System

Abstract

A system is provided.SOLUTION: A system comprising: means for obtaining a profile of a child; means for applying a generative AI model to generate a learning program and a plaything program based on the profile; means for transmitting the generated learning program and plaything program to a school-child facility; and means for receiving activity information of the child from the school-child facility and automatically generating a report for office work.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] In recent years, staff shortages at after-school care facilities, ensuring children's safety, and providing an appropriate learning and play environment have become major issues. Providing adequate care and learning support is particularly difficult when there are a large number of children or when specific instructors are absent. Furthermore, as staff juggle a wide range of tasks, time and effort are spent managing children's learning progress and play, as well as administrative tasks, preventing them from concentrating on caring for and providing mental support to children, which should be their primary focus. This increases the risk of adversely affecting children's development and learning environment, making it necessary to resolve these issues. [Means for solving the problem]

[0005] The present invention provides an after-school support system that utilizes a generative AI model to reduce the burden on staff at after-school facilities and provide appropriate care and education to children. The system includes the following means:

[0006] 1. Means of obtaining child profile data.

[0007] 2. Means for applying generative AI models to generate learning and play programs based on said profile data.

[0008] 3. A means for transmitting the generated learning and play programs to terminals at the after-school facility.

[0009] 4. A means for receiving children's activity data from the terminals of the after-school facility and automatically generating reports for administrative work.

[0010] This will provide an environment where after-school care staff can focus on caring for children, providing mental support, and mediating when problems arise, while also making administrative work more efficient and reducing the overall workload.

[0011] "Child profile data" refers to individual information about children attending after-school care facilities, such as their age, characteristics, interests, and learning progress.

[0012] A "learning program" refers to the learning content and materials that are individually set based on a child's profile data.

[0013] "Play programs" refer to play activities and games that are individually tailored based on a child's profile data.

[0014] A "generative AI model" refers to an artificial intelligence (AI) algorithm that automatically generates learning or play programs based on specified prompts.

[0015] "After-school facility terminals" refers to electronic devices such as computers and tablets used within after-school facilities.

[0016] "Reports for administrative work" refers to documents such as daily and weekly reports that are automatically generated based on children's activity data.

[0017] "Data packaging" refers to the process of combining multiple pieces of data into one package.

[0018] "Alert" refers to a warning notification that is displayed when a specific condition is met.

[0019] "AI assistant" refers to an artificial intelligence agent that acts as a virtual mentor, created based on a generative AI model. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] The present invention relates to an after-school support system that utilizes generative AI models to reduce the burden on staff at after-school care facilities and provide appropriate care and education for children. This system acquires children's profile data, generates learning and play programs based on that data, and distributes the data to terminals at the after-school care facility. A specific example of this system is described below.

[0042] Server-side processing

[0043] 1. Collecting and normalizing child profile data

[0044] The server retrieves profile data for each child from the after-school care facility's database. This profile data includes the child's age, learning progress, interests, and characteristics. The retrieved profile data is converted into a unified format that is easy for the generative AI model to process.

[0045] 2. Applying generative AI models

[0046] The server generates prompts for the generative AI model based on the normalized profile data. These prompts are instructions for generating learning and play programs appropriate for each child. The generative AI model receives these prompts, automatically generates learning and play programs, and returns them to the server.

[0047] 3. Creation of AI school assistants

[0048] The server generates an AI assistant based on the generated learning and play programs. This AI assistant is designed to assist children in learning and play while interacting with them. The appearance, voice, and speaking style of the AI ​​assistant are set based on specific parameters.

[0049] 4. Data transmission

[0050] The server combines the generated learning program, play program, and AI after-school assistant into a single data package and sends this package to a terminal at the after-school facility.

[0051] 5. Support for administrative work

[0052] The server automatically generates reports necessary for administrative work based on the activity data of children sent from the after-school care facility, thereby reducing the workload of instructors.

[0053] Terminal side processing

[0054] 1. Displaying received data

[0055] The terminal receives the data package sent from the server. This data package includes learning programs, play programs, and AI school assistants. The terminal analyzes the data and displays it appropriately.

[0056] 2. Starting and interacting with the AI ​​after-school assistant

[0057] The device then activates the AI ​​assistant, who interacts with the child to support their learning and play. The AI ​​assistant observes the child's reactions and sends the data to a server in real time.

[0058] 3. Status Notification

[0059] The devices monitor the children's behavior and reactions and notify teachers when certain conditions are met, such as an immediate alert if a fight breaks out or if a certain time has passed.

[0060] User (instructor) perspective

[0061] 1. Check and correct the program

[0062] The user (instructor) checks the learning and play programs displayed on the device and fine-tunes the settings as necessary, allowing them to provide appropriate support to each child.

[0063] 2. Collaboration with AI assistants

[0064] Users can work with AI after-school assistants to manage the progress of their children's studies and play, allowing them to focus on caring for their children, providing mental support, and mediating when problems arise.

[0065] 3. Checking and using the report

[0066] Users can check automatically generated reports provided by the server to understand the status of their children, and can use these reports to report to parents and schools, thereby streamlining operations.

[0067] Specific examples

[0068] For example, if a child is good at math and likes soccer, the server will generate a math problem set and a soccer-related indoor game based on that child's profile data. The device receives these programs, and the AI ​​school assistant asks the child math problems and suggests soccer games when the child gets bored. The user (instructor) monitors this process and provides support as needed.

[0069] As a result, the present invention reduces the burden on staff at after-school care facilities and provides high-quality care and education for children.

[0070] The processing flow will be explained below.

[0071] Server-side processing

[0072] Step 1: Collecting child profile data

[0073] The server obtains each child's profile data (age, interests, learning progress, etc.) from the after-school facility's database.

[0074] Step 2: Normalize the data

[0075] The server converts the acquired profile data into a unified format, making it easy for the generative AI model to process.

[0076] Step 3: Generate prompts

[0077] The server generates prompts to input into the generative AI model based on the normalized profile data.

[0078] Step 4: Generate Request

[0079] The server sends the generated prompts to the generative AI model, requesting it to generate learning and play programs.

[0080] Step 5: Receive the generated results

[0081] The server receives the learning programs and play programs returned from the generative AI model and stores them appropriately.

[0082] Step 6: Generate AI school assistants

[0083] The server generates an AI school assistant based on the generated learning and play programs, with the specified appearance, voice, and speaking style. Multiple assistants are generated as needed.

[0084] Step 7: Packaging the Data

[0085] The server combines the generated learning programs, play programs, and AI school assistants into a single package.

[0086] Step 8: Sending Data

[0087] The server transmits the packaged data to the terminal at the after-school facility.

[0088] Step 9: Receiving and processing activity data

[0089] The server receives the children's activity data sent from the after-school care facility and compiles it into statistical information and reports required for administrative work.

[0090] Step 10: Generate reports

[0091] The server checks the automatically generated report and provides it to the instructor.

[0092] Terminal side processing

[0093] Step 1: Receiving Data

[0094] The terminal receives data packages of learning programs, play programs, and AI school assistants sent from the server.

[0095] Step 2: Analyze and display the data

[0096] The device analyzes the received data and displays information appropriate for each child in an appropriate format.

[0097] Step 3: Launching the AI ​​School Assistant

[0098] The device then runs the received AI school assistant program and interacts with the children using the specified appearance and voice.

[0099] Step 4: Dialogue monitoring

[0100] The device monitors the conversation between the AI ​​school assistant and the child, and transmits the child's reaction data to a server in real time.

[0101] Step 5: Configure alerts

[0102] The device sets an alert based on set conditions (e.g., when a specific behavior is observed or when there is no response for a certain period of time).

[0103] Step 6: Send notification

[0104] The device immediately sends a notification to the instructor when the set alert conditions are met.

[0105] User (instructor) perspective

[0106] Step 1: Check the program

[0107] The user (instructor) checks the learning and play programs displayed on the terminal and fine-tunes the settings as necessary.

[0108] Step 2: Collaborate with AI assistants

[0109] Users can work with AI after-school assistants to manage the progress of their children's studies and play, allowing them to focus on caring for their children, providing mental support, and mediating when problems arise.

[0110] Step 3: Review and use the report

[0111] The user checks the automatically generated reports provided by the server to understand the child's situation, and reports to parents and schools based on these reports.

[0112] Through these steps, the AI ​​support system in after-school care facilities will reduce the burden on staff and ensure high-quality care for children.

[0113] Example 1

[0114] 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."

[0115] There is a need to reduce the burden on staff at after-school care facilities and provide high-quality care and education to children. Previous systems struggled to quickly and efficiently provide learning and play programs tailored to each child, and the administrative burden of managing children's activity data was significant. Furthermore, the application of AI after-school assistants lacked the ability to provide support for children's interactions.

[0116] 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.

[0117] In this invention, the server includes means for acquiring child profile data, means for converting and normalizing the profile data into a unified format, means for generating prompts based on the normalized profile data and applying them to the generative AI model, means for generating an AI after-school assistant based on the generated learning program and play program, means for transmitting the learning program, play program, and the generated AI after-school assistant to a terminal at the after-school facility, and means for receiving child activity data from the terminal at the after-school facility and automatically generating reports for administrative work. This reduces the burden on staff at the after-school facility, improves the quality of individualized care and education for children, and makes administrative work more efficient.

[0118] "Child profile data" means data that includes individual characteristics and information about a child, such as the child's age, learning progress, interests, and characteristics.

[0119] "Normalization" is the process of converting acquired profile data into a unified format to maintain data consistency.

[0120] A "prompt" is an input sentence in the form of text or a question that provides instructions to a generative AI model.

[0121] A "generative AI model" is an artificial intelligence model that automatically generates learning or play programs based on given prompts.

[0122] The "AI School Assistant" is an artificial intelligence character that interacts with children to assist them in learning and play, based on learning and play programs generated from a generative AI model.

[0123] "After-school facility terminal" refers to a hardware device such as a computer or tablet used within the after-school facility, and is a device that receives and displays data sent from the server.

[0124] "Child activity data" refers to data on children's reactions and behavior when participating in learning programs or play programs.

[0125] "Administrative work" refers to back-office work such as managing operations and preparing reports at after-school care facilities.

[0126] A "report" is an automatically generated report based on a child's activity data, and is a document containing information provided to instructors, parents, and schools.

[0127] This invention relates to an after-school support system that utilizes generative AI models to reduce the burden on staff at after-school care facilities and provide high-quality care and education to children. This system is composed of a server, a terminal, and a user's perspective, and each process functions in cooperation with each other.

[0128] Server Roles and Operations

[0129] The server accesses the after-school facility's database to obtain the child's profile data. This profile data includes the child's age, learning progress, interests, and characteristics. First, the data is converted into a unified format and normalized. Next, the server generates a prompt based on the normalized profile data. This prompt is used to provide instructions to the generative AI model and is written in the following text format:

[0130] Example prompt sentence:

[0131] "This child is 10 years old, good at math, and loves soccer. Use this profile to generate appropriate learning and play programs."

[0132] The server sends these prompts to a generative AI model, which then automatically generates appropriate learning and play programs based on the prompts. The generated programs are then returned to the server, which then generates an AI school assistant based on these programs. This assistant is designed to interact with children and support them in their learning and play.

[0133] The generated learning programs, play programs, and AI after-school assistants are compiled into a single data package and sent to the after-school facility's terminal. The server also automatically generates reports for administrative work based on the children's activity data sent from the after-school facility, improving work efficiency.

[0134] Terminal roles and processing

[0135] The device receives data packages sent from the server, analyzes them, and displays learning programs, play programs, and AI school assistants. The device launches the AI ​​school assistant, and the user (instructor) supports learning and play by interacting with the children through this assistant. The AI ​​assistant observes the children's reactions and behavior and sends the data to the server in real time.

[0136] For example, the AI ​​assistant might say, "Hello! Let's solve some math problems together today, and then we'll have a soccer quiz," attracting the child's interest while progressing the learning process. Additionally, if certain conditions are met, the device will immediately notify the instructor. For example, if a fight breaks out, it will issue an alert saying, "A fight has just broken out."

[0137] User (instructor) roles and processes

[0138] The user (instructor) checks the learning and play programs displayed on the device and fine-tunes the settings as needed. For example, if a math problem is too difficult, the difficulty level can be adjusted. The user works with the AI ​​after-school assistant to manage the children's learning and play progress. This allows the user to focus on caring for the children, providing mental support, and mediating when problems arise.

[0139] In addition, automatically generated reports provided by the server can be checked to understand the child's situation in detail, and these reports can be used to report to parents and schools, making work more efficient.

[0140] Specific examples

[0141] For example, if a child is good at math and likes soccer, the server will generate a math problem set and soccer-related indoor games based on the child's profile data. A prompt based on this profile might be something like, "This child is 10 years old, good at math, and likes soccer. Please generate appropriate learning and play programs based on this profile."

[0142] The device receives these programs, and the AI ​​assistant asks the children math problems and suggests playing soccer when they get bored. The user (instructor) monitors this process and provides support to the children as needed.

[0143] As a result, the present invention reduces the burden on staff at after-school care facilities and provides high-quality care and education for children.

[0144] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0145] Step 1:

[0146] The server accesses the database of the after-school care facility and retrieves profile data for each child. This profile data includes the child's age, learning progress, interests, characteristics, etc. It receives profile data from the database as input and retrieves profile data as output. Specifically, it extracts the required information from the database using SQL queries.

[0147] Step 2:

[0148] The server converts and normalizes the acquired profile data into a unified format. In this process, for example, age is standardized into a "number" format and interests into a "comma-separated keywords" format. It receives raw profile data as input, processes the data, and then outputs normalized profile data. Specifically, it applies data conversion rules to unify the format.

[0149] Step 3:

[0150] The server generates the prompts required for the generative AI model based on the normalized profile data. It receives the normalized profile data as input and obtains the generated prompt as output. Specifically, it creates a prompt such as, "This child is 10 years old, good at math, and likes soccer. Please generate appropriate learning and play programs based on this profile."

[0151] Step 4:

[0152] The server sends prompts to the generative AI model and automatically generates learning and play programs. It receives the generated prompts as input and obtains the generated learning and play programs as output. Specifically, it sends API requests to the generative AI model and analyzes the response.

[0153] Step 5:

[0154] The server generates an AI school assistant based on the generated learning and play programs. This AI assistant is designed to support learning and play while interacting with children. It receives learning and play programs as input and generates an AI school assistant as output. Specific operations are performed using a voice synthesis engine and character generation tools.

[0155] Step 6:

[0156] The server combines the generated learning program, play program, and AI school assistant into a single data package. This data package is then sent to the terminal. The server receives the learning program, play program, and AI school assistant as input, and obtains a combined data package as output. Specifically, the server combines the data into a format such as JSON and sends it to the terminal using the HTTP protocol.

[0157] Step 7:

[0158] The device receives the data package sent from the server, analyzes it, and displays the learning program, play program, and AI school assistant. It receives the data package as input and displays the analyzed data as output. Specifically, it parses the received data using a JSON parser and displays it on the user interface.

[0159] Step 8:

[0160] The device then activates the AI ​​assistant and has it interact with the children to support their learning and play. It receives the AI ​​assistant as input and starts a dialogue as output. Specific operations include playing the AI ​​assistant's voice and displaying an animated user interface.

[0161] Step 9:

[0162] The device observes the child's reactions and behavior and sends the data to the server in real time. It receives the child's reaction data as input and obtains the transmitted data as output. Specifically, it analyzes the data obtained from sensors and cameras and sends it to the server via an HTTP request.

[0163] Step 10:

[0164] The device notifies the instructor when certain conditions are met. It receives student behavior data and event triggers as input and issues an alert as output. Specific actions include displaying a pop-up message or audio alert on the UI.

[0165] Step 11:

[0166] The user (instructor) checks the learning program and play program displayed on the terminal and fine-tunes the settings as necessary. The displayed program is received as input and the fine-tuned settings are reflected as output. Specific operations involve operating the setting panel on the UI and adjusting the parameters.

[0167] Step 12:

[0168] The user checks the automatically generated report provided by the server and understands the child's situation in detail. The automatically generated report is received as input, and the understood information is obtained as output. Specifically, the user browses the contents of the report and extracts the necessary information.

[0169] (Application example 1)

[0170] 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."

[0171] In today's after-school care facilities, staff are required to handle a wide range of tasks, particularly providing academic guidance and play support to individual children, as well as the administrative work of understanding each child's situation and reporting it to parents and schools, which places a heavy burden on staff. Similarly, in brick-and-mortar stores, it is difficult to provide personalized product recommendations and services to each customer, and measures to increase customer satisfaction are lacking. Furthermore, there is a lack of a way to centrally manage and effectively utilize this data.

[0172] 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.

[0173] In this invention, the server includes: means for acquiring child profile data; means for applying a generative AI model to generate learning programs and play programs based on the profile data; means for transmitting the generated learning programs and play programs to a terminal at the after-school facility; means for receiving child activity data from the terminal at the after-school facility and automatically generating reports for administrative work; means for collecting customer profile data from multiple physical stores and applying a generative AI model to generate product proposals and service details based on the profile data; means for transmitting the generated product proposals and service details to a terminal at the physical store; and means for receiving customer response data from the terminal at the physical store and automatically generating reports required for the physical store's operations. This not only reduces the burden on staff at the after-school facility and enables the provision of high-quality care and education for children, but also enables the physical store to quickly and efficiently provide personalized product proposals and services to each customer.

[0174] "Profile Data" means information about a child or customer, including their age, gender, interests, and past activity.

[0175] A "learning program" is a program that includes teaching materials and teaching methods that are automatically generated by a generative AI model to provide children with appropriate learning content and methods.

[0176] A "play program" is a program that includes play and recreational activities that is automatically generated by a generative AI model based on a child's interests and characteristics.

[0177] A "generative AI model" is an artificial intelligence model that automatically generates appropriate output (learning programs, play programs, product suggestions, service content, etc.) based on input data.

[0178] A "terminal" is a hardware device used to display and process data, specifically a computer or smart device installed in an after-school facility or brick-and-mortar store.

[0179] "Activity data" is a record of the specific actions and reactions that children and customers take while studying, playing, shopping, etc.

[0180] A "report" is a document that summarizes the activities, grades, and reactions of children or clients, and is used to streamline administrative and management tasks.

[0181] "Product suggestions" are recommendations of products suitable for a specific customer, generated by a generative AI model based on customer profile data.

[0182] "Service content" refers to details of the services to be provided to a specific customer, generated by the generative AI model based on the customer's profile data and response data.

[0183] The following system configuration is used as an embodiment of the present invention.

[0184] System Overview

[0185] This system consists of a server, terminals installed in physical stores and after-school care facilities, and users (instructors and store staff) who operate them.

[0186] Server Processing

[0187] 1. Profile Data Collection and Normalization:

[0188] The server collects profile data of children or customers from after-school care facilities and multiple physical stores, including age, gender, interests, and past activity history.

[0189] The collected data is normalized into a unified format, making it easier for generative AI models to process.

[0190] 2. Applying generative AI models:

[0191] Based on the normalized profile data, the server generates prompts, which in turn generate learning and play programs suited to each child, as well as product suggestions and service content suited to each customer.

[0192] The generative AI model receives this prompt, automatically generates an appropriate program or suggestion, and returns it to the server.

[0193] 3. Data submission and reporting:

[0194] The generated programs and proposals are sent to terminals at after-school facilities and physical stores.

[0195] The server also receives activity data sent from after-school care facilities and brick-and-mortar stores and automatically generates reports for administrative work, thereby reducing the workload of instructors and store staff.

[0196] Terminal handling

[0197] 1. Displaying received data:

[0198] The terminal receives the data package sent from the server and appropriately displays learning programs and play programs for the children and product suggestions and service contents for the customers.

[0199] 2. Activating and interacting with the AI ​​assistant:

[0200] Based on the received program and suggestions, the AI ​​assistant will be activated and will support the child in their learning and play through dialogue, as well as recommend the most suitable products to the customer and answer any questions.

[0201] 3. Real-time data transmission:

[0202] The device transmits real-time reaction data from children and customers to a server, allowing for further data analysis.

[0203] User Roles

[0204] 1. Check and correct the program:

[0205] Instructors and store staff can check the programs and suggestions displayed on the terminals and make adjustments as necessary, thereby providing optimal support for each child or customer.

[0206] 2. Collaboration with AI assistants:

[0207] Instructors and store staff will work with AI assistants to streamline their daily work, and the AI ​​assistants will automatically communicate and guide customers, minimizing human intervention.

[0208] 3. Review and use the report:

[0209] Automatically generated reports provided by the server are used to understand children's learning progress and customer purchasing behavior, simplifying reporting to parents and companies and improving operational efficiency.

[0210] Specific examples

[0211] For example, if a schoolchild is good at math and likes soccer, the server can generate a prompt like this based on their profile data:

[0212] "Age: 8 Gender: Male Interests: Math and sports"

[0213] Based on this prompt, the generative AI model automatically generates math puzzles and soccer-related indoor games. Meanwhile, as an example of application in a physical store, the model suggests the latest sportswear and new cosmetics to a 30-year-old female customer based on the prompt: "Age: 30, Gender: Female, Interests: Sports and Fashion."

[0214] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0215] Step 1:

[0216] The server collects customer or child profile data from brick-and-mortar stores and after-school care facilities. This data includes age, gender, past activity history, interests, etc. The input is the raw data sent from each facility, and the output is pre-processed data for normalization.

[0217] Step 2:

[0218] The server normalizes the collected profile data. The input is the preprocessed data obtained in step 1, and the output is data in a unified format. Data normalization converts the data into a form that is easy for the generative AI model to process.

[0219] Step 3:

[0220] The server generates prompts based on the normalized profile data. The input is the normalized data, and the output is prompts to be used as input to the generative AI model. The prompts follow a specific template to appropriately describe the data.

[0221] Step 4:

[0222] The server inputs prompts into the generative AI model to generate learning programs, play programs, product suggestions, and service content. The input is the prompt, and the output is the appropriate program or suggestion. The generative AI model generates a response based on the specified prompt.

[0223] Step 5:

[0224] The server compiles the generated programs and proposals and sends them to terminals at the after-school care facility or physical store. The input is each generated program and proposal, and the output is the transmitted data package. This data package contains the program contents and proposals.

[0225] Step 6:

[0226] The terminal receives the data package sent from the server and displays the program or suggestion content appropriately. The input is the data package from the server, and the output is the displayed content.

[0227] Step 7:

[0228] Based on the received information, the terminal activates an AI assistant and interacts with the child to support learning and play. It also provides optimal product recommendations and service information to customers. The input is the program and recommendations received from the server, and the output is a response to the child or customer.

[0229] Step 8:

[0230] The user (instructor or store staff) checks the content displayed on the terminal and fine-tunes the program and suggestions as necessary. The input is the data displayed on the terminal, and the output is the adjusted program and suggestions.

[0231] Step 9:

[0232] The terminal transmits the reaction and behavior data of the children or customers to the server in real time. The input is the real-time reaction data of the children or customers, and the output is the data transmitted to the server.

[0233] Step 10:

[0234] The server analyzes the received reaction data and automatically generates a new report. The input is real-time reaction data, and the output is an automatically generated report. This report helps instructors and store staff improve their work efficiency.

[0235] The above is a detailed explanation of the application process, broken down into specific steps, that will lead to the creation of an effective support system that utilizes generative AI models and prompts.

[0236] 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.

[0237] The present invention relates to an after-school support system that generates learning and play programs based on children's profile data and further combines an emotion engine to analyze and recognize children's emotions, thereby providing more detailed support. This system utilizes children's profile data and applies a generative AI model and emotion engine to support learning and play, with the aim of reducing the burden on staff at after-school facilities. A specific example of this system is described below.

[0238] Server-side processing

[0239] 1. Collecting and normalizing child profile data

[0240] The server retrieves each child's profile data from the after-school facility's database. This profile data includes the child's age, learning progress, interests, and characteristics. The retrieved profile data is converted into a unified format that is easy for the generative AI model and emotion engine to process.

[0241] 2. Applying generative AI models

[0242] The server generates prompts for the generative AI model based on the normalized profile data. These prompts serve as instructions for generating learning and play programs appropriate for each child. The generative AI model receives the prompts, automatically generates learning and play programs, and returns them to the server.

[0243] 3. Applying the Emotion Engine

[0244] The server uses an emotion engine to analyze the child's facial expressions and tone of voice, allowing it to understand the child's emotional state in real time and adaptively adjust learning and play programs.

[0245] 4. Creation of AI school assistants

[0246] The server generates an AI school assistant based on the generated learning and play programs, as well as emotional data generated by the emotion engine. This AI school assistant supports children in their studies and play while interacting with them, and also provides mental care based on the emotional data.

[0247] 5. Sending and Receiving Data

[0248] The server compiles the generated learning programs, play programs, and AI after-school assistants into a single data package and sends it to the after-school facility's terminal. It also receives the children's activity data sent from the after-school facility and automatically generates reports necessary for administrative work.

[0249] Terminal side processing

[0250] 1. Data Receipt and Analysis

[0251] The device receives data packages (learning programs, play programs, AI school assistants, and emotional data) sent from the server, analyzes the received data, and displays it appropriately.

[0252] 2. Starting and interacting with the AI ​​after-school assistant

[0253] The device then activates the AI ​​assistant, who interacts with the child to support learning and play. Based on the emotional data analyzed by the emotion engine, the device responds adaptively to the child's emotional state.

[0254] 3. Monitoring Emotional Data

[0255] The device monitors the child's facial expressions and tone of voice in real time and uses an emotion engine to transmit emotional data to the server, allowing the device to grasp the child's emotional state in real time.

[0256] 4. Status Notification

[0257] The device sets an alert according to the set conditions (e.g., if a specific emotion continues or if there is a sudden change in emotion) and notifies the instructor as necessary.

[0258] User (instructor) perspective

[0259] 1. Check and correct the program

[0260] The user (instructor) checks the learning program, play program, and emotional data displayed on the device and fine-tunes the settings as needed, allowing them to provide appropriate support to each child.

[0261] 2. Collaboration with AI assistants

[0262] Users can work with AI after-school assistants to manage children's learning and play progress, and can focus on providing mental care for children and mediating when problems arise based on emotional data.

[0263] 3. Checking and using the report

[0264] The user checks the automatically generated reports provided by the server to understand the child's situation, and reports to parents and schools based on these reports.

[0265] Specific examples

[0266] For example, if a child is good at math and likes soccer, but has recently been feeling stressed, the server will generate a math problem set and a soccer-related indoor game based on the child's profile and emotional data. Furthermore, if the emotion engine analyzes that the child is feeling stressed, it will use that information to suggest activities and conversations that will help them relax. The device receives these programs, and the AI ​​school assistant will ask the child math problems and suggest activities to help them relax if they feel stressed. The user (instructor) monitors this process and provides additional support as needed.

[0267] As a result, the present invention reduces the burden on staff at after-school care facilities and provides high-quality care and education for children.

[0268] The processing flow will be explained below.

[0269] Server-side processing

[0270] Step 1: Collecting child profile data

[0271] The server obtains each child's profile data (age, interests, learning progress, characteristics, etc.) from the after-school facility's database.

[0272] Step 2: Normalize the data

[0273] The server converts the acquired profile data into a unified format, making it easier for the generative AI model and emotion engine to process.

[0274] Step 3: Generate prompts

[0275] The server generates prompts to input into the generative AI model based on the normalized profile data.

[0276] Step 4: Generate Request

[0277] The server sends the generated prompts to the generative AI model, requesting it to generate learning and play programs.

[0278] Step 5: Receive the generated results

[0279] The server receives the learning programs and play programs returned from the generative AI model and stores them appropriately.

[0280] Step 6: Applying the Emotion Engine

[0281] The server uses an emotion engine to analyze the child's facial expressions and tone of voice, thereby obtaining emotion data in real time.

[0282] Step 7: Generate AI school assistants

[0283] The server generates an AI school assistant based on the generated learning and play programs, as well as emotional data generated by the emotion engine. This AI school assistant responds adaptively according to the emotional state of the child.

[0284] Step 8: Packaging the Data

[0285] The server compiles the generated learning program, play program, AI school assistant, and emotional data into a single package.

[0286] Step 9: Sending Data

[0287] The server transmits the packaged data to the terminal at the after-school facility.

[0288] Step 10: Receiving and processing activity data

[0289] The server receives the children's activity data sent from the after-school care facility and compiles it into statistical information and reports required for administrative work.

[0290] Step 11: Generate reports

[0291] The server checks the automatically generated report and provides it to the instructor.

[0292] Terminal side processing

[0293] Step 1: Receiving Data

[0294] The terminal receives the learning program, play program, AI school assistant, and emotion data package sent from the server.

[0295] Step 2: Analyze and display the data

[0296] The device analyzes the received data and displays information appropriate for each child in an appropriate format.

[0297] Step 3: Launching the AI ​​School Assistant

[0298] The device then runs the received AI school assistant program and interacts with the children using the specified appearance and voice.

[0299] Step 4: Dialogue monitoring

[0300] The device monitors the conversation between the AI ​​school assistant and the child, and transmits the child's reaction data to a server in real time.

[0301] Step 5: Monitoring sentiment data

[0302] The device uses an emotion engine to analyze the child's facial expressions and tone of voice in real time and transmits the emotional data to a server.

[0303] Step 6: Configure alerts

[0304] The device sets an alert according to the set conditions (e.g., when a specific emotion continues or when there is a sudden change in emotion).

[0305] Step 7: Send notification

[0306] The device immediately sends a notification to the instructor when the set alert conditions are met.

[0307] User (instructor) perspective

[0308] Step 1: Check and correct the program

[0309] The user (instructor) checks the learning program, play program, and emotional data displayed on the terminal and fine-tunes the settings as necessary.

[0310] Step 2: Collaborate with AI assistants

[0311] Users can work with AI after-school assistants to manage the progress of children's studies and play, and use emotional data to focus on mental care and mediation when problems arise.

[0312] Step 3: Review and use the report

[0313] The user checks the automatically generated reports provided by the server to understand the child's situation, and reports to parents and schools based on these reports.

[0314] Specific examples

[0315] For example, if a child is good at math and likes soccer, but has recently been feeling stressed, the server will generate a math problem set and a soccer-related indoor game based on the child's profile and emotional data. Furthermore, if the emotion engine analyzes that the child is feeling stressed, it will use that information to suggest activities and conversations that will help them relax. The device receives these programs, and the AI ​​school assistant will ask the child math problems and suggest activities to help them relax if they feel stressed. The user (instructor) monitors this process and provides additional support as needed.

[0316] Example 2

[0317] 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."

[0318] Modern after-school care facilities are required to provide attentive support to each child while reducing the burden on staff. However, conventional systems have difficulty responding to the diverse needs of children and are limited in the adaptive scientific support that takes into account their emotional state. Therefore, a system is needed that can provide appropriate learning and play programs based on each child's individual characteristics and emotional state, and provide feedback on the effectiveness of these programs in real time.

[0319] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring personal information of children, means for converting the personal information into a unified format, means for applying a generative AI model to generate learning programs and play programs based on the unified personal information, means for generating and sending prompt sentences to the generative AI model, means for using an emotion engine to analyze the children's facial expressions and tone of voice and determine their emotional state, means for integrating the generated learning programs, play programs, and emotion data to generate an AI after-school assistant, means for transmitting the generated learning programs, play programs, and AI after-school assistant to a terminal at the after-school facility, and means for receiving children's activity data from the terminal at the after-school facility and automatically generating reports for administrative work. This makes it possible to provide learning and play programs that take into account the individual characteristics and emotional state of children and to adaptively adjust them in real time.

[0320] "Personal information of children" refers to data that represents individual characteristics of children, such as their age, learning progress, interests, and characteristics.

[0321] "Uniform format" means that data is converted into a consistent format that facilitates subsequent processing.

[0322] A "generative AI model" is an artificial intelligence model that automatically generates learning and play programs based on input prompts.

[0323] A "prompt" is a sentence used to instruct a generative AI model to produce a specific output.

[0324] The "emotion engine" is a system that analyzes a child's facial expressions and tone of voice to determine their emotional state.

[0325] The "AI School Assistant" is an artificial intelligence agent that supports children based on generated learning programs, play programs, and emotional data.

[0326] "After-school facility terminals" refer to devices such as computers and tablets used within the after-school facility.

[0327] "Activity data" is data collected during children's learning and play, including the progress and results of their activities.

[0328] "Reports for administrative work" are automatically generated business reports based on children's activity data, and are used to reduce the burden on staff.

[0329] This invention relates to an after-school support system that generates learning and play programs based on children's profile data and further analyzes and recognizes children's emotions by combining it with an emotion engine to provide more detailed support. This system aims to understand each child's individual characteristics and emotional state in real time, support their learning and play, and reduce the burden on staff at after-school facilities.

[0330] Server-side explanation

[0331] The server retrieves personal information about each child from the after-school care facility's database. This information includes the child's age, learning progress, interests, and characteristics. The retrieved data is converted into a unified format. By organizing it into a data frame using Python's Pandas library, the individual data is organized into a consistent, processable format.

[0332] Next, we generate a prompt to send to the generative AI model. Specifically, we generate a prompt in text format like this:

[0333] "Profile data: Age 10, Interests: Mathematics, Traits: High concentration. Please generate suitable learning and play programs."

[0334] The generated prompts are sent to a generative AI model (e.g., GPT-3), which then uses natural language processing technology to automatically generate learning and play programs for the child.

[0335] Furthermore, the server uses an emotion engine to analyze the child's facial expressions and tone of voice. The emotion analysis results indicate the child's real-time emotional state and are adaptively reflected in the learning and play programs. This analysis utilizes, for example, an emotion analysis service provided through an API.

[0336] Finally, the server integrates the generated learning and play programs with the emotional data generated from them to generate an AI school assistant. This AI school assistant provides support through dialogue with the children and also provides mental care based on the emotional data.

[0337] Terminal side explanation

[0338] The terminal receives the data package (learning program, play program, AI school assistant, emotional data) sent from the server, analyzes it, and displays it appropriately.

[0339] The device launches the AI ​​assistant and begins a dialogue with the child. The assistant presents learning and play programs to the child, while adaptively responding to the child's emotional state based on the analysis results of the emotion engine. Specifically, a dialogue system built using Python generates flexible responses based on the child's responses and emotional state.

[0340] The device also uses a camera and microphone to capture the child's facial expressions and tone of voice in real time, which are then sent to an emotion engine for analysis. The analysis results are then sent to a server for further adaptive responses.

[0341] Furthermore, the device will issue alerts in response to certain conditions (such as sustained stress levels or sudden emotional changes) and notify instructors as needed, enabling prompt response to problems and providing consistent support to children.

[0342] User (instructor) explanation

[0343] The user checks the learning and play programs and emotional data displayed on the device and makes fine adjustments as necessary. The system works in cooperation with AI after-school assistants to manage the children's progress in learning and play. The emotional data is also used to provide mental care for the children and respond to any problems that arise.

[0344] Users can also check automatically generated reports provided by the server to understand their child's progress, which can then be sent to parents and schools to provide consistent support and feedback to the child.

[0345] Specific examples

[0346] For example, consider a child who excels at math and loves soccer, but has recently been feeling stressed. In this case, the server generates a math workbook and a soccer-related indoor game based on the child's profile and emotional data. Furthermore, if the emotion engine analyzes that the child is feeling stressed, it will use that information to suggest activities and conversations that will help them relax.

[0347] The device receives these programs, and the AI ​​assistant asks the children math problems and suggests activities to relax them if they feel stressed. The user (instructor) monitors this process and provides additional support as needed.

[0348] As a result, the present invention reduces the burden on staff at after-school care facilities and enables high-quality care and education for children.

[0349] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0350] Step 1:

[0351] The server retrieves personal information about children from the after-school facility's database. The input data includes data such as the child's age, learning progress, interests, and characteristics, which are extracted from the after-school facility's database. This data is extracted using an SQL query to obtain the data. The output data is raw personal information data.

[0352] Step 2:

[0353] The server converts the acquired personal information into a unified format. The raw personal information data acquired in step 1 is used as input. Specifically, it uses the Python Pandas library to organize the data into a data frame. The output is the personal information data converted into a unified format.

[0354] Step 3:

[0355] The server generates a prompt sentence based on the unified personal information. The input is the unified personal information data obtained in step 2. As a specific operation, the prompt sentence is generated using Python's text manipulation functions. An example of a prompt sentence is generated as follows: "Profile data: age 10, interest: mathematics, characteristic: high concentration. Please generate suitable learning and play programs." The output is the generated prompt sentence.

[0356] Step 4:

[0357] The server sends the prompt sentence to the generative AI model to generate a learning program and a play program. The input is the prompt sentence generated in step 3. This is sent to the generative AI model (e.g., GPT-3) and the generated learning program and play program are received. The output is the generated learning program and play program.

[0358] Step 5:

[0359] The server uses an emotion engine to analyze the child's facial expression and tone of voice to determine their emotional state. The input is the child's facial expression image and voice data. Specifically, the server sends an emotion analysis request to the API and receives the analysis results. The output is the analyzed emotion data.

[0360] Step 6:

[0361] The server integrates the generated learning program, play program, and emotion data to generate an AI school assistant. The inputs are the learning program and play program generated in step 4 and the emotion data from step 5. A dialogue system is built using Python libraries (e.g., NLTK and spaCy) to prepare the AI ​​school assistant. The output is the generated AI school assistant.

[0362] Step 7:

[0363] The server sends the generated learning program, play program, and AI school assistant to the terminal at the after-school facility. The input is the learning program, play program, and AI school assistant obtained in step 6. Specifically, the server sends data packages using a network protocol (e.g., HTTP or WebSocket). The output is the data package sent to the terminal.

[0364] Step 8:

[0365] The terminal receives the data package sent from the server, parses it, and displays it appropriately. The input is the data package sent from the server. Specific operations include parsing the JSON data in Python and using a GUI to display it appropriately. The output is the displayed learning program, play program, and AI school assistant.

[0366] Step 9:

[0367] The terminal starts the AI ​​assistant and begins interacting with the child. The input is the AI ​​assistant received and displayed in step 8. Specifically, the AI ​​assistant presents learning and play programs to the child and provides support through interaction. The output is the result of the interaction with the child.

[0368] Step 10:

[0369] The device monitors the child's facial expressions and tone of voice in real time and sends the emotional data to the server using an emotion engine. The input is the child's facial expression images and voice data. Specific operations include collecting data using a camera and microphone and sending it to the emotion engine. The output is the analyzed emotional data.

[0370] Step 11:

[0371] The device sets alerts according to specific conditions and notifies the instructor as necessary. The input is the emotion data analyzed in step 10. The specific operation is to monitor the alert conditions and notify the instructor via email or SMS when the conditions are met. The output is the notification to the instructor.

[0372] Step 12:

[0373] The user checks the learning program, play program, and emotional data displayed on the device and fine-tunes the settings as needed. The input is the information displayed on the device. Specific actions include changing the settings in the GUI and supporting the child in cooperation with the AI ​​after-school assistant. The output is the adjusted learning program and play program.

[0374] Step 13:

[0375] The user manages the child's progress in learning and play, and provides mental care and responds to problems based on emotional data. The input is the child's activity data and emotional data. Specific actions include checking the activity record and providing support as needed. The output is the result of managing the child's progress.

[0376] Step 14:

[0377] The user checks the automatically generated report provided by the server and understands the child's situation. The input is the report provided by the server. The specific operation is to check the report and report it to the parents or school. The output is the report result.

[0378] As a result, the present invention reduces the burden on staff at after-school care facilities and enables high-quality care and education for children.

[0379] (Application example 2)

[0380] 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."

[0381] The present invention aims to improve the effectiveness of children's education and reduce the burden on after-school care facility staff by creating optimal learning and play programs based on each child's profile data and providing adaptive support through real-time analysis of the child's emotional state in a system that supports children's learning and play. Furthermore, the present invention aims to solve the problem of improving individual user experiences by applying emotion analysis to meal plans and menu suggestions.

[0382] 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.

[0383] In this invention, the server includes means for acquiring profile data of children, means for applying a generative AI model to generate learning programs and play programs based on the profile data, means for transmitting the generated learning programs and play programs to a terminal at the after-school facility, means for receiving activity data of children from the terminal at the after-school facility and automatically generating reports for administrative work, means including an emotion engine for analyzing a user's facial expressions and tone of voice, and means for adaptively suggesting menus based on the user's emotional state analyzed by the emotion engine. This enables detailed educational support and mental care for each child, and further enables the system to suggest meal plans and menus that are optimal for each individual user's emotional state on that day.

[0384] "Profile data" refers to individual information about an individual user (or child), such as age, preferences, past behavioral history, learning progress, and characteristics.

[0385] A "generative AI model" refers to an artificial intelligence model that automatically generates adaptive programs and information based on prompts from input data.

[0386] An "emotion engine" refers to a technology that analyzes a user's emotional state, such as facial expressions and tone of voice, in real time and provides the analysis results.

[0387] A "learning program" refers to educational content and assignments that are individually created to suit each child's learning ability and progress.

[0388] "Play programs" refer to games and activities that are individually created based on a child's interests and preferences.

[0389] "Means" refers to an apparatus, method, or system for performing a particular function.

[0390] "Menu Suggestion" refers to automatically recommending meal plans that best suit a user's current mood and preferences based on their profile data and emotional state.

[0391] "User" refers to individuals who use the system, particularly in the present invention, children and users of food delivery services.

[0392] "Terminal" refers to the device that displays data received from the server and interacts with the user, such as a smartphone or computer.

[0393] "Activity data" refers to data related to the user's actions and reactions when using the system.

[0394] "Server" refers to the central system that receives and sends data from multiple users and processes the data using generative AI models and emotion engines.

[0395] This system generates learning and play programs based on a child's profile data, and provides adaptive support by analyzing and recognizing the child's emotional state using an emotion engine. Examples of applications include a food delivery application that suggests optimal meal plans and menus for individual users.

[0396] Server-side processing

[0397] 1. Profile data collection and normalization

[0398] The server first acquires the profile data of the child or user, including age, preferences, past behavioral history, learning progress, characteristics, etc. The acquired data is then converted into a unified format that can be easily processed by the generative AI model and emotion engine.

[0399] 2. Applying generative AI models

[0400] The server uses the normalized profile data to generate prompts for the generative AI model, which in turn guides the creation of learning, play, or meal plans tailored to each user.

[0401] Example: Prompt statement

[0402] prompt:

[0403] User's age: 25

[0404] Favorite food: Italian

[0405] Allergens: nuts

[0406] Suggested menu: Pizza, salad, herbal tea

[0407] This user's emotion today is "Stressed" but they would like to relax a bit. Please suggest the best meal plan for them.

[0408] 3. Applying the Emotion Engine

[0409] The server uses an emotion engine to analyze the user's facial expressions and tone of voice to understand the user's emotional state in real time, allowing it to make adaptive menu suggestions and adjust learning programs.

[0410] 4. Data transmission and reception

[0411] The system sends a data package containing the generated learning program, play program, meal plan, and emotional data to the user's device, receives data on the child's activities and the user's reaction data, and automatically generates reports required for administrative work.

[0412] Terminal side processing

[0413] 1. Data Receipt and Analysis

[0414] The terminal receives the data packages sent by the server, displays them appropriately, and allows the user to access the plans and programs offered through a user interface.

[0415] 2. Launching and interacting with the AI ​​advisor

[0416] The device then activates the AI ​​advisor (school assistant or food advisor) that receives the information and provides support through dialogue with the user. Based on the emotional data analyzed by the emotion engine, the device responds adaptively.

[0417] 3. Monitoring Emotional Data

[0418] The device monitors the user's facial expressions and tone of voice in real time and uses an emotion engine to transmit emotional data to the server.

[0419] Hardware and software used

[0420] The server uses a high-performance computer (cloud-based or on-premise), and the software incorporates OpenAI's GPT-4 as a generative AI model, and the emotion engine incorporates Microsoft Azure's facial recognition API and Google Cloud's voice analysis API.

[0421] The user device will be a smartphone or computer equipped with a camera and microphone, and the user interface will be a custom food delivery application or educational support application.

[0422] Specific examples

[0423] For example, if a particular user is feeling stressed, the system uses the smartphone's camera and microphone to analyze this emotional data. Since the profile data states "Favorite food: Italian, Allergy: Nuts," the generative AI model suggests a meal plan that includes pizza and salad. An additional suggestion is herbal tea, which is said to have a relaxing effect. The user can then select from the suggested menu and place an order via a food delivery service.

[0424] As described above, the present invention is a system that provides detailed support to individual children and users, improving their quality of life.

[0425] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0426] Step 1:

[0427] The server obtains user profile data, specifically, age, preferences, allergy information, past order history, etc., from a database. The input is the profile data in the database, and the output is the profile data in a unified format that is ready for analysis and generation.

[0428] Step 2:

[0429] The server normalizes the collected profile data. This is a process that standardizes the data format and prepares it in a form that can be efficiently analyzed by generative AI models and emotion engines. The input is raw profile data, and the output is normalized profile data.

[0430] Step 3:

[0431] The server generates prompts for the generative AI model based on the normalized profile data. In a specific example, the prompt text includes information such as age, preferences, past behavioral history, and emotional state. The input is the profile data, and the output is the prompt text to be passed to the generative AI model.

[0432] Step 4:

[0433] The server uses a generative AI model (e.g., OpenAI's GPT-4) to generate an adaptive learning program, play program, or meal plan based on the prompt. The input is the prompt, and the output is the generated program or plan.

[0434] Step 5:

[0435] The server compiles the generated learning programs, play programs, and meal plans into a data package and sends it to the user terminal. The input is the generated program or plan, and the output is the data package sent to the user terminal.

[0436] Step 6:

[0437] The terminal receives the data package sent from the server, analyzes it, and displays it appropriately, allowing the user to access the programs and plans provided. The input is the data package sent from the server, and the output is the program or plan displayed on the user interface.

[0438] Step 7:

[0439] The device then activates the AI ​​advisor (school assistant or food advisor) that received the data and has it interact with the user. The AI ​​advisor responds adaptively based on the emotional data. The input is the data package sent from the server and emotional data collected in real time, and the output is the result of the interaction with the user.

[0440] Step 8:

[0441] The device monitors the user's facial expressions and tone of voice in real time, analyzes the emotional data using an emotion engine (such as Microsoft Azure's facial recognition API or Google Cloud's voice analysis API), and sends the analyzed emotional data to the server. The input is the user's facial expressions and voice data, and the output is the analyzed emotional data.

[0442] Step 9:

[0443] The server adjusts learning programs, play programs, and meal plans in real time based on the received emotional data, and retransmits them to the device as a new data package. The input is the analyzed emotional data, and the output is the adjusted programs and plans.

[0444] 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.

[0445] 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.

[0446] 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.

[0447] [Second embodiment]

[0448] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0449] 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.

[0450] 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).

[0451] 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.

[0452] 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.

[0453] 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).

[0454] 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. 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.

[0455] 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.

[0456] 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.

[0457] 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.

[0458] 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.

[0459] 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."

[0460] The present invention relates to an after-school support system that utilizes generative AI models to reduce the burden on staff at after-school care facilities and provide appropriate care and education for children. This system acquires children's profile data, generates learning and play programs based on that data, and distributes the data to terminals at the after-school care facility. A specific example of this system is described below.

[0461] Server-side processing

[0462] 1. Collecting and normalizing child profile data

[0463] The server retrieves profile data for each child from the after-school care facility's database. This profile data includes the child's age, learning progress, interests, and characteristics. The retrieved profile data is converted into a unified format that is easy for the generative AI model to process.

[0464] 2. Applying generative AI models

[0465] The server generates prompts for the generative AI model based on the normalized profile data. These prompts are instructions for generating learning and play programs appropriate for each child. The generative AI model receives these prompts, automatically generates learning and play programs, and returns them to the server.

[0466] 3. Creation of AI school assistants

[0467] The server generates an AI assistant based on the generated learning and play programs. This AI assistant is designed to assist children in learning and play while interacting with them. The appearance, voice, and speaking style of the AI ​​assistant are set based on specific parameters.

[0468] 4. Data transmission

[0469] The server combines the generated learning program, play program, and AI after-school assistant into a single data package and sends this package to a terminal at the after-school facility.

[0470] 5. Support for administrative work

[0471] The server automatically generates reports necessary for administrative work based on the activity data of children sent from the after-school care facility, thereby reducing the workload of instructors.

[0472] Terminal side processing

[0473] 1. Displaying received data

[0474] The terminal receives the data package sent from the server. This data package includes learning programs, play programs, and AI school assistants. The terminal analyzes the data and displays it appropriately.

[0475] 2. Starting and interacting with the AI ​​after-school assistant

[0476] The device then activates the AI ​​assistant, who interacts with the child to support their learning and play. The AI ​​assistant observes the child's reactions and sends the data to a server in real time.

[0477] 3. Status Notification

[0478] The devices monitor the children's behavior and reactions and notify teachers when certain conditions are met, such as an immediate alert if a fight breaks out or if a certain time has passed.

[0479] User (instructor) perspective

[0480] 1. Check and correct the program

[0481] The user (instructor) checks the learning and play programs displayed on the device and fine-tunes the settings as necessary, allowing them to provide appropriate support to each child.

[0482] 2. Collaboration with AI assistants

[0483] Users can work with AI after-school assistants to manage the progress of their children's studies and play, allowing them to focus on caring for their children, providing mental support, and mediating when problems arise.

[0484] 3. Checking and using the report

[0485] Users can check automatically generated reports provided by the server to understand the status of their children, and can use these reports to report to parents and schools, thereby streamlining operations.

[0486] Specific examples

[0487] For example, if a child is good at math and likes soccer, the server will generate a math problem set and a soccer-related indoor game based on that child's profile data. The device receives these programs, and the AI ​​school assistant asks the child math problems and suggests soccer games when the child gets bored. The user (instructor) monitors this process and provides support as needed.

[0488] As a result, the present invention reduces the burden on staff at after-school care facilities and provides high-quality care and education for children.

[0489] The processing flow will be explained below.

[0490] Server-side processing

[0491] Step 1: Collecting child profile data

[0492] The server obtains each child's profile data (age, interests, learning progress, etc.) from the after-school facility's database.

[0493] Step 2: Normalize the data

[0494] The server converts the acquired profile data into a unified format, making it easy for the generative AI model to process.

[0495] Step 3: Generate prompts

[0496] The server generates prompts to input into the generative AI model based on the normalized profile data.

[0497] Step 4: Generate Request

[0498] The server sends the generated prompts to the generative AI model, requesting it to generate learning and play programs.

[0499] Step 5: Receive the generated results

[0500] The server receives the learning programs and play programs returned from the generative AI model and stores them appropriately.

[0501] Step 6: Generate AI school assistants

[0502] The server generates an AI school assistant based on the generated learning and play programs, with the specified appearance, voice, and speaking style. Multiple assistants are generated as needed.

[0503] Step 7: Packaging the Data

[0504] The server combines the generated learning programs, play programs, and AI school assistants into a single package.

[0505] Step 8: Sending Data

[0506] The server transmits the packaged data to the terminal at the after-school facility.

[0507] Step 9: Receiving and processing activity data

[0508] The server receives the children's activity data sent from the after-school care facility and compiles it into statistical information and reports required for administrative work.

[0509] Step 10: Generate reports

[0510] The server checks the automatically generated report and provides it to the instructor.

[0511] Terminal side processing

[0512] Step 1: Receiving Data

[0513] The terminal receives data packages of learning programs, play programs, and AI school assistants sent from the server.

[0514] Step 2: Analyze and display the data

[0515] The device analyzes the received data and displays information appropriate for each child in an appropriate format.

[0516] Step 3: Launching the AI ​​School Assistant

[0517] The device then runs the received AI school assistant program and interacts with the children using the specified appearance and voice.

[0518] Step 4: Dialogue monitoring

[0519] The device monitors the conversation between the AI ​​school assistant and the child, and transmits the child's reaction data to a server in real time.

[0520] Step 5: Configure alerts

[0521] The device sets an alert based on set conditions (e.g., when a specific behavior is observed or when there is no response for a certain period of time).

[0522] Step 6: Send notification

[0523] The device immediately sends a notification to the instructor when the set alert conditions are met.

[0524] User (instructor) perspective

[0525] Step 1: Check the program

[0526] The user (instructor) checks the learning and play programs displayed on the terminal and fine-tunes the settings as necessary.

[0527] Step 2: Collaborate with AI assistants

[0528] Users can work with AI after-school assistants to manage the progress of their children's studies and play, allowing them to focus on caring for their children, providing mental support, and mediating when problems arise.

[0529] Step 3: Review and use the report

[0530] The user checks the automatically generated reports provided by the server to understand the child's situation, and reports to parents and schools based on these reports.

[0531] Through these steps, the AI ​​support system in after-school care facilities will reduce the burden on staff and ensure high-quality care for children.

[0532] Example 1

[0533] 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."

[0534] There is a need to reduce the burden on staff at after-school care facilities and provide high-quality care and education to children. Previous systems struggled to quickly and efficiently provide learning and play programs tailored to each child, and the administrative burden of managing children's activity data was significant. Furthermore, the application of AI after-school assistants lacked the ability to provide support for children's interactions.

[0535] 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.

[0536] In this invention, the server includes means for acquiring child profile data, means for converting and normalizing the profile data into a unified format, means for generating prompts based on the normalized profile data and applying them to the generative AI model, means for generating an AI after-school assistant based on the generated learning program and play program, means for transmitting the learning program, play program, and the generated AI after-school assistant to a terminal at the after-school facility, and means for receiving child activity data from the terminal at the after-school facility and automatically generating reports for administrative work. This reduces the burden on staff at the after-school facility, improves the quality of individualized care and education for children, and makes administrative work more efficient.

[0537] "Child profile data" means data that includes individual characteristics and information about a child, such as the child's age, learning progress, interests, and characteristics.

[0538] "Normalization" is the process of converting acquired profile data into a unified format to maintain data consistency.

[0539] A "prompt" is an input sentence in the form of text or a question that provides instructions to a generative AI model.

[0540] A "generative AI model" is an artificial intelligence model that automatically generates learning or play programs based on given prompts.

[0541] The "AI School Assistant" is an artificial intelligence character that interacts with children to assist them in learning and play, based on learning and play programs generated from a generative AI model.

[0542] "After-school facility terminal" refers to a hardware device such as a computer or tablet used within the after-school facility, and is a device that receives and displays data sent from the server.

[0543] "Child activity data" refers to data on children's reactions and behavior when participating in learning programs or play programs.

[0544] "Administrative work" refers to back-office work such as managing operations and preparing reports at after-school care facilities.

[0545] A "report" is an automatically generated report based on a child's activity data, and is a document containing information provided to instructors, parents, and schools.

[0546] This invention relates to an after-school support system that utilizes generative AI models to reduce the burden on staff at after-school care facilities and provide high-quality care and education to children. This system is composed of a server, a terminal, and a user's perspective, and each process functions in cooperation with each other.

[0547] Server Roles and Operations

[0548] The server accesses the after-school facility's database to obtain the child's profile data. This profile data includes the child's age, learning progress, interests, and characteristics. First, the data is converted into a unified format and normalized. Next, the server generates a prompt based on the normalized profile data. This prompt is used to provide instructions to the generative AI model and is written in the following text format:

[0549] Example prompt sentence:

[0550] "This child is 10 years old, good at math, and loves soccer. Use this profile to generate appropriate learning and play programs."

[0551] The server sends these prompts to a generative AI model, which then automatically generates appropriate learning and play programs based on the prompts. The generated programs are then returned to the server, which then generates an AI school assistant based on these programs. This assistant is designed to interact with children and support them in their learning and play.

[0552] The generated learning programs, play programs, and AI after-school assistants are compiled into a single data package and sent to the after-school facility's terminal. The server also automatically generates reports for administrative work based on the children's activity data sent from the after-school facility, improving work efficiency.

[0553] Terminal roles and processing

[0554] The device receives data packages sent from the server, analyzes them, and displays learning programs, play programs, and AI school assistants. The device launches the AI ​​school assistant, and the user (instructor) supports learning and play by interacting with the children through this assistant. The AI ​​assistant observes the children's reactions and behavior and sends the data to the server in real time.

[0555] For example, the AI ​​assistant might say, "Hello! Let's solve some math problems together today, and then we'll have a soccer quiz," attracting the child's interest while progressing the learning process. Additionally, if certain conditions are met, the device will immediately notify the instructor. For example, if a fight breaks out, it will issue an alert saying, "A fight has just broken out."

[0556] User (instructor) roles and processes

[0557] The user (instructor) checks the learning and play programs displayed on the device and fine-tunes the settings as needed. For example, if a math problem is too difficult, the difficulty level can be adjusted. The user works with the AI ​​after-school assistant to manage the children's learning and play progress. This allows the user to focus on caring for the children, providing mental support, and mediating when problems arise.

[0558] In addition, automatically generated reports provided by the server can be checked to understand the child's situation in detail, and these reports can be used to report to parents and schools, making work more efficient.

[0559] Specific examples

[0560] For example, if a child is good at math and likes soccer, the server will generate a math problem set and soccer-related indoor games based on the child's profile data. A prompt based on this profile might be something like, "This child is 10 years old, good at math, and likes soccer. Please generate appropriate learning and play programs based on this profile."

[0561] The device receives these programs, and the AI ​​assistant asks the children math problems and suggests playing soccer when they get bored. The user (instructor) monitors this process and provides support to the children as needed.

[0562] As a result, the present invention reduces the burden on staff at after-school care facilities and provides high-quality care and education for children.

[0563] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0564] Step 1:

[0565] The server accesses the database of the after-school care facility and retrieves profile data for each child. This profile data includes the child's age, learning progress, interests, characteristics, etc. It receives profile data from the database as input and retrieves profile data as output. Specifically, it extracts the required information from the database using SQL queries.

[0566] Step 2:

[0567] The server converts and normalizes the acquired profile data into a unified format. In this process, for example, age is standardized into a "number" format and interests into a "comma-separated keywords" format. It receives raw profile data as input, processes the data, and then outputs normalized profile data. Specifically, it applies data conversion rules to unify the format.

[0568] Step 3:

[0569] The server generates the prompts required for the generative AI model based on the normalized profile data. It receives the normalized profile data as input and obtains the generated prompt as output. Specifically, it creates a prompt such as, "This child is 10 years old, good at math, and likes soccer. Please generate appropriate learning and play programs based on this profile."

[0570] Step 4:

[0571] The server sends prompts to the generative AI model and automatically generates learning and play programs. It receives the generated prompts as input and obtains the generated learning and play programs as output. Specifically, it sends API requests to the generative AI model and analyzes the response.

[0572] Step 5:

[0573] The server generates an AI school assistant based on the generated learning and play programs. This AI assistant is designed to support learning and play while interacting with children. It receives learning and play programs as input and generates an AI school assistant as output. Specific operations are performed using a voice synthesis engine and character generation tools.

[0574] Step 6:

[0575] The server combines the generated learning program, play program, and AI school assistant into a single data package. This data package is then sent to the terminal. The server receives the learning program, play program, and AI school assistant as input, and obtains a combined data package as output. Specifically, the server combines the data into a format such as JSON and sends it to the terminal using the HTTP protocol.

[0576] Step 7:

[0577] The device receives the data package sent from the server, analyzes it, and displays the learning program, play program, and AI school assistant. It receives the data package as input and displays the analyzed data as output. Specifically, it parses the received data using a JSON parser and displays it on the user interface.

[0578] Step 8:

[0579] The device then activates the AI ​​assistant and has it interact with the children to support their learning and play. It receives the AI ​​assistant as input and starts a dialogue as output. Specific operations include playing the AI ​​assistant's voice and displaying an animated user interface.

[0580] Step 9:

[0581] The device observes the child's reactions and behavior and sends the data to the server in real time. It receives the child's reaction data as input and obtains the transmitted data as output. Specifically, it analyzes the data obtained from sensors and cameras and sends it to the server via an HTTP request.

[0582] Step 10:

[0583] The device notifies the instructor when certain conditions are met. It receives student behavior data and event triggers as input and issues an alert as output. Specific actions include displaying a pop-up message or audio alert on the UI.

[0584] Step 11:

[0585] The user (instructor) checks the learning program and play program displayed on the terminal and fine-tunes the settings as necessary. The displayed program is received as input and the fine-tuned settings are reflected as output. Specific operations involve operating the setting panel on the UI and adjusting the parameters.

[0586] Step 12:

[0587] The user checks the automatically generated report provided by the server and understands the child's situation in detail. The automatically generated report is received as input, and the understood information is obtained as output. Specifically, the user browses the contents of the report and extracts the necessary information.

[0588] (Application example 1)

[0589] 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."

[0590] In today's after-school care facilities, staff are required to handle a wide range of tasks, particularly providing academic guidance and play support to individual children, as well as the administrative work of understanding each child's situation and reporting it to parents and schools, which places a heavy burden on staff. Similarly, in brick-and-mortar stores, it is difficult to provide personalized product recommendations and services to each customer, and measures to increase customer satisfaction are lacking. Furthermore, there is a lack of a way to centrally manage and effectively utilize this data.

[0591] 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.

[0592] In this invention, the server includes: means for acquiring child profile data; means for applying a generative AI model to generate learning programs and play programs based on the profile data; means for transmitting the generated learning programs and play programs to a terminal at the after-school facility; means for receiving child activity data from the terminal at the after-school facility and automatically generating reports for administrative work; means for collecting customer profile data from multiple physical stores and applying a generative AI model to generate product proposals and service details based on the profile data; means for transmitting the generated product proposals and service details to a terminal at the physical store; and means for receiving customer response data from the terminal at the physical store and automatically generating reports required for the physical store's operations. This not only reduces the burden on staff at the after-school facility and enables the provision of high-quality care and education for children, but also enables the physical store to quickly and efficiently provide personalized product proposals and services to each customer.

[0593] "Profile Data" means information about a child or customer, including their age, gender, interests, and past activity.

[0594] A "learning program" is a program that includes teaching materials and teaching methods that are automatically generated by a generative AI model to provide children with appropriate learning content and methods.

[0595] A "play program" is a program that includes play and recreational activities that is automatically generated by a generative AI model based on a child's interests and characteristics.

[0596] A "generative AI model" is an artificial intelligence model that automatically generates appropriate output (learning programs, play programs, product suggestions, service content, etc.) based on input data.

[0597] A "terminal" is a hardware device used to display and process data, specifically a computer or smart device installed in an after-school facility or brick-and-mortar store.

[0598] "Activity data" is a record of the specific actions and reactions that children and customers take while studying, playing, shopping, etc.

[0599] A "report" is a document that summarizes the activities, grades, and reactions of children or clients, and is used to streamline administrative and management tasks.

[0600] "Product suggestions" are recommendations of products suitable for a specific customer, generated by a generative AI model based on customer profile data.

[0601] "Service content" refers to details of the services to be provided to a specific customer, generated by the generative AI model based on the customer's profile data and response data.

[0602] The following system configuration is used as an embodiment of the present invention.

[0603] System Overview

[0604] This system consists of a server, terminals installed in physical stores and after-school care facilities, and users (instructors and store staff) who operate them.

[0605] Server Processing

[0606] 1. Profile Data Collection and Normalization:

[0607] The server collects profile data of children or customers from after-school care facilities and multiple physical stores, including age, gender, interests, and past activity history.

[0608] The collected data is normalized into a unified format, making it easier for generative AI models to process.

[0609] 2. Applying generative AI models:

[0610] Based on the normalized profile data, the server generates prompts, which in turn generate learning and play programs suited to each child, as well as product suggestions and service content suited to each customer.

[0611] The generative AI model receives this prompt, automatically generates an appropriate program or suggestion, and returns it to the server.

[0612] 3. Data submission and reporting:

[0613] The generated programs and proposals are sent to terminals at after-school facilities and physical stores.

[0614] The server also receives activity data sent from after-school care facilities and brick-and-mortar stores and automatically generates reports for administrative work, thereby reducing the workload of instructors and store staff.

[0615] Terminal handling

[0616] 1. Displaying received data:

[0617] The terminal receives the data package sent from the server and appropriately displays learning programs and play programs for the children and product suggestions and service contents for the customers.

[0618] 2. Activating and interacting with the AI ​​assistant:

[0619] Based on the received program and suggestions, the AI ​​assistant will be activated and will support the child in their learning and play through dialogue, as well as recommend the most suitable products to the customer and answer any questions.

[0620] 3. Real-time data transmission:

[0621] The device transmits real-time reaction data from children and customers to a server, allowing for further data analysis.

[0622] User Roles

[0623] 1. Check and correct the program:

[0624] Instructors and store staff can check the programs and suggestions displayed on the terminals and make adjustments as necessary, thereby providing optimal support for each child or customer.

[0625] 2. Collaboration with AI assistants:

[0626] Instructors and store staff will work with AI assistants to streamline their daily work, and the AI ​​assistants will automatically communicate and guide customers, minimizing human intervention.

[0627] 3. Review and use the report:

[0628] Automatically generated reports provided by the server are used to understand children's learning progress and customer purchasing behavior, simplifying reporting to parents and companies and improving operational efficiency.

[0629] Specific examples

[0630] For example, if a schoolchild is good at math and likes soccer, the server can generate a prompt like this based on their profile data:

[0631] "Age: 8 Gender: Male Interests: Math and sports"

[0632] Based on this prompt, the generative AI model automatically generates math puzzles and soccer-related indoor games. Meanwhile, as an example of application in a physical store, the model suggests the latest sportswear and new cosmetics to a 30-year-old female customer based on the prompt: "Age: 30, Gender: Female, Interests: Sports and Fashion."

[0633] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0634] Step 1:

[0635] The server collects customer or child profile data from brick-and-mortar stores and after-school care facilities. This data includes age, gender, past activity history, interests, etc. The input is the raw data sent from each facility, and the output is pre-processed data for normalization.

[0636] Step 2:

[0637] The server normalizes the collected profile data. The input is the preprocessed data obtained in step 1, and the output is data in a unified format. Data normalization converts the data into a form that is easy for the generative AI model to process.

[0638] Step 3:

[0639] The server generates prompts based on the normalized profile data. The input is the normalized data, and the output is prompts to be used as input to the generative AI model. The prompts follow a specific template to appropriately describe the data.

[0640] Step 4:

[0641] The server inputs prompts into the generative AI model to generate learning programs, play programs, product suggestions, and service content. The input is the prompt, and the output is the appropriate program or suggestion. The generative AI model generates a response based on the specified prompt.

[0642] Step 5:

[0643] The server compiles the generated programs and proposals and sends them to terminals at the after-school care facility or physical store. The input is each generated program and proposal, and the output is the transmitted data package. This data package contains the program contents and proposals.

[0644] Step 6:

[0645] The terminal receives the data package sent from the server and displays the program or suggestion content appropriately. The input is the data package from the server, and the output is the displayed content.

[0646] Step 7:

[0647] Based on the received information, the terminal activates an AI assistant and interacts with the child to support learning and play. It also provides optimal product recommendations and service information to customers. The input is the program and recommendations received from the server, and the output is a response to the child or customer.

[0648] Step 8:

[0649] The user (instructor or store staff) checks the content displayed on the terminal and fine-tunes the program and suggestions as necessary. The input is the data displayed on the terminal, and the output is the adjusted program and suggestions.

[0650] Step 9:

[0651] The terminal transmits the reaction and behavior data of the children or customers to the server in real time. The input is the real-time reaction data of the children or customers, and the output is the data transmitted to the server.

[0652] Step 10:

[0653] The server analyzes the received reaction data and automatically generates a new report. The input is real-time reaction data, and the output is an automatically generated report. This report helps instructors and store staff improve their work efficiency.

[0654] The above is a detailed explanation of the application process, broken down into specific steps, that will lead to the creation of an effective support system that utilizes generative AI models and prompts.

[0655] 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.

[0656] The present invention relates to an after-school support system that generates learning and play programs based on children's profile data and further combines an emotion engine to analyze and recognize children's emotions, thereby providing more detailed support. This system utilizes children's profile data and applies a generative AI model and emotion engine to support learning and play, with the aim of reducing the burden on staff at after-school facilities. A specific example of this system is described below.

[0657] Server-side processing

[0658] 1. Collecting and normalizing child profile data

[0659] The server retrieves each child's profile data from the after-school facility's database. This profile data includes the child's age, learning progress, interests, and characteristics. The retrieved profile data is converted into a unified format that is easy for the generative AI model and emotion engine to process.

[0660] 2. Applying generative AI models

[0661] The server generates prompts for the generative AI model based on the normalized profile data. These prompts serve as instructions for generating learning and play programs appropriate for each child. The generative AI model receives the prompts, automatically generates learning and play programs, and returns them to the server.

[0662] 3. Applying the Emotion Engine

[0663] The server uses an emotion engine to analyze the child's facial expressions and tone of voice, allowing it to understand the child's emotional state in real time and adaptively adjust learning and play programs.

[0664] 4. Creation of AI school assistants

[0665] The server generates an AI school assistant based on the generated learning and play programs, as well as emotional data generated by the emotion engine. This AI school assistant supports children in their studies and play while interacting with them, and also provides mental care based on the emotional data.

[0666] 5. Sending and Receiving Data

[0667] The server compiles the generated learning programs, play programs, and AI after-school assistants into a single data package and sends it to the after-school facility's terminal. It also receives the children's activity data sent from the after-school facility and automatically generates reports necessary for administrative work.

[0668] Terminal side processing

[0669] 1. Data Receipt and Analysis

[0670] The device receives data packages (learning programs, play programs, AI school assistants, and emotional data) sent from the server, analyzes the received data, and displays it appropriately.

[0671] 2. Starting and interacting with the AI ​​after-school assistant

[0672] The device then activates the AI ​​assistant, who interacts with the child to support learning and play. Based on the emotional data analyzed by the emotion engine, the device responds adaptively to the child's emotional state.

[0673] 3. Monitoring Emotional Data

[0674] The device monitors the child's facial expressions and tone of voice in real time and uses an emotion engine to transmit emotional data to the server, allowing the device to grasp the child's emotional state in real time.

[0675] 4. Status Notification

[0676] The device sets an alert according to the set conditions (e.g., if a specific emotion continues or if there is a sudden change in emotion) and notifies the instructor as necessary.

[0677] User (instructor) perspective

[0678] 1. Check and correct the program

[0679] The user (instructor) checks the learning program, play program, and emotional data displayed on the device and fine-tunes the settings as needed, allowing them to provide appropriate support to each child.

[0680] 2. Collaboration with AI assistants

[0681] Users can work with AI after-school assistants to manage children's learning and play progress, and can focus on providing mental care for children and mediating when problems arise based on emotional data.

[0682] 3. Checking and using the report

[0683] The user checks the automatically generated reports provided by the server to understand the child's situation, and reports to parents and schools based on these reports.

[0684] Specific examples

[0685] For example, if a child is good at math and likes soccer, but has recently been feeling stressed, the server will generate a math problem set and a soccer-related indoor game based on the child's profile and emotional data. Furthermore, if the emotion engine analyzes that the child is feeling stressed, it will use that information to suggest activities and conversations that will help them relax. The device receives these programs, and the AI ​​school assistant will ask the child math problems and suggest activities to help them relax if they feel stressed. The user (instructor) monitors this process and provides additional support as needed.

[0686] As a result, the present invention reduces the burden on staff at after-school care facilities and provides high-quality care and education for children.

[0687] The processing flow will be explained below.

[0688] Server-side processing

[0689] Step 1: Collecting child profile data

[0690] The server obtains each child's profile data (age, interests, learning progress, characteristics, etc.) from the after-school facility's database.

[0691] Step 2: Normalize the data

[0692] The server converts the acquired profile data into a unified format, making it easier for the generative AI model and emotion engine to process.

[0693] Step 3: Generate prompts

[0694] The server generates prompts to input into the generative AI model based on the normalized profile data.

[0695] Step 4: Generate Request

[0696] The server sends the generated prompts to the generative AI model, requesting it to generate learning and play programs.

[0697] Step 5: Receive the generated results

[0698] The server receives the learning programs and play programs returned from the generative AI model and stores them appropriately.

[0699] Step 6: Applying the Emotion Engine

[0700] The server uses an emotion engine to analyze the child's facial expressions and tone of voice, thereby obtaining emotion data in real time.

[0701] Step 7: Generate AI school assistants

[0702] The server generates an AI school assistant based on the generated learning and play programs, as well as emotional data generated by the emotion engine. This AI school assistant responds adaptively according to the emotional state of the child.

[0703] Step 8: Packaging the Data

[0704] The server compiles the generated learning program, play program, AI school assistant, and emotional data into a single package.

[0705] Step 9: Sending Data

[0706] The server transmits the packaged data to the terminal at the after-school facility.

[0707] Step 10: Receiving and processing activity data

[0708] The server receives the children's activity data sent from the after-school care facility and compiles it into statistical information and reports required for administrative work.

[0709] Step 11: Generate reports

[0710] The server checks the automatically generated report and provides it to the instructor.

[0711] Terminal side processing

[0712] Step 1: Receiving Data

[0713] The terminal receives the learning program, play program, AI school assistant, and emotion data package sent from the server.

[0714] Step 2: Analyze and display the data

[0715] The device analyzes the received data and displays information appropriate for each child in an appropriate format.

[0716] Step 3: Launching the AI ​​School Assistant

[0717] The device then runs the received AI school assistant program and interacts with the children using the specified appearance and voice.

[0718] Step 4: Dialogue monitoring

[0719] The device monitors the conversation between the AI ​​school assistant and the child, and transmits the child's reaction data to a server in real time.

[0720] Step 5: Monitoring sentiment data

[0721] The device uses an emotion engine to analyze the child's facial expressions and tone of voice in real time and transmits the emotional data to a server.

[0722] Step 6: Configure alerts

[0723] The device sets an alert according to the set conditions (e.g., when a specific emotion continues or when there is a sudden change in emotion).

[0724] Step 7: Send notification

[0725] The device immediately sends a notification to the instructor when the set alert conditions are met.

[0726] User (instructor) perspective

[0727] Step 1: Check and correct the program

[0728] The user (instructor) checks the learning program, play program, and emotional data displayed on the terminal and fine-tunes the settings as necessary.

[0729] Step 2: Collaborate with AI assistants

[0730] Users can work with AI after-school assistants to manage the progress of children's studies and play, and use emotional data to focus on mental care and mediation when problems arise.

[0731] Step 3: Review and use the report

[0732] The user checks the automatically generated reports provided by the server to understand the child's situation, and reports to parents and schools based on these reports.

[0733] Specific examples

[0734] For example, if a child is good at math and likes soccer, but has recently been feeling stressed, the server will generate a math problem set and a soccer-related indoor game based on the child's profile and emotional data. Furthermore, if the emotion engine analyzes that the child is feeling stressed, it will use that information to suggest activities and conversations that will help them relax. The device receives these programs, and the AI ​​school assistant will ask the child math problems and suggest activities to help them relax if they feel stressed. The user (instructor) monitors this process and provides additional support as needed.

[0735] Example 2

[0736] 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."

[0737] Modern after-school care facilities are required to provide attentive support to each child while reducing the burden on staff. However, conventional systems have difficulty responding to the diverse needs of children and are limited in the adaptive scientific support that takes into account their emotional state. Therefore, a system is needed that can provide appropriate learning and play programs based on each child's individual characteristics and emotional state, and provide feedback on the effectiveness of these programs in real time.

[0738] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring personal information of children, means for converting the personal information into a unified format, means for applying a generative AI model to generate learning programs and play programs based on the unified personal information, means for generating and sending prompt sentences to the generative AI model, means for using an emotion engine to analyze the children's facial expressions and tone of voice and determine their emotional state, means for integrating the generated learning programs, play programs, and emotion data to generate an AI after-school assistant, means for transmitting the generated learning programs, play programs, and AI after-school assistant to a terminal at the after-school facility, and means for receiving children's activity data from the terminal at the after-school facility and automatically generating reports for administrative work. This makes it possible to provide learning and play programs that take into account the individual characteristics and emotional state of children and to adaptively adjust them in real time.

[0739] "Personal information of children" refers to data that represents individual characteristics of children, such as their age, learning progress, interests, and characteristics.

[0740] "Uniform format" means that data is converted into a consistent format that facilitates subsequent processing.

[0741] A "generative AI model" is an artificial intelligence model that automatically generates learning and play programs based on input prompts.

[0742] A "prompt" is a sentence used to instruct a generative AI model to produce a specific output.

[0743] The "emotion engine" is a system that analyzes a child's facial expressions and tone of voice to determine their emotional state.

[0744] The "AI School Assistant" is an artificial intelligence agent that supports children based on generated learning programs, play programs, and emotional data.

[0745] "After-school facility terminals" refer to devices such as computers and tablets used within the after-school facility.

[0746] "Activity data" is data collected during children's learning and play, including the progress and results of their activities.

[0747] "Reports for administrative work" are automatically generated business reports based on children's activity data, and are used to reduce the burden on staff.

[0748] This invention relates to an after-school support system that generates learning and play programs based on children's profile data and further analyzes and recognizes children's emotions by combining it with an emotion engine to provide more detailed support. This system aims to understand each child's individual characteristics and emotional state in real time, support their learning and play, and reduce the burden on staff at after-school facilities.

[0749] Server-side explanation

[0750] The server retrieves personal information about each child from the after-school care facility's database. This information includes the child's age, learning progress, interests, and characteristics. The retrieved data is converted into a unified format. By organizing it into a data frame using Python's Pandas library, the individual data is organized into a consistent, processable format.

[0751] Next, we generate a prompt to send to the generative AI model. Specifically, we generate a prompt in text format like this:

[0752] "Profile data: Age 10, Interests: Mathematics, Traits: High concentration. Please generate suitable learning and play programs."

[0753] The generated prompts are sent to a generative AI model (e.g., GPT-3), which then uses natural language processing technology to automatically generate learning and play programs for the child.

[0754] Furthermore, the server uses an emotion engine to analyze the child's facial expressions and tone of voice. The emotion analysis results indicate the child's real-time emotional state and are adaptively reflected in the learning and play programs. This analysis utilizes, for example, an emotion analysis service provided through an API.

[0755] Finally, the server integrates the generated learning and play programs with the emotional data generated from them to generate an AI school assistant. This AI school assistant provides support through dialogue with the children and also provides mental care based on the emotional data.

[0756] Terminal side explanation

[0757] The terminal receives the data package (learning program, play program, AI school assistant, emotional data) sent from the server, analyzes it, and displays it appropriately.

[0758] The device launches the AI ​​assistant and begins a dialogue with the child. The assistant presents learning and play programs to the child, while adaptively responding to the child's emotional state based on the analysis results of the emotion engine. Specifically, a dialogue system built using Python generates flexible responses based on the child's responses and emotional state.

[0759] The device also uses a camera and microphone to capture the child's facial expressions and tone of voice in real time, which are then sent to an emotion engine for analysis. The analysis results are then sent to a server for further adaptive responses.

[0760] Furthermore, the device will issue alerts in response to certain conditions (such as sustained stress levels or sudden emotional changes) and notify instructors as needed, enabling prompt response to problems and providing consistent support to children.

[0761] User (instructor) explanation

[0762] The user checks the learning and play programs and emotional data displayed on the device and makes fine adjustments as necessary. The system works in cooperation with AI after-school assistants to manage the children's progress in learning and play. The emotional data is also used to provide mental care for the children and respond to any problems that arise.

[0763] Users can also check automatically generated reports provided by the server to understand their child's progress, which can then be sent to parents and schools to provide consistent support and feedback to the child.

[0764] Specific examples

[0765] For example, consider a child who excels at math and loves soccer, but has recently been feeling stressed. In this case, the server generates a math workbook and a soccer-related indoor game based on the child's profile and emotional data. Furthermore, if the emotion engine analyzes that the child is feeling stressed, it will use that information to suggest activities and conversations that will help them relax.

[0766] The device receives these programs, and the AI ​​assistant asks the children math problems and suggests activities to relax them if they feel stressed. The user (instructor) monitors this process and provides additional support as needed.

[0767] As a result, the present invention reduces the burden on staff at after-school care facilities and enables high-quality care and education for children.

[0768] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0769] Step 1:

[0770] The server retrieves personal information about children from the after-school facility's database. The input data includes data such as the child's age, learning progress, interests, and characteristics, which are extracted from the after-school facility's database. This data is extracted using an SQL query to obtain the data. The output data is raw personal information data.

[0771] Step 2:

[0772] The server converts the acquired personal information into a unified format. The raw personal information data acquired in step 1 is used as input. Specifically, it uses the Python Pandas library to organize the data into a data frame. The output is the personal information data converted into a unified format.

[0773] Step 3:

[0774] The server generates a prompt sentence based on the unified personal information. The input is the unified personal information data obtained in step 2. As a specific operation, the prompt sentence is generated using Python's text manipulation functions. An example of a prompt sentence is generated as follows: "Profile data: age 10, interest: mathematics, characteristic: high concentration. Please generate suitable learning and play programs." The output is the generated prompt sentence.

[0775] Step 4:

[0776] The server sends the prompt sentence to the generative AI model to generate a learning program and a play program. The input is the prompt sentence generated in step 3. This is sent to the generative AI model (e.g., GPT-3) and the generated learning program and play program are received. The output is the generated learning program and play program.

[0777] Step 5:

[0778] The server uses an emotion engine to analyze the child's facial expression and tone of voice to determine their emotional state. The input is the child's facial expression image and voice data. Specifically, the server sends an emotion analysis request to the API and receives the analysis results. The output is the analyzed emotion data.

[0779] Step 6:

[0780] The server integrates the generated learning program, play program, and emotion data to generate an AI school assistant. The inputs are the learning program and play program generated in step 4 and the emotion data from step 5. A dialogue system is built using Python libraries (e.g., NLTK and spaCy) to prepare the AI ​​school assistant. The output is the generated AI school assistant.

[0781] Step 7:

[0782] The server sends the generated learning program, play program, and AI school assistant to the terminal at the after-school facility. The input is the learning program, play program, and AI school assistant obtained in step 6. Specifically, the server sends data packages using a network protocol (e.g., HTTP or WebSocket). The output is the data package sent to the terminal.

[0783] Step 8:

[0784] The terminal receives the data package sent from the server, parses it, and displays it appropriately. The input is the data package sent from the server. Specific operations include parsing the JSON data in Python and using a GUI to display it appropriately. The output is the displayed learning program, play program, and AI school assistant.

[0785] Step 9:

[0786] The terminal starts the AI ​​assistant and begins interacting with the child. The input is the AI ​​assistant received and displayed in step 8. Specifically, the AI ​​assistant presents learning and play programs to the child and provides support through interaction. The output is the result of the interaction with the child.

[0787] Step 10:

[0788] The device monitors the child's facial expressions and tone of voice in real time and sends the emotional data to the server using an emotion engine. The input is the child's facial expression images and voice data. Specific operations include collecting data using a camera and microphone and sending it to the emotion engine. The output is the analyzed emotional data.

[0789] Step 11:

[0790] The device sets alerts according to specific conditions and notifies the instructor as necessary. The input is the emotion data analyzed in step 10. The specific operation is to monitor the alert conditions and notify the instructor via email or SMS when the conditions are met. The output is the notification to the instructor.

[0791] Step 12:

[0792] The user checks the learning program, play program, and emotional data displayed on the device and fine-tunes the settings as needed. The input is the information displayed on the device. Specific actions include changing the settings in the GUI and supporting the child in cooperation with the AI ​​after-school assistant. The output is the adjusted learning program and play program.

[0793] Step 13:

[0794] The user manages the child's progress in learning and play, and provides mental care and responds to problems based on emotional data. The input is the child's activity data and emotional data. Specific actions include checking the activity record and providing support as needed. The output is the result of managing the child's progress.

[0795] Step 14:

[0796] The user checks the automatically generated report provided by the server and understands the child's situation. The input is the report provided by the server. The specific operation is to check the report and report it to the parents or school. The output is the report result.

[0797] As a result, the present invention reduces the burden on staff at after-school care facilities and enables high-quality care and education for children.

[0798] (Application example 2)

[0799] 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."

[0800] The present invention aims to improve the effectiveness of children's education and reduce the burden on after-school care facility staff by creating optimal learning and play programs based on each child's profile data and providing adaptive support through real-time analysis of the child's emotional state in a system that supports children's learning and play. Furthermore, the present invention aims to solve the problem of improving individual user experiences by applying emotion analysis to meal plans and menu suggestions.

[0801] 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.

[0802] In this invention, the server includes means for acquiring profile data of children, means for applying a generative AI model to generate learning programs and play programs based on the profile data, means for transmitting the generated learning programs and play programs to a terminal at the after-school facility, means for receiving activity data of children from the terminal at the after-school facility and automatically generating reports for administrative work, means including an emotion engine for analyzing a user's facial expressions and tone of voice, and means for adaptively suggesting menus based on the user's emotional state analyzed by the emotion engine. This enables detailed educational support and mental care for each child, and further enables the system to suggest meal plans and menus that are optimal for each individual user's emotional state on that day.

[0803] "Profile data" refers to individual information about an individual user (or child), such as age, preferences, past behavioral history, learning progress, and characteristics.

[0804] A "generative AI model" refers to an artificial intelligence model that automatically generates adaptive programs and information based on prompts from input data.

[0805] An "emotion engine" refers to a technology that analyzes a user's emotional state, such as facial expressions and tone of voice, in real time and provides the analysis results.

[0806] A "learning program" refers to educational content and assignments that are individually created to suit each child's learning ability and progress.

[0807] "Play programs" refer to games and activities that are individually created based on a child's interests and preferences.

[0808] "Means" refers to an apparatus, method, or system for performing a particular function.

[0809] "Menu Suggestion" refers to automatically recommending meal plans that best suit a user's current mood and preferences based on their profile data and emotional state.

[0810] "User" refers to individuals who use the system, particularly in the present invention, children and users of food delivery services.

[0811] "Terminal" refers to the device that displays data received from the server and interacts with the user, such as a smartphone or computer.

[0812] "Activity data" refers to data related to the user's actions and reactions when using the system.

[0813] "Server" refers to the central system that receives and sends data from multiple users and processes the data using generative AI models and emotion engines.

[0814] This system generates learning and play programs based on a child's profile data, and provides adaptive support by analyzing and recognizing the child's emotional state using an emotion engine. Examples of applications include a food delivery application that suggests optimal meal plans and menus for individual users.

[0815] Server-side processing

[0816] 1. Profile data collection and normalization

[0817] The server first acquires the profile data of the child or user, including age, preferences, past behavioral history, learning progress, characteristics, etc. The acquired data is then converted into a unified format that can be easily processed by the generative AI model and emotion engine.

[0818] 2. Applying generative AI models

[0819] The server uses the normalized profile data to generate prompts for the generative AI model, which in turn guides the creation of learning, play, or meal plans tailored to each user.

[0820] Example: Prompt statement

[0821] prompt:

[0822] User's age: 25

[0823] Favorite food: Italian

[0824] Allergens: nuts

[0825] Suggested menu: Pizza, salad, herbal tea

[0826] This user's emotion today is "Stressed" but they would like to relax a bit. Please suggest the best meal plan for them.

[0827] 3. Applying the Emotion Engine

[0828] The server uses an emotion engine to analyze the user's facial expressions and tone of voice to understand the user's emotional state in real time, allowing it to make adaptive menu suggestions and adjust learning programs.

[0829] 4. Data transmission and reception

[0830] The system sends a data package containing the generated learning program, play program, meal plan, and emotional data to the user's device, receives data on the child's activities and the user's reaction data, and automatically generates reports required for administrative work.

[0831] Terminal side processing

[0832] 1. Data Receipt and Analysis

[0833] The terminal receives the data packages sent by the server, displays them appropriately, and allows the user to access the plans and programs offered through a user interface.

[0834] 2. Launching and interacting with the AI ​​advisor

[0835] The device then activates the AI ​​advisor (school assistant or food advisor) that receives the information and provides support through dialogue with the user. Based on the emotional data analyzed by the emotion engine, the device responds adaptively.

[0836] 3. Monitoring Emotional Data

[0837] The device monitors the user's facial expressions and tone of voice in real time and uses an emotion engine to transmit emotional data to the server.

[0838] Hardware and software used

[0839] The server uses a high-performance computer (cloud-based or on-premise), and the software incorporates OpenAI's GPT-4 as a generative AI model, and the emotion engine incorporates Microsoft Azure's facial recognition API and Google Cloud's voice analysis API.

[0840] The user device will be a smartphone or computer equipped with a camera and microphone, and the user interface will be a custom food delivery application or educational support application.

[0841] Specific examples

[0842] For example, if a particular user is feeling stressed, the system uses the smartphone's camera and microphone to analyze this emotional data. Since the profile data states "Favorite food: Italian, Allergy: Nuts," the generative AI model suggests a meal plan that includes pizza and salad. An additional suggestion is herbal tea, which is said to have a relaxing effect. The user can then select from the suggested menu and place an order via a food delivery service.

[0843] As described above, the present invention is a system that provides detailed support to individual children and users, improving their quality of life.

[0844] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0845] Step 1:

[0846] The server obtains user profile data, specifically, age, preferences, allergy information, past order history, etc., from a database. The input is the profile data in the database, and the output is the profile data in a unified format that is ready for analysis and generation.

[0847] Step 2:

[0848] The server normalizes the collected profile data. This is a process that standardizes the data format and prepares it in a form that can be efficiently analyzed by generative AI models and emotion engines. The input is raw profile data, and the output is normalized profile data.

[0849] Step 3:

[0850] The server generates prompts for the generative AI model based on the normalized profile data. In a specific example, the prompt text includes information such as age, preferences, past behavioral history, and emotional state. The input is the profile data, and the output is the prompt text to be passed to the generative AI model.

[0851] Step 4:

[0852] The server uses a generative AI model (e.g., OpenAI's GPT-4) to generate an adaptive learning program, play program, or meal plan based on the prompt. The input is the prompt, and the output is the generated program or plan.

[0853] Step 5:

[0854] The server compiles the generated learning programs, play programs, and meal plans into a data package and sends it to the user terminal. The input is the generated program or plan, and the output is the data package sent to the user terminal.

[0855] Step 6:

[0856] The terminal receives the data package sent from the server, analyzes it, and displays it appropriately, allowing the user to access the programs and plans provided. The input is the data package sent from the server, and the output is the program or plan displayed on the user interface.

[0857] Step 7:

[0858] The device then activates the AI ​​advisor (school assistant or food advisor) that received the data and has it interact with the user. The AI ​​advisor responds adaptively based on the emotional data. The input is the data package sent from the server and emotional data collected in real time, and the output is the result of the interaction with the user.

[0859] Step 8:

[0860] The device monitors the user's facial expressions and tone of voice in real time, analyzes the emotional data using an emotion engine (such as Microsoft Azure's facial recognition API or Google Cloud's voice analysis API), and sends the analyzed emotional data to the server. The input is the user's facial expressions and voice data, and the output is the analyzed emotional data.

[0861] Step 9:

[0862] The server adjusts learning programs, play programs, and meal plans in real time based on the received emotional data, and retransmits them to the device as a new data package. The input is the analyzed emotional data, and the output is the adjusted programs and plans.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] [Third embodiment]

[0867] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0868] 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.

[0869] 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).

[0870] 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.

[0871] 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.

[0872] 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).

[0873] 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. 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.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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."

[0879] The present invention relates to an after-school support system that utilizes generative AI models to reduce the burden on staff at after-school care facilities and provide appropriate care and education for children. This system acquires children's profile data, generates learning and play programs based on that data, and distributes the data to terminals at the after-school care facility. A specific example of this system is described below.

[0880] Server-side processing

[0881] 1. Collecting and normalizing child profile data

[0882] The server retrieves profile data for each child from the after-school care facility's database. This profile data includes the child's age, learning progress, interests, and characteristics. The retrieved profile data is converted into a unified format that is easy for the generative AI model to process.

[0883] 2. Applying generative AI models

[0884] The server generates prompts for the generative AI model based on the normalized profile data. These prompts are instructions for generating learning and play programs appropriate for each child. The generative AI model receives these prompts, automatically generates learning and play programs, and returns them to the server.

[0885] 3. Creation of AI school assistants

[0886] The server generates an AI assistant based on the generated learning and play programs. This AI assistant is designed to assist children in learning and play while interacting with them. The appearance, voice, and speaking style of the AI ​​assistant are set based on specific parameters.

[0887] 4. Data transmission

[0888] The server combines the generated learning program, play program, and AI after-school assistant into a single data package and sends this package to a terminal at the after-school facility.

[0889] 5. Support for administrative work

[0890] The server automatically generates reports necessary for administrative work based on the activity data of children sent from the after-school care facility, thereby reducing the workload of instructors.

[0891] Terminal side processing

[0892] 1. Displaying received data

[0893] The terminal receives the data package sent from the server. This data package includes learning programs, play programs, and AI school assistants. The terminal analyzes the data and displays it appropriately.

[0894] 2. Starting and interacting with the AI ​​after-school assistant

[0895] The device then activates the AI ​​assistant, who interacts with the child to support their learning and play. The AI ​​assistant observes the child's reactions and sends the data to a server in real time.

[0896] 3. Status Notification

[0897] The devices monitor the children's behavior and reactions and notify teachers when certain conditions are met, such as an immediate alert if a fight breaks out or if a certain time has passed.

[0898] User (instructor) perspective

[0899] 1. Check and correct the program

[0900] The user (instructor) checks the learning and play programs displayed on the device and fine-tunes the settings as necessary, allowing them to provide appropriate support to each child.

[0901] 2. Collaboration with AI assistants

[0902] Users can work with AI after-school assistants to manage the progress of their children's studies and play, allowing them to focus on caring for their children, providing mental support, and mediating when problems arise.

[0903] 3. Checking and using the report

[0904] Users can check automatically generated reports provided by the server to understand the status of their children, and can use these reports to report to parents and schools, thereby streamlining operations.

[0905] Specific examples

[0906] For example, if a child is good at math and likes soccer, the server will generate a math problem set and a soccer-related indoor game based on that child's profile data. The device receives these programs, and the AI ​​school assistant asks the child math problems and suggests soccer games when the child gets bored. The user (instructor) monitors this process and provides support as needed.

[0907] As a result, the present invention reduces the burden on staff at after-school care facilities and provides high-quality care and education for children.

[0908] The processing flow will be explained below.

[0909] Server-side processing

[0910] Step 1: Collecting child profile data

[0911] The server obtains each child's profile data (age, interests, learning progress, etc.) from the after-school facility's database.

[0912] Step 2: Normalize the data

[0913] The server converts the acquired profile data into a unified format, making it easy for the generative AI model to process.

[0914] Step 3: Generate prompts

[0915] The server generates prompts to input into the generative AI model based on the normalized profile data.

[0916] Step 4: Generate Request

[0917] The server sends the generated prompts to the generative AI model, requesting it to generate learning and play programs.

[0918] Step 5: Receive the generated results

[0919] The server receives the learning programs and play programs returned from the generative AI model and stores them appropriately.

[0920] Step 6: Generate AI school assistants

[0921] The server generates an AI school assistant based on the generated learning and play programs, with the specified appearance, voice, and speaking style. Multiple assistants are generated as needed.

[0922] Step 7: Packaging the Data

[0923] The server combines the generated learning programs, play programs, and AI school assistants into a single package.

[0924] Step 8: Sending Data

[0925] The server transmits the packaged data to the terminal at the after-school facility.

[0926] Step 9: Receiving and processing activity data

[0927] The server receives the children's activity data sent from the after-school care facility and compiles it into statistical information and reports required for administrative work.

[0928] Step 10: Generate reports

[0929] The server checks the automatically generated report and provides it to the instructor.

[0930] Terminal side processing

[0931] Step 1: Receiving Data

[0932] The terminal receives data packages of learning programs, play programs, and AI school assistants sent from the server.

[0933] Step 2: Analyze and display the data

[0934] The device analyzes the received data and displays information appropriate for each child in an appropriate format.

[0935] Step 3: Launching the AI ​​School Assistant

[0936] The device then runs the received AI school assistant program and interacts with the children using the specified appearance and voice.

[0937] Step 4: Dialogue monitoring

[0938] The device monitors the conversation between the AI ​​school assistant and the child, and transmits the child's reaction data to a server in real time.

[0939] Step 5: Configure alerts

[0940] The device sets an alert based on set conditions (e.g., when a specific behavior is observed or when there is no response for a certain period of time).

[0941] Step 6: Send notification

[0942] The device immediately sends a notification to the instructor when the set alert conditions are met.

[0943] User (instructor) perspective

[0944] Step 1: Check the program

[0945] The user (instructor) checks the learning and play programs displayed on the terminal and fine-tunes the settings as necessary.

[0946] Step 2: Collaborate with AI assistants

[0947] Users can work with AI after-school assistants to manage the progress of their children's studies and play, allowing them to focus on caring for their children, providing mental support, and mediating when problems arise.

[0948] Step 3: Review and use the report

[0949] The user checks the automatically generated reports provided by the server to understand the child's situation, and reports to parents and schools based on these reports.

[0950] Through these steps, the AI ​​support system in after-school care facilities will reduce the burden on staff and ensure high-quality care for children.

[0951] Example 1

[0952] 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."

[0953] There is a need to reduce the burden on staff at after-school care facilities and provide high-quality care and education to children. Previous systems struggled to quickly and efficiently provide learning and play programs tailored to each child, and the administrative burden of managing children's activity data was significant. Furthermore, the application of AI after-school assistants lacked the ability to provide support for children's interactions.

[0954] 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.

[0955] In this invention, the server includes means for acquiring child profile data, means for converting and normalizing the profile data into a unified format, means for generating prompts based on the normalized profile data and applying them to the generative AI model, means for generating an AI after-school assistant based on the generated learning program and play program, means for transmitting the learning program, play program, and the generated AI after-school assistant to a terminal at the after-school facility, and means for receiving child activity data from the terminal at the after-school facility and automatically generating reports for administrative work. This reduces the burden on staff at the after-school facility, improves the quality of individualized care and education for children, and makes administrative work more efficient.

[0956] "Child profile data" means data that includes individual characteristics and information about a child, such as the child's age, learning progress, interests, and characteristics.

[0957] "Normalization" is the process of converting acquired profile data into a unified format to maintain data consistency.

[0958] A "prompt" is an input sentence in the form of text or a question that provides instructions to a generative AI model.

[0959] A "generative AI model" is an artificial intelligence model that automatically generates learning or play programs based on given prompts.

[0960] The "AI School Assistant" is an artificial intelligence character that interacts with children to assist them in learning and play, based on learning and play programs generated from a generative AI model.

[0961] "After-school facility terminal" refers to a hardware device such as a computer or tablet used within the after-school facility, and is a device that receives and displays data sent from the server.

[0962] "Child activity data" refers to data on children's reactions and behavior when participating in learning programs or play programs.

[0963] "Administrative work" refers to back-office work such as managing operations and preparing reports at after-school care facilities.

[0964] A "report" is an automatically generated report based on a child's activity data, and is a document containing information provided to instructors, parents, and schools.

[0965] This invention relates to an after-school support system that utilizes generative AI models to reduce the burden on staff at after-school care facilities and provide high-quality care and education to children. This system is composed of a server, a terminal, and a user's perspective, and each process functions in cooperation with each other.

[0966] Server Roles and Operations

[0967] The server accesses the after-school facility's database to obtain the child's profile data. This profile data includes the child's age, learning progress, interests, and characteristics. First, the data is converted into a unified format and normalized. Next, the server generates a prompt based on the normalized profile data. This prompt is used to provide instructions to the generative AI model and is written in the following text format:

[0968] Example prompt sentence:

[0969] "This child is 10 years old, good at math, and loves soccer. Use this profile to generate appropriate learning and play programs."

[0970] The server sends these prompts to a generative AI model, which then automatically generates appropriate learning and play programs based on the prompts. The generated programs are then returned to the server, which then generates an AI school assistant based on these programs. This assistant is designed to interact with children and support them in their learning and play.

[0971] The generated learning programs, play programs, and AI after-school assistants are compiled into a single data package and sent to the after-school facility's terminal. The server also automatically generates reports for administrative work based on the children's activity data sent from the after-school facility, improving work efficiency.

[0972] Terminal roles and processing

[0973] The device receives data packages sent from the server, analyzes them, and displays learning programs, play programs, and AI school assistants. The device launches the AI ​​school assistant, and the user (instructor) supports learning and play by interacting with the children through this assistant. The AI ​​assistant observes the children's reactions and behavior and sends the data to the server in real time.

[0974] For example, the AI ​​assistant might say, "Hello! Let's solve some math problems together today, and then we'll have a soccer quiz," attracting the child's interest while progressing the learning process. Additionally, if certain conditions are met, the device will immediately notify the instructor. For example, if a fight breaks out, it will issue an alert saying, "A fight has just broken out."

[0975] User (instructor) roles and processes

[0976] The user (instructor) checks the learning and play programs displayed on the device and fine-tunes the settings as needed. For example, if a math problem is too difficult, the difficulty level can be adjusted. The user works with the AI ​​after-school assistant to manage the children's learning and play progress. This allows the user to focus on caring for the children, providing mental support, and mediating when problems arise.

[0977] In addition, automatically generated reports provided by the server can be checked to understand the child's situation in detail, and these reports can be used to report to parents and schools, making work more efficient.

[0978] Specific examples

[0979] For example, if a child is good at math and likes soccer, the server will generate a math problem set and soccer-related indoor games based on the child's profile data. A prompt based on this profile might be something like, "This child is 10 years old, good at math, and likes soccer. Please generate appropriate learning and play programs based on this profile."

[0980] The device receives these programs, and the AI ​​assistant asks the children math problems and suggests playing soccer when they get bored. The user (instructor) monitors this process and provides support to the children as needed.

[0981] As a result, the present invention reduces the burden on staff at after-school care facilities and provides high-quality care and education for children.

[0982] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0983] Step 1:

[0984] The server accesses the database of the after-school care facility and retrieves profile data for each child. This profile data includes the child's age, learning progress, interests, characteristics, etc. It receives profile data from the database as input and retrieves profile data as output. Specifically, it extracts the required information from the database using SQL queries.

[0985] Step 2:

[0986] The server converts and normalizes the acquired profile data into a unified format. In this process, for example, age is standardized into a "number" format and interests into a "comma-separated keywords" format. It receives raw profile data as input, processes the data, and then outputs normalized profile data. Specifically, it applies data conversion rules to unify the format.

[0987] Step 3:

[0988] The server generates the prompts required for the generative AI model based on the normalized profile data. It receives the normalized profile data as input and obtains the generated prompt as output. Specifically, it creates a prompt such as, "This child is 10 years old, good at math, and likes soccer. Please generate appropriate learning and play programs based on this profile."

[0989] Step 4:

[0990] The server sends prompts to the generative AI model and automatically generates learning and play programs. It receives the generated prompts as input and obtains the generated learning and play programs as output. Specifically, it sends API requests to the generative AI model and analyzes the response.

[0991] Step 5:

[0992] The server generates an AI school assistant based on the generated learning and play programs. This AI assistant is designed to support learning and play while interacting with children. It receives learning and play programs as input and generates an AI school assistant as output. Specific operations are performed using a voice synthesis engine and character generation tools.

[0993] Step 6:

[0994] The server combines the generated learning program, play program, and AI school assistant into a single data package. This data package is then sent to the terminal. The server receives the learning program, play program, and AI school assistant as input, and obtains a combined data package as output. Specifically, the server combines the data into a format such as JSON and sends it to the terminal using the HTTP protocol.

[0995] Step 7:

[0996] The device receives the data package sent from the server, analyzes it, and displays the learning program, play program, and AI school assistant. It receives the data package as input and displays the analyzed data as output. Specifically, it parses the received data using a JSON parser and displays it on the user interface.

[0997] Step 8:

[0998] The device then activates the AI ​​assistant and has it interact with the children to support their learning and play. It receives the AI ​​assistant as input and starts a dialogue as output. Specific operations include playing the AI ​​assistant's voice and displaying an animated user interface.

[0999] Step 9:

[1000] The device observes the child's reactions and behavior and sends the data to the server in real time. It receives the child's reaction data as input and obtains the transmitted data as output. Specifically, it analyzes the data obtained from sensors and cameras and sends it to the server via an HTTP request.

[1001] Step 10:

[1002] The device notifies the instructor when certain conditions are met. It receives student behavior data and event triggers as input and issues an alert as output. Specific actions include displaying a pop-up message or audio alert on the UI.

[1003] Step 11:

[1004] The user (instructor) checks the learning program and play program displayed on the terminal and fine-tunes the settings as necessary. The displayed program is received as input and the fine-tuned settings are reflected as output. Specific operations involve operating the setting panel on the UI and adjusting the parameters.

[1005] Step 12:

[1006] The user checks the automatically generated report provided by the server and understands the child's situation in detail. The automatically generated report is received as input, and the understood information is obtained as output. Specifically, the user browses the contents of the report and extracts the necessary information.

[1007] (Application example 1)

[1008] 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."

[1009] In today's after-school care facilities, staff are required to handle a wide range of tasks, particularly providing academic guidance and play support to individual children, as well as the administrative work of understanding each child's situation and reporting it to parents and schools, which places a heavy burden on staff. Similarly, in brick-and-mortar stores, it is difficult to provide personalized product recommendations and services to each customer, and measures to increase customer satisfaction are lacking. Furthermore, there is a lack of a way to centrally manage and effectively utilize this data.

[1010] 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.

[1011] In this invention, the server includes: means for acquiring child profile data; means for applying a generative AI model to generate learning programs and play programs based on the profile data; means for transmitting the generated learning programs and play programs to a terminal at the after-school facility; means for receiving child activity data from the terminal at the after-school facility and automatically generating reports for administrative work; means for collecting customer profile data from multiple physical stores and applying a generative AI model to generate product proposals and service details based on the profile data; means for transmitting the generated product proposals and service details to a terminal at the physical store; and means for receiving customer response data from the terminal at the physical store and automatically generating reports required for the physical store's operations. This not only reduces the burden on staff at the after-school facility and enables the provision of high-quality care and education for children, but also enables the physical store to quickly and efficiently provide personalized product proposals and services to each customer.

[1012] "Profile Data" means information about a child or customer, including their age, gender, interests, and past activity.

[1013] A "learning program" is a program that includes teaching materials and teaching methods that are automatically generated by a generative AI model to provide children with appropriate learning content and methods.

[1014] A "play program" is a program that includes play and recreational activities that is automatically generated by a generative AI model based on a child's interests and characteristics.

[1015] A "generative AI model" is an artificial intelligence model that automatically generates appropriate output (learning programs, play programs, product suggestions, service content, etc.) based on input data.

[1016] A "terminal" is a hardware device used to display and process data, specifically a computer or smart device installed in an after-school facility or brick-and-mortar store.

[1017] "Activity data" is a record of the specific actions and reactions that children and customers take while studying, playing, shopping, etc.

[1018] A "report" is a document that summarizes the activities, grades, and reactions of children or clients, and is used to streamline administrative and management tasks.

[1019] "Product suggestions" are recommendations of products suitable for a specific customer, generated by a generative AI model based on customer profile data.

[1020] "Service content" refers to details of the services to be provided to a specific customer, generated by the generative AI model based on the customer's profile data and response data.

[1021] The following system configuration is used as an embodiment of the present invention.

[1022] System Overview

[1023] This system consists of a server, terminals installed in physical stores and after-school care facilities, and users (instructors and store staff) who operate them.

[1024] Server Processing

[1025] 1. Profile Data Collection and Normalization:

[1026] The server collects profile data of children or customers from after-school care facilities and multiple physical stores, including age, gender, interests, and past activity history.

[1027] The collected data is normalized into a unified format, making it easier for generative AI models to process.

[1028] 2. Applying generative AI models:

[1029] Based on the normalized profile data, the server generates prompts, which in turn generate learning and play programs suited to each child, as well as product suggestions and service content suited to each customer.

[1030] The generative AI model receives this prompt, automatically generates an appropriate program or suggestion, and returns it to the server.

[1031] 3. Data submission and reporting:

[1032] The generated programs and proposals are sent to terminals at after-school facilities and physical stores.

[1033] The server also receives activity data sent from after-school care facilities and brick-and-mortar stores and automatically generates reports for administrative work, thereby reducing the workload of instructors and store staff.

[1034] Terminal handling

[1035] 1. Displaying received data:

[1036] The terminal receives the data package sent from the server and appropriately displays learning programs and play programs for the children and product suggestions and service contents for the customers.

[1037] 2. Activating and interacting with the AI ​​assistant:

[1038] Based on the received program and suggestions, the AI ​​assistant will be activated and will support the child in their learning and play through dialogue, as well as recommend the most suitable products to the customer and answer any questions.

[1039] 3. Real-time data transmission:

[1040] The device transmits real-time reaction data from children and customers to a server, allowing for further data analysis.

[1041] User Roles

[1042] 1. Check and correct the program:

[1043] Instructors and store staff can check the programs and suggestions displayed on the terminals and make adjustments as necessary, thereby providing optimal support for each child or customer.

[1044] 2. Collaboration with AI assistants:

[1045] Instructors and store staff will work with AI assistants to streamline their daily work, and the AI ​​assistants will automatically communicate and guide customers, minimizing human intervention.

[1046] 3. Review and use the report:

[1047] Automatically generated reports provided by the server are used to understand children's learning progress and customer purchasing behavior, simplifying reporting to parents and companies and improving operational efficiency.

[1048] Specific examples

[1049] For example, if a schoolchild is good at math and likes soccer, the server can generate a prompt like this based on their profile data:

[1050] "Age: 8 Gender: Male Interests: Math and sports"

[1051] Based on this prompt, the generative AI model automatically generates math puzzles and soccer-related indoor games. Meanwhile, as an example of application in a physical store, the model suggests the latest sportswear and new cosmetics to a 30-year-old female customer based on the prompt: "Age: 30, Gender: Female, Interests: Sports and Fashion."

[1052] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1053] Step 1:

[1054] The server collects customer or child profile data from brick-and-mortar stores and after-school care facilities. This data includes age, gender, past activity history, interests, etc. The input is the raw data sent from each facility, and the output is pre-processed data for normalization.

[1055] Step 2:

[1056] The server normalizes the collected profile data. The input is the preprocessed data obtained in step 1, and the output is data in a unified format. Data normalization converts the data into a form that is easy for the generative AI model to process.

[1057] Step 3:

[1058] The server generates prompts based on the normalized profile data. The input is the normalized data, and the output is prompts to be used as input to the generative AI model. The prompts follow a specific template to appropriately describe the data.

[1059] Step 4:

[1060] The server inputs prompts into the generative AI model to generate learning programs, play programs, product suggestions, and service content. The input is the prompt, and the output is the appropriate program or suggestion. The generative AI model generates a response based on the specified prompt.

[1061] Step 5:

[1062] The server compiles the generated programs and proposals and sends them to terminals at the after-school care facility or physical store. The input is each generated program and proposal, and the output is the transmitted data package. This data package contains the program contents and proposals.

[1063] Step 6:

[1064] The terminal receives the data package sent from the server and displays the program or suggestion content appropriately. The input is the data package from the server, and the output is the displayed content.

[1065] Step 7:

[1066] Based on the received information, the terminal activates an AI assistant and interacts with the child to support learning and play. It also provides optimal product recommendations and service information to customers. The input is the program and recommendations received from the server, and the output is a response to the child or customer.

[1067] Step 8:

[1068] The user (instructor or store staff) checks the content displayed on the terminal and fine-tunes the program and suggestions as necessary. The input is the data displayed on the terminal, and the output is the adjusted program and suggestions.

[1069] Step 9:

[1070] The terminal transmits the reaction and behavior data of the children or customers to the server in real time. The input is the real-time reaction data of the children or customers, and the output is the data transmitted to the server.

[1071] Step 10:

[1072] The server analyzes the received reaction data and automatically generates a new report. The input is real-time reaction data, and the output is an automatically generated report. This report helps instructors and store staff improve their work efficiency.

[1073] The above is a detailed explanation of the application process, broken down into specific steps, that will lead to the creation of an effective support system that utilizes generative AI models and prompts.

[1074] 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.

[1075] The present invention relates to an after-school support system that generates learning and play programs based on children's profile data and further combines an emotion engine to analyze and recognize children's emotions, thereby providing more detailed support. This system utilizes children's profile data and applies a generative AI model and emotion engine to support learning and play, with the aim of reducing the burden on staff at after-school facilities. A specific example of this system is described below.

[1076] Server-side processing

[1077] 1. Collecting and normalizing child profile data

[1078] The server retrieves each child's profile data from the after-school facility's database. This profile data includes the child's age, learning progress, interests, and characteristics. The retrieved profile data is converted into a unified format that is easy for the generative AI model and emotion engine to process.

[1079] 2. Applying generative AI models

[1080] The server generates prompts for the generative AI model based on the normalized profile data. These prompts serve as instructions for generating learning and play programs appropriate for each child. The generative AI model receives the prompts, automatically generates learning and play programs, and returns them to the server.

[1081] 3. Applying the Emotion Engine

[1082] The server uses an emotion engine to analyze the child's facial expressions and tone of voice, allowing it to understand the child's emotional state in real time and adaptively adjust learning and play programs.

[1083] 4. Creation of AI school assistants

[1084] The server generates an AI school assistant based on the generated learning and play programs, as well as emotional data generated by the emotion engine. This AI school assistant supports children in their studies and play while interacting with them, and also provides mental care based on the emotional data.

[1085] 5. Sending and Receiving Data

[1086] The server compiles the generated learning programs, play programs, and AI after-school assistants into a single data package and sends it to the after-school facility's terminal. It also receives the children's activity data sent from the after-school facility and automatically generates reports necessary for administrative work.

[1087] Terminal side processing

[1088] 1. Data Receipt and Analysis

[1089] The device receives data packages (learning programs, play programs, AI school assistants, and emotional data) sent from the server, analyzes the received data, and displays it appropriately.

[1090] 2. Starting and interacting with the AI ​​after-school assistant

[1091] The device then activates the AI ​​assistant, who interacts with the child to support learning and play. Based on the emotional data analyzed by the emotion engine, the device responds adaptively to the child's emotional state.

[1092] 3. Monitoring Emotional Data

[1093] The device monitors the child's facial expressions and tone of voice in real time and uses an emotion engine to transmit emotional data to the server, allowing the device to grasp the child's emotional state in real time.

[1094] 4. Status Notification

[1095] The device sets an alert according to the set conditions (e.g., if a specific emotion continues or if there is a sudden change in emotion) and notifies the instructor as necessary.

[1096] User (instructor) perspective

[1097] 1. Check and correct the program

[1098] The user (instructor) checks the learning program, play program, and emotional data displayed on the device and fine-tunes the settings as needed, allowing them to provide appropriate support to each child.

[1099] 2. Collaboration with AI assistants

[1100] Users can work with AI after-school assistants to manage children's learning and play progress, and can focus on providing mental care for children and mediating when problems arise based on emotional data.

[1101] 3. Checking and using the report

[1102] The user checks the automatically generated reports provided by the server to understand the child's situation, and reports to parents and schools based on these reports.

[1103] Specific examples

[1104] For example, if a child is good at math and likes soccer, but has recently been feeling stressed, the server will generate a math problem set and a soccer-related indoor game based on the child's profile and emotional data. Furthermore, if the emotion engine analyzes that the child is feeling stressed, it will use that information to suggest activities and conversations that will help them relax. The device receives these programs, and the AI ​​school assistant will ask the child math problems and suggest activities to help them relax if they feel stressed. The user (instructor) monitors this process and provides additional support as needed.

[1105] As a result, the present invention reduces the burden on staff at after-school care facilities and provides high-quality care and education for children.

[1106] The processing flow will be explained below.

[1107] Server-side processing

[1108] Step 1: Collecting child profile data

[1109] The server obtains each child's profile data (age, interests, learning progress, characteristics, etc.) from the after-school facility's database.

[1110] Step 2: Normalize the data

[1111] The server converts the acquired profile data into a unified format, making it easier for the generative AI model and emotion engine to process.

[1112] Step 3: Generate prompts

[1113] The server generates prompts to input into the generative AI model based on the normalized profile data.

[1114] Step 4: Generate Request

[1115] The server sends the generated prompts to the generative AI model, requesting it to generate learning and play programs.

[1116] Step 5: Receive the generated results

[1117] The server receives the learning programs and play programs returned from the generative AI model and stores them appropriately.

[1118] Step 6: Applying the Emotion Engine

[1119] The server uses an emotion engine to analyze the child's facial expressions and tone of voice, thereby obtaining emotion data in real time.

[1120] Step 7: Generate AI school assistants

[1121] The server generates an AI school assistant based on the generated learning and play programs, as well as emotional data generated by the emotion engine. This AI school assistant responds adaptively according to the emotional state of the child.

[1122] Step 8: Packaging the Data

[1123] The server compiles the generated learning program, play program, AI school assistant, and emotional data into a single package.

[1124] Step 9: Sending Data

[1125] The server transmits the packaged data to the terminal at the after-school facility.

[1126] Step 10: Receiving and processing activity data

[1127] The server receives the children's activity data sent from the after-school care facility and compiles it into statistical information and reports required for administrative work.

[1128] Step 11: Generate reports

[1129] The server checks the automatically generated report and provides it to the instructor.

[1130] Terminal side processing

[1131] Step 1: Receiving Data

[1132] The terminal receives the learning program, play program, AI school assistant, and emotion data package sent from the server.

[1133] Step 2: Analyze and display the data

[1134] The device analyzes the received data and displays information appropriate for each child in an appropriate format.

[1135] Step 3: Launching the AI ​​School Assistant

[1136] The device then runs the received AI school assistant program and interacts with the children using the specified appearance and voice.

[1137] Step 4: Dialogue monitoring

[1138] The device monitors the conversation between the AI ​​school assistant and the child, and transmits the child's reaction data to a server in real time.

[1139] Step 5: Monitoring sentiment data

[1140] The device uses an emotion engine to analyze the child's facial expressions and tone of voice in real time and transmits the emotional data to a server.

[1141] Step 6: Configure alerts

[1142] The device sets an alert according to the set conditions (e.g., when a specific emotion continues or when there is a sudden change in emotion).

[1143] Step 7: Send notification

[1144] The device immediately sends a notification to the instructor when the set alert conditions are met.

[1145] User (instructor) perspective

[1146] Step 1: Check and correct the program

[1147] The user (instructor) checks the learning program, play program, and emotional data displayed on the terminal and fine-tunes the settings as necessary.

[1148] Step 2: Collaborate with AI assistants

[1149] Users can work with AI after-school assistants to manage the progress of children's studies and play, and use emotional data to focus on mental care and mediation when problems arise.

[1150] Step 3: Review and use the report

[1151] The user checks the automatically generated reports provided by the server to understand the child's situation, and reports to parents and schools based on these reports.

[1152] Specific examples

[1153] For example, if a child is good at math and likes soccer, but has recently been feeling stressed, the server will generate a math problem set and a soccer-related indoor game based on the child's profile and emotional data. Furthermore, if the emotion engine analyzes that the child is feeling stressed, it will use that information to suggest activities and conversations that will help them relax. The device receives these programs, and the AI ​​school assistant will ask the child math problems and suggest activities to help them relax if they feel stressed. The user (instructor) monitors this process and provides additional support as needed.

[1154] Example 2

[1155] 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."

[1156] Modern after-school care facilities are required to provide attentive support to each child while reducing the burden on staff. However, conventional systems have difficulty responding to the diverse needs of children and are limited in the adaptive scientific support that takes into account their emotional state. Therefore, a system is needed that can provide appropriate learning and play programs based on each child's individual characteristics and emotional state, and provide feedback on the effectiveness of these programs in real time.

[1157] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring personal information of children, means for converting the personal information into a unified format, means for applying a generative AI model to generate learning programs and play programs based on the unified personal information, means for generating and sending prompt sentences to the generative AI model, means for using an emotion engine to analyze the children's facial expressions and tone of voice and determine their emotional state, means for integrating the generated learning programs, play programs, and emotion data to generate an AI after-school assistant, means for transmitting the generated learning programs, play programs, and AI after-school assistant to a terminal at the after-school facility, and means for receiving children's activity data from the terminal at the after-school facility and automatically generating reports for administrative work. This makes it possible to provide learning and play programs that take into account the individual characteristics and emotional state of children and to adaptively adjust them in real time.

[1158] "Personal information of children" refers to data that represents individual characteristics of children, such as their age, learning progress, interests, and characteristics.

[1159] "Uniform format" means that data is converted into a consistent format that facilitates subsequent processing.

[1160] A "generative AI model" is an artificial intelligence model that automatically generates learning and play programs based on input prompts.

[1161] A "prompt" is a sentence used to instruct a generative AI model to produce a specific output.

[1162] The "emotion engine" is a system that analyzes a child's facial expressions and tone of voice to determine their emotional state.

[1163] The "AI School Assistant" is an artificial intelligence agent that supports children based on generated learning programs, play programs, and emotional data.

[1164] "After-school facility terminals" refer to devices such as computers and tablets used within the after-school facility.

[1165] "Activity data" is data collected during children's learning and play, including the progress and results of their activities.

[1166] "Reports for administrative work" are automatically generated business reports based on children's activity data, and are used to reduce the burden on staff.

[1167] This invention relates to an after-school support system that generates learning and play programs based on children's profile data and further analyzes and recognizes children's emotions by combining it with an emotion engine to provide more detailed support. This system aims to understand each child's individual characteristics and emotional state in real time, support their learning and play, and reduce the burden on staff at after-school facilities.

[1168] Server-side explanation

[1169] The server retrieves personal information about each child from the after-school care facility's database. This information includes the child's age, learning progress, interests, and characteristics. The retrieved data is converted into a unified format. By organizing it into a data frame using Python's Pandas library, the individual data is organized into a consistent, processable format.

[1170] Next, we generate a prompt to send to the generative AI model. Specifically, we generate a prompt in text format like this:

[1171] "Profile data: Age 10, Interests: Mathematics, Traits: High concentration. Please generate suitable learning and play programs."

[1172] The generated prompts are sent to a generative AI model (e.g., GPT-3), which then uses natural language processing technology to automatically generate learning and play programs for the child.

[1173] Furthermore, the server uses an emotion engine to analyze the child's facial expressions and tone of voice. The emotion analysis results indicate the child's real-time emotional state and are adaptively reflected in the learning and play programs. This analysis utilizes, for example, an emotion analysis service provided through an API.

[1174] Finally, the server integrates the generated learning and play programs with the emotional data generated from them to generate an AI school assistant. This AI school assistant provides support through dialogue with the children and also provides mental care based on the emotional data.

[1175] Terminal side explanation

[1176] The terminal receives the data package (learning program, play program, AI school assistant, emotional data) sent from the server, analyzes it, and displays it appropriately.

[1177] The device launches the AI ​​assistant and begins a dialogue with the child. The assistant presents learning and play programs to the child, while adaptively responding to the child's emotional state based on the analysis results of the emotion engine. Specifically, a dialogue system built using Python generates flexible responses based on the child's responses and emotional state.

[1178] The device also uses a camera and microphone to capture the child's facial expressions and tone of voice in real time, which are then sent to an emotion engine for analysis. The analysis results are then sent to a server for further adaptive responses.

[1179] Furthermore, the device will issue alerts in response to certain conditions (such as sustained stress levels or sudden emotional changes) and notify instructors as needed, enabling prompt response to problems and providing consistent support to children.

[1180] User (instructor) explanation

[1181] The user checks the learning and play programs and emotional data displayed on the device and makes fine adjustments as necessary. The system works in cooperation with AI after-school assistants to manage the children's progress in learning and play. The emotional data is also used to provide mental care for the children and respond to any problems that arise.

[1182] Users can also check automatically generated reports provided by the server to understand their child's progress, which can then be sent to parents and schools to provide consistent support and feedback to the child.

[1183] Specific examples

[1184] For example, consider a child who excels at math and loves soccer, but has recently been feeling stressed. In this case, the server generates a math workbook and a soccer-related indoor game based on the child's profile and emotional data. Furthermore, if the emotion engine analyzes that the child is feeling stressed, it will use that information to suggest activities and conversations that will help them relax.

[1185] The device receives these programs, and the AI ​​assistant asks the children math problems and suggests activities to relax them if they feel stressed. The user (instructor) monitors this process and provides additional support as needed.

[1186] As a result, the present invention reduces the burden on staff at after-school care facilities and enables high-quality care and education for children.

[1187] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1188] Step 1:

[1189] The server retrieves personal information about children from the after-school facility's database. The input data includes data such as the child's age, learning progress, interests, and characteristics, which are extracted from the after-school facility's database. This data is extracted using an SQL query to obtain the data. The output data is raw personal information data.

[1190] Step 2:

[1191] The server converts the acquired personal information into a unified format. The raw personal information data acquired in step 1 is used as input. Specifically, it uses the Python Pandas library to organize the data into a data frame. The output is the personal information data converted into a unified format.

[1192] Step 3:

[1193] The server generates a prompt sentence based on the unified personal information. The input is the unified personal information data obtained in step 2. As a specific operation, the prompt sentence is generated using Python's text manipulation functions. An example of a prompt sentence is generated as follows: "Profile data: age 10, interest: mathematics, characteristic: high concentration. Please generate suitable learning and play programs." The output is the generated prompt sentence.

[1194] Step 4:

[1195] The server sends the prompt sentence to the generative AI model to generate a learning program and a play program. The input is the prompt sentence generated in step 3. This is sent to the generative AI model (e.g., GPT-3) and the generated learning program and play program are received. The output is the generated learning program and play program.

[1196] Step 5:

[1197] The server uses an emotion engine to analyze the child's facial expression and tone of voice to determine their emotional state. The input is the child's facial expression image and voice data. Specifically, the server sends an emotion analysis request to the API and receives the analysis results. The output is the analyzed emotion data.

[1198] Step 6:

[1199] The server integrates the generated learning program, play program, and emotion data to generate an AI school assistant. The inputs are the learning program and play program generated in step 4 and the emotion data from step 5. A dialogue system is built using Python libraries (e.g., NLTK and spaCy) to prepare the AI ​​school assistant. The output is the generated AI school assistant.

[1200] Step 7:

[1201] The server sends the generated learning program, play program, and AI school assistant to the terminal at the after-school facility. The input is the learning program, play program, and AI school assistant obtained in step 6. Specifically, the server sends data packages using a network protocol (e.g., HTTP or WebSocket). The output is the data package sent to the terminal.

[1202] Step 8:

[1203] The terminal receives the data package sent from the server, parses it, and displays it appropriately. The input is the data package sent from the server. Specific operations include parsing the JSON data in Python and using a GUI to display it appropriately. The output is the displayed learning program, play program, and AI school assistant.

[1204] Step 9:

[1205] The terminal starts the AI ​​assistant and begins interacting with the child. The input is the AI ​​assistant received and displayed in step 8. Specifically, the AI ​​assistant presents learning and play programs to the child and provides support through interaction. The output is the result of the interaction with the child.

[1206] Step 10:

[1207] The device monitors the child's facial expressions and tone of voice in real time and sends the emotional data to the server using an emotion engine. The input is the child's facial expression images and voice data. Specific operations include collecting data using a camera and microphone and sending it to the emotion engine. The output is the analyzed emotional data.

[1208] Step 11:

[1209] The device sets alerts according to specific conditions and notifies the instructor as necessary. The input is the emotion data analyzed in step 10. The specific operation is to monitor the alert conditions and notify the instructor via email or SMS when the conditions are met. The output is the notification to the instructor.

[1210] Step 12:

[1211] The user checks the learning program, play program, and emotional data displayed on the device and fine-tunes the settings as needed. The input is the information displayed on the device. Specific actions include changing the settings in the GUI and supporting the child in cooperation with the AI ​​after-school assistant. The output is the adjusted learning program and play program.

[1212] Step 13:

[1213] The user manages the child's progress in learning and play, and provides mental care and responds to problems based on emotional data. The input is the child's activity data and emotional data. Specific actions include checking the activity record and providing support as needed. The output is the result of managing the child's progress.

[1214] Step 14:

[1215] The user checks the automatically generated report provided by the server and understands the child's situation. The input is the report provided by the server. The specific operation is to check the report and report it to the parents or school. The output is the report result.

[1216] As a result, the present invention reduces the burden on staff at after-school care facilities and enables high-quality care and education for children.

[1217] (Application example 2)

[1218] 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."

[1219] The present invention aims to improve the effectiveness of children's education and reduce the burden on after-school care facility staff by creating optimal learning and play programs based on each child's profile data and providing adaptive support through real-time analysis of the child's emotional state in a system that supports children's learning and play. Furthermore, the present invention aims to solve the problem of improving individual user experiences by applying emotion analysis to meal plans and menu suggestions.

[1220] 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.

[1221] In this invention, the server includes means for acquiring profile data of children, means for applying a generative AI model to generate learning programs and play programs based on the profile data, means for transmitting the generated learning programs and play programs to a terminal at the after-school facility, means for receiving activity data of children from the terminal at the after-school facility and automatically generating reports for administrative work, means including an emotion engine for analyzing a user's facial expressions and tone of voice, and means for adaptively suggesting menus based on the user's emotional state analyzed by the emotion engine. This enables detailed educational support and mental care for each child, and further enables the system to suggest meal plans and menus that are optimal for each individual user's emotional state on that day.

[1222] "Profile data" refers to individual information about an individual user (or child), such as age, preferences, past behavioral history, learning progress, and characteristics.

[1223] A "generative AI model" refers to an artificial intelligence model that automatically generates adaptive programs and information based on prompts from input data.

[1224] An "emotion engine" refers to a technology that analyzes a user's emotional state, such as facial expressions and tone of voice, in real time and provides the analysis results.

[1225] A "learning program" refers to educational content and assignments that are individually created to suit each child's learning ability and progress.

[1226] "Play programs" refer to games and activities that are individually created based on a child's interests and preferences.

[1227] "Means" refers to an apparatus, method, or system for performing a particular function.

[1228] "Menu Suggestion" refers to automatically recommending meal plans that best suit a user's current mood and preferences based on their profile data and emotional state.

[1229] "User" refers to individuals who use the system, particularly in the present invention, children and users of food delivery services.

[1230] "Terminal" refers to the device that displays data received from the server and interacts with the user, such as a smartphone or computer.

[1231] "Activity data" refers to data related to the user's actions and reactions when using the system.

[1232] "Server" refers to the central system that receives and sends data from multiple users and processes the data using generative AI models and emotion engines.

[1233] This system generates learning and play programs based on a child's profile data, and provides adaptive support by analyzing and recognizing the child's emotional state using an emotion engine. Examples of applications include a food delivery application that suggests optimal meal plans and menus for individual users.

[1234] Server-side processing

[1235] 1. Profile data collection and normalization

[1236] The server first acquires the profile data of the child or user, including age, preferences, past behavioral history, learning progress, characteristics, etc. The acquired data is then converted into a unified format that can be easily processed by the generative AI model and emotion engine.

[1237] 2. Applying generative AI models

[1238] The server uses the normalized profile data to generate prompts for the generative AI model, which in turn guides the creation of learning, play, or meal plans tailored to each user.

[1239] Example: Prompt statement

[1240] prompt:

[1241] User's age: 25

[1242] Favorite food: Italian

[1243] Allergens: nuts

[1244] Suggested menu: Pizza, salad, herbal tea

[1245] This user's emotion today is "Stressed" but they would like to relax a bit. Please suggest the best meal plan for them.

[1246] 3. Applying the Emotion Engine

[1247] The server uses an emotion engine to analyze the user's facial expressions and tone of voice to understand the user's emotional state in real time, allowing it to make adaptive menu suggestions and adjust learning programs.

[1248] 4. Data transmission and reception

[1249] The system sends a data package containing the generated learning program, play program, meal plan, and emotional data to the user's device, receives data on the child's activities and the user's reaction data, and automatically generates reports required for administrative work.

[1250] Terminal side processing

[1251] 1. Data Receipt and Analysis

[1252] The terminal receives the data packages sent by the server, displays them appropriately, and allows the user to access the plans and programs offered through a user interface.

[1253] 2. Launching and interacting with the AI ​​advisor

[1254] The device then activates the AI ​​advisor (school assistant or food advisor) that receives the information and provides support through dialogue with the user. Based on the emotional data analyzed by the emotion engine, the device responds adaptively.

[1255] 3. Monitoring Emotional Data

[1256] The device monitors the user's facial expressions and tone of voice in real time and uses an emotion engine to transmit emotional data to the server.

[1257] Hardware and software used

[1258] The server uses a high-performance computer (cloud-based or on-premise), and the software incorporates OpenAI's GPT-4 as a generative AI model, and the emotion engine incorporates Microsoft Azure's facial recognition API and Google Cloud's voice analysis API.

[1259] The user device will be a smartphone or computer equipped with a camera and microphone, and the user interface will be a custom food delivery application or educational support application.

[1260] Specific examples

[1261] For example, if a particular user is feeling stressed, the system uses the smartphone's camera and microphone to analyze this emotional data. Since the profile data states "Favorite food: Italian, Allergy: Nuts," the generative AI model suggests a meal plan that includes pizza and salad. An additional suggestion is herbal tea, which is said to have a relaxing effect. The user can then select from the suggested menu and place an order via a food delivery service.

[1262] As described above, the present invention is a system that provides detailed support to individual children and users, improving their quality of life.

[1263] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1264] Step 1:

[1265] The server obtains user profile data, specifically, age, preferences, allergy information, past order history, etc., from a database. The input is the profile data in the database, and the output is the profile data in a unified format that is ready for analysis and generation.

[1266] Step 2:

[1267] The server normalizes the collected profile data. This is a process that standardizes the data format and prepares it in a form that can be efficiently analyzed by generative AI models and emotion engines. The input is raw profile data, and the output is normalized profile data.

[1268] Step 3:

[1269] The server generates prompts for the generative AI model based on the normalized profile data. In a specific example, the prompt text includes information such as age, preferences, past behavioral history, and emotional state. The input is the profile data, and the output is the prompt text to be passed to the generative AI model.

[1270] Step 4:

[1271] The server uses a generative AI model (e.g., OpenAI's GPT-4) to generate an adaptive learning program, play program, or meal plan based on the prompt. The input is the prompt, and the output is the generated program or plan.

[1272] Step 5:

[1273] The server compiles the generated learning programs, play programs, and meal plans into a data package and sends it to the user terminal. The input is the generated program or plan, and the output is the data package sent to the user terminal.

[1274] Step 6:

[1275] The terminal receives the data package sent from the server, analyzes it, and displays it appropriately, allowing the user to access the programs and plans provided. The input is the data package sent from the server, and the output is the program or plan displayed on the user interface.

[1276] Step 7:

[1277] The device then activates the AI ​​advisor (school assistant or food advisor) that received the data and has it interact with the user. The AI ​​advisor responds adaptively based on the emotional data. The input is the data package sent from the server and emotional data collected in real time, and the output is the result of the interaction with the user.

[1278] Step 8:

[1279] The device monitors the user's facial expressions and tone of voice in real time, analyzes the emotional data using an emotion engine (such as Microsoft Azure's facial recognition API or Google Cloud's voice analysis API), and sends the analyzed emotional data to the server. The input is the user's facial expressions and voice data, and the output is the analyzed emotional data.

[1280] Step 9:

[1281] The server adjusts learning programs, play programs, and meal plans in real time based on the received emotional data, and retransmits them to the device as a new data package. The input is the analyzed emotional data, and the output is the adjusted programs and plans.

[1282] 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.

[1283] 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.

[1284] 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.

[1285] [Fourth embodiment]

[1286] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1287] 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.

[1288] 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).

[1289] 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.

[1290] 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.

[1291] 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).

[1292] 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. 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.

[1293] 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.

[1294] 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.

[1295] 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.

[1296] 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.

[1297] 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.

[1298] 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."

[1299] The present invention relates to an after-school support system that utilizes generative AI models to reduce the burden on staff at after-school care facilities and provide appropriate care and education for children. This system acquires children's profile data, generates learning and play programs based on that data, and distributes the data to terminals at the after-school care facility. A specific example of this system is described below.

[1300] Server-side processing

[1301] 1. Collecting and normalizing child profile data

[1302] The server retrieves profile data for each child from the after-school care facility's database. This profile data includes the child's age, learning progress, interests, and characteristics. The retrieved profile data is converted into a unified format that is easy for the generative AI model to process.

[1303] 2. Applying generative AI models

[1304] The server generates prompts for the generative AI model based on the normalized profile data. These prompts are instructions for generating learning and play programs appropriate for each child. The generative AI model receives these prompts, automatically generates learning and play programs, and returns them to the server.

[1305] 3. Creation of AI school assistants

[1306] The server generates an AI assistant based on the generated learning and play programs. This AI assistant is designed to assist children in learning and play while interacting with them. The appearance, voice, and speaking style of the AI ​​assistant are set based on specific parameters.

[1307] 4. Data transmission

[1308] The server combines the generated learning program, play program, and AI after-school assistant into a single data package and sends this package to a terminal at the after-school facility.

[1309] 5. Support for administrative work

[1310] The server automatically generates reports necessary for administrative work based on the activity data of children sent from the after-school care facility, thereby reducing the workload of instructors.

[1311] Terminal side processing

[1312] 1. Displaying received data

[1313] The terminal receives the data package sent from the server. This data package includes learning programs, play programs, and AI school assistants. The terminal analyzes the data and displays it appropriately.

[1314] 2. Starting and interacting with the AI ​​after-school assistant

[1315] The device then activates the AI ​​assistant, who interacts with the child to support their learning and play. The AI ​​assistant observes the child's reactions and sends the data to a server in real time.

[1316] 3. Status Notification

[1317] The devices monitor the children's behavior and reactions and notify teachers when certain conditions are met, such as an immediate alert if a fight breaks out or if a certain time has passed.

[1318] User (instructor) perspective

[1319] 1. Check and correct the program

[1320] The user (instructor) checks the learning and play programs displayed on the device and fine-tunes the settings as necessary, allowing them to provide appropriate support to each child.

[1321] 2. Collaboration with AI assistants

[1322] Users can work with AI after-school assistants to manage the progress of their children's studies and play, allowing them to focus on caring for their children, providing mental support, and mediating when problems arise.

[1323] 3. Checking and using the report

[1324] Users can check automatically generated reports provided by the server to understand the status of their children, and can use these reports to report to parents and schools, thereby streamlining operations.

[1325] Specific examples

[1326] For example, if a child is good at math and likes soccer, the server will generate a math problem set and a soccer-related indoor game based on that child's profile data. The device receives these programs, and the AI ​​school assistant asks the child math problems and suggests soccer games when the child gets bored. The user (instructor) monitors this process and provides support as needed.

[1327] As a result, the present invention reduces the burden on staff at after-school care facilities and provides high-quality care and education for children.

[1328] The processing flow will be explained below.

[1329] Server-side processing

[1330] Step 1: Collecting child profile data

[1331] The server obtains each child's profile data (age, interests, learning progress, etc.) from the after-school facility's database.

[1332] Step 2: Normalize the data

[1333] The server converts the acquired profile data into a unified format, making it easy for the generative AI model to process.

[1334] Step 3: Generate prompts

[1335] The server generates prompts to input into the generative AI model based on the normalized profile data.

[1336] Step 4: Generate Request

[1337] The server sends the generated prompts to the generative AI model, requesting it to generate learning and play programs.

[1338] Step 5: Receive the generated results

[1339] The server receives the learning programs and play programs returned from the generative AI model and stores them appropriately.

[1340] Step 6: Generate AI school assistants

[1341] The server generates an AI school assistant based on the generated learning and play programs, with the specified appearance, voice, and speaking style. Multiple assistants are generated as needed.

[1342] Step 7: Packaging the Data

[1343] The server combines the generated learning programs, play programs, and AI school assistants into a single package.

[1344] Step 8: Sending Data

[1345] The server transmits the packaged data to the terminal at the after-school facility.

[1346] Step 9: Receiving and processing activity data

[1347] The server receives the children's activity data sent from the after-school care facility and compiles it into statistical information and reports required for administrative work.

[1348] Step 10: Generate reports

[1349] The server checks the automatically generated report and provides it to the instructor.

[1350] Terminal side processing

[1351] Step 1: Receiving Data

[1352] The terminal receives data packages of learning programs, play programs, and AI school assistants sent from the server.

[1353] Step 2: Analyze and display the data

[1354] The device analyzes the received data and displays information appropriate for each child in an appropriate format.

[1355] Step 3: Launching the AI ​​School Assistant

[1356] The device then runs the received AI school assistant program and interacts with the children using the specified appearance and voice.

[1357] Step 4: Dialogue monitoring

[1358] The device monitors the conversation between the AI ​​school assistant and the child, and transmits the child's reaction data to a server in real time.

[1359] Step 5: Configure alerts

[1360] The device sets an alert based on set conditions (e.g., when a specific behavior is observed or when there is no response for a certain period of time).

[1361] Step 6: Send notification

[1362] The device immediately sends a notification to the instructor when the set alert conditions are met.

[1363] User (instructor) perspective

[1364] Step 1: Check the program

[1365] The user (instructor) checks the learning and play programs displayed on the terminal and fine-tunes the settings as necessary.

[1366] Step 2: Collaborate with AI assistants

[1367] Users can work with AI after-school assistants to manage the progress of their children's studies and play, allowing them to focus on caring for their children, providing mental support, and mediating when problems arise.

[1368] Step 3: Review and use the report

[1369] The user checks the automatically generated reports provided by the server to understand the child's situation, and reports to parents and schools based on these reports.

[1370] Through these steps, the AI ​​support system in after-school care facilities will reduce the burden on staff and ensure high-quality care for children.

[1371] Example 1

[1372] 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."

[1373] There is a need to reduce the burden on staff at after-school care facilities and provide high-quality care and education to children. Previous systems struggled to quickly and efficiently provide learning and play programs tailored to each child, and the administrative burden of managing children's activity data was significant. Furthermore, the application of AI after-school assistants lacked the ability to provide support for children's interactions.

[1374] 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.

[1375] In this invention, the server includes means for acquiring child profile data, means for converting and normalizing the profile data into a unified format, means for generating prompts based on the normalized profile data and applying them to the generative AI model, means for generating an AI after-school assistant based on the generated learning program and play program, means for transmitting the learning program, play program, and the generated AI after-school assistant to a terminal at the after-school facility, and means for receiving child activity data from the terminal at the after-school facility and automatically generating reports for administrative work. This reduces the burden on staff at the after-school facility, improves the quality of individualized care and education for children, and makes administrative work more efficient.

[1376] "Child profile data" means data that includes individual characteristics and information about a child, such as the child's age, learning progress, interests, and characteristics.

[1377] "Normalization" is the process of converting acquired profile data into a unified format to maintain data consistency.

[1378] A "prompt" is an input sentence in the form of text or a question that provides instructions to a generative AI model.

[1379] A "generative AI model" is an artificial intelligence model that automatically generates learning or play programs based on given prompts.

[1380] The "AI School Assistant" is an artificial intelligence character that interacts with children to assist them in learning and play, based on learning and play programs generated from a generative AI model.

[1381] "After-school facility terminal" refers to a hardware device such as a computer or tablet used within the after-school facility, and is a device that receives and displays data sent from the server.

[1382] "Child activity data" refers to data on children's reactions and behavior when participating in learning programs or play programs.

[1383] "Administrative work" refers to back-office work such as managing operations and preparing reports at after-school care facilities.

[1384] A "report" is an automatically generated report based on a child's activity data, and is a document containing information provided to instructors, parents, and schools.

[1385] This invention relates to an after-school support system that utilizes generative AI models to reduce the burden on staff at after-school care facilities and provide high-quality care and education to children. This system is composed of a server, a terminal, and a user's perspective, and each process functions in cooperation with each other.

[1386] Server Roles and Operations

[1387] The server accesses the after-school facility's database to obtain the child's profile data. This profile data includes the child's age, learning progress, interests, and characteristics. First, the data is converted into a unified format and normalized. Next, the server generates a prompt based on the normalized profile data. This prompt is used to provide instructions to the generative AI model and is written in the following text format:

[1388] Example prompt sentence:

[1389] "This child is 10 years old, good at math, and loves soccer. Use this profile to generate appropriate learning and play programs."

[1390] The server sends these prompts to a generative AI model, which then automatically generates appropriate learning and play programs based on the prompts. The generated programs are then returned to the server, which then generates an AI school assistant based on these programs. This assistant is designed to interact with children and support them in their learning and play.

[1391] The generated learning programs, play programs, and AI after-school assistants are compiled into a single data package and sent to the after-school facility's terminal. The server also automatically generates reports for administrative work based on the children's activity data sent from the after-school facility, improving work efficiency.

[1392] Terminal roles and processing

[1393] The device receives data packages sent from the server, analyzes them, and displays learning programs, play programs, and AI school assistants. The device launches the AI ​​school assistant, and the user (instructor) supports learning and play by interacting with the children through this assistant. The AI ​​assistant observes the children's reactions and behavior and sends the data to the server in real time.

[1394] For example, the AI ​​assistant might say, "Hello! Let's solve some math problems together today, and then we'll have a soccer quiz," attracting the child's interest while progressing the learning process. Additionally, if certain conditions are met, the device will immediately notify the instructor. For example, if a fight breaks out, it will issue an alert saying, "A fight has just broken out."

[1395] User (instructor) roles and processes

[1396] The user (instructor) checks the learning and play programs displayed on the device and fine-tunes the settings as needed. For example, if a math problem is too difficult, the difficulty level can be adjusted. The user works with the AI ​​after-school assistant to manage the children's learning and play progress. This allows the user to focus on caring for the children, providing mental support, and mediating when problems arise.

[1397] In addition, automatically generated reports provided by the server can be checked to understand the child's situation in detail, and these reports can be used to report to parents and schools, making work more efficient.

[1398] Specific examples

[1399] For example, if a child is good at math and likes soccer, the server will generate a math problem set and soccer-related indoor games based on the child's profile data. A prompt based on this profile might be something like, "This child is 10 years old, good at math, and likes soccer. Please generate appropriate learning and play programs based on this profile."

[1400] The device receives these programs, and the AI ​​assistant asks the children math problems and suggests playing soccer when they get bored. The user (instructor) monitors this process and provides support to the children as needed.

[1401] As a result, the present invention reduces the burden on staff at after-school care facilities and provides high-quality care and education for children.

[1402] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1403] Step 1:

[1404] The server accesses the database of the after-school care facility and retrieves profile data for each child. This profile data includes the child's age, learning progress, interests, characteristics, etc. It receives profile data from the database as input and retrieves profile data as output. Specifically, it extracts the required information from the database using SQL queries.

[1405] Step 2:

[1406] The server converts and normalizes the acquired profile data into a unified format. In this process, for example, age is standardized into a "number" format and interests into a "comma-separated keywords" format. It receives raw profile data as input, processes the data, and then outputs normalized profile data. Specifically, it applies data conversion rules to unify the format.

[1407] Step 3:

[1408] The server generates the prompts required for the generative AI model based on the normalized profile data. It receives the normalized profile data as input and obtains the generated prompt as output. Specifically, it creates a prompt such as, "This child is 10 years old, good at math, and likes soccer. Please generate appropriate learning and play programs based on this profile."

[1409] Step 4:

[1410] The server sends prompts to the generative AI model and automatically generates learning and play programs. It receives the generated prompts as input and obtains the generated learning and play programs as output. Specifically, it sends API requests to the generative AI model and analyzes the response.

[1411] Step 5:

[1412] The server generates an AI school assistant based on the generated learning and play programs. This AI assistant is designed to support learning and play while interacting with children. It receives learning and play programs as input and generates an AI school assistant as output. Specific operations are performed using a voice synthesis engine and character generation tools.

[1413] Step 6:

[1414] The server combines the generated learning program, play program, and AI school assistant into a single data package. This data package is then sent to the terminal. The server receives the learning program, play program, and AI school assistant as input, and obtains a combined data package as output. Specifically, the server combines the data into a format such as JSON and sends it to the terminal using the HTTP protocol.

[1415] Step 7:

[1416] The device receives the data package sent from the server, analyzes it, and displays the learning program, play program, and AI school assistant. It receives the data package as input and displays the analyzed data as output. Specifically, it parses the received data using a JSON parser and displays it on the user interface.

[1417] Step 8:

[1418] The device then activates the AI ​​assistant and has it interact with the children to support their learning and play. It receives the AI ​​assistant as input and starts a dialogue as output. Specific operations include playing the AI ​​assistant's voice and displaying an animated user interface.

[1419] Step 9:

[1420] The device observes the child's reactions and behavior and sends the data to the server in real time. It receives the child's reaction data as input and obtains the transmitted data as output. Specifically, it analyzes the data obtained from sensors and cameras and sends it to the server via an HTTP request.

[1421] Step 10:

[1422] The device notifies the instructor when certain conditions are met. It receives student behavior data and event triggers as input and issues an alert as output. Specific actions include displaying a pop-up message or audio alert on the UI.

[1423] Step 11:

[1424] The user (instructor) checks the learning program and play program displayed on the terminal and fine-tunes the settings as necessary. The displayed program is received as input and the fine-tuned settings are reflected as output. Specific operations involve operating the setting panel on the UI and adjusting the parameters.

[1425] Step 12:

[1426] The user checks the automatically generated report provided by the server and understands the child's situation in detail. The automatically generated report is received as input, and the understood information is obtained as output. Specifically, the user browses the contents of the report and extracts the necessary information.

[1427] (Application example 1)

[1428] 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."

[1429] In today's after-school care facilities, staff are required to handle a wide range of tasks, particularly providing academic guidance and play support to individual children, as well as the administrative work of understanding each child's situation and reporting it to parents and schools, which places a heavy burden on staff. Similarly, in brick-and-mortar stores, it is difficult to provide personalized product recommendations and services to each customer, and measures to increase customer satisfaction are lacking. Furthermore, there is a lack of a way to centrally manage and effectively utilize this data.

[1430] 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.

[1431] In this invention, the server includes: means for acquiring child profile data; means for applying a generative AI model to generate learning programs and play programs based on the profile data; means for transmitting the generated learning programs and play programs to a terminal at the after-school facility; means for receiving child activity data from the terminal at the after-school facility and automatically generating reports for administrative work; means for collecting customer profile data from multiple physical stores and applying a generative AI model to generate product proposals and service details based on the profile data; means for transmitting the generated product proposals and service details to a terminal at the physical store; and means for receiving customer response data from the terminal at the physical store and automatically generating reports required for the physical store's operations. This not only reduces the burden on staff at the after-school facility and enables the provision of high-quality care and education for children, but also enables the physical store to quickly and efficiently provide personalized product proposals and services to each customer.

[1432] "Profile Data" means information about a child or customer, including their age, gender, interests, and past activity.

[1433] A "learning program" is a program that includes teaching materials and teaching methods that are automatically generated by a generative AI model to provide children with appropriate learning content and methods.

[1434] A "play program" is a program that includes play and recreational activities that is automatically generated by a generative AI model based on a child's interests and characteristics.

[1435] A "generative AI model" is an artificial intelligence model that automatically generates appropriate output (learning programs, play programs, product suggestions, service content, etc.) based on input data.

[1436] A "terminal" is a hardware device used to display and process data, specifically a computer or smart device installed in an after-school facility or brick-and-mortar store.

[1437] "Activity data" is a record of the specific actions and reactions that children and customers take while studying, playing, shopping, etc.

[1438] A "report" is a document that summarizes the activities, grades, and reactions of children or clients, and is used to streamline administrative and management tasks.

[1439] "Product suggestions" are recommendations of products suitable for a specific customer, generated by a generative AI model based on customer profile data.

[1440] "Service content" refers to details of the services to be provided to a specific customer, generated by the generative AI model based on the customer's profile data and response data.

[1441] The following system configuration is used as an embodiment of the present invention.

[1442] System Overview

[1443] This system consists of a server, terminals installed in physical stores and after-school care facilities, and users (instructors and store staff) who operate them.

[1444] Server Processing

[1445] 1. Profile Data Collection and Normalization:

[1446] The server collects profile data of children or customers from after-school care facilities and multiple physical stores, including age, gender, interests, and past activity history.

[1447] The collected data is normalized into a unified format, making it easier for generative AI models to process.

[1448] 2. Applying generative AI models:

[1449] Based on the normalized profile data, the server generates prompts, which in turn generate learning and play programs suited to each child, as well as product suggestions and service content suited to each customer.

[1450] The generative AI model receives this prompt, automatically generates an appropriate program or suggestion, and returns it to the server.

[1451] 3. Data submission and reporting:

[1452] The generated programs and proposals are sent to terminals at after-school facilities and physical stores.

[1453] The server also receives activity data sent from after-school care facilities and brick-and-mortar stores and automatically generates reports for administrative work, thereby reducing the workload of instructors and store staff.

[1454] Terminal handling

[1455] 1. Displaying received data:

[1456] The terminal receives the data package sent from the server and appropriately displays learning programs and play programs for the children and product suggestions and service contents for the customers.

[1457] 2. Activating and interacting with the AI ​​assistant:

[1458] Based on the received program and suggestions, the AI ​​assistant will be activated and will support the child in their learning and play through dialogue, as well as recommend the most suitable products to the customer and answer any questions.

[1459] 3. Real-time data transmission:

[1460] The device transmits real-time reaction data from children and customers to a server, allowing for further data analysis.

[1461] User Roles

[1462] 1. Check and correct the program:

[1463] Instructors and store staff can check the programs and suggestions displayed on the terminals and make adjustments as necessary, thereby providing optimal support for each child or customer.

[1464] 2. Collaboration with AI assistants:

[1465] Instructors and store staff will work with AI assistants to streamline their daily work, and the AI ​​assistants will automatically communicate and guide customers, minimizing human intervention.

[1466] 3. Review and use the report:

[1467] Automatically generated reports provided by the server are used to understand children's learning progress and customer purchasing behavior, simplifying reporting to parents and companies and improving operational efficiency.

[1468] Specific examples

[1469] For example, if a schoolchild is good at math and likes soccer, the server can generate a prompt like this based on their profile data:

[1470] "Age: 8 Gender: Male Interests: Math and sports"

[1471] Based on this prompt, the generative AI model automatically generates math puzzles and soccer-related indoor games. Meanwhile, as an example of application in a physical store, the model suggests the latest sportswear and new cosmetics to a 30-year-old female customer based on the prompt: "Age: 30, Gender: Female, Interests: Sports and Fashion."

[1472] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1473] Step 1:

[1474] The server collects customer or child profile data from brick-and-mortar stores and after-school care facilities. This data includes age, gender, past activity history, interests, etc. The input is the raw data sent from each facility, and the output is pre-processed data for normalization.

[1475] Step 2:

[1476] The server normalizes the collected profile data. The input is the preprocessed data obtained in step 1, and the output is data in a unified format. Data normalization converts the data into a form that is easy for the generative AI model to process.

[1477] Step 3:

[1478] The server generates prompts based on the normalized profile data. The input is the normalized data, and the output is prompts to be used as input to the generative AI model. The prompts follow a specific template to appropriately describe the data.

[1479] Step 4:

[1480] The server inputs prompts into the generative AI model to generate learning programs, play programs, product suggestions, and service content. The input is the prompt, and the output is the appropriate program or suggestion. The generative AI model generates a response based on the specified prompt.

[1481] Step 5:

[1482] The server compiles the generated programs and proposals and sends them to terminals at the after-school care facility or physical store. The input is each generated program and proposal, and the output is the transmitted data package. This data package contains the program contents and proposals.

[1483] Step 6:

[1484] The terminal receives the data package sent from the server and displays the program or suggestion content appropriately. The input is the data package from the server, and the output is the displayed content.

[1485] Step 7:

[1486] Based on the received information, the terminal activates an AI assistant and interacts with the child to support learning and play. It also provides optimal product recommendations and service information to customers. The input is the program and recommendations received from the server, and the output is a response to the child or customer.

[1487] Step 8:

[1488] The user (instructor or store staff) checks the content displayed on the terminal and fine-tunes the program and suggestions as necessary. The input is the data displayed on the terminal, and the output is the adjusted program and suggestions.

[1489] Step 9:

[1490] The terminal transmits the reaction and behavior data of the children or customers to the server in real time. The input is the real-time reaction data of the children or customers, and the output is the data transmitted to the server.

[1491] Step 10:

[1492] The server analyzes the received reaction data and automatically generates a new report. The input is real-time reaction data, and the output is an automatically generated report. This report helps instructors and store staff improve their work efficiency.

[1493] The above is a detailed explanation of the application process, broken down into specific steps, that will lead to the creation of an effective support system that utilizes generative AI models and prompts.

[1494] 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.

[1495] The present invention relates to an after-school support system that generates learning and play programs based on children's profile data and further combines an emotion engine to analyze and recognize children's emotions, thereby providing more detailed support. This system utilizes children's profile data and applies a generative AI model and emotion engine to support learning and play, with the aim of reducing the burden on staff at after-school facilities. A specific example of this system is described below.

[1496] Server-side processing

[1497] 1. Collecting and normalizing child profile data

[1498] The server retrieves each child's profile data from the after-school facility's database. This profile data includes the child's age, learning progress, interests, and characteristics. The retrieved profile data is converted into a unified format that is easy for the generative AI model and emotion engine to process.

[1499] 2. Applying generative AI models

[1500] The server generates prompts for the generative AI model based on the normalized profile data. These prompts serve as instructions for generating learning and play programs appropriate for each child. The generative AI model receives the prompts, automatically generates learning and play programs, and returns them to the server.

[1501] 3. Applying the Emotion Engine

[1502] The server uses an emotion engine to analyze the child's facial expressions and tone of voice, allowing it to understand the child's emotional state in real time and adaptively adjust learning and play programs.

[1503] 4. Creation of AI school assistants

[1504] The server generates an AI school assistant based on the generated learning and play programs, as well as emotional data generated by the emotion engine. This AI school assistant supports children in their studies and play while interacting with them, and also provides mental care based on the emotional data.

[1505] 5. Sending and Receiving Data

[1506] The server compiles the generated learning programs, play programs, and AI after-school assistants into a single data package and sends it to the after-school facility's terminal. It also receives the children's activity data sent from the after-school facility and automatically generates reports necessary for administrative work.

[1507] Terminal side processing

[1508] 1. Data Receipt and Analysis

[1509] The device receives data packages (learning programs, play programs, AI school assistants, and emotional data) sent from the server, analyzes the received data, and displays it appropriately.

[1510] 2. Starting and interacting with the AI ​​after-school assistant

[1511] The device then activates the AI ​​assistant, who interacts with the child to support learning and play. Based on the emotional data analyzed by the emotion engine, the device responds adaptively to the child's emotional state.

[1512] 3. Monitoring Emotional Data

[1513] The device monitors the child's facial expressions and tone of voice in real time and uses an emotion engine to transmit emotional data to the server, allowing the device to grasp the child's emotional state in real time.

[1514] 4. Status Notification

[1515] The device sets an alert according to the set conditions (e.g., if a specific emotion continues or if there is a sudden change in emotion) and notifies the instructor as necessary.

[1516] User (instructor) perspective

[1517] 1. Check and correct the program

[1518] The user (instructor) checks the learning program, play program, and emotional data displayed on the device and fine-tunes the settings as needed, allowing them to provide appropriate support to each child.

[1519] 2. Collaboration with AI assistants

[1520] Users can work with AI after-school assistants to manage children's learning and play progress, and can focus on providing mental care for children and mediating when problems arise based on emotional data.

[1521] 3. Checking and using the report

[1522] The user checks the automatically generated reports provided by the server to understand the child's situation, and reports to parents and schools based on these reports.

[1523] Specific examples

[1524] For example, if a child is good at math and likes soccer, but has recently been feeling stressed, the server will generate a math problem set and a soccer-related indoor game based on the child's profile and emotional data. Furthermore, if the emotion engine analyzes that the child is feeling stressed, it will use that information to suggest activities and conversations that will help them relax. The device receives these programs, and the AI ​​school assistant will ask the child math problems and suggest activities to help them relax if they feel stressed. The user (instructor) monitors this process and provides additional support as needed.

[1525] As a result, the present invention reduces the burden on staff at after-school care facilities and provides high-quality care and education for children.

[1526] The processing flow will be explained below.

[1527] Server-side processing

[1528] Step 1: Collecting child profile data

[1529] The server obtains each child's profile data (age, interests, learning progress, characteristics, etc.) from the after-school facility's database.

[1530] Step 2: Normalize the data

[1531] The server converts the acquired profile data into a unified format, making it easier for the generative AI model and emotion engine to process.

[1532] Step 3: Generate prompts

[1533] The server generates prompts to input into the generative AI model based on the normalized profile data.

[1534] Step 4: Generate Request

[1535] The server sends the generated prompts to the generative AI model, requesting it to generate learning and play programs.

[1536] Step 5: Receive the generated results

[1537] The server receives the learning programs and play programs returned from the generative AI model and stores them appropriately.

[1538] Step 6: Applying the Emotion Engine

[1539] The server uses an emotion engine to analyze the child's facial expressions and tone of voice, thereby obtaining emotion data in real time.

[1540] Step 7: Generate AI school assistants

[1541] The server generates an AI school assistant based on the generated learning and play programs, as well as emotional data generated by the emotion engine. This AI school assistant responds adaptively according to the emotional state of the child.

[1542] Step 8: Packaging the Data

[1543] The server compiles the generated learning program, play program, AI school assistant, and emotional data into a single package.

[1544] Step 9: Sending Data

[1545] The server transmits the packaged data to the terminal at the after-school facility.

[1546] Step 10: Receiving and processing activity data

[1547] The server receives the children's activity data sent from the after-school care facility and compiles it into statistical information and reports required for administrative work.

[1548] Step 11: Generate reports

[1549] The server checks the automatically generated report and provides it to the instructor.

[1550] Terminal side processing

[1551] Step 1: Receiving Data

[1552] The terminal receives the learning program, play program, AI school assistant, and emotion data package sent from the server.

[1553] Step 2: Analyze and display the data

[1554] The device analyzes the received data and displays information appropriate for each child in an appropriate format.

[1555] Step 3: Launching the AI ​​School Assistant

[1556] The device then runs the received AI school assistant program and interacts with the children using the specified appearance and voice.

[1557] Step 4: Dialogue monitoring

[1558] The device monitors the conversation between the AI ​​school assistant and the child, and transmits the child's reaction data to a server in real time.

[1559] Step 5: Monitoring sentiment data

[1560] The device uses an emotion engine to analyze the child's facial expressions and tone of voice in real time and transmits the emotional data to a server.

[1561] Step 6: Configure alerts

[1562] The device sets an alert according to the set conditions (e.g., when a specific emotion continues or when there is a sudden change in emotion).

[1563] Step 7: Send notification

[1564] The device immediately sends a notification to the instructor when the set alert conditions are met.

[1565] User (instructor) perspective

[1566] Step 1: Check and correct the program

[1567] The user (instructor) checks the learning program, play program, and emotional data displayed on the terminal and fine-tunes the settings as necessary.

[1568] Step 2: Collaborate with AI assistants

[1569] Users can work with AI after-school assistants to manage the progress of children's studies and play, and use emotional data to focus on mental care and mediation when problems arise.

[1570] Step 3: Review and use the report

[1571] The user checks the automatically generated reports provided by the server to understand the child's situation, and reports to parents and schools based on these reports.

[1572] Specific examples

[1573] For example, if a child is good at math and likes soccer, but has recently been feeling stressed, the server will generate a math problem set and a soccer-related indoor game based on the child's profile and emotional data. Furthermore, if the emotion engine analyzes that the child is feeling stressed, it will use that information to suggest activities and conversations that will help them relax. The device receives these programs, and the AI ​​school assistant will ask the child math problems and suggest activities to help them relax if they feel stressed. The user (instructor) monitors this process and provides additional support as needed.

[1574] Example 2

[1575] 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."

[1576] Modern after-school care facilities are required to provide attentive support to each child while reducing the burden on staff. However, conventional systems have difficulty responding to the diverse needs of children and are limited in the adaptive scientific support that takes into account their emotional state. Therefore, a system is needed that can provide appropriate learning and play programs based on each child's individual characteristics and emotional state, and provide feedback on the effectiveness of these programs in real time.

[1577] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring personal information of children, means for converting the personal information into a unified format, means for applying a generative AI model to generate learning programs and play programs based on the unified personal information, means for generating and sending prompt sentences to the generative AI model, means for using an emotion engine to analyze the children's facial expressions and tone of voice and determine their emotional state, means for integrating the generated learning programs, play programs, and emotion data to generate an AI after-school assistant, means for transmitting the generated learning programs, play programs, and AI after-school assistant to a terminal at the after-school facility, and means for receiving children's activity data from the terminal at the after-school facility and automatically generating reports for administrative work. This makes it possible to provide learning and play programs that take into account the individual characteristics and emotional state of children and to adaptively adjust them in real time.

[1578] "Personal information of children" refers to data that represents individual characteristics of children, such as their age, learning progress, interests, and characteristics.

[1579] "Uniform format" means that data is converted into a consistent format that facilitates subsequent processing.

[1580] A "generative AI model" is an artificial intelligence model that automatically generates learning and play programs based on input prompts.

[1581] A "prompt" is a sentence used to instruct a generative AI model to produce a specific output.

[1582] The "emotion engine" is a system that analyzes a child's facial expressions and tone of voice to determine their emotional state.

[1583] The "AI School Assistant" is an artificial intelligence agent that supports children based on generated learning programs, play programs, and emotional data.

[1584] "After-school facility terminals" refer to devices such as computers and tablets used within the after-school facility.

[1585] "Activity data" is data collected during children's learning and play, including the progress and results of their activities.

[1586] "Reports for administrative work" are automatically generated business reports based on children's activity data, and are used to reduce the burden on staff.

[1587] This invention relates to an after-school support system that generates learning and play programs based on children's profile data and further analyzes and recognizes children's emotions by combining it with an emotion engine to provide more detailed support. This system aims to understand each child's individual characteristics and emotional state in real time, support their learning and play, and reduce the burden on staff at after-school facilities.

[1588] Server-side explanation

[1589] The server retrieves personal information about each child from the after-school care facility's database. This information includes the child's age, learning progress, interests, and characteristics. The retrieved data is converted into a unified format. By organizing it into a data frame using Python's Pandas library, the individual data is organized into a consistent, processable format.

[1590] Next, we generate a prompt to send to the generative AI model. Specifically, we generate a prompt in text format like this:

[1591] "Profile data: Age 10, Interests: Mathematics, Traits: High concentration. Please generate suitable learning and play programs."

[1592] The generated prompts are sent to a generative AI model (e.g., GPT-3), which then uses natural language processing technology to automatically generate learning and play programs for the child.

[1593] Furthermore, the server uses an emotion engine to analyze the child's facial expressions and tone of voice. The emotion analysis results indicate the child's real-time emotional state and are adaptively reflected in the learning and play programs. This analysis utilizes, for example, an emotion analysis service provided through an API.

[1594] Finally, the server integrates the generated learning and play programs with the emotional data generated from them to generate an AI school assistant. This AI school assistant provides support through dialogue with the children and also provides mental care based on the emotional data.

[1595] Terminal side explanation

[1596] The terminal receives the data package (learning program, play program, AI school assistant, emotional data) sent from the server, analyzes it, and displays it appropriately.

[1597] The device launches the AI ​​assistant and begins a dialogue with the child. The assistant presents learning and play programs to the child, while adaptively responding to the child's emotional state based on the analysis results of the emotion engine. Specifically, a dialogue system built using Python generates flexible responses based on the child's responses and emotional state.

[1598] The device also uses a camera and microphone to capture the child's facial expressions and tone of voice in real time, which are then sent to an emotion engine for analysis. The analysis results are then sent to a server for further adaptive responses.

[1599] Furthermore, the device will issue alerts in response to certain conditions (such as sustained stress levels or sudden emotional changes) and notify instructors as needed, enabling prompt response to problems and providing consistent support to children.

[1600] User (instructor) explanation

[1601] The user checks the learning and play programs and emotional data displayed on the device and makes fine adjustments as necessary. The system works in cooperation with AI after-school assistants to manage the children's progress in learning and play. The emotional data is also used to provide mental care for the children and respond to any problems that arise.

[1602] Users can also check automatically generated reports provided by the server to understand their child's progress, which can then be sent to parents and schools to provide consistent support and feedback to the child.

[1603] Specific examples

[1604] For example, consider a child who excels at math and loves soccer, but has recently been feeling stressed. In this case, the server generates a math workbook and a soccer-related indoor game based on the child's profile and emotional data. Furthermore, if the emotion engine analyzes that the child is feeling stressed, it will use that information to suggest activities and conversations that will help them relax.

[1605] The device receives these programs, and the AI ​​assistant asks the children math problems and suggests activities to relax them if they feel stressed. The user (instructor) monitors this process and provides additional support as needed.

[1606] As a result, the present invention reduces the burden on staff at after-school care facilities and enables high-quality care and education for children.

[1607] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1608] Step 1:

[1609] The server retrieves personal information about children from the after-school facility's database. The input data includes data such as the child's age, learning progress, interests, and characteristics, which are extracted from the after-school facility's database. This data is extracted using an SQL query to obtain the data. The output data is raw personal information data.

[1610] Step 2:

[1611] The server converts the acquired personal information into a unified format. The raw personal information data acquired in step 1 is used as input. Specifically, it uses the Python Pandas library to organize the data into a data frame. The output is the personal information data converted into a unified format.

[1612] Step 3:

[1613] The server generates a prompt sentence based on the unified personal information. The input is the unified personal information data obtained in step 2. As a specific operation, the prompt sentence is generated using Python's text manipulation functions. An example of a prompt sentence is generated as follows: "Profile data: age 10, interest: mathematics, characteristic: high concentration. Please generate suitable learning and play programs." The output is the generated prompt sentence.

[1614] Step 4:

[1615] The server sends the prompt sentence to the generative AI model to generate a learning program and a play program. The input is the prompt sentence generated in step 3. This is sent to the generative AI model (e.g., GPT-3) and the generated learning program and play program are received. The output is the generated learning program and play program.

[1616] Step 5:

[1617] The server uses an emotion engine to analyze the child's facial expression and tone of voice to determine their emotional state. The input is the child's facial expression image and voice data. Specifically, the server sends an emotion analysis request to the API and receives the analysis results. The output is the analyzed emotion data.

[1618] Step 6:

[1619] The server integrates the generated learning program, play program, and emotion data to generate an AI school assistant. The inputs are the learning program and play program generated in step 4 and the emotion data from step 5. A dialogue system is built using Python libraries (e.g., NLTK and spaCy) to prepare the AI ​​school assistant. The output is the generated AI school assistant.

[1620] Step 7:

[1621] The server sends the generated learning program, play program, and AI school assistant to the terminal at the after-school facility. The input is the learning program, play program, and AI school assistant obtained in step 6. Specifically, the server sends data packages using a network protocol (e.g., HTTP or WebSocket). The output is the data package sent to the terminal.

[1622] Step 8:

[1623] The terminal receives the data package sent from the server, parses it, and displays it appropriately. The input is the data package sent from the server. Specific operations include parsing the JSON data in Python and using a GUI to display it appropriately. The output is the displayed learning program, play program, and AI school assistant.

[1624] Step 9:

[1625] The terminal starts the AI ​​assistant and begins interacting with the child. The input is the AI ​​assistant received and displayed in step 8. Specifically, the AI ​​assistant presents learning and play programs to the child and provides support through interaction. The output is the result of the interaction with the child.

[1626] Step 10:

[1627] The device monitors the child's facial expressions and tone of voice in real time and sends the emotional data to the server using an emotion engine. The input is the child's facial expression images and voice data. Specific operations include collecting data using a camera and microphone and sending it to the emotion engine. The output is the analyzed emotional data.

[1628] Step 11:

[1629] The device sets alerts according to specific conditions and notifies the instructor as necessary. The input is the emotion data analyzed in step 10. The specific operation is to monitor the alert conditions and notify the instructor via email or SMS when the conditions are met. The output is the notification to the instructor.

[1630] Step 12:

[1631] The user checks the learning program, play program, and emotional data displayed on the device and fine-tunes the settings as needed. The input is the information displayed on the device. Specific actions include changing the settings in the GUI and supporting the child in cooperation with the AI ​​after-school assistant. The output is the adjusted learning program and play program.

[1632] Step 13:

[1633] The user manages the child's progress in learning and play, and provides mental care and responds to problems based on emotional data. The input is the child's activity data and emotional data. Specific actions include checking the activity record and providing support as needed. The output is the result of managing the child's progress.

[1634] Step 14:

[1635] The user checks the automatically generated report provided by the server and understands the child's situation. The input is the report provided by the server. The specific operation is to check the report and report it to the parents or school. The output is the report result.

[1636] As a result, the present invention reduces the burden on staff at after-school care facilities and enables high-quality care and education for children.

[1637] (Application example 2)

[1638] 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."

[1639] The present invention aims to improve the effectiveness of children's education and reduce the burden on after-school care facility staff by creating optimal learning and play programs based on each child's profile data and providing adaptive support through real-time analysis of the child's emotional state in a system that supports children's learning and play. Furthermore, the present invention aims to solve the problem of improving individual user experiences by applying emotion analysis to meal plans and menu suggestions.

[1640] 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.

[1641] In this invention, the server includes means for acquiring profile data of children, means for applying a generative AI model to generate learning programs and play programs based on the profile data, means for transmitting the generated learning programs and play programs to a terminal at the after-school facility, means for receiving activity data of children from the terminal at the after-school facility and automatically generating reports for administrative work, means including an emotion engine for analyzing a user's facial expressions and tone of voice, and means for adaptively suggesting menus based on the user's emotional state analyzed by the emotion engine. This enables detailed educational support and mental care for each child, and further enables the system to suggest meal plans and menus that are optimal for each individual user's emotional state on that day.

[1642] "Profile data" refers to individual information about an individual user (or child), such as age, preferences, past behavioral history, learning progress, and characteristics.

[1643] A "generative AI model" refers to an artificial intelligence model that automatically generates adaptive programs and information based on prompts from input data.

[1644] An "emotion engine" refers to a technology that analyzes a user's emotional state, such as facial expressions and tone of voice, in real time and provides the analysis results.

[1645] A "learning program" refers to educational content and assignments that are individually created to suit each child's learning ability and progress.

[1646] "Play programs" refer to games and activities that are individually created based on a child's interests and preferences.

[1647] "Means" refers to an apparatus, method, or system for performing a particular function.

[1648] "Menu Suggestion" refers to automatically recommending meal plans that best suit a user's current mood and preferences based on their profile data and emotional state.

[1649] "User" refers to individuals who use the system, particularly in the present invention, children and users of food delivery services.

[1650] "Terminal" refers to the device that displays data received from the server and interacts with the user, such as a smartphone or computer.

[1651] "Activity data" refers to data related to the user's actions and reactions when using the system.

[1652] "Server" refers to the central system that receives and sends data from multiple users and processes the data using generative AI models and emotion engines.

[1653] This system generates learning and play programs based on a child's profile data, and provides adaptive support by analyzing and recognizing the child's emotional state using an emotion engine. Examples of applications include a food delivery application that suggests optimal meal plans and menus for individual users.

[1654] Server-side processing

[1655] 1. Profile data collection and normalization

[1656] The server first acquires the profile data of the child or user, including age, preferences, past behavioral history, learning progress, characteristics, etc. The acquired data is then converted into a unified format that can be easily processed by the generative AI model and emotion engine.

[1657] 2. Applying generative AI models

[1658] The server uses the normalized profile data to generate prompts for the generative AI model, which in turn guides the creation of learning, play, or meal plans tailored to each user.

[1659] Example: Prompt statement

[1660] prompt:

[1661] User's age: 25

[1662] Favorite food: Italian

[1663] Allergens: nuts

[1664] Suggested menu: Pizza, salad, herbal tea

[1665] This user's emotion today is "Stressed" but they would like to relax a bit. Please suggest the best meal plan for them.

[1666] 3. Applying the Emotion Engine

[1667] The server uses an emotion engine to analyze the user's facial expressions and tone of voice to understand the user's emotional state in real time, allowing it to make adaptive menu suggestions and adjust learning programs.

[1668] 4. Data transmission and reception

[1669] The system sends a data package containing the generated learning program, play program, meal plan, and emotional data to the user's device, receives data on the child's activities and the user's reaction data, and automatically generates reports required for administrative work.

[1670] Terminal side processing

[1671] 1. Data Receipt and Analysis

[1672] The terminal receives the data packages sent by the server, displays them appropriately, and allows the user to access the plans and programs offered through a user interface.

[1673] 2. Launching and interacting with the AI ​​advisor

[1674] The device then activates the AI ​​advisor (school assistant or food advisor) that receives the information and provides support through dialogue with the user. Based on the emotional data analyzed by the emotion engine, the device responds adaptively.

[1675] 3. Monitoring Emotional Data

[1676] The device monitors the user's facial expressions and tone of voice in real time and uses an emotion engine to transmit emotional data to the server.

[1677] Hardware and software used

[1678] The server uses a high-performance computer (cloud-based or on-premise), and the software incorporates OpenAI's GPT-4 as a generative AI model, and the emotion engine incorporates Microsoft Azure's facial recognition API and Google Cloud's voice analysis API.

[1679] The user device will be a smartphone or computer equipped with a camera and microphone, and the user interface will be a custom food delivery application or educational support application.

[1680] Specific examples

[1681] For example, if a particular user is feeling stressed, the system uses the smartphone's camera and microphone to analyze this emotional data. Since the profile data states "Favorite food: Italian, Allergy: Nuts," the generative AI model suggests a meal plan that includes pizza and salad. An additional suggestion is herbal tea, which is said to have a relaxing effect. The user can then select from the suggested menu and place an order via a food delivery service.

[1682] As described above, the present invention is a system that provides detailed support to individual children and users, improving their quality of life.

[1683] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1684] Step 1:

[1685] The server obtains user profile data, specifically, age, preferences, allergy information, past order history, etc., from a database. The input is the profile data in the database, and the output is the profile data in a unified format that is ready for analysis and generation.

[1686] Step 2:

[1687] The server normalizes the collected profile data. This is a process that standardizes the data format and prepares it in a form that can be efficiently analyzed by generative AI models and emotion engines. The input is raw profile data, and the output is normalized profile data.

[1688] Step 3:

[1689] The server generates prompts for the generative AI model based on the normalized profile data. In a specific example, the prompt text includes information such as age, preferences, past behavioral history, and emotional state. The input is the profile data, and the output is the prompt text to be passed to the generative AI model.

[1690] Step 4:

[1691] The server uses a generative AI model (e.g., OpenAI's GPT-4) to generate an adaptive learning program, play program, or meal plan based on the prompt. The input is the prompt, and the output is the generated program or plan.

[1692] Step 5:

[1693] The server compiles the generated learning programs, play programs, and meal plans into a data package and sends it to the user terminal. The input is the generated program or plan, and the output is the data package sent to the user terminal.

[1694] Step 6:

[1695] The terminal receives the data package sent from the server, analyzes it, and displays it appropriately, allowing the user to access the programs and plans provided. The input is the data package sent from the server, and the output is the program or plan displayed on the user interface.

[1696] Step 7:

[1697] The device then activates the AI ​​advisor (school assistant or food advisor) that received the data and has it interact with the user. The AI ​​advisor responds adaptively based on the emotional data. The input is the data package sent from the server and emotional data collected in real time, and the output is the result of the interaction with the user.

[1698] Step 8:

[1699] The device monitors the user's facial expressions and tone of voice in real time, analyzes the emotional data using an emotion engine (such as Microsoft Azure's facial recognition API or Google Cloud's voice analysis API), and sends the analyzed emotional data to the server. The input is the user's facial expressions and voice data, and the output is the analyzed emotional data.

[1700] Step 9:

[1701] The server adjusts learning programs, play programs, and meal plans in real time based on the received emotional data, and retransmits them to the device as a new data package. The input is the analyzed emotional data, and the output is the adjusted programs and plans.

[1702] 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 acquir...

Claims

1. a means of obtaining profile data of the child; means for applying a generative AI model to generate learning and play programs based on said profile data; means for transmitting the generated learning program and play program to a terminal in the after-school facility; a means for receiving activity data of children from the terminals of the after-school care facility and automatically generating a report for administrative work; A system including:

2. The system of claim 1 further comprising means for normalizing said profile data.

3. 10. The system of claim 1, further comprising means for inputting prompts to the generative AI model to generate learning and play programs.

Images