can analyze the child's geographical location and read the most relevant content. For example, if the child is in a park, it will prioritize reading content related to parks. In this way, the optimal reading method can be selected by considering the child's geographical location. Some or all of the above processing in the reading unit may be performed using AI, or not. For example, the reading unit can perform reading using an AI model that analyzes the child's geographical location and automatically selects the optimal reading method based on that analysis.

[0105] The reading unit analyzes the child's social media activity during reading and suggests a reading method. For example, the reading unit prioritizes reading content related to themes the child shows interest in on social media. For example, if the child shows interest in dinosaurs on social media, it will prioritize reading content related to dinosaurs. The reading unit can also analyze the child's social media activity and read the most relevant content. For example, if the child shows interest in space on social media, it will read content related to space. Furthermore, the reading unit can read relevant content based on the child's social media activity history. For example, if the child shows interest in animals on social media, it will read content related to animals. In this way, by analyzing the child's social media activity, the optimal reading method can be suggested. Some or all of the above processing in the reading unit may be performed using AI or not. For example, the reading unit can perform reading using an AI model that analyzes the child's social media activity and automatically suggests the optimal reading method based on that analysis.

[0106] The storage unit estimates the child's emotions and determines the priority of picture books to save based on the estimated emotions. For example, if the child is excited, the storage unit will prioritize saving the most recent picture books. The storage unit can also save older picture books again if the child is relaxed. Furthermore, if the child is tired, the storage unit can prioritize saving picture books that can be saved in a short amount of time. In this way, by determining the priority of picture books to save according to the child's emotions, more appropriate picture books can be saved preferentially. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI estimates the child's emotions using, for example, facial recognition or voice analysis, and determines the priority of picture books to save based on the results.

[0107] The storage unit adjusts the save format based on the content of the picture book during saving. For example, if a picture book has many illustrations, the storage unit will save it in a high-resolution image format. For example, if a picture book has many illustrations, it will save it in a high-resolution JPEG format. The storage unit can also save picture books with a lot of text in a text format. For example, if a picture book has a lot of text, it will save it in PDF format. Furthermore, if a picture book contains videos, the storage unit can save it in a video format. For example, if a picture book contains videos, it will save it in MP4 format. In this way, by adjusting the save format based on the content of the picture book, the optimal format can be used for saving. Some or all of the above processing in the storage unit may be performed using AI, or it may be performed without AI. For example, the storage unit can perform saving using an AI model that analyzes the content of the picture book and automatically selects the optimal save format based on that analysis.

[0108] The storage unit, when saving, selects the optimal saving method by referring to the child's past saving history. For example, the storage unit may prioritize the format that the child has preferred to save in the past. For example, it may select the optimal saving method based on the format that the child has preferred to save in the past. The storage unit can also analyze the child's past saving history and select the most efficient saving method. For example, it may select the most efficient saving method based on the child's past saving history. Furthermore, the storage unit may adjust the saving format based on the child's past saving history. For example, it may adjust the saving format based on the child's past saving history. This allows the optimal saving method to be selected by referring to the child's past saving history. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit can perform saving using an AI model that analyzes the child's past saving history and automatically selects the optimal saving method based on it.

[0109] The storage unit estimates the child's emotions and adjusts the display method of the stored picture books based on the estimated emotions. For example, if the child is excited, the storage unit provides a visually stimulating display method. For example, when the child is excited, it provides a colorful and dynamic display method. The storage unit can also provide a display method with calm colors if the child is relaxed. For example, when the child is relaxed, it provides a display method with soft colors. Furthermore, the storage unit can also provide a simple and highly visible display method if the child is tired. For example, when the child is tired, it provides a simple and highly visible display method. In this way, by adjusting the display method of the stored picture books according to the child's emotions, a more appropriate display method can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI estimates the child's emotions using, for example, facial recognition or voice analysis, and adjusts the display method of the stored picture books based on the results.

[0110] The preservation unit selects the optimal preservation method when preserving a child, taking into account the child's geographical location. For example, if the child is in a specific location, the preservation unit provides a preservation method related to that location. For example, if the child is in a zoo, it provides a preservation method related to animals. The preservation unit can also select the optimal preservation method based on the child's current location. For example, if the child is in a museum, it selects a preservation method related to the museum. Furthermore, the preservation unit can analyze the child's geographical location and select the most efficient preservation method. For example, if the child is in a park, it selects a preservation method related to the park. In this way, the optimal preservation method can be selected by considering the child's geographical location. Some or all of the above processing in the preservation unit may be performed using AI, or not. For example, the preservation unit can perform preservation using an AI model that analyzes the child's geographical location and automatically selects the optimal preservation method based on that analysis.

[0111] The storage unit analyzes the child's social media activity during storage and proposes a storage method. For example, the storage unit prioritizes saving picture books that the child wants to share on social media. For example, it proposes the optimal storage method based on the picture books the child wants to share on social media. The storage unit can also analyze the child's social media activity and propose the most relevant storage method. For example, it proposes the most relevant storage method based on the child's social media activity. Furthermore, the storage unit can adjust the storage format based on the child's social media activity history. For example, it adjusts the storage format based on the child's social media activity history. This allows the storage unit to propose the optimal storage method by analyzing the child's social media activity. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit can perform storage using an AI model that analyzes the child's social media activity and automatically proposes the optimal storage method based on that analysis.

[0112] The access unit estimates the child's emotions and determines the priority of picture books to access based on the estimated emotions. For example, if the child is excited, the access unit will prioritize accessing the most recent picture books. The access unit can also allow the child to access older picture books again if they are relaxed. Furthermore, if the child is tired, the access unit can prioritize accessing picture books that can be accessed in a short amount of time. In this way, by determining the priority of picture books to access according to the child's emotions, more appropriate picture books can be accessed preferentially. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI estimates the child's emotions using, for example, facial recognition or voice analysis, and determines the priority of picture books to access based on the results.

[0113] The access unit adjusts the access method based on the content of other children's questions when accessing content. For example, the access unit prioritizes access to picture books related to questions that other children are interested in. For example, it adjusts the optimal access method based on picture books related to questions that other children are interested in. The access unit can also analyze the content of other children's questions and access the most relevant picture books. For example, it accesses the most relevant picture books based on the content of other children's questions. Furthermore, the access unit can adjust the access method based on the content of other children's questions. For example, it adjusts the optimal access method based on the content of other children's questions. This allows access to more relevant picture books by adjusting the access method based on the content of other children's questions. Some or all of the above processing in the access unit may be performed using AI or not. For example, the access unit can perform access using an AI model that analyzes the content of other children's questions and automatically adjusts the optimal access method based on that analysis.

[0114] The access unit, upon access, selects the optimal access method by referring to the child's past access history. For example, the access unit may prioritize accessing picture books that the child has previously enjoyed accessing. For example, it may select the optimal access method based on the picture books the child has previously enjoyed accessing. The access unit can also analyze the child's past access history and select the most efficient access method. For example, it may select the most efficient access method based on the child's past access history. Furthermore, the access unit can adjust the access method based on the child's past access history. For example, it may adjust the access method based on the child's past access history. This allows the optimal access method to be selected by referring to the child's past access history. Some or all of the above processing in the access unit may be performed using AI or not. For example, the access unit can perform access using an AI model that analyzes the child's past access history and automatically selects the optimal access method based on it.

[0115] The access unit estimates the child's emotions and adjusts the display method of the accessed picture book based on the estimated emotions. For example, if the child is excited, the access unit provides a visually stimulating display method. For example, when the child is excited, it provides a colorful and dynamic display method. The access unit can also provide a display method with calm colors if the child is relaxed. For example, when the child is relaxed, it provides a display method with soft colors. Furthermore, the access unit can also provide a simple and highly visible display method if the child is tired. For example, when the child is tired, it provides a simple and highly visible display method. In this way, by adjusting the display method of the accessed picture book according to the child's emotions, a more appropriate display method can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI estimates the child's emotions using, for example, facial recognition or voice analysis, and adjusts the display method of the accessed picture book based on the results.

[0116] The access unit selects the optimal access method when accessing content, taking into account the child's geographical location. For example, if the child is in a specific location, the access unit prioritizes accessing picture books related to that location. For example, if the child is in a zoo, it prioritizes accessing picture books related to animals. The access unit can also select the optimal access method based on the child's current location. For example, if the child is in a museum, it selects picture books related to museums. Furthermore, the access unit can analyze the child's geographical location and select the most efficient access method. For example, if the child is in a park, it selects picture books related to parks. In this way, the optimal access method can be selected by considering the child's geographical location. Some or all of the above processing in the access unit may be performed using AI, or not. For example, the access unit can perform access using an AI model that analyzes the child's geographical location and automatically selects the optimal access method based on that analysis.

[0117] The access unit analyzes the child's social media activity and suggests access methods when accessing content. For example, the access unit prioritizes access to picture books related to themes the child shows interest in on social media. For instance, if the child shows interest in dinosaurs on social media, it prioritizes access to picture books related to dinosaurs. The access unit can also analyze the child's social media activity and access the most relevant picture books. For example, if the child shows interest in space on social media, it will access picture books related to space. Furthermore, the access unit can access relevant picture books based on the child's social media activity history. For example, if the child shows interest in animals on social media, it will access picture books related to animals. In this way, by analyzing the child's social media activity, the optimal access method can be suggested. Some or all of the above processing in the access unit may be performed using AI or not. For example, the access unit can perform access using an AI model that analyzes the child's social media activity and automatically suggests the optimal access method based on that analysis.

[0118] The customization unit estimates the child's emotions and adjusts the picture book customization method based on the estimated emotions. For example, if the child is excited, the customization unit generates a picture book with visually stimulating effects. For example, when the child is excited, it generates a picture book that makes extensive use of colorful and dynamic illustrations. The customization unit can also generate a picture book with calm colors and design if the child is relaxed. For example, when the child is relaxed, it generates a picture book with soft colors and a simple design. Furthermore, if the child is tired, the customization unit can generate a simple and highly visible picture book. For example, when the child is tired, it generates a short and concise picture book. In this way, by adjusting the picture book customization method according to the child's emotions, a more appropriate picture book can be generated. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI estimates the child's emotions using, for example, facial recognition or voice analysis, and adjusts the picture book customization method based on the results.

[0119] The customization unit selects the optimal customization method by referring to the child's past question history during the customization process. For example, the customization unit may prioritize customization methods that the child has preferred in the past. For example, it may select the optimal customization method based on the child's past preferred customization methods. The customization unit can also analyze the child's past question history and select the most effective customization method. For example, it may select the most effective customization method based on the child's past question history. Furthermore, the customization unit can adjust the customization method based on the child's past question history. For example, it may adjust the customization method based on the child's past question history. This allows the optimal customization method to be selected by referring to the child's past question history. Some or all of the above processing in the customization unit is performed using a generative AI. For example, the generative AI analyzes the child's past question history and automatically selects the optimal customization method based on it.

[0120] The customization unit performs customization based on the child's current interests and concerns. For example, the customization unit will perform customizations related to themes the child is currently interested in. For instance, if the child is interested in dinosaurs, it will perform customizations related to dinosaurs. The customization unit can also perform customizations related to the child's current interests. For example, if the child is interested in space, it will perform customizations related to space. Furthermore, the customization unit can analyze the child's current interests and concerns and perform the most relevant customizations. For example, if the child is interested in animals, it will perform customizations related to animals. This allows for the generation of more appropriate picture books by customizing based on the child's current interests and concerns. Some or all of the above processing in the customization unit is performed using a generative AI. For example, the generative AI analyzes the child's current interests and concerns and automatically performs the optimal customizations based on that.

[0121] The customization unit estimates the child's emotions and determines the priority of picture books to customize based on the estimated emotions. For example, if the child is excited, the customization unit will prioritize visually stimulating picture books. For example, when the child is excited, it will prioritize colorful and dynamic picture books. The customization unit can also prioritize picture books with calming colors if the child is relaxed. For example, when the child is relaxed, it will prioritize picture books with soft colors. Furthermore, if the child is tired, the customization unit can also prioritize simple and highly visible picture books. For example, when the child is tired, it will prioritize simple and highly visible picture books. In this way, by determining the priority of picture books to customize according to the child's emotions, more appropriate picture books can be prioritized. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI estimates the child's emotions using, for example, facial recognition or voice analysis, and determines the priority of picture books to customize based on the results.

[0122] The customization unit selects the optimal customization method by considering the child's geographical location during the customization process. For example, if the child is in a specific location, the customization unit will perform customizations related to that location. For example, if the child is in a zoo, it will perform customizations related to animals. The customization unit can also select the optimal customization method based on the child's current location. For example, if the child is in a museum, it will select customizations related to the museum. Furthermore, the customization unit can analyze the child's geographical location and select the most relevant customization method. For example, if the child is in a park, it will select customizations related to the park. In this way, the optimal customization method can be selected by considering the child's geographical location. Some or all of the above processing in the customization unit is performed using generative AI. For example, the generative AI analyzes the child's geographical location and automatically selects the optimal customization method based on that analysis.

[0123] The customization unit analyzes the child's social media activity during the customization process and proposes customization methods. For example, the customization unit performs customizations related to themes the child shows interest in on social media. For instance, if the child shows interest in dinosaurs on social media, it will perform dinosaur-related customizations. The customization unit can also analyze the child's social media activity and perform the most relevant customizations. For example, if the child shows interest in space on social media, it will perform space-related customizations. Furthermore, the customization unit can perform relevant customizations based on the child's social media activity history. For example, if the child shows interest in animals on social media, it will perform animal-related customizations. In this way, by analyzing the child's social media activity, the optimal customization method can be proposed. Some or all of the above processing in the customization unit is performed using generative AI. For example, the generative AI analyzes the child's social media activity and automatically proposes the optimal customization method based on that analysis.

[0124] The voice setting unit estimates the child's emotions and adjusts the voice setting method based on the estimated emotions. For example, if the child is excited, the voice setting unit will use a cheerful and bright voice. The voice setting unit can also use a calm voice if the child is relaxed. For example, if the child is relaxed, the voice setting unit will use a calm voice. Furthermore, if the child is tired, the voice setting unit can use a gentle voice. For example, if the child is tired, the voice setting unit will use a gentle voice. In this way, by adjusting the voice setting method according to the child's emotions, more appropriate voice settings can be achieved. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI estimates the child's emotions using, for example, facial recognition or voice analysis, and adjusts the voice setting method based on the results.

[0125] The voice setting unit selects the optimal voice setting based on the characteristics of each family member's voice during the voice setting process. For example, the voice setting unit can analyze the characteristics of the mother's voice and set a voice setting that is similar to the mother's voice. For example, it can select the optimal voice setting based on the characteristics of the mother's voice. The voice setting unit can also analyze the characteristics of the father's voice and set a voice setting that is similar to the father's voice. For example, it can select the optimal voice setting based on the characteristics of the father's voice. Furthermore, the voice setting unit can analyze the characteristics of siblings' voices and set a voice setting that is similar to their voices. For example, it can select the optimal voice setting based on the characteristics of each family member's voice. This allows for a more user-friendly voice setting by selecting the optimal voice setting based on the characteristics of each family member's voice. Some or all of the above-described processes in the voice setting unit may be performed using AI or not. For example, the voice setting unit can perform voice setting using an AI model that analyzes the characteristics of each family member's voice and automatically selects the optimal voice setting based on that analysis.

[0126] The voice setting unit selects the optimal voice setting method by referring to the child's past responses when setting the voice. For example, the voice setting unit may prioritize selecting voice settings that the child has preferred in the past. For example, it may select the optimal voice setting method based on the child's past preferred voice settings. The voice setting unit can also analyze the child's past responses and select the most effective voice setting method. For example, it may select the most effective voice setting method based on the child's past responses. Furthermore, the voice setting unit may adjust the speed and tone of the voice setting based on the child's past responses. For example, it may adjust the speed and tone of the voice setting based on the child's past responses. This allows the optimal voice setting method to be selected by referring to the child's past responses. Some or all of the above processing in the voice setting unit may be performed using AI or not. For example, the voice setting unit can perform voice setting using an AI model that analyzes the child's past responses and automatically selects the optimal voice setting method based on that analysis.

[0127] The voice setting unit estimates the child's emotions and determines the priority of voice settings based on the estimated emotions. For example, if the child is excited, the voice setting unit will prioritize a cheerful and bright voice setting. The voice setting unit can also prioritize a calm voice setting if the child is relaxed. For example, if the child is relaxed, a calm voice setting will be prioritized. Furthermore, the voice setting unit can also prioritize a gentle voice setting if the child is tired. For example, if the child is tired, a gentle voice setting will be prioritized. In this way, more appropriate voice settings can be achieved by determining the priority of voice settings according to the child's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI estimates the child's emotions using, for example, facial recognition or voice analysis, and determines the priority of voice settings based on the results.

[0128] The voice setting unit selects the optimal voice setting method when setting voices, taking into account the child's geographical location. For example, if the child is in a specific location, the voice setting unit will set voices related to that location. For example, if the child is in a zoo, it will set voices related to animals. The voice setting unit can also select the optimal voice setting method based on the child's current location. For example, if the child is in a museum, it will select voices related to the museum. Furthermore, the voice setting unit can analyze the child's geographical location and select the most relevant voice setting method. For example, if the child is in a park, it will select voices related to the park. In this way, the optimal voice setting method can be selected by considering the child's geographical location. Some or all of the above processing in the voice setting unit may be performed using AI or not. For example, the voice setting unit can perform voice settings using an AI model that analyzes the child's geographical location and automatically selects the optimal voice setting method based on that analysis.

[0129] The voice setting unit analyzes the child's social media activity and proposes voice setting methods during voice setting. For example, the voice setting unit sets voice settings related to themes the child shows interest in on social media. For example, if the child shows interest in dinosaurs on social media, it sets voice settings related to dinosaurs. The voice setting unit can also analyze the child's social media activity and set the most relevant voice settings. For example, if the child shows interest in space on social media, it sets voice settings related to space. Furthermore, the voice setting unit can set relevant voice settings based on the child's social media activity history. For example, if the child shows interest in animals on social media, it sets voice settings related to animals. In this way, by analyzing the child's social media activity, the optimal voice setting method can be proposed. Some or all of the above processing in the voice setting unit may be performed using AI or not. For example, the voice setting unit can perform voice setting using an AI model that analyzes the child's social media activity and automatically proposes the optimal voice setting method based on that analysis.

[0130] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0131] The reception desk can estimate a child's emotions and adjust the timing of question input based on the estimated emotions. For example, if a child is excited, the prompt for question input can be delayed, allowing them to input the question in a calmer state. If a child is tired, the question input can be simplified, allowing them to input the question in a shorter time. Furthermore, if a child is focused, the prompt for question input can be given immediately, allowing them to input the question while maintaining their concentration. In this way, by adjusting the timing of question input according to the child's emotions, questions can be entered at a more appropriate time. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI can estimate a child's emotions using, for example, facial recognition or voice analysis, and adjust the input timing based on the results.

[0132] The generation unit can estimate a child's emotions and adjust the presentation of the picture book based on those estimates. For example, if a child is excited, it can generate a picture book with visually stimulating effects. If a child is relaxed, it can generate a picture book with calming colors and design. Furthermore, if a child is tired, it can generate a simple and highly visible picture book. In this way, by adjusting the presentation of the picture book according to the child's emotions, a more appropriate picture book can be generated. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can estimate a child's emotions using, for example, facial recognition or voice analysis, and adjust the presentation of the picture book based on the results.

[0133] The reading unit can estimate a child's emotions and adjust its reading style based on those estimates. For example, if a child is excited, it can read in a cheerful and bright voice. If a child is relaxed, it can read in a calm voice. Furthermore, if a child is tired, it can read in a gentle voice. By adjusting the reading style according to the child's emotions, it can provide more appropriate reading. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI can estimate a child's emotions using, for example, facial recognition or voice analysis, and adjust the reading style based on the results.

[0134] The storage unit can estimate a child's emotions and determine the priority of picture books to save based on the estimated emotions. For example, if a child is excited, the most recent picture book can be saved first. If a child is relaxed, older picture books can be saved again. Furthermore, if a child is tired, picture books that can be saved in a short time can be saved first. In this way, by determining the priority of picture books to save according to the child's emotions, more appropriate picture books can be saved first. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI can estimate a child's emotions using, for example, facial recognition or voice analysis, and determine the priority of picture books to save based on the results.

[0135] The access unit can estimate a child's emotions and determine the priority of picture books to access based on those estimates. For example, if a child is excited, the newest picture book can be prioritized. If a child is relaxed, older picture books can be accessed again. Furthermore, if a child is tired, picture books that can be accessed quickly can be prioritized. This allows for access to more appropriate picture books by prioritizing them according to the child's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI can estimate a child's emotions using, for example, facial recognition or voice analysis, and determine the priority of picture books to access based on the results.

[0136] The reception desk can analyze a child's past question history and select the most suitable input method. For example, it can prioritize suggesting input methods that the child has frequently used in the past (voice, text, etc.). It can also suggest input methods related to specific topics based on the child's past question history. Furthermore, it can analyze the child's past question history and suggest the most efficient input method. In this way, the optimal input method can be selected by analyzing the child's past question history. Some or all of the above processes in the reception desk are performed using AI. For example, the AI ​​can analyze the child's past question history and automatically select the most suitable input method.

[0137] The reception desk can filter questions based on the child's current interests and concerns when they are entered. For example, it can prioritize questions related to topics the child is currently interested in. It can also filter relevant questions based on the child's current interests and prompt for input. Furthermore, it can analyze the child's current interests and concerns and prompt for the most relevant questions. This allows for the input of more relevant questions by filtering questions based on the child's current interests. Some or all of the above processing in the reception desk is performed using AI. For example, the AI ​​can analyze the child's current interests and concerns and automatically filter for the most relevant questions.

[0138] The generation unit can adjust the level of detail in a picture book based on the importance of the question during the book generation process. For example, for highly important questions, it can generate a picture book with detailed explanations and many illustrations. Conversely, for less important questions, it can generate a picture book with concise explanations and fewer illustrations. Furthermore, it can adjust the number of pages and the depth of content of the picture book according to the importance of the question. This allows for the generation of more appropriate picture books by adjusting the level of detail based on the importance of the question. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation AI can analyze the importance of the question and automatically adjust the level of detail of the picture book based on that analysis.

[0139] The generation unit can apply different generation algorithms depending on the category of the question when generating a picture book. For example, a generation algorithm that includes scientific explanations can be applied to questions about science. Similarly, a generation algorithm that includes historical background can be applied to questions about history. Furthermore, a generation algorithm that emphasizes the beauty of nature can be applied to questions about nature. By applying different generation algorithms depending on the category of the question, a more appropriate picture book can be generated. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation AI can analyze the category of the question and automatically apply the most suitable generation algorithm based on that.

[0140] The access unit can adjust its access method based on the content of other children's questions when accessing content. For example, it can prioritize accessing picture books related to questions that other children are interested in. It can also analyze the content of other children's questions and access the most relevant picture books. Furthermore, it can adjust its access method based on the content of other children's questions. This allows access to more relevant picture books by adjusting the access method based on the content of other children's questions. Some or all of the above processing in the access unit is performed using AI. For example, the access unit can analyze the content of other children's questions and automatically adjust the optimal access method based on that analysis.

[0141] The following briefly describes the processing flow for example form 2.

[0142] Step 1: The reception desk inputs the child's question using voice recognition. For example, the child might voice a question like, "Why is the sky blue?", and this question is converted into text by the voice recognition AI. Step 2: The generation unit generates a picture book containing answers to the questions entered by the reception unit. For example, if the image generation AI answers the question "Why is the sky blue?", it will generate a picture book explaining why the sky is blue. The generated picture book will have content that is easy to understand according to the child's age and developmental stage, and will be more relatable and familiar by including the child's name and siblings. Step 3: The reading unit reads aloud the picture book generated by the generation unit. For example, by utilizing voice generation AI, the picture book can be read aloud in a mother's voice. Step 4: The storage unit saves the picture books generated by the generation unit. For example, the generated picture books are saved as a personal bookshelf of knowledge, allowing the user to review their learning. Step 5: The access section accesses other children's questions. For example, if another child has a question like, "Why do rainbows appear?", they can gain new knowledge by reading a picture book that addresses that question.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] Each of the multiple elements described above, including the reception unit, generation unit, reading unit, storage unit, and access unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the microphone 38B and control unit 46A of the smart device 14, and inputs the child's question via voice recognition. The generation unit is implemented by the identification processing unit 290 of the data processing unit 12, and generates a picture book using image generation AI. The reading unit is implemented by the speaker 40B and control unit 46A of the smart device 14, and reads the picture book aloud in the family's voice. The storage unit is implemented by the database 24 of the data processing unit 12, and stores the generated picture book. The access unit is implemented by the communication I / F 44 and control unit 46A of the smart device 14, and accesses the questions of other children. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0147] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0148] 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.

[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 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.

[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 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.

[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 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.

[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 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.

[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 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.

[0162] Each of the multiple elements described above, including the reception unit, generation unit, reading unit, storage unit, and access unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the microphone 238 and control unit 46A of the smart glasses 214, and inputs the child's question via voice recognition. The generation unit is implemented by the identification processing unit 290 of the data processing unit 12, and generates a picture book using image generation AI. The reading unit is implemented by the speaker 240 and control unit 46A of the smart glasses 214, and reads the picture book aloud in the family's voice. The storage unit is implemented by the database 24 of the data processing unit 12, and stores the generated picture book. The access unit is implemented by the communication I / F 44 and control unit 46A of the smart glasses 214, and accesses the questions of other children. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0163] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0164] 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.

[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 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.

[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 (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).

[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] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.).

[0175] 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.

[0176] 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.

[0177] 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.

[0178] Each of the multiple elements described above, including the reception unit, generation unit, reading unit, storage unit, and access unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the microphone 238 and control unit 46A of the headset terminal 314, and inputs the child's question via voice recognition. The generation unit is implemented by the identification processing unit 290 of the data processing unit 12, and generates a picture book using image generation AI. The reading unit is implemented by the speaker 240 and control unit 46A of the headset terminal 314, and reads the picture book aloud in the family's voice. The storage unit is implemented by the database 24 of the data processing unit 12, and stores the generated picture book. The access unit is implemented by the communication I / F 44 and control unit 46A of the headset terminal 314, and accesses the questions of other children. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0179] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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).

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.).

[0192] 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.

[0193] 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.

[0194] 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.

[0195] Each of the multiple elements described above, including the reception unit, generation unit, reading unit, storage unit, and access unit, is implemented, for example, by at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the microphone 238 and control unit 46A of the robot 414, and inputs the child's question by voice recognition. The generation unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, and generates a picture book using image generation AI. The reading unit is implemented, for example, by the speaker 240 and control unit 46A of the robot 414, and reads the picture book aloud in the family's voice. The storage unit is implemented, for example, by the database 24 of the data processing unit 12, and stores the generated picture book. The access unit is implemented, for example, by the communication I / F 44 and control unit 46A of the robot 414, and accesses the questions of other children. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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."

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] (Note 1) A reception desk where children's questions are entered using voice recognition, A generation unit that generates a picture book containing answers to questions entered by the reception unit, A reading unit that reads aloud the picture book generated by the generation unit, A storage unit for storing the picture books produced by the generation unit, It includes an access unit that allows access to other children's questions. A system characterized by the following features. (Note 2) The generating unit is It features a customization section that allows you to customize the content of the picture book to suit the child's age and developmental stage. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned reading unit, It features a voice setting section for reading picture books aloud in the voices of family members. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned storage unit is Save the generated picture books as your own personal bookshelf of knowledge. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned access unit is Access picture books that answer other children's questions The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned customization unit is By including children's names and siblings, we can create picture books that are more relatable and approachable. The system described in Appendix 2, characterized by the features described herein. (Note 7) The aforementioned reception unit is The system estimates the child's emotions and adjusts the timing of question input based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is Analyze the child's past question history and select the optimal input method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is When a question is entered, filtering is performed based on the child's current interests. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is The system estimates the child's emotions and determines the priority of the questions to be entered based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When entering questions, the system prioritizes questions that are highly relevant, taking into account the child's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When you enter a question, the system analyzes your child's social media activity and enters relevant questions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The generating unit is The system estimates the child's emotions and adjusts the way the picture book is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The generating unit is When generating a picture book, adjust the level of detail in the book based on the importance of the question. The system described in Appendix 1, characterized by the features described herein. (Note 15) The generating unit is When generating picture books, different generation algorithms are applied depending on the category of the question. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is The system estimates the child's emotions and adjusts the length of the picture book based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is When creating picture books, the priority of the books is determined based on when the questions were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is When generating picture books, the order of the picture books is adjusted based on the relevance of the questions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned reading unit, The system estimates the child's emotions and adjusts the reading style based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned reading unit, When reading aloud, adjust the reading speed and tone based on the content of the picture book. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned reading unit, When reading aloud, the system selects the most suitable reading method by referring to the child's past responses. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned reading unit, The system estimates the child's emotions and adjusts the reading order based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned reading unit, When reading aloud, the system selects the optimal reading method by taking into account the child's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned reading unit, When reading aloud, analyze the child's social media activity and suggest methods for reading aloud. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned storage unit is The system estimates the child's emotions and determines the priority of picture books to save based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned storage unit is When saving, adjust the save format based on the content of the picture book. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned storage unit is When saving, refer to the child's past saving history to select the optimal saving method. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned storage unit is It estimates a child's emotions and adjusts how the picture book is displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned storage unit is When storing the photos, the optimal storage method should be selected considering the child's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned storage unit is When saving data, we analyze children's social media activity and suggest methods for saving it. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned access unit is The system estimates the child's emotions and determines the priority of picture books to access based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned access unit is When accessing the site, the access method will be adjusted based on the questions of other children. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned access unit is When accessing the system, the system will refer to the child's past access history to select the most suitable access method. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned access unit is It estimates a child's emotions and adjusts how picture books are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned access unit is When accessing the system, the system will select the optimal access method by considering the child's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned access unit is When accessing the system, we analyze the child's social media activity and suggest ways to access it. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned customization unit is It estimates the child's emotions and adjusts how the picture book is customized based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 38) The aforementioned customization unit is During customization, the system will refer to the child's past question history to select the most suitable customization method. The system described in Appendix 2, characterized by the features described herein. (Note 39) The aforementioned customization unit is When customizing, the customization is based on the child's current interests and concerns. The system described in Appendix 2, characterized by the features described herein. (Note 40) The aforementioned customization unit is It estimates the child's emotions and prioritizes picture books that are customized based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 41) The aforementioned customization unit is When customizing, the optimal customization method is selected considering the child's geographical location. The system described in Appendix 2, characterized by the features described herein. (Note 42) The aforementioned customization unit is During customization, we analyze your child's social media activity and suggest ways to customize the system. The system described in Appendix 2, characterized by the features described herein. (Note 43) The aforementioned audio setting unit is It estimates the child's emotions and adjusts the voice settings based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 44) The aforementioned audio setting unit is When setting up voice settings, the system selects the optimal voice settings based on the characteristics of each family member's voice. The system described in Appendix 3, characterized by the features described herein. (Note 45) The aforementioned audio setting unit is When setting up the audio, the system will refer to the child's past responses to select the optimal audio setting method. The system described in Appendix 3, characterized by the features described herein. (Note 46) The aforementioned audio setting unit is It estimates the child's emotions and determines the priority of voice settings based on the estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 47) The aforementioned audio setting unit is When setting up voice settings, the system will select the optimal voice setting method by considering the child's geographical location. The system described in Appendix 3, characterized by the features described herein. (Note 48) The aforementioned audio setting unit is When setting up voice settings, the system analyzes the child's social media activity and suggests methods for adjusting voice settings. The system described in Appendix 3, characterized by the features described herein. [Explanation of symbols]

[0215] 10, 210, 310, 410 data processing systems 12 data processing device 14 smart device 214 smart glasses 314 headset-type terminal 414 robot

Claims

1. A reception desk where children's questions are entered using voice recognition, A generation unit that generates a picture book containing answers to questions entered by the reception unit, A reading unit that reads aloud the picture book generated by the generation unit, A storage unit for storing the picture books produced by the generation unit, It includes an access unit that allows access to other children's questions. A system characterized by the following features.

2. The generating unit is It features a customization section that allows you to customize the content of the picture book to suit the child's age and developmental stage. The system according to feature 1.

3. The aforementioned reading unit, It features a voice setting section for reading picture books aloud in the voices of family members. The system according to feature 1.

4. The aforementioned storage unit is Save the generated picture books as your own personal bookshelf of knowledge. The system according to feature 1.

5. The aforementioned access unit is Access picture books that answer other children's questions The system according to feature 1.

6. The aforementioned customization unit is By including children's names and siblings, we can create picture books that are more relatable and approachable. The system according to feature 2.

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

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

9. The aforementioned reception unit is When a question is entered, filtering is performed based on the child's current interests. The system according to feature 1.

Images