System

Abstract

A system is provided.SOLUTION: This system includes a means for collecting data on the contents of meals, sleeping hours and activities of a child acquired in a nursery facility, a means for analyzing the collected data and evaluating the characteristics of each child, a means for generating a learning menu and an exercise menu suitable for each child based on the evaluation result, a means for notifying a guardian of the generated menu, a means for receiving an inquiry about childcare from the guardian, a means for generating appropriate advice based on the collected data and the evaluation result in response to the received inquiry, and a means for notifying the guardian of the generated advice.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] For parents, raising children is an unknown field, there are many things they don't know, and sometimes there is no one to turn to for advice. In particular, for parents who leave their children in childcare facilities, there are no specific learning programs or menus to help them utilize their daily life records (meals, exercise, sleep time, etc.) at home. For this reason, there is a need for a means to provide childcare support tailored to each individual child. There is also a need for a system that can efficiently provide appropriate advice when parents seek advice on childcare methods. [Means for solving the problem]

[0005] This invention provides a system that collects data on children's diet, sleep duration, and activity details obtained at childcare facilities, analyzes the collected data, and evaluates the characteristics of each child. Based on the evaluation results, it generates learning and exercise menus appropriate for each child and notifies parents of the generated menus. Furthermore, it accepts inquiries about childcare from parents, generates appropriate advice based on the collected data and evaluation results in response to the inquiries, and notifies parents of the generated advice, thereby enabling parents to support childcare without being overwhelmed. This system allows parents to specifically learn the optimal childcare methods for each child and receive appropriate advice when needed.

[0006] A "childcare facility" is a facility such as a nursery school or kindergarten that takes care of children for a certain period of time and provides them with childcare and education.

[0007] "Dietary content" refers to the types, amounts, and timing of food and drink that children consume at childcare facilities and at home.

[0008] "Sleep time" refers to the amount of time a child sleeps during the day, including naps and nighttime sleep.

[0009] "Activities" refers to specific actions and events such as playing, learning, and exercise that children engage in at childcare facilities or at home.

[0010] "Data collection" refers to the process of collecting information from childcare facilities and other organizations about children's diet, sleep, and activities.

[0011] "Data analysis" refers to the process of analyzing collected data using statistical methods and algorithms to evaluate children's characteristics and trends.

[0012] A "learning menu" is a list of educational activities and tasks designed according to a child's developmental stage and interests.

[0013] An "exercise menu" is a list of exercises and activities aimed at promoting a child's physical development and health.

[0014] "Notification" refers to the act of contacting parents with the generated learning menu, exercise menu, or advice, and includes email and app push notifications.

[0015] An "inquiry" is a question or child-rearing consultation that a parent or guardian sends to the system.

[0016] "Generative AI" refers to artificial intelligence that generates advice and suggestions in response to parental inquiries based on collected data and analysis results. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] The present invention provides a system that supports parents in raising their children by providing optimal learning and exercise programs for each child based on data acquired from childcare facilities. Specific embodiments of the system are described below.

[0039] System Overview

[0040] This system works in cooperation with three parties: a server, a terminal, and a user. The server is responsible for collecting, storing, and analyzing data, and generating menus and notifications, while the terminal provides an interface with childcare facilities and parents. Users (mainly parents) receive information necessary for childcare and make inquiries through the system.

[0041] Data collection and storage

[0042] The server periodically receives data from the childcare facility, such as mealtimes, sleep duration, and activity status, via an API. The collected data is categorized for each child and stored in a database. The stored data is updated daily and encrypted for security purposes.

[0043] Data analysis and characterization

[0044] The server analyzes the data stored in the database and evaluates each child's characteristics, such as sleep patterns, nutritional balance, and daily activity levels, to understand the child's health and development.

[0045] Menu generation

[0046] Based on the analysis results, the server generates learning and exercise menus tailored to each child. For example, it may design an exercise menu that focuses on children with low activity levels, and recommend an arts and crafts learning menu for children who like creative activities. The generated menus are stored in a database and are ready to be provided to parents.

[0047] Parental notification

[0048] The server notifies parents of the generated learning and exercise menus. Specifically, notifications are sent via a dedicated application or email. The notifications include details of the menus and information on how to implement them.

[0049] Responding to parental inquiries

[0050] The device provides an interface for parents to make inquiries about childcare, and parents can enter their questions using an application or a web form.

[0051] The server analyzes the received inquiries and uses generative AI to generate appropriate advice based on past data and evaluation results. The advice is then sent to parents via email or in-app notifications.

[0052] Specific examples

[0053] For example, if a child has trouble falling asleep and can only sleep for a certain amount of time, the server will analyze the data and detect irregular sleep patterns. It will then provide parents with suggestions for adjusting nap times and revising their nighttime routine. If it determines that a lack of exercise is the cause, it will suggest easy indoor exercises.

[0054] This system allows parents to receive accurate advice without being overwhelmed by daily childcare, and effectively supports their children's health and development.

[0055] The processing flow will be explained below.

[0056] Step 1: Collect and store data

[0057] The server periodically collects data such as meal contents, sleep time, and activity details from the childcare facility via an API.

[0058] Specific operation: Sends an API request to retrieve the latest data from the childcare facility's system and stores the received data in a temporary buffer.

[0059] Step 2: Classify and encrypt data

[0060] The server categorizes the data it collects by child and encrypts it before storing it in a database.

[0061] Specific operation: The data is sorted by child ID, an encryption algorithm is applied, and the data is inserted into the database.

[0062] Step 3: Preprocessing the data

[0063] The server performs pre-processing to convert the stored data into a format that is easy to analyze.

[0064] Specific operations: Impute missing values, normalize data, check for and correct data inconsistencies and errors.

[0065] Step 4: Data analysis and characterization

[0066] The server evaluates the child's characteristics based on the pre-processed data.

[0067] What it does: Uses statistical methods and machine learning algorithms to assess sleep patterns, nutritional balance, and activity levels.

[0068] Step 5: Generate the menu

[0069] Based on the analysis results, the server generates a learning menu and an exercise menu suitable for each child.

[0070] What it does: Apply rule-based algorithms and machine learning models to convert the generated menu into a format appropriate for each child.

[0071] Step 6: Prepare the menu for notifications

[0072] The server prepares to notify the parent of the generated menu.

[0073] What it does: Gets parent contact information and formats menu information into rich text and HTML.

[0074] Step 7: Menu Notifications

[0075] The server notifies the parent of the menu when it is ready.

[0076] Specific operations: Connect to the mail server or push notification server, send the prepared message, and save the sending log.

[0077] Step 8: Receiving parental inquiries

[0078] The device provides an interface where parents can input questions about childcare.

[0079] Specific operation: Prepare an inquiry form in a mobile or web app and set up an API endpoint to send user input to the server.

[0080] Step 9: Processing the inquiry and generating an answer

[0081] The server receives questions from parents, and the generative AI creates advice based on the collected data and evaluation results.

[0082] What it does: Searches for relevant historical data from a database and generates an answer using a provided natural language processing (NLP) model.

[0083] Step 10: Notification of response

[0084] The server notifies the parent of the generated advice.

[0085] Specific behavior: Sends responses to parents via email or in-app notification, and stores notification sending logs in a database.

[0086] Example 1

[0087] 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."

[0088] Effectively understanding the health and developmental status of children attending childcare facilities and providing childcare support based on that information is an important issue for parents. However, currently, data collection is often done manually, making it difficult to analyze the data and provide appropriate advice. In addition, parents are often not notified of information or their inquiries are not responded to promptly and appropriately. This can cause parents to feel anxious and worried about their children's health management and childcare.

[0089] 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.

[0090] In this invention, the server includes means for collecting data on children's dietary habits, sleep duration, and activity details obtained at the childcare facility, means for analyzing the collected data and evaluating the characteristics of each child, means for generating a learning menu and an exercise menu appropriate for each child based on the evaluation results, means for notifying parents of the generated menus, means for accepting inquiries about childcare from parents, means for generating appropriate advice in response to the accepted inquiries based on the collected data and the evaluation results, means for notifying parents of the generated advice, means for encrypting the collected data for security purposes, means for storing data classified for each child in a database, means for performing time series analysis to analyze the data, means for generating the generated exercise menu and learning menu using a machine learning algorithm, means for generating appropriate advice using a natural language processing model, and means for notifying parents via a dedicated application or email. This allows parents to accurately understand their children's health and developmental status and receive prompt and appropriate childcare support.

[0091] The "data collection means" is a means for collecting data on children's diet, sleep time, and activity details obtained at the childcare facility.

[0092] "Data analysis tools" are tools for analyzing collected data and evaluating the characteristics of individual children.

[0093] The "menu generating means" is a means for generating a learning menu and an exercise menu suitable for each child based on the evaluation results.

[0094] The "menu notification means" is a means for notifying the guardian of the generated learning menu and exercise menu.

[0095] The "inquiry reception means" is a means for receiving inquiries about childcare from parents.

[0096] The "advice generation means" is a means for generating appropriate advice in response to a received inquiry based on the collected data and evaluation results.

[0097] The "advice notification means" is a means for notifying the guardian of the generated advice.

[0098] "Encryption means" means means for encrypting collected data for security purposes.

[0099] The "database storage means" is a means for storing data classified for each individual child in a database.

[0100] The "time series analysis means" is a means for performing time series analysis to analyze data.

[0101] A "machine learning algorithm" is a method for generating exercise menus and learning menus based on machine learning.

[0102] The "natural language processing model" is a model for generating advice in natural language in response to inquiries from parents.

[0103] "Notification means" refers to a means for notifying parents of information via a dedicated application or email.

[0104] This invention is a system that supports parents in raising their children by providing optimal learning and exercise menus for each child based on data obtained from childcare facilities. This system operates in cooperation with three parties: a server, a terminal, and a user.

[0105] Data collection and storage

[0106] The server periodically receives data such as meal contents, sleep time, and activity details sent from the childcare facility via a RESTful API. A common framework (e.g., Spring Boot) is used for this API communication. The obtained data is categorized for each child and stored in a database (e.g., MySQL). The stored data is updated daily and is encrypted with AES-256 for security.

[0107] Data analysis and characterization

[0108] The server analyzes the data stored in the database using Python and Pandas. It performs time-series analysis on sleep data and evaluates nutritional balance on nutritional data. This makes it possible to understand the health and developmental status of each child. The analysis results are stored in the database.

[0109] Menu generation

[0110] Based on the analysis results, the server generates learning and exercise menus suited to each individual child. This process utilizes machine learning models using TensorFlow. For example, it generates a "simple exercise menu" for a child with a low level of physical activity, and recommends "painting and craft activities" for a child who enjoys creative activities.

[0111] Parental notification

[0112] The server notifies parents of the generated learning and exercise menus. Notification methods include email (e.g., SendGrid API) and a dedicated app (e.g., built with React Native). The notification includes details of the menu and information on how to implement it.

[0113] Responding to parental inquiries

[0114] The device provides an interface for accepting inquiries about childcare from parents. Parents can enter questions through a web form or an application (e.g., an app using the Flask framework). For example, a parent can send an inquiry about "the causes and solutions for nighttime crying."

[0115] Advice Generation and Notifications

[0116] The server analyzes the received inquiry and generates appropriate advice using a generative AI model (e.g., GPT-4) based on past data and evaluation results. The generated advice is sent to the parent via email or in-app notification. The following prompt sentences are used to generate the advice:

[0117] Example prompt sentence:

[0118] "Mr. A has trouble falling asleep and is sleeping less at night. Based on his recent sleep pattern data, please provide some advice on adjusting his nap time and reviewing his nighttime routine."

[0119] This system allows parents to receive accurate advice without being overwhelmed by daily childcare, and effectively supports their children's health and development.

[0120] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0121] Step 1:

[0122] The server periodically receives data from the childcare facility about the children's diet, sleep time, and activity via a RESTful API. A common framework (e.g., Spring Boot) is used for this API communication, and the received data is sent to the server in JSON format. The input is data from the childcare facility, and the output is the raw data received by the server. This data is categorized for each child and proceeds to the next step.

[0123] Step 2:

[0124] The server stores the retrieved data in a MySQL database. Before storing the data, each data is classified by child and encrypted using the AES-256 algorithm for security. The input is the raw data and each child's ID, and the output is the encrypted data stored in the database. This storage process is performed using an INSERT query.

[0125] Step 3:

[0126] The server analyzes the data stored in the database using Python and Pandas. For example, it performs time-series analysis on sleep data and calculates activity levels and nutritional balance. The input is data for each child extracted from the database, and the output is the analysis results. The analysis results are then stored back in the database.

[0127] Step 4:

[0128] The server uses a machine learning model (a model using TensorFlow) to evaluate the characteristics of each child based on the analysis results. It performs tasks such as classifying physical activity levels and evaluating learning characteristics. The input is the analysis results, and the output is the characteristic evaluation results. The characteristic evaluation results are also stored in a database.

[0129] Step 5:

[0130] The server generates learning and exercise menus appropriate for each child based on the results of the characteristic assessment. Generative AI models such as GPT-4 are used to create specific menus. For example, gymnastics menus are recommended for children with low physical activity levels, and craft activities are recommended for children who prefer creative activities. The input is the characteristic assessment results, and the output is the generated menu. The generated menu is stored in a database.

[0131] Step 6:

[0132] The server notifies parents of the generated learning and exercise menus. Notification methods include email (using SendGrid's API) and a dedicated app (built with React Native). The input is the generated menu and parent contact information, and the output is the notification sent to the parent.

[0133] Step 7:

[0134] The device provides an interface for accepting inquiries about childcare from parents. Parents can enter questions through a web form or an application (Flask framework). For example, a user can send an inquiry about the cause of nighttime crying and what to do about it from the application. The input is the inquiry from the parent, and the output is the query data sent to the server.

[0135] Step 8:

[0136] The server analyzes the received query using a generative AI model (GPT-4) and generates appropriate advice. The input is the query content, past data in the database, and the characteristic evaluation results, and the output is the generated advice. This advice is generated based on the following prompt:

[0137] Example prompt sentence:

[0138] "Mr. A has trouble falling asleep and is sleeping less at night. Based on his recent sleep pattern data, please provide some advice on adjusting his nap time and reviewing his nighttime routine."

[0139] Step 9:

[0140] The server sends the generated advice to the parent via email or in-app notification. The input is the generated advice and the parent's contact information, and the output is the notification sent to the parent. This allows parents to receive accurate advice.

[0141] (Application example 1)

[0142] 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."

[0143] The goal is to adequately resolve the concerns and questions parents have about childcare. Furthermore, to support the efficient management of children's health and development, it is important to provide the most appropriate learning and exercise programs for each child based on data collected from childcare facilities. Furthermore, there is a need for a system that allows parents to easily check this information and receive appropriate advice in response to inquiries.

[0144] 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.

[0145] In this invention, the server includes means for collecting data on children's dietary habits, sleep duration, and activity details obtained at the childcare facility, means for analyzing the collected data and evaluating the characteristics of each child, means for generating learning and exercise menus appropriate for each child based on the evaluation results, means for notifying parents of the generated menus, means for accepting inquiries about childcare from parents, means for generating appropriate advice in response to the accepted inquiries based on the collected data and evaluation results, means for notifying parents of the generated advice, means for parents to check and manage the generated menus and advice via a smartphone application, means for generating individual advice using a generative AI model in response to inquiries from parents, and means for generating the generated advice using a natural language processing model via prompt sentences. This allows parents to easily obtain all data and advice related to childcare and take appropriate action.

[0146] A "childcare facility" is a facility that temporarily takes care of infants and children and provides them with daily care, including meals, sleep, and play.

[0147] "Dietary content" refers to information about the foods a child ingests at the childcare facility, including their type, quantity, and nutrients.

[0148] "Sleep hours" is the total amount of time a child sleeps in the childcare facility.

[0149] "Activity details" refers to data on specific activities such as exercise, learning, and play that children engage in at the childcare facility.

[0150] "Means for collecting data" refers to a method or device for obtaining data from the childcare facility regarding dietary habits, sleep duration, and activity.

[0151] A "means for analyzing data" is a method or device that uses collected data to assess a child's health status or characteristics.

[0152] A "trait assessment tool" is a method or device for assessing the developmental or health status of an individual child based on collected data.

[0153] A "learning menu" is a combination of materials and activities designed to help children learn appropriately.

[0154] An "exercise menu" is a combination of exercises and games designed to get children moving and exercising appropriately.

[0155] "Means for notifying parents" refers to a method or device for notifying parents of the generated menu or advice.

[0156] "Means for accepting inquiries about childcare" refers to a method or device for accepting questions or inquiries from parents.

[0157] A "means for generating appropriate advice" is a method or apparatus for generating advice based on a query and using collected data and evaluation results.

[0158] "Via a smartphone application" means operating or viewing through an application running on a smartphone.

[0159] A "generative AI model" is a model that uses artificial intelligence technology to create learning menus and advice generated from data.

[0160] A "prompt sentence" is a sentence that specifically describes the question or instruction to be input into the generative AI model.

[0161] A "natural language processing model" is a set of techniques and algorithms that allow computers to understand, analyze, and generate human language.

[0162] This invention is a system that supports parents in raising their children by creating optimal learning and exercise menus for each child based on data acquired from childcare facilities. Specific embodiments of the system are described below.

[0163] System configuration

[0164] The system works in cooperation with three parties: a server, a device, and parents. The server is responsible for collecting, storing, and analyzing data, and generating menus and notifications, while the device provides an interface with childcare facilities and parents. Parents can receive information necessary for childcare and make inquiries through the system.

[0165] Data collection and storage

[0166] The server collects data sent from the childcare facility, such as meal contents, sleep time, and activity details. It uses Amazon Web Services (AWS) to periodically retrieve data via API using AWS Lambda. The collected data is stored in AWS RDS (a relational database service) and is encrypted for added security.

[0167] Data analysis and characterization

[0168] The server analyzes the data stored in the database and evaluates each child's characteristics. It uses Python, Numpy, and Pandas to analyze sleep patterns and check nutritional balance. It also uses TensorFlow to cluster children's health and developmental status using machine learning models.

[0169] Menu generation

[0170] Based on the analysis results, the server generates learning and exercise menus appropriate for each child, using TensorFlow's deep neural network (DNN) model, and stores the generated menus in Amazon RDS.

[0171] Parental notification

[0172] The server notifies parents of the generated learning and exercise menus. Push notifications are sent using AWS SNS (Simple Notification Service), and a smartphone application developed with React Native receives the notifications. The app then displays the menu details to parents.

[0173] Responding to parental inquiries

[0174] The server accepts inquiries about childcare from parents and responds. Parents input their questions through a smartphone application. The server uses a generative AI model (e.g., GPT-4) to generate appropriate advice based on past data and evaluation results. This advice is generated by a natural language processing model (e.g., GPT-4 API) through a prompt sentence and notified to the parent via AWS SNS.

[0175] Specific examples

[0176] For example, if a child has trouble falling asleep and can only sleep for a certain amount of time, the server will analyze the data and detect irregular sleep patterns. It will then provide parents with suggestions for adjusting nap times and revising their nighttime routine. If it determines that a lack of exercise is the cause, it will suggest easy indoor exercises.

[0177] Prompt Sentence Examples

[0178] Parent input: "My child has been having trouble falling asleep lately. Any advice?"

[0179] Use the following prompt: "What advice can you offer to a child who has been having trouble falling asleep recently?"

[0180] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0181] Step 1:

[0182] The server collects data from the childcare facility on children's dietary habits, sleep duration, and activity. This data is periodically sent to the server from the childcare facility's terminal via API. The input data is in JSON format and includes daily data for each child. The collected data is processed by AWS Lambda and stored in AWS RDS.

[0183] Step 2:

[0184] The server periodically analyzes the data stored in AWS RDS. It extracts data using Python scripts and preprocesses the data using Numpy and Pandas. For example, it performs data cleaning such as imputing missing values ​​and detecting outliers. The input data is the preprocessed daily data for each child, and the output data is data converted into a format suitable for analysis.

[0185] Step 3:

[0186] The server evaluates each child's characteristics based on the preprocessed data. It uses a machine learning model using TensorFlow to cluster sleep patterns and activity levels. The input data is the preprocessed data for each child, and the output data is the results of each child's characteristic evaluation. Specific operations for characteristic evaluation include running a clustering algorithm and calculating a score for each characteristic.

[0187] Step 4:

[0188] The server generates learning and exercise menus appropriate for each child based on the evaluation results. This is done using TensorFlow DNN. For example, it might design a focused exercise menu for a child with low activity levels, and recommend an arts and crafts learning menu for a child who enjoys creative activities. The input data is the characteristic evaluation results, and the output data is the learning and exercise menu appropriate for each child.

[0189] Step 5:

[0190] The server notifies parents of the generated learning and exercise menus. Specifically, it uses AWS SNS to send push notifications. The input data is the generated menu, and the output data is a notification sent to the parent's smartphone. The notification contains details about the menu and information on how to implement it.

[0191] Step 6:

[0192] Parents send inquiries about childcare to the server via a smartphone application. The input data is the question or consultation from the parent, and the output data is the inquiry data sent to the server. Specifically, the question is entered into the inquiry form within the app and sent.

[0193] Step 7:

[0194] The server receives inquiries from parents and generates appropriate advice using a generative AI model (GPT-4) based on previous data and evaluation results. It calls the GPT-4 API using a prompt sentence to generate appropriate advice. The input data is the parent's question and related child data, and the output data is the generated advice.

[0195] Step 8:

[0196] The server notifies the parent of the generated advice. The advice is sent to the parent's smartphone via AWS SNS. The input data is the generated advice, and the output data is the notification sent to the parent's smartphone. Specifically, the generated advice is displayed as an in-app notification.

[0197] 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.

[0198] This invention combines a system that provides optimal learning and exercise menus for each child based on data acquired from childcare facilities and supports parents in raising their children with an emotion engine. Specific embodiments of the system are described below.

[0199] System Overview

[0200] This system works in cooperation with four parties: a server, a device, a user, and an emotion engine. The server is responsible for collecting, storing, and analyzing data, and generating menus and notifications, while the device provides an interface with childcare facilities and parents. Users (mainly parents) receive information necessary for childcare through the system and make inquiries. The emotion engine recognizes emotions from the user's input and actions and reflects them in the advice it provides.

[0201] Data collection and storage

[0202] The server periodically receives data from the childcare facility via API, including meal contents, sleep time, and activity details. The data is categorized by child, encrypted, and stored in a database.

[0203] Data analysis and characterization

[0204] The server analyzes the stored data and evaluates each child's characteristics, such as sleep patterns, nutritional balance, and activity levels, using statistical methods and machine learning algorithms to understand the child's health and developmental status.

[0205] Menu generation

[0206] Based on the analysis results, the server generates a learning and exercise menu suited to each child. The generated menu, which is tailored to each child's individual needs, is stored in a database and later provided to parents.

[0207] Parental Notification and Emotion Recognition

[0208] The device provides an interface for notifying parents of the generated learning and exercise menus. Notifications are sent via a dedicated application or email. The emotion engine recognizes emotions from parents' inquiries and daily interactions and adjusts the content and tone of the advice accordingly.

[0209] Responding to parental inquiries and reflecting their feelings

[0210] The device provides an interface for parents to make inquiries about childcare, and parents can enter their questions using an application or a web form.

[0211] The server analyzes the received inquiry and uses generative AI to generate advice based on past data and evaluation results. The emotion engine identifies emotions from the parent's input and generates advice with an appropriate tone and content. The generated advice is sent to the parent via email or in-app notification.

[0212] Specific examples

[0213] For example, if a parent sounds tired and sends a message saying, "My child has been having trouble falling asleep at night lately," the server analyzes the data and considers specific measures to improve the child's sleep pattern based on the analysis. The emotion engine detects "fatigue" in the parent's message and adjusts the tone of the advice to be gentle and empathetic. As a result, advice such as "We understand your concerns about your child's nighttime sleepiness. We'll show you how to adjust nap times and how to relax before bed" is generated and sent to the parent.

[0214] This system allows parents to receive accurate advice without feeling overwhelmed by the daily tasks of childcare, and by receiving support that is sensitive to their emotions, they can feel even more secure in raising their children.

[0215] The processing flow will be explained below.

[0216] Step 1: Collect and store data

[0217] The server periodically collects data such as meal contents, sleep time, and activity details from the childcare facility via an API.

[0218] What it does: Sends an API request to receive the latest data from the childcare system, stores it in a temporary buffer, categorizes it by child, and encrypts it before inserting it into the database.

[0219] Step 2: Preprocessing the data

[0220] The server performs pre-processing to convert the stored data into a format that is easy to analyze.

[0221] Specific actions: Impute missing values, normalize data, check for and correct inconsistencies and errors.

[0222] Step 3: Data analysis and characterization

[0223] The server evaluates the child's characteristics based on the pre-processed data.

[0224] What it does: Uses statistical methods and machine learning algorithms to analyze sleep patterns, nutritional balance, and activity levels to assess a child's health and development.

[0225] Step 4: Generate the menu

[0226] Based on the analysis results, the server generates a learning menu and an exercise menu suitable for each child.

[0227] What it does: It applies rule-based algorithms and machine learning models to design optimal menus for each individual child and stores them in a database.

[0228] Step 5: Prepare the menu for notifications

[0229] The server prepares to notify the parent of the generated menu.

[0230] What it does: Gets parent contact information and formats menu information into rich text and HTML.

[0231] Step 6: Menu Notifications

[0232] The server notifies the parent of the menu when it is ready.

[0233] Specific operations: Connect to the mail server or push notification server to send the message. Save the sending log for later tracking.

[0234] Step 7: Receiving parental inquiries

[0235] The device provides an interface where parents can input questions about childcare.

[0236] Specific operation: Prepare an inquiry form within the mobile app or web app and set up an API endpoint that sends user input to the server.

[0237] Step 8: Parsing the query

[0238] The server receives questions from parents and searches the database for relevant past data.

[0239] Specific operation: Analyzes the inquiry content and generates appropriate advice based on past data and evaluation results.

[0240] Step 9: Recognize emotions

[0241] The server uses an emotion engine to recognize emotions from the parent's inquiry.

[0242] What it does: Analyzes text data using a natural language processing (NLP) model to identify the parent's emotional state (e.g., fatigue, anxiety, joy).

[0243] Step 10: Adjusting Advice

[0244] The server adjusts the content and tone of advice based on the emotional state recognized by the emotion engine.

[0245] Specific behavior: Generate appropriate advice based on the emotional state, and use gentle and empathetic language.

[0246] Step 11: Advice Notification

[0247] The server notifies the parent of the generated advice.

[0248] Specific behavior: Sends advice to parents via email and in-app notifications, and stores the sending log in a database for future reference.

[0249] Example 2

[0250] 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."

[0251] In modern society, parents have limited time to devote to childcare and often rely on childcare facilities. As a result, they face challenges in obtaining sufficient information about their children's activities and health at childcare facilities, making it difficult for them to receive appropriate advice. Furthermore, uniform advice may not adequately reflect each child's individual characteristics, which can cause anxiety and stress for parents. Furthermore, a lack of consideration for parents' feelings can increase the burden of childcare.

[0252] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0253] In this invention, the server includes: means for collecting data on children's dietary habits, sleep duration, and activity details obtained at the childcare facility; means for classifying, encrypting, and storing the collected data in a database; means for analyzing the stored data and evaluating each child's characteristics; and means for generating learning and exercise menus appropriate for each child based on the evaluation results. The server also includes means for identifying the parent's emotions using an emotion engine and adjusting the content and tone of advice, and means for notifying the parent of the generated advice. This allows parents to receive appropriate advice tailored to each child's characteristics, and by receiving responses that are sensitive to their emotions, parents can feel more secure about raising their children.

[0254] A "childcare facility" is a place where children stay for a certain period of time and live and learn under the guidance of caregivers.

[0255] "Children" refers to infants and young children in childcare facilities from whom data such as dietary habits, sleep duration, and activity details are collected.

[0256] "Dietary content" refers to information about the types and amounts of food and beverages consumed by children at childcare facilities.

[0257] "Sleep time" is the total amount of time including the start and end times of a child's sleep.

[0258] "Activity details" is information that indicates details of the activities that children engage in at the childcare facility, such as playing, studying, and exercising.

[0259] "Data collection tools" refer to the interfaces and processes used to obtain data from childcare facilities, such as children's diet, sleep, and activity.

[0260] "Data classification tools" refers to the algorithms or processing tools used to organize and classify the collected data for each child.

[0261] "Encryption methods" refers to the techniques and processes used to encrypt data to ensure its security.

[0262] A "database" is a storage device or system for storing collected data or generated information.

[0263] "Data analysis procedures" refers to the process of using stored data to run statistical methods and machine learning algorithms to assess children's characteristics.

[0264] "Characteristic assessment" refers to information about a child's health and developmental status obtained through data analysis tools.

[0265] A "learning menu" is a learning plan designed based on a child's characteristics to enhance their knowledge and skills.

[0266] An "exercise menu" is an exercise plan designed based on a child's characteristics to improve their physical strength and athletic ability.

[0267] The "menu generation means" refers to an algorithm or process for automatically generating learning menus and exercise menus based on characteristic evaluations.

[0268] "Parental notification means" refers to an interface or process for communicating the generated learning menu, exercise menu, or advice to parents.

[0269] "Inquiry reception means" refers to the interface or process for receiving inquiries about childcare from parents.

[0270] "Advice generation means" refers to the generation AI or process that provides appropriate advice in response to received inquiries based on collected data and evaluation results.

[0271] An "emotion engine" is an algorithm or technology that identifies a parent's emotions and adjusts the content and tone of advice.

[0272] This invention is a system that supports parents in raising their children by providing optimal learning and exercise menus for each child based on data obtained from childcare facilities. Furthermore, the system incorporates an emotion engine that can recognize the emotions of parents and reflect them in the advice it provides.

[0273] System Components

[0274] This system consists of four main components: a server, a terminal, a user (guardian), and an emotion engine.

[0275] Data collection overview

[0276] The server periodically collects data from the childcare facility via API, such as what children eat, how much they sleep, and what their activities are. This data collection uses a data acquisition API that connects to the childcare facility's digital system. The collected data is categorized for each child, encrypted, and stored in a database. This encryption ensures the security of the data.

[0277] Data analysis and characterization process

[0278] The server analyzes the stored data using statistical methods and machine learning algorithms. This allows the system to evaluate a child's characteristics, such as sleep patterns, nutritional balance, and activity level. For example, a child's average sleep duration and activity trends can be analyzed based on their data from the past month. This can also help understand the child's health and developmental status.

[0279] Menu generation

[0280] The server generates learning and exercise menus suited to each child based on the analysis results. The generated menus are tailored to each child's individual needs and are stored in a database. These menus can then be used as information to provide to parents. For example, a menu can be created that recommends playing with educational blocks in the morning and taking a walk outside in the afternoon for a certain child.

[0281] Parental Notification and Emotion Recognition

[0282] The device provides an interface for notifying parents of the generated learning and exercise menus. This notification is done via a dedicated application or email. In addition, an emotion engine recognizes emotions from parents' inquiries and daily conversations and reflects them in the notification content.

[0283] Inquiry response

[0284] The device provides an interface for accepting parenting-related inquiries from parents. Parents can enter their questions using an application or web form. The server analyzes the received inquiries and uses generative AI to create advice based on past data and evaluation results. An emotion engine identifies the parent's emotions and generates advice with an appropriate tone and content. The generated advice is sent to the parent via email or in-app notification.

[0285] Specific examples

[0286] For example, if a parent sends an inquiry saying, "My child has been having trouble falling asleep at night lately," the server analyzes the data and considers specific improvement measures based on the analysis of the child's sleep patterns. The emotion engine detects "fatigue" from the parent's message and adjusts the tone of the advice to be gentle and empathetic. As a result, advice such as "We understand your concerns about your child's nighttime sleepiness. We'll show you how to adjust nap times and how to relax before bed" is generated and sent to the parent.

[0287] In this way, the system allows parents to obtain the information they need for childcare in a timely manner, and by providing emotionally sensitive support, it can increase their sense of security when raising their children.

[0288] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0289] System program processing steps

[0290] Step 1:

[0291] The server periodically collects data on children's diet, sleep, and activity from the childcare facility via API. The input is the data sent from the childcare facility. Specifically, the server sends an API request and receives the data returned from the childcare facility. The output is the retrieved raw data.

[0292] Step 2:

[0293] The server categorizes the collected data by child, encrypts it, and stores it in a database. The input is the raw data obtained in step 1. Specifically, the server tags the data by child and encrypts the data using an encryption algorithm. The output is the encrypted records in the database.

[0294] Step 3:

[0295] The server retrieves data for each child from the database and analyzes it using statistical methods and machine learning algorithms. The input is encrypted data stored in the database. Specifically, the server decrypts the data and feeds it into the machine learning model. The output is an assessment result for each child, including characteristics such as sleep patterns, nutritional balance, and activity level.

[0296] Step 4:

[0297] The server generates learning and exercise menus appropriate for each child based on the characteristic evaluation. The input is the evaluation results obtained in step 3. Specifically, the server executes an algorithm to automatically generate the optimal menu based on the evaluation results. The output is the generated learning and exercise menus.

[0298] Step 5:

[0299] The device notifies the guardian of the generated learning and exercise menus. The input is the menu generated in step 4. Specifically, the device sends a notification to the guardian via a dedicated application or email. The output is a notification confirmed by the guardian.

[0300] Step 6:

[0301] The device accepts inquiries about childcare from parents. The input is a question sent by the parent through an application or a web form. Specifically, the device transfers the inquiry to the server. The output is the accepted inquiry data.

[0302] Step 7:

[0303] The server analyzes the received inquiry and creates appropriate advice using a generative AI model based on the collected data and evaluation results. The input is the inquiry data received in step 6 and the evaluation results in the database. Specifically, the server inputs prompt data into the generative AI model and generates advice content. The output is the created advice.

[0304] Step 8:

[0305] The emotion engine recognizes emotions from parental inquiries and daily interactions and adjusts the content and tone of advice. The input is inquiry data from parents. Specifically, the emotion engine analyzes the input text to identify emotions and adjusts the tone of advice. The output is advice that takes emotions into consideration.

[0306] Step 9:

[0307] The server notifies the guardian of the advice generated. The input is the advice generated in step 7 and step 8. Specifically, the server sends the advice content to the terminal, and the terminal notifies the guardian. The output is the advice sent to the guardian.

[0308] This allows the system to consistently collect data from childcare facilities and provide optimal advice to parents.

[0309] (Application example 2)

[0310] 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."

[0311] In modern childcare, personalized learning and exercise programs are important to support children's growth and development. However, parents often find it difficult to find the optimal educational and exercise programs for their children due to their busy schedules, and they often lack emotional support. Current systems lack personalized advice and emotional support for parents, leaving parents with little relief from the burden of childcare and making it difficult to care for their children with peace of mind.

[0312] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data acquired at the childcare facility, means for analyzing the collected data and evaluating the characteristics of each child, means for generating a learning menu and an exercise menu appropriate for each child based on the evaluation results, means for notifying the guardian of the generated menu, means for accepting inquiries about childcare from the guardian, means for generating appropriate advice based on the collected data and the evaluation results in response to the accepted inquiries, means for notifying the guardian of the generated advice, means including an emotion engine for recognizing the guardian's emotions and adjusting the tone and content of the advice, and means for delivering individual learning videos and exercise programs. This not only allows guardians to receive the optimal learning and exercise menu for their children but also emotionally sensitive advice, allowing them to raise their children with greater peace of mind.

[0313] A "childcare facility" is a specialized facility for the education and care of children.

[0314] "Data" refers to information such as what a child eats, how much they sleep, and what their activities are.

[0315] "Means of collection" refers to the functions and devices used to obtain data from childcare facilities and store it on a server.

[0316] "Means for analysis" refers to functions and devices for analyzing collected data using statistical methods and machine learning algorithms.

[0317] "Assessment means" refers to the functions or devices for assessing the characteristics of individual children based on the results of the analysis.

[0318] "Generating means" refers to a function or device for creating a learning menu and an exercise menu based on the evaluation results.

[0319] "Means of notification" refers to the functions and devices used to communicate the generated menus and advice to parents.

[0320] "Means for accepting inquiries" refers to functions and devices for receiving questions and opinions from parents.

[0321] The "means for generating advice" refers to a function or device for generating an appropriate answer to a received inquiry based on collected data and evaluation results.

[0322] An "emotion engine" refers to a function or device that recognizes parents' emotions and appropriately adjusts the content and tone of advice.

[0323] "Educational videos" are video content intended for the education of children.

[0324] An "exercise program" is a set of exercises or activity plans designed to promote physical activity in children.

[0325] "Means of distribution" refers to the functions and devices used to provide educational videos and exercise programs to parents and children.

[0326] System Overview

[0327] This invention is a system that supports parents in raising their children by providing optimal learning and exercise menus for each child based on data on the children obtained from childcare facilities. This system works in cooperation with four parties: a server, a terminal, a user (parent), and an emotion engine.

[0328] Data collection and storage

[0329] The server periodically retrieves the necessary data from the childcare facility. Data such as meal contents, sleep time, and activity details are automatically retrieved using the childcare facility's API. The retrieved data is categorized by child, encrypted, and stored in MongoDB.

[0330] Data analysis and characterization

[0331] The server analyzes the stored data using TensorFlow and PyTorch to evaluate each child's characteristics, including sleep patterns, nutritional balance, and activity level, providing a detailed understanding of the child's health and development.

[0332] Menu generation

[0333] Based on the analysis results, the server generates learning and exercise menus appropriate for each child, which are then sent to parents via a smartphone application developed using React Native.

[0334] Parental Notification and Emotion Recognition

[0335] The device provides an interface for parents to receive the generated learning and exercise recommendations. Notifications are sent via in-app notifications or email. At the same time, Azure Cognitive Services and IBM Watson are used to recognize emotions, and the content and tone of the advice is adjusted based on the parent's emotions.

[0336] Responding to parental inquiries and reflecting their feelings

[0337] Users (parents) can make inquiries about childcare through the application or web form. The server accepts these inquiries and generates appropriate advice based on the collected data and evaluation results. The advice is adjusted by the emotion engine and delivered to parents in an appropriate tone.

[0338] Distribution of educational videos and exercise programs

[0339] The server also includes means for generating and delivering educational videos and exercise programs tailored to the child, allowing the child to receive individually optimized content.

[0340] Specific examples

[0341] For example, if a parent complains that their child has been having trouble concentrating on their extracurricular activities, the emotion engine will recognize the emotion as "confusion." The server will analyze the data, select appropriate learning videos and exercise programs, and provide advice such as:

[0342] "We understand your concerns about your child's inability to concentrate on their lessons. We have some new educational videos that will help your child learn while having fun, so please take a look."

[0343] Prompt Sentence Examples

[0344] User message: My child has been having trouble concentrating on his lessons lately.

[0345] Q: Please provide a detailed, emotion-based explanation of why your child is having trouble concentrating and what actions you can take to improve it.

[0346] Emotion: Confused

[0347] This system not only provides parents with the optimal learning and exercise menu for their children, but also allows them to receive emotionally sensitive advice, allowing them to raise their children with greater peace of mind.

[0348] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0349] Step 1:

[0350] Data collection

[0351] The server periodically retrieves child data (meals, sleep time, activity) from the childcare facility API. During this process, the data retrieved from the API is temporarily stored and encrypted for secure storage in MongoDB.

[0352] Input: Raw data from the childcare facility API

[0353] Output: Data stored in MongoDB in encrypted form

[0354] Step 2:

[0355] Data analysis

[0356] The server uses TensorFlow and PyTorch to analyze the data stored in MongoDB, which involves using statistical methods and machine learning algorithms to extract child characteristics from the data (e.g., sleep patterns, nutritional balance, activity levels).

[0357] Input: Data stored in MongoDB

[0358] Output: Analysis results evaluating the characteristics of each child

[0359] Step 3:

[0360] Menu generation

[0361] Based on the analysis results, the server generates learning and exercise menus appropriate for each child, which involves using a Python script to create a list of menus according to generation rules.

[0362] Input: Analysis results

[0363] Output: Learning and exercise menus appropriate for each child

[0364] Step 4:

[0365] Parental notification

[0366] The device notifies parents of the generated learning and exercise menus through a smartphone application developed using React Native, either via the app's notification function or email.

[0367] Input: Generated learning menu and exercise menu

[0368] Output: Parental notification message

[0369] Step 5:

[0370] emotion recognition

[0371] The server uses Azure Cognitive Services and IBM Watson to recognize emotions from parental feedback and inquiries, and generates responses based on the parent's emotions.

[0372] Input: Parent inquiries and feedback

[0373] Output: Recognized parent's emotion data

[0374] Step 6:

[0375] Inquiry handling and advice generation

[0376] The server generates appropriate advice based on the collected data and evaluation results in response to the received inquiry. This process involves generating responses using natural language processing (NLP) with a generative AI model.

[0377] Input: Parental inquiries, collected data, assessment results, recognized emotion data

[0378] Output: Generated advice

[0379] Step 7:

[0380] Advice Notification

[0381] The device will then notify the parent of the generated advice via the notification function within the application or email.

[0382] Input: Generated advice

[0383] Output: Parental Advisory Notice

[0384] Step 8:

[0385] Distribution of educational videos and exercise programs

[0386] The server generates educational videos and exercise programs tailored to each child and distributes them through websites and applications, adding appropriate metadata to make them easily accessible to parents and children.

[0387] Input: Generated learning videos and exercise programs

[0388] Output: Distributed learning videos and exercise programs

[0389] 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.

[0390] 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.

[0391] 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.

[0392] [Second embodiment]

[0393] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0394] 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.

[0395] 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).

[0396] 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.

[0397] 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.

[0398] 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).

[0399] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0400] 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.

[0401] 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.

[0402] 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.

[0403] In the smart glasses 214, 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.

[0404] 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."

[0405] The present invention provides a system that supports parents in raising their children by providing optimal learning and exercise programs for each child based on data acquired from childcare facilities. Specific embodiments of the system are described below.

[0406] System Overview

[0407] This system works in cooperation with three parties: a server, a terminal, and a user. The server is responsible for collecting, storing, and analyzing data, and generating menus and notifications, while the terminal provides an interface with childcare facilities and parents. Users (mainly parents) receive information necessary for childcare and make inquiries through the system.

[0408] Data collection and storage

[0409] The server periodically receives data from the childcare facility, such as mealtimes, sleep duration, and activity status, via an API. The collected data is categorized for each child and stored in a database. The stored data is updated daily and encrypted for security purposes.

[0410] Data analysis and characterization

[0411] The server analyzes the data stored in the database and evaluates each child's characteristics, such as sleep patterns, nutritional balance, and daily activity levels, to understand the child's health and development.

[0412] Menu generation

[0413] Based on the analysis results, the server generates learning and exercise menus tailored to each child. For example, it may design an exercise menu that focuses on children with low activity levels, and recommend an arts and crafts learning menu for children who like creative activities. The generated menus are stored in a database and are ready to be provided to parents.

[0414] Parental notification

[0415] The server notifies parents of the generated learning and exercise menus. Specifically, notifications are sent via a dedicated application or email. The notifications include details of the menus and information on how to implement them.

[0416] Responding to parental inquiries

[0417] The device provides an interface for parents to make inquiries about childcare, and parents can enter their questions using an application or a web form.

[0418] The server analyzes the received inquiries and uses generative AI to generate appropriate advice based on past data and evaluation results. The advice is then sent to parents via email or in-app notifications.

[0419] Specific examples

[0420] For example, if a child has trouble falling asleep and can only sleep for a certain amount of time, the server will analyze the data and detect irregular sleep patterns. It will then provide parents with suggestions for adjusting nap times and revising their nighttime routine. If it determines that a lack of exercise is the cause, it will suggest easy indoor exercises.

[0421] This system allows parents to receive accurate advice without being overwhelmed by daily childcare, and effectively supports their children's health and development.

[0422] The processing flow will be explained below.

[0423] Step 1: Collect and store data

[0424] The server periodically collects data such as meal contents, sleep time, and activity details from the childcare facility via an API.

[0425] Specific operation: Sends an API request to retrieve the latest data from the childcare facility's system and stores the received data in a temporary buffer.

[0426] Step 2: Classify and encrypt data

[0427] The server categorizes the data it collects by child and encrypts it before storing it in a database.

[0428] Specific operation: The data is sorted by child ID, an encryption algorithm is applied, and the data is inserted into the database.

[0429] Step 3: Preprocessing the data

[0430] The server performs pre-processing to convert the stored data into a format that is easy to analyze.

[0431] Specific operations: Impute missing values, normalize data, check for and correct data inconsistencies and errors.

[0432] Step 4: Data analysis and characterization

[0433] The server evaluates the child's characteristics based on the pre-processed data.

[0434] What it does: Uses statistical methods and machine learning algorithms to assess sleep patterns, nutritional balance, and activity levels.

[0435] Step 5: Generate the menu

[0436] Based on the analysis results, the server generates a learning menu and an exercise menu suitable for each child.

[0437] What it does: Apply rule-based algorithms and machine learning models to convert the generated menu into a format appropriate for each child.

[0438] Step 6: Prepare the menu for notifications

[0439] The server prepares to notify the parent of the generated menu.

[0440] What it does: Gets parent contact information and formats menu information into rich text and HTML.

[0441] Step 7: Menu Notifications

[0442] The server notifies the parent of the menu when it is ready.

[0443] Specific operations: Connect to the mail server or push notification server, send the prepared message, and save the sending log.

[0444] Step 8: Receiving parental inquiries

[0445] The device provides an interface where parents can input questions about childcare.

[0446] Specific operation: Prepare an inquiry form in a mobile or web app and set up an API endpoint to send user input to the server.

[0447] Step 9: Processing the inquiry and generating an answer

[0448] The server receives questions from parents, and the generative AI creates advice based on the collected data and evaluation results.

[0449] What it does: Searches for relevant historical data from a database and generates an answer using a provided natural language processing (NLP) model.

[0450] Step 10: Notification of response

[0451] The server notifies the parent of the generated advice.

[0452] Specific behavior: Sends responses to parents via email or in-app notification, and stores notification sending logs in a database.

[0453] Example 1

[0454] 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."

[0455] Effectively understanding the health and developmental status of children attending childcare facilities and providing childcare support based on that information is an important issue for parents. However, currently, data collection is often done manually, making it difficult to analyze the data and provide appropriate advice. In addition, parents are often not notified of information or their inquiries are not responded to promptly and appropriately. This can cause parents to feel anxious and worried about their children's health management and childcare.

[0456] 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.

[0457] In this invention, the server includes means for collecting data on children's dietary habits, sleep duration, and activity details obtained at the childcare facility, means for analyzing the collected data and evaluating the characteristics of each child, means for generating a learning menu and an exercise menu appropriate for each child based on the evaluation results, means for notifying parents of the generated menus, means for accepting inquiries about childcare from parents, means for generating appropriate advice in response to the accepted inquiries based on the collected data and the evaluation results, means for notifying parents of the generated advice, means for encrypting the collected data for security purposes, means for storing data classified for each child in a database, means for performing time series analysis to analyze the data, means for generating the generated exercise menu and learning menu using a machine learning algorithm, means for generating appropriate advice using a natural language processing model, and means for notifying parents via a dedicated application or email. This allows parents to accurately understand their children's health and developmental status and receive prompt and appropriate childcare support.

[0458] The "data collection means" is a means for collecting data on children's diet, sleep time, and activity details obtained at the childcare facility.

[0459] "Data analysis tools" are tools for analyzing collected data and evaluating the characteristics of individual children.

[0460] The "menu generating means" is a means for generating a learning menu and an exercise menu suitable for each child based on the evaluation results.

[0461] The "menu notification means" is a means for notifying the guardian of the generated learning menu and exercise menu.

[0462] The "inquiry reception means" is a means for receiving inquiries about childcare from parents.

[0463] The "advice generation means" is a means for generating appropriate advice in response to a received inquiry based on the collected data and evaluation results.

[0464] The "advice notification means" is a means for notifying the guardian of the generated advice.

[0465] "Encryption means" means means for encrypting collected data for security purposes.

[0466] The "database storage means" is a means for storing data classified for each individual child in a database.

[0467] The "time series analysis means" is a means for performing time series analysis to analyze data.

[0468] A "machine learning algorithm" is a method for generating exercise menus and learning menus based on machine learning.

[0469] The "natural language processing model" is a model for generating advice in natural language in response to inquiries from parents.

[0470] "Notification means" refers to a means for notifying parents of information via a dedicated application or email.

[0471] This invention is a system that supports parents in raising their children by providing optimal learning and exercise menus for each child based on data obtained from childcare facilities. This system operates in cooperation with three parties: a server, a terminal, and a user.

[0472] Data collection and storage

[0473] The server periodically receives data such as meal contents, sleep time, and activity details sent from the childcare facility via a RESTful API. A common framework (e.g., Spring Boot) is used for this API communication. The obtained data is categorized for each child and stored in a database (e.g., MySQL). The stored data is updated daily and is encrypted with AES-256 for security.

[0474] Data analysis and characterization

[0475] The server analyzes the data stored in the database using Python and Pandas. It performs time-series analysis on sleep data and evaluates nutritional balance on nutritional data. This makes it possible to understand the health and developmental status of each child. The analysis results are stored in the database.

[0476] Menu generation

[0477] Based on the analysis results, the server generates learning and exercise menus suited to each individual child. This process utilizes machine learning models using TensorFlow. For example, it generates a "simple exercise menu" for a child with a low level of physical activity, and recommends "painting and craft activities" for a child who enjoys creative activities.

[0478] Parental notification

[0479] The server notifies parents of the generated learning and exercise menus. Notification methods include email (e.g., SendGrid API) and a dedicated app (e.g., built with React Native). The notification includes details of the menu and information on how to implement it.

[0480] Responding to parental inquiries

[0481] The device provides an interface for accepting inquiries about childcare from parents. Parents can enter questions through a web form or an application (e.g., an app using the Flask framework). For example, a parent can send an inquiry about "the causes and solutions for nighttime crying."

[0482] Advice Generation and Notifications

[0483] The server analyzes the received inquiry and generates appropriate advice using a generative AI model (e.g., GPT-4) based on past data and evaluation results. The generated advice is sent to the parent via email or in-app notification. The following prompt sentences are used to generate the advice:

[0484] Example prompt sentence:

[0485] "Mr. A has trouble falling asleep and is sleeping less at night. Based on his recent sleep pattern data, please provide some advice on adjusting his nap time and reviewing his nighttime routine."

[0486] This system allows parents to receive accurate advice without being overwhelmed by daily childcare, and effectively supports their children's health and development.

[0487] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0488] Step 1:

[0489] The server periodically receives data from the childcare facility about the children's diet, sleep time, and activity via a RESTful API. A common framework (e.g., Spring Boot) is used for this API communication, and the received data is sent to the server in JSON format. The input is data from the childcare facility, and the output is the raw data received by the server. This data is categorized for each child and proceeds to the next step.

[0490] Step 2:

[0491] The server stores the retrieved data in a MySQL database. Before storing the data, each data is classified by child and encrypted using the AES-256 algorithm for security. The input is the raw data and each child's ID, and the output is the encrypted data stored in the database. This storage process is performed using an INSERT query.

[0492] Step 3:

[0493] The server analyzes the data stored in the database using Python and Pandas. For example, it performs time-series analysis on sleep data and calculates activity levels and nutritional balance. The input is data for each child extracted from the database, and the output is the analysis results. The analysis results are then stored back in the database.

[0494] Step 4:

[0495] The server uses a machine learning model (a model using TensorFlow) to evaluate the characteristics of each child based on the analysis results. It performs tasks such as classifying physical activity levels and evaluating learning characteristics. The input is the analysis results, and the output is the characteristic evaluation results. The characteristic evaluation results are also stored in a database.

[0496] Step 5:

[0497] The server generates learning and exercise menus appropriate for each child based on the results of the characteristic assessment. Generative AI models such as GPT-4 are used to create specific menus. For example, gymnastics menus are recommended for children with low physical activity levels, and craft activities are recommended for children who prefer creative activities. The input is the characteristic assessment results, and the output is the generated menu. The generated menu is stored in a database.

[0498] Step 6:

[0499] The server notifies parents of the generated learning and exercise menus. Notification methods include email (using SendGrid's API) and a dedicated app (built with React Native). The input is the generated menu and parent contact information, and the output is the notification sent to the parent.

[0500] Step 7:

[0501] The device provides an interface for accepting inquiries about childcare from parents. Parents can enter questions through a web form or an application (Flask framework). For example, a user can send an inquiry about the cause of nighttime crying and what to do about it from the application. The input is the inquiry from the parent, and the output is the query data sent to the server.

[0502] Step 8:

[0503] The server analyzes the received query using a generative AI model (GPT-4) and generates appropriate advice. The input is the query content, past data in the database, and the characteristic evaluation results, and the output is the generated advice. This advice is generated based on the following prompt:

[0504] Example prompt sentence:

[0505] "Mr. A has trouble falling asleep and is sleeping less at night. Based on his recent sleep pattern data, please provide some advice on adjusting his nap time and reviewing his nighttime routine."

[0506] Step 9:

[0507] The server sends the generated advice to the parent via email or in-app notification. The input is the generated advice and the parent's contact information, and the output is the notification sent to the parent. This allows parents to receive accurate advice.

[0508] (Application example 1)

[0509] 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."

[0510] The goal is to adequately resolve the concerns and questions parents have about childcare. Furthermore, to support the efficient management of children's health and development, it is important to provide the most appropriate learning and exercise programs for each child based on data collected from childcare facilities. Furthermore, there is a need for a system that allows parents to easily check this information and receive appropriate advice in response to inquiries.

[0511] 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.

[0512] In this invention, the server includes means for collecting data on children's dietary habits, sleep duration, and activity details obtained at the childcare facility, means for analyzing the collected data and evaluating the characteristics of each child, means for generating learning and exercise menus appropriate for each child based on the evaluation results, means for notifying parents of the generated menus, means for accepting inquiries about childcare from parents, means for generating appropriate advice in response to the accepted inquiries based on the collected data and evaluation results, means for notifying parents of the generated advice, means for parents to check and manage the generated menus and advice via a smartphone application, means for generating individual advice using a generative AI model in response to inquiries from parents, and means for generating the generated advice using a natural language processing model via prompt sentences. This allows parents to easily obtain all data and advice related to childcare and take appropriate action.

[0513] A "childcare facility" is a facility that temporarily takes care of infants and children and provides them with daily care, including meals, sleep, and play.

[0514] "Dietary content" refers to information about the foods a child ingests at the childcare facility, including their type, quantity, and nutrients.

[0515] "Sleep hours" is the total amount of time a child sleeps in the childcare facility.

[0516] "Activity details" refers to data on specific activities such as exercise, learning, and play that children engage in at the childcare facility.

[0517] "Means for collecting data" refers to a method or device for obtaining data from the childcare facility regarding dietary habits, sleep duration, and activity.

[0518] A "means for analyzing data" is a method or device that uses collected data to assess a child's health status or characteristics.

[0519] A "trait assessment tool" is a method or device for assessing the developmental or health status of an individual child based on collected data.

[0520] A "learning menu" is a combination of materials and activities designed to help children learn appropriately.

[0521] An "exercise menu" is a combination of exercises and games designed to get children moving and exercising appropriately.

[0522] "Means for notifying parents" refers to a method or device for notifying parents of the generated menu or advice.

[0523] "Means for accepting inquiries about childcare" refers to a method or device for accepting questions or inquiries from parents.

[0524] A "means for generating appropriate advice" is a method or apparatus for generating advice based on a query and using collected data and evaluation results.

[0525] "Via a smartphone application" means operating or viewing through an application running on a smartphone.

[0526] A "generative AI model" is a model that uses artificial intelligence technology to create learning menus and advice generated from data.

[0527] A "prompt sentence" is a sentence that specifically describes the question or instruction to be input into the generative AI model.

[0528] A "natural language processing model" is a set of techniques and algorithms that allow computers to understand, analyze, and generate human language.

[0529] This invention is a system that supports parents in raising their children by creating optimal learning and exercise menus for each child based on data acquired from childcare facilities. Specific embodiments of the system are described below.

[0530] System configuration

[0531] The system works in cooperation with three parties: a server, a device, and parents. The server is responsible for collecting, storing, and analyzing data, and generating menus and notifications, while the device provides an interface with childcare facilities and parents. Parents can receive information necessary for childcare and make inquiries through the system.

[0532] Data collection and storage

[0533] The server collects data sent from the childcare facility, such as meal contents, sleep time, and activity details. It uses Amazon Web Services (AWS) to periodically retrieve data via API using AWS Lambda. The collected data is stored in AWS RDS (a relational database service) and is encrypted for added security.

[0534] Data analysis and characterization

[0535] The server analyzes the data stored in the database and evaluates each child's characteristics. It uses Python, Numpy, and Pandas to analyze sleep patterns and check nutritional balance. It also uses TensorFlow to cluster children's health and developmental status using machine learning models.

[0536] Menu generation

[0537] Based on the analysis results, the server generates learning and exercise menus appropriate for each child, using TensorFlow's deep neural network (DNN) model, and stores the generated menus in Amazon RDS.

[0538] Parental notification

[0539] The server notifies parents of the generated learning and exercise menus. Push notifications are sent using AWS SNS (Simple Notification Service), and a smartphone application developed with React Native receives the notifications. The app then displays the menu details to parents.

[0540] Responding to parental inquiries

[0541] The server accepts inquiries about childcare from parents and responds. Parents input their questions through a smartphone application. The server uses a generative AI model (e.g., GPT-4) to generate appropriate advice based on past data and evaluation results. This advice is generated by a natural language processing model (e.g., GPT-4 API) through a prompt sentence and notified to the parent via AWS SNS.

[0542] Specific examples

[0543] For example, if a child has trouble falling asleep and can only sleep for a certain amount of time, the server will analyze the data and detect irregular sleep patterns. It will then provide parents with suggestions for adjusting nap times and revising their nighttime routine. If it determines that a lack of exercise is the cause, it will suggest easy indoor exercises.

[0544] Prompt Sentence Examples

[0545] Parent input: "My child has been having trouble falling asleep lately. Any advice?"

[0546] Use the following prompt: "What advice can you offer to a child who has been having trouble falling asleep recently?"

[0547] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0548] Step 1:

[0549] The server collects data from the childcare facility on children's dietary habits, sleep duration, and activity. This data is periodically sent to the server from the childcare facility's terminal via API. The input data is in JSON format and includes daily data for each child. The collected data is processed by AWS Lambda and stored in AWS RDS.

[0550] Step 2:

[0551] The server periodically analyzes the data stored in AWS RDS. It extracts data using Python scripts and preprocesses the data using Numpy and Pandas. For example, it performs data cleaning such as imputing missing values ​​and detecting outliers. The input data is the preprocessed daily data for each child, and the output data is data converted into a format suitable for analysis.

[0552] Step 3:

[0553] The server evaluates each child's characteristics based on the preprocessed data. It uses a machine learning model using TensorFlow to cluster sleep patterns and activity levels. The input data is the preprocessed data for each child, and the output data is the results of each child's characteristic evaluation. Specific operations for characteristic evaluation include running a clustering algorithm and calculating a score for each characteristic.

[0554] Step 4:

[0555] The server generates learning and exercise menus appropriate for each child based on the evaluation results. This is done using TensorFlow DNN. For example, it might design a focused exercise menu for a child with low activity levels, and recommend an arts and crafts learning menu for a child who enjoys creative activities. The input data is the characteristic evaluation results, and the output data is the learning and exercise menu appropriate for each child.

[0556] Step 5:

[0557] The server notifies parents of the generated learning and exercise menus. Specifically, it uses AWS SNS to send push notifications. The input data is the generated menu, and the output data is a notification sent to the parent's smartphone. The notification contains details about the menu and information on how to implement it.

[0558] Step 6:

[0559] Parents send inquiries about childcare to the server via a smartphone application. The input data is the question or consultation from the parent, and the output data is the inquiry data sent to the server. Specifically, the question is entered into the inquiry form within the app and sent.

[0560] Step 7:

[0561] The server receives inquiries from parents and generates appropriate advice using a generative AI model (GPT-4) based on previous data and evaluation results. It calls the GPT-4 API using a prompt sentence to generate appropriate advice. The input data is the parent's question and related child data, and the output data is the generated advice.

[0562] Step 8:

[0563] The server notifies the parent of the generated advice. The advice is sent to the parent's smartphone via AWS SNS. The input data is the generated advice, and the output data is the notification sent to the parent's smartphone. Specifically, the generated advice is displayed as an in-app notification.

[0564] 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.

[0565] This invention combines a system that provides optimal learning and exercise menus for each child based on data acquired from childcare facilities and supports parents in raising their children with an emotion engine. Specific embodiments of the system are described below.

[0566] System Overview

[0567] This system works in cooperation with four parties: a server, a device, a user, and an emotion engine. The server is responsible for collecting, storing, and analyzing data, and generating menus and notifications, while the device provides an interface with childcare facilities and parents. Users (mainly parents) receive information necessary for childcare through the system and make inquiries. The emotion engine recognizes emotions from the user's input and actions and reflects them in the advice it provides.

[0568] Data collection and storage

[0569] The server periodically receives data from the childcare facility via API, including meal contents, sleep time, and activity details. The data is categorized by child, encrypted, and stored in a database.

[0570] Data analysis and characterization

[0571] The server analyzes the stored data and evaluates each child's characteristics, such as sleep patterns, nutritional balance, and activity levels, using statistical methods and machine learning algorithms to understand the child's health and developmental status.

[0572] Menu generation

[0573] Based on the analysis results, the server generates a learning and exercise menu suited to each child. The generated menu, which is tailored to each child's individual needs, is stored in a database and later provided to parents.

[0574] Parental Notification and Emotion Recognition

[0575] The device provides an interface for notifying parents of the generated learning and exercise menus. Notifications are sent via a dedicated application or email. The emotion engine recognizes emotions from parents' inquiries and daily interactions and adjusts the content and tone of the advice accordingly.

[0576] Responding to parental inquiries and reflecting their feelings

[0577] The device provides an interface for parents to make inquiries about childcare, and parents can enter their questions using an application or a web form.

[0578] The server analyzes the received inquiry and uses generative AI to generate advice based on past data and evaluation results. The emotion engine identifies emotions from the parent's input and generates advice with an appropriate tone and content. The generated advice is sent to the parent via email or in-app notification.

[0579] Specific examples

[0580] For example, if a parent sounds tired and sends a message saying, "My child has been having trouble falling asleep at night lately," the server analyzes the data and considers specific measures to improve the child's sleep pattern based on the analysis. The emotion engine detects "fatigue" in the parent's message and adjusts the tone of the advice to be gentle and empathetic. As a result, advice such as "We understand your concerns about your child's nighttime sleepiness. We'll show you how to adjust nap times and how to relax before bed" is generated and sent to the parent.

[0581] This system allows parents to receive accurate advice without feeling overwhelmed by the daily tasks of childcare, and by receiving support that is sensitive to their emotions, they can feel even more secure in raising their children.

[0582] The processing flow will be explained below.

[0583] Step 1: Collect and store data

[0584] The server periodically collects data such as meal contents, sleep time, and activity details from the childcare facility via an API.

[0585] What it does: Sends an API request to receive the latest data from the childcare system, stores it in a temporary buffer, categorizes it by child, and encrypts it before inserting it into the database.

[0586] Step 2: Preprocessing the data

[0587] The server performs pre-processing to convert the stored data into a format that is easy to analyze.

[0588] Specific actions: Impute missing values, normalize data, check for and correct inconsistencies and errors.

[0589] Step 3: Data analysis and characterization

[0590] The server evaluates the child's characteristics based on the pre-processed data.

[0591] What it does: Uses statistical methods and machine learning algorithms to analyze sleep patterns, nutritional balance, and activity levels to assess a child's health and development.

[0592] Step 4: Generate the menu

[0593] Based on the analysis results, the server generates a learning menu and an exercise menu suitable for each child.

[0594] What it does: It applies rule-based algorithms and machine learning models to design optimal menus for each individual child and stores them in a database.

[0595] Step 5: Prepare the menu for notifications

[0596] The server prepares to notify the parent of the generated menu.

[0597] What it does: Gets parent contact information and formats menu information into rich text and HTML.

[0598] Step 6: Menu Notifications

[0599] The server notifies the parent of the menu when it is ready.

[0600] Specific operations: Connect to the mail server or push notification server to send the message. Save the sending log for later tracking.

[0601] Step 7: Receiving parental inquiries

[0602] The device provides an interface where parents can input questions about childcare.

[0603] Specific operation: Prepare an inquiry form within the mobile app or web app and set up an API endpoint that sends user input to the server.

[0604] Step 8: Parsing the query

[0605] The server receives questions from parents and searches the database for relevant past data.

[0606] Specific operation: Analyzes the inquiry content and generates appropriate advice based on past data and evaluation results.

[0607] Step 9: Recognize emotions

[0608] The server uses an emotion engine to recognize emotions from the parent's inquiry.

[0609] What it does: Analyzes text data using a natural language processing (NLP) model to identify the parent's emotional state (e.g., fatigue, anxiety, joy).

[0610] Step 10: Adjusting Advice

[0611] The server adjusts the content and tone of advice based on the emotional state recognized by the emotion engine.

[0612] Specific behavior: Generate appropriate advice based on the emotional state, and use gentle and empathetic language.

[0613] Step 11: Advice Notification

[0614] The server notifies the parent of the generated advice.

[0615] Specific behavior: Sends advice to parents via email and in-app notifications, and stores the sending log in a database for future reference.

[0616] Example 2

[0617] 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."

[0618] In modern society, parents have limited time to devote to childcare and often rely on childcare facilities. As a result, they face challenges in obtaining sufficient information about their children's activities and health at childcare facilities, making it difficult for them to receive appropriate advice. Furthermore, uniform advice may not adequately reflect each child's individual characteristics, which can cause anxiety and stress for parents. Furthermore, a lack of consideration for parents' feelings can increase the burden of childcare.

[0619] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0620] In this invention, the server includes: means for collecting data on children's dietary habits, sleep duration, and activity details obtained at the childcare facility; means for classifying, encrypting, and storing the collected data in a database; means for analyzing the stored data and evaluating each child's characteristics; and means for generating learning and exercise menus appropriate for each child based on the evaluation results. The server also includes means for identifying the parent's emotions using an emotion engine and adjusting the content and tone of advice, and means for notifying the parent of the generated advice. This allows parents to receive appropriate advice tailored to each child's characteristics, and by receiving responses that are sensitive to their emotions, parents can feel more secure about raising their children.

[0621] A "childcare facility" is a place where children stay for a certain period of time and live and learn under the guidance of caregivers.

[0622] "Children" refers to infants and young children in childcare facilities from whom data such as dietary habits, sleep duration, and activity details are collected.

[0623] "Dietary content" refers to information about the types and amounts of food and beverages consumed by children at childcare facilities.

[0624] "Sleep time" is the total amount of time including the start and end times of a child's sleep.

[0625] "Activity details" is information that indicates details of the activities that children engage in at the childcare facility, such as playing, studying, and exercising.

[0626] "Data collection tools" refer to the interfaces and processes used to obtain data from childcare facilities, such as children's diet, sleep, and activity.

[0627] "Data classification tools" refers to the algorithms or processing tools used to organize and classify the collected data for each child.

[0628] "Encryption methods" refers to the techniques and processes used to encrypt data to ensure its security.

[0629] A "database" is a storage device or system for storing collected data or generated information.

[0630] "Data analysis procedures" refers to the process of using stored data to run statistical methods and machine learning algorithms to assess children's characteristics.

[0631] "Characteristic assessment" refers to information about a child's health and developmental status obtained through data analysis tools.

[0632] A "learning menu" is a learning plan designed based on a child's characteristics to enhance their knowledge and skills.

[0633] An "exercise menu" is an exercise plan designed based on a child's characteristics to improve their physical strength and athletic ability.

[0634] The "menu generation means" refers to an algorithm or process for automatically generating learning menus and exercise menus based on characteristic evaluations.

[0635] "Parental notification means" refers to an interface or process for communicating the generated learning menu, exercise menu, or advice to parents.

[0636] "Inquiry reception means" refers to the interface or process for receiving inquiries about childcare from parents.

[0637] "Advice generation means" refers to the generation AI or process that provides appropriate advice in response to received inquiries based on collected data and evaluation results.

[0638] An "emotion engine" is an algorithm or technology that identifies a parent's emotions and adjusts the content and tone of advice.

[0639] This invention is a system that supports parents in raising their children by providing optimal learning and exercise menus for each child based on data obtained from childcare facilities. Furthermore, the system incorporates an emotion engine that can recognize the emotions of parents and reflect them in the advice it provides.

[0640] System Components

[0641] This system consists of four main components: a server, a terminal, a user (guardian), and an emotion engine.

[0642] Data collection overview

[0643] The server periodically collects data from the childcare facility via API, such as what children eat, how much they sleep, and what their activities are. This data collection uses a data acquisition API that connects to the childcare facility's digital system. The collected data is categorized for each child, encrypted, and stored in a database. This encryption ensures the security of the data.

[0644] Data analysis and characterization process

[0645] The server analyzes the stored data using statistical methods and machine learning algorithms. This allows the system to evaluate a child's characteristics, such as sleep patterns, nutritional balance, and activity level. For example, a child's average sleep duration and activity trends can be analyzed based on their data from the past month. This can also help understand the child's health and developmental status.

[0646] Menu generation

[0647] The server generates learning and exercise menus suited to each child based on the analysis results. The generated menus are tailored to each child's individual needs and are stored in a database. These menus can then be used as information to provide to parents. For example, a menu can be created that recommends playing with educational blocks in the morning and taking a walk outside in the afternoon for a certain child.

[0648] Parental Notification and Emotion Recognition

[0649] The device provides an interface for notifying parents of the generated learning and exercise menus. This notification is done via a dedicated application or email. In addition, an emotion engine recognizes emotions from parents' inquiries and daily conversations and reflects them in the notification content.

[0650] Inquiry response

[0651] The device provides an interface for accepting parenting-related inquiries from parents. Parents can enter their questions using an application or web form. The server analyzes the received inquiries and uses generative AI to create advice based on past data and evaluation results. An emotion engine identifies the parent's emotions and generates advice with an appropriate tone and content. The generated advice is sent to the parent via email or in-app notification.

[0652] Specific examples

[0653] For example, if a parent sends an inquiry saying, "My child has been having trouble falling asleep at night lately," the server analyzes the data and considers specific improvement measures based on the analysis of the child's sleep patterns. The emotion engine detects "fatigue" from the parent's message and adjusts the tone of the advice to be gentle and empathetic. As a result, advice such as "We understand your concerns about your child's nighttime sleepiness. We'll show you how to adjust nap times and how to relax before bed" is generated and sent to the parent.

[0654] In this way, the system allows parents to obtain the information they need for childcare in a timely manner, and by providing emotionally sensitive support, it can increase their sense of security when raising their children.

[0655] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0656] System program processing steps

[0657] Step 1:

[0658] The server periodically collects data on children's diet, sleep, and activity from the childcare facility via API. The input is the data sent from the childcare facility. Specifically, the server sends an API request and receives the data returned from the childcare facility. The output is the retrieved raw data.

[0659] Step 2:

[0660] The server categorizes the collected data by child, encrypts it, and stores it in a database. The input is the raw data obtained in step 1. Specifically, the server tags the data by child and encrypts the data using an encryption algorithm. The output is the encrypted records in the database.

[0661] Step 3:

[0662] The server retrieves data for each child from the database and analyzes it using statistical methods and machine learning algorithms. The input is encrypted data stored in the database. Specifically, the server decrypts the data and feeds it into the machine learning model. The output is an assessment result for each child, including characteristics such as sleep patterns, nutritional balance, and activity level.

[0663] Step 4:

[0664] The server generates learning and exercise menus appropriate for each child based on the characteristic evaluation. The input is the evaluation results obtained in step 3. Specifically, the server executes an algorithm to automatically generate the optimal menu based on the evaluation results. The output is the generated learning and exercise menus.

[0665] Step 5:

[0666] The device notifies the guardian of the generated learning and exercise menus. The input is the menu generated in step 4. Specifically, the device sends a notification to the guardian via a dedicated application or email. The output is a notification confirmed by the guardian.

[0667] Step 6:

[0668] The device accepts inquiries about childcare from parents. The input is a question sent by the parent through an application or a web form. Specifically, the device transfers the inquiry to the server. The output is the accepted inquiry data.

[0669] Step 7:

[0670] The server analyzes the received inquiry and creates appropriate advice using a generative AI model based on the collected data and evaluation results. The input is the inquiry data received in step 6 and the evaluation results in the database. Specifically, the server inputs prompt data into the generative AI model and generates advice content. The output is the created advice.

[0671] Step 8:

[0672] The emotion engine recognizes emotions from parental inquiries and daily interactions and adjusts the content and tone of advice. The input is inquiry data from parents. Specifically, the emotion engine analyzes the input text to identify emotions and adjusts the tone of advice. The output is advice that takes emotions into consideration.

[0673] Step 9:

[0674] The server notifies the guardian of the advice generated. The input is the advice generated in step 7 and step 8. Specifically, the server sends the advice content to the terminal, and the terminal notifies the guardian. The output is the advice sent to the guardian.

[0675] This allows the system to consistently collect data from childcare facilities and provide optimal advice to parents.

[0676] (Application example 2)

[0677] 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."

[0678] In modern childcare, personalized learning and exercise programs are important to support children's growth and development. However, parents often find it difficult to find the optimal educational and exercise programs for their children due to their busy schedules, and they often lack emotional support. Current systems lack personalized advice and emotional support for parents, leaving parents with little relief from the burden of childcare and making it difficult to care for their children with peace of mind.

[0679] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data acquired at the childcare facility, means for analyzing the collected data and evaluating the characteristics of each child, means for generating a learning menu and an exercise menu appropriate for each child based on the evaluation results, means for notifying the guardian of the generated menu, means for accepting inquiries about childcare from the guardian, means for generating appropriate advice based on the collected data and the evaluation results in response to the accepted inquiries, means for notifying the guardian of the generated advice, means including an emotion engine for recognizing the guardian's emotions and adjusting the tone and content of the advice, and means for delivering individual learning videos and exercise programs. This not only allows guardians to receive the optimal learning and exercise menu for their children but also emotionally sensitive advice, allowing them to raise their children with greater peace of mind.

[0680] A "childcare facility" is a specialized facility for the education and care of children.

[0681] "Data" refers to information such as what a child eats, how much they sleep, and what their activities are.

[0682] "Means of collection" refers to the functions and devices used to obtain data from childcare facilities and store it on a server.

[0683] "Means for analysis" refers to functions and devices for analyzing collected data using statistical methods and machine learning algorithms.

[0684] "Assessment means" refers to the functions or devices for assessing the characteristics of individual children based on the results of the analysis.

[0685] "Generating means" refers to a function or device for creating a learning menu and an exercise menu based on the evaluation results.

[0686] "Means of notification" refers to the functions and devices used to communicate the generated menus and advice to parents.

[0687] "Means for accepting inquiries" refers to functions and devices for receiving questions and opinions from parents.

[0688] The "means for generating advice" refers to a function or device for generating an appropriate answer to a received inquiry based on collected data and evaluation results.

[0689] An "emotion engine" refers to a function or device that recognizes parents' emotions and appropriately adjusts the content and tone of advice.

[0690] "Educational videos" are video content intended for the education of children.

[0691] An "exercise program" is a set of exercises or activity plans designed to promote physical activity in children.

[0692] "Means of distribution" refers to the functions and devices used to provide educational videos and exercise programs to parents and children.

[0693] System Overview

[0694] This invention is a system that supports parents in raising their children by providing optimal learning and exercise menus for each child based on data on the children obtained from childcare facilities. This system works in cooperation with four parties: a server, a terminal, a user (parent), and an emotion engine.

[0695] Data collection and storage

[0696] The server periodically retrieves the necessary data from the childcare facility. Data such as meal contents, sleep time, and activity details are automatically retrieved using the childcare facility's API. The retrieved data is categorized by child, encrypted, and stored in MongoDB.

[0697] Data analysis and characterization

[0698] The server analyzes the stored data using TensorFlow and PyTorch to evaluate each child's characteristics, including sleep patterns, nutritional balance, and activity level, providing a detailed understanding of the child's health and development.

[0699] Menu generation

[0700] Based on the analysis results, the server generates learning and exercise menus appropriate for each child, which are then sent to parents via a smartphone application developed using React Native.

[0701] Parental Notification and Emotion Recognition

[0702] The device provides an interface for parents to receive the generated learning and exercise recommendations. Notifications are sent via in-app notifications or email. At the same time, Azure Cognitive Services and IBM Watson are used to recognize emotions, and the content and tone of the advice is adjusted based on the parent's emotions.

[0703] Responding to parental inquiries and reflecting their feelings

[0704] Users (parents) can make inquiries about childcare through the application or web form. The server accepts these inquiries and generates appropriate advice based on the collected data and evaluation results. The advice is adjusted by the emotion engine and delivered to parents in an appropriate tone.

[0705] Distribution of educational videos and exercise programs

[0706] The server also includes means for generating and delivering educational videos and exercise programs tailored to the child, allowing the child to receive individually optimized content.

[0707] Specific examples

[0708] For example, if a parent complains that their child has been having trouble concentrating on their extracurricular activities, the emotion engine will recognize the emotion as "confusion." The server will analyze the data, select appropriate learning videos and exercise programs, and provide advice such as:

[0709] "We understand your concerns about your child's inability to concentrate on their lessons. We have some new educational videos that will help your child learn while having fun, so please take a look."

[0710] Prompt Sentence Examples

[0711] User message: My child has been having trouble concentrating on his lessons lately.

[0712] Q: Please provide a detailed, emotion-based explanation of why your child is having trouble concentrating and what actions you can take to improve it.

[0713] Emotion: Confused

[0714] This system not only provides parents with the optimal learning and exercise menu for their children, but also allows them to receive emotionally sensitive advice, allowing them to raise their children with greater peace of mind.

[0715] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0716] Step 1:

[0717] Data collection

[0718] The server periodically retrieves child data (meals, sleep time, activity) from the childcare facility API. During this process, the data retrieved from the API is temporarily stored and encrypted for secure storage in MongoDB.

[0719] Input: Raw data from the childcare facility API

[0720] Output: Data stored in MongoDB in encrypted form

[0721] Step 2:

[0722] Data analysis

[0723] The server uses TensorFlow and PyTorch to analyze the data stored in MongoDB, which involves using statistical methods and machine learning algorithms to extract child characteristics from the data (e.g., sleep patterns, nutritional balance, activity levels).

[0724] Input: Data stored in MongoDB

[0725] Output: Analysis results evaluating the characteristics of each child

[0726] Step 3:

[0727] Menu generation

[0728] Based on the analysis results, the server generates learning and exercise menus appropriate for each child, which involves using a Python script to create a list of menus according to generation rules.

[0729] Input: Analysis results

[0730] Output: Learning and exercise menus appropriate for each child

[0731] Step 4:

[0732] Parental notification

[0733] The device notifies parents of the generated learning and exercise menus through a smartphone application developed using React Native, either via the app's notification function or email.

[0734] Input: Generated learning menu and exercise menu

[0735] Output: Parental notification message

[0736] Step 5:

[0737] emotion recognition

[0738] The server uses Azure Cognitive Services and IBM Watson to recognize emotions from parental feedback and inquiries, and generates responses based on the parent's emotions.

[0739] Input: Parent inquiries and feedback

[0740] Output: Recognized parent's emotion data

[0741] Step 6:

[0742] Inquiry handling and advice generation

[0743] The server generates appropriate advice based on the collected data and evaluation results in response to the received inquiry. This process involves generating responses using natural language processing (NLP) with a generative AI model.

[0744] Input: Parental inquiries, collected data, assessment results, recognized emotion data

[0745] Output: Generated advice

[0746] Step 7:

[0747] Advice Notification

[0748] The device will then notify the parent of the generated advice via the notification function within the application or email.

[0749] Input: Generated advice

[0750] Output: Parental Advisory Notice

[0751] Step 8:

[0752] Distribution of educational videos and exercise programs

[0753] The server generates educational videos and exercise programs tailored to each child and distributes them through websites and applications, adding appropriate metadata to make them easily accessible to parents and children.

[0754] Input: Generated learning videos and exercise programs

[0755] Output: Distributed learning videos and exercise programs

[0756] 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.

[0757] 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.

[0758] 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.

[0759] [Third embodiment]

[0760] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0761] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0762] 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).

[0763] 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.

[0764] 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.

[0765] 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).

[0766] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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."

[0772] The present invention provides a system that supports parents in raising their children by providing optimal learning and exercise programs for each child based on data acquired from childcare facilities. Specific embodiments of the system are described below.

[0773] System Overview

[0774] This system works in cooperation with three parties: a server, a terminal, and a user. The server is responsible for collecting, storing, and analyzing data, and generating menus and notifications, while the terminal provides an interface with childcare facilities and parents. Users (mainly parents) receive information necessary for childcare and make inquiries through the system.

[0775] Data collection and storage

[0776] The server periodically receives data from the childcare facility, such as mealtimes, sleep duration, and activity status, via an API. The collected data is categorized for each child and stored in a database. The stored data is updated daily and encrypted for security purposes.

[0777] Data analysis and characterization

[0778] The server analyzes the data stored in the database and evaluates each child's characteristics, such as sleep patterns, nutritional balance, and daily activity levels, to understand the child's health and development.

[0779] Menu generation

[0780] Based on the analysis results, the server generates learning and exercise menus tailored to each child. For example, it may design an exercise menu that focuses on children with low activity levels, and recommend an arts and crafts learning menu for children who like creative activities. The generated menus are stored in a database and are ready to be provided to parents.

[0781] Parental notification

[0782] The server notifies parents of the generated learning and exercise menus. Specifically, notifications are sent via a dedicated application or email. The notifications include details of the menus and information on how to implement them.

[0783] Responding to parental inquiries

[0784] The device provides an interface for parents to make inquiries about childcare, and parents can enter their questions using an application or a web form.

[0785] The server analyzes the received inquiries and uses generative AI to generate appropriate advice based on past data and evaluation results. The advice is then sent to parents via email or in-app notifications.

[0786] Specific examples

[0787] For example, if a child has trouble falling asleep and can only sleep for a certain amount of time, the server will analyze the data and detect irregular sleep patterns. It will then provide parents with suggestions for adjusting nap times and revising their nighttime routine. If it determines that a lack of exercise is the cause, it will suggest easy indoor exercises.

[0788] This system allows parents to receive accurate advice without being overwhelmed by daily childcare, and effectively supports their children's health and development.

[0789] The processing flow will be explained below.

[0790] Step 1: Collect and store data

[0791] The server periodically collects data such as meal contents, sleep time, and activity details from the childcare facility via an API.

[0792] Specific operation: Sends an API request to retrieve the latest data from the childcare facility's system and stores the received data in a temporary buffer.

[0793] Step 2: Classify and encrypt data

[0794] The server categorizes the data it collects by child and encrypts it before storing it in a database.

[0795] Specific operation: The data is sorted by child ID, an encryption algorithm is applied, and the data is inserted into the database.

[0796] Step 3: Preprocessing the data

[0797] The server performs pre-processing to convert the stored data into a format that is easy to analyze.

[0798] Specific operations: Impute missing values, normalize data, check for and correct data inconsistencies and errors.

[0799] Step 4: Data analysis and characterization

[0800] The server evaluates the child's characteristics based on the pre-processed data.

[0801] What it does: Uses statistical methods and machine learning algorithms to assess sleep patterns, nutritional balance, and activity levels.

[0802] Step 5: Generate the menu

[0803] Based on the analysis results, the server generates a learning menu and an exercise menu suitable for each child.

[0804] What it does: Apply rule-based algorithms and machine learning models to convert the generated menu into a format appropriate for each child.

[0805] Step 6: Prepare the menu for notifications

[0806] The server prepares to notify the parent of the generated menu.

[0807] What it does: Gets parent contact information and formats menu information into rich text and HTML.

[0808] Step 7: Menu Notifications

[0809] The server notifies the parent of the menu when it is ready.

[0810] Specific operations: Connect to the mail server or push notification server, send the prepared message, and save the sending log.

[0811] Step 8: Receiving parental inquiries

[0812] The device provides an interface where parents can input questions about childcare.

[0813] Specific operation: Prepare an inquiry form in a mobile or web app and set up an API endpoint to send user input to the server.

[0814] Step 9: Processing the inquiry and generating an answer

[0815] The server receives questions from parents, and the generative AI creates advice based on the collected data and evaluation results.

[0816] What it does: Searches for relevant historical data from a database and generates an answer using a provided natural language processing (NLP) model.

[0817] Step 10: Notification of response

[0818] The server notifies the parent of the generated advice.

[0819] Specific behavior: Sends responses to parents via email or in-app notification, and stores notification sending logs in a database.

[0820] Example 1

[0821] 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."

[0822] Effectively understanding the health and developmental status of children attending childcare facilities and providing childcare support based on that information is an important issue for parents. However, currently, data collection is often done manually, making it difficult to analyze the data and provide appropriate advice. In addition, parents are often not notified of information or their inquiries are not responded to promptly and appropriately. This can cause parents to feel anxious and worried about their children's health management and childcare.

[0823] 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.

[0824] In this invention, the server includes means for collecting data on children's dietary habits, sleep duration, and activity details obtained at the childcare facility, means for analyzing the collected data and evaluating the characteristics of each child, means for generating a learning menu and an exercise menu appropriate for each child based on the evaluation results, means for notifying parents of the generated menus, means for accepting inquiries about childcare from parents, means for generating appropriate advice in response to the accepted inquiries based on the collected data and the evaluation results, means for notifying parents of the generated advice, means for encrypting the collected data for security purposes, means for storing data classified for each child in a database, means for performing time series analysis to analyze the data, means for generating the generated exercise menu and learning menu using a machine learning algorithm, means for generating appropriate advice using a natural language processing model, and means for notifying parents via a dedicated application or email. This allows parents to accurately understand their children's health and developmental status and receive prompt and appropriate childcare support.

[0825] The "data collection means" is a means for collecting data on children's diet, sleep time, and activity details obtained at the childcare facility.

[0826] "Data analysis tools" are tools for analyzing collected data and evaluating the characteristics of individual children.

[0827] The "menu generating means" is a means for generating a learning menu and an exercise menu suitable for each child based on the evaluation results.

[0828] The "menu notification means" is a means for notifying the guardian of the generated learning menu and exercise menu.

[0829] The "inquiry reception means" is a means for receiving inquiries about childcare from parents.

[0830] The "advice generation means" is a means for generating appropriate advice in response to a received inquiry based on the collected data and evaluation results.

[0831] The "advice notification means" is a means for notifying the guardian of the generated advice.

[0832] "Encryption means" means means for encrypting collected data for security purposes.

[0833] The "database storage means" is a means for storing data classified for each individual child in a database.

[0834] The "time series analysis means" is a means for performing time series analysis to analyze data.

[0835] A "machine learning algorithm" is a method for generating exercise menus and learning menus based on machine learning.

[0836] The "natural language processing model" is a model for generating advice in natural language in response to inquiries from parents.

[0837] "Notification means" refers to a means for notifying parents of information via a dedicated application or email.

[0838] This invention is a system that supports parents in raising their children by providing optimal learning and exercise menus for each child based on data obtained from childcare facilities. This system operates in cooperation with three parties: a server, a terminal, and a user.

[0839] Data collection and storage

[0840] The server periodically receives data such as meal contents, sleep time, and activity details sent from the childcare facility via a RESTful API. A common framework (e.g., Spring Boot) is used for this API communication. The obtained data is categorized for each child and stored in a database (e.g., MySQL). The stored data is updated daily and is encrypted with AES-256 for security.

[0841] Data analysis and characterization

[0842] The server analyzes the data stored in the database using Python and Pandas. It performs time-series analysis on sleep data and evaluates nutritional balance on nutritional data. This makes it possible to understand the health and developmental status of each child. The analysis results are stored in the database.

[0843] Menu generation

[0844] Based on the analysis results, the server generates learning and exercise menus suited to each individual child. This process utilizes machine learning models using TensorFlow. For example, it generates a "simple exercise menu" for a child with a low level of physical activity, and recommends "painting and craft activities" for a child who enjoys creative activities.

[0845] Parental notification

[0846] The server notifies parents of the generated learning and exercise menus. Notification methods include email (e.g., SendGrid API) and a dedicated app (e.g., built with React Native). The notification includes details of the menu and information on how to implement it.

[0847] Responding to parental inquiries

[0848] The device provides an interface for accepting inquiries about childcare from parents. Parents can enter questions through a web form or an application (e.g., an app using the Flask framework). For example, a parent can send an inquiry about "the causes and solutions for nighttime crying."

[0849] Advice Generation and Notifications

[0850] The server analyzes the received inquiry and generates appropriate advice using a generative AI model (e.g., GPT-4) based on past data and evaluation results. The generated advice is sent to the parent via email or in-app notification. The following prompt sentences are used to generate the advice:

[0851] Example prompt sentence:

[0852] "Mr. A has trouble falling asleep and is sleeping less at night. Based on his recent sleep pattern data, please provide some advice on adjusting his nap time and reviewing his nighttime routine."

[0853] This system allows parents to receive accurate advice without being overwhelmed by daily childcare, and effectively supports their children's health and development.

[0854] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0855] Step 1:

[0856] The server periodically receives data from the childcare facility about the children's diet, sleep time, and activity via a RESTful API. A common framework (e.g., Spring Boot) is used for this API communication, and the received data is sent to the server in JSON format. The input is data from the childcare facility, and the output is the raw data received by the server. This data is categorized for each child and proceeds to the next step.

[0857] Step 2:

[0858] The server stores the retrieved data in a MySQL database. Before storing the data, each data is classified by child and encrypted using the AES-256 algorithm for security. The input is the raw data and each child's ID, and the output is the encrypted data stored in the database. This storage process is performed using an INSERT query.

[0859] Step 3:

[0860] The server analyzes the data stored in the database using Python and Pandas. For example, it performs time-series analysis on sleep data and calculates activity levels and nutritional balance. The input is data for each child extracted from the database, and the output is the analysis results. The analysis results are then stored back in the database.

[0861] Step 4:

[0862] The server uses a machine learning model (a model using TensorFlow) to evaluate the characteristics of each child based on the analysis results. It performs tasks such as classifying physical activity levels and evaluating learning characteristics. The input is the analysis results, and the output is the characteristic evaluation results. The characteristic evaluation results are also stored in a database.

[0863] Step 5:

[0864] The server generates learning and exercise menus appropriate for each child based on the results of the characteristic assessment. Generative AI models such as GPT-4 are used to create specific menus. For example, gymnastics menus are recommended for children with low physical activity levels, and craft activities are recommended for children who prefer creative activities. The input is the characteristic assessment results, and the output is the generated menu. The generated menu is stored in a database.

[0865] Step 6:

[0866] The server notifies parents of the generated learning and exercise menus. Notification methods include email (using SendGrid's API) and a dedicated app (built with React Native). The input is the generated menu and parent contact information, and the output is the notification sent to the parent.

[0867] Step 7:

[0868] The device provides an interface for accepting inquiries about childcare from parents. Parents can enter questions through a web form or an application (Flask framework). For example, a user can send an inquiry about the cause of nighttime crying and what to do about it from the application. The input is the inquiry from the parent, and the output is the query data sent to the server.

[0869] Step 8:

[0870] The server analyzes the received query using a generative AI model (GPT-4) and generates appropriate advice. The input is the query content, past data in the database, and the characteristic evaluation results, and the output is the generated advice. This advice is generated based on the following prompt:

[0871] Example prompt sentence:

[0872] "Mr. A has trouble falling asleep and is sleeping less at night. Based on his recent sleep pattern data, please provide some advice on adjusting his nap time and reviewing his nighttime routine."

[0873] Step 9:

[0874] The server sends the generated advice to the parent via email or in-app notification. The input is the generated advice and the parent's contact information, and the output is the notification sent to the parent. This allows parents to receive accurate advice.

[0875] (Application example 1)

[0876] 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."

[0877] The goal is to adequately resolve the concerns and questions parents have about childcare. Furthermore, to support the efficient management of children's health and development, it is important to provide the most appropriate learning and exercise programs for each child based on data collected from childcare facilities. Furthermore, there is a need for a system that allows parents to easily check this information and receive appropriate advice in response to inquiries.

[0878] 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.

[0879] In this invention, the server includes means for collecting data on children's dietary habits, sleep duration, and activity details obtained at the childcare facility, means for analyzing the collected data and evaluating the characteristics of each child, means for generating learning and exercise menus appropriate for each child based on the evaluation results, means for notifying parents of the generated menus, means for accepting inquiries about childcare from parents, means for generating appropriate advice in response to the accepted inquiries based on the collected data and evaluation results, means for notifying parents of the generated advice, means for parents to check and manage the generated menus and advice via a smartphone application, means for generating individual advice using a generative AI model in response to inquiries from parents, and means for generating the generated advice using a natural language processing model via prompt sentences. This allows parents to easily obtain all data and advice related to childcare and take appropriate action.

[0880] A "childcare facility" is a facility that temporarily takes care of infants and children and provides them with daily care, including meals, sleep, and play.

[0881] "Dietary content" refers to information about the foods a child ingests at the childcare facility, including their type, quantity, and nutrients.

[0882] "Sleep hours" is the total amount of time a child sleeps in the childcare facility.

[0883] "Activity details" refers to data on specific activities such as exercise, learning, and play that children engage in at the childcare facility.

[0884] "Means for collecting data" refers to a method or device for obtaining data from the childcare facility regarding dietary habits, sleep duration, and activity.

[0885] A "means for analyzing data" is a method or device that uses collected data to assess a child's health status or characteristics.

[0886] A "trait assessment tool" is a method or device for assessing the developmental or health status of an individual child based on collected data.

[0887] A "learning menu" is a combination of materials and activities designed to help children learn appropriately.

[0888] An "exercise menu" is a combination of exercises and games designed to get children moving and exercising appropriately.

[0889] "Means for notifying parents" refers to a method or device for notifying parents of the generated menu or advice.

[0890] "Means for accepting inquiries about childcare" refers to a method or device for accepting questions or inquiries from parents.

[0891] A "means for generating appropriate advice" is a method or apparatus for generating advice based on a query and using collected data and evaluation results.

[0892] "Via a smartphone application" means operating or viewing through an application running on a smartphone.

[0893] A "generative AI model" is a model that uses artificial intelligence technology to create learning menus and advice generated from data.

[0894] A "prompt sentence" is a sentence that specifically describes the question or instruction to be input into the generative AI model.

[0895] A "natural language processing model" is a set of techniques and algorithms that allow computers to understand, analyze, and generate human language.

[0896] This invention is a system that supports parents in raising their children by creating optimal learning and exercise menus for each child based on data acquired from childcare facilities. Specific embodiments of the system are described below.

[0897] System configuration

[0898] The system works in cooperation with three parties: a server, a device, and parents. The server is responsible for collecting, storing, and analyzing data, and generating menus and notifications, while the device provides an interface with childcare facilities and parents. Parents can receive information necessary for childcare and make inquiries through the system.

[0899] Data collection and storage

[0900] The server collects data sent from the childcare facility, such as meal contents, sleep time, and activity details. It uses Amazon Web Services (AWS) to periodically retrieve data via API using AWS Lambda. The collected data is stored in AWS RDS (a relational database service) and is encrypted for added security.

[0901] Data analysis and characterization

[0902] The server analyzes the data stored in the database and evaluates each child's characteristics. It uses Python, Numpy, and Pandas to analyze sleep patterns and check nutritional balance. It also uses TensorFlow to cluster children's health and developmental status using machine learning models.

[0903] Menu generation

[0904] Based on the analysis results, the server generates learning and exercise menus appropriate for each child, using TensorFlow's deep neural network (DNN) model, and stores the generated menus in Amazon RDS.

[0905] Parental notification

[0906] The server notifies parents of the generated learning and exercise menus. Push notifications are sent using AWS SNS (Simple Notification Service), and a smartphone application developed with React Native receives the notifications. The app then displays the menu details to parents.

[0907] Responding to parental inquiries

[0908] The server accepts inquiries about childcare from parents and responds. Parents input their questions through a smartphone application. The server uses a generative AI model (e.g., GPT-4) to generate appropriate advice based on past data and evaluation results. This advice is generated by a natural language processing model (e.g., GPT-4 API) through a prompt sentence and notified to the parent via AWS SNS.

[0909] Specific examples

[0910] For example, if a child has trouble falling asleep and can only sleep for a certain amount of time, the server will analyze the data and detect irregular sleep patterns. It will then provide parents with suggestions for adjusting nap times and revising their nighttime routine. If it determines that a lack of exercise is the cause, it will suggest easy indoor exercises.

[0911] Prompt Sentence Examples

[0912] Parent input: "My child has been having trouble falling asleep lately. Any advice?"

[0913] Use the following prompt: "What advice can you offer to a child who has been having trouble falling asleep recently?"

[0914] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0915] Step 1:

[0916] The server collects data from the childcare facility on children's dietary habits, sleep duration, and activity. This data is periodically sent to the server from the childcare facility's terminal via API. The input data is in JSON format and includes daily data for each child. The collected data is processed by AWS Lambda and stored in AWS RDS.

[0917] Step 2:

[0918] The server periodically analyzes the data stored in AWS RDS. It extracts data using Python scripts and preprocesses the data using Numpy and Pandas. For example, it performs data cleaning such as imputing missing values ​​and detecting outliers. The input data is the preprocessed daily data for each child, and the output data is data converted into a format suitable for analysis.

[0919] Step 3:

[0920] The server evaluates each child's characteristics based on the preprocessed data. It uses a machine learning model using TensorFlow to cluster sleep patterns and activity levels. The input data is the preprocessed data for each child, and the output data is the results of each child's characteristic evaluation. Specific operations for characteristic evaluation include running a clustering algorithm and calculating a score for each characteristic.

[0921] Step 4:

[0922] The server generates learning and exercise menus appropriate for each child based on the evaluation results. This is done using TensorFlow DNN. For example, it might design a focused exercise menu for a child with low activity levels, and recommend an arts and crafts learning menu for a child who enjoys creative activities. The input data is the characteristic evaluation results, and the output data is the learning and exercise menu appropriate for each child.

[0923] Step 5:

[0924] The server notifies parents of the generated learning and exercise menus. Specifically, it uses AWS SNS to send push notifications. The input data is the generated menu, and the output data is a notification sent to the parent's smartphone. The notification contains details about the menu and information on how to implement it.

[0925] Step 6:

[0926] Parents send inquiries about childcare to the server via a smartphone application. The input data is the question or consultation from the parent, and the output data is the inquiry data sent to the server. Specifically, the question is entered into the inquiry form within the app and sent.

[0927] Step 7:

[0928] The server receives inquiries from parents and generates appropriate advice using a generative AI model (GPT-4) based on previous data and evaluation results. It calls the GPT-4 API using a prompt sentence to generate appropriate advice. The input data is the parent's question and related child data, and the output data is the generated advice.

[0929] Step 8:

[0930] The server notifies the parent of the generated advice. The advice is sent to the parent's smartphone via AWS SNS. The input data is the generated advice, and the output data is the notification sent to the parent's smartphone. Specifically, the generated advice is displayed as an in-app notification.

[0931] 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.

[0932] This invention combines a system that provides optimal learning and exercise menus for each child based on data acquired from childcare facilities and supports parents in raising their children with an emotion engine. Specific embodiments of the system are described below.

[0933] System Overview

[0934] This system works in cooperation with four parties: a server, a device, a user, and an emotion engine. The server is responsible for collecting, storing, and analyzing data, and generating menus and notifications, while the device provides an interface with childcare facilities and parents. Users (mainly parents) receive information necessary for childcare through the system and make inquiries. The emotion engine recognizes emotions from the user's input and actions and reflects them in the advice it provides.

[0935] Data collection and storage

[0936] The server periodically receives data from the childcare facility via API, including meal contents, sleep time, and activity details. The data is categorized by child, encrypted, and stored in a database.

[0937] Data analysis and characterization

[0938] The server analyzes the stored data and evaluates each child's characteristics, such as sleep patterns, nutritional balance, and activity levels, using statistical methods and machine learning algorithms to understand the child's health and developmental status.

[0939] Menu generation

[0940] Based on the analysis results, the server generates a learning and exercise menu suited to each child. The generated menu, which is tailored to each child's individual needs, is stored in a database and later provided to parents.

[0941] Parental Notification and Emotion Recognition

[0942] The device provides an interface for notifying parents of the generated learning and exercise menus. Notifications are sent via a dedicated application or email. The emotion engine recognizes emotions from parents' inquiries and daily interactions and adjusts the content and tone of the advice accordingly.

[0943] Responding to parental inquiries and reflecting their feelings

[0944] The device provides an interface for parents to make inquiries about childcare, and parents can enter their questions using an application or a web form.

[0945] The server analyzes the received inquiry and uses generative AI to generate advice based on past data and evaluation results. The emotion engine identifies emotions from the parent's input and generates advice with an appropriate tone and content. The generated advice is sent to the parent via email or in-app notification.

[0946] Specific examples

[0947] For example, if a parent sounds tired and sends a message saying, "My child has been having trouble falling asleep at night lately," the server analyzes the data and considers specific measures to improve the child's sleep pattern based on the analysis. The emotion engine detects "fatigue" in the parent's message and adjusts the tone of the advice to be gentle and empathetic. As a result, advice such as "We understand your concerns about your child's nighttime sleepiness. We'll show you how to adjust nap times and how to relax before bed" is generated and sent to the parent.

[0948] This system allows parents to receive accurate advice without feeling overwhelmed by the daily tasks of childcare, and by receiving support that is sensitive to their emotions, they can feel even more secure in raising their children.

[0949] The processing flow will be explained below.

[0950] Step 1: Collect and store data

[0951] The server periodically collects data such as meal contents, sleep time, and activity details from the childcare facility via an API.

[0952] What it does: Sends an API request to receive the latest data from the childcare system, stores it in a temporary buffer, categorizes it by child, and encrypts it before inserting it into the database.

[0953] Step 2: Preprocessing the data

[0954] The server performs pre-processing to convert the stored data into a format that is easy to analyze.

[0955] Specific actions: Impute missing values, normalize data, check for and correct inconsistencies and errors.

[0956] Step 3: Data analysis and characterization

[0957] The server evaluates the child's characteristics based on the pre-processed data.

[0958] What it does: Uses statistical methods and machine learning algorithms to analyze sleep patterns, nutritional balance, and activity levels to assess a child's health and development.

[0959] Step 4: Generate the menu

[0960] Based on the analysis results, the server generates a learning menu and an exercise menu suitable for each child.

[0961] What it does: It applies rule-based algorithms and machine learning models to design optimal menus for each individual child and stores them in a database.

[0962] Step 5: Prepare the menu for notifications

[0963] The server prepares to notify the parent of the generated menu.

[0964] What it does: Gets parent contact information and formats menu information into rich text and HTML.

[0965] Step 6: Menu Notifications

[0966] The server notifies the parent of the menu when it is ready.

[0967] Specific operations: Connect to the mail server or push notification server to send the message. Save the sending log for later tracking.

[0968] Step 7: Receiving parental inquiries

[0969] The device provides an interface where parents can input questions about childcare.

[0970] Specific operation: Prepare an inquiry form within the mobile app or web app and set up an API endpoint that sends user input to the server.

[0971] Step 8: Parsing the query

[0972] The server receives questions from parents and searches the database for relevant past data.

[0973] Specific operation: Analyzes the inquiry content and generates appropriate advice based on past data and evaluation results.

[0974] Step 9: Recognize emotions

[0975] The server uses an emotion engine to recognize emotions from the parent's inquiry.

[0976] What it does: Analyzes text data using a natural language processing (NLP) model to identify the parent's emotional state (e.g., fatigue, anxiety, joy).

[0977] Step 10: Adjusting Advice

[0978] The server adjusts the content and tone of advice based on the emotional state recognized by the emotion engine.

[0979] Specific behavior: Generate appropriate advice based on the emotional state, and use gentle and empathetic language.

[0980] Step 11: Advice Notification

[0981] The server notifies the parent of the generated advice.

[0982] Specific behavior: Sends advice to parents via email and in-app notifications, and stores the sending log in a database for future reference.

[0983] Example 2

[0984] 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."

[0985] In modern society, parents have limited time to devote to childcare and often rely on childcare facilities. As a result, they face challenges in obtaining sufficient information about their children's activities and health at childcare facilities, making it difficult for them to receive appropriate advice. Furthermore, uniform advice may not adequately reflect each child's individual characteristics, which can cause anxiety and stress for parents. Furthermore, a lack of consideration for parents' feelings can increase the burden of childcare.

[0986] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0987] In this invention, the server includes: means for collecting data on children's dietary habits, sleep duration, and activity details obtained at the childcare facility; means for classifying, encrypting, and storing the collected data in a database; means for analyzing the stored data and evaluating each child's characteristics; and means for generating learning and exercise menus appropriate for each child based on the evaluation results. The server also includes means for identifying the parent's emotions using an emotion engine and adjusting the content and tone of advice, and means for notifying the parent of the generated advice. This allows parents to receive appropriate advice tailored to each child's characteristics, and by receiving responses that are sensitive to their emotions, parents can feel more secure about raising their children.

[0988] A "childcare facility" is a place where children stay for a certain period of time and live and learn under the guidance of caregivers.

[0989] "Children" refers to infants and young children in childcare facilities from whom data such as dietary habits, sleep duration, and activity details are collected.

[0990] "Dietary content" refers to information about the types and amounts of food and beverages consumed by children at childcare facilities.

[0991] "Sleep time" is the total amount of time including the start and end times of a child's sleep.

[0992] "Activity details" is information that indicates details of the activities that children engage in at the childcare facility, such as playing, studying, and exercising.

[0993] "Data collection tools" refer to the interfaces and processes used to obtain data from childcare facilities, such as children's diet, sleep, and activity.

[0994] "Data classification tools" refers to the algorithms or processing tools used to organize and classify the collected data for each child.

[0995] "Encryption methods" refers to the techniques and processes used to encrypt data to ensure its security.

[0996] A "database" is a storage device or system for storing collected data or generated information.

[0997] "Data analysis procedures" refers to the process of using stored data to run statistical methods and machine learning algorithms to assess children's characteristics.

[0998] "Characteristic assessment" refers to information about a child's health and developmental status obtained through data analysis tools.

[0999] A "learning menu" is a learning plan designed based on a child's characteristics to enhance their knowledge and skills.

[1000] An "exercise menu" is an exercise plan designed based on a child's characteristics to improve their physical strength and athletic ability.

[1001] The "menu generation means" refers to an algorithm or process for automatically generating learning menus and exercise menus based on characteristic evaluations.

[1002] "Parental notification means" refers to an interface or process for communicating the generated learning menu, exercise menu, or advice to parents.

[1003] "Inquiry reception means" refers to the interface or process for receiving inquiries about childcare from parents.

[1004] "Advice generation means" refers to the generation AI or process that provides appropriate advice in response to received inquiries based on collected data and evaluation results.

[1005] An "emotion engine" is an algorithm or technology that identifies a parent's emotions and adjusts the content and tone of advice.

[1006] This invention is a system that supports parents in raising their children by providing optimal learning and exercise menus for each child based on data obtained from childcare facilities. Furthermore, the system incorporates an emotion engine that can recognize the emotions of parents and reflect them in the advice it provides.

[1007] System Components

[1008] This system consists of four main components: a server, a terminal, a user (guardian), and an emotion engine.

[1009] Data collection overview

[1010] The server periodically collects data from the childcare facility via API, such as what children eat, how much they sleep, and what their activities are. This data collection uses a data acquisition API that connects to the childcare facility's digital system. The collected data is categorized for each child, encrypted, and stored in a database. This encryption ensures the security of the data.

[1011] Data analysis and characterization process

[1012] The server analyzes the stored data using statistical methods and machine learning algorithms. This allows the system to evaluate a child's characteristics, such as sleep patterns, nutritional balance, and activity level. For example, a child's average sleep duration and activity trends can be analyzed based on their data from the past month. This can also help understand the child's health and developmental status.

[1013] Menu generation

[1014] The server generates learning and exercise menus suited to each child based on the analysis results. The generated menus are tailored to each child's individual needs and are stored in a database. These menus can then be used as information to provide to parents. For example, a menu can be created that recommends playing with educational blocks in the morning and taking a walk outside in the afternoon for a certain child.

[1015] Parental Notification and Emotion Recognition

[1016] The device provides an interface for notifying parents of the generated learning and exercise menus. This notification is done via a dedicated application or email. In addition, an emotion engine recognizes emotions from parents' inquiries and daily conversations and reflects them in the notification content.

[1017] Inquiry response

[1018] The device provides an interface for accepting parenting-related inquiries from parents. Parents can enter their questions using an application or web form. The server analyzes the received inquiries and uses generative AI to create advice based on past data and evaluation results. An emotion engine identifies the parent's emotions and generates advice with an appropriate tone and content. The generated advice is sent to the parent via email or in-app notification.

[1019] Specific examples

[1020] For example, if a parent sends an inquiry saying, "My child has been having trouble falling asleep at night lately," the server analyzes the data and considers specific improvement measures based on the analysis of the child's sleep patterns. The emotion engine detects "fatigue" from the parent's message and adjusts the tone of the advice to be gentle and empathetic. As a result, advice such as "We understand your concerns about your child's nighttime sleepiness. We'll show you how to adjust nap times and how to relax before bed" is generated and sent to the parent.

[1021] In this way, the system allows parents to obtain the information they need for childcare in a timely manner, and by providing emotionally sensitive support, it can increase their sense of security when raising their children.

[1022] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1023] System program processing steps

[1024] Step 1:

[1025] The server periodically collects data on children's diet, sleep, and activity from the childcare facility via API. The input is the data sent from the childcare facility. Specifically, the server sends an API request and receives the data returned from the childcare facility. The output is the retrieved raw data.

[1026] Step 2:

[1027] The server categorizes the collected data by child, encrypts it, and stores it in a database. The input is the raw data obtained in step 1. Specifically, the server tags the data by child and encrypts the data using an encryption algorithm. The output is the encrypted records in the database.

[1028] Step 3:

[1029] The server retrieves data for each child from the database and analyzes it using statistical methods and machine learning algorithms. The input is encrypted data stored in the database. Specifically, the server decrypts the data and feeds it into the machine learning model. The output is an assessment result for each child, including characteristics such as sleep patterns, nutritional balance, and activity level.

[1030] Step 4:

[1031] The server generates learning and exercise menus appropriate for each child based on the characteristic evaluation. The input is the evaluation results obtained in step 3. Specifically, the server executes an algorithm to automatically generate the optimal menu based on the evaluation results. The output is the generated learning and exercise menus.

[1032] Step 5:

[1033] The device notifies the guardian of the generated learning and exercise menus. The input is the menu generated in step 4. Specifically, the device sends a notification to the guardian via a dedicated application or email. The output is a notification confirmed by the guardian.

[1034] Step 6:

[1035] The device accepts inquiries about childcare from parents. The input is a question sent by the parent through an application or a web form. Specifically, the device transfers the inquiry to the server. The output is the accepted inquiry data.

[1036] Step 7:

[1037] The server analyzes the received inquiry and creates appropriate advice using a generative AI model based on the collected data and evaluation results. The input is the inquiry data received in step 6 and the evaluation results in the database. Specifically, the server inputs prompt data into the generative AI model and generates advice content. The output is the created advice.

[1038] Step 8:

[1039] The emotion engine recognizes emotions from parental inquiries and daily interactions and adjusts the content and tone of advice. The input is inquiry data from parents. Specifically, the emotion engine analyzes the input text to identify emotions and adjusts the tone of advice. The output is advice that takes emotions into consideration.

[1040] Step 9:

[1041] The server notifies the guardian of the advice generated. The input is the advice generated in step 7 and step 8. Specifically, the server sends the advice content to the terminal, and the terminal notifies the guardian. The output is the advice sent to the guardian.

[1042] This allows the system to consistently collect data from childcare facilities and provide optimal advice to parents.

[1043] (Application example 2)

[1044] 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."

[1045] In modern childcare, personalized learning and exercise programs are important to support children's growth and development. However, parents often find it difficult to find the optimal educational and exercise programs for their children due to their busy schedules, and they often lack emotional support. Current systems lack personalized advice and emotional support for parents, leaving parents with little relief from the burden of childcare and making it difficult to care for their children with peace of mind.

[1046] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data acquired at the childcare facility, means for analyzing the collected data and evaluating the characteristics of each child, means for generating a learning menu and an exercise menu appropriate for each child based on the evaluation results, means for notifying the guardian of the generated menu, means for accepting inquiries about childcare from the guardian, means for generating appropriate advice based on the collected data and the evaluation results in response to the accepted inquiries, means for notifying the guardian of the generated advice, means including an emotion engine for recognizing the guardian's emotions and adjusting the tone and content of the advice, and means for delivering individual learning videos and exercise programs. This not only allows guardians to receive the optimal learning and exercise menu for their children but also emotionally sensitive advice, allowing them to raise their children with greater peace of mind.

[1047] A "childcare facility" is a specialized facility for the education and care of children.

[1048] "Data" refers to information such as what a child eats, how much they sleep, and what their activities are.

[1049] "Means of collection" refers to the functions and devices used to obtain data from childcare facilities and store it on a server.

[1050] "Means for analysis" refers to functions and devices for analyzing collected data using statistical methods and machine learning algorithms.

[1051] "Assessment means" refers to the functions or devices for assessing the characteristics of individual children based on the results of the analysis.

[1052] "Generating means" refers to a function or device for creating a learning menu and an exercise menu based on the evaluation results.

[1053] "Means of notification" refers to the functions and devices used to communicate the generated menus and advice to parents.

[1054] "Means for accepting inquiries" refers to functions and devices for receiving questions and opinions from parents.

[1055] The "means for generating advice" refers to a function or device for generating an appropriate answer to a received inquiry based on collected data and evaluation results.

[1056] An "emotion engine" refers to a function or device that recognizes parents' emotions and appropriately adjusts the content and tone of advice.

[1057] "Educational videos" are video content intended for the education of children.

[1058] An "exercise program" is a set of exercises or activity plans designed to promote physical activity in children.

[1059] "Means of distribution" refers to the functions and devices used to provide educational videos and exercise programs to parents and children.

[1060] System Overview

[1061] This invention is a system that supports parents in raising their children by providing optimal learning and exercise menus for each child based on data on the children obtained from childcare facilities. This system works in cooperation with four parties: a server, a terminal, a user (parent), and an emotion engine.

[1062] Data collection and storage

[1063] The server periodically retrieves the necessary data from the childcare facility. Data such as meal contents, sleep time, and activity details are automatically retrieved using the childcare facility's API. The retrieved data is categorized by child, encrypted, and stored in MongoDB.

[1064] Data analysis and characterization

[1065] The server analyzes the stored data using TensorFlow and PyTorch to evaluate each child's characteristics, including sleep patterns, nutritional balance, and activity level, providing a detailed understanding of the child's health and development.

[1066] Menu generation

[1067] Based on the analysis results, the server generates learning and exercise menus appropriate for each child, which are then sent to parents via a smartphone application developed using React Native.

[1068] Parental Notification and Emotion Recognition

[1069] The device provides an interface for parents to receive the generated learning and exercise recommendations. Notifications are sent via in-app notifications or email. At the same time, Azure Cognitive Services and IBM Watson are used to recognize emotions, and the content and tone of the advice is adjusted based on the parent's emotions.

[1070] Responding to parental inquiries and reflecting their feelings

[1071] Users (parents) can make inquiries about childcare through the application or web form. The server accepts these inquiries and generates appropriate advice based on the collected data and evaluation results. The advice is adjusted by the emotion engine and delivered to parents in an appropriate tone.

[1072] Distribution of educational videos and exercise programs

[1073] The server also includes means for generating and delivering educational videos and exercise programs tailored to the child, allowing the child to receive individually optimized content.

[1074] Specific examples

[1075] For example, if a parent complains that their child has been having trouble concentrating on their extracurricular activities, the emotion engine will recognize the emotion as "confusion." The server will analyze the data, select appropriate learning videos and exercise programs, and provide advice such as:

[1076] "We understand your concerns about your child's inability to concentrate on their lessons. We have some new educational videos that will help your child learn while having fun, so please take a look."

[1077] Prompt Sentence Examples

[1078] User message: My child has been having trouble concentrating on his lessons lately.

[1079] Q: Please provide a detailed, emotion-based explanation of why your child is having trouble concentrating and what actions you can take to improve it.

[1080] Emotion: Confused

[1081] This system not only provides parents with the optimal learning and exercise menu for their children, but also allows them to receive emotionally sensitive advice, allowing them to raise their children with greater peace of mind.

[1082] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1083] Step 1:

[1084] Data collection

[1085] The server periodically retrieves child data (meals, sleep time, activity) from the childcare facility API. During this process, the data retrieved from the API is temporarily stored and encrypted for secure storage in MongoDB.

[1086] Input: Raw data from the childcare facility API

[1087] Output: Data stored in MongoDB in encrypted form

[1088] Step 2:

[1089] Data analysis

[1090] The server uses TensorFlow and PyTorch to analyze the data stored in MongoDB, which involves using statistical methods and machine learning algorithms to extract child characteristics from the data (e.g., sleep patterns, nutritional balance, activity levels).

[1091] Input: Data stored in MongoDB

[1092] Output: Analysis results evaluating the characteristics of each child

[1093] Step 3:

[1094] Menu generation

[1095] Based on the analysis results, the server generates learning and exercise menus appropriate for each child, which involves using a Python script to create a list of menus according to generation rules.

[1096] Input: Analysis results

[1097] Output: Learning and exercise menus appropriate for each child

[1098] Step 4:

[1099] Parental notification

[1100] The device notifies parents of the generated learning and exercise menus through a smartphone application developed using React Native, either via the app's notification function or email.

[1101] Input: Generated learning menu and exercise menu

[1102] Output: Parental notification message

[1103] Step 5:

[1104] emotion recognition

[1105] The server uses Azure Cognitive Services and IBM Watson to recognize emotions from parental feedback and inquiries, and generates responses based on the parent's emotions.

[1106] Input: Parent inquiries and feedback

[1107] Output: Recognized parent's emotion data

[1108] Step 6:

[1109] Inquiry handling and advice generation

[1110] The server generates appropriate advice based on the collected data and evaluation results in response to the received inquiry. This process involves generating responses using natural language processing (NLP) with a generative AI model.

[1111] Input: Parental inquiries, collected data, assessment results, recognized emotion data

[1112] Output: Generated advice

[1113] Step 7:

[1114] Advice Notification

[1115] The device will then notify the parent of the generated advice via the notification function within the application or email.

[1116] Input: Generated advice

[1117] Output: Parental Advisory Notice

[1118] Step 8:

[1119] Distribution of educational videos and exercise programs

[1120] The server generates educational videos and exercise programs tailored to each child and distributes them through websites and applications, adding appropriate metadata to make them easily accessible to parents and children.

[1121] Input: Generated learning videos and exercise programs

[1122] Output: Distributed learning videos and exercise programs

[1123] 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.

[1124] 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.

[1125] 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.

[1126] [Fourth embodiment]

[1127] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1128] 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.

[1129] 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).

[1130] 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.

[1131] 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.

[1132] 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).

[1133] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1134] 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.

[1135] 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.

[1136] 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.

[1137] 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.

[1138] 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.

[1139] 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."

[1140] The present invention provides a system that supports parents in raising their children by providing optimal learning and exercise programs for each child based on data acquired from childcare facilities. Specific embodiments of the system are described below.

[1141] System Overview

[1142] This system works in cooperation with three parties: a server, a terminal, and a user. The server is responsible for collecting, storing, and analyzing data, and generating menus and notifications, while the terminal provides an interface with childcare facilities and parents. Users (mainly parents) receive information necessary for childcare and make inquiries through the system.

[1143] Data collection and storage

[1144] The server periodically receives data from the childcare facility, such as mealtimes, sleep duration, and activity status, via an API. The collected data is categorized for each child and stored in a database. The stored data is updated daily and encrypted for security purposes.

[1145] Data analysis and characterization

[1146] The server analyzes the data stored in the database and evaluates each child's characteristics, such as sleep patterns, nutritional balance, and daily activity levels, to understand the child's health and development.

[1147] Menu generation

[1148] Based on the analysis results, the server generates learning and exercise menus tailored to each child. For example, it may design an exercise menu that focuses on children with low activity levels, and recommend an arts and crafts learning menu for children who like creative activities. The generated menus are stored in a database and are ready to be provided to parents.

[1149] Parental notification

[1150] The server notifies parents of the generated learning and exercise menus. Specifically, notifications are sent via a dedicated application or email. The notifications include details of the menus and information on how to implement them.

[1151] Responding to parental inquiries

[1152] The device provides an interface for parents to make inquiries about childcare, and parents can enter their questions using an application or a web form.

[1153] The server analyzes the received inquiries and uses generative AI to generate appropriate advice based on past data and evaluation results. The advice is then sent to parents via email or in-app notifications.

[1154] Specific examples

[1155] For example, if a child has trouble falling asleep and can only sleep for a certain amount of time, the server will analyze the data and detect irregular sleep patterns. It will then provide parents with suggestions for adjusting nap times and revising their nighttime routine. If it determines that a lack of exercise is the cause, it will suggest easy indoor exercises.

[1156] This system allows parents to receive accurate advice without being overwhelmed by daily childcare, and effectively supports their children's health and development.

[1157] The processing flow will be explained below.

[1158] Step 1: Collect and store data

[1159] The server periodically collects data such as meal contents, sleep time, and activity details from the childcare facility via an API.

[1160] Specific operation: Sends an API request to retrieve the latest data from the childcare facility's system and stores the received data in a temporary buffer.

[1161] Step 2: Classify and encrypt data

[1162] The server categorizes the data it collects by child and encrypts it before storing it in a database.

[1163] Specific operation: The data is sorted by child ID, an encryption algorithm is applied, and the data is inserted into the database.

[1164] Step 3: Preprocessing the data

[1165] The server performs pre-processing to convert the stored data into a format that is easy to analyze.

[1166] Specific operations: Impute missing values, normalize data, check for and correct data inconsistencies and errors.

[1167] Step 4: Data analysis and characterization

[1168] The server evaluates the child's characteristics based on the pre-processed data.

[1169] What it does: Uses statistical methods and machine learning algorithms to assess sleep patterns, nutritional balance, and activity levels.

[1170] Step 5: Generate the menu

[1171] Based on the analysis results, the server generates a learning menu and an exercise menu suitable for each child.

[1172] What it does: Apply rule-based algorithms and machine learning models to convert the generated menu into a format appropriate for each child.

[1173] Step 6: Prepare the menu for notifications

[1174] The server prepares to notify the parent of the generated menu.

[1175] What it does: Gets parent contact information and formats menu information into rich text and HTML.

[1176] Step 7: Menu Notifications

[1177] The server notifies the parent of the menu when it is ready.

[1178] Specific operations: Connect to the mail server or push notification server, send the prepared message, and save the sending log.

[1179] Step 8: Receiving parental inquiries

[1180] The device provides an interface where parents can input questions about childcare.

[1181] Specific operation: Prepare an inquiry form in a mobile or web app and set up an API endpoint to send user input to the server.

[1182] Step 9: Processing the inquiry and generating an answer

[1183] The server receives questions from parents, and the generative AI creates advice based on the collected data and evaluation results.

[1184] What it does: Searches for relevant historical data from a database and generates an answer using a provided natural language processing (NLP) model.

[1185] Step 10: Notification of response

[1186] The server notifies the parent of the generated advice.

[1187] Specific behavior: Sends responses to parents via email or in-app notification, and stores notification sending logs in a database.

[1188] Example 1

[1189] 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."

[1190] Effectively understanding the health and developmental status of children attending childcare facilities and providing childcare support based on that information is an important issue for parents. However, currently, data collection is often done manually, making it difficult to analyze the data and provide appropriate advice. In addition, parents are often not notified of information or their inquiries are not responded to promptly and appropriately. This can cause parents to feel anxious and worried about their children's health management and childcare.

[1191] 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.

[1192] In this invention, the server includes means for collecting data on children's dietary habits, sleep duration, and activity details obtained at the childcare facility, means for analyzing the collected data and evaluating the characteristics of each child, means for generating a learning menu and an exercise menu appropriate for each child based on the evaluation results, means for notifying parents of the generated menus, means for accepting inquiries about childcare from parents, means for generating appropriate advice in response to the accepted inquiries based on the collected data and the evaluation results, means for notifying parents of the generated advice, means for encrypting the collected data for security purposes, means for storing data classified for each child in a database, means for performing time series analysis to analyze the data, means for generating the generated exercise menu and learning menu using a machine learning algorithm, means for generating appropriate advice using a natural language processing model, and means for notifying parents via a dedicated application or email. This allows parents to accurately understand their children's health and developmental status and receive prompt and appropriate childcare support.

[1193] The "data collection means" is a means for collecting data on children's diet, sleep time, and activity details obtained at the childcare facility.

[1194] "Data analysis tools" are tools for analyzing collected data and evaluating the characteristics of individual children.

[1195] The "menu generating means" is a means for generating a learning menu and an exercise menu suitable for each child based on the evaluation results.

[1196] The "menu notification means" is a means for notifying the guardian of the generated learning menu and exercise menu.

[1197] The "inquiry reception means" is a means for receiving inquiries about childcare from parents.

[1198] The "advice generation means" is a means for generating appropriate advice in response to a received inquiry based on the collected data and evaluation results.

[1199] The "advice notification means" is a means for notifying the guardian of the generated advice.

[1200] "Encryption means" means means for encrypting collected data for security purposes.

[1201] The "database storage means" is a means for storing data classified for each individual child in a database.

[1202] The "time series analysis means" is a means for performing time series analysis to analyze data.

[1203] A "machine learning algorithm" is a method for generating exercise menus and learning menus based on machine learning.

[1204] The "natural language processing model" is a model for generating advice in natural language in response to inquiries from parents.

[1205] "Notification means" refers to a means for notifying parents of information via a dedicated application or email.

[1206] This invention is a system that supports parents in raising their children by providing optimal learning and exercise menus for each child based on data obtained from childcare facilities. This system operates in cooperation with three parties: a server, a terminal, and a user.

[1207] Data collection and storage

[1208] The server periodically receives data such as meal contents, sleep time, and activity details sent from the childcare facility via a RESTful API. A common framework (e.g., Spring Boot) is used for this API communication. The obtained data is categorized for each child and stored in a database (e.g., MySQL). The stored data is updated daily and is encrypted with AES-256 for security.

[1209] Data analysis and characterization

[1210] The server analyzes the data stored in the database using Python and Pandas. It performs time-series analysis on sleep data and evaluates nutritional balance on nutritional data. This makes it possible to understand the health and developmental status of each child. The analysis results are stored in the database.

[1211] Menu generation

[1212] Based on the analysis results, the server generates learning and exercise menus suited to each individual child. This process utilizes machine learning models using TensorFlow. For example, it generates a "simple exercise menu" for a child with a low level of physical activity, and recommends "painting and craft activities" for a child who enjoys creative activities.

[1213] Parental notification

[1214] The server notifies parents of the generated learning and exercise menus. Notification methods include email (e.g., SendGrid API) and a dedicated app (e.g., built with React Native). The notification includes details of the menu and information on how to implement it.

[1215] Responding to parental inquiries

[1216] The device provides an interface for accepting inquiries about childcare from parents. Parents can enter questions through a web form or an application (e.g., an app using the Flask framework). For example, a parent can send an inquiry about "the causes and solutions for nighttime crying."

[1217] Advice Generation and Notifications

[1218] The server analyzes the received inquiry and generates appropriate advice using a generative AI model (e.g., GPT-4) based on past data and evaluation results. The generated advice is sent to the parent via email or in-app notification. The following prompt sentences are used to generate the advice:

[1219] Example prompt sentence:

[1220] "Mr. A has trouble falling asleep and is sleeping less at night. Based on his recent sleep pattern data, please provide some advice on adjusting his nap time and reviewing his nighttime routine."

[1221] This system allows parents to receive accurate advice without being overwhelmed by daily childcare, and effectively supports their children's health and development.

[1222] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1223] Step 1:

[1224] The server periodically receives data from the childcare facility about the children's diet, sleep time, and activity via a RESTful API. A common framework (e.g., Spring Boot) is used for this API communication, and the received data is sent to the server in JSON format. The input is data from the childcare facility, and the output is the raw data received by the server. This data is categorized for each child and proceeds to the next step.

[1225] Step 2:

[1226] The server stores the retrieved data in a MySQL database. Before storing the data, each data is classified by child and encrypted using the AES-256 algorithm for security. The input is the raw data and each child's ID, and the output is the encrypted data stored in the database. This storage process is performed using an INSERT query.

[1227] Step 3:

[1228] The server analyzes the data stored in the database using Python and Pandas. For example, it performs time-series analysis on sleep data and calculates activity levels and nutritional balance. The input is data for each child extracted from the database, and the output is the analysis results. The analysis results are then stored back in the database.

[1229] Step 4:

[1230] The server uses a machine learning model (a model using TensorFlow) to evaluate the characteristics of each child based on the analysis results. It performs tasks such as classifying physical activity levels and evaluating learning characteristics. The input is the analysis results, and the output is the characteristic evaluation results. The characteristic evaluation results are also stored in a database.

[1231] Step 5:

[1232] The server generates learning and exercise menus appropriate for each child based on the results of the characteristic assessment. Generative AI models such as GPT-4 are used to create specific menus. For example, gymnastics menus are recommended for children with low physical activity levels, and craft activities are recommended for children who prefer creative activities. The input is the characteristic assessment results, and the output is the generated menu. The generated menu is stored in a database.

[1233] Step 6:

[1234] The server notifies parents of the generated learning and exercise menus. Notification methods include email (using SendGrid's API) and a dedicated app (built with React Native). The input is the generated menu and parent contact information, and the output is the notification sent to the parent.

[1235] Step 7:

[1236] The device provides an interface for accepting inquiries about childcare from parents. Parents can enter questions through a web form or an application (Flask framework). For example, a user can send an inquiry about the cause of nighttime crying and what to do about it from the application. The input is the inquiry from the parent, and the output is the query data sent to the server.

[1237] Step 8:

[1238] The server analyzes the received query using a generative AI model (GPT-4) and generates appropriate advice. The input is the query content, past data in the database, and the characteristic evaluation results, and the output is the generated advice. This advice is generated based on the following prompt:

[1239] Example prompt sentence:

[1240] "Mr. A has trouble falling asleep and is sleeping less at night. Based on his recent sleep pattern data, please provide some advice on adjusting his nap time and reviewing his nighttime routine."

[1241] Step 9:

[1242] The server sends the generated advice to the parent via email or in-app notification. The input is the generated advice and the parent's contact information, and the output is the notification sent to the parent. This allows parents to receive accurate advice.

[1243] (Application example 1)

[1244] 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."

[1245] The goal is to adequately resolve the concerns and questions parents have about childcare. Furthermore, to support the efficient management of children's health and development, it is important to provide the most appropriate learning and exercise programs for each child based on data collected from childcare facilities. Furthermore, there is a need for a system that allows parents to easily check this information and receive appropriate advice in response to inquiries.

[1246] 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.

[1247] In this invention, the server includes means for collecting data on children's dietary habits, sleep duration, and activity details obtained at the childcare facility, means for analyzing the collected data and evaluating the characteristics of each child, means for generating learning and exercise menus appropriate for each child based on the evaluation results, means for notifying parents of the generated menus, means for accepting inquiries about childcare from parents, means for generating appropriate advice in response to the accepted inquiries based on the collected data and evaluation results, means for notifying parents of the generated advice, means for parents to check and manage the generated menus and advice via a smartphone application, means for generating individual advice using a generative AI model in response to inquiries from parents, and means for generating the generated advice using a natural language processing model via prompt sentences. This allows parents to easily obtain all data and advice related to childcare and take appropriate action.

[1248] A "childcare facility" is a facility that temporarily takes care of infants and children and provides them with daily care, including meals, sleep, and play.

[1249] "Dietary content" refers to information about the foods a child ingests at the childcare facility, including their type, quantity, and nutrients.

[1250] "Sleep hours" is the total amount of time a child sleeps in the childcare facility.

[1251] "Activity details" refers to data on specific activities such as exercise, learning, and play that children engage in at the childcare facility.

[1252] "Means for collecting data" refers to a method or device for obtaining data from the childcare facility regarding dietary habits, sleep duration, and activity.

[1253] A "means for analyzing data" is a method or device that uses collected data to assess a child's health status or characteristics.

[1254] A "trait assessment tool" is a method or device for assessing the developmental or health status of an individual child based on collected data.

[1255] A "learning menu" is a combination of materials and activities designed to help children learn appropriately.

[1256] An "exercise menu" is a combination of exercises and games designed to get children moving and exercising appropriately.

[1257] "Means for notifying parents" refers to a method or device for notifying parents of the generated menu or advice.

[1258] "Means for accepting inquiries about childcare" refers to a method or device for accepting questions or inquiries from parents.

[1259] A "means for generating appropriate advice" is a method or apparatus for generating advice based on a query and using collected data and evaluation results.

[1260] "Via a smartphone application" means operating or viewing through an application running on a smartphone.

[1261] A "generative AI model" is a model that uses artificial intelligence technology to create learning menus and advice generated from data.

[1262] A "prompt sentence" is a sentence that specifically describes the question or instruction to be input into the generative AI model.

[1263] A "natural language processing model" is a set of techniques and algorithms that allow computers to understand, analyze, and generate human language.

[1264] This invention is a system that supports parents in raising their children by creating optimal learning and exercise menus for each child based on data acquired from childcare facilities. Specific embodiments of the system are described below.

[1265] System configuration

[1266] The system works in cooperation with three parties: a server, a device, and parents. The server is responsible for collecting, storing, and analyzing data, and generating menus and notifications, while the device provides an interface with childcare facilities and parents. Parents can receive information necessary for childcare and make inquiries through the system.

[1267] Data collection and storage

[1268] The server collects data sent from the childcare facility, such as meal contents, sleep time, and activity details. It uses Amazon Web Services (AWS) to periodically retrieve data via API using AWS Lambda. The collected data is stored in AWS RDS (a relational database service) and is encrypted for added security.

[1269] Data analysis and characterization

[1270] The server analyzes the data stored in the database and evaluates each child's characteristics. It uses Python, Numpy, and Pandas to analyze sleep patterns and check nutritional balance. It also uses TensorFlow to cluster children's health and developmental status using machine learning models.

[1271] Menu generation

[1272] Based on the analysis results, the server generates learning and exercise menus appropriate for each child, using TensorFlow's deep neural network (DNN) model, and stores the generated menus in Amazon RDS.

[1273] Parental notification

[1274] The server notifies parents of the generated learning and exercise menus. Push notifications are sent using AWS SNS (Simple Notification Service), and a smartphone application developed with React Native receives the notifications. The app then displays the menu details to parents.

[1275] Responding to parental inquiries

[1276] The server accepts inquiries about childcare from parents and responds. Parents input their questions through a smartphone application. The server uses a generative AI model (e.g., GPT-4) to generate appropriate advice based on past data and evaluation results. This advice is generated by a natural language processing model (e.g., GPT-4 API) through a prompt sentence and notified to the parent via AWS SNS.

[1277] Specific examples

[1278] For example, if a child has trouble falling asleep and can only sleep for a certain amount of time, the server will analyze the data and detect irregular sleep patterns. It will then provide parents with suggestions for adjusting nap times and revising their nighttime routine. If it determines that a lack of exercise is the cause, it will suggest easy indoor exercises.

[1279] Prompt Sentence Examples

[1280] Parent input: "My child has been having trouble falling asleep lately. Any advice?"

[1281] Use the following prompt: "What advice can you offer to a child who has been having trouble falling asleep recently?"

[1282] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1283] Step 1:

[1284] The server collects data from the childcare facility on children's dietary habits, sleep duration, and activity. This data is periodically sent to the server from the childcare facility's terminal via API. The input data is in JSON format and includes daily data for each child. The collected data is processed by AWS Lambda and stored in AWS RDS.

[1285] Step 2:

[1286] The server periodically analyzes the data stored in AWS RDS. It extracts data using Python scripts and preprocesses the data using Numpy and Pandas. For example, it performs data cleaning such as imputing missing values ​​and detecting outliers. The input data is the preprocessed daily data for each child, and the output data is data converted into a format suitable for analysis.

[1287] Step 3:

[1288] The server evaluates each child's characteristics based on the preprocessed data. It uses a machine learning model using TensorFlow to cluster sleep patterns and activity levels. The input data is the preprocessed data for each child, and the output data is the results of each child's characteristic evaluation. Specific operations for characteristic evaluation include running a clustering algorithm and calculating a score for each characteristic.

[1289] Step 4:

[1290] The server generates learning and exercise menus appropriate for each child based on the evaluation results. This is done using TensorFlow DNN. For example, it might design a focused exercise menu for a child with low activity levels, and recommend an arts and crafts learning menu for a child who enjoys creative activities. The input data is the characteristic evaluation results, and the output data is the learning and exercise menu appropriate for each child.

[1291] Step 5:

[1292] The server notifies parents of the generated learning and exercise menus. Specifically, it uses AWS SNS to send push notifications. The input data is the generated menu, and the output data is a notification sent to the parent's smartphone. The notification contains details about the menu and information on how to implement it.

[1293] Step 6:

[1294] Parents send inquiries about childcare to the server via a smartphone application. The input data is the question or consultation from the parent, and the output data is the inquiry data sent to the server. Specifically, the question is entered into the inquiry form within the app and sent.

[1295] Step 7:

[1296] The server receives inquiries from parents and generates appropriate advice using a generative AI model (GPT-4) based on previous data and evaluation results. It calls the GPT-4 API using a prompt sentence to generate appropriate advice. The input data is the parent's question and related child data, and the output data is the generated advice.

[1297] Step 8:

[1298] The server notifies the parent of the generated advice. The advice is sent to the parent's smartphone via AWS SNS. The input data is the generated advice, and the output data is the notification sent to the parent's smartphone. Specifically, the generated advice is displayed as an in-app notification.

[1299] 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.

[1300] This invention combines a system that provides optimal learning and exercise menus for each child based on data acquired from childcare facilities and supports parents in raising their children with an emotion engine. Specific embodiments of the system are described below.

[1301] System Overview

[1302] This system works in cooperation with four parties: a server, a device, a user, and an emotion engine. The server is responsible for collecting, storing, and analyzing data, and generating menus and notifications, while the device provides an interface with childcare facilities and parents. Users (mainly parents) receive information necessary for childcare through the system and make inquiries. The emotion engine recognizes emotions from the user's input and actions and reflects them in the advice it provides.

[1303] Data collection and storage

[1304] The server periodically receives data from the childcare facility via API, including meal contents, sleep time, and activity details. The data is categorized by child, encrypted, and stored in a database.

[1305] Data analysis and characterization

[1306] The server analyzes the stored data and evaluates each child's characteristics, such as sleep patterns, nutritional balance, and activity levels, using statistical methods and machine learning algorithms to understand the child's health and developmental status.

[1307] Menu generation

[1308] Based on the analysis results, the server generates a learning and exercise menu suited to each child. The generated menu, which is tailored to each child's individual needs, is stored in a database and later provided to parents.

[1309] Parental Notification and Emotion Recognition

[1310] The device provides an interface for notifying parents of the generated learning and exercise menus. Notifications are sent via a dedicated application or email. The emotion engine recognizes emotions from parents' inquiries and daily interactions and adjusts the content and tone of the advice accordingly.

[1311] Responding to parental inquiries and reflecting their feelings

[1312] The device provides an interface for parents to make inquiries about childcare, and parents can enter their questions using an application or a web form.

[1313] The server analyzes the received inquiry and uses generative AI to generate advice based on past data and evaluation results. The emotion engine identifies emotions from the parent's input and generates advice with an appropriate tone and content. The generated advice is sent to the parent via email or in-app notification.

[1314] Specific examples

[1315] For example, if a parent sounds tired and sends a message saying, "My child has been having trouble falling asleep at night lately," the server analyzes the data and considers specific measures to improve the child's sleep pattern based on the analysis. The emotion engine detects "fatigue" in the parent's message and adjusts the tone of the advice to be gentle and empathetic. As a result, advice such as "We understand your concerns about your child's nighttime sleepiness. We'll show you how to adjust nap times and how to relax before bed" is generated and sent to the parent.

[1316] This system allows parents to receive accurate advice without feeling overwhelmed by the daily tasks of childcare, and by receiving support that is sensitive to their emotions, they can feel even more secure in raising their children.

[1317] The processing flow will be explained below.

[1318] Step 1: Collect and store data

[1319] The server periodically collects data such as meal contents, sleep time, and activity details from the childcare facility via an API.

[1320] What it does: Sends an API request to receive the latest data from the childcare system, stores it in a temporary buffer, categorizes it by child, and encrypts it before inserting it into the database.

[1321] Step 2: Preprocessing the data

[1322] The server performs pre-processing to convert the stored data into a format that is easy to analyze.

[1323] Specific actions: Impute missing values, normalize data, check for and correct inconsistencies and errors.

[1324] Step 3: Data analysis and characterization

[1325] The server evaluates the child's characteristics based on the pre-processed data.

[1326] What it does: Uses statistical methods and machine learning algorithms to analyze sleep patterns, nutritional balance, and activity levels to assess a child's health and development.

[1327] Step 4: Generate the menu

[1328] Based on the analysis results, the server generates a learning menu and an exercise menu suitable for each child.

[1329] What it does: It applies rule-based algorithms and machine learning models to design optimal menus for each individual child and stores them in a database.

[1330] Step 5: Prepare the menu for notifications

[1331] The server prepares to notify the parent of the generated menu.

[1332] What it does: Gets parent contact information and formats menu information into rich text and HTML.

[1333] Step 6: Menu Notifications

[1334] The server notifies the parent of the menu when it is ready.

[1335] Specific operations: Connect to the mail server or push notification server to send the message. Save the sending log for later tracking.

[1336] Step 7: Receiving parental inquiries

[1337] The device provides an interface where parents can input questions about childcare.

[1338] Specific operation: Prepare an inquiry form within the mobile app or web app and set up an API endpoint that sends user input to the server.

[1339] Step 8: Parsing the query

[1340] The server receives questions from parents and searches the database for relevant past data.

[1341] Specific operation: Analyzes the inquiry content and generates appropriate advice based on past data and evaluation results.

[1342] Step 9: Recognize emotions

[1343] The server uses an emotion engine to recognize emotions from the parent's inquiry.

[1344] What it does: Analyzes text data using a natural language processing (NLP) model to identify the parent's emotional state (e.g., fatigue, anxiety, joy).

[1345] Step 10: Adjusting Advice

[1346] The server adjusts the content and tone of advice based on the emotional state recognized by the emotion engine.

[1347] Specific behavior: Generate appropriate advice based on the emotional state, and use gentle and empathetic language.

[1348] Step 11: Advice Notification

[1349] The server notifies the parent of the generated advice.

[1350] Specific behavior: Sends advice to parents via email and in-app notifications, and stores the sending log in a database for future reference.

[1351] Example 2

[1352] 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."

[1353] In modern society, parents have limited time to devote to childcare and often rely on childcare facilities. As a result, they face challenges in obtaining sufficient information about their children's activities and health at childcare facilities, making it difficult for them to receive appropriate advice. Furthermore, uniform advice may not adequately reflect each child's individual characteristics, which can cause anxiety and stress for parents. Furthermore, a lack of consideration for parents' feelings can increase the burden of childcare.

[1354] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1355] In this invention, the server includes: means for collecting data on children's dietary habits, sleep duration, and activity details obtained at the childcare facility; means for classifying, encrypting, and storing the collected data in a database; means for analyzing the stored data and evaluating each child's characteristics; and means for generating learning and exercise menus appropriate for each child based on the evaluation results. The server also includes means for identifying the parent's emotions using an emotion engine and adjusting the content and tone of advice, and means for notifying the parent of the generated advice. This allows parents to receive appropriate advice tailored to each child's characteristics, and by receiving responses that are sensitive to their emotions, parents can feel more secure about raising their children.

[1356] A "childcare facility" is a place where children stay for a certain period of time and live and learn under the guidance of caregivers.

[1357] "Children" refers to infants and young children in childcare facilities from whom data such as dietary habits, sleep duration, and activity details are collected.

[1358] "Dietary content" refers to information about the types and amounts of food and beverages consumed by children at childcare facilities.

[1359] "Sleep time" is the total amount of time including the start and end times of a child's sleep.

[1360] "Activity details" is information that indicates details of the activities that children engage in at the childcare facility, such as playing, studying, and exercising.

[1361] "Data collection tools" refer to the interfaces and processes used to obtain data from childcare facilities, such as children's diet, sleep, and activity.

[1362] "Data classification tools" refers to the algorithms or processing tools used to organize and classify the collected data for each child.

[1363] "Encryption methods" refers to the techniques and processes used to encrypt data to ensure its security.

[1364] A "database" is a storage device or system for storing collected data or generated information.

[1365] "Data analysis procedures" refers to the process of using stored data to run statistical methods and machine learning algorithms to assess children's characteristics.

[1366] "Characteristic assessment" refers to information about a child's health and developmental status obtained through data analysis tools.

[1367] A "learning menu" is a learning plan designed based on a child's characteristics to enhance their knowledge and skills.

[1368] An "exercise menu" is an exercise plan designed based on a child's characteristics to improve their physical strength and athletic ability.

[1369] The "menu generation means" refers to an algorithm or process for automatically generating learning menus and exercise menus based on characteristic evaluations.

[1370] "Parental notification means" refers to an interface or process for communicating the generated learning menu, exercise menu, or advice to parents.

[1371] "Inquiry reception means" refers to the interface or process for receiving inquiries about childcare from parents.

[1372] "Advice generation means" refers to the generation AI or process that provides appropriate advice in response to received inquiries based on collected data and evaluation results.

[1373] An "emotion engine" is an algorithm or technology that identifies a parent's emotions and adjusts the content and tone of advice.

[1374] This invention is a system that supports parents in raising their children by providing optimal learning and exercise menus for each child based on data obtained from childcare facilities. Furthermore, the system incorporates an emotion engine that can recognize the emotions of parents and reflect them in the advice it provides.

[1375] System Components

[1376] This system consists of four main components: a server, a terminal, a user (guardian), and an emotion engine.

[1377] Data collection overview

[1378] The server periodically collects data from the childcare facility via API, such as what children eat, how much they sleep, and what their activities are. This data collection uses a data acquisition API that connects to the childcare facility's digital system. The collected data is categorized for each child, encrypted, and stored in a database. This encryption ensures the security of the data.

[1379] Data analysis and characterization process

[1380] The server analyzes the stored data using statistical methods and machine learning algorithms. This allows the system to evaluate a child's characteristics, such as sleep patterns, nutritional balance, and activity level. For example, a child's average sleep duration and activity trends can be analyzed based on their data from the past month. This can also help understand the child's health and developmental status.

[1381] Menu generation

[1382] The server generates learning and exercise menus suited to each child based on the analysis results. The generated menus are tailored to each child's individual needs and are stored in a database. These menus can then be used as information to provide to parents. For example, a menu can be created that recommends playing with educational blocks in the morning and taking a walk outside in the afternoon for a certain child.

[1383] Parental Notification and Emotion Recognition

[1384] The device provides an interface for notifying parents of the generated learning and exercise menus. This notification is done via a dedicated application or email. In addition, an emotion engine recognizes emotions from parents' inquiries and daily conversations and reflects them in the notification content.

[1385] Inquiry response

[1386] The device provides an interface for accepting parenting-related inquiries from parents. Parents can enter their questions using an application or web form. The server analyzes the received inquiries and uses generative AI to create advice based on past data and evaluation results. An emotion engine identifies the parent's emotions and generates advice with an appropriate tone and content. The generated advice is sent to the parent via email or in-app notification.

[1387] Specific examples

[1388] For example, if a parent sends an inquiry saying, "My child has been having trouble falling asleep at night lately," the server analyzes the data and considers specific improvement measures based on the analysis of the child's sleep patterns. The emotion engine detects "fatigue" from the parent's message and adjusts the tone of the advice to be gentle and empathetic. As a result, advice such as "We understand your concerns about your child's nighttime sleepiness. We'll show you how to adjust nap times and how to relax before bed" is generated and sent to the parent.

[1389] In this way, the system allows parents to obtain the information they need for childcare in a timely manner, and by providing emotionally sensitive support, it can increase their sense of security when raising their children.

[1390] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1391] System program processing steps

[1392] Step 1:

[1393] The server periodically collects data on children's diet, sleep, and activity from the childcare facility via API. The input is the data sent from the childcare facility. Specifically, the server sends an API request and receives the data returned from the childcare facility. The output is the retrieved raw data.

[1394] Step 2:

[1395] The server categorizes the collected data by child, encrypts it, and stores it in a database. The input is the raw data obtained in step 1. Specifically, the server tags the data by child and encrypts the data using an encryption algorithm. The output is the encrypted records in the database.

[1396] Step 3:

[1397] The server retrieves data for each child from the database and analyzes it using statistical methods and machine learning algorithms. The input is encrypted data stored in the database. Specifically, the server decrypts the data and feeds it into the machine learning model. The output is an assessment result for each child, including characteristics such as sleep patterns, nutritional balance, and activity level.

[1398] Step 4:

[1399] The server generates learning and exercise menus appropriate for each child based on the characteristic evaluation. The input is the evaluation results obtained in step 3. Specifically, the server executes an algorithm to automatically generate the optimal menu based on the evaluation results. The output is the generated learning and exercise menus.

[1400] Step 5:

[1401] The device notifies the guardian of the generated learning and exercise menus. The input is the menu generated in step 4. Specifically, the device sends a notification to the guardian via a dedicated application or email. The output is a notification confirmed by the guardian.

[1402] Step 6:

[1403] The device accepts inquiries about childcare from parents. The input is a question sent by the parent through an application or a web form. Specifically, the device transfers the inquiry to the server. The output is the accepted inquiry data.

[1404] Step 7:

[1405] The server analyzes the received inquiry and creates appropriate advice using a generative AI model based on the collected data and evaluation results. The input is the inquiry data received in step 6 and the evaluation results in the database. Specifically, the server inputs prompt data into the generative AI model and generates advice content. The output is the created advice.

[1406] Step 8:

[1407] The emotion engine recognizes emotions from parental inquiries and daily interactions and adjusts the content and tone of advice. The input is inquiry data from parents. Specifically, the emotion engine analyzes the input text to identify emotions and adjusts the tone of advice. The output is advice that takes emotions into consideration.

[1408] Step 9:

[1409] The server notifies the guardian of the advice generated. The input is the advice generated in step 7 and step 8. Specifically, the server sends the advice content to the terminal, and the terminal notifies the guardian. The output is the advice sent to the guardian.

[1410] This allows the system to consistently collect data from childcare facilities and provide optimal advice to parents.

[1411] (Application example 2)

[1412] 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."

[1413] In modern childcare, personalized learning and exercise programs are important to support children's growth and development. However, parents often find it difficult to find the optimal educational and exercise programs for their children due to their busy schedules, and they often lack emotional support. Current systems lack personalized advice and emotional support for parents, leaving parents with little relief from the burden of childcare and making it difficult to care for their children with peace of mind.

[1414] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data acquired at the childcare facility, means for analyzing the collected data and evaluating the characteristics of each child, means for generating a learning menu and an exercise menu appropriate for each child based on the evaluation results, means for notifying the guardian of the generated menu, means for accepting inquiries about childcare from the guardian, means for generating appropriate advice based on the collected data and the evaluation results in response to the accepted inquiries, means for notifying the guardian of the generated advice, means including an emotion engine for recognizing the guardian's emotions and adjusting the tone and content of the advice, and means for delivering individual learning videos and exercise programs. This not only allows guardians to receive the optimal learning and exercise menu for their children but also emotionally sensitive advice, allowing them to raise their children with greater peace of mind.

[1415] A "childcare facility" is a specialized facility for the education and care of children.

[1416] "Data" refers to information such as what a child eats, how much they sleep, and what their activities are.

[1417] "Means of collection" refers to the functions and devices used to obtain data from childcare facilities and store it on a server.

[1418] "Means for analysis" refers to functions and devices for analyzing collected data using statistical methods and machine learning algorithms.

[1419] "Assessment means" refers to the functions or devices for assessing the characteristics of individual children based on the results of the analysis.

[1420] "Generating means" refers to a function or device for creating a learning menu and an exercise menu based on the evaluation results.

[1421] "Means of notification" refers to the functions and devices used to communicate the generated menus and advice to parents.

[1422] "Means for accepting inquiries" refers to functions and devices for receiving questions and opinions from parents.

[1423] The "means for generating advice" refers to a function or device for generating an appropriate answer to a received inquiry based on collected data and evaluation results.

[1424] An "emotion engine" refers to a function or device that recognizes parents' emotions and appropriately adjusts the content and tone of advice.

[1425] "Educational videos" are video content intended for the education of children.

[1426] An "exercise program" is a set of exercises or activity plans designed to promote physical activity in children.

[1427] "Means of distribution" refers to the functions and devices used to provide educational videos and exercise programs to parents and children.

[1428] System Overview

[1429] This invention is a system that supports parents in raising their children by providing optimal learning and exercise menus for each child based on data on the children obtained from childcare facilities. This system works in cooperation with four parties: a server, a terminal, a user (parent), and an emotion engine.

[1430] Data collection and storage

[1431] The server periodically retrieves the necessary data from the childcare facility. Data such as meal contents, sleep time, and activity details are automatically retrieved using the childcare facility's API. The retrieved data is categorized by child, encrypted, and stored in MongoDB.

[1432] Data analysis and characterization

[1433] The server analyzes the stored data using TensorFlow and PyTorch to evaluate each child's characteristics, including sleep patterns, nutritional balance, and activity level, providing a detailed understanding of the child's health and development.

[1434] Menu generation

[1435] Based on the analysis results, the server generates learning and exercise menus appropriate for each child, which are then sent to parents via a smartphone application developed using React Native.

[1436] Parental Notification and Emotion Recognition

[1437] The device provides an interface for parents to receive the generated learning and exercise recommendations. Notifications are sent via in-app notifications or email. At the same time, Azure Cognitive Services and IBM Watson are used to recognize emotions, and the content and tone of the advice is adjusted based on the parent's emotions.

[1438] Responding to parental inquiries and reflecting their feelings

[1439] Users (parents) can make inquiries about childcare through the application or web form. The server accepts these inquiries and generates appropriate advice based on the collected data and evaluation results. The advice is adjusted by the emotion engine and delivered to parents in an appropriate tone.

[1440] Distribution of educational videos and exercise programs

[1441] The server also includes means for generating and delivering educational videos and exercise programs tailored to the child, allowing the child to receive individually optimized content.

[1442] Specific examples

[1443] For example, if a parent complains that their child has been having trouble concentrating on their extracurricular activities, the emotion engine will recognize the emotion as "confusion." The server will analyze the data, select appropriate learning videos and exercise programs, and provide advice such as:

[1444] "We understand your concerns about your child's inability to concentrate on their lessons. We have some new educational videos that will help your child learn while having fun, so please take a look."

[1445] Prompt Sentence Examples

[1446] User message: My child has been having trouble concentrating on his lessons lately.

[1447] Q: Please provide a detailed, emotion-based explanation of why your child is having trouble concentrating and what actions you can take to improve it.

[1448] Emotion: Confused

[1449] This system not only provides parents with the optimal learning and exercise menu for their children, but also allows them to receive emotionally sensitive advice, allowing them to raise their children with greater peace of mind.

[1450] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1451] Step 1:

[1452] Data collection

[1453] The server periodically retrieves child data (meals, sleep time, activity) from the childcare facility API. During this process, the data retrieved from the API is temporarily stored and encrypted for secure storage in MongoDB.

[1454] Input: Raw data from the childcare facility API

[1455] Output: Data stored in MongoDB in encrypted form

[1456] Step 2:

[1457] Data analysis

[1458] The server uses TensorFlow and PyTorch to analyze the data stored in MongoDB, which involves using statistical methods and machine learning algorithms to extract child characteristics from the data (e.g., sleep patterns, nutritional balance, activity levels).

[1459] Input: Data stored in MongoDB

[1460] Output: Analysis results evaluating the characteristics of each child

[1461] Step 3:

[1462] Menu generation

[1463] Based on the analysis results, the server generates learning and exercise menus appropriate for each child, which involves using a Python script to create a list of menus according to generation rules.

[1464] Input: Analysis results

[1465] Output: Learning and exercise menus appropriate for each child

[1466] Step 4:

[1467] Parental notification

[1468] The device notifies parents of the generated learning and exercise menus through a smartphone application developed using React Native, either via the app's notification function or email.

[1469] Input: Generated learning menu and exercise menu

[1470] Output: Parental notification message

[1471] Step 5:

[1472] emotion recognition

[1473] The server uses Azure Cognitive Services and IBM Watson to recognize emotions from parental feedback and inquiries, and generates responses based on the parent's emotions.

[1474] Input: Parent inquiries and feedback

[1475] Output: Recognized parent's emotion data

[1476] Step 6:

[1477] Inquiry handling and advice generation

[1478] The server generates appropriate advice based on the collected data and evaluation results in response to the received inquiry. This process involves generating responses using natural language processing (NLP) with a generative AI model.

[1479] Input: Parental inquiries, collected data, assessment results, recognized emotion data

[1480] Output: Generated advice

[1481] Step 7:

[1482] Advice Notification

[1483] The device will then notify the parent of the generated advice via the notification function within the application or email.

[1484] Input: Generated advice

[1485] Output: Parental Advisory Notice

[1486] Step 8:

[1487] Distribution of educational videos and exercise programs

[1488] The server generates educational videos and exercise programs tailored to each child and distributes them through websites and applications, adding appropriate metadata to make them easily accessible to parents and children.

[1489] Input: Generated learning videos and exercise programs

[1490] Output: Distributed learning videos and exercise programs

[1491] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1492] 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.

[1493] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1494] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1495] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1496] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1497] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1498] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1499] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1500] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1501] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1502] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1503] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1504] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1505] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1506] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1507] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1508] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1509] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1510] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1511] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1512] The following is further disclosed regarding the above embodiment.

[1513] (Claim 1)

[1514] A means for collecting data on the diet, sleep duration, and activity of children obtained at a childcare facility;

[1515] A means of analyzing the collected data and assessing the characteristics of each individual child;

[1516] A means for generating a learning menu and an exercise menu suitable for each child based on the evaluation results;

[1517] a means for notifying a parent of the generated menu;

[1518] A means of receiving inquiries from parents regarding childcare, and

[1519] A means for generating appropriate advice in response to a received inquiry based on the collected data and evaluation results;

[1520] The system includes a means for notifying parents of the generated advice.

[1521] (Claim 2)

[1522] 2. The system according to claim 1, wherein a natural language processing model is used when generating advice in response to inquiries from parents about childcare.

[1523] (Claim 3)

[1524] 10. The system of claim 1, wherein the system uses a data acquisition API to automate data collection from child care facilities.

[1525] "Example 1"

[1526] (Claim 1)

[1527] A means for collecting data on the diet, sleep duration, and activity of children obtained at a childcare facility;

[1528] A means of analyzing the collected data and assessing the characteristics of each individual child;

[1529] A means for generating a learning menu and an exercise menu suitable for each child based on the evaluation results;

[1530] a means for notifying a parent of the generated menu;

[1531] A means of receiving inquiries from parents regarding childcare, and

[1532] A means for generating appropriate advice in response to a received inquiry based on the collected data and evaluation results;

[1533] a means for notifying parents of the generated advice;

[1534] A means of encrypting collected data for security purposes;

[1535] a means for storing the data categorized for each individual child in a database;

[1536] a means for performing time series analysis to analyze the data;

[1537] A means for generating the exercise menu and learning menu using a machine learning algorithm;

[1538] a means for generating appropriate advice using a natural language processing model;

[1539] A system that includes a means of notifying parents via a dedicated application or email.

[1540] (Claim 2)

[1541] The system of claim 1, wherein a generative AI model is used to generate advice in response to parenting inquiries from parents.

[1542] (Claim 3)

[1543] 10. The system of claim 1, wherein the system uses a data acquisition API to automate data collection from child care facilities.

[1544] "Application Example 1"

[1545] (Claim 1)

[1546] A means for collecting data on the diet, sleep duration, and activity of children obtained at a childcare facility;

[1547] A means of analyzing the collected data and assessing the characteristics of each individual child;

[1548] A means for generating a learning menu and an exercise menu suitable for each child based on the evaluation results;

[1549] a means for notifying a parent of the generated menu;

[1550] A means of receiving inquiries from parents regarding childcare, and

[1551] A means for generating appropriate advice in response to a received inquiry based on the collected data and evaluation results;

[1552] a means for notifying parents of the generated advice;

[1553] A smartphone application allows parents to view and manage the generated menus and advice.

[1554] A means of generating personalized advice using generative AI models in response to parental inquiries; and

[1555] The system includes a means for generating generated advice through a prompt sentence using a natural language processing model.

[1556] (Claim 2)

[1557] The system of claim 1, wherein a generative AI model and prompt sentences are used when generating advice in response to parenting inquiries from parents.

[1558] (Claim 3)

[1559] 10. The system of claim 1, wherein the system uses a data acquisition API to automate data collection from child care facilities.

[1560] "Example 2: Combining Emotion Engines"

[1561] (Claim 1)

[1562] A means for collecting data on the diet, sleep duration, and activity of children obtained at a childcare facility;

[1563] A means to classify, encrypt and store the collected data in a database;

[1564] A means of analyzing the stored data and assessing the characteristics of each child;

[1565] A means for generating a learning menu and an exercise menu suitable for each child based on the evaluation results;

[1566] a means for notifying a parent of the generated menu;

[1567] A means of receiving inquiries from parents regarding childcare, and

[1568] A means for generating appropriate advice in response to a received inquiry based on the collected data and evaluation results;

[1569] A means of identifying parents' emotions and adjusting the content and tone of advice;

[1570] The system includes a means for notifying parents of the generated advice.

[1571] (Claim 2)

[1572] 2. The system according to claim 1, wherein a natural language processing model is used when generating advice in response to inquiries from parents about childcare.

[1573] (Claim 3)

[1574] 10. The system of claim 1, wherein the system uses a data acquisition API to automate data collection from child care facilities.

[1575] "Application example 2 when combining emotion engines"

[1576] (Claim 1)

[1577] A means for collecting data on the diet, sleep duration, and activity of children obtained at a childcare facility;

[1578] A means of analyzing the collected data and assessing the characteristics of each individual child;

[1579] A means for generating a learning menu and an exercise menu suitable for each child based on the evaluation results;

[1580] a means for notifying a parent of the generated menu;

[1581] A means of receiving inquiries from parents regarding childcare, and

[1582] A means for generating appropriate advice in response to a received inquiry based on the collected data and evaluation results;

[1583] a means for notifying parents of the generated advice;

[1584] a means including an emotion engine that recognizes the parent's emotions and adjusts the tone and content of the advice;

[1585] A means to deliver individual learning videos and exercise programs,

[1586] A system including:

[1587] (Claim 2)

[1588] 2. The system according to claim 1, wherein a natural language processing model is used when generating advice in response to inquiries from parents about childcare.

[1589] (Claim 3)

[1590] 10. The system of claim 1, wherein the system uses a data acquisition API to automate data collection from child care facilities. [Explanation of symbols]

[1591] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for collecting data on the diet, sleep duration, and activity of children obtained at a childcare facility; A means of analyzing the collected data and assessing the characteristics of each individual child; A means for generating a learning menu and an exercise menu suitable for each child based on the evaluation results; a means for notifying a parent of the generated menu; A means of receiving inquiries from parents regarding childcare, and A means for generating appropriate advice in response to a received inquiry based on the collected data and evaluation results; The system includes a means for notifying parents of the generated advice.

2. The system according to claim 1, wherein a natural language processing model is used when generating advice in response to inquiries from parents about childcare.

3. 10. The system of claim 1, wherein the system uses a data acquisition API to automate data collection from child care facilities.

Images