System

Abstract

An object of the system according to the embodiment is to modify the expression to match the level of the child and generate content that attracts the interest of the child.SOLUTION: A system includes an expression correction part and a content generation part. The expression modifying unit modifies the provided content to an expression that matches the level of the child. The content generator generates content that attracts the infant's interest based on the content corrected by the expression corrector.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem that the content provided is not adjusted to suit the level of young children, and there is no mechanism to attract young children's interest.

[0005] The system according to the embodiment aims to generate content that attracts the interest of young children by modifying the expressions to suit the level of young children. [Means for solving the problem]

[0006] The system according to the embodiment includes an expression correction unit and a content generation unit. The expression correction unit corrects the provided content to expressions suited to the level of young children. The content generation unit generates content that attracts the interest of young children based on the content corrected by the expression correction unit. [Effects of the Invention]

[0007] The system according to the embodiment can modify the expressions to suit the level of young children and generate content that will attract the interest of young children. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The content generation platform according to the embodiment of the present invention is a system that modifies provided content to expressions suited to the level of young children and generates content that attracts the interest of young children, thereby enabling the content generation platform to improve the quality of content for young children.

[0029] A content generation platform according to an embodiment includes an expression correction unit and a content generation unit. The expression correction unit corrects provided content to expressions appropriate for the level of young children. For example, the expression correction unit replaces difficult words and technical terms with simpler words. The expression correction unit also converts complex sentences into short, easy-to-understand sentences. The expression correction unit also corrects expressions to be appropriate based on the reader's age and level of understanding. For example, the expression correction unit replaces the content of a picture book for young children with simpler words. The content generation unit generates content that attracts the interest of young children based on the content corrected by the expression correction unit. For example, the content generation unit generates stories featuring animals and characters. The content generation unit also generates educational materials including colorful illustrations. The content generation unit also generates content customized based on the interests of young children. For example, the content generation unit generates stories based on specific characters or themes. This enables the content generation platform according to an embodiment to improve the quality of content for young children.

[0030] The expression correction unit can analyze the reader's past learning history and revise the expressions to be individually optimized. For example, using LLM, the expression correction unit analyzes the reader's past learning history and replaces difficult words and phrases with simpler expressions. For example, it avoids words that were difficult to understand in the past and uses easier-to-understand words. The expression correction unit also evaluates the reader's level of understanding of a specific theme or topic based on the reader's learning history and revise the expressions accordingly. For example, for a science topic, it starts with the basic concepts. The expression correction unit also analyzes the reader's past test results and feedback to identify parts that were difficult to understand and focuses on revising those parts to make them simpler. For example, for a math problem, it adds step-by-step explanations. This allows the expression to be revised to be easier to understand based on the reader's past learning history.

[0031] The expression correction unit can monitor the reader's real-time reactions and dynamically correct expressions according to the level of understanding. The expression correction unit can, for example, use LLM to monitor the reader's real-time reactions and instantly correct parts that are determined to be difficult to understand into simpler expressions. For example, it can detect parts where the reader pauses for a long time and re-explain those parts. The expression correction unit can also analyze the reader's facial expressions and vocal responses and add simpler words or examples if it determines that the level of understanding is low. For example, if the reader shows a confused expression, it can provide additional explanation. The expression correction unit can also build a system that dynamically corrects expressions to make them easier for the reader to understand based on real-time reaction data. For example, it can identify parts where readers ask the most questions and change those parts to simpler expressions. This makes it possible to dynamically correct expressions to make them easier to understand based on the reader's real-time reactions.

[0032] The expression correction unit can automatically correct expressions to suit different cultural spheres and languages. The expression correction unit uses, for example, LLM to build a system that automatically corrects expressions to suit different cultural spheres and languages. For example, English content is translated into Japanese or French and corrected to suit cultural differences. The expression correction unit also automatically corrects expressions to suit readers in different cultural spheres, taking into account their cultural backgrounds and customs. For example, it uses the example of Thanksgiving for American readers and the example of New Year's for Japanese readers. The expression correction unit also takes language-specific nuances and expressions into account when automatically correcting expressions to suit different languages. For example, when translating an English joke into Japanese, it replaces it with a Japanese joke that has the same meaning. This allows automatic correction to suit different cultural spheres and languages.

[0033] The expression correction unit can have a function to provide related additional information based on the reader's interests and concerns. The expression correction unit uses, for example, LLM to build a system that provides related additional information based on the reader's interests and concerns. For example, if the reader is interested in dinosaurs, additional information about dinosaurs is provided. The expression correction unit also analyzes the reader's past browsing history and search history to provide related additional information. For example, if the reader reads many articles about space, additional information about space is provided. The expression correction unit also adds a function to provide related videos and images based on the reader's interests and concerns. For example, if the reader is interested in animals, videos and images of animals are provided. This makes it possible to provide related additional information based on the reader's interests and concerns.

[0034] The content generation unit can analyze the past browsing history of a young child and generate individually optimized content. For example, the content generation unit analyzes the past browsing history of a young child and identifies themes and characters that are likely to interest the young child. For example, for a young child who is interested in animals or vehicles, it generates stories related to those. The content generation unit also builds a system that automatically generates content related to specific themes and characters based on the young child's browsing history. For example, for a young child who likes dinosaurs, it generates stories featuring dinosaurs. The content generation unit also analyzes the past browsing history of a young child and generates content that is likely to interest the young child. For example, it generates educational materials that include colorful illustrations and simple quizzes. In this way, individually optimized content can be generated based on the past browsing history of a young child.

[0035] The content generation unit can monitor the real-time reactions of the infant and dynamically generate content to maintain the infant's interest. The content generation unit, for example, builds a system that monitors the real-time reactions of the infant and dynamically generates content to maintain the infant's interest. For example, it frequently uses scenes in which the infant smiles. The content generation unit also analyzes the infant's facial expressions and vocal reactions and dynamically generates content to maintain the infant's interest. For example, it frequently uses characters that the infant shows interest in. The content generation unit also develops a system that dynamically generates content based on real-time reaction data to maintain the infant's interest. For example, it frequently uses scenes in which the infant is having fun. In this way, content can be dynamically generated based on the infant's real-time reactions to maintain the infant's interest.

[0036] The content generation unit can generate new content by combining different themes and characters. The content generation unit, for example, builds a system that generates new content by combining different themes and characters. For example, it generates a story that combines animals and space. The content generation unit also generates new stories and teaching materials by combining different characters. For example, it generates a story in which dinosaurs and robots appear together. The content generation unit also generates new content by combining different themes. For example, it generates a story with a theme of sea creatures and adventure. This makes it possible to generate new content by combining different themes and characters.

[0037] The content generation unit may have a function to suggest related additional content based on the interests of the young child. The content generation unit, for example, builds a system that suggests related additional content based on the interests of the young child. For example, for a young child who is interested in animals, additional stories and videos related to animals are suggested. The content generation unit also analyzes the young child's past browsing history and search history to suggest related additional content. For example, for a young child who is interested in dinosaurs, additional educational materials related to dinosaurs are suggested. The content generation unit also adds a function to suggest related additional content based on the interests of the young child. For example, for a young child who is interested in space, additional quizzes and games related to space are suggested. In this way, related additional content can be suggested based on the interests of the young child.

[0038] The content generation unit can generate customized teaching materials tailored to specific learning goals. The content generation unit uses, for example, LLM to build a system that generates customized teaching materials tailored to specific learning goals. For example, for young children whose goal is to learn the alphabet, the content generation unit generates stories and quizzes using the alphabet. The content generation unit also adjusts the content and difficulty of the teaching materials according to the learning goal. For example, in teaching materials for learning number concepts, the content generation unit starts with easy number problems and gradually increases the difficulty. The content generation unit also takes into account the interests and concerns of young children when generating customized teaching materials tailored to specific learning goals. For example, for young children who like animals, the content generation unit provides animal-themed math problems. In this way, customized teaching materials tailored to specific learning goals can be generated.

[0039] The content generation unit can continuously improve customized content based on reader feedback. For example, the content generation unit collects reader feedback and builds a system that continuously improves customized content based on that data. For example, it corrects parts that readers find difficult to understand. The content generation unit also adjusts the content and expression of the content based on the feedback. For example, it makes greater use of topics that readers find interesting and reduces topics that readers do not find interesting. The content generation unit also develops a system that analyzes reader feedback in real time and immediately improves content. For example, it identifies parts that readers find confusing and changes those parts to simpler expressions. This allows customized content to be continuously improved based on reader feedback.

[0040] The content generation unit can be equipped with a function for customizing to accommodate different learning styles. For example, the content generation unit uses LLM to build a system that customizes to accommodate different learning styles. For example, it uses a lot of diagrams and illustrations for visual learners and adds audio commentary for auditory learners. The content generation unit also analyzes the reader's learning style and customizes accordingly. For example, it provides learning materials that make heavy use of animations to readers who prefer dynamic animations. Furthermore, when customizing to accommodate different learning styles, the content generation unit makes adjustments based on reader feedback. For example, if a reader prefers visual explanations, it uses a lot of diagrams and graphs. This makes it possible to customize to accommodate different learning styles.

[0041] The content generation unit may have a function to suggest related additional customizations based on the reader's interests and concerns. The content generation unit, for example, builds a system that suggests related additional customizations based on the reader's interests and concerns. For example, for a reader who is interested in animals, additional stories and quizzes related to animals are suggested. The content generation unit also analyzes the reader's past browsing history and search history to suggest related additional customizations. For example, for a reader who is interested in dinosaurs, additional educational materials related to dinosaurs are suggested. The content generation unit also adds a function to suggest related additional customizations based on the reader's interests and concerns. For example, for a reader who is interested in space, additional quizzes and games related to space are suggested. This makes it possible to suggest related additional customizations based on the reader's interests and concerns.

[0042] The content generation unit can dynamically generate interactive elements according to the reader's real-time reactions. The content generation unit, for example, uses LLM to build a system that dynamically generates interactive elements according to the reader's real-time reactions. For example, it generates quizzes related to topics that the reader has shown interest in. The content generation unit also analyzes the reader's facial expressions and vocal reactions and dynamically generates interactive elements to maintain interest. For example, it makes frequent use of scenes in which the reader is smiling. The content generation unit also develops a system that dynamically generates interactive elements based on real-time reaction data to maintain interest. For example, it makes frequent use of scenes in which the reader is having fun. This makes it possible to dynamically generate interactive elements according to the reader's real-time reactions.

[0043] The content generation unit can generate new content by combining different interactive elements. The content generation unit, for example, builds a system for generating new content by combining different interactive elements. For example, it generates learning materials that combine quizzes and games. The content generation unit also generates new stories and learning materials by combining different interactive elements. For example, it generates content that combines an interactive story and a quiz. The content generation unit also generates new content by combining different interactive elements. For example, it generates learning materials that combine animation and an interactive quiz. This makes it possible to generate new content by combining different interactive elements.

[0044] The content generation unit may have a function to suggest related additional interactive elements based on the reader's interests and concerns. The content generation unit, for example, builds a system that suggests related additional interactive elements based on the reader's interests and concerns. For example, for a reader who is interested in animals, additional quizzes and games related to animals are suggested. The content generation unit also analyzes the reader's past browsing history and search history to suggest related additional interactive elements. For example, for a reader who is interested in dinosaurs, additional quizzes and games related to dinosaurs are suggested. The content generation unit also adds a function to suggest related additional interactive elements based on the reader's interests and concerns. For example, for a reader who is interested in space, additional quizzes and games related to space are suggested. In this way, related additional interactive elements can be suggested based on the reader's interests and concerns.

[0045] The content generation department can analyze reader feedback in real time and dynamically improve content. For example, using LLM, the content generation department can analyze reader feedback in real time and build a system that dynamically improves content based on that data. For example, it can instantly correct parts that readers find difficult to understand. The content generation department can also adjust the content and expression of the content based on the feedback. For example, it can make more use of topics that readers find interesting and reduce topics that they do not find interesting. The content generation department can also develop a system that analyzes reader feedback in real time and instantly improves content. For example, it can identify parts that readers find confusing and change those parts to simpler expressions. This allows the content to be dynamically improved by analyzing reader feedback in real time.

[0046] The content generation unit can analyze readers' past evaluation histories and identify optimal areas for improvement. The content generation unit, for example, builds a system that analyzes readers' past evaluation histories and identifies optimal areas for improvement. For example, it identifies parts that readers have rated low and improves those parts. The content generation unit also adjusts the content and expression of the content based on the evaluation history. For example, it makes frequent use of themes that readers have rated high and reduces themes that readers have rated low. The content generation unit also analyzes readers' past evaluation histories and identifies optimal areas for improvement. For example, it identifies parts that readers find difficult to understand and changes those parts to simpler expressions. In this way, it is possible to identify optimal areas for improvement based on readers' past evaluation history.

[0047] The content generation unit can introduce a new evaluation method that combines different evaluation criteria. The content generation unit, for example, builds a system that introduces a new evaluation method that combines different evaluation criteria. For example, it comprehensively evaluates the reader's level of understanding, interest, and emotional response. The content generation unit also adjusts the content and expression of the content based on the different evaluation criteria. For example, it changes parts that readers find difficult to understand to simpler expressions and makes frequent use of themes that are of high interest. When introducing a new evaluation method that combines different evaluation criteria, the content generation unit also makes adjustments based on reader feedback. For example, it identifies parts that readers find difficult to understand and improves those parts. This makes it possible to introduce a new evaluation method that combines different evaluation criteria.

[0048] The content generation unit can be provided with a function to suggest related additional rating items based on the reader's interests and concerns. The content generation unit, for example, builds a system that suggests related additional rating items based on the reader's interests and concerns. For example, for a reader who is interested in animals, it suggests additional rating items related to animals. The content generation unit also analyzes the reader's past browsing history and search history to suggest related additional rating items. For example, for a reader who is interested in dinosaurs, it suggests additional rating items related to dinosaurs. The content generation unit also adds a function to suggest related additional rating items based on the reader's interests and concerns. For example, for a reader who is interested in space, it suggests additional rating items related to space. This makes it possible to suggest related additional rating items based on the reader's interests and concerns.

[0049] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0050] The content generation unit can analyze the child's past learning history and generate individually optimized content. For example, it can generate new stories and teaching materials based on themes and characters that the child has been interested in in the past. It can also provide content to strengthen specific skills and knowledge based on the child's past learning history. It can also analyze the child's past learning history and provide complementary content for areas in which the child is weak. In this way, it is possible to generate individually optimized content based on the child's past learning history.

[0051] The content generation unit can monitor the infant's real-time reactions and dynamically generate content to maintain the infant's interest. For example, the content generation unit can frequently use scenes in which the infant smiles, and if the infant shows a confused expression, it can change to additional explanations or simpler expressions. The content can also be adjusted to maintain the infant's interest by frequently using characters or themes that the infant is interested in. Furthermore, based on the real-time reaction data, it is also possible to dynamically generate content to maintain the infant's interest by frequently using scenes in which the infant is having fun. In this way, content can be dynamically generated to maintain the infant's interest based on the infant's real-time reactions.

[0052] The content generation unit can automatically correct expressions to suit different cultural spheres and languages. For example, English content is translated into Japanese or French and corrected to suit cultural differences. It can also automatically correct expressions to suit readers in different cultural spheres, taking into account their cultural backgrounds and customs. For example, it uses an example of Thanksgiving for American readers and an example of New Year's for Japanese readers. Furthermore, when automatically correcting expressions to suit different languages, it is also possible to take into account language-specific nuances and expressions. This makes it possible to automatically correct expressions to suit different cultural spheres and languages.

[0053] The content generation unit can generate customized teaching materials tailored to specific learning goals. For example, for a young child aiming to learn the alphabet, it can generate stories and quizzes using the alphabet. The content and difficulty of the teaching materials can also be adjusted depending on the learning goal. For example, in teaching materials for learning number concepts, it can start with easy number problems and gradually increase the difficulty. Furthermore, it is also possible to take into account the interests and concerns of young children when generating customized teaching materials tailored to specific learning goals. For example, for a young child who likes animals, it can provide animal-themed math problems. In this way, it is possible to generate customized teaching materials tailored to specific learning goals.

[0054] The content generation unit can be equipped with a function for customizing to accommodate different learning styles. For example, it can use more diagrams and illustrations for visual learners and add audio commentary for auditory learners. It can also analyze the reader's learning style and customize accordingly. For example, it can provide materials that make heavy use of animation to readers who prefer dynamic animations. Furthermore, when customizing to accommodate different learning styles, it can also make adjustments based on reader feedback. For example, if a reader prefers visual explanations, it can use more diagrams and graphs. This makes it possible to customize to accommodate different learning styles.

[0055] The content generation unit may have a function to suggest related additional customizations based on the reader's interests. For example, for a reader who is interested in animals, additional stories or quizzes related to animals may be suggested. The content generation unit may also analyze the reader's past browsing history or search history to suggest related additional customizations. For example, for a reader who is interested in dinosaurs, additional educational materials related to dinosaurs may be suggested. Furthermore, it is also possible to add a function to suggest related additional customizations based on the reader's interests. For example, for a reader who is interested in space, additional quizzes or games related to space may be suggested. In this way, related additional customizations can be suggested based on the reader's interests.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The expression correction unit corrects the provided content to be at the level of a young child. For example, it replaces difficult words and technical terms with simpler ones, and converts complex sentences into short, easy-to-understand sentences. It also corrects the expressions to be appropriate based on the reader's age and level of understanding. For example, it replaces the content of a picture book for young children with simpler words. Step 2: The content generation unit generates content that attracts the interest of young children based on the content modified by the expression modification unit. For example, it generates stories featuring animals and characters, or educational materials with colorful illustrations. It also generates content customized based on the interests of young children. For example, it generates stories based on specific characters or themes.

[0058] (Example 2) The content generation platform according to the embodiment of the present invention is a system that modifies provided content to expressions suited to the level of young children and generates content that attracts the interest of young children, thereby enabling the content generation platform to improve the quality of content for young children.

[0059] A content generation platform according to an embodiment includes an expression correction unit and a content generation unit. The expression correction unit corrects provided content to expressions appropriate for the level of young children. For example, the expression correction unit replaces difficult words and technical terms with simpler words. The expression correction unit also converts complex sentences into short, easy-to-understand sentences. The expression correction unit also corrects expressions to be appropriate based on the reader's age and level of understanding. For example, the expression correction unit replaces the content of a picture book for young children with simpler words. The content generation unit generates content that attracts the interest of young children based on the content corrected by the expression correction unit. For example, the content generation unit generates stories featuring animals and characters. The content generation unit also generates educational materials including colorful illustrations. The content generation unit also generates content customized based on the interests of young children. For example, the content generation unit generates stories based on specific characters or themes. This enables the content generation platform according to an embodiment to improve the quality of content for young children.

[0060] The expression correction unit can analyze the reader's past learning history and revise the expressions to be individually optimized. For example, using LLM, the expression correction unit analyzes the reader's past learning history and replaces difficult words and phrases with simpler expressions. For example, it avoids words that were difficult to understand in the past and uses easier-to-understand words. The expression correction unit also evaluates the reader's level of understanding of a specific theme or topic based on the reader's learning history and revise the expressions accordingly. For example, for a science topic, it starts with the basic concepts. The expression correction unit also analyzes the reader's past test results and feedback to identify parts that were difficult to understand and focuses on revising those parts to make them simpler. For example, for a math problem, it adds step-by-step explanations. This allows the expression to be revised to be easier to understand based on the reader's past learning history.

[0061] The expression correction unit can monitor the reader's real-time reactions and dynamically correct expressions according to the level of understanding. The expression correction unit can, for example, use LLM to monitor the reader's real-time reactions and instantly correct parts that are determined to be difficult to understand into simpler expressions. For example, it can detect parts where the reader pauses for a long time and re-explain those parts. The expression correction unit can also analyze the reader's facial expressions and vocal responses and add simpler words or examples if it determines that the level of understanding is low. For example, if the reader shows a confused expression, it can provide additional explanation. The expression correction unit can also build a system that dynamically corrects expressions to make them easier for the reader to understand based on real-time reaction data. For example, it can identify parts where readers ask the most questions and change those parts to simpler expressions. This makes it possible to dynamically correct expressions to make them easier to understand based on the reader's real-time reactions.

[0062] The expression correction unit can use the emotion estimation function to grasp the reader's emotional state and modify expressions to elicit positive emotions. For example, the expression correction unit uses the emotion estimation function to identify expressions that evoke positive emotions in the reader and frequently uses those expressions. For example, it analyzes parts where the reader smiles and applies similar expressions to other parts. The expression correction unit also monitors the reader's emotional state in real time and, if a negative emotion is detected, modifies the expression to elicit positive emotions. For example, if the reader shows a confused expression, it adds words of encouragement. The expression correction unit also identifies expressions that evoke the most positive emotions in the reader based on the emotion estimation data and builds a system that frequently uses those expressions. For example, it frequently uses expressions that make the reader feel happy and increases their motivation to learn. This makes it possible to modify expressions to elicit positive emotions based on the reader's emotional state.

[0063] The expression correction unit can automatically correct expressions to suit different cultural spheres and languages. The expression correction unit uses, for example, LLM to build a system that automatically corrects expressions to suit different cultural spheres and languages. For example, English content is translated into Japanese or French and corrected to suit cultural differences. The expression correction unit also automatically corrects expressions to suit readers in different cultural spheres, taking into account their cultural backgrounds and customs. For example, it uses the example of Thanksgiving for American readers and the example of New Year's for Japanese readers. The expression correction unit also takes language-specific nuances and expressions into account when automatically correcting expressions to suit different languages. For example, when translating an English joke into Japanese, it replaces it with a Japanese joke that has the same meaning. This allows automatic correction to suit different cultural spheres and languages.

[0064] The expression correction unit can have a function to provide related additional information based on the reader's interests and concerns. The expression correction unit uses, for example, LLM to build a system that provides related additional information based on the reader's interests and concerns. For example, if the reader is interested in dinosaurs, additional information about dinosaurs is provided. The expression correction unit also analyzes the reader's past browsing history and search history to provide related additional information. For example, if the reader reads many articles about space, additional information about space is provided. The expression correction unit also adds a function to provide related videos and images based on the reader's interests and concerns. For example, if the reader is interested in animals, videos and images of animals are provided. This makes it possible to provide related additional information based on the reader's interests and concerns.

[0065] The expression correction unit can use the emotion estimation function to correct expressions to those related to topics that interest the reader most. For example, the expression correction unit uses the emotion estimation function to identify topics that interest the reader most and corrects expressions to those related to the topics. For example, if the reader is interested in animals, the expression correction unit uses many animal-related examples. The expression correction unit also monitors the reader's emotional reactions in real time and dynamically corrects expressions to those related to the topics of interest. For example, it adds information related to topics that make the reader smile. The expression correction unit also builds a system that identifies topics that interest the reader most based on the emotion estimation data and corrects expressions to those related to the topics. For example, it uses many information related to topics that make the reader happy. This makes it possible to correct expressions to those related to the topics that interest the reader most.

[0066] The content generation unit can analyze the past browsing history of a young child and generate individually optimized content. For example, the content generation unit analyzes the past browsing history of a young child and identifies themes and characters that are likely to interest the young child. For example, for a young child who is interested in animals or vehicles, it generates stories related to those. The content generation unit also builds a system that automatically generates content related to specific themes and characters based on the young child's browsing history. For example, for a young child who likes dinosaurs, it generates stories featuring dinosaurs. The content generation unit also analyzes the past browsing history of a young child and generates content that is likely to interest the young child. For example, it generates educational materials that include colorful illustrations and simple quizzes. In this way, individually optimized content can be generated based on the past browsing history of a young child.

[0067] The content generation unit can monitor the real-time reactions of the infant and dynamically generate content to maintain the infant's interest. The content generation unit, for example, builds a system that monitors the real-time reactions of the infant and dynamically generates content to maintain the infant's interest. For example, it frequently uses scenes in which the infant smiles. The content generation unit also analyzes the infant's facial expressions and vocal reactions and dynamically generates content to maintain the infant's interest. For example, it frequently uses characters that the infant shows interest in. The content generation unit also develops a system that dynamically generates content based on real-time reaction data to maintain the infant's interest. For example, it frequently uses scenes in which the infant is having fun. In this way, content can be dynamically generated based on the infant's real-time reactions to maintain the infant's interest.

[0068] The content generation unit can generate new content by combining different themes and characters. The content generation unit, for example, builds a system that generates new content by combining different themes and characters. For example, it generates a story that combines animals and space. The content generation unit also generates new stories and teaching materials by combining different characters. For example, it generates a story in which dinosaurs and robots appear together. The content generation unit also generates new content by combining different themes. For example, it generates a story with a theme of sea creatures and adventure. This makes it possible to generate new content by combining different themes and characters.

[0069] The content generation unit may have a function to suggest related additional content based on the interests of the young child. The content generation unit, for example, builds a system that suggests related additional content based on the interests of the young child. For example, for a young child who is interested in animals, additional stories and videos related to animals are suggested. The content generation unit also analyzes the young child's past browsing history and search history to suggest related additional content. For example, for a young child who is interested in dinosaurs, additional educational materials related to dinosaurs are suggested. The content generation unit also adds a function to suggest related additional content based on the interests of the young child. For example, for a young child who is interested in space, additional quizzes and games related to space are suggested. In this way, related additional content can be suggested based on the interests of the young child.

[0070] The content generation unit can use the emotion estimation function to generate content related to themes that infants are most interested in. For example, the content generation unit uses the emotion estimation function to identify themes that infants are most interested in and generate content related to those themes. For example, themes that make infants smile are frequently used. The content generation unit also monitors the infant's emotional reactions in real time and generates content related to themes that interest them. For example, themes that infants enjoy are frequently used. The content generation unit also builds a system that identifies themes that infants are most interested in based on the emotion estimation data and generates content related to those themes. For example, themes that infants find joyful are frequently used. In this way, content related to themes that infants are most interested in can be generated.

[0071] The content generation unit can generate customized teaching materials tailored to specific learning goals. The content generation unit uses, for example, LLM to build a system that generates customized teaching materials tailored to specific learning goals. For example, for young children whose goal is to learn the alphabet, the content generation unit generates stories and quizzes using the alphabet. The content generation unit also adjusts the content and difficulty of the teaching materials according to the learning goal. For example, in teaching materials for learning number concepts, the content generation unit starts with easy number problems and gradually increases the difficulty. The content generation unit also takes into account the interests and concerns of young children when generating customized teaching materials tailored to specific learning goals. For example, for young children who like animals, the content generation unit provides animal-themed math problems. In this way, customized teaching materials tailored to specific learning goals can be generated.

[0072] The content generation unit can continuously improve customized content based on reader feedback. For example, the content generation unit collects reader feedback and builds a system that continuously improves customized content based on that data. For example, it corrects parts that readers find difficult to understand. The content generation unit also adjusts the content and expression of the content based on the feedback. For example, it makes greater use of topics that readers find interesting and reduces topics that readers do not find interesting. The content generation unit also develops a system that analyzes reader feedback in real time and immediately improves content. For example, it identifies parts that readers find confusing and changes those parts to simpler expressions. This allows customized content to be continuously improved based on reader feedback.

[0073] The content generation unit can use the emotion estimation function to customize content according to the reader's emotional state. For example, the content generation unit uses the emotion estimation function to monitor the reader's emotional state in real time and provide customized content based on that data. For example, if the reader is confused, words of encouragement can be added. The content generation unit also dynamically adjusts the content and expression of the content according to the reader's emotional state. For example, if the reader is enjoying themselves, that theme can be used frequently. The content generation unit also builds a system that customizes content according to the reader's emotional state based on the emotion estimation data. For example, expressions that evoke positive emotions in the reader can be used frequently to increase motivation to learn. This makes it possible to customize content according to the reader's emotional state.

[0074] The content generation unit can be equipped with a function for customizing to accommodate different learning styles. For example, the content generation unit uses LLM to build a system that customizes to accommodate different learning styles. For example, it uses a lot of diagrams and illustrations for visual learners and adds audio commentary for auditory learners. The content generation unit also analyzes the reader's learning style and customizes accordingly. For example, it provides learning materials that make heavy use of animations to readers who prefer dynamic animations. Furthermore, when customizing to accommodate different learning styles, the content generation unit makes adjustments based on reader feedback. For example, if a reader prefers visual explanations, it uses a lot of diagrams and graphs. This makes it possible to customize to accommodate different learning styles.

[0075] The content generation unit may have a function to suggest related additional customizations based on the reader's interests and concerns. The content generation unit, for example, builds a system that suggests related additional customizations based on the reader's interests and concerns. For example, for a reader who is interested in animals, additional stories and quizzes related to animals are suggested. The content generation unit also analyzes the reader's past browsing history and search history to suggest related additional customizations. For example, for a reader who is interested in dinosaurs, additional educational materials related to dinosaurs are suggested. The content generation unit also adds a function to suggest related additional customizations based on the reader's interests and concerns. For example, for a reader who is interested in space, additional quizzes and games related to space are suggested. This makes it possible to suggest related additional customizations based on the reader's interests and concerns.

[0076] The content generation unit can use the emotion estimation function to suggest customizations that will interest the reader most. The content generation unit, for example, uses the emotion estimation function to build a system that suggests customizations that will interest the reader most. For example, it may frequently use themes that make the reader smile. The content generation unit also monitors the reader's emotional reactions in real time to suggest customizations that will interest them. For example, it may frequently use themes that the reader enjoys. The content generation unit also develops a system that suggests customizations that will interest the reader most based on the emotion estimation data. For example, it may frequently use themes that make the reader feel joy. This makes it possible to suggest customizations that will interest the reader most.

[0077] The content generation unit can dynamically generate interactive elements according to the reader's real-time reactions. The content generation unit, for example, uses LLM to build a system that dynamically generates interactive elements according to the reader's real-time reactions. For example, it generates quizzes related to topics that the reader has shown interest in. The content generation unit also analyzes the reader's facial expressions and vocal reactions and dynamically generates interactive elements to maintain interest. For example, it makes frequent use of scenes in which the reader is smiling. The content generation unit also develops a system that dynamically generates interactive elements based on real-time reaction data to maintain interest. For example, it makes frequent use of scenes in which the reader is having fun. This makes it possible to dynamically generate interactive elements according to the reader's real-time reactions.

[0078] The content generation unit can use the emotion estimation function to add interactive elements according to the reader's emotional state. For example, the content generation unit uses the emotion estimation function to monitor the reader's emotional state in real time and add interactive elements based on that data. For example, if the reader is confused, words of encouragement are added. The content generation unit also dynamically adjusts the interactive elements according to the reader's emotional state. For example, if the reader is enjoying themselves, that theme is used frequently. The content generation unit also builds a system that adds interactive elements according to the reader's emotional state based on the emotion estimation data. For example, expressions that evoke positive emotions in the reader are used frequently to increase motivation to learn. This makes it possible to add interactive elements according to the reader's emotional state.

[0079] The content generation unit can generate new content by combining different interactive elements. The content generation unit, for example, builds a system for generating new content by combining different interactive elements. For example, it generates learning materials that combine quizzes and games. The content generation unit also generates new stories and learning materials by combining different interactive elements. For example, it generates content that combines an interactive story and a quiz. The content generation unit also generates new content by combining different interactive elements. For example, it generates learning materials that combine animation and an interactive quiz. This makes it possible to generate new content by combining different interactive elements.

[0080] The content generation unit may have a function to suggest related additional interactive elements based on the reader's interests and concerns. The content generation unit, for example, builds a system that suggests related additional interactive elements based on the reader's interests and concerns. For example, for a reader who is interested in animals, additional quizzes and games related to animals are suggested. The content generation unit also analyzes the reader's past browsing history and search history to suggest related additional interactive elements. For example, for a reader who is interested in dinosaurs, additional quizzes and games related to dinosaurs are suggested. The content generation unit also adds a function to suggest related additional interactive elements based on the reader's interests and concerns. For example, for a reader who is interested in space, additional quizzes and games related to space are suggested. In this way, related additional interactive elements can be suggested based on the reader's interests and concerns.

[0081] The content generation unit can use the emotion estimation function to suggest interactive elements that readers will be most interested in. For example, the content generation unit uses the emotion estimation function to build a system that suggests interactive elements that readers will be most interested in. For example, it frequently uses themes that make readers smile. The content generation unit also monitors readers' emotional reactions in real time to suggest interactive elements that readers will be interested in. For example, it frequently uses themes that readers enjoy. The content generation unit also develops a system that suggests interactive elements that readers will be most interested in based on the emotion estimation data. For example, it frequently uses themes that readers will feel joy. This makes it possible to suggest interactive elements that readers will be most interested in.

[0082] The content generation department can analyze reader feedback in real time and dynamically improve content. For example, using LLM, the content generation department can analyze reader feedback in real time and build a system that dynamically improves content based on that data. For example, it can instantly correct parts that readers find difficult to understand. The content generation department can also adjust the content and expression of the content based on the feedback. For example, it can make more use of topics that readers find interesting and reduce topics that they do not find interesting. The content generation department can also develop a system that analyzes reader feedback in real time and instantly improves content. For example, it can identify parts that readers find confusing and change those parts to simpler expressions. This allows the content to be dynamically improved by analyzing reader feedback in real time.

[0083] The content generation unit can analyze readers' past evaluation histories and identify optimal areas for improvement. The content generation unit, for example, builds a system that analyzes readers' past evaluation histories and identifies optimal areas for improvement. For example, it identifies parts that readers have rated low and improves those parts. The content generation unit also adjusts the content and expression of the content based on the evaluation history. For example, it makes frequent use of themes that readers have rated high and reduces themes that readers have rated low. The content generation unit also analyzes readers' past evaluation histories and identifies optimal areas for improvement. For example, it identifies parts that readers find difficult to understand and changes those parts to simpler expressions. In this way, it is possible to identify optimal areas for improvement based on readers' past evaluation history.

[0084] The content generation unit can use the emotion estimation function to make improvements based on the reader's emotional state. For example, the content generation unit uses the emotion estimation function to monitor the reader's emotional state in real time and builds a system to improve content based on that data. For example, if the reader is confused, words of encouragement are added. The content generation unit also dynamically adjusts the content and expressions of the content according to the reader's emotional state. For example, if the reader is enjoying something, that theme is used frequently. The content generation unit also builds a system to make improvements based on the reader's emotional state based on the emotion estimation data. For example, expressions that evoke positive emotions in the reader are used frequently to increase motivation to learn. This makes it possible to make improvements based on the reader's emotional state.

[0085] The content generation unit can introduce a new evaluation method that combines different evaluation criteria. The content generation unit, for example, builds a system that introduces a new evaluation method that combines different evaluation criteria. For example, it comprehensively evaluates the reader's level of understanding, interest, and emotional response. The content generation unit also adjusts the content and expression of the content based on the different evaluation criteria. For example, it changes parts that readers find difficult to understand to simpler expressions and makes frequent use of themes that are of high interest. When introducing a new evaluation method that combines different evaluation criteria, the content generation unit also makes adjustments based on reader feedback. For example, it identifies parts that readers find difficult to understand and improves those parts. This makes it possible to introduce a new evaluation method that combines different evaluation criteria.

[0086] The content generation unit can be provided with a function to suggest related additional rating items based on the reader's interests and concerns. The content generation unit, for example, builds a system that suggests related additional rating items based on the reader's interests and concerns. For example, for a reader who is interested in animals, it suggests additional rating items related to animals. The content generation unit also analyzes the reader's past browsing history and search history to suggest related additional rating items. For example, for a reader who is interested in dinosaurs, it suggests additional rating items related to dinosaurs. The content generation unit also adds a function to suggest related additional rating items based on the reader's interests and concerns. For example, for a reader who is interested in space, it suggests additional rating items related to space. This makes it possible to suggest related additional rating items based on the reader's interests and concerns.

[0087] The content generation unit can use the emotion estimation function to suggest evaluation items that readers are most interested in. For example, the content generation unit uses the emotion estimation function to build a system that suggests evaluation items that readers are most interested in. For example, it frequently uses themes that make readers smile. The content generation unit also monitors readers' emotional reactions in real time to suggest evaluation items that readers are interested in. For example, it frequently uses themes that readers enjoy. The content generation unit also develops a system that suggests evaluation items that readers are most interested in based on the emotion estimation data. For example, it frequently uses themes that readers feel joy. This makes it possible to suggest evaluation items that readers are most interested in.

[0088] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0089] The content generation unit can estimate the emotional state of the infant and dynamically adjust the content based on the estimated emotion. For example, if the infant is having fun, that theme can be used frequently, and if the infant is confused, simpler expressions or additional explanations can be provided. Also, if the infant is excited, activities or games can be added to maintain the excitement. Furthermore, if the infant is tired, content that helps the infant to relax can be provided. In this way, customized content can be provided according to the infant's emotional state.

[0090] The content generation unit can analyze the child's past learning history and generate individually optimized content. For example, it can generate new stories and teaching materials based on themes and characters that the child has been interested in in the past. It can also provide content to strengthen specific skills and knowledge based on the child's past learning history. It can also analyze the child's past learning history and provide complementary content for areas in which the child is weak. In this way, it is possible to generate individually optimized content based on the child's past learning history.

[0091] The content generation unit can monitor the infant's real-time reactions and dynamically generate content to maintain the infant's interest. For example, the content generation unit can frequently use scenes in which the infant smiles, and if the infant shows a confused expression, it can change to additional explanations or simpler expressions. The content can also be adjusted to maintain the infant's interest by frequently using characters or themes that the infant is interested in. Furthermore, based on the real-time reaction data, it is also possible to dynamically generate content to maintain the infant's interest by frequently using scenes in which the infant is having fun. In this way, content can be dynamically generated to maintain the infant's interest based on the infant's real-time reactions.

[0092] The content generation unit can automatically correct expressions to suit different cultural spheres and languages. For example, English content is translated into Japanese or French and corrected to suit cultural differences. It can also automatically correct expressions to suit readers in different cultural spheres, taking into account their cultural backgrounds and customs. For example, it uses an example of Thanksgiving for American readers and an example of New Year's for Japanese readers. Furthermore, when automatically correcting expressions to suit different languages, it is also possible to take into account language-specific nuances and expressions. This makes it possible to automatically correct expressions to suit different cultural spheres and languages.

[0093] The content generation unit can use the emotion estimation function to generate content related to themes that interest young children most. For example, it can frequently use themes that make young children smile, and if they appear confused, it can provide simpler expressions or additional explanations. Also, if the young child is excited, it can add activities or games to keep them excited. Furthermore, if the young child is tired, it can provide content that helps them relax. In this way, it is possible to generate content related to themes that interest young children most.

[0094] The content generation unit can generate customized teaching materials tailored to specific learning goals. For example, for a young child aiming to learn the alphabet, it can generate stories and quizzes using the alphabet. The content and difficulty of the teaching materials can also be adjusted depending on the learning goal. For example, in teaching materials for learning number concepts, it can start with easy number problems and gradually increase the difficulty. Furthermore, it is also possible to take into account the interests and concerns of young children when generating customized teaching materials tailored to specific learning goals. For example, for a young child who likes animals, it can provide animal-themed math problems. In this way, it is possible to generate customized teaching materials tailored to specific learning goals.

[0095] The content generation unit can use the emotion estimation function to customize content according to the reader's emotional state. For example, if the reader is confused, it can add words of encouragement, and if the reader is enjoying themselves, it can frequently use that theme. It can also monitor the reader's emotional state in real time and provide customized content based on that data. Furthermore, it can use expressions that evoke positive emotions in the reader based on emotion estimation data to increase their motivation to learn. This allows for customization according to the reader's emotional state.

[0096] The content generation unit can be equipped with a function for customizing to accommodate different learning styles. For example, it can use more diagrams and illustrations for visual learners and add audio commentary for auditory learners. It can also analyze the reader's learning style and customize accordingly. For example, it can provide materials that make heavy use of animation to readers who prefer dynamic animations. Furthermore, when customizing to accommodate different learning styles, it can also make adjustments based on reader feedback. For example, if a reader prefers visual explanations, it can use more diagrams and graphs. This makes it possible to customize to accommodate different learning styles.

[0097] The content generation unit may have a function to suggest related additional customizations based on the reader's interests. For example, for a reader who is interested in animals, additional stories or quizzes related to animals may be suggested. The content generation unit may also analyze the reader's past browsing history or search history to suggest related additional customizations. For example, for a reader who is interested in dinosaurs, additional educational materials related to dinosaurs may be suggested. Furthermore, it is also possible to add a function to suggest related additional customizations based on the reader's interests. For example, for a reader who is interested in space, additional quizzes or games related to space may be suggested. In this way, related additional customizations can be suggested based on the reader's interests.

[0098] The content generation unit can use the emotion estimation function to suggest customizations that will be of most interest to the reader. For example, it can frequently use themes that make the reader smile, and if the reader is confused, it can provide simpler expressions or additional explanations. It can also monitor the reader's emotional reactions in real time to suggest customizations that will be of interest to the reader. Furthermore, it is possible to develop a system that suggests customizations that will be of most interest to the reader based on emotion estimation data. For example, it can frequently use themes that make the reader feel happy. This makes it possible to suggest customizations that will be of most interest to the reader.

[0099] The processing flow of the second embodiment will be briefly explained below.

[0100] Step 1: The expression correction unit corrects the provided content to be at the level of a young child. For example, it replaces difficult words and technical terms with simpler ones, and converts complex sentences into short, easy-to-understand sentences. It also corrects the expressions to be appropriate based on the reader's age and level of understanding. For example, it replaces the content of a picture book for young children with simpler words. Step 2: The content generation unit generates content that attracts the interest of young children based on the content modified by the expression modification unit. For example, it generates stories featuring animals and characters, or educational materials with colorful illustrations. It also generates content customized based on the interests of young children. For example, it generates stories based on specific characters or themes.

[0101] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0102] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0103] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0104] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0105] 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.

[0106] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0107] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0108] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0109] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0110] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0111] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0112] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0113] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0114] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0115] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0116] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0117] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0118] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0119] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0120] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0121] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0122] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0123] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0124] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0125] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0126] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0127] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0128] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0129] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0130] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0131] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0132] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0133] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0134] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0135] 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.

[0136] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0137] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0138] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0139] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0140] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0141] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0142] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0143] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0144] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0145] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0146] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0147] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0148] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0149] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0150] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0151] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0152] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0153] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0154] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0155] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0156] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0157] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0158] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0159] 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.

[0160] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0161] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0162] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0163] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0164] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0165] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0166] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0167] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0168] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an expression correction unit that corrects the provided content to expressions suited to the level of young children; a content generation unit that generates content that attracts the interest of young children based on the content corrected by the expression correction unit. A system characterized by:

2. The expression correction unit Analyzes the reader's past learning history and modifies the content to suit individual needs 2. The system of claim 1.

3. The expression correction unit Monitor real-time reader responses and dynamically adjust content based on comprehension 2. The system of claim 1.

4. The expression correction unit Understand the reader's emotional state and modify the content to elicit positive emotions 2. The system of claim 1.

5. The expression correction unit Automatically correct expressions to suit different cultures and languages 2. The system of claim 1.

6. The expression correction unit Provide additional relevant information based on reader interests 2. The system of claim 1.

Images