System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting basic child information; means for receiving the basic child information transmitted from the means for inputting basic child information and analyzing the information; means for generating customized learning content using a generative AI model based on the analyzed information; means for transmitting the generated learning content to the means for inputting basic child information; and means for displaying the learning content received by the means for inputting basic child information.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] Many parents face the problem of their children not actively engaging with their work. This problem is particularly pronounced when standardized learning materials do not match the child's interests or proficiency level. Traditional learning systems make it difficult to customize learning materials that are appropriate for each individual child, which can lead to children not enjoying learning. [Means for solving the problem]

[0005] The present invention provides a system that generates customized learning content based on a child's interests and proficiency. This system uses a terminal device to input basic information about the child, and the information sent from the terminal device is analyzed on the server side. Based on the analysis results, a generative AI model is used to generate customized learning content. The generated learning content is sent to the terminal device and displayed on the terminal device. This method allows children to engage with the learning content with interest, improving learning effectiveness.

[0006] The "terminal means" is a device that allows a user to input basic information about a child and transmit that information to a server.

[0007] The "analysis means" is a function within the server that receives basic information about the child sent from the terminal means, analyzes the information, and determines the child's interests and level of proficiency.

[0008] The "generation means" is a function within the server that uses a generative AI model to automatically generate customized learning content based on the analyzed information.

[0009] The "transmission means" is a function within the server that transmits the generated study content to the terminal means.

[0010] The "display means" is a function for displaying the learning content received by the terminal means on the screen and providing it to the user (parent) or child.

[0011] "Basic information about the child" includes information such as the child's age, topics of interest, and level of proficiency.

[0012] A "generative AI model" is an artificial intelligence algorithm that generates customized learning content based on analyzed basic information about a child.

[0013] "Learning content" refers to questions and teaching materials created based on children's interests and level of proficiency. [Brief explanation of the drawings]

[0014] [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. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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, a 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), and an APU (Accelerated Processing Unit).

[0018] 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.

[0019] 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.

[0020] 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), Bluetooth (registered trademark), etc.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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).

[0026] 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.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. 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 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] The present invention is a system that generates and provides individually customized learning content based on basic information about children. This system is realized by the following steps.

[0036] Basic system configuration

[0037] Children's information input method

[0038] The device provides a form for users (parents) to enter basic information about their children, such as their age, interests (e.g., space, animals), and current learning status (e.g., unlearned vocabulary).

[0039] Data transmission and analysis

[0040] The device sends the input data to the server, which analyzes the received data and determines the requirements based on the child's interests and learning status. This analysis can determine, for example, that space-related questions are appropriate for a child who likes space.

[0041] Generating learning content

[0042] The server uses the analysis results to generate learning content appropriate for the child using a generative AI model. The generative AI model provides questions and learning materials tailored to the child's interests and level of proficiency. For example, for a 5-year-old child interested in space, it generates a coloring book that teaches the names of planets and stars in the solar system.

[0043] Submitting and Viewing Learning Content

[0044] The server then sends the generated learning content to the device, which then displays the received learning content on its screen and provides the user with the option to download or print it, allowing parents and children to easily access the content.

[0045] Specific examples

[0046] Example 1: A 5-year-old child who loves space

[0047] The user enters the information "Age: 5 years old" and "Interest: Space" into the terminal and sends it. The terminal then sends this information to the server.

[0048] The server analyzes the input data and generates "simple space-related questions" and "coloring pages to learn the names of stars."

[0049] The server transmits the generated learning content to the terminal.

[0050] The terminal displays the content and gives the user the option to download or print.

[0051] Example 2: A 6-year-old child who loves animals

[0052] The user enters the information "Age: 6 years old" and "Interest: animals" into the terminal and sends it. The terminal then sends this information to the server.

[0053] The server analyzes the input data and generates questions about animal types and their characteristics, as well as puzzles that teach about the habitats of each animal.

[0054] The server transmits the generated learning content to the terminal.

[0055] The terminal displays the content and gives the user the option to download or print.

[0056] In this way, this system uses a generative AI model to provide customized learning content tailored to children's interests and proficiency levels, creating an environment where children can learn while having fun.

[0057] The processing flow will be explained below.

[0058] Step 1:

[0059] The device displays a form for the user (parent) to enter basic information about their child, including fields such as the child's age, topics of interest (e.g., space, animals), and current learning status (e.g., unlearned vocabulary).

[0060] Step 2:

[0061] The user enters basic information about the child into the form and clicks the submit button.

[0062] Step 3:

[0063] The terminal sends the input data to the server. The data is structured in, for example, JSON or XML format.

[0064] Step 4:

[0065] The server analyzes the data received from the terminal, which may include, for example, validating the data and storing it in a database.

[0066] Step 5:

[0067] The server determines the child's interests and proficiency based on the analysis results. For example, if the input interest topic is "space" and the child is 5 years old, it generates space-related learning content.

[0068] Step 6:

[0069] The server passes necessary parameters (e.g., topics of interest and proficiency) to the generative AI model, instructing it to generate customized learning content.

[0070] Step 7:

[0071] Based on given parameters, the generative AI model generates customized learning content, such as simple questions about planets in space or a coloring book to learn the names of stars.

[0072] Step 8:

[0073] The server converts the generated learning content into a user-friendly format, such as HTML or PDF, before sending it to the device.

[0074] Step 9:

[0075] The server transmits the prepared learning content to the terminal.

[0076] Step 10:

[0077] The device then displays the received learning content on its screen, which may involve, for example, rendering an HTML page or launching a PDF viewer.

[0078] Step 11:

[0079] The terminal provides users with download and print options, allowing them to download or print the learning content as needed.

[0080] In this way, customized learning content is provided to the child, making it interesting and effective for the child to learn.

[0081] Example 1

[0082] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0083] Conventional educational systems have faced the challenge of providing learning content tailored to each child's individual interests and proficiency level. In particular, they were unable to automatically generate learning materials tailored to each child's individual characteristics, resulting in a decline in learning effectiveness. Furthermore, preparing content manually required a great deal of time and effort, making it difficult to provide efficient learning support.

[0084] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0085] In this invention, the server includes a terminal means for inputting basic information about the child, an analysis means for receiving the basic information about the child from the terminal means and analyzing the information, a generation means for generating prompt sentences using a generative AI model based on the analyzed information to generate customized learning content, a transmission means for transmitting the generated learning content to the terminal means, and a display means for displaying the learning content received by the terminal means and providing it to the user in a downloadable or printable format. This enables the automatic generation and provision of customized learning content tailored to each child's individual interests and proficiency.

[0086] "Terminal means" means a device or system for inputting basic information about a child.

[0087] "Analysis means" refers to a device or system that receives the basic information about the child sent from the terminal means and analyzes that information.

[0088] "Generative AI model" means an artificial intelligence model that generates prompt sentences based on analyzed information and generates individually customized learning content.

[0089] "Generation means" refers to a device or system that generates customized learning content using a generative AI model based on the information analyzed by the analysis means.

[0090] "Transmission means" refers to a device or system that transmits the generated study content to the terminal means.

[0091] "Display means" refers to a device or system that displays the study content received by the terminal means and provides it to the user in a form that can be downloaded or printed.

[0092] "Prompt sentence" means an instruction sentence that a generative AI model uses as a reference when generating learning content appropriate for children.

[0093] MODE FOR CARRYING OUT THE INVENTION

[0094] The present invention is a system for generating and providing individually customized learning content based on basic information about children. Next, the overall configuration and specific operation of the system will be described.

[0095] Basic system configuration

[0096] The system consists of the following main components:

[0097] 1. Terminal means

[0098] 2. Analysis method

[0099] 3. Generative means (including generative AI models)

[0100] 4. Transmission Method

[0101] 5. Display means

[0102] Terminal means

[0103] The device provides an input form for the user (parent) to enter basic information about their child. This form includes fields for entering information such as the child's age, topics of interest (e.g., space, animals), current learning status (e.g., unlearned vocabulary), etc. When the user enters the information and clicks the submit button, this data is sent from the device to the server.

[0104] Analysis means

[0105] The server receives the child's basic information sent from the terminal means. The received data is deserialized and compared with the database. This comparison allows the server to analyze the requirements for appropriate learning content based on the child's interests and learning status. For example, based on the input data "Age: 6 years old" and "Interest: animals," the server determines that it is appropriate to generate basic questions and teaching materials related to animals.

[0106] generation means

[0107] The server generates appropriate learning content using a generative AI model (e.g., GPT-3) based on the analysis results. The generator operates as a server-side application program, sending prompt sentences to the generative AI model and receiving the generated content.

[0108] Examples of prompts:

[0109] "Create questions for 6-year-olds to help them learn about animal characteristics. These could include simple questions about animal types, characteristics, and habitats. Examples include a quiz where children are asked to look at a picture of an animal and name it, or choose its habitat."

[0110] Based on the prompt, the generative AI model generates customized learning content tailored to the child's interests and proficiency level.

[0111] Transmission method

[0112] The server sends the generated learning content to the terminal. The generated data is serialized in JSON format and sent as an HTTP response. The terminal receives this data and proceeds to the next step.

[0113] Display means

[0114] The device deserializes the learning content received from the server and displays it to the user. The displayed content also provides options for downloading or printing so that children can use it directly for their studies. This creates an environment where children and parents can easily access learning content.

[0115] Specific examples

[0116] Example 1: A 5-year-old child who loves space

[0117] The user enters information such as "Age: 5 years old" and "Interest: Space" into the device and submits it. The device then sends this information to the server. The server analyzes the input data and generates "simple space-related questions" and "coloring pages to learn the names of stars." The server then sends the generated learning content to the device. The device then displays the content and gives the user the option to download or print it.

[0118] Example 2: A 6-year-old child who loves animals

[0119] The user enters information such as "Age: 6 years old" and "Interest: Animals" into the device and submits it. The device then sends this information to the server. The server analyzes the input data and generates questions about animal species and their characteristics, as well as puzzles to learn about the habitats of each animal. The server then sends the generated learning content to the device. The device then displays the content and gives the user the option to download or print it.

[0120] As described above, this system uses a generative AI model to provide customized learning content tailored to children's interests and proficiency levels, allowing children to enjoy learning and parents to easily acquire and use the content.

[0121] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0122] Step 1: Enter your child's basic information

[0123] The user enters basic information about their child into an input form displayed on the device. Input items include the child's age, interests (e.g., space, animals), learning status, etc. The input data is converted into JSON format. This data is input by the user by entering accurate information.

[0124] Input: Child's age, interest topic, learning status

[0125] Output: Basic information about the child in JSON format

[0126] Specific behavior:

[0127] The age input field has a numeric check.

[0128] There is a drop-down menu of topics of interest.

[0129] A text area is provided for the learning status.

[0130] Step 2: Sending data

[0131] The device sends the entered basic information about the child to the server. Specifically, after the submit button is pressed, JSON data is sent to the server as an HTTP POST request.

[0132] Input: Basic information data entered by the user in JSON format

[0133] Output: HTTP POST request to the server

[0134] Specific behavior:

[0135] The user clicks the submit button.

[0136] Form data is collected and converted to JSON format.

[0137] Data is sent asynchronously using AJAX.

[0138] Step 3: Receiving and analyzing data

[0139] The server receives the child's basic information data sent from the device. The received data is deserialized and analyzed against a database (e.g., MySQL). As a result of the analysis, requirements based on the child's interests and learning progress are determined.

[0140] Input: Basic information data in JSON format sent from the terminal

[0141] Output: Learning content requirements based on the analysis results

[0142] Specific behavior:

[0143] Deserialize the received data and convert it to the internal data format.

[0144] Execute the corresponding query on the database to retrieve the relevant data.

[0145] Based on the acquired data, the analysis engine determines the requirements for learning content.

[0146] Step 4: Prompt generation and content generation

[0147] The server sends prompts to a generative AI model (e.g., GPT-3) based on the analysis results, and generates appropriate learning content. The generated content is temporarily stored on the server.

[0148] Input: Prompt text based on the analysis result

[0149] Output: Customized learning content from generative AI models

[0150] Examples of prompts:

[0151] "Create questions for 6-year-olds to help them learn about animal characteristics. These could include simple questions about animal types, characteristics, and habitats. Examples include a quiz where children are asked to look at a picture of an animal and name it, or choose its habitat."

[0152] Specific behavior:

[0153] Generates a prompt string based on the parsed data used to construct the prompt statement.

[0154] Send an HTTP request to the API endpoint of the generative AI model.

[0155] Receive a response from the generative AI model.

[0156] Step 5: Submit your learning content

[0157] The server serializes the generated learning content into JSON format and sends it to the terminal as an HTTP response.

[0158] Input: Customized learning content from a generative AI model

[0159] Output: Learning content as an HTTP response to the device

[0160] Specific behavior:

[0161] Serialize the generated content into JSON format.

[0162] Create an HTTP response object and send it to the device.

[0163] Step 6: View learning content

[0164] The device deserializes the learning content received from the server and displays it to the user, offering the user the option to download or print the content.

[0165] Input: Learning content received as an HTTP response from the server

[0166] Output: The learning content that users see, along with download and print options

[0167] Specific behavior:

[0168] Deserialize the received data.

[0169] The data is applied to an HTML template and displayed in the user interface.

[0170] Enable buttons for downloading and printing.

[0171] (Application example 1)

[0172] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0173] Conventional learning content provision systems have had the problem of being unable to provide content that appropriately reflects differences in children's ages and interests, and are only able to provide uniform educational materials. Furthermore, there is no system that allows parents to easily download and print learning content for their children, which makes them inconvenient.

[0174] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0175] In this invention, the server includes a terminal means for inputting basic information about the child, an analysis means for receiving the basic information about the child from the terminal means and analyzing the information, a generation means for generating customized learning content using a generative AI model based on the analyzed information, a transmission means for transmitting the generated learning content to the terminal means, a display means for displaying the learning content received by the terminal means and providing it to the user, and a means for the terminal means to provide the option to download or print the learning content in response to a user's request. This allows for the provision of personalized learning content according to the child's age and interests, and for parents to easily download and print the content.

[0176] "Terminal means" is a device for inputting basic information about a child and transmitting that information to a server.

[0177] The "analysis means" is a function that analyzes the received basic information about the child and determines the requirements for generating appropriate learning content based on that data.

[0178] The "generation means" is a function that uses a generative AI model based on the analysis results to create customized learning content suitable for children.

[0179] The "transmission means" is a function that transmits the generated study content to the terminal means.

[0180] The "display means" is a function that displays and provides the study content received by the terminal means to the user.

[0181] The "means for providing download and print options" is a function that allows the terminal means to download or print the generated study content according to the user's request.

[0182] "Educational Materials" refers generally to content that is individually customized using generative AI models to support learning.

[0183] "Unacquired vocabulary" refers to words and phrases that a child has not yet learned or fully understood.

[0184] A "generative AI model" is an artificial intelligence model that generates optimal learning content based on input data.

[0185] This invention is a system that generates and provides individually customized learning content based on basic information about children. This system is realized by the following steps.

[0186] Basic system configuration

[0187] Children's information input method

[0188] The terminal provides a form for the user (parent) to input basic information about their child, including the child's age, topics of interest, and current learning status (e.g., vocabulary that has not yet been mastered).

[0189] Data transmission and analysis

[0190] The terminal device sends the input data to the server, which analyzes the received data and determines the requirements based on the child's interests and learning status. Based on this analysis, for example, it can suggest space-related educational materials to a child who likes space.

[0191] Generating learning content

[0192] The server uses the analysis results to generate learning content appropriate for the child using a generative AI model. The generative AI model provides questions and learning materials tailored to the child's interests and level of proficiency. For example, for a 6-year-old child interested in animals, it would generate content that teaches them about different animal species and their characteristics.

[0193] Submitting and Viewing Learning Content

[0194] The server transmits the generated learning content to the terminal device, which displays the received learning content on the screen and provides it to the user. The terminal device also provides the user with the option to download or print the content, depending on the user's request.

[0195] Hardware and software used

[0196] Hardware: Smartphones, tablets, personal computers

[0197] Software: Python scripts, Flask (for the server side), generative AI models (e.g., OpenAI GPT-3)

[0198] Data processing and calculation

[0199] Data collection: Parents enter their child's age, interests, and learning status into a dedicated device.

[0200] Data transmission: Data is transmitted from the terminal means to the server.

[0201] Data analysis: Based on the received data, the server inputs the data into a generative AI model to generate optimal learning content.

[0202] Content generation: Generated content is generated by the server and sent to the terminal means.

[0203] Content display: Displays the learning content generated on the terminal means and provides the user with the option to download or print.

[0204] Specific examples

[0205] Example 1

[0206] Child: 6 years old

[0207] Interests: Animals

[0208] Learning level: Intermediate

[0209] "Intermediate-level content tailored for 6-year-olds who love animals"

[0210] Example 2

[0211] Child: 7 years old

[0212] Interests: Science

[0213] Learning level: Advanced

[0214] "Advanced level teaching materials specifically designed for 7-year-old science-loving children"

[0215] Prompt Sentence Examples

[0216] "Intermediate-level content tailored for 6-year-olds who love animals"

[0217] "Advanced level teaching materials specifically designed for 7-year-old science-loving children"

[0218] This makes it possible to provide personalized learning content tailored to each child's age, interests, and learning level.

[0219] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0220] Step 1:

[0221] The user (parent) enters basic information about the child (age, interests, learning status, etc.) into the terminal means. The terminal means collects this input data and converts it into JSON format data. Specifically, the parent enters the required information into a form using a dedicated application.

[0222] input:

[0223] Children's age, interests, and learning status

[0224] output:

[0225] Basic information data in JSON format

[0226] Step 2:

[0227] The terminal sends the collected data in JSON format to the server using an HTTP POST request, and the server waits to analyze the received data.

[0228] input:

[0229] Basic information data in JSON format

[0230] output:

[0231] HTTP POST request

[0232] Step 3:

[0233] The server analyzes the received basic information about the child. Specifically, it parses the JSON format data to determine the child's interests and learning status. The analyzed data is then converted into a format suitable for the generative AI model.

[0234] input:

[0235] Basic information about the child passed to the server

[0236] output:

[0237] Data in a format suitable for generative AI models

[0238] Step 4:

[0239] The server generates customized learning content using a generative AI model. Based on the analysis results, the server inputs corresponding prompt sentences into the generative AI model. The generative AI model generates optimal learning content based on the prompt sentences.

[0240] input:

[0241] Data in a format suitable for generative AI models

[0242] Prompt statement

[0243] output:

[0244] Customized learning content

[0245] Step 5:

[0246] The server transmits the generated customized learning content to the terminal means, again using an HTTP POST request or other suitable communication means.

[0247] input:

[0248] Customized learning content

[0249] output:

[0250] HTTP POST request or other communication method

[0251] Step 6:

[0252] The terminal displays the received learning content on the screen, and the user (parent) can check the displayed content and use the option to download or print the content if necessary.

[0253] input:

[0254] Customized learning content received

[0255] output:

[0256] On-screen learning content

[0257] Download and print options

[0258] Step 7:

[0259] The user utilizes the download and print options to obtain the learning content in a format that can be physically stored or used. Depending on the user's selection, the terminal means performs a specific action (downloading a file or issuing a print command).

[0260] input:

[0261] On-screen learning content

[0262] User's choice (download or print)

[0263] output:

[0264] Downloaded files or printed materials

[0265] This ensures that learning content that is customized to a child's age, interests, and learning level is generated and delivered efficiently and effectively.

[0266] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0267] The present invention is a system that generates and provides individually customized learning content based on basic information about children and emotional information about users. This system is realized by the following steps.

[0268] Basic system configuration

[0269] Children's information input method

[0270] The device provides a form for users (parents) to enter basic information about their children, such as their age, interests (e.g., space, animals), and current learning status (e.g., unlearned vocabulary).

[0271] Data transmission and analysis

[0272] The terminal sends the input data to the server. The data is structured in, for example, JSON or XML format.

[0273] The server analyzes the data received from the terminal, which may include, for example, validating the data and storing it in a database.

[0274] Acquiring and analyzing user emotion information

[0275] The device uses an emotion engine to acquire emotion data from the user's facial expressions and voice information, including emotions such as joy, sadness, surprise, and anger.

[0276] The terminal transmits the acquired emotion data to the server.

[0277] The server analyzes the emotion data provided by the emotion engine and evaluates the user's emotional state.

[0278] Generating learning content

[0279] The server uses the analysis results to generate learning content appropriate for the child using a generative AI model. The generative AI model adjusts questions and learning materials according to the child's interests and proficiency, as well as the user's emotional state. For example, if the user is relaxed, it will generate slightly more difficult questions, and if they are stressed, it will provide easier questions and interactive learning materials.

[0280] Submitting and Viewing Learning Content

[0281] The server then sends the generated learning content to the device, which then displays the received learning content on its screen and provides the user with the option to download or print it, allowing parents and children to easily access the content.

[0282] Specific examples

[0283] Example 1: A 5-year-old child who loves space

[0284] The user enters the information "Age: 5 years old" and "Interest: Space" into the terminal and sends it. The terminal then sends this information to the server.

[0285] The server analyzes the input data and generates "simple space-related questions" and "coloring pages to learn the names of stars."

[0286] The server transmits the generated learning content to the terminal.

[0287] At the same time, the device uses an emotion engine to obtain emotional information while the child is learning. For example, if the child is having fun, that information is sent to the server, and challenging questions are added to the next learning content.

[0288] The terminal displays the content and gives the user the option to download or print.

[0289] Example 2: A 6-year-old child who loves animals

[0290] The user enters the information "Age: 6 years old" and "Interest: animals" into the terminal and sends it. The terminal then sends this information to the server.

[0291] The server analyzes the input data and generates questions about animal types and their characteristics, as well as puzzles that teach about the habitats of each animal.

[0292] The server transmits the generated learning content to the terminal.

[0293] At the same time, the device uses an emotion engine to capture the child's emotions in real time. For example, if the child is tired, that information is sent to the server, and the device will provide a relaxing activity for the next learning content.

[0294] The terminal displays the content and gives the user the option to download or print.

[0295] In this way, by combining a generative AI model with an emotion engine, this system provides customized learning content tailored to children's interests, proficiency levels, and even emotional states, creating an environment where children can learn while having fun.

[0296] The processing flow will be explained below.

[0297] Step 1:

[0298] The device displays a form for the user (parent) to enter basic information about their child, including fields such as the child's age, topics of interest (e.g., space, animals), and current learning status (e.g., unlearned vocabulary).

[0299] Step 2:

[0300] The user enters basic information about the child into the form and clicks the submit button.

[0301] Step 3:

[0302] The terminal sends the input data to the server. The data is structured in, for example, JSON or XML format.

[0303] Step 4:

[0304] The server analyzes the data received from the terminal, which may include, for example, validating the data and storing it in a database.

[0305] Step 5:

[0306] The device runs an emotion engine and captures facial expressions and voices while the user is monitoring their child's learning, thereby obtaining the user's emotion data.

[0307] Step 6:

[0308] The terminal transmits the acquired emotion data to the server. The emotion data includes various emotions of the user, such as joy, anger, sadness, and pleasure.

[0309] Step 7:

[0310] The server analyzes the emotion data provided by the emotion engine to assess the user's emotional state, for example, determining whether the user is stressed or relaxed.

[0311] Step 8:

[0312] The server uses the analysis results to provide the necessary parameters (e.g., topics of interest, proficiency, emotional state, etc.) to the generative AI model, instructing it to generate customized learning content.

[0313] Step 9:

[0314] Based on given parameters, the generative AI model generates customized learning content, such as simple questions about planets in space or a coloring book to learn the names of stars.

[0315] Step 10:

[0316] The server converts the generated learning content into a user-friendly format, such as HTML or PDF, before sending it to the device.

[0317] Step 11:

[0318] The server transmits the prepared learning content to the terminal.

[0319] Step 12:

[0320] The device then displays the received learning content on its screen, which may involve, for example, rendering an HTML page or launching a PDF viewer.

[0321] Step 13:

[0322] The terminal provides users with download and print options, allowing them to download or print the learning content as needed.

[0323] Step 14:

[0324] After the learning session ends, the device will start the emotion engine again and capture the final emotional state.

[0325] Step 15:

[0326] The device sends the final emotion data to the server, which stores it in a database for reference during the next learning session.

[0327] In this way, customized learning content is provided to children, taking into account the user's emotional state in the process, making learning more engaging and effective for children.

[0328] Example 2

[0329] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0330] Conventional learning content generation systems have not adequately provided content tailored to each child's individual interests and level of proficiency. Furthermore, there is no mechanism for customizing learning content that takes into account the user's emotional state, making it difficult to provide effective learning support. This makes it difficult for children to become interested in learning, resulting in reduced learning effectiveness.

[0331] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0332] In this invention, the server includes terminal means for inputting basic information about the child, analysis means for receiving the basic information about the child from the terminal means and analyzing the information, generation means for generating customized learning content using a generative AI model based on the analyzed information and the user's emotional information, transmission means for transmitting the generated learning content to the terminal means, display means for displaying the learning content received by the terminal means and providing it to the user, an emotion engine for acquiring emotional information from the user's facial expressions and voice, and means for transmitting the emotional information to the server and analyzing it. This makes it possible to provide individually customized learning content based on the child's interests and proficiency, and further take the user's emotional state into consideration, thereby achieving a more effective and engaging learning experience.

[0333] The "terminal means" is a device used by the user to input basic information and emotional information about the child and transmit that information to the server.

[0334] The "analysis means" is a means for analyzing the basic information and emotional information of the child received from the terminal means and generating learning content based on the results.

[0335] A "generative AI model" is an artificial intelligence model that generates learning content suitable for children based on analyzed information.

[0336] "Generative means" means a means for creating customized learning content using a generative AI model.

[0337] The "transmission means" is a means for transmitting the generated study content to the terminal means.

[0338] The "display means" refers to a means for visually presenting the study content received by the terminal means to the user.

[0339] The "emotion engine" is an engine that acquires emotion data from the user's facial expressions and voice information and evaluates their emotional state.

[0340] "Emotion information" is information about the emotional state analyzed based on data acquired from the user's facial expressions and voice.

[0341] The present invention is a system for generating and providing individually customized learning content based on basic information about a child and emotional information about a user. The following describes an embodiment of this system.

[0342] Basic system configuration

[0343] Children's information input method

[0344] The device provides a form for the user to enter basic information about the child, including the child's age, interests, current level of proficiency, etc. For example, the user can open a web browser, enter this information into the form, and click the submit button.

[0345] Data transmission and analysis

[0346] The terminal sends the entered data to the server in JSON or XML format. Specifically, the data is sent using an HTTP POST request. The server analyzes the received data, first validating it and checking that all required data is included. It then saves it in a database and waits for the analysis results. The Python pandas library can be used for analysis.

[0347] Acquiring and analyzing user emotion information

[0348] The device uses an emotion engine to acquire emotion data from the user's facial expressions and voice. For example, a webcam or microphone is used to collect the user's face and voice, which are then analyzed by the emotion engine. The acquired emotion data is then sent to the server again using an HTTP POST request. The server analyzes the emotion data provided by the emotion engine and evaluates the user's emotional state. A machine learning model can be used for this analysis.

[0349] Generating learning content

[0350] The server uses a generative AI model based on the child's basic information and the user's emotional data to generate appropriate learning content. For example, a generative AI model such as GPT-3 can be used, and a prompt such as "5-year-old child, interested in space" can be created and input into the model. Based on this prompt, simple questions and learning materials are generated.

[0351] Submitting and Viewing Learning Content

[0352] The server sends the generated learning content to the device, which then displays the received content on the screen and provides the user with the option to download or print it. For example, this can be achieved by displaying the content on a web page with download and print buttons.

[0353] Specific examples

[0354] Example 1: A 5-year-old child who loves space

[0355] The user enters information such as "Age: 5 years old" and "Interest: Space" into the device and sends it. The device then sends this to the server, which analyzes the input data and generates "easy space-related questions" and "coloring pages to learn the names of stars." The server then sends the generated learning content to the device, which then displays the content. In addition, an emotion engine is used to obtain emotional information while the user is learning, and if the user is enjoying the learning experience, this information is sent to the server, and more challenging questions are added to the next learning content.

[0356] Example 2: A 6-year-old child who loves animals

[0357] The user enters information such as "Age: 6 years old" and "Interest: animals" into the device and sends it. The device then sends this to the server, which analyzes the input data and generates questions about animal species and their characteristics, as well as puzzles to learn about each animal's habitat. The server then sends the generated learning content to the device, which then displays it. The device also uses an emotion engine to obtain the child's emotions in real time and offers relaxing activities if the child is tired.

[0358] Examples of prompt statements

[0359] 1. "My child is 5 years old and is interested in space. What educational content can you provide him?"

[0360] 2. "What materials would be appropriate for a 6-year-old child to learn about animals?"

[0361] In this way, by combining a generative AI model with an emotion engine, this system can customize and provide learning content according to a child's interests, proficiency level, and even emotional state.

[0362] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0363] Step 1: Enter your child's information

[0364] The user uses the device to enter basic information about their child. Specifically, the user opens a web browser and enters the child's age, interests, and current level of proficiency in the form that appears. This input form includes text boxes and drop-down menus, and once the input is complete, the information is sent by clicking the submit button.

[0365] Input: Child's age, topics of interest, current level of proficiency

[0366] Output: Structured data (e.g., JSON format)

[0367] Step 2: Sending data

[0368] The terminal sends the input structured data to the server. Specifically, the data is sent using an HTTP POST request. This request includes the user's input information.

[0369] Input: Structured data (e.g., JSON format)

[0370] Output: Send data to the server

[0371] Step 3: Analyze the data

[0372] The server analyzes the received data. Specifically, it first validates the data to check whether it contains all the required data. It then saves it in the database and waits for the analysis results. This analysis can be done using Python's pandas library or SQL.

[0373] Input: Data submitted by the user

[0374] Output: Data validation results, saved to database

[0375] Step 4: Obtaining user emotion information

[0376] The device uses an emotion engine to acquire emotion data from the user's facial expressions and voice in real time. For example, it uses a webcam or microphone to collect the user's face and voice and analyzes them. This analysis is performed by the emotion engine.

[0377] Input: User's facial expressions and voice information

[0378] Output: Emotion data (e.g., happiness, sadness)

[0379] Step 5: Send and analyze emotion data

[0380] The device sends the acquired emotion data to the server, again using an HTTP POST request. The server analyzes the emotion data provided by the emotion engine and evaluates the user's emotional state. A machine learning model can be used for the analysis.

[0381] Input: Emotion data

[0382] Output: Evaluation of the user's emotional state

[0383] Step 6: Generate learning content

[0384] The server uses a generative AI model based on the child's basic information and the user's emotional data to generate appropriate learning content. Specifically, the server creates a prompt for the generative AI model: "A 5-year-old child interested in space." This prompt is then input into the model. Based on this prompt, simple questions and learning materials are generated.

[0385] Input: Basic information about the child, user's emotional data

[0386] Output: Generated learning content

[0387] Step 7: Submit and view your learning content

[0388] The server sends the generated learning content to the device. Specifically, it sends the content using an HTTP response. The device displays the received content on the screen and offers the user the option to download or print it. Specifically, this is achieved by displaying the content on a web page and providing download and print buttons.

[0389] Input: Generated learning content

[0390] Output: The learning content displayed to the user, with options to download and print

[0391] (Application example 2)

[0392] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0393] In conventional factories, only standardized education and training has been provided to improve individual worker capabilities and work efficiency. However, because optimal support varies depending on the worker's level of proficiency and emotional state, the effectiveness of a one-size-fits-all approach has been limited. In particular, in work environments where workers are prone to fatigue and stress, individually customized support is important. The objective of this invention is to provide a system that improves worker efficiency and satisfaction by providing individually customized support content based on the worker's basic information and emotional information.

[0394] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0395] In this invention, the server includes terminal means for inputting basic information about the worker, analysis means for receiving the basic information about the worker sent from the terminal means and analyzing the information, emotion engine means for acquiring emotional information about the worker, analysis means for receiving the emotional information sent from the emotion engine means and analyzing the information, generation means for generating customized assistance content using a generative AI model based on the analyzed basic information and emotional information, transmission means for transmitting the generated assistance content to the terminal means, and display means for displaying the assistance content received by the terminal means and providing it to the worker. This makes it possible to provide optimal work assistance and relaxation content based on the basic information and real-time emotional information of the worker.

[0396] "Basic information about workers" refers to information about the individual characteristics of workers, such as their age, work experience, specialties, and problems.

[0397] "Terminal means" refers to an electronic device for inputting and transmitting basic information about workers.

[0398] The "analysis means" is a processing device or software for receiving and analyzing information sent from the terminal means.

[0399] The "emotion engine means" is a device or software that uses sensors such as a camera and a microphone to obtain emotional information from the facial expressions and voices of workers.

[0400] The "generation means" refers to a processing device or software that uses a generative AI model to generate customized assistance content based on the analyzed basic information and emotional information.

[0401] The "transmission means" is a communication device or software for transmitting the generated assistance content to the terminal means.

[0402] The "display means" is a device or software that displays the support content received by the terminal means on a screen and provides it to the worker.

[0403] A "generative AI model" is a model that uses machine learning algorithms to automatically generate content tailored to a specific purpose based on input data.

[0404] "Support content" is information for work support and relaxation that is individually customized based on the worker's basic information and emotional state.

[0405] The present invention is a system for providing individually customized support content based on basic information and emotional information of a worker. Specific embodiments of the present invention will be described in detail below.

[0406] Basic system configuration

[0407] Employee information input method

[0408] The terminal means provides a form for inputting basic information about the worker. The basic information about the worker includes age, work experience, specialty work, current problems, etc. For example, information such as "Age: 35 years old," "Work experience: 10 years," "Specialty work: assembly," and "Problem: inspection work takes a long time" is input.

[0409] Data transmission and analysis

[0410] The terminal means sends the input data to the server. The data is structured in, for example, JSON or XML format. The server analyzes the data received from the terminal. Analysis includes data validation and saving to a database.

[0411] Acquiring and analyzing worker emotion information

[0412] The emotion engine means acquires emotion data from the worker's facial expressions and voice information using a camera and microphone mounted on the terminal means. The emotion information includes fatigue, stress, concentration, etc. The terminal means transmits the acquired emotion data to the server. The server analyzes the emotion data provided by the emotion engine means and evaluates the worker's emotional state.

[0413] Support content generation

[0414] The server uses the analysis results to generate support content tailored to the worker using a generative AI model. The generative AI model adjusts the support content based on the worker's basic information and emotional state. For example, if the worker is tired, it will suggest relaxing stretches, and if the worker is working and requires concentration, it will provide specific advice to improve efficiency.

[0415] Sending and displaying support content

[0416] The server transmits the generated support content to the terminal means. The terminal means displays the received support content on a screen and provides it to the worker. For example, the display may say, "Please perform relaxing stretches for five minutes."

[0417] Hardware and software used

[0418] Hardware: Camera, microphone, and display attached to the robot

[0419] software:

[0420] Emotion engine: Software that processes data from the camera and microphone to assess emotional state

[0421] Generative AI model: A machine learning model that generates optimal support content based on basic and emotional information about the worker.

[0422] Server: API that analyzes data and generates support content

[0423] Specific examples

[0424] Example 1: Content creation flow for worker "Factory Worker A"

[0425] The factory's robot AI reads the facial expression of "Worker A" and detects that he is tired.

[0426] The data is analyzed on the server and content is generated that suggests relaxing stretches for "Worker A."

[0427] The robot calls out, "Mr. A, you look tired. Would you like to try stretching for five minutes?"

[0428] Example prompt sentence:

[0429] Design a system in which a factory robot analyzes the emotions of "Factory Worker A" from his facial expressions and voice, and suggests relaxing stretches to the worker. Specifically, the system will include a process in which the worker's basic information is input, emotional data is acquired in real time using an emotion engine, customized support content is generated using a generative AI model, and finally the robot provides the support content on a screen or via voice.

[0430] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0431] Step 1:

[0432] The user inputs basic information about the worker on the terminal and submits it. The input data includes age, work experience, specialties, problems, etc. This information is structured in JSON or XML format and sent to the server.

[0433] Input: Basic information of the worker (age, work experience, specialty, problems)

[0434] Output: JSON or XML data sent to the server

[0435] Step 2:

[0436] The server analyzes the received worker's basic information, performs data validation (format check, missing value check, etc.), and stores the data in the database if it is in the correct format.

[0437] Input: Basic information about the worker (JSON or XML data)

[0438] Output: Worker information stored in the database

[0439] Step 3:

[0440] Using the camera and microphone installed in the terminal, the emotion engine means acquires emotion data from the worker's facial expressions and voice information, using facial recognition and voice analysis of the worker.

[0441] Input: Camera video, audio data

[0442] Output: Emotion data (e.g., tiredness, stress, concentration)

[0443] Step 4:

[0444] The device sends the acquired emotion data to the server, which in turn structures the data in JSON or XML format.

[0445] Input: Emotion data (data obtained in real time)

[0446] Output: JSON or XML data sent to the server

[0447] Step 5:

[0448] The server analyzes the emotion data provided by the emotion engine means and uses the analysis results to evaluate the worker's emotional state.

[0449] Input: Emotion data (JSON or XML data)

[0450] Output: Evaluation result (e.g., worker's current emotional state)

[0451] Step 6:

[0452] The server uses a generative AI model based on the analysis results (basic information and emotional state of the worker) to generate customized support content. The generative AI model creates appropriate support content according to the worker's situation.

[0453] Input: Basic information and emotional state (evaluation results)

[0454] Output: Generated assistance content

[0455] Step 7:

[0456] The server sends the generated support content to the device in HTML or JSON format, which is suitable for display.

[0457] Input: Generated assistance content

[0458] Output: Support content (HTML or JSON data) sent to the device

[0459] Step 8:

[0460] The device then displays the received support content on its screen and provides it to the worker, such as advice on stretching techniques to relax or improving work efficiency.

[0461] Input: Received support content (HTML or JSON data)

[0462] Output: The display content provided to the worker

[0463] 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.

[0464] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. 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 voice, text data indicating text, and image data indicating an image is also input. 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.

[0465] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0466] [Second embodiment]

[0467] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0468] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0469] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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).

[0470] 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.

[0471] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0472] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0473] 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.

[0474] 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.

[0475] 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 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.

[0476] 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.

[0477] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0478] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0479] The present invention is a system that generates and provides individually customized learning content based on basic information about children. This system is realized by the following steps.

[0480] Basic system configuration

[0481] Children's information input method

[0482] The device provides a form for users (parents) to enter basic information about their children, such as their age, interests (e.g., space, animals), and current learning status (e.g., unlearned vocabulary).

[0483] Data transmission and analysis

[0484] The device sends the input data to the server, which analyzes the received data and determines the requirements based on the child's interests and learning status. This analysis can determine, for example, that space-related questions are appropriate for a child who likes space.

[0485] Generating learning content

[0486] The server uses the analysis results to generate learning content appropriate for the child using a generative AI model. The generative AI model provides questions and learning materials tailored to the child's interests and level of proficiency. For example, for a 5-year-old child interested in space, it generates a coloring book that teaches the names of planets and stars in the solar system.

[0487] Submitting and Viewing Learning Content

[0488] The server then sends the generated learning content to the device, which then displays the received learning content on its screen and provides the user with the option to download or print it, allowing parents and children to easily access the content.

[0489] Specific examples

[0490] Example 1: A 5-year-old child who loves space

[0491] The user enters the information "Age: 5 years old" and "Interest: Space" into the terminal and sends it. The terminal then sends this information to the server.

[0492] The server analyzes the input data and generates "simple space-related questions" and "coloring pages to learn the names of stars."

[0493] The server transmits the generated learning content to the terminal.

[0494] The terminal displays the content and gives the user the option to download or print.

[0495] Example 2: A 6-year-old child who loves animals

[0496] The user enters the information "Age: 6 years old" and "Interest: animals" into the terminal and sends it. The terminal then sends this information to the server.

[0497] The server analyzes the input data and generates questions about animal types and their characteristics, as well as puzzles that teach about the habitats of each animal.

[0498] The server transmits the generated learning content to the terminal.

[0499] The terminal displays the content and gives the user the option to download or print.

[0500] In this way, this system uses a generative AI model to provide customized learning content tailored to children's interests and proficiency levels, creating an environment where children can learn while having fun.

[0501] The processing flow will be explained below.

[0502] Step 1:

[0503] The device displays a form for the user (parent) to enter basic information about their child, including fields such as the child's age, topics of interest (e.g., space, animals), and current learning status (e.g., unlearned vocabulary).

[0504] Step 2:

[0505] The user enters basic information about the child into the form and clicks the submit button.

[0506] Step 3:

[0507] The terminal sends the input data to the server. The data is structured in, for example, JSON or XML format.

[0508] Step 4:

[0509] The server analyzes the data received from the terminal, which may include, for example, validating the data and storing it in a database.

[0510] Step 5:

[0511] The server determines the child's interests and proficiency based on the analysis results. For example, if the input interest topic is "space" and the child is 5 years old, it generates space-related learning content.

[0512] Step 6:

[0513] The server passes necessary parameters (e.g., topics of interest and proficiency) to the generative AI model, instructing it to generate customized learning content.

[0514] Step 7:

[0515] Based on given parameters, the generative AI model generates customized learning content, such as simple questions about planets in space or a coloring book to learn the names of stars.

[0516] Step 8:

[0517] The server converts the generated learning content into a user-friendly format, such as HTML or PDF, before sending it to the device.

[0518] Step 9:

[0519] The server transmits the prepared learning content to the terminal.

[0520] Step 10:

[0521] The device then displays the received learning content on its screen, which may involve, for example, rendering an HTML page or launching a PDF viewer.

[0522] Step 11:

[0523] The terminal provides users with download and print options, allowing them to download or print the learning content as needed.

[0524] In this way, customized learning content is provided to the child, making it interesting and effective for the child to learn.

[0525] Example 1

[0526] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0527] Conventional educational systems have faced the challenge of providing learning content tailored to each child's individual interests and proficiency level. In particular, they were unable to automatically generate learning materials tailored to each child's individual characteristics, resulting in a decline in learning effectiveness. Furthermore, preparing content manually required a great deal of time and effort, making it difficult to provide efficient learning support.

[0528] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0529] In this invention, the server includes a terminal means for inputting basic information about the child, an analysis means for receiving the basic information about the child from the terminal means and analyzing the information, a generation means for generating prompt sentences using a generative AI model based on the analyzed information to generate customized learning content, a transmission means for transmitting the generated learning content to the terminal means, and a display means for displaying the learning content received by the terminal means and providing it to the user in a downloadable or printable format. This enables the automatic generation and provision of customized learning content tailored to each child's individual interests and proficiency.

[0530] "Terminal means" means a device or system for inputting basic information about a child.

[0531] "Analysis means" refers to a device or system that receives the basic information about the child sent from the terminal means and analyzes that information.

[0532] "Generative AI model" means an artificial intelligence model that generates prompt sentences based on analyzed information and generates individually customized learning content.

[0533] "Generation means" refers to a device or system that generates customized learning content using a generative AI model based on the information analyzed by the analysis means.

[0534] "Transmission means" refers to a device or system that transmits the generated study content to the terminal means.

[0535] "Display means" refers to a device or system that displays the study content received by the terminal means and provides it to the user in a form that can be downloaded or printed.

[0536] "Prompt sentence" means an instruction sentence that a generative AI model uses as a reference when generating learning content appropriate for children.

[0537] MODE FOR CARRYING OUT THE INVENTION

[0538] The present invention is a system for generating and providing individually customized learning content based on basic information about children. Next, the overall configuration and specific operation of the system will be described.

[0539] Basic system configuration

[0540] The system consists of the following main components:

[0541] 1. Terminal means

[0542] 2. Analysis method

[0543] 3. Generative means (including generative AI models)

[0544] 4. Transmission Method

[0545] 5. Display means

[0546] Terminal means

[0547] The device provides an input form for the user (parent) to enter basic information about their child. This form includes fields for entering information such as the child's age, topics of interest (e.g., space, animals), current learning status (e.g., unlearned vocabulary), etc. When the user enters the information and clicks the submit button, this data is sent from the device to the server.

[0548] Analysis means

[0549] The server receives the child's basic information sent from the terminal means. The received data is deserialized and compared with the database. This comparison allows the server to analyze the requirements for appropriate learning content based on the child's interests and learning status. For example, based on the input data "Age: 6 years old" and "Interest: animals," the server determines that it is appropriate to generate basic questions and teaching materials related to animals.

[0550] generation means

[0551] The server generates appropriate learning content using a generative AI model (e.g., GPT-3) based on the analysis results. The generator operates as a server-side application program, sending prompt sentences to the generative AI model and receiving the generated content.

[0552] Examples of prompts:

[0553] "Create questions for 6-year-olds to help them learn about animal characteristics. These could include simple questions about animal types, characteristics, and habitats. Examples include a quiz where children are asked to look at a picture of an animal and name it, or choose its habitat."

[0554] Based on the prompt, the generative AI model generates customized learning content tailored to the child's interests and proficiency level.

[0555] Transmission method

[0556] The server sends the generated learning content to the terminal. The generated data is serialized in JSON format and sent as an HTTP response. The terminal receives this data and proceeds to the next step.

[0557] Display means

[0558] The device deserializes the learning content received from the server and displays it to the user. The displayed content also provides options for downloading or printing so that children can use it directly for their studies. This creates an environment where children and parents can easily access learning content.

[0559] Specific examples

[0560] Example 1: A 5-year-old child who loves space

[0561] The user enters information such as "Age: 5 years old" and "Interest: Space" into the device and submits it. The device then sends this information to the server. The server analyzes the input data and generates "simple space-related questions" and "coloring pages to learn the names of stars." The server then sends the generated learning content to the device. The device then displays the content and gives the user the option to download or print it.

[0562] Example 2: A 6-year-old child who loves animals

[0563] The user enters information such as "Age: 6 years old" and "Interest: Animals" into the device and submits it. The device then sends this information to the server. The server analyzes the input data and generates questions about animal species and their characteristics, as well as puzzles to learn about the habitats of each animal. The server then sends the generated learning content to the device. The device then displays the content and gives the user the option to download or print it.

[0564] As described above, this system uses a generative AI model to provide customized learning content tailored to children's interests and proficiency levels, allowing children to enjoy learning and parents to easily acquire and use the content.

[0565] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0566] Step 1: Enter your child's basic information

[0567] The user enters basic information about their child into an input form displayed on the device. Input items include the child's age, interests (e.g., space, animals), learning status, etc. The input data is converted into JSON format. This data is input by the user by entering accurate information.

[0568] Input: Child's age, interest topic, learning status

[0569] Output: Basic information about the child in JSON format

[0570] Specific behavior:

[0571] The age input field has a numeric check.

[0572] There is a drop-down menu of topics of interest.

[0573] A text area is provided for the learning status.

[0574] Step 2: Sending data

[0575] The device sends the entered basic information about the child to the server. Specifically, after the submit button is pressed, JSON data is sent to the server as an HTTP POST request.

[0576] Input: Basic information data entered by the user in JSON format

[0577] Output: HTTP POST request to the server

[0578] Specific behavior:

[0579] The user clicks the submit button.

[0580] Form data is collected and converted to JSON format.

[0581] Data is sent asynchronously using AJAX.

[0582] Step 3: Receiving and analyzing data

[0583] The server receives the child's basic information data sent from the device. The received data is deserialized and analyzed against a database (e.g., MySQL). As a result of the analysis, requirements based on the child's interests and learning progress are determined.

[0584] Input: Basic information data in JSON format sent from the terminal

[0585] Output: Learning content requirements based on the analysis results

[0586] Specific behavior:

[0587] Deserialize the received data and convert it to the internal data format.

[0588] Execute the corresponding query on the database to retrieve the relevant data.

[0589] Based on the acquired data, the analysis engine determines the requirements for learning content.

[0590] Step 4: Prompt generation and content generation

[0591] The server sends prompts to a generative AI model (e.g., GPT-3) based on the analysis results, and generates appropriate learning content. The generated content is temporarily stored on the server.

[0592] Input: Prompt text based on the analysis result

[0593] Output: Customized learning content from generative AI models

[0594] Examples of prompts:

[0595] "Create questions for 6-year-olds to help them learn about animal characteristics. These could include simple questions about animal types, characteristics, and habitats. Examples include a quiz where children are asked to look at a picture of an animal and name it, or choose its habitat."

[0596] Specific behavior:

[0597] Generates a prompt string based on the parsed data used to construct the prompt statement.

[0598] Send an HTTP request to the API endpoint of the generative AI model.

[0599] Receive a response from the generative AI model.

[0600] Step 5: Submit your learning content

[0601] The server serializes the generated learning content into JSON format and sends it to the terminal as an HTTP response.

[0602] Input: Customized learning content from a generative AI model

[0603] Output: Learning content as an HTTP response to the device

[0604] Specific behavior:

[0605] Serialize the generated content into JSON format.

[0606] Create an HTTP response object and send it to the device.

[0607] Step 6: View learning content

[0608] The device deserializes the learning content received from the server and displays it to the user, offering the user the option to download or print the content.

[0609] Input: Learning content received as an HTTP response from the server

[0610] Output: The learning content that users see, along with download and print options

[0611] Specific behavior:

[0612] Deserialize the received data.

[0613] The data is applied to an HTML template and displayed in the user interface.

[0614] Enable buttons for downloading and printing.

[0615] (Application example 1)

[0616] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0617] Conventional learning content provision systems have had the problem of being unable to provide content that appropriately reflects differences in children's ages and interests, and are only able to provide uniform educational materials. Furthermore, there is no system that allows parents to easily download and print learning content for their children, which makes them inconvenient.

[0618] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0619] In this invention, the server includes a terminal means for inputting basic information about the child, an analysis means for receiving the basic information about the child from the terminal means and analyzing the information, a generation means for generating customized learning content using a generative AI model based on the analyzed information, a transmission means for transmitting the generated learning content to the terminal means, a display means for displaying the learning content received by the terminal means and providing it to the user, and a means for the terminal means to provide the option to download or print the learning content in response to a user's request. This allows for the provision of personalized learning content according to the child's age and interests, and for parents to easily download and print the content.

[0620] "Terminal means" is a device for inputting basic information about a child and transmitting that information to a server.

[0621] The "analysis means" is a function that analyzes the received basic information about the child and determines the requirements for generating appropriate learning content based on that data.

[0622] The "generation means" is a function that uses a generative AI model based on the analysis results to create customized learning content suitable for children.

[0623] The "transmission means" is a function that transmits the generated study content to the terminal means.

[0624] The "display means" is a function that displays and provides the study content received by the terminal means to the user.

[0625] The "means for providing download and print options" is a function that allows the terminal means to download or print the generated study content according to the user's request.

[0626] "Educational Materials" refers generally to content that is individually customized using generative AI models to support learning.

[0627] "Unacquired vocabulary" refers to words and phrases that a child has not yet learned or fully understood.

[0628] A "generative AI model" is an artificial intelligence model that generates optimal learning content based on input data.

[0629] This invention is a system that generates and provides individually customized learning content based on basic information about children. This system is realized by the following steps.

[0630] Basic system configuration

[0631] Children's information input method

[0632] The terminal provides a form for the user (parent) to input basic information about their child, including the child's age, topics of interest, and current learning status (e.g., vocabulary that has not yet been mastered).

[0633] Data transmission and analysis

[0634] The terminal device sends the input data to the server, which analyzes the received data and determines the requirements based on the child's interests and learning status. Based on this analysis, for example, it can suggest space-related educational materials to a child who likes space.

[0635] Generating learning content

[0636] The server uses the analysis results to generate learning content appropriate for the child using a generative AI model. The generative AI model provides questions and learning materials tailored to the child's interests and level of proficiency. For example, for a 6-year-old child interested in animals, it would generate content that teaches them about different animal species and their characteristics.

[0637] Submitting and Viewing Learning Content

[0638] The server transmits the generated learning content to the terminal device, which displays the received learning content on the screen and provides it to the user. The terminal device also provides the user with the option to download or print the content, depending on the user's request.

[0639] Hardware and software used

[0640] Hardware: Smartphones, tablets, personal computers

[0641] Software: Python scripts, Flask (for the server side), generative AI models (e.g., OpenAI GPT-3)

[0642] Data processing and calculation

[0643] Data collection: Parents enter their child's age, interests, and learning status into a dedicated device.

[0644] Data transmission: Data is transmitted from the terminal means to the server.

[0645] Data analysis: Based on the received data, the server inputs the data into a generative AI model to generate optimal learning content.

[0646] Content generation: Generated content is generated by the server and sent to the terminal means.

[0647] Content display: Displays the learning content generated on the terminal means and provides the user with the option to download or print.

[0648] Specific examples

[0649] Example 1

[0650] Child: 6 years old

[0651] Interests: Animals

[0652] Learning level: Intermediate

[0653] "Intermediate-level content tailored for 6-year-olds who love animals"

[0654] Example 2

[0655] Child: 7 years old

[0656] Interests: Science

[0657] Learning level: Advanced

[0658] "Advanced level teaching materials specifically designed for 7-year-old science-loving children"

[0659] Prompt Sentence Examples

[0660] "Intermediate-level content tailored for 6-year-olds who love animals"

[0661] "Advanced level teaching materials specifically designed for 7-year-old science-loving children"

[0662] This makes it possible to provide personalized learning content tailored to each child's age, interests, and learning level.

[0663] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0664] Step 1:

[0665] The user (parent) enters basic information about the child (age, interests, learning status, etc.) into the terminal means. The terminal means collects this input data and converts it into JSON format data. Specifically, the parent enters the required information into a form using a dedicated application.

[0666] input:

[0667] Children's age, interests, and learning status

[0668] output:

[0669] Basic information data in JSON format

[0670] Step 2:

[0671] The terminal sends the collected data in JSON format to the server using an HTTP POST request, and the server waits to analyze the received data.

[0672] input:

[0673] Basic information data in JSON format

[0674] output:

[0675] HTTP POST request

[0676] Step 3:

[0677] The server analyzes the received basic information about the child. Specifically, it parses the JSON format data to determine the child's interests and learning status. The analyzed data is then converted into a format suitable for the generative AI model.

[0678] input:

[0679] Basic information about the child passed to the server

[0680] output:

[0681] Data in a format suitable for generative AI models

[0682] Step 4:

[0683] The server generates customized learning content using a generative AI model. Based on the analysis results, the server inputs corresponding prompt sentences into the generative AI model. The generative AI model generates optimal learning content based on the prompt sentences.

[0684] input:

[0685] Data in a format suitable for generative AI models

[0686] Prompt statement

[0687] output:

[0688] Customized learning content

[0689] Step 5:

[0690] The server transmits the generated customized learning content to the terminal means, again using an HTTP POST request or other suitable communication means.

[0691] input:

[0692] Customized learning content

[0693] output:

[0694] HTTP POST request or other communication method

[0695] Step 6:

[0696] The terminal displays the received learning content on the screen, and the user (parent) can check the displayed content and use the option to download or print the content if necessary.

[0697] input:

[0698] Customized learning content received

[0699] output:

[0700] On-screen learning content

[0701] Download and print options

[0702] Step 7:

[0703] The user utilizes the download and print options to obtain the learning content in a format that can be physically stored or used. Depending on the user's selection, the terminal means performs a specific action (downloading a file or issuing a print command).

[0704] input:

[0705] On-screen learning content

[0706] User's choice (download or print)

[0707] output:

[0708] Downloaded files or printed materials

[0709] This ensures that learning content that is customized to a child's age, interests, and learning level is generated and delivered efficiently and effectively.

[0710] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0711] The present invention is a system that generates and provides individually customized learning content based on basic information about children and emotional information about users. This system is realized by the following steps.

[0712] Basic system configuration

[0713] Children's information input method

[0714] The device provides a form for users (parents) to enter basic information about their children, such as their age, interests (e.g., space, animals), and current learning status (e.g., unlearned vocabulary).

[0715] Data transmission and analysis

[0716] The terminal sends the input data to the server. The data is structured in, for example, JSON or XML format.

[0717] The server analyzes the data received from the terminal, which may include, for example, validating the data and storing it in a database.

[0718] Acquiring and analyzing user emotion information

[0719] The device uses an emotion engine to acquire emotion data from the user's facial expressions and voice information, including emotions such as joy, sadness, surprise, and anger.

[0720] The terminal transmits the acquired emotion data to the server.

[0721] The server analyzes the emotion data provided by the emotion engine and evaluates the user's emotional state.

[0722] Generating learning content

[0723] The server uses the analysis results to generate learning content appropriate for the child using a generative AI model. The generative AI model adjusts questions and learning materials according to the child's interests and proficiency, as well as the user's emotional state. For example, if the user is relaxed, it will generate slightly more difficult questions, and if they are stressed, it will provide easier questions and interactive learning materials.

[0724] Submitting and Viewing Learning Content

[0725] The server then sends the generated learning content to the device, which then displays the received learning content on its screen and provides the user with the option to download or print it, allowing parents and children to easily access the content.

[0726] Specific examples

[0727] Example 1: A 5-year-old child who loves space

[0728] The user enters the information "Age: 5 years old" and "Interest: Space" into the terminal and sends it. The terminal then sends this information to the server.

[0729] The server analyzes the input data and generates "simple space-related questions" and "coloring pages to learn the names of stars."

[0730] The server transmits the generated learning content to the terminal.

[0731] At the same time, the device uses an emotion engine to obtain emotional information while the child is learning. For example, if the child is having fun, that information is sent to the server, and challenging questions are added to the next learning content.

[0732] The terminal displays the content and gives the user the option to download or print.

[0733] Example 2: A 6-year-old child who loves animals

[0734] The user enters the information "Age: 6 years old" and "Interest: animals" into the terminal and sends it. The terminal then sends this information to the server.

[0735] The server analyzes the input data and generates questions about animal types and their characteristics, as well as puzzles that teach about the habitats of each animal.

[0736] The server transmits the generated learning content to the terminal.

[0737] At the same time, the device uses an emotion engine to capture the child's emotions in real time. For example, if the child is tired, that information is sent to the server, and the device will provide a relaxing activity for the next learning content.

[0738] The terminal displays the content and gives the user the option to download or print.

[0739] In this way, by combining a generative AI model with an emotion engine, this system provides customized learning content tailored to children's interests, proficiency levels, and even emotional states, creating an environment where children can learn while having fun.

[0740] The processing flow will be explained below.

[0741] Step 1:

[0742] The device displays a form for the user (parent) to enter basic information about their child, including fields such as the child's age, topics of interest (e.g., space, animals), and current learning status (e.g., unlearned vocabulary).

[0743] Step 2:

[0744] The user enters basic information about the child into the form and clicks the submit button.

[0745] Step 3:

[0746] The terminal sends the input data to the server. The data is structured in, for example, JSON or XML format.

[0747] Step 4:

[0748] The server analyzes the data received from the terminal, which may include, for example, validating the data and storing it in a database.

[0749] Step 5:

[0750] The device runs an emotion engine and captures facial expressions and voices while the user is monitoring their child's learning, thereby obtaining the user's emotion data.

[0751] Step 6:

[0752] The terminal transmits the acquired emotion data to the server. The emotion data includes various emotions of the user, such as joy, anger, sadness, and pleasure.

[0753] Step 7:

[0754] The server analyzes the emotion data provided by the emotion engine to assess the user's emotional state, for example, determining whether the user is stressed or relaxed.

[0755] Step 8:

[0756] The server uses the analysis results to provide the necessary parameters (e.g., topics of interest, proficiency, emotional state, etc.) to the generative AI model, instructing it to generate customized learning content.

[0757] Step 9:

[0758] Based on given parameters, the generative AI model generates customized learning content, such as simple questions about planets in space or a coloring book to learn the names of stars.

[0759] Step 10:

[0760] The server converts the generated learning content into a user-friendly format, such as HTML or PDF, before sending it to the device.

[0761] Step 11:

[0762] The server transmits the prepared learning content to the terminal.

[0763] Step 12:

[0764] The device then displays the received learning content on its screen, which may involve, for example, rendering an HTML page or launching a PDF viewer.

[0765] Step 13:

[0766] The terminal provides users with download and print options, allowing them to download or print the learning content as needed.

[0767] Step 14:

[0768] After the learning session ends, the device will start the emotion engine again and capture the final emotional state.

[0769] Step 15:

[0770] The device sends the final emotion data to the server, which stores it in a database for reference during the next learning session.

[0771] In this way, customized learning content is provided to children, taking into account the user's emotional state in the process, making learning more engaging and effective for children.

[0772] Example 2

[0773] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0774] Conventional learning content generation systems have not adequately provided content tailored to each child's individual interests and level of proficiency. Furthermore, there is no mechanism for customizing learning content that takes into account the user's emotional state, making it difficult to provide effective learning support. This makes it difficult for children to become interested in learning, resulting in reduced learning effectiveness.

[0775] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0776] In this invention, the server includes terminal means for inputting basic information about the child, analysis means for receiving the basic information about the child from the terminal means and analyzing the information, generation means for generating customized learning content using a generative AI model based on the analyzed information and the user's emotional information, transmission means for transmitting the generated learning content to the terminal means, display means for displaying the learning content received by the terminal means and providing it to the user, an emotion engine for acquiring emotional information from the user's facial expressions and voice, and means for transmitting the emotional information to the server and analyzing it. This makes it possible to provide individually customized learning content based on the child's interests and proficiency, and further take the user's emotional state into consideration, thereby achieving a more effective and engaging learning experience.

[0777] The "terminal means" is a device used by the user to input basic information and emotional information about the child and transmit that information to the server.

[0778] The "analysis means" is a means for analyzing the basic information and emotional information of the child received from the terminal means and generating learning content based on the results.

[0779] A "generative AI model" is an artificial intelligence model that generates learning content suitable for children based on analyzed information.

[0780] "Generative means" means a means for creating customized learning content using a generative AI model.

[0781] The "transmission means" is a means for transmitting the generated study content to the terminal means.

[0782] The "display means" refers to a means for visually presenting the study content received by the terminal means to the user.

[0783] The "emotion engine" is an engine that acquires emotion data from the user's facial expressions and voice information and evaluates their emotional state.

[0784] "Emotion information" is information about the emotional state analyzed based on data acquired from the user's facial expressions and voice.

[0785] The present invention is a system for generating and providing individually customized learning content based on basic information about a child and emotional information about a user. The following describes an embodiment of this system.

[0786] Basic system configuration

[0787] Children's information input method

[0788] The device provides a form for the user to enter basic information about the child, including the child's age, interests, current level of proficiency, etc. For example, the user can open a web browser, enter this information into the form, and click the submit button.

[0789] Data transmission and analysis

[0790] The terminal sends the entered data to the server in JSON or XML format. Specifically, the data is sent using an HTTP POST request. The server analyzes the received data, first validating it and checking that all required data is included. It then saves it in a database and waits for the analysis results. The Python pandas library can be used for analysis.

[0791] Acquiring and analyzing user emotion information

[0792] The device uses an emotion engine to acquire emotion data from the user's facial expressions and voice. For example, a webcam or microphone is used to collect the user's face and voice, which are then analyzed by the emotion engine. The acquired emotion data is then sent to the server again using an HTTP POST request. The server analyzes the emotion data provided by the emotion engine and evaluates the user's emotional state. A machine learning model can be used for this analysis.

[0793] Generating learning content

[0794] The server uses a generative AI model based on the child's basic information and the user's emotional data to generate appropriate learning content. For example, a generative AI model such as GPT-3 can be used, and a prompt such as "5-year-old child, interested in space" can be created and input into the model. Based on this prompt, simple questions and learning materials are generated.

[0795] Submitting and Viewing Learning Content

[0796] The server sends the generated learning content to the device, which then displays the received content on the screen and provides the user with the option to download or print it. For example, this can be achieved by displaying the content on a web page with download and print buttons.

[0797] Specific examples

[0798] Example 1: A 5-year-old child who loves space

[0799] The user enters information such as "Age: 5 years old" and "Interest: Space" into the device and sends it. The device then sends this to the server, which analyzes the input data and generates "easy space-related questions" and "coloring pages to learn the names of stars." The server then sends the generated learning content to the device, which then displays the content. In addition, an emotion engine is used to obtain emotional information while the user is learning, and if the user is enjoying the learning experience, this information is sent to the server, and more challenging questions are added to the next learning content.

[0800] Example 2: A 6-year-old child who loves animals

[0801] The user enters information such as "Age: 6 years old" and "Interest: animals" into the device and sends it. The device then sends this to the server, which analyzes the input data and generates questions about animal species and their characteristics, as well as puzzles to learn about each animal's habitat. The server then sends the generated learning content to the device, which then displays it. The device also uses an emotion engine to obtain the child's emotions in real time and offers relaxing activities if the child is tired.

[0802] Examples of prompt statements

[0803] 1. "My child is 5 years old and is interested in space. What educational content can you provide him?"

[0804] 2. "What materials would be appropriate for a 6-year-old child to learn about animals?"

[0805] In this way, by combining a generative AI model with an emotion engine, this system can customize and provide learning content according to a child's interests, proficiency level, and even emotional state.

[0806] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0807] Step 1: Enter your child's information

[0808] The user uses the device to enter basic information about their child. Specifically, the user opens a web browser and enters the child's age, interests, and current level of proficiency in the form that appears. This input form includes text boxes and drop-down menus, and once the input is complete, the information is sent by clicking the submit button.

[0809] Input: Child's age, topics of interest, current level of proficiency

[0810] Output: Structured data (e.g., JSON format)

[0811] Step 2: Sending data

[0812] The terminal sends the input structured data to the server. Specifically, the data is sent using an HTTP POST request. This request includes the user's input information.

[0813] Input: Structured data (e.g., JSON format)

[0814] Output: Send data to the server

[0815] Step 3: Analyze the data

[0816] The server analyzes the received data. Specifically, it first validates the data to check whether it contains all the required data. It then saves it in the database and waits for the analysis results. This analysis can be done using Python's pandas library or SQL.

[0817] Input: Data submitted by the user

[0818] Output: Data validation results, saved to database

[0819] Step 4: Obtaining user emotion information

[0820] The device uses an emotion engine to acquire emotion data from the user's facial expressions and voice in real time. For example, it uses a webcam or microphone to collect the user's face and voice and analyzes them. This analysis is performed by the emotion engine.

[0821] Input: User's facial expressions and voice information

[0822] Output: Emotion data (e.g., happiness, sadness)

[0823] Step 5: Send and analyze emotion data

[0824] The device sends the acquired emotion data to the server, again using an HTTP POST request. The server analyzes the emotion data provided by the emotion engine and evaluates the user's emotional state. A machine learning model can be used for the analysis.

[0825] Input: Emotion data

[0826] Output: Evaluation of the user's emotional state

[0827] Step 6: Generate learning content

[0828] The server uses a generative AI model based on the child's basic information and the user's emotional data to generate appropriate learning content. Specifically, the server creates a prompt for the generative AI model: "A 5-year-old child interested in space." This prompt is then input into the model. Based on this prompt, simple questions and learning materials are generated.

[0829] Input: Basic information about the child, user's emotional data

[0830] Output: Generated learning content

[0831] Step 7: Submit and view your learning content

[0832] The server sends the generated learning content to the device. Specifically, it sends the content using an HTTP response. The device displays the received content on the screen and offers the user the option to download or print it. Specifically, this is achieved by displaying the content on a web page and providing download and print buttons.

[0833] Input: Generated learning content

[0834] Output: The learning content displayed to the user, with options to download and print

[0835] (Application example 2)

[0836] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0837] In conventional factories, only standardized education and training has been provided to improve individual worker capabilities and work efficiency. However, because optimal support varies depending on the worker's level of proficiency and emotional state, the effectiveness of a one-size-fits-all approach has been limited. In particular, in work environments where workers are prone to fatigue and stress, individually customized support is important. The objective of this invention is to provide a system that improves worker efficiency and satisfaction by providing individually customized support content based on the worker's basic information and emotional information.

[0838] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0839] In this invention, the server includes terminal means for inputting basic information about the worker, analysis means for receiving the basic information about the worker sent from the terminal means and analyzing the information, emotion engine means for acquiring emotional information about the worker, analysis means for receiving the emotional information sent from the emotion engine means and analyzing the information, generation means for generating customized assistance content using a generative AI model based on the analyzed basic information and emotional information, transmission means for transmitting the generated assistance content to the terminal means, and display means for displaying the assistance content received by the terminal means and providing it to the worker. This makes it possible to provide optimal work assistance and relaxation content based on the basic information and real-time emotional information of the worker.

[0840] "Basic information about workers" refers to information about the individual characteristics of workers, such as their age, work experience, specialties, and problems.

[0841] "Terminal means" refers to an electronic device for inputting and transmitting basic information about workers.

[0842] The "analysis means" is a processing device or software for receiving and analyzing information sent from the terminal means.

[0843] The "emotion engine means" is a device or software that uses sensors such as a camera and a microphone to obtain emotional information from the facial expressions and voices of workers.

[0844] The "generation means" refers to a processing device or software that uses a generative AI model to generate customized assistance content based on the analyzed basic information and emotional information.

[0845] The "transmission means" is a communication device or software for transmitting the generated assistance content to the terminal means.

[0846] The "display means" is a device or software that displays the support content received by the terminal means on a screen and provides it to the worker.

[0847] A "generative AI model" is a model that uses machine learning algorithms to automatically generate content tailored to a specific purpose based on input data.

[0848] "Support content" is information for work support and relaxation that is individually customized based on the worker's basic information and emotional state.

[0849] The present invention is a system for providing individually customized support content based on basic information and emotional information of a worker. Specific embodiments of the present invention will be described in detail below.

[0850] Basic system configuration

[0851] Employee information input method

[0852] The terminal means provides a form for inputting basic information about the worker. The basic information about the worker includes age, work experience, specialty work, current problems, etc. For example, information such as "Age: 35 years old," "Work experience: 10 years," "Specialty work: assembly," and "Problem: inspection work takes a long time" is input.

[0853] Data transmission and analysis

[0854] The terminal means sends the input data to the server. The data is structured in, for example, JSON or XML format. The server analyzes the data received from the terminal. Analysis includes data validation and saving to a database.

[0855] Acquiring and analyzing worker emotion information

[0856] The emotion engine means acquires emotion data from the worker's facial expressions and voice information using a camera and microphone mounted on the terminal means. The emotion information includes fatigue, stress, concentration, etc. The terminal means transmits the acquired emotion data to the server. The server analyzes the emotion data provided by the emotion engine means and evaluates the worker's emotional state.

[0857] Support content generation

[0858] The server uses the analysis results to generate support content tailored to the worker using a generative AI model. The generative AI model adjusts the support content based on the worker's basic information and emotional state. For example, if the worker is tired, it will suggest relaxing stretches, and if the worker is working and requires concentration, it will provide specific advice to improve efficiency.

[0859] Sending and displaying support content

[0860] The server transmits the generated support content to the terminal means. The terminal means displays the received support content on a screen and provides it to the worker. For example, the display may say, "Please perform relaxing stretches for five minutes."

[0861] Hardware and software used

[0862] Hardware: Camera, microphone, and display attached to the robot

[0863] software:

[0864] Emotion engine: Software that processes data from the camera and microphone to assess emotional state

[0865] Generative AI model: A machine learning model that generates optimal support content based on basic and emotional information about the worker.

[0866] Server: API that analyzes data and generates support content

[0867] Specific examples

[0868] Example 1: Content creation flow for worker "Factory Worker A"

[0869] The factory's robot AI reads the facial expression of "Worker A" and detects that he is tired.

[0870] The data is analyzed on the server and content is generated that suggests relaxing stretches for "Worker A."

[0871] The robot calls out, "Mr. A, you look tired. Would you like to try stretching for five minutes?"

[0872] Example prompt sentence:

[0873] Design a system in which a factory robot analyzes the emotions of "Factory Worker A" from his facial expressions and voice, and suggests relaxing stretches to the worker. Specifically, the system will include a process in which the worker's basic information is input, emotional data is acquired in real time using an emotion engine, customized support content is generated using a generative AI model, and finally the robot provides the support content on a screen or via voice.

[0874] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0875] Step 1:

[0876] The user inputs basic information about the worker on the terminal and submits it. The input data includes age, work experience, specialties, problems, etc. This information is structured in JSON or XML format and sent to the server.

[0877] Input: Basic information of the worker (age, work experience, specialty, problems)

[0878] Output: JSON or XML data sent to the server

[0879] Step 2:

[0880] The server analyzes the received worker's basic information, performs data validation (format check, missing value check, etc.), and stores the data in the database if it is in the correct format.

[0881] Input: Basic information about the worker (JSON or XML data)

[0882] Output: Worker information stored in the database

[0883] Step 3:

[0884] Using the camera and microphone installed in the terminal, the emotion engine means acquires emotion data from the worker's facial expressions and voice information, using facial recognition and voice analysis of the worker.

[0885] Input: Camera video, audio data

[0886] Output: Emotion data (e.g., tiredness, stress, concentration)

[0887] Step 4:

[0888] The device sends the acquired emotion data to the server, which in turn structures the data in JSON or XML format.

[0889] Input: Emotion data (data obtained in real time)

[0890] Output: JSON or XML data sent to the server

[0891] Step 5:

[0892] The server analyzes the emotion data provided by the emotion engine means and uses the analysis results to evaluate the worker's emotional state.

[0893] Input: Emotion data (JSON or XML data)

[0894] Output: Evaluation result (e.g., worker's current emotional state)

[0895] Step 6:

[0896] The server uses a generative AI model based on the analysis results (basic information and emotional state of the worker) to generate customized support content. The generative AI model creates appropriate support content according to the worker's situation.

[0897] Input: Basic information and emotional state (evaluation results)

[0898] Output: Generated assistance content

[0899] Step 7:

[0900] The server sends the generated support content to the device in HTML or JSON format, which is suitable for display.

[0901] Input: Generated assistance content

[0902] Output: Support content (HTML or JSON data) sent to the device

[0903] Step 8:

[0904] The device then displays the received support content on its screen and provides it to the worker, such as advice on stretching techniques to relax or improving work efficiency.

[0905] Input: Received support content (HTML or JSON data)

[0906] Output: The display content provided to the worker

[0907] 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.

[0908] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. 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 voice, text data indicating text, and image data indicating an image is also input. 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.

[0909] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0910] [Third embodiment]

[0911] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0912] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0913] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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).

[0914] 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.

[0915] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0916] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0917] 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.

[0918] 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.

[0919] 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 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.

[0920] 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.

[0921] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0922] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0923] The present invention is a system that generates and provides individually customized learning content based on basic information about children. This system is realized by the following steps.

[0924] Basic system configuration

[0925] Children's information input method

[0926] The device provides a form for users (parents) to enter basic information about their children, such as their age, interests (e.g., space, animals), and current learning status (e.g., unlearned vocabulary).

[0927] Data transmission and analysis

[0928] The device sends the input data to the server, which analyzes the received data and determines the requirements based on the child's interests and learning status. This analysis can determine, for example, that space-related questions are appropriate for a child who likes space.

[0929] Generating learning content

[0930] The server uses the analysis results to generate learning content appropriate for the child using a generative AI model. The generative AI model provides questions and learning materials tailored to the child's interests and level of proficiency. For example, for a 5-year-old child interested in space, it generates a coloring book that teaches the names of planets and stars in the solar system.

[0931] Submitting and Viewing Learning Content

[0932] The server then sends the generated learning content to the device, which then displays the received learning content on its screen and provides the user with the option to download or print it, allowing parents and children to easily access the content.

[0933] Specific examples

[0934] Example 1: A 5-year-old child who loves space

[0935] The user enters the information "Age: 5 years old" and "Interest: Space" into the terminal and sends it. The terminal then sends this information to the server.

[0936] The server analyzes the input data and generates "simple space-related questions" and "coloring pages to learn the names of stars."

[0937] The server transmits the generated learning content to the terminal.

[0938] The terminal displays the content and gives the user the option to download or print.

[0939] Example 2: A 6-year-old child who loves animals

[0940] The user enters the information "Age: 6 years old" and "Interest: animals" into the terminal and sends it. The terminal then sends this information to the server.

[0941] The server analyzes the input data and generates questions about animal types and their characteristics, as well as puzzles that teach about the habitats of each animal.

[0942] The server transmits the generated learning content to the terminal.

[0943] The terminal displays the content and gives the user the option to download or print.

[0944] In this way, this system uses a generative AI model to provide customized learning content tailored to children's interests and proficiency levels, creating an environment where children can learn while having fun.

[0945] The processing flow will be explained below.

[0946] Step 1:

[0947] The device displays a form for the user (parent) to enter basic information about their child, including fields such as the child's age, topics of interest (e.g., space, animals), and current learning status (e.g., unlearned vocabulary).

[0948] Step 2:

[0949] The user enters basic information about the child into the form and clicks the submit button.

[0950] Step 3:

[0951] The terminal sends the input data to the server. The data is structured in, for example, JSON or XML format.

[0952] Step 4:

[0953] The server analyzes the data received from the terminal, which may include, for example, validating the data and storing it in a database.

[0954] Step 5:

[0955] The server determines the child's interests and proficiency based on the analysis results. For example, if the input interest topic is "space" and the child is 5 years old, it generates space-related learning content.

[0956] Step 6:

[0957] The server passes necessary parameters (e.g., topics of interest and proficiency) to the generative AI model, instructing it to generate customized learning content.

[0958] Step 7:

[0959] Based on given parameters, the generative AI model generates customized learning content, such as simple questions about planets in space or a coloring book to learn the names of stars.

[0960] Step 8:

[0961] The server converts the generated learning content into a user-friendly format, such as HTML or PDF, before sending it to the device.

[0962] Step 9:

[0963] The server transmits the prepared learning content to the terminal.

[0964] Step 10:

[0965] The device then displays the received learning content on its screen, which may involve, for example, rendering an HTML page or launching a PDF viewer.

[0966] Step 11:

[0967] The terminal provides users with download and print options, allowing them to download or print the learning content as needed.

[0968] In this way, customized learning content is provided to the child, making it interesting and effective for the child to learn.

[0969] Example 1

[0970] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0971] Conventional educational systems have faced the challenge of providing learning content tailored to each child's individual interests and proficiency level. In particular, they were unable to automatically generate learning materials tailored to each child's individual characteristics, resulting in a decline in learning effectiveness. Furthermore, preparing content manually required a great deal of time and effort, making it difficult to provide efficient learning support.

[0972] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0973] In this invention, the server includes a terminal means for inputting basic information about the child, an analysis means for receiving the basic information about the child from the terminal means and analyzing the information, a generation means for generating prompt sentences using a generative AI model based on the analyzed information to generate customized learning content, a transmission means for transmitting the generated learning content to the terminal means, and a display means for displaying the learning content received by the terminal means and providing it to the user in a downloadable or printable format. This enables the automatic generation and provision of customized learning content tailored to each child's individual interests and proficiency.

[0974] "Terminal means" means a device or system for inputting basic information about a child.

[0975] "Analysis means" refers to a device or system that receives the basic information about the child sent from the terminal means and analyzes that information.

[0976] "Generative AI model" means an artificial intelligence model that generates prompt sentences based on analyzed information and generates individually customized learning content.

[0977] "Generation means" refers to a device or system that generates customized learning content using a generative AI model based on the information analyzed by the analysis means.

[0978] "Transmission means" refers to a device or system that transmits the generated study content to the terminal means.

[0979] "Display means" refers to a device or system that displays the study content received by the terminal means and provides it to the user in a form that can be downloaded or printed.

[0980] "Prompt sentence" means an instruction sentence that a generative AI model uses as a reference when generating learning content appropriate for children.

[0981] MODE FOR CARRYING OUT THE INVENTION

[0982] The present invention is a system for generating and providing individually customized learning content based on basic information about children. Next, the overall configuration and specific operation of the system will be described.

[0983] Basic system configuration

[0984] The system consists of the following main components:

[0985] 1. Terminal means

[0986] 2. Analysis method

[0987] 3. Generative means (including generative AI models)

[0988] 4. Transmission Method

[0989] 5. Display means

[0990] Terminal means

[0991] The device provides an input form for the user (parent) to enter basic information about their child. This form includes fields for entering information such as the child's age, topics of interest (e.g., space, animals), current learning status (e.g., unlearned vocabulary), etc. When the user enters the information and clicks the submit button, this data is sent from the device to the server.

[0992] Analysis means

[0993] The server receives the child's basic information sent from the terminal means. The received data is deserialized and compared with the database. This comparison allows the server to analyze the requirements for appropriate learning content based on the child's interests and learning status. For example, based on the input data "Age: 6 years old" and "Interest: animals," the server determines that it is appropriate to generate basic questions and teaching materials related to animals.

[0994] generation means

[0995] The server generates appropriate learning content using a generative AI model (e.g., GPT-3) based on the analysis results. The generator operates as a server-side application program, sending prompt sentences to the generative AI model and receiving the generated content.

[0996] Examples of prompts:

[0997] "Create questions for 6-year-olds to help them learn about animal characteristics. These could include simple questions about animal types, characteristics, and habitats. Examples include a quiz where children are asked to look at a picture of an animal and name it, or choose its habitat."

[0998] Based on the prompt, the generative AI model generates customized learning content tailored to the child's interests and proficiency level.

[0999] Transmission method

[1000] The server sends the generated learning content to the terminal. The generated data is serialized in JSON format and sent as an HTTP response. The terminal receives this data and proceeds to the next step.

[1001] Display means

[1002] The device deserializes the learning content received from the server and displays it to the user. The displayed content also provides options for downloading or printing so that children can use it directly for their studies. This creates an environment where children and parents can easily access learning content.

[1003] Specific examples

[1004] Example 1: A 5-year-old child who loves space

[1005] The user enters information such as "Age: 5 years old" and "Interest: Space" into the device and submits it. The device then sends this information to the server. The server analyzes the input data and generates "simple space-related questions" and "coloring pages to learn the names of stars." The server then sends the generated learning content to the device. The device then displays the content and gives the user the option to download or print it.

[1006] Example 2: A 6-year-old child who loves animals

[1007] The user enters information such as "Age: 6 years old" and "Interest: Animals" into the device and submits it. The device then sends this information to the server. The server analyzes the input data and generates questions about animal species and their characteristics, as well as puzzles to learn about the habitats of each animal. The server then sends the generated learning content to the device. The device then displays the content and gives the user the option to download or print it.

[1008] As described above, this system uses a generative AI model to provide customized learning content tailored to children's interests and proficiency levels, allowing children to enjoy learning and parents to easily acquire and use the content.

[1009] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1010] Step 1: Enter your child's basic information

[1011] The user enters basic information about their child into an input form displayed on the device. Input items include the child's age, interests (e.g., space, animals), learning status, etc. The input data is converted into JSON format. This data is input by the user by entering accurate information.

[1012] Input: Child's age, interest topic, learning status

[1013] Output: Basic information about the child in JSON format

[1014] Specific behavior:

[1015] The age input field has a numeric check.

[1016] There is a drop-down menu of topics of interest.

[1017] A text area is provided for the learning status.

[1018] Step 2: Sending data

[1019] The device sends the entered basic information about the child to the server. Specifically, after the submit button is pressed, JSON data is sent to the server as an HTTP POST request.

[1020] Input: Basic information data entered by the user in JSON format

[1021] Output: HTTP POST request to the server

[1022] Specific behavior:

[1023] The user clicks the submit button.

[1024] Form data is collected and converted to JSON format.

[1025] Data is sent asynchronously using AJAX.

[1026] Step 3: Receiving and analyzing data

[1027] The server receives the child's basic information data sent from the device. The received data is deserialized and analyzed against a database (e.g., MySQL). As a result of the analysis, requirements based on the child's interests and learning progress are determined.

[1028] Input: Basic information data in JSON format sent from the terminal

[1029] Output: Learning content requirements based on the analysis results

[1030] Specific behavior:

[1031] Deserialize the received data and convert it to the internal data format.

[1032] Execute the corresponding query on the database to retrieve the relevant data.

[1033] Based on the acquired data, the analysis engine determines the requirements for learning content.

[1034] Step 4: Prompt generation and content generation

[1035] The server sends prompts to a generative AI model (e.g., GPT-3) based on the analysis results, and generates appropriate learning content. The generated content is temporarily stored on the server.

[1036] Input: Prompt text based on the analysis result

[1037] Output: Customized learning content from generative AI models

[1038] Examples of prompts:

[1039] "Create questions for 6-year-olds to help them learn about animal characteristics. These could include simple questions about animal types, characteristics, and habitats. Examples include a quiz where children are asked to look at a picture of an animal and name it, or choose its habitat."

[1040] Specific behavior:

[1041] Generates a prompt string based on the parsed data used to construct the prompt statement.

[1042] Send an HTTP request to the API endpoint of the generative AI model.

[1043] Receive a response from the generative AI model.

[1044] Step 5: Submit your learning content

[1045] The server serializes the generated learning content into JSON format and sends it to the terminal as an HTTP response.

[1046] Input: Customized learning content from a generative AI model

[1047] Output: Learning content as an HTTP response to the device

[1048] Specific behavior:

[1049] Serialize the generated content into JSON format.

[1050] Create an HTTP response object and send it to the device.

[1051] Step 6: View learning content

[1052] The device deserializes the learning content received from the server and displays it to the user, offering the user the option to download or print the content.

[1053] Input: Learning content received as an HTTP response from the server

[1054] Output: The learning content that users see, along with download and print options

[1055] Specific behavior:

[1056] Deserialize the received data.

[1057] The data is applied to an HTML template and displayed in the user interface.

[1058] Enable buttons for downloading and printing.

[1059] (Application example 1)

[1060] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1061] Conventional learning content provision systems have had the problem of being unable to provide content that appropriately reflects differences in children's ages and interests, and are only able to provide uniform educational materials. Furthermore, there is no system that allows parents to easily download and print learning content for their children, which makes them inconvenient.

[1062] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1063] In this invention, the server includes a terminal means for inputting basic information about the child, an analysis means for receiving the basic information about the child from the terminal means and analyzing the information, a generation means for generating customized learning content using a generative AI model based on the analyzed information, a transmission means for transmitting the generated learning content to the terminal means, a display means for displaying the learning content received by the terminal means and providing it to the user, and a means for the terminal means to provide the option to download or print the learning content in response to a user's request. This allows for the provision of personalized learning content according to the child's age and interests, and for parents to easily download and print the content.

[1064] "Terminal means" is a device for inputting basic information about a child and transmitting that information to a server.

[1065] The "analysis means" is a function that analyzes the received basic information about the child and determines the requirements for generating appropriate learning content based on that data.

[1066] The "generation means" is a function that uses a generative AI model based on the analysis results to create customized learning content suitable for children.

[1067] The "transmission means" is a function that transmits the generated study content to the terminal means.

[1068] The "display means" is a function that displays and provides the study content received by the terminal means to the user.

[1069] The "means for providing download and print options" is a function that allows the terminal means to download or print the generated study content according to the user's request.

[1070] "Educational Materials" refers generally to content that is individually customized using generative AI models to support learning.

[1071] "Unacquired vocabulary" refers to words and phrases that a child has not yet learned or fully understood.

[1072] A "generative AI model" is an artificial intelligence model that generates optimal learning content based on input data.

[1073] This invention is a system that generates and provides individually customized learning content based on basic information about children. This system is realized by the following steps.

[1074] Basic system configuration

[1075] Children's information input method

[1076] The terminal provides a form for the user (parent) to input basic information about their child, including the child's age, topics of interest, and current learning status (e.g., vocabulary that has not yet been mastered).

[1077] Data transmission and analysis

[1078] The terminal device sends the input data to the server, which analyzes the received data and determines the requirements based on the child's interests and learning status. Based on this analysis, for example, it can suggest space-related educational materials to a child who likes space.

[1079] Generating learning content

[1080] The server uses the analysis results to generate learning content appropriate for the child using a generative AI model. The generative AI model provides questions and learning materials tailored to the child's interests and level of proficiency. For example, for a 6-year-old child interested in animals, it would generate content that teaches them about different animal species and their characteristics.

[1081] Submitting and Viewing Learning Content

[1082] The server transmits the generated learning content to the terminal device, which displays the received learning content on the screen and provides it to the user. The terminal device also provides the user with the option to download or print the content, depending on the user's request.

[1083] Hardware and software used

[1084] Hardware: Smartphones, tablets, personal computers

[1085] Software: Python scripts, Flask (for the server side), generative AI models (e.g., OpenAI GPT-3)

[1086] Data processing and calculation

[1087] Data collection: Parents enter their child's age, interests, and learning status into a dedicated device.

[1088] Data transmission: Data is transmitted from the terminal means to the server.

[1089] Data analysis: Based on the received data, the server inputs the data into a generative AI model to generate optimal learning content.

[1090] Content generation: Generated content is generated by the server and sent to the terminal means.

[1091] Content display: Displays the learning content generated on the terminal means and provides the user with the option to download or print.

[1092] Specific examples

[1093] Example 1

[1094] Child: 6 years old

[1095] Interests: Animals

[1096] Learning level: Intermediate

[1097] "Intermediate-level content tailored for 6-year-olds who love animals"

[1098] Example 2

[1099] Child: 7 years old

[1100] Interests: Science

[1101] Learning level: Advanced

[1102] "Advanced level teaching materials specifically designed for 7-year-old science-loving children"

[1103] Prompt Sentence Examples

[1104] "Intermediate-level content tailored for 6-year-olds who love animals"

[1105] "Advanced level teaching materials specifically designed for 7-year-old science-loving children"

[1106] This makes it possible to provide personalized learning content tailored to each child's age, interests, and learning level.

[1107] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1108] Step 1:

[1109] The user (parent) enters basic information about the child (age, interests, learning status, etc.) into the terminal means. The terminal means collects this input data and converts it into JSON format data. Specifically, the parent enters the required information into a form using a dedicated application.

[1110] input:

[1111] Children's age, interests, and learning status

[1112] output:

[1113] Basic information data in JSON format

[1114] Step 2:

[1115] The terminal sends the collected data in JSON format to the server using an HTTP POST request, and the server waits to analyze the received data.

[1116] input:

[1117] Basic information data in JSON format

[1118] output:

[1119] HTTP POST request

[1120] Step 3:

[1121] The server analyzes the received basic information about the child. Specifically, it parses the JSON format data to determine the child's interests and learning status. The analyzed data is then converted into a format suitable for the generative AI model.

[1122] input:

[1123] Basic information about the child passed to the server

[1124] output:

[1125] Data in a format suitable for generative AI models

[1126] Step 4:

[1127] The server generates customized learning content using a generative AI model. Based on the analysis results, the server inputs corresponding prompt sentences into the generative AI model. The generative AI model generates optimal learning content based on the prompt sentences.

[1128] input:

[1129] Data in a format suitable for generative AI models

[1130] Prompt statement

[1131] output:

[1132] Customized learning content

[1133] Step 5:

[1134] The server transmits the generated customized learning content to the terminal means, again using an HTTP POST request or other suitable communication means.

[1135] input:

[1136] Customized learning content

[1137] output:

[1138] HTTP POST request or other communication method

[1139] Step 6:

[1140] The terminal displays the received learning content on the screen, and the user (parent) can check the displayed content and use the option to download or print the content if necessary.

[1141] input:

[1142] Customized learning content received

[1143] output:

[1144] On-screen learning content

[1145] Download and print options

[1146] Step 7:

[1147] The user utilizes the download and print options to obtain the learning content in a format that can be physically stored or used. Depending on the user's selection, the terminal means performs a specific action (downloading a file or issuing a print command).

[1148] input:

[1149] On-screen learning content

[1150] User's choice (download or print)

[1151] output:

[1152] Downloaded files or printed materials

[1153] This ensures that learning content that is customized to a child's age, interests, and learning level is generated and delivered efficiently and effectively.

[1154] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1155] The present invention is a system that generates and provides individually customized learning content based on basic information about children and emotional information about users. This system is realized by the following steps.

[1156] Basic system configuration

[1157] Children's information input method

[1158] The device provides a form for users (parents) to enter basic information about their children, such as their age, interests (e.g., space, animals), and current learning status (e.g., unlearned vocabulary).

[1159] Data transmission and analysis

[1160] The terminal sends the input data to the server. The data is structured in, for example, JSON or XML format.

[1161] The server analyzes the data received from the terminal, which may include, for example, validating the data and storing it in a database.

[1162] Acquiring and analyzing user emotion information

[1163] The device uses an emotion engine to acquire emotion data from the user's facial expressions and voice information, including emotions such as joy, sadness, surprise, and anger.

[1164] The terminal transmits the acquired emotion data to the server.

[1165] The server analyzes the emotion data provided by the emotion engine and evaluates the user's emotional state.

[1166] Generating learning content

[1167] The server uses the analysis results to generate learning content appropriate for the child using a generative AI model. The generative AI model adjusts questions and learning materials according to the child's interests and proficiency, as well as the user's emotional state. For example, if the user is relaxed, it will generate slightly more difficult questions, and if they are stressed, it will provide easier questions and interactive learning materials.

[1168] Submitting and Viewing Learning Content

[1169] The server then sends the generated learning content to the device, which then displays the received learning content on its screen and provides the user with the option to download or print it, allowing parents and children to easily access the content.

[1170] Specific examples

[1171] Example 1: A 5-year-old child who loves space

[1172] The user enters the information "Age: 5 years old" and "Interest: Space" into the terminal and sends it. The terminal then sends this information to the server.

[1173] The server analyzes the input data and generates "simple space-related questions" and "coloring pages to learn the names of stars."

[1174] The server transmits the generated learning content to the terminal.

[1175] At the same time, the device uses an emotion engine to obtain emotional information while the child is learning. For example, if the child is having fun, that information is sent to the server, and challenging questions are added to the next learning content.

[1176] The terminal displays the content and gives the user the option to download or print.

[1177] Example 2: A 6-year-old child who loves animals

[1178] The user enters the information "Age: 6 years old" and "Interest: animals" into the terminal and sends it. The terminal then sends this information to the server.

[1179] The server analyzes the input data and generates questions about animal types and their characteristics, as well as puzzles that teach about the habitats of each animal.

[1180] The server transmits the generated learning content to the terminal.

[1181] At the same time, the device uses an emotion engine to capture the child's emotions in real time. For example, if the child is tired, that information is sent to the server, and the device will provide a relaxing activity for the next learning content.

[1182] The terminal displays the content and gives the user the option to download or print.

[1183] In this way, by combining a generative AI model with an emotion engine, this system provides customized learning content tailored to children's interests, proficiency levels, and even emotional states, creating an environment where children can learn while having fun.

[1184] The processing flow will be explained below.

[1185] Step 1:

[1186] The device displays a form for the user (parent) to enter basic information about their child, including fields such as the child's age, topics of interest (e.g., space, animals), and current learning status (e.g., unlearned vocabulary).

[1187] Step 2:

[1188] The user enters basic information about the child into the form and clicks the submit button.

[1189] Step 3:

[1190] The terminal sends the input data to the server. The data is structured in, for example, JSON or XML format.

[1191] Step 4:

[1192] The server analyzes the data received from the terminal, which may include, for example, validating the data and storing it in a database.

[1193] Step 5:

[1194] The device runs an emotion engine and captures facial expressions and voices while the user is monitoring their child's learning, thereby obtaining the user's emotion data.

[1195] Step 6:

[1196] The terminal transmits the acquired emotion data to the server. The emotion data includes various emotions of the user, such as joy, anger, sadness, and pleasure.

[1197] Step 7:

[1198] The server analyzes the emotion data provided by the emotion engine to assess the user's emotional state, for example, determining whether the user is stressed or relaxed.

[1199] Step 8:

[1200] The server uses the analysis results to provide the necessary parameters (e.g., topics of interest, proficiency, emotional state, etc.) to the generative AI model, instructing it to generate customized learning content.

[1201] Step 9:

[1202] Based on given parameters, the generative AI model generates customized learning content, such as simple questions about planets in space or a coloring book to learn the names of stars.

[1203] Step 10:

[1204] The server converts the generated learning content into a user-friendly format, such as HTML or PDF, before sending it to the device.

[1205] Step 11:

[1206] The server transmits the prepared learning content to the terminal.

[1207] Step 12:

[1208] The device then displays the received learning content on its screen, which may involve, for example, rendering an HTML page or launching a PDF viewer.

[1209] Step 13:

[1210] The terminal provides users with download and print options, allowing them to download or print the learning content as needed.

[1211] Step 14:

[1212] After the learning session ends, the device will start the emotion engine again and capture the final emotional state.

[1213] Step 15:

[1214] The device sends the final emotion data to the server, which stores it in a database for reference during the next learning session.

[1215] In this way, customized learning content is provided to children, taking into account the user's emotional state in the process, making learning more engaging and effective for children.

[1216] Example 2

[1217] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1218] Conventional learning content generation systems have not adequately provided content tailored to each child's individual interests and level of proficiency. Furthermore, there is no mechanism for customizing learning content that takes into account the user's emotional state, making it difficult to provide effective learning support. This makes it difficult for children to become interested in learning, resulting in reduced learning effectiveness.

[1219] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1220] In this invention, the server includes terminal means for inputting basic information about the child, analysis means for receiving the basic information about the child from the terminal means and analyzing the information, generation means for generating customized learning content using a generative AI model based on the analyzed information and the user's emotional information, transmission means for transmitting the generated learning content to the terminal means, display means for displaying the learning content received by the terminal means and providing it to the user, an emotion engine for acquiring emotional information from the user's facial expressions and voice, and means for transmitting the emotional information to the server and analyzing it. This makes it possible to provide individually customized learning content based on the child's interests and proficiency, and further take the user's emotional state into consideration, thereby achieving a more effective and engaging learning experience.

[1221] The "terminal means" is a device used by the user to input basic information and emotional information about the child and transmit that information to the server.

[1222] The "analysis means" is a means for analyzing the basic information and emotional information of the child received from the terminal means and generating learning content based on the results.

[1223] A "generative AI model" is an artificial intelligence model that generates learning content suitable for children based on analyzed information.

[1224] "Generative means" means a means for creating customized learning content using a generative AI model.

[1225] The "transmission means" is a means for transmitting the generated study content to the terminal means.

[1226] The "display means" refers to a means for visually presenting the study content received by the terminal means to the user.

[1227] The "emotion engine" is an engine that acquires emotion data from the user's facial expressions and voice information and evaluates their emotional state.

[1228] "Emotion information" is information about the emotional state analyzed based on data acquired from the user's facial expressions and voice.

[1229] The present invention is a system for generating and providing individually customized learning content based on basic information about a child and emotional information about a user. The following describes an embodiment of this system.

[1230] Basic system configuration

[1231] Children's information input method

[1232] The device provides a form for the user to enter basic information about the child, including the child's age, interests, current level of proficiency, etc. For example, the user can open a web browser, enter this information into the form, and click the submit button.

[1233] Data transmission and analysis

[1234] The terminal sends the entered data to the server in JSON or XML format. Specifically, the data is sent using an HTTP POST request. The server analyzes the received data, first validating it and checking that all required data is included. It then saves it in a database and waits for the analysis results. The Python pandas library can be used for analysis.

[1235] Acquiring and analyzing user emotion information

[1236] The device uses an emotion engine to acquire emotion data from the user's facial expressions and voice. For example, a webcam or microphone is used to collect the user's face and voice, which are then analyzed by the emotion engine. The acquired emotion data is then sent to the server again using an HTTP POST request. The server analyzes the emotion data provided by the emotion engine and evaluates the user's emotional state. A machine learning model can be used for this analysis.

[1237] Generating learning content

[1238] The server uses a generative AI model based on the child's basic information and the user's emotional data to generate appropriate learning content. For example, a generative AI model such as GPT-3 can be used, and a prompt such as "5-year-old child, interested in space" can be created and input into the model. Based on this prompt, simple questions and learning materials are generated.

[1239] Submitting and Viewing Learning Content

[1240] The server sends the generated learning content to the device, which then displays the received content on the screen and provides the user with the option to download or print it. For example, this can be achieved by displaying the content on a web page with download and print buttons.

[1241] Specific examples

[1242] Example 1: A 5-year-old child who loves space

[1243] The user enters information such as "Age: 5 years old" and "Interest: Space" into the device and sends it. The device then sends this to the server, which analyzes the input data and generates "easy space-related questions" and "coloring pages to learn the names of stars." The server then sends the generated learning content to the device, which then displays the content. In addition, an emotion engine is used to obtain emotional information while the user is learning, and if the user is enjoying the learning experience, this information is sent to the server, and more challenging questions are added to the next learning content.

[1244] Example 2: A 6-year-old child who loves animals

[1245] The user enters information such as "Age: 6 years old" and "Interest: animals" into the device and sends it. The device then sends this to the server, which analyzes the input data and generates questions about animal species and their characteristics, as well as puzzles to learn about each animal's habitat. The server then sends the generated learning content to the device, which then displays it. The device also uses an emotion engine to obtain the child's emotions in real time and offers relaxing activities if the child is tired.

[1246] Examples of prompt statements

[1247] 1. "My child is 5 years old and is interested in space. What educational content can you provide him?"

[1248] 2. "What materials would be appropriate for a 6-year-old child to learn about animals?"

[1249] In this way, by combining a generative AI model with an emotion engine, this system can customize and provide learning content according to a child's interests, proficiency level, and even emotional state.

[1250] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1251] Step 1: Enter your child's information

[1252] The user uses the device to enter basic information about their child. Specifically, the user opens a web browser and enters the child's age, interests, and current level of proficiency in the form that appears. This input form includes text boxes and drop-down menus, and once the input is complete, the information is sent by clicking the submit button.

[1253] Input: Child's age, topics of interest, current level of proficiency

[1254] Output: Structured data (e.g., JSON format)

[1255] Step 2: Sending data

[1256] The terminal sends the input structured data to the server. Specifically, the data is sent using an HTTP POST request. This request includes the user's input information.

[1257] Input: Structured data (e.g., JSON format)

[1258] Output: Send data to the server

[1259] Step 3: Analyze the data

[1260] The server analyzes the received data. Specifically, it first validates the data to check whether it contains all the required data. It then saves it in the database and waits for the analysis results. This analysis can be done using Python's pandas library or SQL.

[1261] Input: Data submitted by the user

[1262] Output: Data validation results, saved to database

[1263] Step 4: Obtaining user emotion information

[1264] The device uses an emotion engine to acquire emotion data from the user's facial expressions and voice in real time. For example, it uses a webcam or microphone to collect the user's face and voice and analyzes them. This analysis is performed by the emotion engine.

[1265] Input: User's facial expressions and voice information

[1266] Output: Emotion data (e.g., happiness, sadness)

[1267] Step 5: Send and analyze emotion data

[1268] The device sends the acquired emotion data to the server, again using an HTTP POST request. The server analyzes the emotion data provided by the emotion engine and evaluates the user's emotional state. A machine learning model can be used for the analysis.

[1269] Input: Emotion data

[1270] Output: Evaluation of the user's emotional state

[1271] Step 6: Generate learning content

[1272] The server uses a generative AI model based on the child's basic information and the user's emotional data to generate appropriate learning content. Specifically, the server creates a prompt for the generative AI model: "A 5-year-old child interested in space." This prompt is then input into the model. Based on this prompt, simple questions and learning materials are generated.

[1273] Input: Basic information about the child, user's emotional data

[1274] Output: Generated learning content

[1275] Step 7: Submit and view your learning content

[1276] The server sends the generated learning content to the device. Specifically, it sends the content using an HTTP response. The device displays the received content on the screen and offers the user the option to download or print it. Specifically, this is achieved by displaying the content on a web page and providing download and print buttons.

[1277] Input: Generated learning content

[1278] Output: The learning content displayed to the user, with options to download and print

[1279] (Application example 2)

[1280] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1281] In conventional factories, only standardized education and training has been provided to improve individual worker capabilities and work efficiency. However, because optimal support varies depending on the worker's level of proficiency and emotional state, the effectiveness of a one-size-fits-all approach has been limited. In particular, in work environments where workers are prone to fatigue and stress, individually customized support is important. The objective of this invention is to provide a system that improves worker efficiency and satisfaction by providing individually customized support content based on the worker's basic information and emotional information.

[1282] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1283] In this invention, the server includes terminal means for inputting basic information about the worker, analysis means for receiving the basic information about the worker sent from the terminal means and analyzing the information, emotion engine means for acquiring emotional information about the worker, analysis means for receiving the emotional information sent from the emotion engine means and analyzing the information, generation means for generating customized assistance content using a generative AI model based on the analyzed basic information and emotional information, transmission means for transmitting the generated assistance content to the terminal means, and display means for displaying the assistance content received by the terminal means and providing it to the worker. This makes it possible to provide optimal work assistance and relaxation content based on the basic information and real-time emotional information of the worker.

[1284] "Basic information about workers" refers to information about the individual characteristics of workers, such as their age, work experience, specialties, and problems.

[1285] "Terminal means" refers to an electronic device for inputting and transmitting basic information about workers.

[1286] The "analysis means" is a processing device or software for receiving and analyzing information sent from the terminal means.

[1287] The "emotion engine means" is a device or software that uses sensors such as a camera and a microphone to obtain emotional information from the facial expressions and voices of workers.

[1288] The "generation means" refers to a processing device or software that uses a generative AI model to generate customized assistance content based on the analyzed basic information and emotional information.

[1289] The "transmission means" is a communication device or software for transmitting the generated assistance content to the terminal means.

[1290] The "display means" is a device or software that displays the support content received by the terminal means on a screen and provides it to the worker.

[1291] A "generative AI model" is a model that uses machine learning algorithms to automatically generate content tailored to a specific purpose based on input data.

[1292] "Support content" is information for work support and relaxation that is individually customized based on the worker's basic information and emotional state.

[1293] The present invention is a system for providing individually customized support content based on basic information and emotional information of a worker. Specific embodiments of the present invention will be described in detail below.

[1294] Basic system configuration

[1295] Employee information input method

[1296] The terminal means provides a form for inputting basic information about the worker. The basic information about the worker includes age, work experience, specialty work, current problems, etc. For example, information such as "Age: 35 years old," "Work experience: 10 years," "Specialty work: assembly," and "Problem: inspection work takes a long time" is input.

[1297] Data transmission and analysis

[1298] The terminal means sends the input data to the server. The data is structured in, for example, JSON or XML format. The server analyzes the data received from the terminal. Analysis includes data validation and saving to a database.

[1299] Acquiring and analyzing worker emotion information

[1300] The emotion engine means acquires emotion data from the worker's facial expressions and voice information using a camera and microphone mounted on the terminal means. The emotion information includes fatigue, stress, concentration, etc. The terminal means transmits the acquired emotion data to the server. The server analyzes the emotion data provided by the emotion engine means and evaluates the worker's emotional state.

[1301] Support content generation

[1302] The server uses the analysis results to generate support content tailored to the worker using a generative AI model. The generative AI model adjusts the support content based on the worker's basic information and emotional state. For example, if the worker is tired, it will suggest relaxing stretches, and if the worker is working and requires concentration, it will provide specific advice to improve efficiency.

[1303] Sending and displaying support content

[1304] The server transmits the generated support content to the terminal means. The terminal means displays the received support content on a screen and provides it to the worker. For example, the display may say, "Please perform relaxing stretches for five minutes."

[1305] Hardware and software used

[1306] Hardware: Camera, microphone, and display attached to the robot

[1307] software:

[1308] Emotion engine: Software that processes data from the camera and microphone to assess emotional state

[1309] Generative AI model: A machine learning model that generates optimal support content based on basic and emotional information about the worker.

[1310] Server: API that analyzes data and generates support content

[1311] Specific examples

[1312] Example 1: Content creation flow for worker "Factory Worker A"

[1313] The factory's robot AI reads the facial expression of "Worker A" and detects that he is tired.

[1314] The data is analyzed on the server and content is generated that suggests relaxing stretches for "Worker A."

[1315] The robot calls out, "Mr. A, you look tired. Would you like to try stretching for five minutes?"

[1316] Example prompt sentence:

[1317] Design a system in which a factory robot analyzes the emotions of "Factory Worker A" from his facial expressions and voice, and suggests relaxing stretches to the worker. Specifically, the system will include a process in which the worker's basic information is input, emotional data is acquired in real time using an emotion engine, customized support content is generated using a generative AI model, and finally the robot provides the support content on a screen or via voice.

[1318] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1319] Step 1:

[1320] The user inputs basic information about the worker on the terminal and submits it. The input data includes age, work experience, specialties, problems, etc. This information is structured in JSON or XML format and sent to the server.

[1321] Input: Basic information of the worker (age, work experience, specialty, problems)

[1322] Output: JSON or XML data sent to the server

[1323] Step 2:

[1324] The server analyzes the received worker's basic information, performs data validation (format check, missing value check, etc.), and stores the data in the database if it is in the correct format.

[1325] Input: Basic information about the worker (JSON or XML data)

[1326] Output: Worker information stored in the database

[1327] Step 3:

[1328] Using the camera and microphone installed in the terminal, the emotion engine means acquires emotion data from the worker's facial expressions and voice information, using facial recognition and voice analysis of the worker.

[1329] Input: Camera video, audio data

[1330] Output: Emotion data (e.g., tiredness, stress, concentration)

[1331] Step 4:

[1332] The device sends the acquired emotion data to the server, which in turn structures the data in JSON or XML format.

[1333] Input: Emotion data (data obtained in real time)

[1334] Output: JSON or XML data sent to the server

[1335] Step 5:

[1336] The server analyzes the emotion data provided by the emotion engine means and uses the analysis results to evaluate the worker's emotional state.

[1337] Input: Emotion data (JSON or XML data)

[1338] Output: Evaluation result (e.g., worker's current emotional state)

[1339] Step 6:

[1340] The server uses a generative AI model based on the analysis results (basic information and emotional state of the worker) to generate customized support content. The generative AI model creates appropriate support content according to the worker's situation.

[1341] Input: Basic information and emotional state (evaluation results)

[1342] Output: Generated assistance content

[1343] Step 7:

[1344] The server sends the generated support content to the device in HTML or JSON format, which is suitable for display.

[1345] Input: Generated assistance content

[1346] Output: Support content (HTML or JSON data) sent to the device

[1347] Step 8:

[1348] The device then displays the received support content on its screen and provides it to the worker, such as advice on stretching techniques to relax or improving work efficiency.

[1349] Input: Received support content (HTML or JSON data)

[1350] Output: The display content provided to the worker

[1351] 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.

[1352] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. 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 voice, text data indicating text, and image data indicating an image is also input. 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.

[1353] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1354] [Fourth embodiment]

[1355] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1356] 7, a 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.

[1357] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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).

[1358] 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.

[1359] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1360] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1361] 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.

[1362] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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.

[1363] 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.

[1364] 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 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.

[1365] 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.

[1366] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1367] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1368] The present invention is a system that generates and provides individually customized learning content based on basic information about children. This system is realized by the following steps.

[1369] Basic system configuration

[1370] Children's information input method

[1371] The device provides a form for users (parents) to enter basic information about their children, such as their age, interests (e.g., space, animals), and current learning status (e.g., unlearned vocabulary).

[1372] Data transmission and analysis

[1373] The device sends the input data to the server, which analyzes the received data and determines the requirements based on the child's interests and learning status. This analysis can determine, for example, that space-related questions are appropriate for a child who likes space.

[1374] Generating learning content

[1375] The server uses the analysis results to generate learning content appropriate for the child using a generative AI model. The generative AI model provides questions and learning materials tailored to the child's interests and level of proficiency. For example, for a 5-year-old child interested in space, it generates a coloring book that teaches the names of planets and stars in the solar system.

[1376] Submitting and Viewing Learning Content

[1377] The server then sends the generated learning content to the device, which then displays the received learning content on its screen and provides the user with the option to download or print it, allowing parents and children to easily access the content.

[1378] Specific examples

[1379] Example 1: A 5-year-old child who loves space

[1380] The user enters the information "Age: 5 years old" and "Interest: Space" into the terminal and sends it. The terminal then sends this information to the server.

[1381] The server analyzes the input data and generates "simple space-related questions" and "coloring pages to learn the names of stars."

[1382] The server transmits the generated learning content to the terminal.

[1383] The terminal displays the content and gives the user the option to download or print.

[1384] Example 2: A 6-year-old child who loves animals

[1385] The user enters the information "Age: 6 years old" and "Interest: animals" into the terminal and sends it. The terminal then sends this information to the server.

[1386] The server analyzes the input data and generates questions about animal types and their characteristics, as well as puzzles that teach about the habitats of each animal.

[1387] The server transmits the generated learning content to the terminal.

[1388] The terminal displays the content and gives the user the option to download or print.

[1389] In this way, this system uses a generative AI model to provide customized learning content tailored to children's interests and proficiency levels, creating an environment where children can learn while having fun.

[1390] The processing flow will be explained below.

[1391] Step 1:

[1392] The device displays a form for the user (parent) to enter basic information about their child, including fields such as the child's age, topics of interest (e.g., space, animals), and current learning status (e.g., unlearned vocabulary).

[1393] Step 2:

[1394] The user enters basic information about the child into the form and clicks the submit button.

[1395] Step 3:

[1396] The terminal sends the input data to the server. The data is structured in, for example, JSON or XML format.

[1397] Step 4:

[1398] The server analyzes the data received from the terminal, which may include, for example, validating the data and storing it in a database.

[1399] Step 5:

[1400] The server determines the child's interests and proficiency based on the analysis results. For example, if the input interest topic is "space" and the child is 5 years old, it generates space-related learning content.

[1401] Step 6:

[1402] The server passes necessary parameters (e.g., topics of interest and proficiency) to the generative AI model, instructing it to generate customized learning content.

[1403] Step 7:

[1404] Based on given parameters, the generative AI model generates customized learning content, such as simple questions about planets in space or a coloring book to learn the names of stars.

[1405] Step 8:

[1406] The server converts the generated learning content into a user-friendly format, such as HTML or PDF, before sending it to the device.

[1407] Step 9:

[1408] The server transmits the prepared learning content to the terminal.

[1409] Step 10:

[1410] The device then displays the received learning content on its screen, which may involve, for example, rendering an HTML page or launching a PDF viewer.

[1411] Step 11:

[1412] The terminal provides users with download and print options, allowing them to download or print the learning content as needed.

[1413] In this way, customized learning content is provided to the child, making it interesting and effective for the child to learn.

[1414] Example 1

[1415] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1416] Conventional educational systems have faced the challenge of providing learning content tailored to each child's individual interests and proficiency level. In particular, they were unable to automatically generate learning materials tailored to each child's individual characteristics, resulting in a decline in learning effectiveness. Furthermore, preparing content manually required a great deal of time and effort, making it difficult to provide efficient learning support.

[1417] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1418] In this invention, the server includes a terminal means for inputting basic information about the child, an analysis means for receiving the basic information about the child from the terminal means and analyzing the information, a generation means for generating prompt sentences using a generative AI model based on the analyzed information to generate customized learning content, a transmission means for transmitting the generated learning content to the terminal means, and a display means for displaying the learning content received by the terminal means and providing it to the user in a downloadable or printable format. This enables the automatic generation and provision of customized learning content tailored to each child's individual interests and proficiency.

[1419] "Terminal means" means a device or system for inputting basic information about a child.

[1420] "Analysis means" refers to a device or system that receives the basic information about the child sent from the terminal means and analyzes that information.

[1421] "Generative AI model" means an artificial intelligence model that generates prompt sentences based on analyzed information and generates individually customized learning content.

[1422] "Generation means" refers to a device or system that generates customized learning content using a generative AI model based on the information analyzed by the analysis means.

[1423] "Transmission means" refers to a device or system that transmits the generated study content to the terminal means.

[1424] "Display means" refers to a device or system that displays the study content received by the terminal means and provides it to the user in a form that can be downloaded or printed.

[1425] "Prompt sentence" means an instruction sentence that a generative AI model uses as a reference when generating learning content appropriate for children.

[1426] MODE FOR CARRYING OUT THE INVENTION

[1427] The present invention is a system for generating and providing individually customized learning content based on basic information about children. Next, the overall configuration and specific operation of the system will be described.

[1428] Basic system configuration

[1429] The system consists of the following main components:

[1430] 1. Terminal means

[1431] 2. Analysis method

[1432] 3. Generative means (including generative AI models)

[1433] 4. Transmission Method

[1434] 5. Display means

[1435] Terminal means

[1436] The device provides an input form for the user (parent) to enter basic information about their child. This form includes fields for entering information such as the child's age, topics of interest (e.g., space, animals), current learning status (e.g., unlearned vocabulary), etc. When the user enters the information and clicks the submit button, this data is sent from the device to the server.

[1437] Analysis means

[1438] The server receives the child's basic information sent from the terminal means. The received data is deserialized and compared with the database. This comparison allows the server to analyze the requirements for appropriate learning content based on the child's interests and learning status. For example, based on the input data "Age: 6 years old" and "Interest: animals," the server determines that it is appropriate to generate basic questions and teaching materials related to animals.

[1439] generation means

[1440] The server generates appropriate learning content using a generative AI model (e.g., GPT-3) based on the analysis results. The generator operates as a server-side application program, sending prompt sentences to the generative AI model and receiving the generated content.

[1441] Examples of prompts:

[1442] "Create questions for 6-year-olds to help them learn about animal characteristics. These could include simple questions about animal types, characteristics, and habitats. Examples include a quiz where children are asked to look at a picture of an animal and name it, or choose its habitat."

[1443] Based on the prompt, the generative AI model generates customized learning content tailored to the child's interests and proficiency level.

[1444] Transmission method

[1445] The server sends the generated learning content to the terminal. The generated data is serialized in JSON format and sent as an HTTP response. The terminal receives this data and proceeds to the next step.

[1446] Display means

[1447] The device deserializes the learning content received from the server and displays it to the user. The displayed content also provides options for downloading or printing so that children can use it directly for their studies. This creates an environment where children and parents can easily access learning content.

[1448] Specific examples

[1449] Example 1: A 5-year-old child who loves space

[1450] The user enters information such as "Age: 5 years old" and "Interest: Space" into the device and submits it. The device then sends this information to the server. The server analyzes the input data and generates "simple space-related questions" and "coloring pages to learn the names of stars." The server then sends the generated learning content to the device. The device then displays the content and gives the user the option to download or print it.

[1451] Example 2: A 6-year-old child who loves animals

[1452] The user enters information such as "Age: 6 years old" and "Interest: Animals" into the device and submits it. The device then sends this information to the server. The server analyzes the input data and generates questions about animal species and their characteristics, as well as puzzles to learn about the habitats of each animal. The server then sends the generated learning content to the device. The device then displays the content and gives the user the option to download or print it.

[1453] As described above, this system uses a generative AI model to provide customized learning content tailored to children's interests and proficiency levels, allowing children to enjoy learning and parents to easily acquire and use the content.

[1454] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1455] Step 1: Enter your child's basic information

[1456] The user enters basic information about their child into an input form displayed on the device. Input items include the child's age, interests (e.g., space, animals), learning status, etc. The input data is converted into JSON format. This data is input by the user by entering accurate information.

[1457] Input: Child's age, interest topic, learning status

[1458] Output: Basic information about the child in JSON format

[1459] Specific behavior:

[1460] The age input field has a numeric check.

[1461] There is a drop-down menu of topics of interest.

[1462] A text area is provided for the learning status.

[1463] Step 2: Sending data

[1464] The device sends the entered basic information about the child to the server. Specifically, after the submit button is pressed, JSON data is sent to the server as an HTTP POST request.

[1465] Input: Basic information data entered by the user in JSON format

[1466] Output: HTTP POST request to the server

[1467] Specific behavior:

[1468] The user clicks the submit button.

[1469] Form data is collected and converted to JSON format.

[1470] Data is sent asynchronously using AJAX.

[1471] Step 3: Receiving and analyzing data

[1472] The server receives the child's basic information data sent from the device. The received data is deserialized and analyzed against a database (e.g., MySQL). As a result of the analysis, requirements based on the child's interests and learning progress are determined.

[1473] Input: Basic information data in JSON format sent from the terminal

[1474] Output: Learning content requirements based on the analysis results

[1475] Specific behavior:

[1476] Deserialize the received data and convert it to the internal data format.

[1477] Execute the corresponding query on the database to retrieve the relevant data.

[1478] Based on the acquired data, the analysis engine determines the requirements for learning content.

[1479] Step 4: Prompt generation and content generation

[1480] The server sends prompts to a generative AI model (e.g., GPT-3) based on the analysis results, and generates appropriate learning content. The generated content is temporarily stored on the server.

[1481] Input: Prompt text based on the analysis result

[1482] Output: Customized learning content from generative AI models

[1483] Examples of prompts:

[1484] "Create questions for 6-year-olds to help them learn about animal characteristics. These could include simple questions about animal types, characteristics, and habitats. Examples include a quiz where children are asked to look at a picture of an animal and name it, or choose its habitat."

[1485] Specific behavior:

[1486] Generates a prompt string based on the parsed data used to construct the prompt statement.

[1487] Send an HTTP request to the API endpoint of the generative AI model.

[1488] Receive a response from the generative AI model.

[1489] Step 5: Submit your learning content

[1490] The server serializes the generated learning content into JSON format and sends it to the terminal as an HTTP response.

[1491] Input: Customized learning content from a generative AI model

[1492] Output: Learning content as an HTTP response to the device

[1493] Specific behavior:

[1494] Serialize the generated content into JSON format.

[1495] Create an HTTP response object and send it to the device.

[1496] Step 6: View learning content

[1497] The device deserializes the learning content received from the server and displays it to the user, offering the user the option to download or print the content.

[1498] Input: Learning content received as an HTTP response from the server

[1499] Output: The learning content that users see, along with download and print options

[1500] Specific behavior:

[1501] Deserialize the received data.

[1502] The data is applied to an HTML template and displayed in the user interface.

[1503] Enable buttons for downloading and printing.

[1504] (Application example 1)

[1505] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1506] Conventional learning content provision systems have had the problem of being unable to provide content that appropriately reflects differences in children's ages and interests, and are only able to provide uniform educational materials. Furthermore, there is no system that allows parents to easily download and print learning content for their children, which makes them inconvenient.

[1507] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1508] In this invention, the server includes a terminal means for inputting basic information about the child, an analysis means for receiving the basic information about the child from the terminal means and analyzing the information, a generation means for generating customized learning content using a generative AI model based on the analyzed information, a transmission means for transmitting the generated learning content to the terminal means, a display means for displaying the learning content received by the terminal means and providing it to the user, and a means for the terminal means to provide the option to download or print the learning content in response to a user's request. This allows for the provision of personalized learning content according to the child's age and interests, and for parents to easily download and print the content.

[1509] "Terminal means" is a device for inputting basic information about a child and transmitting that information to a server.

[1510] The "analysis means" is a function that analyzes the received basic information about the child and determines the requirements for generating appropriate learning content based on that data.

[1511] The "generation means" is a function that uses a generative AI model based on the analysis results to create customized learning content suitable for children.

[1512] The "transmission means" is a function that transmits the generated study content to the terminal means.

[1513] The "display means" is a function that displays and provides the study content received by the terminal means to the user.

[1514] The "means for providing download and print options" is a function that allows the terminal means to download or print the generated study content according to the user's request.

[1515] "Educational Materials" refers generally to content that is individually customized using generative AI models to support learning.

[1516] "Unacquired vocabulary" refers to words and phrases that a child has not yet learned or fully understood.

[1517] A "generative AI model" is an artificial intelligence model that generates optimal learning content based on input data.

[1518] This invention is a system that generates and provides individually customized learning content based on basic information about children. This system is realized by the following steps.

[1519] Basic system configuration

[1520] Children's information input method

[1521] The terminal provides a form for the user (parent) to input basic information about their child, including the child's age, topics of interest, and current learning status (e.g., vocabulary that has not yet been mastered).

[1522] Data transmission and analysis

[1523] The terminal device sends the input data to the server, which analyzes the received data and determines the requirements based on the child's interests and learning status. Based on this analysis, for example, it can suggest space-related educational materials to a child who likes space.

[1524] Generating learning content

[1525] The server uses the analysis results to generate learning content appropriate for the child using a generative AI model. The generative AI model provides questions and learning materials tailored to the child's interests and level of proficiency. For example, for a 6-year-old child interested in animals, it would generate content that teaches them about different animal species and their characteristics.

[1526] Submitting and Viewing Learning Content

[1527] The server transmits the generated learning content to the terminal device, which displays the received learning content on the screen and provides it to the user. The terminal device also provides the user with the option to download or print the content, depending on the user's request.

[1528] Hardware and software used

[1529] Hardware: Smartphones, tablets, personal computers

[1530] Software: Python scripts, Flask (for the server side), generative AI models (e.g., OpenAI GPT-3)

[1531] Data processing and calculation

[1532] Data collection: Parents enter their child's age, interests, and learning status into a dedicated device.

[1533] Data transmission: Data is transmitted from the terminal means to the server.

[1534] Data analysis: Based on the received data, the server inputs the data into a generative AI model to generate optimal learning content.

[1535] Content generation: Generated content is generated by the server and sent to the terminal means.

[1536] Content display: Displays the learning content generated on the terminal means and provides the user with the option to download or print.

[1537] Specific examples

[1538] Example 1

[1539] Child: 6 years old

[1540] Interests: Animals

[1541] Learning level: Intermediate

[1542] "Intermediate-level content tailored for 6-year-olds who love animals"

[1543] Example 2

[1544] Child: 7 years old

[1545] Interests: Science

[1546] Learning level: Advanced

[1547] "Advanced level teaching materials specifically designed for 7-year-old science-loving children"

[1548] Prompt Sentence Examples

[1549] "Intermediate-level content tailored for 6-year-olds who love animals"

[1550] "Advanced level teaching materials specifically designed for 7-year-old science-loving children"

[1551] This makes it possible to provide personalized learning content tailored to each child's age, interests, and learning level.

[1552] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1553] Step 1:

[1554] The user (parent) enters basic information about the child (age, interests, learning status, etc.) into the terminal means. The terminal means collects this input data and converts it into JSON format data. Specifically, the parent enters the required information into a form using a dedicated application.

[1555] input:

[1556] Children's age, interests, and learning status

[1557] output:

[1558] Basic information data in JSON format

[1559] Step 2:

[1560] The terminal sends the collected data in JSON format to the server using an HTTP POST request, and the server waits to analyze the received data.

[1561] input:

[1562] Basic information data in JSON format

[1563] output:

[1564] HTTP POST request

[1565] Step 3:

[1566] The server analyzes the received basic information about the child. Specifically, it parses the JSON format data to determine the child's interests and learning status. The analyzed data is then converted into a format suitable for the generative AI model.

[1567] input:

[1568] Basic information about the child passed to the server

[1569] output:

[1570] Data in a format suitable for generative AI models

[1571] Step 4:

[1572] The server generates customized learning content using a generative AI model. Based on the analysis results, the server inputs corresponding prompt sentences into the generative AI model. The generative AI model generates optimal learning content based on the prompt sentences.

[1573] input:

[1574] Data in a format suitable for generative AI models

[1575] Prompt statement

[1576] output:

[1577] Customized learning content

[1578] Step 5:

[1579] The server transmits the generated customized learning content to the terminal means, again using an HTTP POST request or other suitable communication means.

[1580] input:

[1581] Customized learning content

[1582] output:

[1583] HTTP POST request or other communication method

[1584] Step 6:

[1585] The terminal displays the received learning content on the screen, and the user (parent) can check the displayed content and use the option to download or print the content if necessary.

[1586] input:

[1587] Customized learning content received

[1588] output:

[1589] On-screen learning content

[1590] Download and print options

[1591] Step 7:

[1592] The user utilizes the download and print options to obtain the learning content in a format that can be physically stored or used. Depending on the user's selection, the terminal means performs a specific action (downloading a file or issuing a print command).

[1593] input:

[1594] On-screen learning content

[1595] User's choice (download or print)

[1596] output:

[1597] Downloaded files or printed materials

[1598] This ensures that learning content that is customized to a child's age, interests, and learning level is generated and delivered efficiently and effectively.

[1599] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1600] The present invention is a system that generates and provides individually customized learning content based on basic information about children and emotional information about users. This system is realized by the following steps.

[1601] Basic system configuration

[1602] Children's information input method

[1603] The device provides a form for users (parents) to enter basic information about their children, such as their age, interests (e.g., space, animals), and current learning status (e.g., unlearned vocabulary).

[1604] Data transmission and analysis

[1605] The terminal sends the input data to the server. The data is structured in, for example, JSON or XML format.

[1606] The server analyzes the data received from the terminal, which may include, for example, validating the data and storing it in a database.

[1607] Acquiring and analyzing user emotion information

[1608] The device uses an emotion engine to acquire emotion data from the user's facial expressions and voice information, including emotions such as joy, sadness, surprise, and anger.

[1609] The terminal transmits the acquired emotion data to the server.

[1610] The server analyzes the emotion data provided by the emotion engine and evaluates the user's emotional state.

[1611] Generating learning content

[1612] The server uses the analysis results to generate learning content appropriate for the child using a generative AI model. The generative AI model adjusts questions and learning materials according to the child's interests and proficiency, as well as the user's emotional state. For example, if the user is relaxed, it will generate slightly more difficult questions, and if they are stressed, it will provide easier questions and interactive learning materials.

[1613] Submitting and Viewing Learning Content

[1614] The server then sends the generated learning content to the device, which then displays the received learning content on its screen and provides the user with the option to download or print it, allowing parents and children to easily access the content.

[1615] Specific examples

[1616] Example 1: A 5-year-old child who loves space

[1617] The user enters the information "Age: 5 years old" and "Interest: Space" into the terminal and sends it. The terminal then sends this information to the server.

[1618] The server analyzes the input data and generates "simple space-related questions" and "coloring pages to learn the names of stars."

[1619] The server transmits the generated learning content to the terminal.

[1620] At the same time, the device uses an emotion engine to obtain emotional information while the child is learning. For example, if the child is having fun, that information is sent to the server, and challenging questions are added to the next learning content.

[1621] The terminal displays the content and gives the user the option to download or print.

[1622] Example 2: A 6-year-old child who loves animals

[1623] The user enters the information "Age: 6 years old" and "Interest: animals" into the terminal and sends it. The terminal then sends this information to the server.

[1624] The server analyzes the input data and generates questions about animal types and their characteristics, as well as puzzles that teach about the habitats of each animal.

[1625] The server transmits the generated learning content to the terminal.

[1626] At the same time, the device uses an emotion engine to capture the child's emotions in real time. For example, if the child is tired, that information is sent to the server, and the device will provide a relaxing activity for the next learning content.

[1627] The terminal displays the content and gives the user the option to download or print.

[1628] In this way, by combining a generative AI model with an emotion engine, this system provides customized learning content tailored to children's interests, proficiency levels, and even emotional states, creating an environment where children can learn while having fun.

[1629] The processing flow will be explained below.

[1630] Step 1:

[1631] The device displays a form for the user (parent) to enter basic information about their child, including fields such as the child's age, topics of interest (e.g., space, animals), and current learning status (e.g., unlearned vocabulary).

[1632] Step 2:

[1633] The user enters basic information about the child into the form and clicks the submit button.

[1634] Step 3:

[1635] The terminal sends the input data to the server. The data is structured in, for example, JSON or XML format.

[1636] Step 4:

[1637] The server analyzes the data received from the terminal, which may include, for example, validating the data and storing it in a database.

[1638] Step 5:

[1639] The device runs an emotion engine and captures facial expressions and voices while the user is monitoring their child's learning, thereby obtaining the user's emotion data.

[1640] Step 6:

[1641] The terminal transmits the acquired emotion data to the server. The emotion data includes various emotions of the user, such as joy, anger, sadness, and pleasure.

[1642] Step 7:

[1643] The server analyzes the emotion data provided by the emotion engine to assess the user's emotional state, for example, determining whether the user is stressed or relaxed.

[1644] Step 8:

[1645] The server uses the analysis results to provide the necessary parameters (e.g., topics of interest, proficiency, emotional state, etc.) to the generative AI model, instructing it to generate customized learning content.

[1646] Step 9:

[1647] Based on given parameters, the generative AI model generates customized learning content, such as simple questions about planets in space or a coloring book to learn the names of stars.

[1648] Step 10:

[1649] The server converts the generated learning content into a user-friendly format, such as HTML or PDF, before sending it to the device.

[1650] Step 11:

[1651] The server transmits the prepared learning content to the terminal.

[1652] Step 12:

[1653] The device then displays the received learning content on its screen, which may involve, for example, rendering an HTML page or launching a PDF viewer.

[1654] Step 13:

[1655] The terminal provides users with download and print options, allowing them to download or print the learning content as needed.

[1656] Step 14:

[1657] After the learning session ends, the device will start the emotion engine again and capture the final emotional state.

[1658] Step 15:

[1659] The device sends the final emotion data to the server, which stores it in a database for reference during the next learning session.

[1660] In this way, customized learning content is provided to children, taking into account the user's emotional state in the process, making learning more engaging and effective for children.

[1661] Example 2

[1662] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1663] Conventional learning content generation systems have not adequately provided content tailored to each child's individual interests and level of proficiency. Furthermore, there is no mechanism for customizing learning content that takes into account the user's emotional state, making it difficult to provide effective learning support. This makes it difficult for children to become interested in learning, resulting in reduced learning effectiveness.

[1664] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1665] In this invention, the server includes terminal means for inputting basic information about the child, analysis means for receiving the basic information about the child from the terminal means and analyzing the information, generation means for generating customized learning content using a generative AI model based on the analyzed information and the user's emotional information, transmission means for transmitting the generated learning content to the terminal means, display means for displaying the learning content received by the terminal means and providing it to the user, an emotion engine for acquiring emotional information from the user's facial expressions and voice, and means for transmitting the emotional information to the server and analyzing it. This makes it possible to provide individually customized learning content based on the child's interests and proficiency, and further take the user's emotional state into consideration, thereby achieving a more effective and engaging learning experience.

[1666] The "terminal means" is a device used by the user to input basic information and emotional information about the child and transmit that information to the server.

[1667] The "analysis means" is a means for analyzing the basic information and emotional information of the child received from the terminal means and generating learning content based on the results.

[1668] A "generative AI model" is an artificial intelligence model that generates learning content suitable for children based on analyzed information.

[1669] "Generative means" means a means for creating customized learning content using a generative AI model.

[1670] The "transmission means" is a means for transmitting the generated study content to the terminal means.

[1671] The "display means" refers to a means for visually presenting the study content received by the terminal means to the user.

[1672] The "emotion engine" is an engine that acquires emotion data from the user's facial expressions and voice information and evaluates their emotional state.

[1673] "Emotion information" is information about the emotional state analyzed based on data acquired from the user's facial expressions and voice.

[1674] The present invention is a system for generating and providing individually customized learning content based on basic information about a child and emotional information about a user. The following describes an embodiment of this system.

[1675] Basic system configuration

[1676] Children's information input method

[1677] The device provides a form for the user to enter basic information about the child, including the child's age, interests, current level of proficiency, etc. For example, the user can open a web browser, enter this information into the form, and click the submit button.

[1678] Data transmission and analysis

[1679] The terminal sends the entered data to the server in JSON or XML format. Specifically, the data is sent using an HTTP POST request. The server analyzes the received data, first validating it and checking that all required data is included. It then saves it in a database and waits for the analysis results. The Python pandas library can be used for analysis.

[1680] Acquiring and analyzing user emotion information

[1681] The device uses an emotion engine to acquire emotion data from the user's facial expressions and voice. For example, a webcam or microphone is used to collect the user's face and voice, which are then analyzed by the emotion engine. The acquired emotion data is then sent to the server again using an HTTP POST request. The server analyzes the emotion data provided by the emotion engine and evaluates the user's emotional state. A machine learning model can be used for this analysis.

[1682] Generating learning content

[1683] The server uses a generative AI model based on the child's basic information and the user's emotional data to generate appropriate learning content. For example, a generative AI model such as GPT-3 can be used, and a prompt such as "5-year-old child, interested in space" can be created and input into the model. Based on this prompt, simple questions and learning materials are generated.

[1684] Submitting and Viewing Learning Content

[1685] The server sends the generated learning content to the device, which then displays the received content on the screen and provides the user with the option to download or print it. For example, this can be achieved by displaying the content on a web page with download and print buttons.

[1686] Specific examples

[1687] Example 1: A 5-year-old child who loves space

[1688] The user enters information such as "Age: 5 years old" and "Interest: Space" into the device and sends it. The device then sends this to the server, which analyzes the input data and generates "easy space-related questions" and "coloring pages to learn the names of stars." The server then sends the generated learning content to the device, which then displays the content. In addition, an emotion engine is used to obtain emotional information while the user is learning, and if the user is enjoying the learning experience, this information is sent to the server, and more challenging questions are added to the next learning content.

[1689] Example 2: A 6-year-old child who loves animals

[1690] The user enters information such as "Age: 6 years old" and "Interest: animals" into the device and sends it. The device then sends this to the server, which analyzes the input data and generates questions about animal species and their characteristics, as well as puzzles to learn about each animal's habitat. The server then sends the generated learning content to the device, which then displays it. The device also uses an emotion engine to obtain the child's emotions in real time and offers relaxing activities if the child is tired.

[1691] Examples of prompt statements

[1692] 1. "My child is 5 years old and is interested in space. What educational content can you provide him?"

[1693] 2. "What materials would be appropriate for a 6-year-old child to learn about animals?"

[1694] In this way, by combining a generative AI model with an emotion engine, this system can customize and provide learning content according to a child's interests, proficiency level, and even emotional state.

[1695] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1696] Step 1: Enter your child's information

[1697] The user uses the device to enter basic information about their child. Specifically, the user opens a web browser and enters the child's age, interests, and current level of proficiency in the form that appears. This input form includes text boxes and drop-down menus, and once the input is complete, the information is sent by clicking the submit button.

[1698] Input: Child's age, topics of interest, current level of proficiency

[1699] Output: Structured data (e.g., JSON format)

[1700] Step 2: Sending data

[1701] The terminal sends the input structured data to the server. Specifically, the data is sent using an HTTP POST request. This request includes the user's input information.

[1702] Input: Structured data (e.g., JSON format)

[1703] Output: Send data to the server

[1704] Step 3: Analyze the data

[1705] The server analyzes the received data. Specifically, it first validates the data to check whether it contains all the required data. It then saves it in the database and waits for the analysis results. This analysis can be done using Python's pandas library or SQL.

[1706] Input: Data submitted by the user

[1707] Output: Data validation results, saved to database

[1708] Step 4: Obtaining user emotion information

[1709] The device uses an emotion engine to acquire emotion data from the user's facial expressions and voice in real time. For example, it uses a webcam or microphone to collect the user's face and voice and analyzes them. This analysis is performed by the emotion engine.

[1710] Input: User's facial expressions and voice information

[1711] Output: Emotion data (e.g., happiness, sadness)

[1712] Step 5: Send and analyze emotion data

[1713] The device sends the acquired emotion data to the server, again using an HTTP POST request. The server analyzes the emotion data provided by the emotion engine and evaluates the user's emotional state. A machine learning model can be used for the analysis.

[1714] Input: Emotion data

[1715] Output: Evaluation of the user's emotional state

[1716] Step 6: Generate learning content

[1717] The server uses a generative AI model based on the child's basic information and the user's emotional data to generate appropriate learning content. Specifically, the server creates a prompt for the generative AI model: "A 5-year-old child interested in space." This prompt is then input into the model. Based on this prompt, simple questions and learning materials are generated.

[1718] Input: Basic information about the child, user's emotional data

[1719] Output: Generated learning content

[1720] Step 7: Submit and view your learning content

[1721] The server sends the generated learning content to the device. Specifically, it sends the content using an HTTP response. The device displays the received content on the screen and offers the user the option to download or print it. Specifically, this is achieved by displaying the content on a web page and providing download and print buttons.

[1722] Input: Generated learning content

[1723] Output: The learning content displayed to the user, with options to download and print

[1724] (Application example 2)

[1725] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1726] In conventional factories, only standardized education and training has been provided to improve individual worker capabilities and work efficiency. However, because optimal support varies depending on the worker's level of proficiency and emotional state, the effectiveness of a one-size-fits-all approach has been limited. In particular, in work environments where workers are prone to fatigue and stress, individually customized support is important. The objective of this invention is to provide a system that improves worker efficiency and satisfaction by providing individually customized support content based on the worker's basic information and emotional information.

[1727] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1728] In this invention, the server includes terminal means for inputting basic information about the worker, analysis means for receiving the basic information about the worker sent from the terminal means and analyzing the information, emotion engine means for acquiring emotional information about the worker, analysis means for receiving the emotional information sent from the emotion engine means and analyzing the information, generation means for generating customized assistance content using a generative AI model based on the analyzed basic information and emotional information, transmission means for transmitting the generated assistance content to the terminal means, and display means for displaying the assistance content received by the terminal means and providing it to the worker. This makes it possible to provide optimal work assistance and relaxation content based on the basic information and real-time emotional information of the worker.

[1729] "Basic information about workers" refers to information about the individual characteristics of workers, such as their age, work experience, specialties, and problems.

[1730] "Terminal means" refers to an electronic device for inputting and transmitting basic information about workers.

[1731] The "analysis means" is a processing device or software for receiving and analyzing information sent from the terminal means.

[1732] The "emotion engine means" is a device or software that uses sensors such as a camera and a microphone to obtain emotional information from the facial expressions and voices of workers.

[1733] The "generation means" refers to a processing device or software that uses a generative AI model to generate customized assistance content based on the analyzed basic information and emotional information.

[1734] The "transmission means" is a communication device or software for transmitting the generated assistance content to the terminal means.

[1735] The "display means" is a device or software that displays the support content received by the terminal means on a screen and provides it to the worker.

[1736] A "generative AI model" is a model that uses machine learning algorithms to automatically generate content tailored to a specific purpose based on input data.

[1737] "Support content" is information for work support and relaxation that is individually customized based on the worker's basic information and emotional state.

[1738] The present invention is a system for providing individually customized support content based on basic information and emotional information of a worker. Specific embodiments of the present invention will be described in detail below.

[1739] Basic system configuration

[1740] Employee information input method

[1741] The terminal means provides a form for inputting basic information about the worker. The basic information about the worker includes age, work experience, specialty work, current problems, etc. For example, information such as "Age: 35 years old," "Work experience: 10 years," "Specialty work: assembly," and "Problem: inspection work takes a long time" is input.

[1742] Data transmission and analysis

[1743] The terminal means sends the input data to the server. The data is structured in, for example, JSON or XML format. The server analyzes the data received from the terminal. Analysis includes data validation and saving to a database.

[1744] Acquiring and analyzing worker emotion information

[1745] The emotion engine means acquires emotion data from the worker's facial expressions and voice information using a camera and microphone mounted on the terminal means. The emotion information includes fatigue, stress, concentration, etc. The terminal means transmits the acquired emotion data to the server. The server analyzes the emotion data provided by the emotion engine means and evaluates the worker's emotional state.

[1746] Support content generation

[1747] The server uses the analysis results to generate support content tailored to the worker using a generative AI model. The generative AI model adjusts the support content based on the worker's basic information and emotional state. For example, if the worker is tired, it will suggest relaxing stretches, and if the worker is working and requires concentration, it will provide specific advice to improve efficiency.

[1748] Sending and displaying support content

[1749] The server transmits the generated support content to the terminal means. The terminal means displays the received support content on a screen and provides it to the worker. For example, the display may say, "Please perform relaxing stretches for five minutes."

[1750] Hardware and software used

[1751] Hardware: Camera, microphone, and display attached to the robot

[1752] software:

[1753] Emotion engine: Software that processes data from the camera and microphone to assess emotional state

[1754] Generative AI model: A machine learning model that generates optimal support content based on basic and emotional information about the worker.

[1755] Server: API that analyzes data and generates support content

[1756] Specific examples

[1757] Example 1: Content creation flow for worker "Factory Worker A"

[1758] The factory's robot AI reads the facial expression of "Worker A" and detects that he is tired.

[1759] The data is analyzed on the server and content is generated that suggests relaxing stretches for "Worker A."

[1760] The robot calls out, "Mr. A, you look tired. Would you like to try stretching for five minutes?"

[1761] Example prompt sentence:

[1762] Design a system in which a factory robot analyzes the emotions of "Factory Worker A" from his facial expressions and voice, and suggests relaxing stretches to the worker. Specifically, the system will include a process in which the worker's basic information is input, emotional data is acquired in real time using an emotion engine, customized support content is generated using a generative AI model, and finally the robot provides the support content on a screen or via voice.

[1763] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1764] Step 1:

[1765] The user inputs basic information about the worker on the terminal and submits it. The input data includes age, work experience, specialties, problems, etc. This information is structured in JSON or XML format and sent to the server.

[1766] Input: Basic information of the worker (age, work experience, specialty, problems)

[1767] Output: JSON or XML data sent to the server

[1768] Step 2:

[1769] The server analyzes the received worker's basic information, performs data validation (format check, missing value check, etc.), and stores the data in the database if it is in the correct format.

[1770] Input: Basic information about the worker (JSON or XML data)

[1771] Output: Worker information stored in the database

[1772] Step 3:

[1773] Using the camera and microphone installed in the terminal, the emotion engine means acquires emotion data from the worker's facial expressions and voice information, using facial recognition and voice analysis of the worker.

[1774] Input: Camera video, audio data

[1775] Output: Emotion data (e.g., tiredness, stress, concentration)

[1776] Step 4:

[1777] The device sends the acquired emotion data to the server, which in turn structures the data in JSON or XML format.

[1778] Input: Emotion data (data obtained in real time)

[1779] Output: JSON or XML data sent to the server

[1780] Step 5:

[1781] The server analyzes the emotion data provided by the emotion engine means and uses the analysis results to evaluate the worker's emotional state.

[1782] Input: Emotion data (JSON or XML data)

[1783] Output: Evaluation result (e.g., worker's current emotional state)

[1784] Step 6:

[1785] The server uses a generative AI model based on the analysis results (basic information and emotional state of the worker) to generate customized support content. The generative AI model creates appropriate support content according to the worker's situation.

[1786] Input: Basic information and emotional state (evaluation results)

[1787] Output: Generated assistance content

[1788] Step 7:

[1789] The server sends the generated support content to the device in HTML or JSON format, which is suitable for display.

[1790] Input: Generated assistance content

[1791] Output: Support content (HTML or JSON data) sent to the device

[1792] Step 8:

[1793] The device then displays the received support content on its screen and provides it to the worker, such as advice on stretching techniques to relax or improving work efficiency.

[1794] Input: Received support content (HTML or JSON data)

[1795] Output: The display content provided to the worker

[1796] 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.

[1797] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. 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 voice, text data indicating text, and image data indicating an image is also input. 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.

[1798] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1799] 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.

[1800] FIG. 9 is a diagram illustrating 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 actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect 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.

[1801] 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.

[1802] 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).

[1803] 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 indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, 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 indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1804] 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."

[1805] 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.

[1806] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1807] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1808] 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.

[1809] 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.

[1810] 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.

[1811] The hardware resource for executing a specific process can be any of the following processors: An example of a processor 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. Another example of a processor is 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.

[1812] The hardware resource that executes the specific processing 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 processing may be a single processor.

[1813] 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.

[1814] 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.

[1815] 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.

[1816] 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.

[1817] The following is further disclosed regarding the above embodiment.

[1818] (Claim 1)

[1819] a terminal means for inputting basic information about a child;

[1820] analysis means for receiving the basic information of the child transmitted from the terminal means and analyzing the information;

[1821] a generating means for generating customized learning content using a generative AI model based on the analyzed information;

[1822] a transmitting means for transmitting the generated study content to the terminal means;

[1823] a display means for displaying the learning content received by the terminal means and providing it to the user;

[1824] A system including:

[1825] (Claim 2)

[1826] 2. The system according to claim 1, which automatically generates individually customized questions based on basic information about the child that is entered.

[1827] (Claim 3)

[1828] The system according to claim 1, wherein the received basic information of the child is analyzed and content is generated based on themes of interest and vocabulary that the child has not yet acquired.

[1829] "Example 1"

[1830] (Claim 1)

[1831] a terminal means for inputting basic information about a child;

[1832] analysis means for receiving the basic information of the child transmitted from the terminal means and analyzing the information;

[1833] a generating means for generating a prompt sentence using a generative AI model based on the analyzed information to generate customized learning content;

[1834] a transmitting means for transmitting the generated study content to the terminal means;

[1835] a display means for displaying the learning content received by the terminal means and providing it to the user in a downloadable or printable format;

[1836] A system including:

[1837] (Claim 2)

[1838] The system of claim 1, which automatically generates individually customized questions and teaching materials based on the basic information of the child that is entered.

[1839] (Claim 3)

[1840] The system according to claim 1, wherein the received basic information of the child is analyzed and content is generated based on the child's interests and learning content that the child has not yet mastered.

[1841] "Application Example 1"

[1842] (Claim 1)

[1843] a terminal means for inputting basic information about a child;

[1844] analysis means for receiving the basic information of the child transmitted from the terminal means and analyzing the information;

[1845] a generating means for generating customized learning content using a generative AI model based on the analyzed information;

[1846] a transmitting means for transmitting the generated study content to the terminal means;

[1847] a display means for displaying the learning content received by the terminal means and providing it to the user;

[1848] a terminal means for providing an option to download or print the learning content in response to a request from the user;

[1849] A system including:

[1850] (Claim 2)

[1851] 2. The system of claim 1, which automatically generates individually customized educational materials based on the basic information of the child that is input.

[1852] (Claim 3)

[1853] The system according to claim 1, wherein the received basic information of the child is analyzed and teaching materials are generated based on themes of interest and vocabulary that the child has not yet mastered.

[1854] "Example 2: Combining Emotion Engines"

[1855] (Claim 1)

[1856] a terminal means for inputting basic information about a child;

[1857] analysis means for receiving the basic information of the child transmitted from the terminal means and analyzing the information;

[1858] A generating means for generating customized learning content using a generating AI model based on the analyzed information and the user's emotional information;

[1859] a transmitting means for transmitting the generated study content to the terminal means;

[1860] a display means for displaying the learning content received by the terminal means and providing it to the user;

[1861] an emotion engine for acquiring emotion information from the user's facial expressions and voice;

[1862] means for transmitting the emotion information to a server and analyzing it;

[1863] A system including:

[1864] (Claim 2)

[1865] 2. The system according to claim 1, wherein the system automatically generates individually customized questions based on the input basic information of the child and the acquired emotional information of the user.

[1866] (Claim 3)

[1867] 2. The system according to claim 1, wherein the received basic information about the child and the user's emotional information are analyzed, and content is generated based on themes of interest and unlearned vocabulary.

[1868] "Application example 2 when combining emotion engines"

[1869] (Claim 1)

[1870] a terminal means for inputting basic information of workers;

[1871] an analysis means for receiving the basic information of the worker transmitted from the terminal means and analyzing the information;

[1872] emotion engine means for acquiring emotion information of the worker;

[1873] analysis means for receiving emotion information transmitted from the emotion engine means and analyzing the information;

[1874] a generation means for generating customized assistance content by using a generation AI model based on the analyzed basic information and emotional information;

[1875] a transmitting means for transmitting the generated assistance content to the terminal means;

[1876] a display means for displaying the support content received by the terminal means and providing it to the worker;

[1877] A system including:

[1878] (Claim 2)

[1879] 2. The system according to claim 1, wherein the system automatically generates individually customized support content based on the basic information and emotional information of the worker that is input.

[1880] (Claim 3)

[1881] The system according to claim 1, wherein the system analyzes the received basic information and emotional information of the worker and generates content that provides tips for improving work efficiency and relaxing activities. [Explanation of symbols]

[1882] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a terminal means for inputting basic information about a child; analysis means for receiving the basic information of the child transmitted from the terminal means and analyzing the information; a generating means for generating customized learning content using a generative AI model based on the analyzed information; a transmitting means for transmitting the generated study content to the terminal means; a display means for displaying the learning content received by the terminal means and providing it to the user; A system including:

2. 2. The system according to claim 1, wherein the system automatically generates individually customized questions based on the basic information of the child that is input.

3. The system according to claim 1, wherein the received basic information of the child is analyzed and content is generated based on themes of interest and vocabulary that the child has not yet acquired.

Images