System

Abstract

A system is provided.SOLUTION: A system comprising: means for providing a user interface for inputting child-care information; means for transmitting the child-care information to a server; means for analyzing the AI comprising a generated AI model and artificial general intelligence techniques for analyzing the child-care information; means for generating child-care advice based on the analysis; means for transmitting the generated child-care advice to a user device; means for displaying the advice at the user device; and means for receiving feedback from the user and improving the generated data model.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] Today's parents face difficulties in obtaining appropriate child-rearing information and are concerned about time management and their children's health and development. It is also difficult to obtain child-rearing advice tailored to the individual needs of each child. This results in a decline in the quality of child-rearing and increased stress for both parents and children. The present invention aims to resolve these parenting concerns and improve the quality of child-rearing. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by the following means. The system includes a means for providing a user interface for inputting childcare information, a means for transmitting the childcare information to a server, a data analysis means equipped with a generative AI model and general artificial intelligence technology for analyzing the childcare information, a means for generating childcare advice based on the analysis results, a means for transmitting the generated childcare advice to a user terminal, a means for displaying the advice on the user terminal, and a means for receiving feedback from the user and improving the generative AI model. This allows parents to receive personalized childcare advice, leading to more effective childcare. Furthermore, the system suggests optimal educational activities and games based on the child's developmental stage, further improving the quality of childcare.

[0006] "Childcare information" is a general term for specific information related to childcare, such as a child's age, height, weight, sleep patterns, diet, and behavioral data.

[0007] "User interface" refers to the interaction means, such as a screen or input field, through which the user inputs childcare information.

[0008] "Server" refers to a computer system for receiving, storing, and analyzing parenting information.

[0009] A "generative AI model" refers to an algorithm that uses artificial intelligence techniques to analyze data for a specific purpose and generate predictions or suggestions.

[0010] "General artificial intelligence technology" refers to flexible artificial intelligence technology that can perform a wide range of tasks and can be used for multiple purposes, not just for specific applications.

[0011] "Data analysis" refers to the process of analyzing various data based on childcare information and extracting useful information.

[0012] "Parenting advice" refers to specific parenting guidance and suggestions provided to parents and educators based on the results of data analysis.

[0013] "User terminal" refers to a device (smartphone, tablet, PC, etc.) that parents use to access the system, input childcare information, and receive advice.

[0014] "Feedback" refers to the act of users systematically returning information about the effectiveness of the advice or solutions they received.

[0015] "Educational activities" refer to learning and play activities designed to enhance children's development. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] This invention is a comprehensive childcare support system that analyzes childcare information and provides customized childcare advice. This system is composed of the following elements: a user interface for inputting childcare information, a function for sending the childcare information to a server, a data analysis function, a function for generating childcare advice, a function for sending advice to a user's device, a function for receiving feedback, and a function for improving the generated AI model.

[0038] Overall system configuration

[0039] 1. User Interface

[0040] Terminal

[0041] Users enter childcare information through a dedicated application using a smartphone, tablet, or other device. The interface is designed to be intuitive and easy to use, providing fields for quickly and accurately entering the necessary information.

[0042] 2. Sending childcare information

[0043] Terminal

[0044] The childcare information entered by the user is sent to the server via an API request, and the device converts this data into a standardized format to ensure data integrity.

[0045] 3. Data analysis and model use

[0046] server

[0047] The server stores the received parenting information in a cloud database. An analysis engine then retrieves the parenting information from the database and analyzes it using generative AI models and general artificial intelligence technology. This analysis evaluates the child's sleep patterns, nutritional status, and behavioral health, and identifies specific improvement measures.

[0048] 4. Generating parenting advice

[0049] server

[0050] Based on the results of the data analysis, customized parenting advice is automatically generated, tailored to the user's individual parenting needs and includes specific, practical content.

[0051] 5. Sending and Viewing Advice

[0052] server

[0053] The generated parenting advice is sent to the user's device via a dedicated API.

[0054] Terminal

[0055] The device displays the received parenting advice to the user, and can also use the notification function to notify the user of important advice in a timely manner.

[0056] 6. Receiving and Analyzing Feedback

[0057] User

[0058] Users can enter and submit feedback on the advice and solutions provided.

[0059] Terminal

[0060] The terminal transmits the feedback data to the server.

[0061] server

[0062] The server evaluates the performance of the generative AI model based on the received feedback and improves the analysis algorithm, allowing the system to continuously evolve and provide more accurate and effective parenting advice.

[0063] Specific examples

[0064] User

[0065] For example, consider a case where a user is concerned about the sleep patterns of their two-year-old child. The user enters the child's sleep patterns (bedtime, wake-up time, number of nighttime awakenings, etc.) through an application.

[0066] Terminal

[0067] The terminal converts this information into an appropriate format and sends it to the server.

[0068] server

[0069] The server analyzes the received data and generates specific sleep improvement measures (e.g., recommending bath time and reading picture books to get the child to bed at 9 p.m.) using a generative AI model that suggests a sleep routine suitable for a two-year-old.

[0070] Terminal

[0071] The device displays the sleep improvement measures received from the server to the user and uses the notification function to inform the user of important suggestions.

[0072] User

[0073] The user tries these suggestions for a week, then enters the results as feedback and submits it.

[0074] server

[0075] The server analyzes this feedback and uses it as data to improve the accuracy of the model.

[0076] This system will enable parents to receive specific and useful advice for their individual child-rearing concerns, and is expected to improve the quality of child-rearing.

[0077] The processing flow will be explained below.

[0078] Step 1:

[0079] The user launches the application on the terminal and inputs childcare information (for example, the child's age, height, weight, sleep patterns, dietary content, behavioral data, etc.).

[0080] Step 2:

[0081] The terminal converts the childcare information input by the user into a standardized format and generates an HTTP POST request.

[0082] Step 3:

[0083] The terminal sends the generated HTTP POST request to the server.

[0084] Step 4:

[0085] The server analyzes the received HTTP POST request, extracts the childcare information data, and stores it in a cloud database.

[0086] Step 5:

[0087] The server retrieves the stored childcare information data from the cloud database and transfers it to the analysis engine.

[0088] Step 6:

[0089] The server's analytical engine uses generative AI models and general artificial intelligence technology to analyze childcare information data and assess children's sleep patterns, nutritional status, and behavioral health.

[0090] Step 7:

[0091] The server generates specific parenting advice (e.g., optimal sleep schedules, nutritionally balanced meal plans, behavioral improvements) based on the analysis results.

[0092] Step 8:

[0093] The server generates an HTTP response for transmitting the generated child-rearing advice to the user's terminal.

[0094] Step 9:

[0095] The terminal analyzes the HTTP response received from the server, extracts the child-rearing advice data, and displays it to the user.

[0096] Step 10:

[0097] If necessary, the device will notify the user of important advice via push notifications.

[0098] Step 11:

[0099] The user follows the advice provided to them and performs childcare, and inputs the results as feedback.

[0100] Step 12:

[0101] The terminal receives feedback from the user and generates an HTTP POST request to send to the server.

[0102] Step 13:

[0103] The server analyzes the received feedback data and uses it to improve the accuracy of the generative AI model.

[0104] Step 14:

[0105] Based on the feedback, the server improves the generative AI model and general artificial intelligence technology and reflects this in the next analysis.

[0106] Example 1

[0107] 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."

[0108] Conventional childcare support systems have had problems with the complicated input and management of childcare information, and the inability to perform sufficient data analysis to provide appropriate advice. Furthermore, the childcare information was not personalized enough, making it difficult to generate appropriate advice for each user. Furthermore, there was no mechanism in place to reflect feedback on advice in the system, making it difficult to evolve and improve the system.

[0109] 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.

[0110] In this invention, the server includes a means for converting childcare information into a standardized data format, a means for storing the childcare information in a cloud database, and a data analysis means equipped with a generative AI model and general artificial intelligence technology for analyzing the childcare information. This enables efficient management of childcare information and advanced data analysis. Furthermore, it automatically generates personalized childcare advice based on the analysis results, enabling continuous system improvement through feedback.

[0111] "Childcare information" refers to various data related to childcare, such as children's sleep patterns, diet, and behavior.

[0112] "User interface" refers to an interface through which a user inputs or obtains information.

[0113] "Data format" refers to a format for standardizing and processing information.

[0114] A "cloud database" refers to an online database for storing and managing data via the Internet.

[0115] A "generative AI model" refers to a machine learning model that uses artificial intelligence technology to automatically process specific tasks.

[0116] "General artificial intelligence technology" refers to artificial intelligence technology that is not limited to specific tasks and can be used for a wide range of applications.

[0117] "Data analysis tools" refer to methods and processes for collecting, analyzing, and evaluating data.

[0118] A "prompt sentence" refers to a sentence used to give instructions or ask questions to a generative AI model.

[0119] "Private API" refers to an application program interface for accessing specific functions or data.

[0120] "Feedback" refers to information used to collect user ratings and opinions.

[0121] MODE FOR CARRYING OUT THE INVENTION

[0122] The present invention is a comprehensive childcare support system that analyzes childcare information and provides customized childcare advice. This system includes a user interface for inputting childcare information, a function for sending the childcare information to a server, a data analysis function, a function for generating childcare advice, a function for sending the advice to a user terminal, a function for receiving feedback, and a function for improving the generated AI model.

[0123] Hardware and software used

[0124] Device: The user uses a smartphone or tablet, on which a dedicated application is installed.

[0125] Server: A server built in a cloud computing environment is used. Generative AI models and general artificial intelligence technology are implemented as data analysis engines.

[0126] Database: Use a cloud database to store childcare information.

[0127] System Operation Overview

[0128] Entering childcare information via a user interface

[0129] Users can open a dedicated application on their smartphone or tablet and input childcare information such as their child's sleep patterns, diet, and behavior. For example, they can input information such as "the child frequently wakes up at night."

[0130] Sending childcare information to the server

[0131] The device converts the childcare information entered by the user into a standardized data format, such as JSON, and sends it to the server as an API request, which then stores the data in a cloud database.

[0132] Analyzing the data and using the model

[0133] The server retrieves childcare information from a cloud database and analyzes the data using an analytical engine, utilizing generative AI models and general artificial intelligence techniques. The analysis results are used to assess children's sleep patterns, nutritional status, and behavioral health, and identify specific improvement measures.

[0134] Generating parenting advice

[0135] The server generates prompts based on the analysis results, such as "Generate specific suggestions to improve a two-year-old's sleep patterns," and issues them to the generative AI model. The generative AI model then generates specific childcare advice based on these prompts, such as "Read picture books before bedtime and avoid watching TV for 30 minutes before bed."

[0136] Sending and viewing advice

[0137] The generated parenting advice is sent to the user's device via a dedicated API, where it is displayed to the user and notifies them of important advice in a timely manner using the notification function.

[0138] Receiving and analyzing feedback

[0139] The user enters feedback about the results of following the provided advice into a dedicated application. The device then sends this feedback data to a server, which analyzes the received feedback data and uses it to evaluate and improve the performance of the generative AI model.

[0140] Examples of concrete examples and prompts

[0141] For example, here's a scenario where a user enters concerns about their 2-year-old's sleep patterns:

[0142] The user enters "frequent nighttime awakenings" into the application. The device converts this information into JSON format and sends it to the server. The server uses an analysis engine to create "advice to reduce nighttime awakenings in a 2-year-old child" using a generative AI model, providing specific advice such as "read picture books before bedtime and avoid watching TV for 30 minutes before bed." The device displays this to the user and uses the notification function to inform them of important advice.

[0143] An example prompt is "Generate specific suggestions to improve a two-year-old's sleep patterns."

[0144] The present invention is expected to enable efficient management of child-rearing information and provision of personalized advice, thereby effectively supporting users in child-rearing.

[0145] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0146] Step 1:

[0147] Entering childcare information

[0148] The user opens the dedicated application on a smartphone or tablet. The application's user interface provides a form for inputting childcare information. The user enters specific childcare information into the form, such as the child's sleep patterns, diet, and behavior. Input information includes "bedtime," "wake-up time," and "number of nighttime awakenings."

[0149] Input: Childcare information (e.g., bedtime, wake-up time, number of nighttime awakenings)

[0150] Output: The input childcare information is formatted as data.

[0151] Step 2:

[0152] Formatting and sending childcare information

[0153] The device receives the childcare information entered by the user and converts it into a standardized data format (e.g., JSON format). The formatted data is prepared as an API request and sent to the server.

[0154] Input: Childcare information entered in the input form

[0155] Output: Parenting information converted to JSON format

[0156] Step 3:

[0157] Receiving and storing data

[0158] The server receives the API request sent from the device and stores the sent childcare information in a cloud database, which is then used for later analysis.

[0159] Input: JSON format childcare information data

[0160] Output: Parenting information stored in a cloud database

[0161] Step 4:

[0162] Data acquisition and analysis

[0163] The server retrieves stored parenting information from a cloud database. The retrieved data is analyzed using generative AI models and artificial general intelligence techniques. This analysis process evaluates children's sleep patterns, nutritional status, and behavioral health, and identifies specific improvement measures.

[0164] Input: Parenting information stored in a cloud database

[0165] Output: Analysis results (evaluation of children's sleep patterns, nutritional status, behavioral health, etc.)

[0166] Step 5:

[0167] Generating parenting advice

[0168] The server generates a prompt based on the analysis results and inputs it into the generative AI model. An example of a prompt is "Generate specific suggestions to improve the sleep patterns of a two-year-old child." The generative AI model generates specific parenting advice based on this prompt.

[0169] Input: Analysis results and generated prompt statements

[0170] Output: Generated parenting advice

[0171] Step 6:

[0172] Sending parenting advice

[0173] The server sends the generated parenting advice to the user's device via a dedicated API. This API request includes the generated advice.

[0174] Input: Generated parenting advice

[0175] Output: Parenting advice sent in API request

[0176] Step 7:

[0177] Receiving and viewing advice

[0178] The device displays the childcare advice received from the server. The advice display screen is displayed within the application, and important advice is notified to the user using the notification function.

[0179] Input: Parenting advice sent in API request

[0180] Output: Parenting advice displayed within the application

[0181] Step 8:

[0182] Enter and submit feedback

[0183] The user follows the advice provided and inputs the results into the application. The feedback content may be, for example, "I've woken up less at night." The device then sends this feedback data back to the server as an API request.

[0184] Input: User feedback information

[0185] Output: Feedback information converted to JSON format

[0186] Step 9:

[0187] Receiving and analyzing feedback

[0188] The server receives the feedback data sent from the device and analyzes it to evaluate and improve the performance of the generative AI model, thereby improving the accuracy of parenting advice from the next time onwards.

[0189] Input: Feedback information in JSON format

[0190] Output: Model performance evaluation and improvement suggestions

[0191] (Application example 1)

[0192] 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."

[0193] Conventional childcare support systems not only analyze childcare information and provide advice, but also lack the ability to provide customized meal suggestions based on each child's nutritional needs. They also lack the functionality to provide advice in a format that parents can immediately implement and receive feedback. This makes it difficult to solve the specific nutritional management challenges faced by parents.

[0194] 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.

[0195] In this invention, the server includes means for providing a user interface for inputting childcare information, means for transmitting the childcare information to the server, means for analyzing the childcare information using a generative AI model and general artificial intelligence (AI) technology, means for generating childcare advice based on the analysis results, means for transmitting the generated childcare advice to a user terminal, means for displaying the advice on the user terminal, means for receiving feedback from the user and improving the generative AI model, means for providing customized nutritional advice based on the childcare information and generating a recommended ingredient list, and means for ordering ingredients and meals from the user terminal. This allows parents to receive specific and actionable dietary advice tailored to their children's individual nutritional needs, thereby optimally supporting their children's health and growth.

[0196] "Childcare information" refers to specific data related to childcare, such as a child's age, allergy information, food preferences, sleep patterns, and behavioral health.

[0197] "User interface" refers to the part of a computer system through which a user inputs childcare information, and refers to an intuitive and easy-to-use input means, including devices such as smartphones and tablets.

[0198] "Generative AI models" are algorithms and systems that use artificial intelligence techniques to generate customized advice and suggestions based on analyzed parenting information.

[0199] "General artificial intelligence technology" refers to artificial intelligence technology that can be applied to a variety of uses, not just specific problems.

[0200] "Data analysis means" refers to a combination of software and hardware used to analyze collected childcare information and identify specific patterns and improvements.

[0201] The "child-rearing advice generating means" is a function that automatically generates specific and actionable child-rearing advice based on the analysis results obtained by the data analysis means.

[0202] A "user terminal" is an electronic terminal such as a smartphone, tablet, or PC that allows a user to input childcare information and receive advice.

[0203] The "feedback receiving means" refers to an interface and communication means for receiving opinions and reactions from users.

[0204] "Model Improvement Tools" means the processes and techniques for evaluating and improving the performance of a Generative AI Model based on received feedback.

[0205] "Nutrition advice" is specific dietary suggestions and recommended food lists based on a child's individual nutritional needs.

[0206] The "recommended food list" is a list of foods that are appropriate for supporting children's health and growth, selected by a generative AI model.

[0207] The "ingredient ordering means" is a function that allows users to order ingredients and meals online based on a recommended ingredient list.

[0208] The present invention is a comprehensive childcare support system for analyzing childcare information and providing customized childcare advice. As an application example, a specific embodiment focusing on a food delivery service will be described.

[0209] Overall system configuration

[0210] 1. User Interface

[0211] Terminal

[0212] Users enter childcare information through a dedicated application using a smartphone, tablet, or other device. The interface is designed to be intuitive and easy to use, providing fields for quickly and accurately entering the necessary information.

[0213] 2. Sending childcare information

[0214] Terminal

[0215] The childcare information entered by the user is sent to the server via an API request, and the device converts this data into a standardized format to ensure data integrity.

[0216] 3. Data analysis and model use

[0217] server

[0218] The server stores the received childcare information in a cloud database. The analysis engine then retrieves the information from the database and analyzes it using generative AI models and general artificial intelligence technology. This analysis evaluates the child's nutritional status and generates specific nutritional advice and a recommended food list.

[0219] 4. Generating nutrition advice

[0220] server

[0221] Based on the data analysis results, customized nutrition advice is automatically generated that is specific and practical, tailored to the user's individual parenting needs.

[0222] 5. Sending and Viewing Advice

[0223] server

[0224] The generated nutrition advice is sent to the user's device via a dedicated API.

[0225] Terminal

[0226] The device displays the received nutrition advice to the user, and can also use the notification function to notify the user of important advice in a timely manner.

[0227] 6. Ordering ingredients

[0228] User

[0229] Users can view customized nutrition advice and recommended ingredients lists, and order ingredients and meals directly through the application.

[0230] Terminal

[0231] The terminal sends the order information to a server and works with the food delivery service to confirm the order.

[0232] 7. Receiving and Analyzing Feedback

[0233] User

[0234] Users can input and submit feedback on the food and service provided.

[0235] Terminal

[0236] The terminal transmits the feedback data to the server.

[0237] server

[0238] The server evaluates the performance of the generative AI model based on the received feedback and improves the analysis algorithm, allowing the system to continuously evolve and provide more accurate and effective nutritional advice.

[0239] Specific examples

[0240] Consider a case where a user is having trouble managing the nutrition of their two-year-old child. The user enters the child's dietary information (allergies, disliked ingredients, etc.) through the application. For example, the user can enter, "My child is two years old and has a peanut allergy. He likes fruit but doesn't eat many vegetables." Based on this information, the system generates appropriate nutrition advice and a recommended ingredient list, which the parent receives. Furthermore, the parent can order ingredients and meals directly through the app, enabling immediate implementation.

[0241] This allows parents to receive a specific and customized list of ingredients based on their child's nutritional needs, improving the quality of their childcare with access to a quality food delivery service.

[0242] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0243] Step 1:

[0244] Users use a device such as a smartphone or tablet to enter childcare information through a dedicated application, including the child's age, allergies, and dietary preferences. This information is then saved on the device as childcare information and converted into a standardized format.

[0245] Input: Childcare information entered by the user (age, allergy information, preferences, etc.)

[0246] Output: Standardized childcare information data

[0247] Step 2:

[0248] The device sends standardized childcare information data to the server. The data is transferred securely and efficiently using API requests. It is important that the data is transmitted in a state where its integrity is maintained.

[0249] Input: Standardized childcare information data

[0250] Output: Data sent to the server

[0251] Step 3:

[0252] The server stores the received childcare information data in a cloud database, which is used for later data analysis.

[0253] Input: Childcare information data sent to the server

[0254] Output: Data stored in a cloud database

[0255] Step 4:

[0256] A data analytics engine retrieves childcare information from a cloud database and analyzes the data using generative AI models and artificial general intelligence techniques. This analysis assesses children's nutritional status and identifies individualized improvement measures.

[0257] Input: Childcare information retrieved from a cloud database

[0258] Output: Analysis results (nutritional status assessment, specific improvement measures)

[0259] Step 5:

[0260] The server automatically generates customized nutrition advice and recommended food lists based on the data analysis results. This generative AI model is used to provide specific advice tailored to the user's specific needs.

[0261] Input: Analysis results

[0262] Output: Customized nutrition advice, recommended food list

[0263] Step 6:

[0264] The generated nutrition advice and recommended food list are sent to the user's device via a dedicated API. The server provides the information quickly while ensuring data security.

[0265] Input: Customized nutrition advice, recommended food lists

[0266] Output: Data sent to the user's terminal

[0267] Step 7:

[0268] The device displays the received nutrition advice and recommended food lists to the user, usually using a notification function to provide timely notification of important advice.

[0269] Input: Nutrition advice and recommended food list sent to your device

[0270] Output: Nutrition advice and recommended ingredients displayed to the user

[0271] Step 8:

[0272] Users can view customized nutrition advice and recommended ingredients lists and order ingredients and meals through the application, which automatically fills in the necessary information to simplify the ordering process.

[0273] Input: nutrition advice, recommended food list

[0274] Output: User orders ingredients and meals

[0275] Step 9:

[0276] The terminal sends the user's order information to the server and confirms the order in cooperation with the food delivery service. It is important that the order information is transmitted accurately.

[0277] Input: User's order information

[0278] Output: Order information sent to grocery delivery service

[0279] Step 10:

[0280] Users can input and submit feedback on the meals and services provided, including the quality of the meals and their children's reactions.

[0281] Input: User feedback

[0282] Output: Feedback saved on the device

[0283] Step 11:

[0284] The device sends the feedback data to the server using an API, which transfers the feedback information securely and quickly.

[0285] Input: Feedback stored on the device

[0286] Output: Feedback data sent to the server

[0287] Step 12:

[0288] The server evaluates the performance of the generative AI model based on the received feedback and improves the analysis algorithm, allowing the system to continuously evolve and provide more accurate and effective advice.

[0289] Input: Feedback data sent to the server

[0290] Output: Improved generative AI models, improved analysis algorithms

[0291] 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.

[0292] This invention is a comprehensive childcare support system that analyzes childcare information and provides customized childcare advice, and in particular has the function of recognizing the user's emotional state and incorporating it into the analysis. This system is composed of the following elements: a user interface for inputting childcare information, a function for sending the childcare information to a server, a data analysis function, a function for generating childcare advice, a function for sending the advice to the user's device, a feedback reception function, a function for improving the generated AI model, and an emotion engine.

[0293] Overall system configuration

[0294] 1. User Interface

[0295] Terminal

[0296] Users enter childcare information through a dedicated application on their smartphone, tablet, or other device. The interface is designed to be intuitive and easy to use, providing fields for quickly and accurately entering the necessary information.

[0297] 2. Sending childcare information

[0298] Terminal

[0299] The childcare information entered by the user is sent to the server via an API request, and the device converts this data into a standardized format to ensure data integrity.

[0300] 3. Data analysis and model use

[0301] server

[0302] The server stores the received parenting information in a cloud database. An analysis engine then retrieves the parenting information from the database and analyzes it using generative AI models and general artificial intelligence technology. This analysis evaluates the child's sleep patterns, nutritional status, and behavioral health, and identifies specific improvement measures.

[0303] 4. Generating parenting advice

[0304] server

[0305] Based on the results of the data analysis, customized parenting advice is automatically generated, tailored to the user's individual parenting needs and includes specific, practical content.

[0306] 5. Sending and Viewing Advice

[0307] server

[0308] The generated parenting advice is sent to the user's device via a dedicated API.

[0309] Terminal

[0310] The device displays the received parenting advice to the user, and can also use the notification function to notify the user of important advice in a timely manner.

[0311] 6. Leveraging Emotional Engines

[0312] Terminal

[0313] The device collects emotional data based on the user's voice input, facial expression recognition, text input (e.g., diary entries and comments), etc.

[0314] server

[0315] The server uses an emotion engine to analyze the user's emotional data. Based on the results of this analysis, the server can further customize parenting advice and provide optimal support based on the user's psychological state. For example, if the user is feeling stressed, the server can provide information on relaxation techniques and support groups.

[0316] 7. Receiving and Analyzing Feedback

[0317] User

[0318] Users can enter and submit feedback on the advice and solutions provided.

[0319] Terminal

[0320] The terminal receives feedback from the user and generates an HTTP POST request to send to the server.

[0321] server

[0322] The server evaluates the performance of the generative AI model based on the received feedback and improves the analysis algorithm. At the same time, it also incorporates feedback from the emotion engine to improve the system so that it can provide even more accurate advice.

[0323] Specific examples

[0324] User

[0325] For example, if a user is concerned about their two-year-old child's sleep patterns, they can input their child's sleep patterns through the application. Also, if a user is feeling stressed, the emotion engine will recognize that emotion.

[0326] Terminal

[0327] The terminal converts the childcare information and emotion data into an appropriate format and transmits it to the server.

[0328] server

[0329] The server analyzes the childcare information and emotional data, evaluates the user's psychological state using an emotion engine, and then suggests a sleep routine suitable for a two-year-old and ways for the user to relax.

[0330] Terminal

[0331] The device will display advice to the user on how to improve sleep and relax, and will notify them using notifications.

[0332] User

[0333] The user inputs the results of the proposed suggestions as feedback and submits them.

[0334] server

[0335] The server analyzes the feedback and emotion data and uses it to improve the accuracy of the model and emotion engine.

[0336] This allows the system to continuously evolve and provide advanced childcare support that responds to the individual childcare needs and psychological state of each user.

[0337] The processing flow will be explained below.

[0338] Step 1:

[0339] Users launch the application on their device and enter childcare information (e.g., their child's age, height, weight, sleep patterns, dietary habits, and behavioral data). They also record their emotional state using voice input and facial expression recognition functions.

[0340] Step 2:

[0341] The terminal collects parenting information and emotional data input by the user and converts it into a standardized format.

[0342] Step 3:

[0343] The device generates an HTTP POST request including the converted childcare information and emotion data and sends it to the server.

[0344] Step 4:

[0345] The server analyzes the received HTTP POST request, extracts childcare information data and emotion data, and stores them in a cloud database.

[0346] Step 5:

[0347] The server acquires childcare information data and emotion data from the cloud database and transfers them to the analysis engine.

[0348] Step 6:

[0349] The server's analysis engine uses generative AI models and general artificial intelligence technology to analyze childcare information data and evaluate children's sleep patterns, nutritional status, and behavioral health, while the emotion engine analyzes the user's emotional data and evaluates their psychological state.

[0350] Step 7:

[0351] The server generates specific parenting advice based on the analysis of the parenting information data and emotion data, and the advice is customized according to the child's parenting needs and the user's psychological state.

[0352] Step 8:

[0353] The server generates an HTTP response for transmitting the generated child-rearing advice to the user's terminal.

[0354] Step 9:

[0355] The device analyzes the HTTP response received from the server, extracts the parenting advice data, and displays it to the user. It selects a notification method (e.g., push notification or voice message) based on the emotion data and notifies the user at the appropriate time.

[0356] Step 10:

[0357] The user follows the provided advice and performs parenting, inputting the results as feedback and recording the new emotional state.

[0358] Step 11:

[0359] The device collects feedback data and new emotion data from the user, converts it into a standardized format, and generates an HTTP POST request to send it to the server.

[0360] Step 12:

[0361] The server analyzes the received feedback data and new emotion data, evaluates the performance of the generative AI model and emotion engine, and improves the analysis algorithm.

[0362] Step 13:

[0363] The server will use the improved model and emotion engine in the next analysis to provide more accurate advice tailored to the user's individual parenting needs and psychological state.

[0364] This process flow allows the system to continuously evolve, improving the user's parenting experience and providing more effective support.

[0365] Example 2

[0366] 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."

[0367] Parenting requires accurate advice that takes into account a child's developmental stage and individual needs. However, conventional systems struggle to provide detailed advice that takes into account the user's emotional state. Furthermore, they lack a mechanism for effectively utilizing user feedback on the advice provided to improve the system. This makes it difficult for users to efficiently input parenting information and receive practical parenting advice by analyzing that data.

[0368] 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.

[0369] In this invention, the server includes a data analysis means equipped with a generative AI model and general artificial intelligence technology for analyzing childcare information and emotion data, a means for generating childcare advice based on the analysis results and the user's emotional state, and a means for receiving feedback from the user and improving the generative AI model and emotion engine. This makes it possible to provide customized childcare advice that takes the user's emotional state into consideration, and the user's feedback can be effectively used to improve the system, thereby improving the accuracy and effectiveness of childcare support.

[0370] "Childcare information" refers to data related to childcare, such as a child's sleep patterns, diet, and behavior.

[0371] "Emotional data" is data that represents the user's psychological and emotional state, and is collected through voice input, facial expression recognition, text input, and the like.

[0372] A "user interface" is an interface through which a user inputs information and receives feedback from the system, and primarily refers to applications on smartphones and tablets.

[0373] A "generative AI model" is an algorithm or technology that generates new information based on given data, and often uses general artificial intelligence technology.

[0374] "General artificial intelligence technology" is artificial intelligence technology designed to perform a wide range of tasks, and is capable of analyzing a variety of data without specializing in any particular problem.

[0375] "Data analysis means" refers to a system or program for analyzing received data, and for appropriately processing childcare information and emotional data to gain insights.

[0376] "Childcare advice" is specific advice and recommendations on childcare that are generated based on the analysis results.

[0377] "Feedback" refers to the user's input of their reactions and results to the advice or solutions provided, and is information that is used to improve the system.

[0378] The "emotion engine" is an engine that analyzes input emotion data and determines the user's psychological state.

[0379] A "user terminal" is a device used by a user (e.g., a smartphone or tablet) to interact with the system.

[0380] The "notification function" is a function for notifying the user of important advice and information in a timely manner.

[0381] MODE FOR CARRYING OUT THE INVENTION

[0382] This invention is a comprehensive childcare support system that analyzes childcare information and provides customized childcare advice, and in particular has the function of recognizing the user's emotional state and incorporating it into the analysis. This system is composed of the following elements: a user interface for inputting childcare information, a function for sending childcare information and emotional data to a server, a data analysis function, a function for generating childcare advice, a function for sending advice to the user's device, a feedback reception function, a function for improving the generated AI model, and an emotion engine.

[0383] User Interface

[0384] Users can enter childcare information through a dedicated application on a smartphone, tablet, or other device. The interface is designed to be intuitive and easy to use, and provides fields for quickly and accurately entering the necessary information. Specifically, users can record their child's sleep time, diet, and behavior.

[0385] Sending parenting information and emotional data

[0386] The parenting information and emotion data entered by the user are sent to the server via API requests. The device converts this data into a standardized format to ensure data integrity. Emotion data is collected based on voice input, facial expression recognition, and text input (e.g., diary entries and comments).

[0387] Data analysis and model use

[0388] The server stores the received parenting information and emotional data in a cloud database. The analysis engine then retrieves the information from the database and analyzes it using generative AI models and general artificial intelligence techniques. This analysis evaluates the child's sleep patterns, nutritional status, and behavioral health and identifies specific improvement measures. For example, it detects disrupted sleep patterns and suggests appropriate countermeasures.

[0389] Generating parenting advice

[0390] Based on the data analysis results, customized parenting advice is automatically generated. This advice is tailored to the user's individual parenting needs and contains specific and practical content. For example, it suggests an appropriate sleep routine for a two-year-old.

[0391] Sending and viewing advice

[0392] The generated parenting advice is sent to the user's device via a dedicated API. The device displays the received parenting advice to the user. In addition, the notification function can be used to notify the user of important advice in a timely manner. For example, the user can be notified of "ways to improve children's sleep."

[0393] Utilizing the Emotion Engine

[0394] The device collects emotional data based on the user's voice input, facial expression recognition, text input, etc. The server then analyzes the user's emotional data using an emotion engine. Based on the results of this analysis, the system can further customize parenting advice and provide optimal support according to the user's psychological state. For example, if the user is feeling stressed, the system can provide information on relaxation techniques and support groups.

[0395] Receiving and analyzing feedback

[0396] The user inputs and submits feedback on the advice and solutions provided. The device receives the user's feedback, generates an HTTP POST request, and sends it to the server. The server evaluates the performance of the generative AI model based on the received feedback and improves the analysis algorithm. At the same time, it also incorporates feedback from the emotion engine to improve the system so that it can provide even more accurate advice.

[0397] For example, if a user is concerned about their two-year-old's sleep patterns, they can input their child's sleep patterns through the application. Also, if a user is feeling stressed, the emotion engine will recognize that emotion.

[0398] For example, the user can use the following prompt:

[0399] "I'm having trouble with my child's sleep patterns. Specifically, he wakes up every hour every night. I'm also finding this situation stressful. Can you give me some specific advice on how to resolve this?"

[0400] By using this system, users can receive parenting advice and psychological support tailored to their individual needs, improving the quality and efficiency of parenting.

[0401] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0402] Step 1:

[0403] The user inputs childcare information and emotional data.

[0404] Users launch a dedicated application on their smartphone or tablet and enter information about their child's sleep patterns, diet, behavior, and other childcare information, as well as their own emotional state (e.g., stress and satisfaction).The application is designed so that users can comfortably enter the required information into input fields.

[0405] Input: Childcare information (sleep time, diet, behavior, etc.) and user emotional data

[0406] Output: Input data saved on the device

[0407] Step 2:

[0408] The terminal formats the input data and sends it to the server.

[0409] The device converts the childcare information and emotional data entered by the user into a standardized format. Specifically, it standardizes the child's sleep time and dietary content into time units and nutritional units, and expresses emotional data as numbers and text. It then generates an API request and sends the data to the server using the HTTP POST method.

[0410] Input: User-entered standardized parenting information and emotional data

[0411] Output: Parenting information and emotion data sent to the server

[0412] Step 3:

[0413] The server stores the received data in a cloud database.

[0414] The server receives the parenting information and emotion data sent from the device. The received data is stored in a cloud database while ensuring security and privacy. Cloud services used include AWS and Google Cloud.

[0415] Input: Childcare information and emotional data sent from the device

[0416] Output: Data stored in a cloud database

[0417] Step 4:

[0418] The server analyzes the stored data.

[0419] The server retrieves stored parenting information and emotional data from the cloud database, processes the data using an analytics engine, and evaluates the child's sleep patterns, nutritional status, and behavioral health to identify issues. For example, it can detect disrupted sleep patterns and provide appropriate countermeasures.

[0420] Input: Parenting information and emotion data obtained from a cloud database.

[0421] Output: Analysis results (children's sleep patterns, nutritional status, behavioral assessment, etc.)

[0422] Step 5:

[0423] The server generates parenting advice using the generative AI model.

[0424] Based on the analyzed data, the server automatically generates parenting advice using a generative AI model (e.g., GPT-3). This advice is specific and practical, tailored to the user's individual parenting needs. For example, it suggests a suitable sleep routine for a two-year-old child or ways for the user to relax.

[0425] Input: Analysis results (child's sleep patterns, nutritional status, behavioral assessment, etc.)

[0426] Output: Customized parenting advice

[0427] Step 6:

[0428] The server transmits the generated advice to the user's terminal.

[0429] The server sends the generated parenting advice to the user's device via a dedicated API, using an HTTP POST request designed to maintain data integrity.

[0430] Input: Generated customized parenting advice

[0431] Output: Advice sent to the user's terminal

[0432] Step 7:

[0433] The terminal displays the advice to the user.

[0434] The device displays the parenting advice received from the server to the user within the application. It can also use the notification function to provide timely notification of important advice. Specifically, it notifies the user of "measures to improve children's sleep."

[0435] Input: Customized parenting advice received from the server

[0436] Output: Advice and notifications displayed to the user

[0437] Step 8:

[0438] The user enters feedback.

[0439] Users can enter feedback through the application about the parenting advice and solutions provided, including an assessment of the effectiveness of the advice and suggestions for further improvement.

[0440] Input: User feedback data (effectiveness of advice, areas for improvement, etc.)

[0441] Output: Feedback data stored on the device

[0442] Step 9:

[0443] The device sends the feedback to the server.

[0444] The terminal receives the user's feedback and generates an HTTP POST request to send it to the server, during which the feedback data is standardized and sent to the server in an appropriate format.

[0445] Input: User feedback data

[0446] Output: Feedback data sent to the server

[0447] Step 10:

[0448] The server analyzes the feedback and improves the system.

[0449] The server analyzes the received feedback and evaluates the performance of the generative AI model and emotion engine. It also uses the feedback to improve the data analysis algorithm. This improves the accuracy of the system and provides advanced childcare support that responds to the user's individual childcare needs and psychological state.

[0450] Input: Received feedback data

[0451] Output: A system with improved generative AI models and emotion engines

[0452] (Application example 2)

[0453] 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."

[0454] In child-rearing, especially for first-time parents, gathering child-rearing information and receiving appropriate advice is important. However, conventional child-rearing support systems have difficulty responding to the individual needs and emotional state of users, and lack specific support to reduce stress and anxiety. Furthermore, they often provide uniform advice that ignores the user's emotional state, making them ineffective. This leads to a decline in the quality of child-rearing support and to situations where parents are unable to receive appropriate support.

[0455] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0456] In this invention, the server includes a data analysis means equipped with a generative AI model and general artificial intelligence technology for analyzing childcare information, an emotion engine for recognizing the user's emotional state and incorporating it into the analysis, and a means for generating and providing customized childcare advice based on the emotion data. This makes it possible to integrate and analyze the childcare information and emotion data in real time and provide highly accurate childcare advice tailored to the user's individual needs and psychological state.

[0457] "Childcare information" is a general term for a wide range of data related to childcare, such as a child's developmental status, health condition, behavioral patterns, nutritional intake, and sleep patterns.

[0458] A "user interface" refers to a screen or input device through which a user inputs childcare information, and is provided in the form of a smartphone app, tablet app, or the like.

[0459] A "server" is a computer system that analyzes childcare information and emotional data via a network, and stores and distributes the results.

[0460] A "generative AI model" is an artificial intelligence-based algorithm and its implementation used to analyze parenting information and generate customized parenting advice.

[0461] "General artificial intelligence technology" is an artificial intelligence technology that is not dependent on a specific application and can perform a wide range of data analysis and recognition tasks.

[0462] "Data analysis means" refers to the functions and processes for analyzing childcare information using generative AI models and general artificial intelligence technology.

[0463] "Childcare advice" refers to specific advice or suggestions provided to the user based on the analyzed childcare information.

[0464] An "emotion engine" is a technology that recognizes a user's emotional state based on their voice, facial expressions, text input, etc., and incorporates that data into analysis.

[0465] A "user terminal" is a device such as a smartphone or tablet that allows a user to input childcare information and receive advice.

[0466] "Feedback" refers to the user's evaluation and opinions of the parenting advice provided and the system's functionality.

[0467] This invention is a comprehensive childcare support system that analyzes childcare information and provides customized childcare advice, and in particular has the function of recognizing the user's emotional state and incorporating it into the analysis. This system is composed of the following elements.

[0468] User Interface

[0469] User terminal

[0470] Users enter childcare information through a dedicated application on a smartphone, tablet, or other device. The interface is designed to be intuitive and easy to use, providing fields for quickly and accurately entering the necessary information. Voice input and facial recognition functions are also used to collect emotional data from users.

[0471] Sending childcare information

[0472] User terminal

[0473] The childcare information entered by the user is sent to the server via an API request, and the device converts this data into a standardized format to ensure data integrity.

[0474] Data analysis and model use

[0475] server

[0476] The server stores the received parenting information in a cloud database. An analysis engine then retrieves the parenting information from the database and analyzes it using generative AI models and general artificial intelligence technology. This analysis evaluates the child's sleep patterns, nutritional status, and behavioral health, and identifies specific improvement measures.

[0477] Utilizing the Emotion Engine

[0478] User terminal

[0479] Emotional data is collected based on the user's voice input, facial expression recognition, and text input (e.g., diary entries and comments).

[0480] server

[0481] The server uses an emotion engine to analyze the user's emotional data. Based on the results of this analysis, the server can further customize parenting advice and provide optimal support based on the user's psychological state. For example, if the user is feeling stressed, the server can provide information on relaxation techniques and support groups.

[0482] Generating parenting advice

[0483] server

[0484] Based on the results of the data analysis, customized parenting advice is automatically generated, tailored to the user's individual parenting needs and includes specific, practical content.

[0485] Sending and viewing advice

[0486] server

[0487] The generated parenting advice is sent to the user's device via a dedicated API.

[0488] User terminal

[0489] The device displays the received parenting advice to the user, and can also use the notification function to notify the user of important advice in a timely manner.

[0490] Receiving and analyzing feedback

[0491] User

[0492] Users can enter and submit feedback on the advice and solutions provided.

[0493] User terminal

[0494] The terminal receives feedback from the user and generates an HTTP POST request to send to the server.

[0495] server

[0496] The server evaluates the performance of the generative AI model based on the received feedback and improves the analysis algorithm. At the same time, it also incorporates feedback from the emotion engine to improve the system so that it can provide even more accurate advice.

[0497] Examples of concrete examples and prompts

[0498] User

[0499] For example, if a user is concerned about their two-year-old child's sleep patterns, they can input their child's sleep patterns through the application. Also, if a user is feeling stressed, the emotion engine will recognize that emotion.

[0500] User terminal

[0501] The terminal converts the childcare information and emotion data into an appropriate format and transmits it to the server.

[0502] server

[0503] The server analyzes the childcare information and emotional data, evaluates the user's psychological state using an emotion engine, and then suggests a sleep routine suitable for a two-year-old and ways for the user to relax.

[0504] User terminal

[0505] The device will display advice to the user on how to improve sleep and relax, and will notify them using notifications.

[0506] User

[0507] The user inputs the results of the proposed suggestions as feedback and submits them.

[0508] server

[0509] The server analyzes the feedback and emotion data and uses it to improve the accuracy of the model and emotion engine.

[0510] Example prompt sentence:

[0511] Your child's current sleep patterns:

[0512] Start time: 20:00

[0513] End time: 06:00

[0514] User's emotional state: Stress

[0515] What parenting advice should you offer?

[0516] By using this system, users can receive optimal childcare support in real time according to their emotional state.

[0517] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0518] Step 1:

[0519] The user device collects childcare information (such as the child's sleep patterns, nutritional intake, and behavioral records) from the user through a dedicated application, as well as emotional data through voice input and facial expression recognition.

[0520] Step 2:

[0521] The user device converts the collected parenting information and emotion data into an appropriate format and sends it to the server via an API request. Specifically, the data is encoded in JSON format and a POST request is sent to the appropriate endpoint on the server.

[0522] Step 3:

[0523] The server stores the received childcare information and emotion data in a cloud database. The stored data is available for the next analysis step. Standardization and validation are also performed to ensure data integrity.

[0524] Step 4:

[0525] The server retrieves the stored parenting information and emotional data and analyzes it using a data analysis tool. Specifically, it processes the data using a generative AI model to evaluate the child's sleep patterns, nutritional status, and behavioral health. At the same time, it also evaluates the user's psychological state using an emotional engine.

[0526] Step 5:

[0527] The server generates customized parenting advice for users based on the results of data analysis. The generative AI model and emotion engine work together to generate specific advice, such as "A specific routine is effective for children who sleep between 8:00 PM and 6:00 AM."

[0528] Step 6:

[0529] The generated parenting advice is sent to the user's device via a dedicated API. The advice is formatted in JSON, which the user's device parses and prepares for display.

[0530] Step 7:

[0531] The user device displays the received parenting advice to the user and notifies the user of important advice in a timely manner using a notification function, for example, by using in-app notifications or push notifications.

[0532] Step 8:

[0533] The user enters feedback into the application on the proposed advice or solution, for example, comments about the effectiveness of the advice or areas for improvement.

[0534] Step 9:

[0535] The user device sends the entered feedback to the server as an HTTP POST request, and the feedback data is also encoded in JSON format and sent to the appropriate endpoint on the server.

[0536] Step 10:

[0537] The server stores the received feedback in a database and uses it for analysis. Based on this feedback, the performance of the generative AI model and emotion engine is evaluated and further improved. This will improve the accuracy of parenting advice from the next time onwards.

[0538] In this way, by utilizing childcare information and emotional data to provide customized advice, users can receive more accurate and practical childcare support.

[0539] 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.

[0540] 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.

[0541] 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.

[0542] [Second embodiment]

[0543] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0544] 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.

[0545] 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).

[0546] 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.

[0547] 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.

[0548] 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).

[0549] 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.

[0550] 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.

[0551] 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.

[0552] 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.

[0553] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0554] 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."

[0555] This invention is a comprehensive childcare support system that analyzes childcare information and provides customized childcare advice. This system is composed of the following elements: a user interface for inputting childcare information, a function for sending the childcare information to a server, a data analysis function, a function for generating childcare advice, a function for sending advice to a user's device, a function for receiving feedback, and a function for improving the generated AI model.

[0556] Overall system configuration

[0557] 1. User Interface

[0558] Terminal

[0559] Users enter childcare information through a dedicated application using a smartphone, tablet, or other device. The interface is designed to be intuitive and easy to use, providing fields for quickly and accurately entering the necessary information.

[0560] 2. Sending childcare information

[0561] Terminal

[0562] The childcare information entered by the user is sent to the server via an API request, and the device converts this data into a standardized format to ensure data integrity.

[0563] 3. Data analysis and model use

[0564] server

[0565] The server stores the received parenting information in a cloud database. An analysis engine then retrieves the parenting information from the database and analyzes it using generative AI models and general artificial intelligence technology. This analysis evaluates the child's sleep patterns, nutritional status, and behavioral health, and identifies specific improvement measures.

[0566] 4. Generating parenting advice

[0567] server

[0568] Based on the results of the data analysis, customized parenting advice is automatically generated, tailored to the user's individual parenting needs and includes specific, practical content.

[0569] 5. Sending and Viewing Advice

[0570] server

[0571] The generated parenting advice is sent to the user's device via a dedicated API.

[0572] Terminal

[0573] The device displays the received parenting advice to the user, and can also use the notification function to notify the user of important advice in a timely manner.

[0574] 6. Receiving and Analyzing Feedback

[0575] User

[0576] Users can enter and submit feedback on the advice and solutions provided.

[0577] Terminal

[0578] The terminal transmits the feedback data to the server.

[0579] server

[0580] The server evaluates the performance of the generative AI model based on the received feedback and improves the analysis algorithm, allowing the system to continuously evolve and provide more accurate and effective parenting advice.

[0581] Specific examples

[0582] User

[0583] For example, consider a case where a user is concerned about the sleep patterns of their two-year-old child. The user enters the child's sleep patterns (bedtime, wake-up time, number of nighttime awakenings, etc.) through an application.

[0584] Terminal

[0585] The terminal converts this information into an appropriate format and sends it to the server.

[0586] server

[0587] The server analyzes the received data and generates specific sleep improvement measures (e.g., recommending bath time and reading picture books to get the child to bed at 9 p.m.) using a generative AI model that suggests a sleep routine suitable for a two-year-old.

[0588] Terminal

[0589] The device displays the sleep improvement measures received from the server to the user and uses the notification function to inform the user of important suggestions.

[0590] User

[0591] The user tries these suggestions for a week, then enters the results as feedback and submits it.

[0592] server

[0593] The server analyzes this feedback and uses it as data to improve the accuracy of the model.

[0594] This system will enable parents to receive specific and useful advice for their individual child-rearing concerns, and is expected to improve the quality of child-rearing.

[0595] The processing flow will be explained below.

[0596] Step 1:

[0597] The user launches the application on the terminal and inputs childcare information (for example, the child's age, height, weight, sleep patterns, dietary content, behavioral data, etc.).

[0598] Step 2:

[0599] The terminal converts the childcare information input by the user into a standardized format and generates an HTTP POST request.

[0600] Step 3:

[0601] The terminal sends the generated HTTP POST request to the server.

[0602] Step 4:

[0603] The server analyzes the received HTTP POST request, extracts the childcare information data, and stores it in a cloud database.

[0604] Step 5:

[0605] The server retrieves the stored childcare information data from the cloud database and transfers it to the analysis engine.

[0606] Step 6:

[0607] The server's analytical engine uses generative AI models and general artificial intelligence technology to analyze childcare information data and assess children's sleep patterns, nutritional status, and behavioral health.

[0608] Step 7:

[0609] The server generates specific parenting advice (e.g., optimal sleep schedules, nutritionally balanced meal plans, behavioral improvements) based on the analysis results.

[0610] Step 8:

[0611] The server generates an HTTP response for transmitting the generated child-rearing advice to the user's terminal.

[0612] Step 9:

[0613] The terminal analyzes the HTTP response received from the server, extracts the child-rearing advice data, and displays it to the user.

[0614] Step 10:

[0615] If necessary, the device will notify the user of important advice via push notifications.

[0616] Step 11:

[0617] The user follows the advice provided to them and performs childcare, and inputs the results as feedback.

[0618] Step 12:

[0619] The terminal receives feedback from the user and generates an HTTP POST request to send to the server.

[0620] Step 13:

[0621] The server analyzes the received feedback data and uses it to improve the accuracy of the generative AI model.

[0622] Step 14:

[0623] Based on the feedback, the server improves the generative AI model and general artificial intelligence technology and reflects this in the next analysis.

[0624] Example 1

[0625] 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."

[0626] Conventional childcare support systems have had problems with the complicated input and management of childcare information, and the inability to perform sufficient data analysis to provide appropriate advice. Furthermore, the childcare information was not personalized enough, making it difficult to generate appropriate advice for each user. Furthermore, there was no mechanism in place to reflect feedback on advice in the system, making it difficult to evolve and improve the system.

[0627] 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.

[0628] In this invention, the server includes a means for converting childcare information into a standardized data format, a means for storing the childcare information in a cloud database, and a data analysis means equipped with a generative AI model and general artificial intelligence technology for analyzing the childcare information. This enables efficient management of childcare information and advanced data analysis. Furthermore, it automatically generates personalized childcare advice based on the analysis results, enabling continuous system improvement through feedback.

[0629] "Childcare information" refers to various data related to childcare, such as children's sleep patterns, diet, and behavior.

[0630] "User interface" refers to an interface through which a user inputs or obtains information.

[0631] "Data format" refers to a format for standardizing and processing information.

[0632] A "cloud database" refers to an online database for storing and managing data via the Internet.

[0633] A "generative AI model" refers to a machine learning model that uses artificial intelligence technology to automatically process specific tasks.

[0634] "General artificial intelligence technology" refers to artificial intelligence technology that is not limited to specific tasks and can be used for a wide range of applications.

[0635] "Data analysis tools" refer to methods and processes for collecting, analyzing, and evaluating data.

[0636] A "prompt sentence" refers to a sentence used to give instructions or ask questions to a generative AI model.

[0637] "Private API" refers to an application program interface for accessing specific functions or data.

[0638] "Feedback" refers to information used to collect user ratings and opinions.

[0639] MODE FOR CARRYING OUT THE INVENTION

[0640] The present invention is a comprehensive childcare support system that analyzes childcare information and provides customized childcare advice. This system includes a user interface for inputting childcare information, a function for sending the childcare information to a server, a data analysis function, a function for generating childcare advice, a function for sending the advice to a user terminal, a function for receiving feedback, and a function for improving the generated AI model.

[0641] Hardware and software used

[0642] Device: The user uses a smartphone or tablet, on which a dedicated application is installed.

[0643] Server: A server built in a cloud computing environment is used. Generative AI models and general artificial intelligence technology are implemented as data analysis engines.

[0644] Database: Use a cloud database to store childcare information.

[0645] System Operation Overview

[0646] Entering childcare information via a user interface

[0647] Users can open a dedicated application on their smartphone or tablet and input childcare information such as their child's sleep patterns, diet, and behavior. For example, they can input information such as "the child frequently wakes up at night."

[0648] Sending childcare information to the server

[0649] The device converts the childcare information entered by the user into a standardized data format, such as JSON, and sends it to the server as an API request, which then stores the data in a cloud database.

[0650] Analyzing the data and using the model

[0651] The server retrieves childcare information from a cloud database and analyzes the data using an analytical engine, utilizing generative AI models and general artificial intelligence techniques. The analysis results are used to assess children's sleep patterns, nutritional status, and behavioral health, and identify specific improvement measures.

[0652] Generating parenting advice

[0653] The server generates prompts based on the analysis results, such as "Generate specific suggestions to improve a two-year-old's sleep patterns," and issues them to the generative AI model. The generative AI model then generates specific childcare advice based on these prompts, such as "Read picture books before bedtime and avoid watching TV for 30 minutes before bed."

[0654] Sending and viewing advice

[0655] The generated parenting advice is sent to the user's device via a dedicated API, where it is displayed to the user and notifies them of important advice in a timely manner using the notification function.

[0656] Receiving and analyzing feedback

[0657] The user enters feedback about the results of following the provided advice into a dedicated application. The device then sends this feedback data to a server, which analyzes the received feedback data and uses it to evaluate and improve the performance of the generative AI model.

[0658] Examples of concrete examples and prompts

[0659] For example, here's a scenario where a user enters concerns about their 2-year-old's sleep patterns:

[0660] The user enters "frequent nighttime awakenings" into the application. The device converts this information into JSON format and sends it to the server. The server uses an analysis engine to create "advice to reduce nighttime awakenings in a 2-year-old child" using a generative AI model, providing specific advice such as "read picture books before bedtime and avoid watching TV for 30 minutes before bed." The device displays this to the user and uses the notification function to inform them of important advice.

[0661] An example prompt is "Generate specific suggestions to improve a two-year-old's sleep patterns."

[0662] The present invention is expected to enable efficient management of child-rearing information and provision of personalized advice, thereby effectively supporting users in child-rearing.

[0663] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0664] Step 1:

[0665] Entering childcare information

[0666] The user opens the dedicated application on a smartphone or tablet. The application's user interface provides a form for inputting childcare information. The user enters specific childcare information into the form, such as the child's sleep patterns, diet, and behavior. Input information includes "bedtime," "wake-up time," and "number of nighttime awakenings."

[0667] Input: Childcare information (e.g., bedtime, wake-up time, number of nighttime awakenings)

[0668] Output: The input childcare information is formatted as data.

[0669] Step 2:

[0670] Formatting and sending childcare information

[0671] The device receives the childcare information entered by the user and converts it into a standardized data format (e.g., JSON format). The formatted data is prepared as an API request and sent to the server.

[0672] Input: Childcare information entered in the input form

[0673] Output: Parenting information converted to JSON format

[0674] Step 3:

[0675] Receiving and storing data

[0676] The server receives the API request sent from the device and stores the sent childcare information in a cloud database, which is then used for later analysis.

[0677] Input: JSON format childcare information data

[0678] Output: Parenting information stored in a cloud database

[0679] Step 4:

[0680] Data acquisition and analysis

[0681] The server retrieves stored parenting information from a cloud database. The retrieved data is analyzed using generative AI models and artificial general intelligence techniques. This analysis process evaluates children's sleep patterns, nutritional status, and behavioral health, and identifies specific improvement measures.

[0682] Input: Parenting information stored in a cloud database

[0683] Output: Analysis results (evaluation of children's sleep patterns, nutritional status, behavioral health, etc.)

[0684] Step 5:

[0685] Generating parenting advice

[0686] The server generates a prompt based on the analysis results and inputs it into the generative AI model. An example of a prompt is "Generate specific suggestions to improve the sleep patterns of a two-year-old child." The generative AI model generates specific parenting advice based on this prompt.

[0687] Input: Analysis results and generated prompt statements

[0688] Output: Generated parenting advice

[0689] Step 6:

[0690] Sending parenting advice

[0691] The server sends the generated parenting advice to the user's device via a dedicated API. This API request includes the generated advice.

[0692] Input: Generated parenting advice

[0693] Output: Parenting advice sent in API request

[0694] Step 7:

[0695] Receiving and viewing advice

[0696] The device displays the childcare advice received from the server. The advice display screen is displayed within the application, and important advice is notified to the user using the notification function.

[0697] Input: Parenting advice sent in API request

[0698] Output: Parenting advice displayed within the application

[0699] Step 8:

[0700] Enter and submit feedback

[0701] The user follows the advice provided and inputs the results into the application. The feedback content may be, for example, "I've woken up less at night." The device then sends this feedback data back to the server as an API request.

[0702] Input: User feedback information

[0703] Output: Feedback information converted to JSON format

[0704] Step 9:

[0705] Receiving and analyzing feedback

[0706] The server receives the feedback data sent from the device and analyzes it to evaluate and improve the performance of the generative AI model, thereby improving the accuracy of parenting advice from the next time onwards.

[0707] Input: Feedback information in JSON format

[0708] Output: Model performance evaluation and improvement suggestions

[0709] (Application example 1)

[0710] 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."

[0711] Conventional childcare support systems not only analyze childcare information and provide advice, but also lack the ability to provide customized meal suggestions based on each child's nutritional needs. They also lack the functionality to provide advice in a format that parents can immediately implement and receive feedback. This makes it difficult to solve the specific nutritional management challenges faced by parents.

[0712] 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.

[0713] In this invention, the server includes means for providing a user interface for inputting childcare information, means for transmitting the childcare information to the server, means for analyzing the childcare information using a generative AI model and general artificial intelligence (AI) technology, means for generating childcare advice based on the analysis results, means for transmitting the generated childcare advice to a user terminal, means for displaying the advice on the user terminal, means for receiving feedback from the user and improving the generative AI model, means for providing customized nutritional advice based on the childcare information and generating a recommended ingredient list, and means for ordering ingredients and meals from the user terminal. This allows parents to receive specific and actionable dietary advice tailored to their children's individual nutritional needs, thereby optimally supporting their children's health and growth.

[0714] "Childcare information" refers to specific data related to childcare, such as a child's age, allergy information, food preferences, sleep patterns, and behavioral health.

[0715] "User interface" refers to the part of a computer system through which a user inputs childcare information, and refers to an intuitive and easy-to-use input means, including devices such as smartphones and tablets.

[0716] "Generative AI models" are algorithms and systems that use artificial intelligence techniques to generate customized advice and suggestions based on analyzed parenting information.

[0717] "General artificial intelligence technology" refers to artificial intelligence technology that can be applied to a variety of uses, not just specific problems.

[0718] "Data analysis means" refers to a combination of software and hardware used to analyze collected childcare information and identify specific patterns and improvements.

[0719] The "child-rearing advice generating means" is a function that automatically generates specific and actionable child-rearing advice based on the analysis results obtained by the data analysis means.

[0720] A "user terminal" is an electronic terminal such as a smartphone, tablet, or PC that allows a user to input childcare information and receive advice.

[0721] The "feedback receiving means" refers to an interface and communication means for receiving opinions and reactions from users.

[0722] "Model Improvement Tools" means the processes and techniques for evaluating and improving the performance of a Generative AI Model based on received feedback.

[0723] "Nutrition advice" is specific dietary suggestions and recommended food lists based on a child's individual nutritional needs.

[0724] The "recommended food list" is a list of foods that are appropriate for supporting children's health and growth, selected by a generative AI model.

[0725] The "ingredient ordering means" is a function that allows users to order ingredients and meals online based on a recommended ingredient list.

[0726] The present invention is a comprehensive childcare support system for analyzing childcare information and providing customized childcare advice. As an application example, a specific embodiment focusing on a food delivery service will be described.

[0727] Overall system configuration

[0728] 1. User Interface

[0729] Terminal

[0730] Users enter childcare information through a dedicated application using a smartphone, tablet, or other device. The interface is designed to be intuitive and easy to use, providing fields for quickly and accurately entering the necessary information.

[0731] 2. Sending childcare information

[0732] Terminal

[0733] The childcare information entered by the user is sent to the server via an API request, and the device converts this data into a standardized format to ensure data integrity.

[0734] 3. Data analysis and model use

[0735] server

[0736] The server stores the received childcare information in a cloud database. The analysis engine then retrieves the information from the database and analyzes it using generative AI models and general artificial intelligence technology. This analysis evaluates the child's nutritional status and generates specific nutritional advice and a recommended food list.

[0737] 4. Generating nutrition advice

[0738] server

[0739] Based on the data analysis results, customized nutrition advice is automatically generated that is specific and practical, tailored to the user's individual parenting needs.

[0740] 5. Sending and Viewing Advice

[0741] server

[0742] The generated nutrition advice is sent to the user's device via a dedicated API.

[0743] Terminal

[0744] The device displays the received nutrition advice to the user, and can also use the notification function to notify the user of important advice in a timely manner.

[0745] 6. Ordering ingredients

[0746] User

[0747] Users can view customized nutrition advice and recommended ingredients lists, and order ingredients and meals directly through the application.

[0748] Terminal

[0749] The terminal sends the order information to a server and works with the food delivery service to confirm the order.

[0750] 7. Receiving and Analyzing Feedback

[0751] User

[0752] Users can input and submit feedback on the food and service provided.

[0753] Terminal

[0754] The terminal transmits the feedback data to the server.

[0755] server

[0756] The server evaluates the performance of the generative AI model based on the received feedback and improves the analysis algorithm, allowing the system to continuously evolve and provide more accurate and effective nutritional advice.

[0757] Specific examples

[0758] Consider a case where a user is having trouble managing the nutrition of their two-year-old child. The user enters the child's dietary information (allergies, disliked ingredients, etc.) through the application. For example, the user can enter, "My child is two years old and has a peanut allergy. He likes fruit but doesn't eat many vegetables." Based on this information, the system generates appropriate nutrition advice and a recommended ingredient list, which the parent receives. Furthermore, the parent can order ingredients and meals directly through the app, enabling immediate implementation.

[0759] This allows parents to receive a specific and customized list of ingredients based on their child's nutritional needs, improving the quality of their childcare with access to a quality food delivery service.

[0760] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0761] Step 1:

[0762] Users use a device such as a smartphone or tablet to enter childcare information through a dedicated application, including the child's age, allergies, and dietary preferences. This information is then saved on the device as childcare information and converted into a standardized format.

[0763] Input: Childcare information entered by the user (age, allergy information, preferences, etc.)

[0764] Output: Standardized childcare information data

[0765] Step 2:

[0766] The device sends standardized childcare information data to the server. The data is transferred securely and efficiently using API requests. It is important that the data is transmitted in a state where its integrity is maintained.

[0767] Input: Standardized childcare information data

[0768] Output: Data sent to the server

[0769] Step 3:

[0770] The server stores the received childcare information data in a cloud database, which is used for later data analysis.

[0771] Input: Childcare information data sent to the server

[0772] Output: Data stored in a cloud database

[0773] Step 4:

[0774] A data analytics engine retrieves childcare information from a cloud database and analyzes the data using generative AI models and artificial general intelligence techniques. This analysis assesses children's nutritional status and identifies individualized improvement measures.

[0775] Input: Childcare information retrieved from a cloud database

[0776] Output: Analysis results (nutritional status assessment, specific improvement measures)

[0777] Step 5:

[0778] The server automatically generates customized nutrition advice and recommended food lists based on the data analysis results. This generative AI model is used to provide specific advice tailored to the user's specific needs.

[0779] Input: Analysis results

[0780] Output: Customized nutrition advice, recommended food list

[0781] Step 6:

[0782] The generated nutrition advice and recommended food list are sent to the user's device via a dedicated API. The server provides the information quickly while ensuring data security.

[0783] Input: Customized nutrition advice, recommended food lists

[0784] Output: Data sent to the user's terminal

[0785] Step 7:

[0786] The device displays the received nutrition advice and recommended food lists to the user, usually using a notification function to provide timely notification of important advice.

[0787] Input: Nutrition advice and recommended food list sent to your device

[0788] Output: Nutrition advice and recommended ingredients displayed to the user

[0789] Step 8:

[0790] Users can view customized nutrition advice and recommended ingredients lists and order ingredients and meals through the application, which automatically fills in the necessary information to simplify the ordering process.

[0791] Input: nutrition advice, recommended food list

[0792] Output: User orders ingredients and meals

[0793] Step 9:

[0794] The terminal sends the user's order information to the server and confirms the order in cooperation with the food delivery service. It is important that the order information is transmitted accurately.

[0795] Input: User's order information

[0796] Output: Order information sent to grocery delivery service

[0797] Step 10:

[0798] Users can input and submit feedback on the meals and services provided, including the quality of the meals and their children's reactions.

[0799] Input: User feedback

[0800] Output: Feedback saved on the device

[0801] Step 11:

[0802] The device sends the feedback data to the server using an API, which transfers the feedback information securely and quickly.

[0803] Input: Feedback stored on the device

[0804] Output: Feedback data sent to the server

[0805] Step 12:

[0806] The server evaluates the performance of the generative AI model based on the received feedback and improves the analysis algorithm, allowing the system to continuously evolve and provide more accurate and effective advice.

[0807] Input: Feedback data sent to the server

[0808] Output: Improved generative AI models, improved analysis algorithms

[0809] 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.

[0810] This invention is a comprehensive childcare support system that analyzes childcare information and provides customized childcare advice, and in particular has the function of recognizing the user's emotional state and incorporating it into the analysis. This system is composed of the following elements: a user interface for inputting childcare information, a function for sending the childcare information to a server, a data analysis function, a function for generating childcare advice, a function for sending the advice to the user's device, a feedback reception function, a function for improving the generated AI model, and an emotion engine.

[0811] Overall system configuration

[0812] 1. User Interface

[0813] Terminal

[0814] Users enter childcare information through a dedicated application on their smartphone, tablet, or other device. The interface is designed to be intuitive and easy to use, providing fields for quickly and accurately entering the necessary information.

[0815] 2. Sending childcare information

[0816] Terminal

[0817] The childcare information entered by the user is sent to the server via an API request, and the device converts this data into a standardized format to ensure data integrity.

[0818] 3. Data analysis and model use

[0819] server

[0820] The server stores the received parenting information in a cloud database. An analysis engine then retrieves the parenting information from the database and analyzes it using generative AI models and general artificial intelligence technology. This analysis evaluates the child's sleep patterns, nutritional status, and behavioral health, and identifies specific improvement measures.

[0821] 4. Generating parenting advice

[0822] server

[0823] Based on the results of the data analysis, customized parenting advice is automatically generated, tailored to the user's individual parenting needs and includes specific, practical content.

[0824] 5. Sending and Viewing Advice

[0825] server

[0826] The generated parenting advice is sent to the user's device via a dedicated API.

[0827] Terminal

[0828] The device displays the received parenting advice to the user, and can also use the notification function to notify the user of important advice in a timely manner.

[0829] 6. Leveraging Emotional Engines

[0830] Terminal

[0831] The device collects emotional data based on the user's voice input, facial expression recognition, text input (e.g., diary entries and comments), etc.

[0832] server

[0833] The server uses an emotion engine to analyze the user's emotional data. Based on the results of this analysis, the server can further customize parenting advice and provide optimal support based on the user's psychological state. For example, if the user is feeling stressed, the server can provide information on relaxation techniques and support groups.

[0834] 7. Receiving and Analyzing Feedback

[0835] User

[0836] Users can enter and submit feedback on the advice and solutions provided.

[0837] Terminal

[0838] The terminal receives feedback from the user and generates an HTTP POST request to send to the server.

[0839] server

[0840] The server evaluates the performance of the generative AI model based on the received feedback and improves the analysis algorithm. At the same time, it also incorporates feedback from the emotion engine to improve the system so that it can provide even more accurate advice.

[0841] Specific examples

[0842] User

[0843] For example, if a user is concerned about their two-year-old child's sleep patterns, they can input their child's sleep patterns through the application. Also, if a user is feeling stressed, the emotion engine will recognize that emotion.

[0844] Terminal

[0845] The terminal converts the childcare information and emotion data into an appropriate format and transmits it to the server.

[0846] server

[0847] The server analyzes the childcare information and emotional data, evaluates the user's psychological state using an emotion engine, and then suggests a sleep routine suitable for a two-year-old and ways for the user to relax.

[0848] Terminal

[0849] The device will display advice to the user on how to improve sleep and relax, and will notify them using notifications.

[0850] User

[0851] The user inputs the results of the proposed suggestions as feedback and submits them.

[0852] server

[0853] The server analyzes the feedback and emotion data and uses it to improve the accuracy of the model and emotion engine.

[0854] This allows the system to continuously evolve and provide advanced childcare support that responds to the individual childcare needs and psychological state of each user.

[0855] The processing flow will be explained below.

[0856] Step 1:

[0857] Users launch the application on their device and enter childcare information (e.g., their child's age, height, weight, sleep patterns, dietary habits, and behavioral data). They also record their emotional state using voice input and facial expression recognition functions.

[0858] Step 2:

[0859] The terminal collects parenting information and emotional data input by the user and converts it into a standardized format.

[0860] Step 3:

[0861] The device generates an HTTP POST request including the converted childcare information and emotion data and sends it to the server.

[0862] Step 4:

[0863] The server analyzes the received HTTP POST request, extracts childcare information data and emotion data, and stores them in a cloud database.

[0864] Step 5:

[0865] The server acquires childcare information data and emotion data from the cloud database and transfers them to the analysis engine.

[0866] Step 6:

[0867] The server's analysis engine uses generative AI models and general artificial intelligence technology to analyze childcare information data and evaluate children's sleep patterns, nutritional status, and behavioral health, while the emotion engine analyzes the user's emotional data and evaluates their psychological state.

[0868] Step 7:

[0869] The server generates specific parenting advice based on the analysis of the parenting information data and emotion data, and the advice is customized according to the child's parenting needs and the user's psychological state.

[0870] Step 8:

[0871] The server generates an HTTP response for transmitting the generated child-rearing advice to the user's terminal.

[0872] Step 9:

[0873] The device analyzes the HTTP response received from the server, extracts the parenting advice data, and displays it to the user. It selects a notification method (e.g., push notification or voice message) based on the emotion data and notifies the user at the appropriate time.

[0874] Step 10:

[0875] The user follows the provided advice and performs parenting, inputting the results as feedback and recording the new emotional state.

[0876] Step 11:

[0877] The device collects feedback data and new emotion data from the user, converts it into a standardized format, and generates an HTTP POST request to send it to the server.

[0878] Step 12:

[0879] The server analyzes the received feedback data and new emotion data, evaluates the performance of the generative AI model and emotion engine, and improves the analysis algorithm.

[0880] Step 13:

[0881] The server will use the improved model and emotion engine in the next analysis to provide more accurate advice tailored to the user's individual parenting needs and psychological state.

[0882] This process flow allows the system to continuously evolve, improving the user's parenting experience and providing more effective support.

[0883] Example 2

[0884] 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."

[0885] Parenting requires accurate advice that takes into account a child's developmental stage and individual needs. However, conventional systems struggle to provide detailed advice that takes into account the user's emotional state. Furthermore, they lack a mechanism for effectively utilizing user feedback on the advice provided to improve the system. This makes it difficult for users to efficiently input parenting information and receive practical parenting advice by analyzing that data.

[0886] 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.

[0887] In this invention, the server includes a data analysis means equipped with a generative AI model and general artificial intelligence technology for analyzing childcare information and emotion data, a means for generating childcare advice based on the analysis results and the user's emotional state, and a means for receiving feedback from the user and improving the generative AI model and emotion engine. This makes it possible to provide customized childcare advice that takes the user's emotional state into consideration, and the user's feedback can be effectively used to improve the system, thereby improving the accuracy and effectiveness of childcare support.

[0888] "Childcare information" refers to data related to childcare, such as a child's sleep patterns, diet, and behavior.

[0889] "Emotional data" is data that represents the user's psychological and emotional state, and is collected through voice input, facial expression recognition, text input, and the like.

[0890] A "user interface" is an interface through which a user inputs information and receives feedback from the system, and primarily refers to applications on smartphones and tablets.

[0891] A "generative AI model" is an algorithm or technology that generates new information based on given data, and often uses general artificial intelligence technology.

[0892] "General artificial intelligence technology" is artificial intelligence technology designed to perform a wide range of tasks, and is capable of analyzing a variety of data without specializing in any particular problem.

[0893] "Data analysis means" refers to a system or program for analyzing received data, and for appropriately processing childcare information and emotional data to gain insights.

[0894] "Childcare advice" is specific advice and recommendations on childcare that are generated based on the analysis results.

[0895] "Feedback" refers to the user's input of their reactions and results to the advice or solutions provided, and is information that is used to improve the system.

[0896] The "emotion engine" is an engine that analyzes input emotion data and determines the user's psychological state.

[0897] A "user terminal" is a device used by a user (e.g., a smartphone or tablet) to interact with the system.

[0898] The "notification function" is a function for notifying the user of important advice and information in a timely manner.

[0899] MODE FOR CARRYING OUT THE INVENTION

[0900] This invention is a comprehensive childcare support system that analyzes childcare information and provides customized childcare advice, and in particular has the function of recognizing the user's emotional state and incorporating it into the analysis. This system is composed of the following elements: a user interface for inputting childcare information, a function for sending childcare information and emotional data to a server, a data analysis function, a function for generating childcare advice, a function for sending advice to the user's device, a feedback reception function, a function for improving the generated AI model, and an emotion engine.

[0901] User Interface

[0902] Users can enter childcare information through a dedicated application on a smartphone, tablet, or other device. The interface is designed to be intuitive and easy to use, and provides fields for quickly and accurately entering the necessary information. Specifically, users can record their child's sleep time, diet, and behavior.

[0903] Sending parenting information and emotional data

[0904] The parenting information and emotion data entered by the user are sent to the server via API requests. The device converts this data into a standardized format to ensure data integrity. Emotion data is collected based on voice input, facial expression recognition, and text input (e.g., diary entries and comments).

[0905] Data analysis and model use

[0906] The server stores the received parenting information and emotional data in a cloud database. The analysis engine then retrieves the information from the database and analyzes it using generative AI models and general artificial intelligence techniques. This analysis evaluates the child's sleep patterns, nutritional status, and behavioral health and identifies specific improvement measures. For example, it detects disrupted sleep patterns and suggests appropriate countermeasures.

[0907] Generating parenting advice

[0908] Based on the data analysis results, customized parenting advice is automatically generated. This advice is tailored to the user's individual parenting needs and contains specific and practical content. For example, it suggests an appropriate sleep routine for a two-year-old.

[0909] Sending and viewing advice

[0910] The generated parenting advice is sent to the user's device via a dedicated API. The device displays the received parenting advice to the user. In addition, the notification function can be used to notify the user of important advice in a timely manner. For example, the user can be notified of "ways to improve children's sleep."

[0911] Utilizing the Emotion Engine

[0912] The device collects emotional data based on the user's voice input, facial expression recognition, text input, etc. The server then analyzes the user's emotional data using an emotion engine. Based on the results of this analysis, the system can further customize parenting advice and provide optimal support according to the user's psychological state. For example, if the user is feeling stressed, the system can provide information on relaxation techniques and support groups.

[0913] Receiving and analyzing feedback

[0914] The user inputs and submits feedback on the advice and solutions provided. The device receives the user's feedback, generates an HTTP POST request, and sends it to the server. The server evaluates the performance of the generative AI model based on the received feedback and improves the analysis algorithm. At the same time, it also incorporates feedback from the emotion engine to improve the system so that it can provide even more accurate advice.

[0915] For example, if a user is concerned about their two-year-old's sleep patterns, they can input their child's sleep patterns through the application. Also, if a user is feeling stressed, the emotion engine will recognize that emotion.

[0916] For example, the user can use the following prompt:

[0917] "I'm having trouble with my child's sleep patterns. Specifically, he wakes up every hour every night. I'm also finding this situation stressful. Can you give me some specific advice on how to resolve this?"

[0918] By using this system, users can receive parenting advice and psychological support tailored to their individual needs, improving the quality and efficiency of parenting.

[0919] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0920] Step 1:

[0921] The user inputs childcare information and emotional data.

[0922] Users launch a dedicated application on their smartphone or tablet and enter information about their child's sleep patterns, diet, behavior, and other childcare information, as well as their own emotional state (e.g., stress and satisfaction).The application is designed so that users can comfortably enter the required information into input fields.

[0923] Input: Childcare information (sleep time, diet, behavior, etc.) and user emotional data

[0924] Output: Input data saved on the device

[0925] Step 2:

[0926] The terminal formats the input data and sends it to the server.

[0927] The device converts the childcare information and emotional data entered by the user into a standardized format. Specifically, it standardizes the child's sleep time and dietary content into time units and nutritional units, and expresses emotional data as numbers and text. It then generates an API request and sends the data to the server using the HTTP POST method.

[0928] Input: User-entered standardized parenting information and emotional data

[0929] Output: Parenting information and emotion data sent to the server

[0930] Step 3:

[0931] The server stores the received data in a cloud database.

[0932] The server receives the parenting information and emotion data sent from the device. The received data is stored in a cloud database while ensuring security and privacy. Cloud services used include AWS and Google Cloud.

[0933] Input: Childcare information and emotional data sent from the device

[0934] Output: Data stored in a cloud database

[0935] Step 4:

[0936] The server analyzes the stored data.

[0937] The server retrieves stored parenting information and emotional data from the cloud database, processes the data using an analytics engine, and evaluates the child's sleep patterns, nutritional status, and behavioral health to identify issues. For example, it can detect disrupted sleep patterns and provide appropriate countermeasures.

[0938] Input: Parenting information and emotion data obtained from a cloud database.

[0939] Output: Analysis results (children's sleep patterns, nutritional status, behavioral assessment, etc.)

[0940] Step 5:

[0941] The server generates parenting advice using the generative AI model.

[0942] Based on the analyzed data, the server automatically generates parenting advice using a generative AI model (e.g., GPT-3). This advice is specific and practical, tailored to the user's individual parenting needs. For example, it suggests a suitable sleep routine for a two-year-old child or ways for the user to relax.

[0943] Input: Analysis results (child's sleep patterns, nutritional status, behavioral assessment, etc.)

[0944] Output: Customized parenting advice

[0945] Step 6:

[0946] The server transmits the generated advice to the user's terminal.

[0947] The server sends the generated parenting advice to the user's device via a dedicated API, using an HTTP POST request designed to maintain data integrity.

[0948] Input: Generated customized parenting advice

[0949] Output: Advice sent to the user's terminal

[0950] Step 7:

[0951] The terminal displays the advice to the user.

[0952] The device displays the parenting advice received from the server to the user within the application. It can also use the notification function to provide timely notification of important advice. Specifically, it notifies the user of "measures to improve children's sleep."

[0953] Input: Customized parenting advice received from the server

[0954] Output: Advice and notifications displayed to the user

[0955] Step 8:

[0956] The user enters feedback.

[0957] Users can enter feedback through the application about the parenting advice and solutions provided, including an assessment of the effectiveness of the advice and suggestions for further improvement.

[0958] Input: User feedback data (effectiveness of advice, areas for improvement, etc.)

[0959] Output: Feedback data stored on the device

[0960] Step 9:

[0961] The device sends the feedback to the server.

[0962] The terminal receives the user's feedback and generates an HTTP POST request to send it to the server, during which the feedback data is standardized and sent to the server in an appropriate format.

[0963] Input: User feedback data

[0964] Output: Feedback data sent to the server

[0965] Step 10:

[0966] The server analyzes the feedback and improves the system.

[0967] The server analyzes the received feedback and evaluates the performance of the generative AI model and emotion engine. It also uses the feedback to improve the data analysis algorithm. This improves the accuracy of the system and provides advanced childcare support that responds to the user's individual childcare needs and psychological state.

[0968] Input: Received feedback data

[0969] Output: A system with improved generative AI models and emotion engines

[0970] (Application example 2)

[0971] 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."

[0972] In child-rearing, especially for first-time parents, gathering child-rearing information and receiving appropriate advice is important. However, conventional child-rearing support systems have difficulty responding to the individual needs and emotional state of users, and lack specific support to reduce stress and anxiety. Furthermore, they often provide uniform advice that ignores the user's emotional state, making them ineffective. This leads to a decline in the quality of child-rearing support and to situations where parents are unable to receive appropriate support.

[0973] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0974] In this invention, the server includes a data analysis means equipped with a generative AI model and general artificial intelligence technology for analyzing childcare information, an emotion engine for recognizing the user's emotional state and incorporating it into the analysis, and a means for generating and providing customized childcare advice based on the emotion data. This makes it possible to integrate and analyze the childcare information and emotion data in real time and provide highly accurate childcare advice tailored to the user's individual needs and psychological state.

[0975] "Childcare information" is a general term for a wide range of data related to childcare, such as a child's developmental status, health condition, behavioral patterns, nutritional intake, and sleep patterns.

[0976] A "user interface" refers to a screen or input device through which a user inputs childcare information, and is provided in the form of a smartphone app, tablet app, or the like.

[0977] A "server" is a computer system that analyzes childcare information and emotional data via a network, and stores and distributes the results.

[0978] A "generative AI model" is an artificial intelligence-based algorithm and its implementation used to analyze parenting information and generate customized parenting advice.

[0979] "General artificial intelligence technology" is an artificial intelligence technology that is not dependent on a specific application and can perform a wide range of data analysis and recognition tasks.

[0980] "Data analysis means" refers to the functions and processes for analyzing childcare information using generative AI models and general artificial intelligence technology.

[0981] "Childcare advice" refers to specific advice or suggestions provided to the user based on the analyzed childcare information.

[0982] An "emotion engine" is a technology that recognizes a user's emotional state based on their voice, facial expressions, text input, etc., and incorporates that data into analysis.

[0983] A "user terminal" is a device such as a smartphone or tablet that allows a user to input childcare information and receive advice.

[0984] "Feedback" refers to the user's evaluation and opinions of the parenting advice provided and the system's functionality.

[0985] This invention is a comprehensive childcare support system that analyzes childcare information and provides customized childcare advice, and in particular has the function of recognizing the user's emotional state and incorporating it into the analysis. This system is composed of the following elements.

[0986] User Interface

[0987] User terminal

[0988] Users enter childcare information through a dedicated application on a smartphone, tablet, or other device. The interface is designed to be intuitive and easy to use, providing fields for quickly and accurately entering the necessary information. Voice input and facial recognition functions are also used to collect emotional data from users.

[0989] Sending childcare information

[0990] User terminal

[0991] The childcare information entered by the user is sent to the server via an API request, and the device converts this data into a standardized format to ensure data integrity.

[0992] Data analysis and model use

[0993] server

[0994] The server stores the received parenting information in a cloud database. An analysis engine then retrieves the parenting information from the database and analyzes it using generative AI models and general artificial intelligence technology. This analysis evaluates the child's sleep patterns, nutritional status, and behavioral health, and identifies specific improvement measures.

[0995] Utilizing the Emotion Engine

[0996] User terminal

[0997] Emotional data is collected based on the user's voice input, facial expression recognition, and text input (e.g., diary entries and comments).

[0998] server

[0999] The server uses an emotion engine to analyze the user's emotional data. Based on the results of this analysis, the server can further customize parenting advice and provide optimal support based on the user's psychological state. For example, if the user is feeling stressed, the server can provide information on relaxation techniques and support groups.

[1000] Generating parenting advice

[1001] server

[1002] Based on the results of the data analysis, customized parenting advice is automatically generated, tailored to the user's individual parenting needs and includes specific, practical content.

[1003] Sending and viewing advice

[1004] server

[1005] The generated parenting advice is sent to the user's device via a dedicated API.

[1006] User terminal

[1007] The device displays the received parenting advice to the user, and can also use the notification function to notify the user of important advice in a timely manner.

[1008] Receiving and analyzing feedback

[1009] User

[1010] Users can enter and submit feedback on the advice and solutions provided.

[1011] User terminal

[1012] The terminal receives feedback from the user and generates an HTTP POST request to send to the server.

[1013] server

[1014] The server evaluates the performance of the generative AI model based on the received feedback and improves the analysis algorithm. At the same time, it also incorporates feedback from the emotion engine to improve the system so that it can provide even more accurate advice.

[1015] Examples of concrete examples and prompts

[1016] User

[1017] For example, if a user is concerned about their two-year-old child's sleep patterns, they can input their child's sleep patterns through the application. Also, if a user is feeling stressed, the emotion engine will recognize that emotion.

[1018] User terminal

[1019] The terminal converts the childcare information and emotion data into an appropriate format and transmits it to the server.

[1020] server

[1021] The server analyzes the childcare information and emotional data, evaluates the user's psychological state using an emotion engine, and then suggests a sleep routine suitable for a two-year-old and ways for the user to relax.

[1022] User terminal

[1023] The device will display advice to the user on how to improve sleep and relax, and will notify them using notifications.

[1024] User

[1025] The user inputs the results of the proposed suggestions as feedback and submits them.

[1026] server

[1027] The server analyzes the feedback and emotion data and uses it to improve the accuracy of the model and emotion engine.

[1028] Example prompt sentence:

[1029] Your child's current sleep patterns:

[1030] Start time: 20:00

[1031] End time: 06:00

[1032] User's emotional state: Stress

[1033] What parenting advice should you offer?

[1034] By using this system, users can receive optimal childcare support in real time according to their emotional state.

[1035] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1036] Step 1:

[1037] The user device collects childcare information (such as the child's sleep patterns, nutritional intake, and behavioral records) from the user through a dedicated application, as well as emotional data through voice input and facial expression recognition.

[1038] Step 2:

[1039] The user device converts the collected parenting information and emotion data into an appropriate format and sends it to the server via an API request. Specifically, the data is encoded in JSON format and a POST request is sent to the appropriate endpoint on the server.

[1040] Step 3:

[1041] The server stores the received childcare information and emotion data in a cloud database. The stored data is available for the next analysis step. Standardization and validation are also performed to ensure data integrity.

[1042] Step 4:

[1043] The server retrieves the stored parenting information and emotional data and analyzes it using a data analysis tool. Specifically, it processes the data using a generative AI model to evaluate the child's sleep patterns, nutritional status, and behavioral health. At the same time, it also evaluates the user's psychological state using an emotional engine.

[1044] Step 5:

[1045] The server generates customized parenting advice for users based on the results of data analysis. The generative AI model and emotion engine work together to generate specific advice, such as "A specific routine is effective for children who sleep between 8:00 PM and 6:00 AM."

[1046] Step 6:

[1047] The generated parenting advice is sent to the user's device via a dedicated API. The advice is formatted in JSON, which the user's device parses and prepares for display.

[1048] Step 7:

[1049] The user device displays the received parenting advice to the user and notifies the user of important advice in a timely manner using a notification function, for example, by using in-app notifications or push notifications.

[1050] Step 8:

[1051] The user enters feedback into the application on the proposed advice or solution, for example, comments about the effectiveness of the advice or areas for improvement.

[1052] Step 9:

[1053] The user device sends the entered feedback to the server as an HTTP POST request, and the feedback data is also encoded in JSON format and sent to the appropriate endpoint on the server.

[1054] Step 10:

[1055] The server stores the received feedback in a database and uses it for analysis. Based on this feedback, the performance of the generative AI model and emotion engine is evaluated and further improved. This will improve the accuracy of parenting advice from the next time onwards.

[1056] In this way, by utilizing childcare information and emotional data to provide customized advice, users can receive more accurate and practical childcare support.

[1057] 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.

[1058] 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.

[1059] 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.

[1060] [Third embodiment]

[1061] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1062] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1063] 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).

[1064] 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.

[1065] 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.

[1066] 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).

[1067] 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.

[1068] 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.

[1069] 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.

[1070] 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.

[1071] 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.

[1072] 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."

[1073] This invention is a comprehensive childcare support system that analyzes childcare information and provides customized childcare advice. This system is composed of the following elements: a user interface for inputting childcare information, a function for sending the childcare information to a server, a data analysis function, a function for generating childcare advice, a function for sending advice to a user's device, a function for receiving feedback, and a function for improving the generated AI model.

[1074] Overall system configuration

[1075] 1. User Interface

[1076] Terminal

[1077] Users enter childcare information through a dedicated application using a smartphone, tablet, or other device. The interface is designed to be intuitive and easy to use, providing fields for quickly and accurately entering the necessary information.

[1078] 2. Sending childcare information

[1079] Terminal

[1080] The childcare information entered by the user is sent to the server via an API request, and the device converts this data into a standardized format to ensure data integrity.

[1081] 3. Data analysis and model use

[1082] server

[1083] The server stores the received parenting information in a cloud database. An analysis engine then retrieves the parenting information from the database and analyzes it using generative AI models and general artificial intelligence technology. This analysis evaluates the child's sleep patterns, nutritional status, and behavioral health, and identifies specific improvement measures.

[1084] 4. Generating parenting advice

[1085] server

[1086] Based on the results of the data analysis, customized parenting advice is automatically generated, tailored to the user's individual parenting needs and includes specific, practical content.

[1087] 5. Sending and Viewing Advice

[1088] server

[1089] The generated parenting advice is sent to the user's device via a dedicated API.

[1090] Terminal

[1091] The device displays the received parenting advice to the user, and can also use the notification function to notify the user of important advice in a timely manner.

[1092] 6. Receiving and Analyzing Feedback

[1093] User

[1094] Users can enter and submit feedback on the advice and solutions provided.

[1095] Terminal

[1096] The terminal transmits the feedback data to the server.

[1097] server

[1098] The server evaluates the performance of the generative AI model based on the received feedback and improves the analysis algorithm, allowing the system to continuously evolve and provide more accurate and effective parenting advice.

[1099] Specific examples

[1100] User

[1101] For example, consider a case where a user is concerned about the sleep patterns of their two-year-old child. The user enters the child's sleep patterns (bedtime, wake-up time, number of nighttime awakenings, etc.) through an application.

[1102] Terminal

[1103] The terminal converts this information into an appropriate format and sends it to the server.

[1104] server

[1105] The server analyzes the received data and generates specific sleep improvement measures (e.g., recommending bath time and reading picture books to get the child to bed at 9 p.m.) using a generative AI model that suggests a sleep routine suitable for a two-year-old.

[1106] Terminal

[1107] The device displays the sleep improvement measures received from the server to the user and uses the notification function to inform the user of important suggestions.

[1108] User

[1109] The user tries these suggestions for a week, then enters the results as feedback and submits it.

[1110] server

[1111] The server analyzes this feedback and uses it as data to improve the accuracy of the model.

[1112] This system will enable parents to receive specific and useful advice for their individual child-rearing concerns, and is expected to improve the quality of child-rearing.

[1113] The processing flow will be explained below.

[1114] Step 1:

[1115] The user launches the application on the terminal and inputs childcare information (for example, the child's age, height, weight, sleep patterns, dietary content, behavioral data, etc.).

[1116] Step 2:

[1117] The terminal converts the childcare information input by the user into a standardized format and generates an HTTP POST request.

[1118] Step 3:

[1119] The terminal sends the generated HTTP POST request to the server.

[1120] Step 4:

[1121] The server analyzes the received HTTP POST request, extracts the childcare information data, and stores it in a cloud database.

[1122] Step 5:

[1123] The server retrieves the stored childcare information data from the cloud database and transfers it to the analysis engine.

[1124] Step 6:

[1125] The server's analytical engine uses generative AI models and general artificial intelligence technology to analyze childcare information data and assess children's sleep patterns, nutritional status, and behavioral health.

[1126] Step 7:

[1127] The server generates specific parenting advice (e.g., optimal sleep schedules, nutritionally balanced meal plans, behavioral improvements) based on the analysis results.

[1128] Step 8:

[1129] The server generates an HTTP response for transmitting the generated child-rearing advice to the user's terminal.

[1130] Step 9:

[1131] The terminal analyzes the HTTP response received from the server, extracts the child-rearing advice data, and displays it to the user.

[1132] Step 10:

[1133] If necessary, the device will notify the user of important advice via push notifications.

[1134] Step 11:

[1135] The user follows the advice provided to them and performs childcare, and inputs the results as feedback.

[1136] Step 12:

[1137] The terminal receives feedback from the user and generates an HTTP POST request to send to the server.

[1138] Step 13:

[1139] The server analyzes the received feedback data and uses it to improve the accuracy of the generative AI model.

[1140] Step 14:

[1141] Based on the feedback, the server improves the generative AI model and general artificial intelligence technology and reflects this in the next analysis.

[1142] Example 1

[1143] 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."

[1144] Conventional childcare support systems have had problems with the complicated input and management of childcare information, and the inability to perform sufficient data analysis to provide appropriate advice. Furthermore, the childcare information was not personalized enough, making it difficult to generate appropriate advice for each user. Furthermore, there was no mechanism in place to reflect feedback on advice in the system, making it difficult to evolve and improve the system.

[1145] 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.

[1146] In this invention, the server includes a means for converting childcare information into a standardized data format, a means for storing the childcare information in a cloud database, and a data analysis means equipped with a generative AI model and general artificial intelligence technology for analyzing the childcare information. This enables efficient management of childcare information and advanced data analysis. Furthermore, it automatically generates personalized childcare advice based on the analysis results, enabling continuous system improvement through feedback.

[1147] "Childcare information" refers to various data related to childcare, such as children's sleep patterns, diet, and behavior.

[1148] "User interface" refers to an interface through which a user inputs or obtains information.

[1149] "Data format" refers to a format for standardizing and processing information.

[1150] A "cloud database" refers to an online database for storing and managing data via the Internet.

[1151] A "generative AI model" refers to a machine learning model that uses artificial intelligence technology to automatically process specific tasks.

[1152] "General artificial intelligence technology" refers to artificial intelligence technology that is not limited to specific tasks and can be used for a wide range of applications.

[1153] "Data analysis tools" refer to methods and processes for collecting, analyzing, and evaluating data.

[1154] A "prompt sentence" refers to a sentence used to give instructions or ask questions to a generative AI model.

[1155] "Private API" refers to an application program interface for accessing specific functions or data.

[1156] "Feedback" refers to information used to collect user ratings and opinions.

[1157] MODE FOR CARRYING OUT THE INVENTION

[1158] The present invention is a comprehensive childcare support system that analyzes childcare information and provides customized childcare advice. This system includes a user interface for inputting childcare information, a function for sending the childcare information to a server, a data analysis function, a function for generating childcare advice, a function for sending the advice to a user terminal, a function for receiving feedback, and a function for improving the generated AI model.

[1159] Hardware and software used

[1160] Device: The user uses a smartphone or tablet, on which a dedicated application is installed.

[1161] Server: A server built in a cloud computing environment is used. Generative AI models and general artificial intelligence technology are implemented as data analysis engines.

[1162] Database: Use a cloud database to store childcare information.

[1163] System Operation Overview

[1164] Entering childcare information via a user interface

[1165] Users can open a dedicated application on their smartphone or tablet and input childcare information such as their child's sleep patterns, diet, and behavior. For example, they can input information such as "the child frequently wakes up at night."

[1166] Sending childcare information to the server

[1167] The device converts the childcare information entered by the user into a standardized data format, such as JSON, and sends it to the server as an API request, which then stores the data in a cloud database.

[1168] Analyzing the data and using the model

[1169] The server retrieves childcare information from a cloud database and analyzes the data using an analytical engine, utilizing generative AI models and general artificial intelligence techniques. The analysis results are used to assess children's sleep patterns, nutritional status, and behavioral health, and identify specific improvement measures.

[1170] Generating parenting advice

[1171] The server generates prompts based on the analysis results, such as "Generate specific suggestions to improve a two-year-old's sleep patterns," and issues them to the generative AI model. The generative AI model then generates specific childcare advice based on these prompts, such as "Read picture books before bedtime and avoid watching TV for 30 minutes before bed."

[1172] Sending and viewing advice

[1173] The generated parenting advice is sent to the user's device via a dedicated API, where it is displayed to the user and notifies them of important advice in a timely manner using the notification function.

[1174] Receiving and analyzing feedback

[1175] The user enters feedback about the results of following the provided advice into a dedicated application. The device then sends this feedback data to a server, which analyzes the received feedback data and uses it to evaluate and improve the performance of the generative AI model.

[1176] Examples of concrete examples and prompts

[1177] For example, here's a scenario where a user enters concerns about their 2-year-old's sleep patterns:

[1178] The user enters "frequent nighttime awakenings" into the application. The device converts this information into JSON format and sends it to the server. The server uses an analysis engine to create "advice to reduce nighttime awakenings in a 2-year-old child" using a generative AI model, providing specific advice such as "read picture books before bedtime and avoid watching TV for 30 minutes before bed." The device displays this to the user and uses the notification function to inform them of important advice.

[1179] An example prompt is "Generate specific suggestions to improve a two-year-old's sleep patterns."

[1180] The present invention is expected to enable efficient management of child-rearing information and provision of personalized advice, thereby effectively supporting users in child-rearing.

[1181] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1182] Step 1:

[1183] Entering childcare information

[1184] The user opens the dedicated application on a smartphone or tablet. The application's user interface provides a form for inputting childcare information. The user enters specific childcare information into the form, such as the child's sleep patterns, diet, and behavior. Input information includes "bedtime," "wake-up time," and "number of nighttime awakenings."

[1185] Input: Childcare information (e.g., bedtime, wake-up time, number of nighttime awakenings)

[1186] Output: The input childcare information is formatted as data.

[1187] Step 2:

[1188] Formatting and sending childcare information

[1189] The device receives the childcare information entered by the user and converts it into a standardized data format (e.g., JSON format). The formatted data is prepared as an API request and sent to the server.

[1190] Input: Childcare information entered in the input form

[1191] Output: Parenting information converted to JSON format

[1192] Step 3:

[1193] Receiving and storing data

[1194] The server receives the API request sent from the device and stores the sent childcare information in a cloud database, which is then used for later analysis.

[1195] Input: JSON format childcare information data

[1196] Output: Parenting information stored in a cloud database

[1197] Step 4:

[1198] Data acquisition and analysis

[1199] The server retrieves stored parenting information from a cloud database. The retrieved data is analyzed using generative AI models and artificial general intelligence techniques. This analysis process evaluates children's sleep patterns, nutritional status, and behavioral health, and identifies specific improvement measures.

[1200] Input: Parenting information stored in a cloud database

[1201] Output: Analysis results (evaluation of children's sleep patterns, nutritional status, behavioral health, etc.)

[1202] Step 5:

[1203] Generating parenting advice

[1204] The server generates a prompt based on the analysis results and inputs it into the generative AI model. An example of a prompt is "Generate specific suggestions to improve the sleep patterns of a two-year-old child." The generative AI model generates specific parenting advice based on this prompt.

[1205] Input: Analysis results and generated prompt statements

[1206] Output: Generated parenting advice

[1207] Step 6:

[1208] Sending parenting advice

[1209] The server sends the generated parenting advice to the user's device via a dedicated API. This API request includes the generated advice.

[1210] Input: Generated parenting advice

[1211] Output: Parenting advice sent in API request

[1212] Step 7:

[1213] Receiving and viewing advice

[1214] The device displays the childcare advice received from the server. The advice display screen is displayed within the application, and important advice is notified to the user using the notification function.

[1215] Input: Parenting advice sent in API request

[1216] Output: Parenting advice displayed within the application

[1217] Step 8:

[1218] Enter and submit feedback

[1219] The user follows the advice provided and inputs the results into the application. The feedback content may be, for example, "I've woken up less at night." The device then sends this feedback data back to the server as an API request.

[1220] Input: User feedback information

[1221] Output: Feedback information converted to JSON format

[1222] Step 9:

[1223] Receiving and analyzing feedback

[1224] The server receives the feedback data sent from the device and analyzes it to evaluate and improve the performance of the generative AI model, thereby improving the accuracy of parenting advice from the next time onwards.

[1225] Input: Feedback information in JSON format

[1226] Output: Model performance evaluation and improvement suggestions

[1227] (Application example 1)

[1228] 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."

[1229] Conventional childcare support systems not only analyze childcare information and provide advice, but also lack the ability to provide customized meal suggestions based on each child's nutritional needs. They also lack the functionality to provide advice in a format that parents can immediately implement and receive feedback. This makes it difficult to solve the specific nutritional management challenges faced by parents.

[1230] 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.

[1231] In this invention, the server includes means for providing a user interface for inputting childcare information, means for transmitting the childcare information to the server, means for analyzing the childcare information using a generative AI model and general artificial intelligence (AI) technology, means for generating childcare advice based on the analysis results, means for transmitting the generated childcare advice to a user terminal, means for displaying the advice on the user terminal, means for receiving feedback from the user and improving the generative AI model, means for providing customized nutritional advice based on the childcare information and generating a recommended ingredient list, and means for ordering ingredients and meals from the user terminal. This allows parents to receive specific and actionable dietary advice tailored to their children's individual nutritional needs, thereby optimally supporting their children's health and growth.

[1232] "Childcare information" refers to specific data related to childcare, such as a child's age, allergy information, food preferences, sleep patterns, and behavioral health.

[1233] "User interface" refers to the part of a computer system through which a user inputs childcare information, and refers to an intuitive and easy-to-use input means, including devices such as smartphones and tablets.

[1234] "Generative AI models" are algorithms and systems that use artificial intelligence techniques to generate customized advice and suggestions based on analyzed parenting information.

[1235] "General artificial intelligence technology" refers to artificial intelligence technology that can be applied to a variety of uses, not just specific problems.

[1236] "Data analysis means" refers to a combination of software and hardware used to analyze collected childcare information and identify specific patterns and improvements.

[1237] The "child-rearing advice generating means" is a function that automatically generates specific and actionable child-rearing advice based on the analysis results obtained by the data analysis means.

[1238] A "user terminal" is an electronic terminal such as a smartphone, tablet, or PC that allows a user to input childcare information and receive advice.

[1239] The "feedback receiving means" refers to an interface and communication means for receiving opinions and reactions from users.

[1240] "Model Improvement Tools" means the processes and techniques for evaluating and improving the performance of a Generative AI Model based on received feedback.

[1241] "Nutrition advice" is specific dietary suggestions and recommended food lists based on a child's individual nutritional needs.

[1242] The "recommended food list" is a list of foods that are appropriate for supporting children's health and growth, selected by a generative AI model.

[1243] The "ingredient ordering means" is a function that allows users to order ingredients and meals online based on a recommended ingredient list.

[1244] The present invention is a comprehensive childcare support system for analyzing childcare information and providing customized childcare advice. As an application example, a specific embodiment focusing on a food delivery service will be described.

[1245] Overall system configuration

[1246] 1. User Interface

[1247] Terminal

[1248] Users enter childcare information through a dedicated application using a smartphone, tablet, or other device. The interface is designed to be intuitive and easy to use, providing fields for quickly and accurately entering the necessary information.

[1249] 2. Sending childcare information

[1250] Terminal

[1251] The childcare information entered by the user is sent to the server via an API request, and the device converts this data into a standardized format to ensure data integrity.

[1252] 3. Data analysis and model use

[1253] server

[1254] The server stores the received childcare information in a cloud database. The analysis engine then retrieves the information from the database and analyzes it using generative AI models and general artificial intelligence technology. This analysis evaluates the child's nutritional status and generates specific nutritional advice and a recommended food list.

[1255] 4. Generating nutrition advice

[1256] server

[1257] Based on the data analysis results, customized nutrition advice is automatically generated that is specific and practical, tailored to the user's individual parenting needs.

[1258] 5. Sending and Viewing Advice

[1259] server

[1260] The generated nutrition advice is sent to the user's device via a dedicated API.

[1261] Terminal

[1262] The device displays the received nutrition advice to the user, and can also use the notification function to notify the user of important advice in a timely manner.

[1263] 6. Ordering ingredients

[1264] User

[1265] Users can view customized nutrition advice and recommended ingredients lists, and order ingredients and meals directly through the application.

[1266] Terminal

[1267] The terminal sends the order information to a server and works with the food delivery service to confirm the order.

[1268] 7. Receiving and Analyzing Feedback

[1269] User

[1270] Users can input and submit feedback on the food and service provided.

[1271] Terminal

[1272] The terminal transmits the feedback data to the server.

[1273] server

[1274] The server evaluates the performance of the generative AI model based on the received feedback and improves the analysis algorithm, allowing the system to continuously evolve and provide more accurate and effective nutritional advice.

[1275] Specific examples

[1276] Consider a case where a user is having trouble managing the nutrition of their two-year-old child. The user enters the child's dietary information (allergies, disliked ingredients, etc.) through the application. For example, the user can enter, "My child is two years old and has a peanut allergy. He likes fruit but doesn't eat many vegetables." Based on this information, the system generates appropriate nutrition advice and a recommended ingredient list, which the parent receives. Furthermore, the parent can order ingredients and meals directly through the app, enabling immediate implementation.

[1277] This allows parents to receive a specific and customized list of ingredients based on their child's nutritional needs, improving the quality of their childcare with access to a quality food delivery service.

[1278] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1279] Step 1:

[1280] Users use a device such as a smartphone or tablet to enter childcare information through a dedicated application, including the child's age, allergies, and dietary preferences. This information is then saved on the device as childcare information and converted into a standardized format.

[1281] Input: Childcare information entered by the user (age, allergy information, preferences, etc.)

[1282] Output: Standardized childcare information data

[1283] Step 2:

[1284] The device sends standardized childcare information data to the server. The data is transferred securely and efficiently using API requests. It is important that the data is transmitted in a state where its integrity is maintained.

[1285] Input: Standardized childcare information data

[1286] Output: Data sent to the server

[1287] Step 3:

[1288] The server stores the received childcare information data in a cloud database, which is used for later data analysis.

[1289] Input: Childcare information data sent to the server

[1290] Output: Data stored in a cloud database

[1291] Step 4:

[1292] A data analytics engine retrieves childcare information from a cloud database and analyzes the data using generative AI models and artificial general intelligence techniques. This analysis assesses children's nutritional status and identifies individualized improvement measures.

[1293] Input: Childcare information retrieved from a cloud database

[1294] Output: Analysis results (nutritional status assessment, specific improvement measures)

[1295] Step 5:

[1296] The server automatically generates customized nutrition advice and recommended food lists based on the data analysis results. This generative AI model is used to provide specific advice tailored to the user's specific needs.

[1297] Input: Analysis results

[1298] Output: Customized nutrition advice, recommended food list

[1299] Step 6:

[1300] The generated nutrition advice and recommended food list are sent to the user's device via a dedicated API. The server provides the information quickly while ensuring data security.

[1301] Input: Customized nutrition advice, recommended food lists

[1302] Output: Data sent to the user's terminal

[1303] Step 7:

[1304] The device displays the received nutrition advice and recommended food lists to the user, usually using a notification function to provide timely notification of important advice.

[1305] Input: Nutrition advice and recommended food list sent to your device

[1306] Output: Nutrition advice and recommended ingredients displayed to the user

[1307] Step 8:

[1308] Users can view customized nutrition advice and recommended ingredients lists and order ingredients and meals through the application, which automatically fills in the necessary information to simplify the ordering process.

[1309] Input: nutrition advice, recommended food list

[1310] Output: User orders ingredients and meals

[1311] Step 9:

[1312] The terminal sends the user's order information to the server and confirms the order in cooperation with the food delivery service. It is important that the order information is transmitted accurately.

[1313] Input: User's order information

[1314] Output: Order information sent to grocery delivery service

[1315] Step 10:

[1316] Users can input and submit feedback on the meals and services provided, including the quality of the meals and their children's reactions.

[1317] Input: User feedback

[1318] Output: Feedback saved on the device

[1319] Step 11:

[1320] The device sends the feedback data to the server using an API, which transfers the feedback information securely and quickly.

[1321] Input: Feedback stored on the device

[1322] Output: Feedback data sent to the server

[1323] Step 12:

[1324] The server evaluates the performance of the generative AI model based on the received feedback and improves the analysis algorithm, allowing the system to continuously evolve and provide more accurate and effective advice.

[1325] Input: Feedback data sent to the server

[1326] Output: Improved generative AI models, improved analysis algorithms

[1327] 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.

[1328] This invention is a comprehensive childcare support system that analyzes childcare information and provides customized childcare advice, and in particular has the function of recognizing the user's emotional state and incorporating it into the analysis. This system is composed of the following elements: a user interface for inputting childcare information, a function for sending the childcare information to a server, a data analysis function, a function for generating childcare advice, a function for sending the advice to the user's device, a feedback reception function, a function for improving the generated AI model, and an emotion engine.

[1329] Overall system configuration

[1330] 1. User Interface

[1331] Terminal

[1332] Users enter childcare information through a dedicated application on their smartphone, tablet, or other device. The interface is designed to be intuitive and easy to use, providing fields for quickly and accurately entering the necessary information.

[1333] 2. Sending childcare information

[1334] Terminal

[1335] The childcare information entered by the user is sent to the server via an API request, and the device converts this data into a standardized format to ensure data integrity.

[1336] 3. Data analysis and model use

[1337] server

[1338] The server stores the received parenting information in a cloud database. An analysis engine then retrieves the parenting information from the database and analyzes it using generative AI models and general artificial intelligence technology. This analysis evaluates the child's sleep patterns, nutritional status, and behavioral health, and identifies specific improvement measures.

[1339] 4. Generating parenting advice

[1340] server

[1341] Based on the results of the data analysis, customized parenting advice is automatically generated, tailored to the user's individual parenting needs and includes specific, practical content.

[1342] 5. Sending and Viewing Advice

[1343] server

[1344] The generated parenting advice is sent to the user's device via a dedicated API.

[1345] Terminal

[1346] The device displays the received parenting advice to the user, and can also use the notification function to notify the user of important advice in a timely manner.

[1347] 6. Leveraging Emotional Engines

[1348] Terminal

[1349] The device collects emotional data based on the user's voice input, facial expression recognition, text input (e.g., diary entries and comments), etc.

[1350] server

[1351] The server uses an emotion engine to analyze the user's emotional data. Based on the results of this analysis, the server can further customize parenting advice and provide optimal support based on the user's psychological state. For example, if the user is feeling stressed, the server can provide information on relaxation techniques and support groups.

[1352] 7. Receiving and Analyzing Feedback

[1353] User

[1354] Users can enter and submit feedback on the advice and solutions provided.

[1355] Terminal

[1356] The terminal receives feedback from the user and generates an HTTP POST request to send to the server.

[1357] server

[1358] The server evaluates the performance of the generative AI model based on the received feedback and improves the analysis algorithm. At the same time, it also incorporates feedback from the emotion engine to improve the system so that it can provide even more accurate advice.

[1359] Specific examples

[1360] User

[1361] For example, if a user is concerned about their two-year-old child's sleep patterns, they can input their child's sleep patterns through the application. Also, if a user is feeling stressed, the emotion engine will recognize that emotion.

[1362] Terminal

[1363] The terminal converts the childcare information and emotion data into an appropriate format and transmits it to the server.

[1364] server

[1365] The server analyzes the childcare information and emotional data, evaluates the user's psychological state using an emotion engine, and then suggests a sleep routine suitable for a two-year-old and ways for the user to relax.

[1366] Terminal

[1367] The device will display advice to the user on how to improve sleep and relax, and will notify them using notifications.

[1368] User

[1369] The user inputs the results of the proposed suggestions as feedback and submits them.

[1370] server

[1371] The server analyzes the feedback and emotion data and uses it to improve the accuracy of the model and emotion engine.

[1372] This allows the system to continuously evolve and provide advanced childcare support that responds to the individual childcare needs and psychological state of each user.

[1373] The processing flow will be explained below.

[1374] Step 1:

[1375] Users launch the application on their device and enter childcare information (e.g., their child's age, height, weight, sleep patterns, dietary habits, and behavioral data). They also record their emotional state using voice input and facial expression recognition functions.

[1376] Step 2:

[1377] The terminal collects parenting information and emotional data input by the user and converts it into a standardized format.

[1378] Step 3:

[1379] The device generates an HTTP POST request including the converted childcare information and emotion data and sends it to the server.

[1380] Step 4:

[1381] The server analyzes the received HTTP POST request, extracts childcare information data and emotion data, and stores them in a cloud database.

[1382] Step 5:

[1383] The server acquires childcare information data and emotion data from the cloud database and transfers them to the analysis engine.

[1384] Step 6:

[1385] The server's analysis engine uses generative AI models and general artificial intelligence technology to analyze childcare information data and evaluate children's sleep patterns, nutritional status, and behavioral health, while the emotion engine analyzes the user's emotional data and evaluates their psychological state.

[1386] Step 7:

[1387] The server generates specific parenting advice based on the analysis of the parenting information data and emotion data, and the advice is customized according to the child's parenting needs and the user's psychological state.

[1388] Step 8:

[1389] The server generates an HTTP response for transmitting the generated child-rearing advice to the user's terminal.

[1390] Step 9:

[1391] The device analyzes the HTTP response received from the server, extracts the parenting advice data, and displays it to the user. It selects a notification method (e.g., push notification or voice message) based on the emotion data and notifies the user at the appropriate time.

[1392] Step 10:

[1393] The user follows the provided advice and performs parenting, inputting the results as feedback and recording the new emotional state.

[1394] Step 11:

[1395] The device collects feedback data and new emotion data from the user, converts it into a standardized format, and generates an HTTP POST request to send it to the server.

[1396] Step 12:

[1397] The server analyzes the received feedback data and new emotion data, evaluates the performance of the generative AI model and emotion engine, and improves the analysis algorithm.

[1398] Step 13:

[1399] The server will use the improved model and emotion engine in the next analysis to provide more accurate advice tailored to the user's individual parenting needs and psychological state.

[1400] This process flow allows the system to continuously evolve, improving the user's parenting experience and providing more effective support.

[1401] Example 2

[1402] 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."

[1403] Parenting requires accurate advice that takes into account a child's developmental stage and individual needs. However, conventional systems struggle to provide detailed advice that takes into account the user's emotional state. Furthermore, they lack a mechanism for effectively utilizing user feedback on the advice provided to improve the system. This makes it difficult for users to efficiently input parenting information and receive practical parenting advice by analyzing that data.

[1404] 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.

[1405] In this invention, the server includes a data analysis means equipped with a generative AI model and general artificial intelligence technology for analyzing childcare information and emotion data, a means for generating childcare advice based on the analysis results and the user's emotional state, and a means for receiving feedback from the user and improving the generative AI model and emotion engine. This makes it possible to provide customized childcare advice that takes the user's emotional state into consideration, and the user's feedback can be effectively used to improve the system, thereby improving the accuracy and effectiveness of childcare support.

[1406] "Childcare information" refers to data related to childcare, such as a child's sleep patterns, diet, and behavior.

[1407] "Emotional data" is data that represents the user's psychological and emotional state, and is collected through voice input, facial expression recognition, text input, and the like.

[1408] A "user interface" is an interface through which a user inputs information and receives feedback from the system, and primarily refers to applications on smartphones and tablets.

[1409] A "generative AI model" is an algorithm or technology that generates new information based on given data, and often uses general artificial intelligence technology.

[1410] "General artificial intelligence technology" is artificial intelligence technology designed to perform a wide range of tasks, and is capable of analyzing a variety of data without specializing in any particular problem.

[1411] "Data analysis means" refers to a system or program for analyzing received data, and for appropriately processing childcare information and emotional data to gain insights.

[1412] "Childcare advice" is specific advice and recommendations on childcare that are generated based on the analysis results.

[1413] "Feedback" refers to the user's input of their reactions and results to the advice or solutions provided, and is information that is used to improve the system.

[1414] The "emotion engine" is an engine that analyzes input emotion data and determines the user's psychological state.

[1415] A "user terminal" is a device used by a user (e.g., a smartphone or tablet) to interact with the system.

[1416] The "notification function" is a function for notifying the user of important advice and information in a timely manner.

[1417] MODE FOR CARRYING OUT THE INVENTION

[1418] This invention is a comprehensive childcare support system that analyzes childcare information and provides customized childcare advice, and in particular has the function of recognizing the user's emotional state and incorporating it into the analysis. This system is composed of the following elements: a user interface for inputting childcare information, a function for sending childcare information and emotional data to a server, a data analysis function, a function for generating childcare advice, a function for sending advice to the user's device, a feedback reception function, a function for improving the generated AI model, and an emotion engine.

[1419] User Interface

[1420] Users can enter childcare information through a dedicated application on a smartphone, tablet, or other device. The interface is designed to be intuitive and easy to use, and provides fields for quickly and accurately entering the necessary information. Specifically, users can record their child's sleep time, diet, and behavior.

[1421] Sending parenting information and emotional data

[1422] The parenting information and emotion data entered by the user are sent to the server via API requests. The device converts this data into a standardized format to ensure data integrity. Emotion data is collected based on voice input, facial expression recognition, and text input (e.g., diary entries and comments).

[1423] Data analysis and model use

[1424] The server stores the received parenting information and emotional data in a cloud database. The analysis engine then retrieves the information from the database and analyzes it using generative AI models and general artificial intelligence techniques. This analysis evaluates the child's sleep patterns, nutritional status, and behavioral health and identifies specific improvement measures. For example, it detects disrupted sleep patterns and suggests appropriate countermeasures.

[1425] Generating parenting advice

[1426] Based on the data analysis results, customized parenting advice is automatically generated. This advice is tailored to the user's individual parenting needs and contains specific and practical content. For example, it suggests an appropriate sleep routine for a two-year-old.

[1427] Sending and viewing advice

[1428] The generated parenting advice is sent to the user's device via a dedicated API. The device displays the received parenting advice to the user. In addition, the notification function can be used to notify the user of important advice in a timely manner. For example, the user can be notified of "ways to improve children's sleep."

[1429] Utilizing the Emotion Engine

[1430] The device collects emotional data based on the user's voice input, facial expression recognition, text input, etc. The server then analyzes the user's emotional data using an emotion engine. Based on the results of this analysis, the system can further customize parenting advice and provide optimal support according to the user's psychological state. For example, if the user is feeling stressed, the system can provide information on relaxation techniques and support groups.

[1431] Receiving and analyzing feedback

[1432] The user inputs and submits feedback on the advice and solutions provided. The device receives the user's feedback, generates an HTTP POST request, and sends it to the server. The server evaluates the performance of the generative AI model based on the received feedback and improves the analysis algorithm. At the same time, it also incorporates feedback from the emotion engine to improve the system so that it can provide even more accurate advice.

[1433] For example, if a user is concerned about their two-year-old's sleep patterns, they can input their child's sleep patterns through the application. Also, if a user is feeling stressed, the emotion engine will recognize that emotion.

[1434] For example, the user can use the following prompt:

[1435] "I'm having trouble with my child's sleep patterns. Specifically, he wakes up every hour every night. I'm also finding this situation stressful. Can you give me some specific advice on how to resolve this?"

[1436] By using this system, users can receive parenting advice and psychological support tailored to their individual needs, improving the quality and efficiency of parenting.

[1437] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1438] Step 1:

[1439] The user inputs childcare information and emotional data.

[1440] Users launch a dedicated application on their smartphone or tablet and enter information about their child's sleep patterns, diet, behavior, and other childcare information, as well as their own emotional state (e.g., stress and satisfaction).The application is designed so that users can comfortably enter the required information into input fields.

[1441] Input: Childcare information (sleep time, diet, behavior, etc.) and user emotional data

[1442] Output: Input data saved on the device

[1443] Step 2:

[1444] The terminal formats the input data and sends it to the server.

[1445] The device converts the childcare information and emotional data entered by the user into a standardized format. Specifically, it standardizes the child's sleep time and dietary content into time units and nutritional units, and expresses emotional data as numbers and text. It then generates an API request and sends the data to the server using the HTTP POST method.

[1446] Input: User-entered standardized parenting information and emotional data

[1447] Output: Parenting information and emotion data sent to the server

[1448] Step 3:

[1449] The server stores the received data in a cloud database.

[1450] The server receives the parenting information and emotion data sent from the device. The received data is stored in a cloud database while ensuring security and privacy. Cloud services used include AWS and Google Cloud.

[1451] Input: Childcare information and emotional data sent from the device

[1452] Output: Data stored in a cloud database

[1453] Step 4:

[1454] The server analyzes the stored data.

[1455] The server retrieves stored parenting information and emotional data from the cloud database, processes the data using an analytics engine, and evaluates the child's sleep patterns, nutritional status, and behavioral health to identify issues. For example, it can detect disrupted sleep patterns and provide appropriate countermeasures.

[1456] Input: Parenting information and emotion data obtained from a cloud database.

[1457] Output: Analysis results (children's sleep patterns, nutritional status, behavioral assessment, etc.)

[1458] Step 5:

[1459] The server generates parenting advice using the generative AI model.

[1460] Based on the analyzed data, the server automatically generates parenting advice using a generative AI model (e.g., GPT-3). This advice is specific and practical, tailored to the user's individual parenting needs. For example, it suggests a suitable sleep routine for a two-year-old child or ways for the user to relax.

[1461] Input: Analysis results (child's sleep patterns, nutritional status, behavioral assessment, etc.)

[1462] Output: Customized parenting advice

[1463] Step 6:

[1464] The server transmits the generated advice to the user's terminal.

[1465] The server sends the generated parenting advice to the user's device via a dedicated API, using an HTTP POST request designed to maintain data integrity.

[1466] Input: Generated customized parenting advice

[1467] Output: Advice sent to the user's terminal

[1468] Step 7:

[1469] The terminal displays the advice to the user.

[1470] The device displays the parenting advice received from the server to the user within the application. It can also use the notification function to provide timely notification of important advice. Specifically, it notifies the user of "measures to improve children's sleep."

[1471] Input: Customized parenting advice received from the server

[1472] Output: Advice and notifications displayed to the user

[1473] Step 8:

[1474] The user enters feedback.

[1475] Users can enter feedback through the application about the parenting advice and solutions provided, including an assessment of the effectiveness of the advice and suggestions for further improvement.

[1476] Input: User feedback data (effectiveness of advice, areas for improvement, etc.)

[1477] Output: Feedback data stored on the device

[1478] Step 9:

[1479] The device sends the feedback to the server.

[1480] The terminal receives the user's feedback and generates an HTTP POST request to send it to the server, during which the feedback data is standardized and sent to the server in an appropriate format.

[1481] Input: User feedback data

[1482] Output: Feedback data sent to the server

[1483] Step 10:

[1484] The server analyzes the feedback and improves the system.

[1485] The server analyzes the received feedback and evaluates the performance of the generative AI model and emotion engine. It also uses the feedback to improve the data analysis algorithm. This improves the accuracy of the system and provides advanced childcare support that responds to the user's individual childcare needs and psychological state.

[1486] Input: Received feedback data

[1487] Output: A system with improved generative AI models and emotion engines

[1488] (Application example 2)

[1489] 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."

[1490] In child-rearing, especially for first-time parents, gathering child-rearing information and receiving appropriate advice is important. However, conventional child-rearing support systems have difficulty responding to the individual needs and emotional state of users, and lack specific support to reduce stress and anxiety. Furthermore, they often provide uniform advice that ignores the user's emotional state, making them ineffective. This leads to a decline in the quality of child-rearing support and to situations where parents are unable to receive appropriate support.

[1491] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1492] In this invention, the server includes a data analysis means equipped with a generative AI model and general artificial intelligence technology for analyzing childcare information, an emotion engine for recognizing the user's emotional state and incorporating it into the analysis, and a means for generating and providing customized childcare advice based on the emotion data. This makes it possible to integrate and analyze the childcare information and emotion data in real time and provide highly accurate childcare advice tailored to the user's individual needs and psychological state.

[1493] "Childcare information" is a general term for a wide range of data related to childcare, such as a child's developmental status, health condition, behavioral patterns, nutritional intake, and sleep patterns.

[1494] A "user interface" refers to a screen or input device through which a user inputs childcare information, and is provided in the form of a smartphone app, tablet app, or the like.

[1495] A "server" is a computer system that analyzes childcare information and emotional data via a network, and stores and distributes the results.

[1496] A "generative AI model" is an artificial intelligence-based algorithm and its implementation used to analyze parenting information and generate customized parenting advice.

[1497] "General artificial intelligence technology" is an artificial intelligence technology that is not dependent on a specific application and can perform a wide range of data analysis and recognition tasks.

[1498] "Data analysis means" refers to the functions and processes for analyzing childcare information using generative AI models and general artificial intelligence technology.

[1499] "Childcare advice" refers to specific advice or suggestions provided to the user based on the analyzed childcare information.

[1500] An "emotion engine" is a technology that recognizes a user's emotional state based on their voice, facial expressions, text input, etc., and incorporates that data into analysis.

[1501] A "user terminal" is a device such as a smartphone or tablet that allows a user to input childcare information and receive advice.

[1502] "Feedback" refers to the user's evaluation and opinions of the parenting advice provided and the system's functionality.

[1503] This invention is a comprehensive childcare support system that analyzes childcare information and provides customized childcare advice, and in particular has the function of recognizing the user's emotional state and incorporating it into the analysis. This system is composed of the following elements.

[1504] User Interface

[1505] User terminal

[1506] Users enter childcare information through a dedicated application on a smartphone, tablet, or other device. The interface is designed to be intuitive and easy to use, providing fields for quickly and accurately entering the necessary information. Voice input and facial recognition functions are also used to collect emotional data from users.

[1507] Sending childcare information

[1508] User terminal

[1509] The childcare information entered by the user is sent to the server via an API request, and the device converts this data into a standardized format to ensure data integrity.

[1510] Data analysis and model use

[1511] server

[1512] The server stores the received parenting information in a cloud database. An analysis engine then retrieves the parenting information from the database and analyzes it using generative AI models and general artificial intelligence technology. This analysis evaluates the child's sleep patterns, nutritional status, and behavioral health, and identifies specific improvement measures.

[1513] Utilizing the Emotion Engine

[1514] User terminal

[1515] Emotional data is collected based on the user's voice input, facial expression recognition, and text input (e.g., diary entries and comments).

[1516] server

[1517] The server uses an emotion engine to analyze the user's emotional data. Based on the results of this analysis, the server can further customize parenting advice and provide optimal support based on the user's psychological state. For example, if the user is feeling stressed, the server can provide information on relaxation techniques and support groups.

[1518] Generating parenting advice

[1519] server

[1520] Based on the results of the data analysis, customized parenting advice is automatically generated, tailored to the user's individual parenting needs and includes specific, practical content.

[1521] Sending and viewing advice

[1522] server

[1523] The generated parenting advice is sent to the user's device via a dedicated API.

[1524] User terminal

[1525] The device displays the received parenting advice to the user, and can also use the notification function to notify the user of important advice in a timely manner.

[1526] Receiving and analyzing feedback

[1527] User

[1528] Users can enter and submit feedback on the advice and solutions provided.

[1529] User terminal

[1530] The terminal receives feedback from the user and generates an HTTP POST request to send to the server.

[1531] server

[1532] The server evaluates the performance of the generative AI model based on the received feedback and improves the analysis algorithm. At the same time, it also incorporates feedback from the emotion engine to improve the system so that it can provide even more accurate advice.

[1533] Examples of concrete examples and prompts

[1534] User

[1535] For example, if a user is concerned about their two-year-old child's sleep patterns, they can input their child's sleep patterns through the application. Also, if a user is feeling stressed, the emotion engine will recognize that emotion.

[1536] User terminal

[1537] The terminal converts the childcare information and emotion data into an appropriate format and transmits it to the server.

[1538] server

[1539] The server analyzes the childcare information and emotional data, evaluates the user's psychological state using an emotion engine, and then suggests a sleep routine suitable for a two-year-old and ways for the user to relax.

[1540] User terminal

[1541] The device will display advice to the user on how to improve sleep and relax, and will notify them using notifications.

[1542] User

[1543] The user inputs the results of the proposed suggestions as feedback and submits them.

[1544] server

[1545] The server analyzes the feedback and emotion data and uses it to improve the accuracy of the model and emotion engine.

[1546] Example prompt sentence:

[1547] Your child's current sleep patterns:

[1548] Start time: 20:00

[1549] End time: 06:00

[1550] User's emotional state: Stress

[1551] What parenting advice should you offer?

[1552] By using this system, users can receive optimal childcare support in real time according to their emotional state.

[1553] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1554] Step 1:

[1555] The user device collects childcare information (such as the child's sleep patterns, nutritional intake, and behavioral records) from the user through a dedicated application, as well as emotional data through voice input and facial expression recognition.

[1556] Step 2:

[1557] The user device converts the collected parenting information and emotion data into an appropriate format and sends it to the server via an API request. Specifically, the data is encoded in JSON format and a POST request is sent to the appropriate endpoint on the server.

[1558] Step 3:

[1559] The server stores the received childcare information and emotion data in a cloud database. The stored data is available for the next analysis step. Standardization and validation are also performed to ensure data integrity.

[1560] Step 4:

[1561] The server retrieves the stored parenting information and emotional data and analyzes it using a data analysis tool. Specifically, it processes the data using a generative AI model to evaluate the child's sleep patterns, nutritional status, and behavioral health. At the same time, it also evaluates the user's psychological state using an emotional engine.

[1562] Step 5:

[1563] The server generates customized parenting advice for users based on the results of data analysis. The generative AI model and emotion engine work together to generate specific advice, such as "A specific routine is effective for children who sleep between 8:00 PM and 6:00 AM."

[1564] Step 6:

[1565] The generated parenting advice is sent to the user's device via a dedicated API. The advice is formatted in JSON, which the user's device parses and prepares for display.

[1566] Step 7:

[1567] The user device displays the received parenting advice to the user and notifies the user of important advice in a timely manner using a notification function, for example, by using in-app notifications or push notifications.

[1568] Step 8:

[1569] The user enters feedback into the application on the proposed advice or solution, for example, comments about the effectiveness of the advice or areas for improvement.

[1570] Step 9:

[1571] The user device sends the entered feedback to the server as an HTTP POST request, and the feedback data is also encoded in JSON format and sent to the appropriate endpoint on the server.

[1572] Step 10:

[1573] The server stores the received feedback in a database and uses it for analysis. Based on this feedback, the performance of the generative AI model and emotion engine is evaluated and further improved. This will improve the accuracy of parenting advice from the next time onwards.

[1574] In this way, by utilizing childcare information and emotional data to provide customized advice, users can receive more accurate and practical childcare support.

[1575] 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.

[1576] 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.

[1577] 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.

[1578] [Fourth embodiment]

[1579] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1580] 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.

[1581] 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).

[1582] 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.

[1583] 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.

[1584] 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).

[1585] 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.

[1586] 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.

[1587] 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.

[1588] 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.

[1589] 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.

[1590] 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.

[1591] 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."

[1592] This invention is a comprehensive childcare support system that analyzes childcare information and provides customized childcare advice. This system is composed of the following elements: a user interface for inputting childcare information, a function for sending the childcare information to a server, a data analysis function, a function for generating childcare advice, a function for sending advice to a user's device, a function for receiving feedback, and a function for improving the generated AI model.

[1593] Overall system configuration

[1594] 1. User Interface

[1595] Terminal

[1596] Users enter childcare information through a dedicated application using a smartphone, tablet, or other device. The interface is designed to be intuitive and easy to use, providing fields for quickly and accurately entering the necessary information.

[1597] 2. Sending childcare information

[1598] Terminal

[1599] The childcare information entered by the user is sent to the server via an API request, and the device converts this data into a standardized format to ensure data integrity.

[1600] 3. Data analysis and model use

[1601] server

[1602] The server stores the received parenting information in a cloud database. An analysis engine then retrieves the parenting information from the database and analyzes it using generative AI models and general artificial intelligence technology. This analysis evaluates the child's sleep patterns, nutritional status, and behavioral health, and identifies specific improvement measures.

[1603] 4. Generating parenting advice

[1604] server

[1605] Based on the results of the data analysis, customized parenting advice is automatically generated, tailored to the user's individual parenting needs and includes specific, practical content.

[1606] 5. Sending and Viewing Advice

[1607] server

[1608] The generated parenting advice is sent to the user's device via a dedicated API.

[1609] Terminal

[1610] The device displays the received parenting advice to the user, and can also use the notification function to notify the user of important advice in a timely manner.

[1611] 6. Receiving and Analyzing Feedback

[1612] User

[1613] Users can enter and submit feedback on the advice and solutions provided.

[1614] Terminal

[1615] The terminal transmits the feedback data to the server.

[1616] server

[1617] The server evaluates the performance of the generative AI model based on the received feedback and improves the analysis algorithm, allowing the system to continuously evolve and provide more accurate and effective parenting advice.

[1618] Specific examples

[1619] User

[1620] For example, consider a case where a user is concerned about the sleep patterns of their two-year-old child. The user enters the child's sleep patterns (bedtime, wake-up time, number of nighttime awakenings, etc.) through an application.

[1621] Terminal

[1622] The terminal converts this information into an appropriate format and sends it to the server.

[1623] server

[1624] The server analyzes the received data and generates specific sleep improvement measures (e.g., recommending bath time and reading picture books to get the child to bed at 9 p.m.) using a generative AI model that suggests a sleep routine suitable for a two-year-old.

[1625] Terminal

[1626] The device displays the sleep improvement measures received from the server to the user and uses the notification function to inform the user of important suggestions.

[1627] User

[1628] The user tries these suggestions for a week, then enters the results as feedback and submits it.

[1629] server

[1630] The server analyzes this feedback and uses it as data to improve the accuracy of the model.

[1631] This system will enable parents to receive specific and useful advice for their individual child-rearing concerns, and is expected to improve the quality of child-rearing.

[1632] The processing flow will be explained below.

[1633] Step 1:

[1634] The user launches the application on the terminal and inputs childcare information (for example, the child's age, height, weight, sleep patterns, dietary content, behavioral data, etc.).

[1635] Step 2:

[1636] The terminal converts the childcare information input by the user into a standardized format and generates an HTTP POST request.

[1637] Step 3:

[1638] The terminal sends the generated HTTP POST request to the server.

[1639] Step 4:

[1640] The server analyzes the received HTTP POST request, extracts the childcare information data, and stores it in a cloud database.

[1641] Step 5:

[1642] The server retrieves the stored childcare information data from the cloud database and transfers it to the analysis engine.

[1643] Step 6:

[1644] The server's analytical engine uses generative AI models and general artificial intelligence technology to analyze childcare information data and assess children's sleep patterns, nutritional status, and behavioral health.

[1645] Step 7:

[1646] The server generates specific parenting advice (e.g., optimal sleep schedules, nutritionally balanced meal plans, behavioral improvements) based on the analysis results.

[1647] Step 8:

[1648] The server generates an HTTP response for transmitting the generated child-rearing advice to the user's terminal.

[1649] Step 9:

[1650] The terminal analyzes the HTTP response received from the server, extracts the child-rearing advice data, and displays it to the user.

[1651] Step 10:

[1652] If necessary, the device will notify the user of important advice via push notifications.

[1653] Step 11:

[1654] The user follows the advice provided to them and performs childcare, and inputs the results as feedback.

[1655] Step 12:

[1656] The terminal receives feedback from the user and generates an HTTP POST request to send to the server.

[1657] Step 13:

[1658] The server analyzes the received feedback data and uses it to improve the accuracy of the generative AI model.

[1659] Step 14:

[1660] Based on the feedback, the server improves the generative AI model and general artificial intelligence technology and reflects this in the next analysis.

[1661] Example 1

[1662] 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."

[1663] Conventional childcare support systems have had problems with the complicated input and management of childcare information, and the inability to perform sufficient data analysis to provide appropriate advice. Furthermore, the childcare information was not personalized enough, making it difficult to generate appropriate advice for each user. Furthermore, there was no mechanism in place to reflect feedback on advice in the system, making it difficult to evolve and improve the system.

[1664] 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.

[1665] In this invention, the server includes a means for converting childcare information into a standardized data format, a means for storing the childcare information in a cloud database, and a data analysis means equipped with a generative AI model and general artificial intelligence technology for analyzing the childcare information. This enables efficient management of childcare information and advanced data analysis. Furthermore, it automatically generates personalized childcare advice based on the analysis results, enabling continuous system improvement through feedback.

[1666] "Childcare information" refers to various data related to childcare, such as children's sleep patterns, diet, and behavior.

[1667] "User interface" refers to an interface through which a user inputs or obtains information.

[1668] "Data format" refers to a format for standardizing and processing information.

[1669] A "cloud database" refers to an online database for storing and managing data via the Internet.

[1670] A "generative AI model" refers to a machine learning model that uses artificial intelligence technology to automatically process specific tasks.

[1671] "General artificial intelligence technology" refers to artificial intelligence technology that is not limited to specific tasks and can be used for a wide range of applications.

[1672] "Data analysis tools" refer to methods and processes for collecting, analyzing, and evaluating data.

[1673] A "prompt sentence" refers to a sentence used to give instructions or ask questions to a generative AI model.

[1674] "Private API" refers to an application program interface for accessing specific functions or data.

[1675] "Feedback" refers to information used to collect user ratings and opinions.

[1676] MODE FOR CARRYING OUT THE INVENTION

[1677] The present invention is a comprehensive childcare support system that analyzes childcare information and provides customized childcare advice. This system includes a user interface for inputting childcare information, a function for sending the childcare information to a server, a data analysis function, a function for generating childcare advice, a function for sending the advice to a user terminal, a function for receiving feedback, and a function for improving the generated AI model.

[1678] Hardware and software used

[1679] Device: The user uses a smartphone or tablet, on which a dedicated application is installed.

[1680] Server: A server built in a cloud computing environment is used. Generative AI models and general artificial intelligence technology are implemented as data analysis engines.

[1681] Database: Use a cloud database to store childcare information.

[1682] System Operation Overview

[1683] Entering childcare information via a user interface

[1684] Users can open a dedicated application on their smartphone or tablet and input childcare information such as their child's sleep patterns, diet, and behavior. For example, they can input information such as "the child frequently wakes up at night."

[1685] Sending childcare information to the server

[1686] The device converts the childcare information entered by the user into a standardized data format, such as JSON, and sends it to the server as an API request, which then stores the data in a cloud database.

[1687] Analyzing the data and using the model

[1688] The server retrieves childcare information from a cloud database and analyzes the data using an analytical engine, utilizing generative AI models and general artificial intelligence techniques. The analysis results are used to assess children's sleep patterns, nutritional status, and behavioral health, and identify specific improvement measures.

[1689] Generating parenting advice

[1690] The server generates prompts based on the analysis results, such as "Generate specific suggestions to improve a two-year-old's sleep patterns," and issues them to the generative AI model. The generative AI model then generates specific childcare advice based on these prompts, such as "Read picture books before bedtime and avoid watching TV for 30 minutes before bed."

[1691] Sending and viewing advice

[1692] The generated parenting advice is sent to the user's device via a dedicated API, where it is displayed to the user and notifies them of important advice in a timely manner using the notification function.

[1693] Receiving and analyzing feedback

[1694] The user enters feedback about the results of following the provided advice into a dedicated application. The device then sends this feedback data to a server, which analyzes the received feedback data and uses it to evaluate and improve the performance of the generative AI model.

[1695] Examples of concrete examples and prompts

[1696] For example, here's a scenario where a user enters concerns about their 2-year-old's sleep patterns:

[1697] The user enters "frequent nighttime awakenings" into the application. The device converts this information into JSON format and sends it to the server. The server uses an analysis engine to create "advice to reduce nighttime awakenings in a 2-year-old child" using a generative AI model, providing specific advice such as "read picture books before bedtime and avoid watching TV for 30 minutes before bed." The device displays this to the user and uses the notification function to inform them of important advice.

[1698] An example prompt is "Generate specific suggestions to improve a two-year-old's sleep patterns."

[1699] The present invention is expected to enable efficient management of child-rearing information and provision of personalized advice, thereby effectively supporting users in child-rearing.

[1700] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1701] Step 1:

[1702] Entering childcare information

[1703] The user opens the dedicated application on a smartphone or tablet. The application's user interface provides a form for inputting childcare information. The user enters specific childcare information into the form, such as the child's sleep patterns, diet, and behavior. Input information includes "bedtime," "wake-up time," and "number of nighttime awakenings."

[1704] Input: Childcare information (e.g., bedtime, wake-up time, number of nighttime awakenings)

[1705] Output: The input childcare information is formatted as data.

[1706] Step 2:

[1707] Formatting and sending childcare information

[1708] The device receives the childcare information entered by the user and converts it into a standardized data format (e.g., JSON format). The formatted data is prepared as an API request and sent to the server.

[1709] Input: Childcare information entered in the input form

[1710] Output: Parenting information converted to JSON format

[1711] Step 3:

[1712] Receiving and storing data

[1713] The server receives the API request sent from the device and stores the sent childcare information in a cloud database, which is then used for later analysis.

[1714] Input: JSON format childcare information data

[1715] Output: Parenting information stored in a cloud database

[1716] Step 4:

[1717] Data acquisition and analysis

[1718] The server retrieves stored parenting information from a cloud database. The retrieved data is analyzed using generative AI models and artificial general intelligence techniques. This analysis process evaluates children's sleep patterns, nutritional status, and behavioral health, and identifies specific improvement measures.

[1719] Input: Parenting information stored in a cloud database

[1720] Output: Analysis results (evaluation of children's sleep patterns, nutritional status, behavioral health, etc.)

[1721] Step 5:

[1722] Generating parenting advice

[1723] The server generates a prompt based on the analysis results and inputs it into the generative AI model. An example of a prompt is "Generate specific suggestions to improve the sleep patterns of a two-year-old child." The generative AI model generates specific parenting advice based on this prompt.

[1724] Input: Analysis results and generated prompt statements

[1725] Output: Generated parenting advice

[1726] Step 6:

[1727] Sending parenting advice

[1728] The server sends the generated parenting advice to the user's device via a dedicated API. This API request includes the generated advice.

[1729] Input: Generated parenting advice

[1730] Output: Parenting advice sent in API request

[1731] Step 7:

[1732] Receiving and viewing advice

[1733] The device displays the childcare advice received from the server. The advice display screen is displayed within the application, and important advice is notified to the user using the notification function.

[1734] Input: Parenting advice sent in API request

[1735] Output: Parenting advice displayed within the application

[1736] Step 8:

[1737] Enter and submit feedback

[1738] The user follows the advice provided and inputs the results into the application. The feedback content may be, for example, "I've woken up less at night." The device then sends this feedback data back to the server as an API request.

[1739] Input: User feedback information

[1740] Output: Feedback information converted to JSON format

[1741] Step 9:

[1742] Receiving and analyzing feedback

[1743] The server receives the feedback data sent from the device and analyzes it to evaluate and improve the performance of the generative AI model, thereby improving the accuracy of parenting advice from the next time onwards.

[1744] Input: Feedback information in JSON format

[1745] Output: Model performance evaluation and improvement suggestions

[1746] (Application example 1)

[1747] 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."

[1748] Conventional childcare support systems not only analyze childcare information and provide advice, but also lack the ability to provide customized meal suggestions based on each child's nutritional needs. They also lack the functionality to provide advice in a format that parents can immediately implement and receive feedback. This makes it difficult to solve the specific nutritional management challenges faced by parents.

[1749] 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.

[1750] In this invention, the server includes means for providing a user interface for inputting childcare information, means for transmitting the childcare information to the server, means for analyzing the childcare information using a generative AI model and general artificial intelligence (AI) technology, means for generating childcare advice based on the analysis results, means for transmitting the generated childcare advice to a user terminal, means for displaying the advice on the user terminal, means for receiving feedback from the user and improving the generative AI model, means for providing customized nutritional advice based on the childcare information and generating a recommended ingredient list, and means for ordering ingredients and meals from the user terminal. This allows parents to receive specific and actionable dietary advice tailored to their children's individual nutritional needs, thereby optimally supporting their children's health and growth.

[1751] "Childcare information" refers to specific data related to childcare, such as a child's age, allergy information, food preferences, sleep patterns, and behavioral health.

[1752] "User interface" refers to the part of a computer system through which a user inputs childcare information, and refers to an intuitive and easy-to-use input means, including devices such as smartphones and tablets.

[1753] "Generative AI models" are algorithms and systems that use artificial intelligence techniques to generate customized advice and suggestions based on analyzed parenting information.

[1754] "General artificial intelligence technology" refers to artificial intelligence technology that can be applied to a variety of uses, not just specific problems.

[1755] "Data analysis means" refers to a combination of software and hardware used to analyze collected childcare information and identify specific patterns and improvements.

[1756] The "child-rearing advice generating means" is a function that automatically generates specific and actionable child-rearing advice based on the analysis results obtained by the data analysis means.

[1757] A "user terminal" is an electronic terminal such as a smartphone, tablet, or PC that allows a user to input childcare information and receive advice.

[1758] The "feedback receiving means" refers to an interface and communication means for receiving opinions and reactions from users.

[1759] "Model Improvement Tools" means the processes and techniques for evaluating and improving the performance of a Generative AI Model based on received feedback.

[1760] "Nutrition advice" is specific dietary suggestions and recommended food lists based on a child's individual nutritional needs.

[1761] The "recommended food list" is a list of foods that are appropriate for supporting children's health and growth, selected by a generative AI model.

[1762] The "ingredient ordering means" is a function that allows users to order ingredients and meals online based on a recommended ingredient list.

[1763] The present invention is a comprehensive childcare support system for analyzing childcare information and providing customized childcare advice. As an application example, a specific embodiment focusing on a food delivery service will be described.

[1764] Overall system configuration

[1765] 1. User Interface

[1766] Terminal

[1767] Users enter childcare information through a dedicated application using a smartphone, tablet, or other device. The interface is designed to be intuitive and easy to use, providing fields for quickly and accurately entering the necessary information.

[1768] 2. Sending childcare information

[1769] Terminal

[1770] The childcare information entered by the user is sent to the server via an API request, and the device converts this data into a standardized format to ensure data integrity.

[1771] 3. Data analysis and model use

[1772] server

[1773] The server stores the received childcare information in a cloud database. The analysis engine then retrieves the information from the database and analyzes it using generative AI models and general artificial intelligence technology. This analysis evaluates the child's nutritional status and generates specific nutritional advice and a recommended food list.

[1774] 4. Generating nutrition advice

[1775] server

[1776] Based on the data analysis results, customized nutrition advice is automatically generated that is specific and practical, tailored to the user's individual parenting needs.

[1777] 5. Sending and Viewing Advice

[1778] server

[1779] The generated nutrition advice is sent to the user's device via a dedicated API.

[1780] Terminal

[1781] The device displays the received nutrition advice to the user, and can also use the notification function to notify the user of important advice in a timely manner.

[1782] 6. Ordering ingredients

[1783] User

[1784] Users can view customized nutrition advice and recommended ingredients lists, and order ingredients and meals directly through the application.

[1785] Terminal

[1786] The terminal sends the order information to a server and works with the food delivery service to confirm the order.

[1787] 7. Receiving and Analyzing Feedback

[1788] User

[1789] Users can input and submit feedback on the food and service provided.

[1790] Terminal

[1791] The terminal transmits the feedback data to the server.

[1792] server

[1793] The server evaluates the performance of the generative AI model based on the received feedback and improves the analysis algorithm, allowing the system to continuously evolve and provide more accurate and effective nutritional advice.

[1794] Specific examples

[1795] Consider a case where a user is having trouble managing the nutrition of their two-year-old child. The user enters the child's dietary information (allergies, disliked ingredients, etc.) through the application. For example, the user can enter, "My child is two years old and has a peanut allergy. He likes fruit but doesn't eat many vegetables." Based on this information, the system generates appropriate nutrition advice and a recommended ingredient list, which the parent receives. Furthermore, the parent can order ingredients and meals directly through the app, enabling immediate implementation.

[1796] This allows parents to receive a specific and customized list of ingredients based on their child's nutritional needs, improving the quality of their childcare with access to a quality food delivery service.

[1797] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1798] Step 1:

[1799] Users use a device such as a smartphone or tablet to enter childcare information through a dedicated application, including the child's age, allergies, and dietary preferences. This information is then saved on the device as childcare information and converted into a standardized format.

[1800] Input: Childcare information entered by the user (age, allergy information, preferences, etc.)

[1801] Output: Standardized childcare information data

[1802] Step 2:

[1803] The device sends standardized childcare information data to the server. The data is transferred securely and efficiently using API requests. It is important that the data is transmitted in a state where its integrity is maintained.

[1804] Input: Standardized childcare information data

[1805] Output: Data sent to the server

[1806] Step 3:

[1807] The server stores the received childcare information data in a cloud database, which is used for later data analysis.

[1808] Input: Childcare information data sent to the server

[1809] Output: Data stored in a cloud database

[1810] Step 4:

[1811] A data analytics engine retrieves childcare information from a cloud database and analyzes the data using generative AI models and artificial general intelligence techniques. This analysis assesses children's nutritional status and identifies individualized improvement measures.

[1812] Input: Childcare information retrieved from a cloud database

[1813] Output: Analysis results (nutritional status assessment, specific improvement measures)

[1814] Step 5:

[1815] The server automatically generates customized nutrition advice and recommended food lists based on the data analysis results. This generative AI model is used to provide specific advice tailored to the user's specific needs.

[1816] Input: Analysis results

[1817] Output: Customized nutrition advice, recommended food list

[1818] Step 6:

[1819] The generated nutrition advice and recommended food list are sent to the user's device via a dedicated API. The server provides the information quickly while ensuring data security.

[1820] Input: Customized nutrition advice, recommended food lists

[1821] Output: Data sent to the user's terminal

[1822] Step 7:

[1823] The device displays the received nutrition advice and recommended food lists to the user, usually using a notification function to provide timely notification of important advice.

[1824] Input: Nutrition advice and recommended food list sent to your device

[1825] Output: Nutrition advice and recommended ingredients displayed to the user

[1826] Step 8:

[1827] Users can view customized nutrition advice and recommended ingredients lists and order ingredients and meals through the application, which automatically fills in the necessary information to simplify the ordering process.

[1828] Input: nutrition advice, recommended food list

[1829] Output: User orders ingredients and meals

[1830] Step 9:

[1831] The terminal sends the user's order information to the server and confirms the order in cooperation with the food delivery service. It is important that the order information is transmitted accurately.

[1832] Input: User's order information

[1833] Output: Order information sent to grocery delivery service

[1834] Step 10:

[1835] Users can input and submit feedback on the meals and services provided, including the quality of the meals and their children's reactions.

[1836] Input: User feedback

[1837] Output: Feedback saved on the device

[1838] Step 11:

[1839] The device sends the feedback data to the server using an API, which transfers the feedback information securely and quickly.

[1840] Input: Feedback stored on the device

[1841] Output: Feedback data sent to the server

[1842] Step 12:

[1843] The server evaluates the performance of the generative AI model based on the received feedback and improves the analysis algorithm, allowing the system to continuously evolve and provide more accurate and effective advice.

[1844] Input: Feedback data sent to the server

[1845] Output: Improved generative AI models, improved analysis algorithms

[1846] 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.

[1847] This invention is a comprehensive childcare support system that analyzes childcare information and provides customized childcare advice, and in particular has the function of recognizing the user's emotional state and incorporating it into the analysis. This system is composed of the following elements: a user interface for inputting childcare information, a function for sending the childcare information to a server, a data analysis function, a function for generating childcare advice, a function for sending the advice to the user's device, a feedback reception function, a function for improving the generated AI model, and an emotion engine.

[1848] Overall system configuration

[1849] 1. User Interface

[1850] Terminal

[1851] Users enter childcare information through a dedicated application on their smartphone, tablet, or other device. The interface is designed to be intuitive and easy to use, providing fields for quickly and accurately entering the necessary information.

[1852] 2. Sending childcare information

[1853] Terminal

[1854] The childcare information entered by the user is sent to the server via an API request, and the device converts this data into a standardized format to ensure data integrity.

[1855] 3. Data analysis and model use

[1856] server

[1857] The server stores the received parenting information in a cloud database. An analysis engine then retrieves the parenting information from the database and analyzes it using generative AI models and general artificial intelligence technology. This analysis evaluates the child's sleep patterns, nutritional status, and behavioral health, and identifies specific improvement measures.

[1858] 4. Generating parenting advice

[1859] server

[1860] Based on the results of the data analysis, customized parenting advice is automatically generated, tailored to the user's individual parenting needs and includes specific, practical content.

[1861] 5. Sending and Viewing Advice

[1862] server

[1863] The generated parenting advice is sent to the user's device via a dedicated API.

[1864] Terminal

[1865] The device displays the received parenting advice to the user, and can also use the notification function to notify the user of important advice in a timely manner.

[1866] 6. Leveraging Emotional Engines

[1867] Terminal

[1868] The device collects emotional data based on the user's voice input, facial expression recognition, text input (e.g., diary entries and comments), etc.

[1869] server

[1870] The server uses an emotion engine to analyze the user's emotional data. Based on the results of this analysis, the server can further customize parenting advice and provide optimal support based on the user's psychological state. For example, if the user is feeling stressed, the server can provide information on relaxation techniques and support groups.

[1871] 7. Receiving and Analyzing Feedback

[1872] User

[1873] Users can enter and submit feedback on the advice and solutions provided.

[1874] Terminal

[1875] The terminal receives feedback from the user and generates an HTTP POST request to send to the server.

[1876] server

[1877] The server evaluates the performance of the generative AI model based on the received feedback and improves the analysis algorithm. At the same time, it also incorporates feedback from the emotion engine to improve the system so that it can provide even more accurate advice.

[1878] Specific examples

[1879] User

[1880] For example, if a user is concerned about their two-year-old child's sleep patterns, they can input their child's sleep patterns through the application. Also, if a user is feeling stressed, the emotion engine will recognize that emotion.

[1881] Terminal

[1882] The terminal converts the childcare information and emotion data into an appropriate format and transmits it to the server.

[1883] server

[1884] The server analyzes the childcare information and emotional data, evaluates the user's psychological state using an emotion engine, and then suggests a sleep routine suitable for a two-year-old and ways for the user to relax.

[1885] Terminal

[1886] The device will display advice to the user on how to improve sleep and relax, and will notify them using notifications.

[1887] User

[1888] The user inputs the results of the proposed suggestions as feedback and submits them.

[1889] server

[1890] The server analyzes the feedback and emotion data and uses it to improve the accuracy of the model and emotion engine.

[1891] This allows the system to continuously evolve and provide advanced childcare support that responds to the individual childcare needs and psychological state of each user.

[1892] The processing flow will be explained below.

[1893] Step 1:

[1894] Users launch the application on their device and enter childcare information (e.g., their child's age, height, weight, sleep patterns, dietary habits, and behavioral data). They also record their emotional state using voice input and facial expression recognition functions.

[1895] Step 2:

[1896] The terminal collects parenting information and emotional data input by the user and converts it into a standardized format.

[1897] Step 3:

[1898] The device generates an HTTP POST request including the converted childcare information and emotion data and sends it to the server.

[1899] Step 4:

[1900] The server analyzes the received HTTP POST request, extracts childcare information data and emotion data, and stores them in a cloud database.

[1901] Step 5:

[1902] The server acquires childcare information data and emotion data from the cloud database and transfers them to the analysis engine.

[1903] Step 6:

[1904] The server's analysis engine uses generative AI models and general artificial intelligence technology to analyze childcare information data and evaluate children's sleep patterns, nutritional status, and behavioral health, while the emotion engine analyzes the user's emotional data and evaluates their psychological state.

[1905] Step 7:

[1906] The server generates specific parenting advice based on the analysis of the parenting information data and emotion data, and the advice is customized according to the child's parenting needs and the user's psychological state.

[1907] Step 8:

[1908] The server generates an HTTP response for transmitting the generated child-rearing advice to the user's terminal.

[1909] Step 9:

[1910] The device analyzes the HTTP response received from the server, extracts the parenting advice data, and displays it to the user. It selects a notification method (e.g., push notification or voice message) based on the emotion data and notifies the user at the appropriate time.

[1911] Step 10:

[1912] The user follows the provided advice and performs parenting, inputting the results as feedback and recording the new emotional state.

[1913] Step 11:

[1914] The device collects feedback data and new emotion data from the user, converts it into a standardized format, and generates an HTTP POST request to send it to the server.

[1915] Step 12:

[1916] The server analyzes the received feedback data and new emotion data, evaluates the performance of the generative AI model and emotion engine, and improves the analysis algorithm.

[1917] Step 13:

[1918] The server will use the improved model and emotion engine in the next analysis to provide more accurate advice tailored to the user's individual parenting needs and psychological state.

[1919] This process flow allows the system to continuously evolve, improving the user's parenting experience and providing more effective support.

[1920] Example 2

[1921] 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."

[1922] Parenting requires accurate advice that takes into account a child's developmental stage and individual needs. However, conventional systems struggle to provide detailed advice that takes into account the user's emotional state. Furthermore, they lack a mechanism for effectively utilizing user feedback on the advice provided to improve the system. This makes it difficult for users to efficiently input parenting information and receive practical parenting advice by analyzing that data.

[1923] 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.

[1924] In this invention, the server includes a data analysis means equipped with a generative AI model and general artificial intelligence technology for analyzing childcare information and emotion data, a means for generating childcare advice based on the analysis results and the user's emotional state, and a means for receiving feedback from the user and improving the generative AI model and emotion engine. This makes it possible to provide customized childcare advice that takes the user's emotional state into consideration, and the user's feedback can be effectively used to improve the system, thereby improving the accuracy and effectiveness of childcare support.

[1925] "Childcare information" refers to data related to childcare, such as a child's sleep patterns, diet, and behavior.

[1926] "Emotional data" is data that represents the user's psychological and emotional state, and is collected through voice input, facial expression recognition, text input, and the like.

[1927] A "user interface" is an interface through which a user inputs information and receives feedback from the system, and primarily refers to applications on smartphones and tablets.

[1928] A "generative AI model" is an algorithm or technology that generates new information based on given data, and often uses general artificial intelligence technology.

[1929] "General artificial intelligence technology" is artificial intelligence technology designed to perform a wide range of tasks, and is capable of analyzing a variety of data without specializing in any particular problem.

[1930] "Data analysis means" refers to a system or program for analyzing received data, and for appropriately processing childcare information and emotional data to gain insights.

[1931] "Childcare advice" is specific advice and recommendations on childcare that are generated based on the analysis results.

[1932] "Feedback" refers to the user's input of their reactions and results to the advice or solutions provided, and is information that is used to improve the system.

[1933] The "emotion engine" is an engine that analyzes input emotion data and determines the user's psychological state.

[1934] A "user terminal" is a device used by a user (e.g., a smartphone or tablet) to interact with the system.

[1935] The "notification function" is a function for notifying the user of important advice and information in a timely manner.

[1936] MODE FOR CARRYING OUT THE INVENTION

[1937] This invention is a comprehensive childcare support system that analyzes childcare information and provides customized childcare advice, and in particular has the function of recognizing the user's emotional state and incorporating it into the analysis. This system is composed of the following elements: a user interface for inputting childcare information, a function for sending childcare information and emotional data to a server, a data analysis function, a function for generating childcare advice, a function for sending advice to the user's device, a feedback reception function, a function for improving the generated AI model, and an emotion engine.

[1938] User Interface

[1939] Users can enter childcare information through a dedicated application on a smartphone, tablet, or other device. The interface is designed to be intuitive and easy to use, and provides fields for quickly and accurately entering the necessary information. Specifically, users can record their child's sleep time, diet, and behavior.

[1940] Sending parenting information and emotional data

[1941] The parenting information and emotion data entered by the user are sent to the server via API requests. The device converts this data into a standardized format to ensure data integrity. Emotion data is collected based on voice input, facial expression recognition, and text input (e.g., diary entries and comments).

[1942] Data analysis and model use

[1943] The server stores the received parenting information and emotional data in a cloud database. The analysis engine then retrieves the information from the database and analyzes it using generative AI models and general artificial intelligence techniques. This analysis evaluates the child's sleep patterns, nutritional status, and behavioral health and identifies specific improvement measures. For example, it detects disrupted sleep patterns and suggests appropriate countermeasures.

[1944] Generating parenting advice

[1945] Based on the data analysis results, customized parenting advice is automatically generated. This advice is tailored to the user's individual parenting needs and contains specific and practical content. For example, it suggests an appropriate sleep routine for a two-year-old.

[1946] Sending and viewing advice

[1947] The generated parenting advice is sent to the user's device via a dedicated API. The device displays the received parenting advice to the user. In addition, the notification function can be used to notify the user of important advice in a timely manner. For example, the user can be notified of "ways to improve children's sleep."

[1948] Utilizing the Emotion Engine

[1949] The device collects emotional data based on the user's voice input, facial expression recognition, text input, etc. The server then analyzes the user's emotional data using an emotion engine. Based on the results of this analysis, the system can further customize parenting advice and provide optimal support according to the user's psychological state. For example, if the user is feeling stressed, the system can provide information on relaxation techniques and support groups.

[1950] Receiving and analyzing feedback

[1951] The user inputs and submits feedback on the advice and solutions provided. The device receives the user's feedback, generates an HTTP POST request, and sends it to the server. The server evaluates the performance of the generative AI model based on the received feedback and improves the analysis algorithm. At the same time, it also incorporates feedback from the emotion engine to improve the system so that it can provide even more accurate advice.

[1952] For example, if a user is concerned about their two-year-old's sleep patterns, they can input their child's sleep patterns through the application. Also, if a user is feeling stressed, the emotion engine will recognize that emotion.

[1953] For example, the user can use the following prompt:

[1954] "I'm having trouble with my child's sleep patterns. Specifically, he wakes up every hour every night. I'm also finding this situation stressful. Can you give me some specific advice on how to resolve this?"

[1955] By using this system, users can receive parenting advice and psychological support tailored to their individual needs, improving the quality and efficiency of parenting.

[1956] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1957] Step 1:

[1958] The user inputs childcare information and emotional data.

[1959] Users launch a dedicated application on their smartphone or tablet and enter information about their child's sleep patterns, diet, behavior, and other childcare information, as well as their own emotional state (e.g., stress and satisfaction).The application is designed so that users can comfortably enter the required information into input fields.

[1960] Input: Childcare information (sleep time, diet, behavior, etc.) and user emotional data

[1961] Output: Input data saved on the device

[1962] Step 2:

[1963] The terminal formats the input data and sends it to the server.

[1964] The device converts the childcare information and emotional data entered by the user into a standardized format. Specifically, it standardizes the child's sleep time and dietary content into time units and nutritional units, and expresses emotional data as numbers and text. It then generates an API request and sends the data to the server using the HTTP POST method.

[1965] Input: User-entered standardized parenting information and emotional data

[1966] Output: Parenting information and emotion data sent to the server

[1967] Step 3:

[1968] The server stores the received data in a cloud database.

[1969] The server receives the parenting information and emotion data sent from the device. The received data is stored in a cloud database while ensuring security and privacy. Cloud services used include AWS and Google Cloud.

[1970] Input: Childcare information and emotional data sent from the device

[1971] Output: Data stored in a cloud database

[1972] Step 4:

[1973] The server analyzes the stored data.

[1974] The server retrieves stored parenting information and emotional data from the cloud database, processes the data using an analytics engine, and evaluates the child's sleep patterns, nutritional status, and behavioral health to identify issues. For example, it can detect disrupted sleep patterns and provide appropriate countermeasures.

[1975] Input: Parenting information and emotion data obtained from a cloud database.

[1976] Output: Analysis results (children's sleep patterns, nutritional status, behavioral assessment, etc.)

[1977] Step 5:

[1978] The server generates parenting advice using the generative AI model.

[1979] Based on the analyzed data, the server automatically generates parenting advice using a generative AI model (e.g., GPT-3). This advice is specific and practical, tailored to the user's individual parenting needs. For example, it suggests a suitable sleep routine for a two-year-old child or ways for the user to relax.

[1980] Input: Analysis results (child's sleep patterns, nutritional status, behavioral assessment, etc.)

[1981] Output: Customized parenting advice

[1982] Step 6:

[1983] The server transmits the generated advice to the user's terminal.

[1984] The server sends the generated parenting advice to the user's device via a dedicated API, using an HTTP POST request designed to maintain data integrity.

[1985] Input: Generated customized parenting advice

[1986] Output: Advice sent to the user's terminal

[1987] Step 7:

[1988] The terminal displays the advice to the user.

[1989] The device displays the parenting advice received from the server to the user within the application. It can also use the notification function to provide timely notification of important advice. Specifically, it notifies the user of "measures to improve children's sleep."

[1990] Input: Customized parenting advice received from the server

[1991] Output: Advice and notifications displayed to the user

[1992] Step 8:

[1993] The user enters feedback.

[1994] Users can enter feedback through the application about the parenting advice and solutions provided, including an assessment of the effectiveness of the advice and suggestions for further improvement.

[1995] Input: User feedback data (effectiveness of advice, areas for improvement, etc.)

[1996] Output: Feedback data stored on the device

[1997] Step 9:

[1998] The device sends the feedback to the server.

[1999] The terminal receives the user's feedback and generates an HTTP POST request to send it to the server, during which the feedback data is standardized and sent to the server in an appropriate format.

[2000] Input: User feedback data

[2001] Output: Feedback data sent to the server

[2002] Step 10:

[2003] The server analyzes the feedback and improves the system.

[2004] The server analyzes the received feedback and evaluates the performance of the generative AI model and emotion engine. It also uses the feedback to improve the data analysis algorithm. This improves the accuracy of the system and provides advanced childcare support that responds to the user's individual childcare needs and psychological state.

[2005] Input: Received feedback data

[2006] Output: A system with improved generative AI models and emotion engines

[2007] (Application example 2)

[2008] 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."

[2009] In child-rearing, especially for first-time parents, gathering child-rearing information and receiving appropriate advice is important. However, conventional child-rearing support systems have difficulty responding to the individual needs and emotional state of users, and lack specific support to reduce stress and anxiety. Furthermore, they often provide uniform advice that ignores the user's emotional state, making them ineffective. This leads to a decline in the quality of child-rearing support and to situations where parents are unable to receive appropriate support.

[2010] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2011] In this invention, the server includes a data analysis means equipped with a generative AI model and general artificial intelligence technology for analyzing childcare information, an emotion engine for recognizing the user's emotional state and incorporating it into the analysis, and a means for generating and providing customized childcare advice based on the emotion data. This makes it possible to integrate and analyze the childcare information and emotion data in real time and provide highly accurate childcare advice tailored to the user's individual needs and psychological state.

[2012] "Childcare information" is a general term for a wide range of data related to childcare, such as a child's developmental status, health condition, behavioral patterns, nutritional intake, and sleep patterns.

[2013] A "user interface" refers to a screen or input device through which a user inputs childcare information, and is provided in the form of a smartphone app, tablet app, or the like.

[2014] A "server" is a computer system that analyzes childcare information and emotional data via a network, and stores and distributes the results.

[2015] A "generative AI model" is an artificial intelligence-based algorithm and its implementation used to analyze parenting information and generate customized parenting advice.

[2016] "General artificial intelligence technology" is an artificial intelligence technology that is not dependent on a specific application and can perform a wide range of data analysis and recognition tasks.

[2017] "Data analysis means" refers to the functions and processes for analyzing childcare information using generative AI models and general artificial intelligence technology.

[2018] "Childcare advice" refers to specific advice or suggestions provided to the user based on the analyzed childcare information.

[2019] An "emotion engine" is a technology that recognizes a user's emotional state based on their voice, facial expressions, text input, etc., and incorporates that data into analysis.

[2020] A "user terminal" is a device such as a smartphone or tablet that allows a user to input childcare information and receive advice.

[2021] "Feedback" refers to the user's evaluation and opinions of the parenting advice provided and the system's functionality.

[2022] This invention is a comprehensive childcare support system that analyzes childcare information and provides customized childcare advice, and in particular has the function of recognizing the user's emotional state and incorporating it into the analysis. This system is composed of the following elements.

[2023] User Interface

[2024] User terminal

[2025] Users enter childcare information through a dedicated application on a smartphone, tablet, or other device. The interface is designed to be intuitive and easy to use, providing fields for quickly and accurately entering the necessary information. Voice input and facial recognition functions are also used to collect emotional data from users.

[2026] Sending childcare information

[2027] User terminal

[2028] The childcare information entered by the user is sent to the server via an API request, and the device converts this data into a standardized format to ensure data integrity.

[2029] Data analysis and model use

[2030] server

[2031] The server stores the received parenting information in a cloud database. An analysis engine then retrieves the parenting information from the database and analyzes it using generative AI models and general artificial intelligence technology. This analysis evaluates the child's sleep patterns, nutritional status, and behavioral health, and identifies specific improvement measures.

[2032] Utilizing the Emotion Engine

[2033] User terminal

[2034] Emotional data is collected based on the user's voice input, facial expression recognition, and text input (e.g., diary entries and comments).

[2035] server

[2036] The server uses an emotion engine to analyze the user's emotional data. Based on the results of this analysis, the server can further customize parenting advice and provide optimal support based on the user's psychological state. For example, if the user is feeling stressed, the server can provide information on relaxation techniques and support groups.

[2037] Generating parenting advice

[2038] server

[2039] Based on the results of the data analysis, customized parenting advice is automatically generated, tailored to the user's individual parenting needs and includes specific, practical content.

[2040] Sending and viewing advice

[2041] server

[2042] The generated parenting advice is sent to the user's device via a dedicated API.

[2043] User terminal

[2044] The device displays the received parenting advice to the user, and can also use the notification function to notify the user of important advice in a timely manner.

[2045] Receiving and analyzing feedback

[2046] User

[2047] Users can enter and submit feedback on the advice and solutions provided.

[2048] User terminal

[2049] The terminal receives feedback from the user and generates an HTTP POST request to send to the server.

[2050] server

[2051] The server evaluates the performance of the generative AI model based on the received feedback and improves the analysis algorithm. At the same time, it also incorporates feedback from the emotion engine to improve the system so that it can provide even more accurate advice.

[2052] Examples of concrete examples and prompts

[2053] User

[2054] For example, if a user is concerned about their two-year-old child's sleep patterns, they can input their child's sleep patterns through the application. Also, if a user is feeling stressed, the emotion engine will recognize that emotion.

[2055] User terminal

[2056] The terminal converts the childcare information and emotion data into an appropriate format and transmits it to the server.

[2057] server

[2058] The server analyzes the childcare information and emotional data, evaluates the user's psychological state using an emotion engine, and then suggests a sleep routine suitable for a two-year-old and ways for the user to relax.

[2059] User terminal

[2060] The device will display advice to the user on how to improve sleep and relax, and will notify them using notifications.

[2061] User

[2062] The user inputs the results of the proposed suggestions as feedback and submits them.

[2063] server

[2064] The server analyzes the feedback and emotion data and uses it to improve the accuracy of the model and emotion engine.

[2065] Example prompt sentence:

[2066] Your child's current sleep patterns:

[2067] Start time: 20:00

[2068] End time: 06:00

[2069] User's emotional state: Stress

[2070] What parenting advice should you offer?

[2071] By using this system, users can receive optimal childcare support in real time according to their emotional state.

[2072] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2073] Step 1:

[2074] The user device collects childcare information (such as the child's sleep patterns, nutritional intake, and behavioral records) from the user through a dedicated application, as well as emotional data through voice input and facial expression recognition.

[2075] Step 2:

[2076] The user device converts the collected parenting information and emotion data into an appropriate format and sends it to the server via an API request. Specifically, the data is encoded in JSON format and a POST request is sent to the appropriate endpoint on the server.

[2077] Step 3:

[2078] The server stores the received childcare information and emotion data in a cloud database. The stored data is available for the next analysis step. Standardization and validation are also performed to ensure data integrity.

[2079] Step 4:

[2080] The server retrieves the stored parenting information and emotional data and analyzes it using a data analysis tool. Specifically, it processes the data using a generative AI model to evaluate the child's sleep patterns, nutritional status, and behavioral health. At the same time, it also evaluates the user's psychological state using an emotional engine.

[2081] Step 5:

[2082] The server generates customized parenting advice for users based on the results of data analysis. The generative AI model and emotion engine work together to generate specific advice, such as "A specific routine is effective for children who sleep between 8:00 PM and 6:00 AM."

[2083] Step 6:

[2084] The generated parenting advice is sent to the user's device via a dedicated API. The advice is formatted in JSON, which the user's device parses and prepares for display.

[2085] Step 7:

[2086] The user device displays the received parenting advice to the user and notifies the user of important advice in a timely manner using a notification function, for example, by using in-app notifications or push notifications.

[2087] Step 8:

[2088] The user enters feedback into the application on the proposed advice or solution, for example, comments about the effectiveness of the advice or areas for improvement.

[2089] Step 9:

[2090] The user device sends the entered feedback to the server as an HTTP POST request, and the feedback data is also encoded in JSON format and sent to the appropriate endpoint on the server.

[2091] Step 10:

[2092] The server stores the received feedback in a database and uses it for analysis. Based on this feedback, the performance of the generative AI model and emotion engine is evaluated and further improved. This will improve the accuracy of parenting advice from the next time onwards.

[2093] In this way, by utilizing childcare information and emotional data to provide customized advice, users can receive more accurate and practical childcare support.

[2094] 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.

[2095] 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.

[2096] 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.

[2097] 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.

[2098] 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.

[2099] 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.

[2100] 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).

[2101] 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.

[2102] 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."

[2103] 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.

[2104] 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).

[2105] 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.

[2106] 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.

[2107] 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.

[2108] 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.

[2109] 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.

[2110] 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.

[2111] 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.

[2112] 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.

[2113] 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.

[2114] 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.

[2115] The following is further disclosed regarding the above embodiment.

[2116] (Claim 1)

[2117] means for providing a user interface for inputting child care information;

[2118] means for transmitting childcare information to a server;

[2119] A data analysis means equipped with a generative AI model and general artificial intelligence technology for analyzing childcare information;

[2120] A means for generating parenting advice based on the analysis results;

[2121] means for transmitting the generated child-rearing advice to a user terminal;

[2122] means for displaying the advice on the user terminal;

[2123] a means for receiving user feedback and improving the generative AI model; and

[2124] A system including:

[2125] (Claim 2)

[2126] 10. The system of claim 1, further comprising means for selecting optimal educational activities and play based on the child's developmental stage.

[2127] (Claim 3)

[2128] 10. The system of claim 1, further comprising means for evaluating the child's sleep patterns, nutritional management, and behavioral well-being based on the analyzed parenting information and suggesting personalized remedial measures.

[2129] "Example 1"

[2130] (Claim 1)

[2131] means for providing a user interface for inputting child care information;

[2132] means for transmitting childcare information to a server;

[2133] a means of converting child care information into a standardized data format;

[2134] a means for storing childcare information in a cloud database;

[2135] A data analysis means equipped with a generative AI model and general artificial intelligence technology for analyzing childcare information;

[2136] A means for generating prompt sentences based on the analysis results and automatically generating childcare advice;

[2137] means for transmitting the generated childcare advice to a user terminal, the means including a dedicated API;

[2138] a means for displaying advice on a user terminal and notifying the user of important advice by a notification function;

[2139] A means for receiving user feedback to evaluate and improve the performance of the generative AI model; and

[2140] A system including:

[2141] (Claim 2)

[2142] 10. The system of claim 1, further comprising means for selecting optimal educational activities and play based on the child's developmental stage.

[2143] (Claim 3)

[2144] 10. The system of claim 1, further comprising means for evaluating the child's sleep patterns, nutritional management, and behavioral well-being based on the analyzed parenting information and suggesting personalized remedial measures.

[2145] "Application Example 1"

[2146] (Claim 1)

[2147] means for providing a user interface for inputting child care information;

[2148] means for transmitting childcare information to a server;

[2149] A data analysis means equipped with a generative AI model and general artificial intelligence technology for analyzing childcare information;

[2150] A means for generating parenting advice based on the analysis results;

[2151] means for transmitting the generated child-rearing advice to a user terminal;

[2152] means for displaying the advice on the user terminal;

[2153] a means for receiving user feedback and improving the generative AI model; and

[2154] a means for providing customized nutrition advice based on parenting information and generating a recommended food list;

[2155] a means for ordering ingredients and meals from a user terminal;

[2156] A system including:

[2157] (Claim 2)

[2158] 10. The system of claim 1, further comprising means for selecting optimal educational activities and play based on the child's developmental stage.

[2159] (Claim 3)

[2160] 10. The system of claim 1, further comprising means for evaluating the child's sleep patterns, nutritional management, and behavioral well-being based on the analyzed parenting information and suggesting personalized remedial measures.

[2161] "Example 2: Combining Emotion Engines"

[2162] (Claim 1)

[2163] means for providing a user interface for inputting child care information;

[2164] means for transmitting childcare information and emotion data to a server;

[2165] a data analysis means equipped with a generative AI model and general artificial intelligence technology for analyzing childcare informatio...

Claims

1. means for providing a user interface for inputting child care information; means for transmitting childcare information to a server; A data analysis means equipped with a generative AI model and general artificial intelligence technology for analyzing childcare information; A means for generating parenting advice based on the analysis results; means for transmitting the generated child-rearing advice to a user terminal; means for displaying the advice on the user terminal; a means for receiving user feedback and improving the generative AI model; and A system including:

2. The system of claim 1 further comprising means for selecting appropriate educational activities and play based on the child's developmental stage.

3. The system of claim 1 , further comprising means for evaluating the child's sleep patterns, nutritional management, and behavioral well-being based on the analyzed parenting information and suggesting personalized remedial measures.

Images