System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a question about child care input by a user; means for analyzing the question to extract main keywords; means for generating an advice using expert knowledge based on the extracted keywords; means for transmitting the generated advice to a corresponding user; and means for adding the user to an appropriate community group through cooperation with a local community.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] When it comes to childcare, beginners and parents seeking information face challenges such as a lack of reliable childcare information, a lack of connections with local communities, and anxiety and stress about childcare. These issues can reduce the quality of childcare and have a negative impact on the health and happiness of families. As traditional information sources and support are insufficient and it is difficult to receive appropriate advice in real time, a new system that provides comprehensive support for childcare is needed. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a childcare support system including: means for receiving questions about childcare input by users; means for analyzing the questions and extracting key keywords; means for generating advice based on the extracted keywords using expert knowledge; means for sending the generated advice to the corresponding users; and means for adding the users to appropriate community groups through collaboration with local communities. This allows users to receive reliable advice in real time, reducing anxiety and stress related to childcare and improving the quality of childcare. Furthermore, collaboration between local communities and online parent-child groups allows users to build a support network among users, strengthening social support.

[0006] "User" refers to an individual who enters a parenting question and receives expert advice and support from the local community.

[0007] "Questions about child-rearing" refers to text data containing specific questions or concerns related to child-rearing.

[0008] The term "receiving means" refers to a device or program that includes a communication function for acquiring input data from a user and transmitting it to a server.

[0009] "Means for analyzing and extracting key keywords" refers to algorithms or programs that identify important information from the input question and extract the necessary keywords.

[0010] "Means for generating advice using expert knowledge" refers to algorithms or systems that use a database of experts and past information to automatically generate appropriate answers to users' questions.

[0011] The "means for transmitting to a corresponding user" refers to a device or program including a communication function for converting the generated advice into an appropriate format and transmitting it to the user's terminal.

[0012] "Collaboration with local communities" refers to online or offline structures and systems that allow geographically close users to interact and support each other.

[0013] The "means for adding a user to an appropriate community group" refers to an algorithm or program for registering a user in an optimal community group based on the user's participation preference information and granting access rights.

[0014] The "childcare support system" refers to a comprehensive platform that supports families raising children by providing expert advice on childcare and collaborating with the local community. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] The present invention is a system that allows users to input questions about child-rearing, receive advice from experts in real time, and even receive child-rearing support in collaboration with local communities.

[0037] System Overview

[0038] This system includes a device used by the user, a server that analyzes questions about childcare and generates advice, and expert knowledge and information provided based on that advice. Furthermore, it will build a support network among users through collaboration with the local community.

[0039] Program processing

[0040] User inputs and submits questions

[0041] A user inputs a question about childcare through a mobile or web app and presses the send button. For example, the user inputs a question such as, "What should I do if my 6-month-old baby cries at night?" This question is sent from the device to the server.

[0042] Question Analysis

[0043] The server receives the question sent by the user. The question data is sent to the multimodal AI, which analyzes the question. For example, it extracts key keywords such as "6 months old" and "night crying."

[0044] Generating Advice

[0045] Based on the analysis results, the server uses the extracted keywords to send a request for advice to the AGI model. The AGI model then references a knowledge base of experts and past data to generate optimal advice. For example, it might generate advice such as, "There are many causes of nighttime crying, but it's important to create a good bedtime and environment for your baby. For example, it would be a good idea to set a consistent bedtime and let your baby sleep in a quiet environment."

[0046] Sending Advice

[0047] The server sends the generated advice to the user's terminal, which receives the advice and displays it on the screen.

[0048] Collaboration with local communities

[0049] When a user selects the local community participation option, a request is sent from the device to the server. The server searches for an appropriate community group based on the user's local information and past participation history, and adds the user. The user can then obtain more information and support through support and interaction from the community group.

[0050] Specific examples and applications

[0051] For example, the following is a specific example of a user asking about their 6-month-old baby crying at night.

[0052] 1. User inputs and submits question

[0053] The user enters a question into the app: "What should I do if my 6-month-old baby cries at night?" and submits it.

[0054] The device sends the question data to the server as an HTTP request.

[0055] 2. Question Analysis

[0056] The server receives the question data and performs text analysis.

[0057] Multimodal AI analyzes the question and extracts the keywords "6 months old" and "night crying."

[0058] 3. Generating Advice

[0059] The server sends a request to the AGI model using the extracted keywords.

[0060] The AGI model generates advice such as, "There are many causes of nighttime crying, but it is important to create a good sleeping environment for your baby."

[0061] 4. Submitting Advice

[0062] The server transmits the generated advice to the user's terminal.

[0063] The terminal receives the advice and displays it on the user screen.

[0064] 5. Collaboration with local communities

[0065] The user selects the local community participation option.

[0066] The server searches for an appropriate community group based on the user's area information and adds the user to it.

[0067] Users can get further support through participation in community groups.

[0068] The system allows users to receive reliable childcare information and expert advice in real time, and also strengthens connections with the local community, providing comprehensive support to reduce stress and anxiety related to childcare.

[0069] The processing flow will be explained below.

[0070] Step 1:

[0071] A user opens a mobile or web app, types a parenting question, and hits submit. For example, a user types a question like, "What should I do about my 6-month-old baby crying at night?"

[0072] Step 2:

[0073] The device creates an HTTP request with the entered question data and sends it to the server. The device then packages the data in the required format and initiates communication with the server.

[0074] Step 3:

[0075] The server receives the HTTP request and converts the question data into a format suitable for analysis. The server temporarily stores the received data and prepares it in a format suitable for analysis.

[0076] Step 4:

[0077] The server sends the question data to a multimodal AI model, which analyzes the question content. The AI ​​model then performs text analysis to extract key keywords such as "6 months old" and "night crying."

[0078] Step 5:

[0079] The server sends a request to the AGI model to generate advice based on the extracted keywords, and the server makes the appropriate API calls to establish communication with the AGI model.

[0080] Step 6:

[0081] The AGI model will refer to a knowledge base of experts and past data to generate optimal advice. For example, it might say, "There are many causes of nighttime crying, but it's important to create a good bedtime and environment for your baby. For example, it would be a good idea to set a consistent bedtime and let your baby sleep in a quiet environment."

[0082] Step 7:

[0083] The server receives the advice generated by the AGI model, converts it into a format suitable for the user, temporarily stores the advice, and prepares a response for the user device.

[0084] Step 8:

[0085] The server sends an HTTP response containing the advice to the user's device, which then encodes the response in the appropriate protocol and communicates.

[0086] Step 9:

[0087] The device receives the HTTP response and displays the advice on the user's screen. The device analyzes the received data and displays it in a format that is easy for the user to understand.

[0088] Step 10:

[0089] The user selects a local community participation option and sends a request from the terminal to the server. For example, the user selects an option saying "I want to join a local childcare support group."

[0090] Step 11:

[0091] The server checks the user's location and past participation history to search for appropriate community groups. The server then checks the database to identify the most suitable group for the user.

[0092] Step 12:

[0093] The server adds the user to the community group it finds and sends an HTTP response to the terminal indicating that the user has joined. The server then updates the database as needed and notifies the user of the results.

[0094] Step 13:

[0095] The device receives the HTTP response and displays a message indicating participation on the user's screen. The device also provides an access link to the community group, allowing users to easily join.

[0096] Example 1

[0097] 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."

[0098] Questions and consultations about childcare are diverse, making it difficult to provide appropriate advice quickly. Furthermore, there is a lack of collaboration and information sharing with local communities, making it difficult to build a support network among users. The present invention aims to solve these problems, enabling users to receive reliable advice quickly and strengthening collaboration with local communities.

[0099] 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.

[0100] In this invention, the server includes means for receiving questions about child-rearing input by a user, means for analyzing the questions and extracting key keywords, means for generating advice using an advanced knowledge base based on the extracted keywords, means for sending the generated advice to a corresponding user, means for adding the user to an appropriate community group by linking with a local community, means for receiving questions from the user through a dedicated application, and means for analyzing the user's questions using multimodal artificial intelligence. This allows the user to receive reliable advice quickly and makes it easier to receive support through linkage with the local community.

[0101] "User" refers to a person who uses the system by inputting questions about childcare.

[0102] A "question" refers to text data that a user enters to obtain information or advice about childcare.

[0103] "Server" refers to a computer system that receives questions from users and performs analysis and advice generation.

[0104] "Multimodal artificial intelligence" refers to algorithms that analyze multiple data formats to extract key keywords.

[0105] "Expert knowledge base" refers to a database containing expert knowledge and historical data on childcare.

[0106] "Advice" refers to answers or suggestions generated based on a user's question.

[0107] "Local community" refers to a support network built for each area where a user lives.

[0108] "Specialized application" refers to software that allows a user to enter questions and receive answers.

[0109] An "advanced knowledge base" refers to a database that contains more comprehensive and detailed information than an expert knowledge base.

[0110] A "generative artificial intelligence model" refers to an algorithm that uses expert knowledge bases and past data to generate optimal advice.

[0111] "Key keywords" refer to words and phrases extracted from a user's question that are important for generating advice.

[0112] "Community groups" refer to small groups within a local community that support each other.

[0113] The present invention is a system that allows users to input questions about childcare and receive necessary advice in real time. This system is composed of a user terminal, a server, an advanced knowledge base, and links with local communities.

[0114] Overall system configuration

[0115] User terminal

[0116] Users use a device such as a smartphone or PC to input questions about childcare through a dedicated application. This device includes a question input form, a submit button, and an interface for displaying advice.

[0117] server

[0118] The server receives questions sent by users, analyzes the questions, generates advice, and finally sends the advice to the corresponding users. The server implements a multimodal AI model and a generative AI model.

[0119] Data processing and calculation

[0120] Receiving and parsing questions

[0121] The server receives questions sent from user devices. For example, if a user sends a question such as, "What should I do if my 6-month-old baby cries at night?", the server analyzes the question using multimodal artificial intelligence. Through the analysis, key keywords such as "6-month-old" and "crying at night" are extracted.

[0122] Generating Advice

[0123] Based on the analysis results, the server inputs the extracted keywords into the generative AI model as a prompt sentence. The following is an example of such a prompt sentence:

[0124] TXT

[0125] "What causes a 6-month-old baby to cry at night and what can I do about it?"

[0126] Based on this prompt, the generative AI model will refer to a knowledge base of childcare experts and past data to generate optimal advice. For example, it might generate advice such as, "There are many causes of nighttime crying, but it's important to create a good bedtime and environment for your baby. For example, it's a good idea to set a consistent bedtime and let your baby sleep in a quiet environment."

[0127] Sending Advice

[0128] The generated advice is transmitted from the server to the user terminal, and the transmitted advice is displayed on the user terminal so that the user can confirm it.

[0129] Collaboration with local communities

[0130] If the user selects the local community participation option, a request is sent from the user's terminal to the server. The server searches for an appropriate community group based on the user's local information and past participation history, and adds the user to the appropriate community group. The user can obtain further support and information through the community group.

[0131] Specific hardware and software

[0132] The specific hardware used in this system includes a smartphone, a PC, and a server, while the software and algorithms used include a dedicated application, the HTTP protocol, the JSON format, multimodal artificial intelligence, and a generative artificial intelligence model.

[0133] This system will enable users to receive quick and reliable childcare advice, and will also enable them to receive multifaceted support through collaboration with the local community.

[0134] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0135] Step 1: User enters question

[0136] The user opens a dedicated application on a smartphone or PC.

[0137] The user enters questions about childcare into the application's input form.

[0138] Example input: "What can I do about my 6-month-old baby crying at night?"

[0139] Input: Text data related to childcare.

[0140] Output: Question data ready to be sent.

[0141] Step 2: Submit your question

[0142] The user confirms the entered question by pressing the send button.

[0143] The terminal sends the question data to the server as an HTTP request.

[0144] What happens: The device packages the data into JSON format and establishes an internet connection to send it to the server.

[0145] Input: The question data that the user entered and pressed submit.

[0146] Output: The query data sent to the server.

[0147] Step 3: Receiving and parsing the question

[0148] The server receives a question sent by a user.

[0149] The server analyzes the received question data using multimodal artificial intelligence.

[0150] How it works: The text analysis engine breaks down the question and extracts key keywords such as "6 months old" and "night crying."

[0151] Input: Question data submitted by the user.

[0152] Output: Extracted main keywords.

[0153] Step 4: Generating Advice

[0154] The server inputs the extracted keywords as prompt sentences into the generative artificial intelligence model.

[0155] The generative artificial intelligence model generates advice based on the prompt sentence.

[0156] Example prompt: "What causes my 6-month-old baby to cry at night and what can I do about it?"

[0157] How it works: The generative artificial intelligence model references expert knowledge bases and past data to generate appropriate advice.

[0158] Input: A prompt sentence based on the extracted main keywords.

[0159] Output: The generated advice.

[0160] Step 5: Submitting Advice

[0161] The server transmits the generated advice to the user's terminal.

[0162] Specific operation: Advice data is packaged in JSON format as an HTTP response and sent to the user's device.

[0163] Input: The generated advice.

[0164] Output: Advice data sent to the user's device.

[0165] Step 6: Receive and view advice

[0166] The terminal receives the advice sent from the server.

[0167] The terminal displays the received advice on the screen.

[0168] What it does: The application parses the advice data, formats it in a user-friendly format, and displays it.

[0169] Input: Advice data sent by the server.

[0170] Output: Advice displayed on the user's terminal.

[0171] Step 7: Engage with local communities

[0172] The user selects the local community participation option within the application.

[0173] The terminal sends the request to the server.

[0174] The server searches for an appropriate community group based on the user's area information and past participation history, and adds the user to that group.

[0175] What it does: Analyzes the user's location, identifies the most suitable community group, and adds the user.

[0176] Input: A request to join a local community and the user's local information.

[0177] Output: Notification that the user has been added to the appropriate community group.

[0178] (Application example 1)

[0179] 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."

[0180] Obtaining appropriate and prompt advice on child-rearing-related questions is a major challenge for parents. Obtaining expert advice is often time-consuming and costly, making it difficult to respond in real time. Furthermore, a lack of collaboration with local communities means that parents are unable to share information or provide support to each other. This leads to increased anxiety and stress about child-rearing.

[0181] 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.

[0182] In this invention, the server includes means for receiving questions about child-rearing input by users, means for analyzing the questions and extracting key keywords, means for generating advice using an artificial intelligence model based on the extracted keywords, means for sending the generated advice to corresponding users, means for adding users to appropriate community groups through collaboration with local communities, means for users to input and send questions through a dedicated application, and means for enhancing the advice content by referring to a knowledge base of experts. This allows users to obtain expert advice in real time and further enables them to receive mutual support through collaboration with the local community.

[0183] The "means for receiving questions about child-rearing entered by the user" is a function that allows the user to enter questions or problems about child-rearing via a terminal such as a smartphone or computer and send them to the server.

[0184] The "means for analyzing the question and extracting key keywords" is a software function for analyzing the content of the question and identifying and extracting important keywords.

[0185] The "means for generating advice using an artificial intelligence model based on extracted keywords" is a system for generating optimal advice using artificial intelligence, using extracted keywords as input.

[0186] The "means for transmitting the generated advice to the corresponding user" is a communication function for transmitting the generated advice to the user's terminal and displaying it.

[0187] The "means for adding a user to an appropriate community group through collaboration with local communities" is a system for searching for the most suitable community group based on the user's local information and adding the user to that group.

[0188] "Means for users to input and send questions via a dedicated application" refers to a function that allows users to input questions via a dedicated application and send them to the server.

[0189] "Means for enhancing advice content by referencing an expert knowledge base" refers to a system that uses expert knowledge and past data to improve the accuracy and usefulness of the advice generated.

[0190] This invention is a system that analyzes user questions related to childcare and provides expert advice in real time. Furthermore, it enables mutual support through collaboration with local communities. Specific embodiments are described below.

[0191] Hardware and software used

[0192] Hardware: Smartphone (user device), computer (server)

[0193] Software: Dedicated application (user side), Django (server side), OpenAI GPT-3 (artificial intelligence model)

[0194] Processing flow and data processing

[0195] 1. User question input: A user uses a dedicated application installed on a smartphone to input a question about childcare. For example, they input a question such as, "What should I do if my 6-month-old baby cries at night?"

[0196] 2. Submit Question: When the user presses the submit question button, the question data is sent from the application to the server as an HTTP POST request.

[0197] 3. Question analysis: The server analyzes the received question data. Specifically, it uses an artificial intelligence model based on OpenAI GPT-3 to analyze the text of the question and extract key keywords. For example, keywords such as "6 months old" and "night crying" are extracted.

[0198] 4. Advice generation: Based on the extracted keywords, a request is sent again to OpenAI GPT-3 to generate appropriate advice. An example of generated advice might be, "There are various causes of nighttime crying, but it is important to create a good bedtime and environment for your baby. For example, it would be a good idea to set a consistent bedtime and let your baby sleep in a quiet environment."

[0199] Example prompt sentence:

[0200] Extract key parenting keywords from the following questions:

[0201] Question: 'What can I do about my 6-month-old baby crying at night?'

[0202] keyword:

[0203] Example prompt sentence:

[0204] Offer parenting advice based on the following keywords:

[0205] Keywords: '6 months old, night crying'

[0206] advice:

[0207] 5. Sending advice: The generated advice is sent from the server to the user's smartphone and displayed on the application.

[0208] 6. Collaboration with local communities: If a user selects the local community participation option, the server will search for and add the user to appropriate community groups based on the user's area of ​​residence, allowing the user to share information and receive support from other parents in the same area.

[0209] This allows users to receive reliable advice in real time, and also enables them to receive mutual support through collaboration with local communities.

[0210] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0211] Step 1:

[0212] The user uses a dedicated application to input questions about childcare, such as, "What should I do if my 6-month-old baby cries at night?" The input data is saved in text format.

[0213] Step 2:

[0214] When the user presses the "Send" button, a dedicated application on the device sends the question entered by the user to the server as an HTTP POST request. The input data is sent to the server as text data.

[0215] Step 3:

[0216] The server analyzes the received HTTP POST request, extracts the question text, and starts the analysis process based on the received text data. Specifically, it generates an API request to perform text analysis.

[0217] Step 4:

[0218] The server calls the OpenAI GPT-3 API and sends the question text as a prompt. This prompt includes instructions for extracting key keywords. For example, it could be in the format "Please extract key parenting keywords from the following question: Question: 'What should I do if my 6-month-old baby cries at night?' Keywords: "

[0219] Step 5:

[0220] The GPT-3 model analyzes the input prompt and extracts key keywords, such as "6 months old" and "night crying." The server receives the extracted results and stores them as data.

[0221] Step 6:

[0222] The server then calls the GPT-3 API again and sends a prompt to generate advice based on the extracted keywords. The prompt contains instructions for generating advice content. For example, it could be in the format "Please provide parenting advice based on the following keywords: Keywords: '6 months old, night crying' Advice: "

[0223] Step 7:

[0224] The GPT-3 model generates appropriate advice based on the prompt and returns it to the server. This output includes specific advice such as, "There are various causes of nighttime crying, but it is important to create a good bedtime and environment for your baby. For example, it would be a good idea to set a consistent bedtime and let your baby sleep in a quiet environment."

[0225] Step 8:

[0226] The server receives the generated advice and sends it to the user's device. The advice is returned as an HTTP response and displayed on the screen by a dedicated application.

[0227] Step 9:

[0228] When the user selects the local community participation option, a request is sent from the terminal to the server, and the request includes information about the user's local area.

[0229] Step 10:

[0230] The server searches for appropriate community groups based on the user's location information and adds the user to them, allowing them to share information and receive support from other parents in their area.

[0231] 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.

[0232] The present invention is a system that provides accurate advice in real time in response to questions about child rearing, and further adjusts the content of the advice by recognizing the emotional state of the user. Details of this system will be described below.

[0233] System Overview

[0234] This system includes a device used by the user, a server that analyzes questions about childcare and generates advice, an emotion engine that recognizes the user's emotions, and a function for linking with local communities. Specifically, it has the following functions:

[0235] 1. User inputs and submits question

[0236] The user enters a question about childcare into the device and presses the send button. For example, the user enters a question such as, "What should I do if my 6-month-old baby cries at night?" This question is sent from the device to the server.

[0237] 2. Question Analysis and Emotion Recognition

[0238] The server receives the question sent by the user. The question data is sent to the multimodal AI, which analyzes the question. At the same time, the emotion engine recognizes the user's emotions from the question. For example, emotions such as "anxiety" or "stress" are identified.

[0239] 3. Advice Generation and Adjustment

[0240] Based on the analysis results and the emotion engine results, the server sends a request to the AGI model to generate advice. The AGI model then references a knowledge base of experts and past data to generate optimal advice. The generated advice is adjusted according to the user's emotions. For example, in addition to basic advice such as "There are various causes of nighttime crying, but it is important to organize the baby's bedtime and environment," emotional advice such as "It is important for the mother to take time to relax together" is also added.

[0241] 4. Submitting Advice

[0242] The server sends the generated advice to the user's terminal, which receives the advice and displays it on the screen.

[0243] 5. Collaboration with local communities

[0244] When a user selects the local community participation option, a request is sent from the device to the server. The server searches for an appropriate community group based on the user's local information and past participation history, and adds the user. The user can then obtain more information and support through support and interaction from the community group.

[0245] Specific examples and applications

[0246] For example, the following is a specific example of a case where a user asks a question about their 6-month-old baby's crying at night, and the emotion engine recognizes the user's "anxiety."

[0247] 1. User inputs and submits question

[0248] The user enters a question into the app: "What should I do if my 6-month-old baby cries at night?" and submits it.

[0249] The device sends the question data to the server as an HTTP request.

[0250] 2. Question Analysis and Emotion Recognition

[0251] The server receives the question data and performs text analysis.

[0252] Multimodal AI analyzes the question and extracts the keywords "6 months old" and "night crying."

[0253] The emotion engine recognizes the user's "anxiety" from the content of the question.

[0254] 3. Advice Generation and Adjustment

[0255] The server sends a request to the AGI model using the extracted keywords and emotion recognition results.

[0256] The AGI model generates advice such as, "There are various causes of nighttime crying, but it is important to create a good sleeping environment and time for the baby to sleep," along with emotionally sensitive advice such as, "It is important to create time for the mother to relax together."

[0257] 4. Submitting Advice

[0258] The server transmits the generated advice to the user's terminal.

[0259] The terminal receives the advice and displays it on the user screen.

[0260] 5. Collaboration with local communities

[0261] The user selects the local community participation option.

[0262] The server searches for an appropriate community group based on the user's area information and adds the user to it.

[0263] Users can get further support through participation in community groups.

[0264] The system allows users to receive reliable childcare information and expert advice in real time, as well as customized support tailored to their emotional state. By strengthening connections with the local community, the system can reduce anxiety and stress related to childcare and improve the quality of childcare.

[0265] The processing flow will be explained below.

[0266] Step 1:

[0267] A user opens a mobile or web app, types a parenting question, and hits submit. For example, a user types a question like, "What should I do about my 6-month-old baby crying at night?"

[0268] Step 2:

[0269] The device creates an HTTP request with the entered question data and sends it to the server. The device then packages the data in the required format and initiates communication with the server.

[0270] Step 3:

[0271] The server receives the HTTP request and retrieves the query data. The server temporarily stores the received data and converts it into a format suitable for analysis.

[0272] Step 4:

[0273] The server sends the question data to the multimodal AI model, which analyzes the question content. At the same time, the emotion engine recognizes the user's emotions from the question data.

[0274] Step 5:

[0275] The emotion engine analyzes the question data and identifies the user's emotions, such as "anxiety" or "stress." The emotion recognition results are returned to the server.

[0276] Step 6:

[0277] The server sends a request to the AGI model to generate advice based on the analysis results (major keywords) and the emotion engine results (user emotions). The server makes the appropriate API calls to establish communication with the AGI model.

[0278] Step 7:

[0279] The AGI model references expert knowledge bases and past data to generate optimal advice. For example, it generates main advice such as, "There are various causes of nighttime crying, but it is important to create a good bedtime and environment for your baby. For example, it is a good idea to set a consistent bedtime and let your baby sleep in a quiet environment." It also generates emotional advice, taking into account emotion recognition results, such as, "It is important to create time for the mother to relax together."

[0280] Step 8:

[0281] The server receives the advice generated by the AGI model, converts it into a format suitable for the user, temporarily stores the advice, and prepares a response for the user device.

[0282] Step 9:

[0283] The server sends an HTTP response containing the advice to the user's device, which then encodes the response in the appropriate protocol and communicates.

[0284] Step 10:

[0285] The device receives the HTTP response and displays the advice on the user's screen. The device analyzes the received data and displays it in a format that is easy for the user to understand.

[0286] Step 11:

[0287] When the user selects a local community participation option, the terminal sends a request to the server. For example, the user selects an option saying "I want to join a local childcare support group."

[0288] Step 12:

[0289] The server checks the user's location and past participation history to search for appropriate community groups. The server then checks the database to identify the most suitable group for the user.

[0290] Step 13:

[0291] The server adds the user to the community group it finds and sends an HTTP response to the terminal indicating that the user has joined. The server then updates the database as needed and notifies the user of the results.

[0292] Step 14:

[0293] The device receives the HTTP response and displays a message indicating participation on the user's screen. The device also provides an access link to the community group, allowing users to easily join.

[0294] Example 2

[0295] 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."

[0296] In addition to providing appropriate childcare advice in real time, there is a need to build a support system that reduces the emotional anxiety and stress experienced by users while raising children and improves the quality of childcare. However, existing systems have issues in that they do not provide advice that takes into account the user's emotional state or sufficiently collaborate with effective local communities.

[0297] 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.

[0298] In this invention, the server includes means for receiving questions about child-rearing entered by users, means for analyzing the questions and extracting key keywords, means for generating advice based on the extracted keywords using expert knowledge, means for recognizing the user's emotional state and adjusting the advice content, means for sending the generated advice to the corresponding user, and means for adding the user to an appropriate community group through collaboration with a local community. This allows users to receive professional and reliable child-rearing advice in real time and also to receive customized support tailored to their own emotional state. In addition, collaboration with the local community allows users to obtain further information and support related to child-rearing, improving the quality of child-rearing and reducing users' anxiety and stress.

[0299] 1. "User" refers to a person who inputs a parenting question.

[0300] 2. "Questions about childcare" refers to problems or inquiries related to childcare that users enter into the system.

[0301] 3. "Means for receiving" refers to a component that has the function of receiving question data sent from a user via a network.

[0302] 4. "Means of analyzing and extracting key keywords" refers to the process of analyzing the content of the question using natural language processing technology, etc., to find important information and keywords.

[0303] 5. "Means for generating advice using expert knowledge" refers to a function for creating specific advice in response to a user's question by referring to an expert's knowledge base or past data.

[0304] 6. "Means for recognizing the user's emotional state and tailoring advice content" refers to the process of analyzing the user's emotions from the content of the question and customizing advice based on the recognized emotions.

[0305] 7. "Means for sending the generated advice to the corresponding user" refers to the function for sending the created advice to the user's terminal via the Internet.

[0306] 8. "Means for adding users to appropriate community groups through collaboration with local communities" refers to a system function that uses the user's local information to appropriately collaborate with the local community in which the user wishes to join.

[0307] 9. "System" refers to the entire information processing device including the above means.

[0308] The present invention is a system that provides accurate advice in real time in response to questions about child rearing and further adjusts the content of the advice by recognizing the emotional state of the user, and is implemented as follows.

[0309] This system includes a device used by the user, a server that analyzes questions about childcare and generates advice, an emotion engine that recognizes the user's emotions, and a function for linking with local communities. Specifically, the system uses the following hardware and software:

[0310] Hardware and software used

[0311] Device: A device through which a user inputs questions about childcare, including smartphones, tablets, and personal computers.

[0312] Server: Analyzes questions, generates advice, recognizes emotions, sends advice, and collaborates with the local community. Specifically, a cloud server equipped with a high-performance processor and large memory capacity is used.

[0313] Multimodal AI: An AI engine used to analyze question content and extract key keywords. It uses natural language processing technology and a BERT-based model.

[0314] Emotion engine: Software that recognizes the user's emotions from the content of the question. Emotion analysis algorithms identify emotions such as "anxiety" and "stress."

[0315] Generative AI model: Uses AGI (artificial general intelligence) to generate advice based on the question, referencing expert knowledge bases and past data to provide optimal advice.

[0316] Specific examples

[0317] For example, consider a case where a user wants to ask a question about their 6-month-old baby crying at night. The user opens a device app, enters "What can I do about my 6-month-old baby crying at night?" into the input field, and presses the send button. This question is sent as an HTTP request to the server, and the server receives the request.

[0318] The server passes the question data to the multimodal AI, which analyzes the question and extracts keywords such as "6 months old" and "night crying." At the same time, the emotion engine identifies the emotion "anxiety" from the question. Based on these analysis results and emotion recognition results, the server sends a request to the AGI model.

[0319] Based on the questions, the AGI model generates specific advice about the causes of nighttime crying and countermeasures. For example, the model might generate advice such as, "There are various causes of nighttime crying, but it is important to create a good sleeping environment for your baby." Taking the user's emotions into consideration, the model also provides additional advice such as, "It is important to create time for the mother to relax together."

[0320] Finally, the generated advice is sent from the server to the user's device, and the user receives the advice through the app. If the user wishes, they can also be added to an appropriate community group via a local community linkage function, allowing them to receive support from local support groups.

[0321] As described above, this system allows users to receive professional and reliable child-rearing advice in real time, and also allows them to receive support tailored to their own emotional state. Furthermore, by connecting with the local community, users can obtain further information and support related to child-rearing, improving the quality of child-rearing and reducing users' anxiety and stress.

[0322] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0323] System program processing flow

[0324] Step 1: User enters question and submits

[0325] Specific behavior:

[0326] A user opens a device app, types a question such as "What should I do about my 6-month-old baby crying at night?", and presses the send button.

[0327] Input: Parenting questions entered by the user.

[0328] Data processing / data calculation:

[0329] The device application receives the user's question as text data.

[0330] The system converts the question into an HTTP request format and adds metadata (e.g., user ID, timestamp).

[0331] Output: The generated HTTP request is sent to the server.

[0332] Step 2: Question analysis and emotion recognition

[0333] Specific behavior:

[0334] The server receives the HTTP request and extracts the question data from the request body.

[0335] Input: HTTP request (question data) sent from the terminal.

[0336] Data processing / data calculation:

[0337] The server sends the question data to the multimodal AI, which uses natural language processing technology to analyze the question text and extract key keywords (e.g., "6 months old" or "night crying"). At the same time, the emotion engine recognizes the user's emotion (e.g., "anxiety") from the question content.

[0338] Output: Analyzed keyword data and emotion recognition results (emotion data).

[0339] Step 3: Generate and refine advice

[0340] Specific behavior:

[0341] The server sends the analysis results (keyword data and emotion data) to the AGI model as a request.

[0342] The AGI model references expert knowledge bases and past data to generate appropriate advice.

[0343] Input: Parsed keyword data and sentiment data.

[0344] Data processing / data calculation:

[0345] Using keywords such as "6 months old" and "night crying," the AGI model generates basic advice such as, "There are various causes of night crying, but it is important to create a good sleeping environment for your baby." At the same time, it also generates additional advice that takes into consideration emotions, such as, "It is important to create time for the mother to relax together," based on emotional data.

[0346] Output: Optimized advice data.

[0347] Step 4: Submitting Advice

[0348] Specific behavior:

[0349] The server transmits the generated advice to the user's terminal.

[0350] The device receives the advice and displays it on the app's user interface.

[0351] Input: Optimized advice data.

[0352] Data processing / data calculation:

[0353] Advice data is encrypted and sent over a secure channel (SSL / TLS). The device decrypts the data and converts it into a format for display in the user interface.

[0354] Output: The advice displayed to the user.

[0355] Step 5: Engage with local communities

[0356] Specific behavior:

[0357] The user selects the local community participation option on the device settings screen.

[0358] Optional data is sent from the terminal to the server.

[0359] The server searches for an appropriate community group based on the user's local area information and adds the user to it.

[0360] Input: Community participation options data, local information.

[0361] Data processing / data calculation:

[0362] The server retrieves the user's location information from the database, searches for matching community groups, and adds the user to the appropriate group based on the search results.

[0363] Output: Details of the community groups the user has joined.

[0364] This easy-to-follow process allows users to receive real-time parenting advice and customized support based on their emotional state, while also enabling them to access further parenting information and support from their local community.

[0365] (Application example 2)

[0366] 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."

[0367] Conventional childcare support systems can only provide uniform advice to users' questions, making it difficult to provide personalized support that takes into account specific emotional states. Furthermore, they lack connections with local communities, limiting the means by which users can receive personalized support. Furthermore, they lack a function to recommend childcare products and services, making it difficult for users to obtain the information they need in a centralized location.

[0368] 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.

[0369] In this invention, the server includes means for receiving questions about childcare input by a user, means for analyzing the questions and extracting key keywords, means for generating advice based on the extracted keywords and using expert knowledge, means for sending the generated advice to the corresponding user, means for recognizing the user's emotional state, means for adjusting the content of the advice based on the recognized emotional state, means for adding the user to an appropriate community group through collaboration with a local community, and means for recommending related childcare products and services. This makes it possible to provide appropriate advice according to the user's individual emotional state, strengthen collaboration with the local community, and improve user convenience through the recommendation of childcare products and services.

[0370] "User" refers to an individual or organization who uses this system to input questions about childcare and receive advice.

[0371] "Question" refers to a specific question or issue regarding childcare, and is information that is entered into the system and transmitted to the server.

[0372] "Keywords" are important words and phrases extracted during the question analysis process, and refer to the information that forms the basis for generating advice.

[0373] "Expert knowledge" refers to information based on specialized understanding and experience in child-rearing, a database required for the system to generate optimal advice.

[0374] "Advice" refers to parenting recommendations and solutions generated by the system and provided to the user.

[0375] "Emotional state" refers to the psychological or emotional state the user is in when asking a question, and includes specific emotions such as anxiety or stress.

[0376] A "local community" refers to a group that is part of the local community to which the user belongs and that exchanges information and provides support regarding childcare.

[0377] A "community group" is a group of users who share common interests or goals, and is formed to provide support, particularly regarding childcare.

[0378] "Related childcare products and services" refers to childcare-related products and services that the system recommends based on the content of the question and the user's emotional state.

[0379] The following describes an embodiment of the present invention.

[0380] System Overview

[0381] The system receives questions about childcare input from users, analyzes the questions to extract key keywords, and generates advice using expert knowledge. It also recognizes the user's emotional state, adjusts the advice, and recommends childcare products and services related to the advice. It also has a function for linking with local communities.

[0382] Hardware and Software Configuration

[0383] 1. User Device

[0384] The user device is a smartphone or tablet, and a dedicated childcare application is installed on it. The user uses this device to input and submit questions.

[0385] Example: Smartphone (Android, iOS)

[0386] 2. Server

[0387] The server performs multiple functions, including receiving questions, parsing, generating advice, recognizing emotional states, searching community groups, and recommending childcare products. The following software is mainly used:

[0388] Question analysis: Text analysis engines (e.g. NLTK, SpaCy)

[0389] Emotion Recognition: Emotion engine (e.g. Google Cloud Natural Language API)

[0390] Advice generation: Generative AI models (e.g., GPT-3)

[0391] Community Collaboration: Regional Information Database

[0392] Baby Product Recommendation: Recommendation Systems (e.g., Collaborative Filtering)

[0393] Data processing and calculation explanation

[0394] The server receives question data sent from the user's device and extracts key keywords using a text analysis engine. Based on the extracted keywords and emotion recognition results, it sends a request for advice generation to the generative AI model. The generative AI model references expert knowledge bases and past data to generate optimal advice. The content of the advice is adjusted according to the recognized emotional state, and is finally sent to the user's device. Related childcare products and services are also recommended. By linking with local communities, appropriate community groups are searched for and users are added.

[0395] Specific examples

[0396] The user enters a question: "What should I do if my 6-month-old baby cries at night?" This question is sent to the server via an HTTP request. The server receives the question data and analyzes it using a text analysis engine. The main keywords "6 months old" and "crying at night" are extracted, and the emotion engine recognizes the emotion "anxiety." A generative AI model (e.g., GPT-3) then generates emotion-sensitive advice such as "There are various causes of night crying, but it is important to create a good environment," along with "It is important for the mother to spend time relaxing together." This advice is then sent to the user's device along with recommendations for related childcare products and services.

[0397] Prompt Sentence Examples

[0398] A user has asked the question, "What should I do about my 6-month-old baby crying at night?" The user is worried. Please provide appropriate advice and suggest baby products related to night crying.

[0399] In this way, the system can provide appropriate advice based on the user's individual emotional state and recommendations for childcare products and services, improving convenience and quality of support.

[0400] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0401] Step 1:

[0402] The user enters a question about childcare through a dedicated application and presses the send button. The question is specific, such as, "What should I do if my 6-month-old baby cries at night?" The user's device sends this question data to the server as an HTTP request.

[0403] Input: The question text entered by the user

[0404] Output: The question data in the form of an HTTP request sent to the server

[0405] Step 2:

[0406] The server analyzes the question data received from the user using a text analysis engine (e.g., NLTK, SpaCy). Here, key keywords such as "6 months old" and "night crying" are extracted from the question.

[0407] Input: Question data in HTTP request format

[0408] Output: Extracted keywords (e.g., "6 months old", "night crying")

[0409] Step 3:

[0410] The server uses an emotion recognition engine (e.g., Google Cloud Natural Language API) to analyze the emotional state of the user's question, in this case identifying whether the user is feeling emotions such as "anxiety" or "stress."

[0411] Input: Question data in HTTP request format

[0412] Output: Perceived emotional state (e.g., "anxiety")

[0413] Step 4:

[0414] The server sends a request for advice generation to a generative AI model (e.g., GPT-3) based on the extracted keywords and the recognized emotional state. The generative AI model then refers to an expert knowledge base and past data to generate appropriate advice.

[0415] Input: extracted keywords and recognized emotional states

[0416] Output: Generated advice text (e.g., "There are various causes of nighttime crying, but it is important to create a good environment. It is also important for the mother to spend time relaxing together.")

[0417] Step 5:

[0418] Based on the generated advice, the server uses a recommendation system (e.g., Collaborative Filtering) to recommend relevant childcare products and services, taking into account the user's past history and general data in the process.

[0419] Input: Generated advice text

[0420] Output: A list of recommended childcare products and services (e.g., specific toys or relaxation items)

[0421] Step 6:

[0422] The server sends the generated advice and a list of recommended childcare products and services to the user's device, which receives this information and displays it in a dedicated application.

[0423] Input: Generated advice text, recommended childcare products and services list

[0424] Output: Advice and product / service information displayed on the user's device

[0425] Step 7:

[0426] If the user selects the local community participation option, the server will search for an appropriate community group based on the user's local information and add the user to it. After that, the user can obtain further information and support through support and interaction with the community group.

[0427] Input: Request to join local community, user's local information

[0428] Output: Community group information to which the user was added

[0429] 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.

[0430] 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.

[0431] 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.

[0432] [Second embodiment]

[0433] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0434] 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.

[0435] 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).

[0436] 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.

[0437] 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.

[0438] 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).

[0439] 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.

[0440] 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.

[0441] 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.

[0442] 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.

[0443] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0444] 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."

[0445] The present invention is a system that allows users to input questions about child-rearing, receive advice from experts in real time, and even receive child-rearing support in collaboration with local communities.

[0446] System Overview

[0447] This system includes a device used by the user, a server that analyzes questions about childcare and generates advice, and expert knowledge and information provided based on that advice. Furthermore, it will build a support network among users through collaboration with the local community.

[0448] Program processing

[0449] User inputs and submits questions

[0450] A user inputs a question about childcare through a mobile or web app and presses the send button. For example, the user inputs a question such as, "What should I do if my 6-month-old baby cries at night?" This question is sent from the device to the server.

[0451] Question Analysis

[0452] The server receives the question sent by the user. The question data is sent to the multimodal AI, which analyzes the question. For example, it extracts key keywords such as "6 months old" and "night crying."

[0453] Generating Advice

[0454] Based on the analysis results, the server uses the extracted keywords to send a request for advice to the AGI model. The AGI model then references a knowledge base of experts and past data to generate optimal advice. For example, it might generate advice such as, "There are many causes of nighttime crying, but it's important to create a good bedtime and environment for your baby. For example, it would be a good idea to set a consistent bedtime and let your baby sleep in a quiet environment."

[0455] Sending Advice

[0456] The server sends the generated advice to the user's terminal, which receives the advice and displays it on the screen.

[0457] Collaboration with local communities

[0458] When a user selects the local community participation option, a request is sent from the device to the server. The server searches for an appropriate community group based on the user's local information and past participation history, and adds the user. The user can then obtain more information and support through support and interaction from the community group.

[0459] Specific examples and applications

[0460] For example, the following is a specific example of a user asking about their 6-month-old baby crying at night.

[0461] 1. User inputs and submits question

[0462] The user enters a question into the app: "What should I do if my 6-month-old baby cries at night?" and submits it.

[0463] The device sends the question data to the server as an HTTP request.

[0464] 2. Question Analysis

[0465] The server receives the question data and performs text analysis.

[0466] Multimodal AI analyzes the question and extracts the keywords "6 months old" and "night crying."

[0467] 3. Generating Advice

[0468] The server sends a request to the AGI model using the extracted keywords.

[0469] The AGI model generates advice such as, "There are many causes of nighttime crying, but it is important to create a good sleeping environment for your baby."

[0470] 4. Submitting Advice

[0471] The server transmits the generated advice to the user's terminal.

[0472] The terminal receives the advice and displays it on the user screen.

[0473] 5. Collaboration with local communities

[0474] The user selects the local community participation option.

[0475] The server searches for an appropriate community group based on the user's area information and adds the user to it.

[0476] Users can get further support through participation in community groups.

[0477] The system allows users to receive reliable childcare information and expert advice in real time, and also strengthens connections with the local community, providing comprehensive support to reduce stress and anxiety related to childcare.

[0478] The processing flow will be explained below.

[0479] Step 1:

[0480] A user opens a mobile or web app, types a parenting question, and hits submit. For example, a user types a question like, "What should I do about my 6-month-old baby crying at night?"

[0481] Step 2:

[0482] The device creates an HTTP request with the entered question data and sends it to the server. The device then packages the data in the required format and initiates communication with the server.

[0483] Step 3:

[0484] The server receives the HTTP request and converts the question data into a format suitable for analysis. The server temporarily stores the received data and prepares it in a format suitable for analysis.

[0485] Step 4:

[0486] The server sends the question data to a multimodal AI model, which analyzes the question content. The AI ​​model then performs text analysis to extract key keywords such as "6 months old" and "night crying."

[0487] Step 5:

[0488] The server sends a request to the AGI model to generate advice based on the extracted keywords, and the server makes the appropriate API calls to establish communication with the AGI model.

[0489] Step 6:

[0490] The AGI model will refer to a knowledge base of experts and past data to generate optimal advice. For example, it might say, "There are many causes of nighttime crying, but it's important to create a good bedtime and environment for your baby. For example, it would be a good idea to set a consistent bedtime and let your baby sleep in a quiet environment."

[0491] Step 7:

[0492] The server receives the advice generated by the AGI model, converts it into a format suitable for the user, temporarily stores the advice, and prepares a response for the user device.

[0493] Step 8:

[0494] The server sends an HTTP response containing the advice to the user's device, which then encodes the response in the appropriate protocol and communicates.

[0495] Step 9:

[0496] The device receives the HTTP response and displays the advice on the user's screen. The device analyzes the received data and displays it in a format that is easy for the user to understand.

[0497] Step 10:

[0498] The user selects a local community participation option and sends a request from the terminal to the server. For example, the user selects an option saying "I want to join a local childcare support group."

[0499] Step 11:

[0500] The server checks the user's location and past participation history to search for appropriate community groups. The server then checks the database to identify the most suitable group for the user.

[0501] Step 12:

[0502] The server adds the user to the community group it finds and sends an HTTP response to the terminal indicating that the user has joined. The server then updates the database as needed and notifies the user of the results.

[0503] Step 13:

[0504] The device receives the HTTP response and displays a message indicating participation on the user's screen. The device also provides an access link to the community group, allowing users to easily join.

[0505] Example 1

[0506] 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."

[0507] Questions and consultations about childcare are diverse, making it difficult to provide appropriate advice quickly. Furthermore, there is a lack of collaboration and information sharing with local communities, making it difficult to build a support network among users. The present invention aims to solve these problems, enabling users to receive reliable advice quickly and strengthening collaboration with local communities.

[0508] 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.

[0509] In this invention, the server includes means for receiving questions about child-rearing input by a user, means for analyzing the questions and extracting key keywords, means for generating advice using an advanced knowledge base based on the extracted keywords, means for sending the generated advice to a corresponding user, means for adding the user to an appropriate community group by linking with a local community, means for receiving questions from the user through a dedicated application, and means for analyzing the user's questions using multimodal artificial intelligence. This allows the user to receive reliable advice quickly and makes it easier to receive support through linkage with the local community.

[0510] "User" refers to a person who uses the system by inputting questions about childcare.

[0511] A "question" refers to text data that a user enters to obtain information or advice about childcare.

[0512] "Server" refers to a computer system that receives questions from users and performs analysis and advice generation.

[0513] "Multimodal artificial intelligence" refers to algorithms that analyze multiple data formats to extract key keywords.

[0514] "Expert knowledge base" refers to a database containing expert knowledge and historical data on childcare.

[0515] "Advice" refers to answers or suggestions generated based on a user's question.

[0516] "Local community" refers to a support network built for each area where a user lives.

[0517] "Specialized application" refers to software that allows a user to enter questions and receive answers.

[0518] An "advanced knowledge base" refers to a database that contains more comprehensive and detailed information than an expert knowledge base.

[0519] A "generative artificial intelligence model" refers to an algorithm that uses expert knowledge bases and past data to generate optimal advice.

[0520] "Key keywords" refer to words and phrases extracted from a user's question that are important for generating advice.

[0521] "Community groups" refer to small groups within a local community that support each other.

[0522] The present invention is a system that allows users to input questions about childcare and receive necessary advice in real time. This system is composed of a user terminal, a server, an advanced knowledge base, and links with local communities.

[0523] Overall system configuration

[0524] User terminal

[0525] Users use a device such as a smartphone or PC to input questions about childcare through a dedicated application. This device includes a question input form, a submit button, and an interface for displaying advice.

[0526] server

[0527] The server receives questions sent by users, analyzes the questions, generates advice, and finally sends the advice to the corresponding users. The server implements a multimodal AI model and a generative AI model.

[0528] Data processing and calculation

[0529] Receiving and parsing questions

[0530] The server receives questions sent from user devices. For example, if a user sends a question such as, "What should I do if my 6-month-old baby cries at night?", the server analyzes the question using multimodal artificial intelligence. Through the analysis, key keywords such as "6-month-old" and "crying at night" are extracted.

[0531] Generating Advice

[0532] Based on the analysis results, the server inputs the extracted keywords into the generative AI model as a prompt sentence. The following is an example of such a prompt sentence:

[0533] TXT

[0534] "What causes a 6-month-old baby to cry at night and what can I do about it?"

[0535] Based on this prompt, the generative AI model will refer to a knowledge base of childcare experts and past data to generate optimal advice. For example, it might generate advice such as, "There are many causes of nighttime crying, but it's important to create a good bedtime and environment for your baby. For example, it's a good idea to set a consistent bedtime and let your baby sleep in a quiet environment."

[0536] Sending Advice

[0537] The generated advice is transmitted from the server to the user terminal, and the transmitted advice is displayed on the user terminal so that the user can confirm it.

[0538] Collaboration with local communities

[0539] If the user selects the local community participation option, a request is sent from the user's terminal to the server. The server searches for an appropriate community group based on the user's local information and past participation history, and adds the user to the appropriate community group. The user can obtain further support and information through the community group.

[0540] Specific hardware and software

[0541] The specific hardware used in this system includes a smartphone, a PC, and a server, while the software and algorithms used include a dedicated application, the HTTP protocol, the JSON format, multimodal artificial intelligence, and a generative artificial intelligence model.

[0542] This system will enable users to receive quick and reliable childcare advice, and will also enable them to receive multifaceted support through collaboration with the local community.

[0543] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0544] Step 1: User enters question

[0545] The user opens a dedicated application on a smartphone or PC.

[0546] The user enters questions about childcare into the application's input form.

[0547] Example input: "What can I do about my 6-month-old baby crying at night?"

[0548] Input: Text data related to childcare.

[0549] Output: Question data ready to be sent.

[0550] Step 2: Submit your question

[0551] The user confirms the entered question by pressing the send button.

[0552] The terminal sends the question data to the server as an HTTP request.

[0553] What happens: The device packages the data into JSON format and establishes an internet connection to send it to the server.

[0554] Input: The question data that the user entered and pressed submit.

[0555] Output: The query data sent to the server.

[0556] Step 3: Receiving and parsing the question

[0557] The server receives a question sent by a user.

[0558] The server analyzes the received question data using multimodal artificial intelligence.

[0559] How it works: The text analysis engine breaks down the question and extracts key keywords such as "6 months old" and "night crying."

[0560] Input: Question data submitted by the user.

[0561] Output: Extracted main keywords.

[0562] Step 4: Generating Advice

[0563] The server inputs the extracted keywords as prompt sentences into the generative artificial intelligence model.

[0564] The generative artificial intelligence model generates advice based on the prompt sentence.

[0565] Example prompt: "What causes my 6-month-old baby to cry at night and what can I do about it?"

[0566] How it works: The generative artificial intelligence model references expert knowledge bases and past data to generate appropriate advice.

[0567] Input: A prompt sentence based on the extracted main keywords.

[0568] Output: The generated advice.

[0569] Step 5: Submitting Advice

[0570] The server transmits the generated advice to the user's terminal.

[0571] Specific operation: Advice data is packaged in JSON format as an HTTP response and sent to the user's device.

[0572] Input: The generated advice.

[0573] Output: Advice data sent to the user's device.

[0574] Step 6: Receive and view advice

[0575] The terminal receives the advice sent from the server.

[0576] The terminal displays the received advice on the screen.

[0577] What it does: The application parses the advice data, formats it in a user-friendly format, and displays it.

[0578] Input: Advice data sent by the server.

[0579] Output: Advice displayed on the user's terminal.

[0580] Step 7: Engage with local communities

[0581] The user selects the local community participation option within the application.

[0582] The terminal sends the request to the server.

[0583] The server searches for an appropriate community group based on the user's area information and past participation history, and adds the user to that group.

[0584] What it does: Analyzes the user's location, identifies the most suitable community group, and adds the user.

[0585] Input: A request to join a local community and the user's local information.

[0586] Output: Notification that the user has been added to the appropriate community group.

[0587] (Application example 1)

[0588] 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."

[0589] Obtaining appropriate and prompt advice on child-rearing-related questions is a major challenge for parents. Obtaining expert advice is often time-consuming and costly, making it difficult to respond in real time. Furthermore, a lack of collaboration with local communities means that parents are unable to share information or provide support to each other. This leads to increased anxiety and stress about child-rearing.

[0590] 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.

[0591] In this invention, the server includes means for receiving questions about child-rearing input by users, means for analyzing the questions and extracting key keywords, means for generating advice using an artificial intelligence model based on the extracted keywords, means for sending the generated advice to corresponding users, means for adding users to appropriate community groups through collaboration with local communities, means for users to input and send questions through a dedicated application, and means for enhancing the advice content by referring to a knowledge base of experts. This allows users to obtain expert advice in real time and further enables them to receive mutual support through collaboration with the local community.

[0592] The "means for receiving questions about child-rearing entered by the user" is a function that allows the user to enter questions or problems about child-rearing via a terminal such as a smartphone or computer and send them to the server.

[0593] The "means for analyzing the question and extracting key keywords" is a software function for analyzing the content of the question and identifying and extracting important keywords.

[0594] The "means for generating advice using an artificial intelligence model based on extracted keywords" is a system for generating optimal advice using artificial intelligence, using extracted keywords as input.

[0595] The "means for transmitting the generated advice to the corresponding user" is a communication function for transmitting the generated advice to the user's terminal and displaying it.

[0596] The "means for adding a user to an appropriate community group through collaboration with local communities" is a system for searching for the most suitable community group based on the user's local information and adding the user to that group.

[0597] "Means for users to input and send questions via a dedicated application" refers to a function that allows users to input questions via a dedicated application and send them to the server.

[0598] "Means for enhancing advice content by referencing an expert knowledge base" refers to a system that uses expert knowledge and past data to improve the accuracy and usefulness of the advice generated.

[0599] This invention is a system that analyzes user questions related to childcare and provides expert advice in real time. Furthermore, it enables mutual support through collaboration with local communities. Specific embodiments are described below.

[0600] Hardware and software used

[0601] Hardware: Smartphone (user device), computer (server)

[0602] Software: Dedicated application (user side), Django (server side), OpenAI GPT-3 (artificial intelligence model)

[0603] Processing flow and data processing

[0604] 1. User question input: A user uses a dedicated application installed on a smartphone to input a question about childcare. For example, they input a question such as, "What should I do if my 6-month-old baby cries at night?"

[0605] 2. Submit Question: When the user presses the submit question button, the question data is sent from the application to the server as an HTTP POST request.

[0606] 3. Question analysis: The server analyzes the received question data. Specifically, it uses an artificial intelligence model based on OpenAI GPT-3 to analyze the text of the question and extract key keywords. For example, keywords such as "6 months old" and "night crying" are extracted.

[0607] 4. Advice generation: Based on the extracted keywords, a request is sent again to OpenAI GPT-3 to generate appropriate advice. An example of generated advice might be, "There are various causes of nighttime crying, but it is important to create a good bedtime and environment for your baby. For example, it would be a good idea to set a consistent bedtime and let your baby sleep in a quiet environment."

[0608] Example prompt sentence:

[0609] Extract key parenting keywords from the following questions:

[0610] Question: 'What can I do about my 6-month-old baby crying at night?'

[0611] keyword:

[0612] Example prompt sentence:

[0613] Offer parenting advice based on the following keywords:

[0614] Keywords: '6 months old, night crying'

[0615] advice:

[0616] 5. Sending advice: The generated advice is sent from the server to the user's smartphone and displayed on the application.

[0617] 6. Collaboration with local communities: If a user selects the local community participation option, the server will search for and add the user to appropriate community groups based on the user's area of ​​residence, allowing the user to share information and receive support from other parents in the same area.

[0618] This allows users to receive reliable advice in real time, and also enables them to receive mutual support through collaboration with local communities.

[0619] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0620] Step 1:

[0621] The user uses a dedicated application to input questions about childcare, such as, "What should I do if my 6-month-old baby cries at night?" The input data is saved in text format.

[0622] Step 2:

[0623] When the user presses the "Send" button, a dedicated application on the device sends the question entered by the user to the server as an HTTP POST request. The input data is sent to the server as text data.

[0624] Step 3:

[0625] The server analyzes the received HTTP POST request, extracts the question text, and starts the analysis process based on the received text data. Specifically, it generates an API request to perform text analysis.

[0626] Step 4:

[0627] The server calls the OpenAI GPT-3 API and sends the question text as a prompt. This prompt includes instructions for extracting key keywords. For example, it could be in the format "Please extract key parenting keywords from the following question: Question: 'What should I do if my 6-month-old baby cries at night?' Keywords: "

[0628] Step 5:

[0629] The GPT-3 model analyzes the input prompt and extracts key keywords, such as "6 months old" and "night crying." The server receives the extracted results and stores them as data.

[0630] Step 6:

[0631] The server then calls the GPT-3 API again and sends a prompt to generate advice based on the extracted keywords. The prompt contains instructions for generating advice content. For example, it could be in the format "Please provide parenting advice based on the following keywords: Keywords: '6 months old, night crying' Advice: "

[0632] Step 7:

[0633] The GPT-3 model generates appropriate advice based on the prompt and returns it to the server. This output includes specific advice such as, "There are various causes of nighttime crying, but it is important to create a good bedtime and environment for your baby. For example, it would be a good idea to set a consistent bedtime and let your baby sleep in a quiet environment."

[0634] Step 8:

[0635] The server receives the generated advice and sends it to the user's device. The advice is returned as an HTTP response and displayed on the screen by a dedicated application.

[0636] Step 9:

[0637] When the user selects the local community participation option, a request is sent from the terminal to the server, and the request includes information about the user's local area.

[0638] Step 10:

[0639] The server searches for appropriate community groups based on the user's location information and adds the user to them, allowing them to share information and receive support from other parents in their area.

[0640] 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.

[0641] The present invention is a system that provides accurate advice in real time in response to questions about child rearing, and further adjusts the content of the advice by recognizing the emotional state of the user. Details of this system will be described below.

[0642] System Overview

[0643] This system includes a device used by the user, a server that analyzes questions about childcare and generates advice, an emotion engine that recognizes the user's emotions, and a function for linking with local communities. Specifically, it has the following functions:

[0644] 1. User inputs and submits question

[0645] The user enters a question about childcare into the device and presses the send button. For example, the user enters a question such as, "What should I do if my 6-month-old baby cries at night?" This question is sent from the device to the server.

[0646] 2. Question Analysis and Emotion Recognition

[0647] The server receives the question sent by the user. The question data is sent to the multimodal AI, which analyzes the question. At the same time, the emotion engine recognizes the user's emotions from the question. For example, emotions such as "anxiety" or "stress" are identified.

[0648] 3. Advice Generation and Adjustment

[0649] Based on the analysis results and the emotion engine results, the server sends a request to the AGI model to generate advice. The AGI model then references a knowledge base of experts and past data to generate optimal advice. The generated advice is adjusted according to the user's emotions. For example, in addition to basic advice such as "There are various causes of nighttime crying, but it is important to organize the baby's bedtime and environment," emotional advice such as "It is important for the mother to take time to relax together" is also added.

[0650] 4. Submitting Advice

[0651] The server sends the generated advice to the user's terminal, which receives the advice and displays it on the screen.

[0652] 5. Collaboration with local communities

[0653] When a user selects the local community participation option, a request is sent from the device to the server. The server searches for an appropriate community group based on the user's local information and past participation history, and adds the user. The user can then obtain more information and support through support and interaction from the community group.

[0654] Specific examples and applications

[0655] For example, the following is a specific example of a case where a user asks a question about their 6-month-old baby's crying at night, and the emotion engine recognizes the user's "anxiety."

[0656] 1. User inputs and submits question

[0657] The user enters a question into the app: "What should I do if my 6-month-old baby cries at night?" and submits it.

[0658] The device sends the question data to the server as an HTTP request.

[0659] 2. Question Analysis and Emotion Recognition

[0660] The server receives the question data and performs text analysis.

[0661] Multimodal AI analyzes the question and extracts the keywords "6 months old" and "night crying."

[0662] The emotion engine recognizes the user's "anxiety" from the content of the question.

[0663] 3. Advice Generation and Adjustment

[0664] The server sends a request to the AGI model using the extracted keywords and emotion recognition results.

[0665] The AGI model generates advice such as, "There are various causes of nighttime crying, but it is important to create a good sleeping environment and time for the baby to sleep," along with emotionally sensitive advice such as, "It is important to create time for the mother to relax together."

[0666] 4. Submitting Advice

[0667] The server transmits the generated advice to the user's terminal.

[0668] The terminal receives the advice and displays it on the user screen.

[0669] 5. Collaboration with local communities

[0670] The user selects the local community participation option.

[0671] The server searches for an appropriate community group based on the user's area information and adds the user to it.

[0672] Users can get further support through participation in community groups.

[0673] The system allows users to receive reliable childcare information and expert advice in real time, as well as customized support tailored to their emotional state. By strengthening connections with the local community, the system can reduce anxiety and stress related to childcare and improve the quality of childcare.

[0674] The processing flow will be explained below.

[0675] Step 1:

[0676] A user opens a mobile or web app, types a parenting question, and hits submit. For example, a user types a question like, "What should I do about my 6-month-old baby crying at night?"

[0677] Step 2:

[0678] The device creates an HTTP request with the entered question data and sends it to the server. The device then packages the data in the required format and initiates communication with the server.

[0679] Step 3:

[0680] The server receives the HTTP request and retrieves the query data. The server temporarily stores the received data and converts it into a format suitable for analysis.

[0681] Step 4:

[0682] The server sends the question data to the multimodal AI model, which analyzes the question content. At the same time, the emotion engine recognizes the user's emotions from the question data.

[0683] Step 5:

[0684] The emotion engine analyzes the question data and identifies the user's emotions, such as "anxiety" or "stress." The emotion recognition results are returned to the server.

[0685] Step 6:

[0686] The server sends a request to the AGI model to generate advice based on the analysis results (major keywords) and the emotion engine results (user emotions). The server makes the appropriate API calls to establish communication with the AGI model.

[0687] Step 7:

[0688] The AGI model references expert knowledge bases and past data to generate optimal advice. For example, it generates main advice such as, "There are various causes of nighttime crying, but it is important to create a good bedtime and environment for your baby. For example, it is a good idea to set a consistent bedtime and let your baby sleep in a quiet environment." It also generates emotional advice, taking into account emotion recognition results, such as, "It is important to create time for the mother to relax together."

[0689] Step 8:

[0690] The server receives the advice generated by the AGI model, converts it into a format suitable for the user, temporarily stores the advice, and prepares a response for the user device.

[0691] Step 9:

[0692] The server sends an HTTP response containing the advice to the user's device, which then encodes the response in the appropriate protocol and communicates.

[0693] Step 10:

[0694] The device receives the HTTP response and displays the advice on the user's screen. The device analyzes the received data and displays it in a format that is easy for the user to understand.

[0695] Step 11:

[0696] When the user selects a local community participation option, the terminal sends a request to the server. For example, the user selects an option saying "I want to join a local childcare support group."

[0697] Step 12:

[0698] The server checks the user's location and past participation history to search for appropriate community groups. The server then checks the database to identify the most suitable group for the user.

[0699] Step 13:

[0700] The server adds the user to the community group it finds and sends an HTTP response to the terminal indicating that the user has joined. The server then updates the database as needed and notifies the user of the results.

[0701] Step 14:

[0702] The device receives the HTTP response and displays a message indicating participation on the user's screen. The device also provides an access link to the community group, allowing users to easily join.

[0703] Example 2

[0704] 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."

[0705] In addition to providing appropriate childcare advice in real time, there is a need to build a support system that reduces the emotional anxiety and stress experienced by users while raising children and improves the quality of childcare. However, existing systems have issues in that they do not provide advice that takes into account the user's emotional state or sufficiently collaborate with effective local communities.

[0706] 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.

[0707] In this invention, the server includes means for receiving questions about child-rearing entered by users, means for analyzing the questions and extracting key keywords, means for generating advice based on the extracted keywords using expert knowledge, means for recognizing the user's emotional state and adjusting the advice content, means for sending the generated advice to the corresponding user, and means for adding the user to an appropriate community group through collaboration with a local community. This allows users to receive professional and reliable child-rearing advice in real time and also to receive customized support tailored to their own emotional state. In addition, collaboration with the local community allows users to obtain further information and support related to child-rearing, improving the quality of child-rearing and reducing users' anxiety and stress.

[0708] 1. "User" refers to a person who inputs a parenting question.

[0709] 2. "Questions about childcare" refers to problems or inquiries related to childcare that users enter into the system.

[0710] 3. "Means for receiving" refers to a component that has the function of receiving question data sent from a user via a network.

[0711] 4. "Means of analyzing and extracting key keywords" refers to the process of analyzing the content of the question using natural language processing technology, etc., to find important information and keywords.

[0712] 5. "Means for generating advice using expert knowledge" refers to a function for creating specific advice in response to a user's question by referring to an expert's knowledge base or past data.

[0713] 6. "Means for recognizing the user's emotional state and tailoring advice content" refers to the process of analyzing the user's emotions from the content of the question and customizing advice based on the recognized emotions.

[0714] 7. "Means for sending the generated advice to the corresponding user" refers to the function for sending the created advice to the user's terminal via the Internet.

[0715] 8. "Means for adding users to appropriate community groups through collaboration with local communities" refers to a system function that uses the user's local information to appropriately collaborate with the local community in which the user wishes to join.

[0716] 9. "System" refers to the entire information processing device including the above means.

[0717] The present invention is a system that provides accurate advice in real time in response to questions about child rearing and further adjusts the content of the advice by recognizing the emotional state of the user, and is implemented as follows.

[0718] This system includes a device used by the user, a server that analyzes questions about childcare and generates advice, an emotion engine that recognizes the user's emotions, and a function for linking with local communities. Specifically, the system uses the following hardware and software:

[0719] Hardware and software used

[0720] Device: A device through which a user inputs questions about childcare, including smartphones, tablets, and personal computers.

[0721] Server: Analyzes questions, generates advice, recognizes emotions, sends advice, and collaborates with the local community. Specifically, a cloud server equipped with a high-performance processor and large memory capacity is used.

[0722] Multimodal AI: An AI engine used to analyze question content and extract key keywords. It uses natural language processing technology and a BERT-based model.

[0723] Emotion engine: Software that recognizes the user's emotions from the content of the question. Emotion analysis algorithms identify emotions such as "anxiety" and "stress."

[0724] Generative AI model: Uses AGI (artificial general intelligence) to generate advice based on the question, referencing expert knowledge bases and past data to provide optimal advice.

[0725] Specific examples

[0726] For example, consider a case where a user wants to ask a question about their 6-month-old baby crying at night. The user opens a device app, enters "What can I do about my 6-month-old baby crying at night?" into the input field, and presses the send button. This question is sent as an HTTP request to the server, and the server receives the request.

[0727] The server passes the question data to the multimodal AI, which analyzes the question and extracts keywords such as "6 months old" and "night crying." At the same time, the emotion engine identifies the emotion "anxiety" from the question. Based on these analysis results and emotion recognition results, the server sends a request to the AGI model.

[0728] Based on the questions, the AGI model generates specific advice about the causes of nighttime crying and countermeasures. For example, the model might generate advice such as, "There are various causes of nighttime crying, but it is important to create a good sleeping environment for your baby." Taking the user's emotions into consideration, the model also provides additional advice such as, "It is important to create time for the mother to relax together."

[0729] Finally, the generated advice is sent from the server to the user's device, and the user receives the advice through the app. If the user wishes, they can also be added to an appropriate community group via a local community linkage function, allowing them to receive support from local support groups.

[0730] As described above, this system allows users to receive professional and reliable child-rearing advice in real time, and also allows them to receive support tailored to their own emotional state. Furthermore, by connecting with the local community, users can obtain further information and support related to child-rearing, improving the quality of child-rearing and reducing users' anxiety and stress.

[0731] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0732] System program processing flow

[0733] Step 1: User enters question and submits

[0734] Specific behavior:

[0735] A user opens a device app, types a question such as "What should I do about my 6-month-old baby crying at night?", and presses the send button.

[0736] Input: Parenting questions entered by the user.

[0737] Data processing / data calculation:

[0738] The device application receives the user's question as text data.

[0739] The system converts the question into an HTTP request format and adds metadata (e.g., user ID, timestamp).

[0740] Output: The generated HTTP request is sent to the server.

[0741] Step 2: Question analysis and emotion recognition

[0742] Specific behavior:

[0743] The server receives the HTTP request and extracts the question data from the request body.

[0744] Input: HTTP request (question data) sent from the terminal.

[0745] Data processing / data calculation:

[0746] The server sends the question data to the multimodal AI, which uses natural language processing technology to analyze the question text and extract key keywords (e.g., "6 months old" or "night crying"). At the same time, the emotion engine recognizes the user's emotion (e.g., "anxiety") from the question content.

[0747] Output: Analyzed keyword data and emotion recognition results (emotion data).

[0748] Step 3: Generate and refine advice

[0749] Specific behavior:

[0750] The server sends the analysis results (keyword data and emotion data) to the AGI model as a request.

[0751] The AGI model references expert knowledge bases and past data to generate appropriate advice.

[0752] Input: Parsed keyword data and sentiment data.

[0753] Data processing / data calculation:

[0754] Using keywords such as "6 months old" and "night crying," the AGI model generates basic advice such as, "There are various causes of night crying, but it is important to create a good sleeping environment for your baby." At the same time, it also generates additional advice that takes into consideration emotions, such as, "It is important to create time for the mother to relax together," based on emotional data.

[0755] Output: Optimized advice data.

[0756] Step 4: Submitting Advice

[0757] Specific behavior:

[0758] The server transmits the generated advice to the user's terminal.

[0759] The device receives the advice and displays it on the app's user interface.

[0760] Input: Optimized advice data.

[0761] Data processing / data calculation:

[0762] Advice data is encrypted and sent over a secure channel (SSL / TLS). The device decrypts the data and converts it into a format for display in the user interface.

[0763] Output: The advice displayed to the user.

[0764] Step 5: Engage with local communities

[0765] Specific behavior:

[0766] The user selects the local community participation option on the device settings screen.

[0767] Optional data is sent from the terminal to the server.

[0768] The server searches for an appropriate community group based on the user's local area information and adds the user to it.

[0769] Input: Community participation options data, local information.

[0770] Data processing / data calculation:

[0771] The server retrieves the user's location information from the database, searches for matching community groups, and adds the user to the appropriate group based on the search results.

[0772] Output: Details of the community groups the user has joined.

[0773] This easy-to-follow process allows users to receive real-time parenting advice and customized support based on their emotional state, while also enabling them to access further parenting information and support from their local community.

[0774] (Application example 2)

[0775] 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."

[0776] Conventional childcare support systems can only provide uniform advice to users' questions, making it difficult to provide personalized support that takes into account specific emotional states. Furthermore, they lack connections with local communities, limiting the means by which users can receive personalized support. Furthermore, they lack a function to recommend childcare products and services, making it difficult for users to obtain the information they need in a centralized location.

[0777] 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.

[0778] In this invention, the server includes means for receiving questions about childcare input by a user, means for analyzing the questions and extracting key keywords, means for generating advice based on the extracted keywords and using expert knowledge, means for sending the generated advice to the corresponding user, means for recognizing the user's emotional state, means for adjusting the content of the advice based on the recognized emotional state, means for adding the user to an appropriate community group through collaboration with a local community, and means for recommending related childcare products and services. This makes it possible to provide appropriate advice according to the user's individual emotional state, strengthen collaboration with the local community, and improve user convenience through the recommendation of childcare products and services.

[0779] "User" refers to an individual or organization who uses this system to input questions about childcare and receive advice.

[0780] "Question" refers to a specific question or issue regarding childcare, and is information that is entered into the system and transmitted to the server.

[0781] "Keywords" are important words and phrases extracted during the question analysis process, and refer to the information that forms the basis for generating advice.

[0782] "Expert knowledge" refers to information based on specialized understanding and experience in child-rearing, a database required for the system to generate optimal advice.

[0783] "Advice" refers to parenting recommendations and solutions generated by the system and provided to the user.

[0784] "Emotional state" refers to the psychological or emotional state the user is in when asking a question, and includes specific emotions such as anxiety or stress.

[0785] A "local community" refers to a group that is part of the local community to which the user belongs and that exchanges information and provides support regarding childcare.

[0786] A "community group" is a group of users who share common interests or goals, and is formed to provide support, particularly regarding childcare.

[0787] "Related childcare products and services" refers to childcare-related products and services that the system recommends based on the content of the question and the user's emotional state.

[0788] The following describes an embodiment of the present invention.

[0789] System Overview

[0790] The system receives questions about childcare input from users, analyzes the questions to extract key keywords, and generates advice using expert knowledge. It also recognizes the user's emotional state, adjusts the advice, and recommends childcare products and services related to the advice. It also has a function for linking with local communities.

[0791] Hardware and Software Configuration

[0792] 1. User Device

[0793] The user device is a smartphone or tablet, and a dedicated childcare application is installed on it. The user uses this device to input and submit questions.

[0794] Example: Smartphone (Android, iOS)

[0795] 2. Server

[0796] The server performs multiple functions, including receiving questions, parsing, generating advice, recognizing emotional states, searching community groups, and recommending childcare products. The following software is mainly used:

[0797] Question analysis: Text analysis engines (e.g. NLTK, SpaCy)

[0798] Emotion Recognition: Emotion engine (e.g. Google Cloud Natural Language API)

[0799] Advice generation: Generative AI models (e.g., GPT-3)

[0800] Community Collaboration: Regional Information Database

[0801] Baby Product Recommendation: Recommendation Systems (e.g., Collaborative Filtering)

[0802] Data processing and calculation explanation

[0803] The server receives question data sent from the user's device and extracts key keywords using a text analysis engine. Based on the extracted keywords and emotion recognition results, it sends a request for advice generation to the generative AI model. The generative AI model references expert knowledge bases and past data to generate optimal advice. The content of the advice is adjusted according to the recognized emotional state, and is finally sent to the user's device. Related childcare products and services are also recommended. By linking with local communities, appropriate community groups are searched for and users are added.

[0804] Specific examples

[0805] The user enters a question: "What should I do if my 6-month-old baby cries at night?" This question is sent to the server via an HTTP request. The server receives the question data and analyzes it using a text analysis engine. The main keywords "6 months old" and "crying at night" are extracted, and the emotion engine recognizes the emotion "anxiety." A generative AI model (e.g., GPT-3) then generates emotion-sensitive advice such as "There are various causes of night crying, but it is important to create a good environment," along with "It is important for the mother to spend time relaxing together." This advice is then sent to the user's device along with recommendations for related childcare products and services.

[0806] Prompt Sentence Examples

[0807] A user has asked the question, "What should I do about my 6-month-old baby crying at night?" The user is worried. Please provide appropriate advice and suggest baby products related to night crying.

[0808] In this way, the system can provide appropriate advice based on the user's individual emotional state and recommendations for childcare products and services, improving convenience and quality of support.

[0809] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0810] Step 1:

[0811] The user enters a question about childcare through a dedicated application and presses the send button. The question is specific, such as, "What should I do if my 6-month-old baby cries at night?" The user's device sends this question data to the server as an HTTP request.

[0812] Input: The question text entered by the user

[0813] Output: The question data in the form of an HTTP request sent to the server

[0814] Step 2:

[0815] The server analyzes the question data received from the user using a text analysis engine (e.g., NLTK, SpaCy). Here, key keywords such as "6 months old" and "night crying" are extracted from the question.

[0816] Input: Question data in HTTP request format

[0817] Output: Extracted keywords (e.g., "6 months old", "night crying")

[0818] Step 3:

[0819] The server uses an emotion recognition engine (e.g., Google Cloud Natural Language API) to analyze the emotional state of the user's question, in this case identifying whether the user is feeling emotions such as "anxiety" or "stress."

[0820] Input: Question data in HTTP request format

[0821] Output: Perceived emotional state (e.g., "anxiety")

[0822] Step 4:

[0823] The server sends a request for advice generation to a generative AI model (e.g., GPT-3) based on the extracted keywords and the recognized emotional state. The generative AI model then refers to an expert knowledge base and past data to generate appropriate advice.

[0824] Input: extracted keywords and recognized emotional states

[0825] Output: Generated advice text (e.g., "There are various causes of nighttime crying, but it is important to create a good environment. It is also important for the mother to spend time relaxing together.")

[0826] Step 5:

[0827] Based on the generated advice, the server uses a recommendation system (e.g., Collaborative Filtering) to recommend relevant childcare products and services, taking into account the user's past history and general data in the process.

[0828] Input: Generated advice text

[0829] Output: A list of recommended childcare products and services (e.g., specific toys or relaxation items)

[0830] Step 6:

[0831] The server sends the generated advice and a list of recommended childcare products and services to the user's device, which receives this information and displays it in a dedicated application.

[0832] Input: Generated advice text, recommended childcare products and services list

[0833] Output: Advice and product / service information displayed on the user's device

[0834] Step 7:

[0835] If the user selects the local community participation option, the server will search for an appropriate community group based on the user's local information and add the user to it. After that, the user can obtain further information and support through support and interaction with the community group.

[0836] Input: Request to join local community, user's local information

[0837] Output: Community group information to which the user was added

[0838] 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.

[0839] 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.

[0840] 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.

[0841] [Third embodiment]

[0842] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0843] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0844] 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).

[0845] 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.

[0846] 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.

[0847] 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).

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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."

[0854] The present invention is a system that allows users to input questions about child-rearing, receive advice from experts in real time, and even receive child-rearing support in collaboration with local communities.

[0855] System Overview

[0856] This system includes a device used by the user, a server that analyzes questions about childcare and generates advice, and expert knowledge and information provided based on that advice. Furthermore, it will build a support network among users through collaboration with the local community.

[0857] Program processing

[0858] User inputs and submits questions

[0859] A user inputs a question about childcare through a mobile or web app and presses the send button. For example, the user inputs a question such as, "What should I do if my 6-month-old baby cries at night?" This question is sent from the device to the server.

[0860] Question Analysis

[0861] The server receives the question sent by the user. The question data is sent to the multimodal AI, which analyzes the question. For example, it extracts key keywords such as "6 months old" and "night crying."

[0862] Generating Advice

[0863] Based on the analysis results, the server uses the extracted keywords to send a request for advice to the AGI model. The AGI model then references a knowledge base of experts and past data to generate optimal advice. For example, it might generate advice such as, "There are many causes of nighttime crying, but it's important to create a good bedtime and environment for your baby. For example, it would be a good idea to set a consistent bedtime and let your baby sleep in a quiet environment."

[0864] Sending Advice

[0865] The server sends the generated advice to the user's terminal, which receives the advice and displays it on the screen.

[0866] Collaboration with local communities

[0867] When a user selects the local community participation option, a request is sent from the device to the server. The server searches for an appropriate community group based on the user's local information and past participation history, and adds the user. The user can then obtain more information and support through support and interaction from the community group.

[0868] Specific examples and applications

[0869] For example, the following is a specific example of a user asking about their 6-month-old baby crying at night.

[0870] 1. User inputs and submits question

[0871] The user enters a question into the app: "What should I do if my 6-month-old baby cries at night?" and submits it.

[0872] The device sends the question data to the server as an HTTP request.

[0873] 2. Question Analysis

[0874] The server receives the question data and performs text analysis.

[0875] Multimodal AI analyzes the question and extracts the keywords "6 months old" and "night crying."

[0876] 3. Generating Advice

[0877] The server sends a request to the AGI model using the extracted keywords.

[0878] The AGI model generates advice such as, "There are many causes of nighttime crying, but it is important to create a good sleeping environment for your baby."

[0879] 4. Submitting Advice

[0880] The server transmits the generated advice to the user's terminal.

[0881] The terminal receives the advice and displays it on the user screen.

[0882] 5. Collaboration with local communities

[0883] The user selects the local community participation option.

[0884] The server searches for an appropriate community group based on the user's area information and adds the user to it.

[0885] Users can get further support through participation in community groups.

[0886] The system allows users to receive reliable childcare information and expert advice in real time, and also strengthens connections with the local community, providing comprehensive support to reduce stress and anxiety related to childcare.

[0887] The processing flow will be explained below.

[0888] Step 1:

[0889] A user opens a mobile or web app, types a parenting question, and hits submit. For example, a user types a question like, "What should I do about my 6-month-old baby crying at night?"

[0890] Step 2:

[0891] The device creates an HTTP request with the entered question data and sends it to the server. The device then packages the data in the required format and initiates communication with the server.

[0892] Step 3:

[0893] The server receives the HTTP request and converts the question data into a format suitable for analysis. The server temporarily stores the received data and prepares it in a format suitable for analysis.

[0894] Step 4:

[0895] The server sends the question data to a multimodal AI model, which analyzes the question content. The AI ​​model then performs text analysis to extract key keywords such as "6 months old" and "night crying."

[0896] Step 5:

[0897] The server sends a request to the AGI model to generate advice based on the extracted keywords, and the server makes the appropriate API calls to establish communication with the AGI model.

[0898] Step 6:

[0899] The AGI model will refer to a knowledge base of experts and past data to generate optimal advice. For example, it might say, "There are many causes of nighttime crying, but it's important to create a good bedtime and environment for your baby. For example, it would be a good idea to set a consistent bedtime and let your baby sleep in a quiet environment."

[0900] Step 7:

[0901] The server receives the advice generated by the AGI model, converts it into a format suitable for the user, temporarily stores the advice, and prepares a response for the user device.

[0902] Step 8:

[0903] The server sends an HTTP response containing the advice to the user's device, which then encodes the response in the appropriate protocol and communicates.

[0904] Step 9:

[0905] The device receives the HTTP response and displays the advice on the user's screen. The device analyzes the received data and displays it in a format that is easy for the user to understand.

[0906] Step 10:

[0907] The user selects a local community participation option and sends a request from the terminal to the server. For example, the user selects an option saying "I want to join a local childcare support group."

[0908] Step 11:

[0909] The server checks the user's location and past participation history to search for appropriate community groups. The server then checks the database to identify the most suitable group for the user.

[0910] Step 12:

[0911] The server adds the user to the community group it finds and sends an HTTP response to the terminal indicating that the user has joined. The server then updates the database as needed and notifies the user of the results.

[0912] Step 13:

[0913] The device receives the HTTP response and displays a message indicating participation on the user's screen. The device also provides an access link to the community group, allowing users to easily join.

[0914] Example 1

[0915] 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."

[0916] Questions and consultations about childcare are diverse, making it difficult to provide appropriate advice quickly. Furthermore, there is a lack of collaboration and information sharing with local communities, making it difficult to build a support network among users. The present invention aims to solve these problems, enabling users to receive reliable advice quickly and strengthening collaboration with local communities.

[0917] 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.

[0918] In this invention, the server includes means for receiving questions about child-rearing input by a user, means for analyzing the questions and extracting key keywords, means for generating advice using an advanced knowledge base based on the extracted keywords, means for sending the generated advice to a corresponding user, means for adding the user to an appropriate community group by linking with a local community, means for receiving questions from the user through a dedicated application, and means for analyzing the user's questions using multimodal artificial intelligence. This allows the user to receive reliable advice quickly and makes it easier to receive support through linkage with the local community.

[0919] "User" refers to a person who uses the system by inputting questions about childcare.

[0920] A "question" refers to text data that a user enters to obtain information or advice about childcare.

[0921] "Server" refers to a computer system that receives questions from users and performs analysis and advice generation.

[0922] "Multimodal artificial intelligence" refers to algorithms that analyze multiple data formats to extract key keywords.

[0923] "Expert knowledge base" refers to a database containing expert knowledge and historical data on childcare.

[0924] "Advice" refers to answers or suggestions generated based on a user's question.

[0925] "Local community" refers to a support network built for each area where a user lives.

[0926] "Specialized application" refers to software that allows a user to enter questions and receive answers.

[0927] An "advanced knowledge base" refers to a database that contains more comprehensive and detailed information than an expert knowledge base.

[0928] A "generative artificial intelligence model" refers to an algorithm that uses expert knowledge bases and past data to generate optimal advice.

[0929] "Key keywords" refer to words and phrases extracted from a user's question that are important for generating advice.

[0930] "Community groups" refer to small groups within a local community that support each other.

[0931] The present invention is a system that allows users to input questions about childcare and receive necessary advice in real time. This system is composed of a user terminal, a server, an advanced knowledge base, and links with local communities.

[0932] Overall system configuration

[0933] User terminal

[0934] Users use a device such as a smartphone or PC to input questions about childcare through a dedicated application. This device includes a question input form, a submit button, and an interface for displaying advice.

[0935] server

[0936] The server receives questions sent by users, analyzes the questions, generates advice, and finally sends the advice to the corresponding users. The server implements a multimodal AI model and a generative AI model.

[0937] Data processing and calculation

[0938] Receiving and parsing questions

[0939] The server receives questions sent from user devices. For example, if a user sends a question such as, "What should I do if my 6-month-old baby cries at night?", the server analyzes the question using multimodal artificial intelligence. Through the analysis, key keywords such as "6-month-old" and "crying at night" are extracted.

[0940] Generating Advice

[0941] Based on the analysis results, the server inputs the extracted keywords into the generative AI model as a prompt sentence. The following is an example of such a prompt sentence:

[0942] TXT

[0943] "What causes a 6-month-old baby to cry at night and what can I do about it?"

[0944] Based on this prompt, the generative AI model will refer to a knowledge base of childcare experts and past data to generate optimal advice. For example, it might generate advice such as, "There are many causes of nighttime crying, but it's important to create a good bedtime and environment for your baby. For example, it's a good idea to set a consistent bedtime and let your baby sleep in a quiet environment."

[0945] Sending Advice

[0946] The generated advice is transmitted from the server to the user terminal, and the transmitted advice is displayed on the user terminal so that the user can confirm it.

[0947] Collaboration with local communities

[0948] If the user selects the local community participation option, a request is sent from the user's terminal to the server. The server searches for an appropriate community group based on the user's local information and past participation history, and adds the user to the appropriate community group. The user can obtain further support and information through the community group.

[0949] Specific hardware and software

[0950] The specific hardware used in this system includes a smartphone, a PC, and a server, while the software and algorithms used include a dedicated application, the HTTP protocol, the JSON format, multimodal artificial intelligence, and a generative artificial intelligence model.

[0951] This system will enable users to receive quick and reliable childcare advice, and will also enable them to receive multifaceted support through collaboration with the local community.

[0952] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0953] Step 1: User enters question

[0954] The user opens a dedicated application on a smartphone or PC.

[0955] The user enters questions about childcare into the application's input form.

[0956] Example input: "What can I do about my 6-month-old baby crying at night?"

[0957] Input: Text data related to childcare.

[0958] Output: Question data ready to be sent.

[0959] Step 2: Submit your question

[0960] The user confirms the entered question by pressing the send button.

[0961] The terminal sends the question data to the server as an HTTP request.

[0962] What happens: The device packages the data into JSON format and establishes an internet connection to send it to the server.

[0963] Input: The question data that the user entered and pressed submit.

[0964] Output: The query data sent to the server.

[0965] Step 3: Receiving and parsing the question

[0966] The server receives a question sent by a user.

[0967] The server analyzes the received question data using multimodal artificial intelligence.

[0968] How it works: The text analysis engine breaks down the question and extracts key keywords such as "6 months old" and "night crying."

[0969] Input: Question data submitted by the user.

[0970] Output: Extracted main keywords.

[0971] Step 4: Generating Advice

[0972] The server inputs the extracted keywords as prompt sentences into the generative artificial intelligence model.

[0973] The generative artificial intelligence model generates advice based on the prompt sentence.

[0974] Example prompt: "What causes my 6-month-old baby to cry at night and what can I do about it?"

[0975] How it works: The generative artificial intelligence model references expert knowledge bases and past data to generate appropriate advice.

[0976] Input: A prompt sentence based on the extracted main keywords.

[0977] Output: The generated advice.

[0978] Step 5: Submitting Advice

[0979] The server transmits the generated advice to the user's terminal.

[0980] Specific operation: Advice data is packaged in JSON format as an HTTP response and sent to the user's device.

[0981] Input: The generated advice.

[0982] Output: Advice data sent to the user's device.

[0983] Step 6: Receive and view advice

[0984] The terminal receives the advice sent from the server.

[0985] The terminal displays the received advice on the screen.

[0986] What it does: The application parses the advice data, formats it in a user-friendly format, and displays it.

[0987] Input: Advice data sent by the server.

[0988] Output: Advice displayed on the user's terminal.

[0989] Step 7: Engage with local communities

[0990] The user selects the local community participation option within the application.

[0991] The terminal sends the request to the server.

[0992] The server searches for an appropriate community group based on the user's area information and past participation history, and adds the user to that group.

[0993] What it does: Analyzes the user's location, identifies the most suitable community group, and adds the user.

[0994] Input: A request to join a local community and the user's local information.

[0995] Output: Notification that the user has been added to the appropriate community group.

[0996] (Application example 1)

[0997] 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."

[0998] Obtaining appropriate and prompt advice on child-rearing-related questions is a major challenge for parents. Obtaining expert advice is often time-consuming and costly, making it difficult to respond in real time. Furthermore, a lack of collaboration with local communities means that parents are unable to share information or provide support to each other. This leads to increased anxiety and stress about child-rearing.

[0999] 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.

[1000] In this invention, the server includes means for receiving questions about child-rearing input by users, means for analyzing the questions and extracting key keywords, means for generating advice using an artificial intelligence model based on the extracted keywords, means for sending the generated advice to corresponding users, means for adding users to appropriate community groups through collaboration with local communities, means for users to input and send questions through a dedicated application, and means for enhancing the advice content by referring to a knowledge base of experts. This allows users to obtain expert advice in real time and further enables them to receive mutual support through collaboration with the local community.

[1001] The "means for receiving questions about child-rearing entered by the user" is a function that allows the user to enter questions or problems about child-rearing via a terminal such as a smartphone or computer and send them to the server.

[1002] The "means for analyzing the question and extracting key keywords" is a software function for analyzing the content of the question and identifying and extracting important keywords.

[1003] The "means for generating advice using an artificial intelligence model based on extracted keywords" is a system for generating optimal advice using artificial intelligence, using extracted keywords as input.

[1004] The "means for transmitting the generated advice to the corresponding user" is a communication function for transmitting the generated advice to the user's terminal and displaying it.

[1005] The "means for adding a user to an appropriate community group through collaboration with local communities" is a system for searching for the most suitable community group based on the user's local information and adding the user to that group.

[1006] "Means for users to input and send questions via a dedicated application" refers to a function that allows users to input questions via a dedicated application and send them to the server.

[1007] "Means for enhancing advice content by referencing an expert knowledge base" refers to a system that uses expert knowledge and past data to improve the accuracy and usefulness of the advice generated.

[1008] This invention is a system that analyzes user questions related to childcare and provides expert advice in real time. Furthermore, it enables mutual support through collaboration with local communities. Specific embodiments are described below.

[1009] Hardware and software used

[1010] Hardware: Smartphone (user device), computer (server)

[1011] Software: Dedicated application (user side), Django (server side), OpenAI GPT-3 (artificial intelligence model)

[1012] Processing flow and data processing

[1013] 1. User question input: A user uses a dedicated application installed on a smartphone to input a question about childcare. For example, they input a question such as, "What should I do if my 6-month-old baby cries at night?"

[1014] 2. Submit Question: When the user presses the submit question button, the question data is sent from the application to the server as an HTTP POST request.

[1015] 3. Question analysis: The server analyzes the received question data. Specifically, it uses an artificial intelligence model based on OpenAI GPT-3 to analyze the text of the question and extract key keywords. For example, keywords such as "6 months old" and "night crying" are extracted.

[1016] 4. Advice generation: Based on the extracted keywords, a request is sent again to OpenAI GPT-3 to generate appropriate advice. An example of generated advice might be, "There are various causes of nighttime crying, but it is important to create a good bedtime and environment for your baby. For example, it would be a good idea to set a consistent bedtime and let your baby sleep in a quiet environment."

[1017] Example prompt sentence:

[1018] Extract key parenting keywords from the following questions:

[1019] Question: 'What can I do about my 6-month-old baby crying at night?'

[1020] keyword:

[1021] Example prompt sentence:

[1022] Offer parenting advice based on the following keywords:

[1023] Keywords: '6 months old, night crying'

[1024] advice:

[1025] 5. Sending advice: The generated advice is sent from the server to the user's smartphone and displayed on the application.

[1026] 6. Collaboration with local communities: If a user selects the local community participation option, the server will search for and add the user to appropriate community groups based on the user's area of ​​residence, allowing the user to share information and receive support from other parents in the same area.

[1027] This allows users to receive reliable advice in real time, and also enables them to receive mutual support through collaboration with local communities.

[1028] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1029] Step 1:

[1030] The user uses a dedicated application to input questions about childcare, such as, "What should I do if my 6-month-old baby cries at night?" The input data is saved in text format.

[1031] Step 2:

[1032] When the user presses the "Send" button, a dedicated application on the device sends the question entered by the user to the server as an HTTP POST request. The input data is sent to the server as text data.

[1033] Step 3:

[1034] The server analyzes the received HTTP POST request, extracts the question text, and starts the analysis process based on the received text data. Specifically, it generates an API request to perform text analysis.

[1035] Step 4:

[1036] The server calls the OpenAI GPT-3 API and sends the question text as a prompt. This prompt includes instructions for extracting key keywords. For example, it could be in the format "Please extract key parenting keywords from the following question: Question: 'What should I do if my 6-month-old baby cries at night?' Keywords: "

[1037] Step 5:

[1038] The GPT-3 model analyzes the input prompt and extracts key keywords, such as "6 months old" and "night crying." The server receives the extracted results and stores them as data.

[1039] Step 6:

[1040] The server then calls the GPT-3 API again and sends a prompt to generate advice based on the extracted keywords. The prompt contains instructions for generating advice content. For example, it could be in the format "Please provide parenting advice based on the following keywords: Keywords: '6 months old, night crying' Advice: "

[1041] Step 7:

[1042] The GPT-3 model generates appropriate advice based on the prompt and returns it to the server. This output includes specific advice such as, "There are various causes of nighttime crying, but it is important to create a good bedtime and environment for your baby. For example, it would be a good idea to set a consistent bedtime and let your baby sleep in a quiet environment."

[1043] Step 8:

[1044] The server receives the generated advice and sends it to the user's device. The advice is returned as an HTTP response and displayed on the screen by a dedicated application.

[1045] Step 9:

[1046] When the user selects the local community participation option, a request is sent from the terminal to the server, and the request includes information about the user's local area.

[1047] Step 10:

[1048] The server searches for appropriate community groups based on the user's location information and adds the user to them, allowing them to share information and receive support from other parents in their area.

[1049] 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.

[1050] The present invention is a system that provides accurate advice in real time in response to questions about child rearing, and further adjusts the content of the advice by recognizing the emotional state of the user. Details of this system will be described below.

[1051] System Overview

[1052] This system includes a device used by the user, a server that analyzes questions about childcare and generates advice, an emotion engine that recognizes the user's emotions, and a function for linking with local communities. Specifically, it has the following functions:

[1053] 1. User inputs and submits question

[1054] The user enters a question about childcare into the device and presses the send button. For example, the user enters a question such as, "What should I do if my 6-month-old baby cries at night?" This question is sent from the device to the server.

[1055] 2. Question Analysis and Emotion Recognition

[1056] The server receives the question sent by the user. The question data is sent to the multimodal AI, which analyzes the question. At the same time, the emotion engine recognizes the user's emotions from the question. For example, emotions such as "anxiety" or "stress" are identified.

[1057] 3. Advice Generation and Adjustment

[1058] Based on the analysis results and the emotion engine results, the server sends a request to the AGI model to generate advice. The AGI model then references a knowledge base of experts and past data to generate optimal advice. The generated advice is adjusted according to the user's emotions. For example, in addition to basic advice such as "There are various causes of nighttime crying, but it is important to organize the baby's bedtime and environment," emotional advice such as "It is important for the mother to take time to relax together" is also added.

[1059] 4. Submitting Advice

[1060] The server sends the generated advice to the user's terminal, which receives the advice and displays it on the screen.

[1061] 5. Collaboration with local communities

[1062] When a user selects the local community participation option, a request is sent from the device to the server. The server searches for an appropriate community group based on the user's local information and past participation history, and adds the user. The user can then obtain more information and support through support and interaction from the community group.

[1063] Specific examples and applications

[1064] For example, the following is a specific example of a case where a user asks a question about their 6-month-old baby's crying at night, and the emotion engine recognizes the user's "anxiety."

[1065] 1. User inputs and submits question

[1066] The user enters a question into the app: "What should I do if my 6-month-old baby cries at night?" and submits it.

[1067] The device sends the question data to the server as an HTTP request.

[1068] 2. Question Analysis and Emotion Recognition

[1069] The server receives the question data and performs text analysis.

[1070] Multimodal AI analyzes the question and extracts the keywords "6 months old" and "night crying."

[1071] The emotion engine recognizes the user's "anxiety" from the content of the question.

[1072] 3. Advice Generation and Adjustment

[1073] The server sends a request to the AGI model using the extracted keywords and emotion recognition results.

[1074] The AGI model generates advice such as, "There are various causes of nighttime crying, but it is important to create a good sleeping environment and time for the baby to sleep," along with emotionally sensitive advice such as, "It is important to create time for the mother to relax together."

[1075] 4. Submitting Advice

[1076] The server transmits the generated advice to the user's terminal.

[1077] The terminal receives the advice and displays it on the user screen.

[1078] 5. Collaboration with local communities

[1079] The user selects the local community participation option.

[1080] The server searches for an appropriate community group based on the user's area information and adds the user to it.

[1081] Users can get further support through participation in community groups.

[1082] The system allows users to receive reliable childcare information and expert advice in real time, as well as customized support tailored to their emotional state. By strengthening connections with the local community, the system can reduce anxiety and stress related to childcare and improve the quality of childcare.

[1083] The processing flow will be explained below.

[1084] Step 1:

[1085] A user opens a mobile or web app, types a parenting question, and hits submit. For example, a user types a question like, "What should I do about my 6-month-old baby crying at night?"

[1086] Step 2:

[1087] The device creates an HTTP request with the entered question data and sends it to the server. The device then packages the data in the required format and initiates communication with the server.

[1088] Step 3:

[1089] The server receives the HTTP request and retrieves the query data. The server temporarily stores the received data and converts it into a format suitable for analysis.

[1090] Step 4:

[1091] The server sends the question data to the multimodal AI model, which analyzes the question content. At the same time, the emotion engine recognizes the user's emotions from the question data.

[1092] Step 5:

[1093] The emotion engine analyzes the question data and identifies the user's emotions, such as "anxiety" or "stress." The emotion recognition results are returned to the server.

[1094] Step 6:

[1095] The server sends a request to the AGI model to generate advice based on the analysis results (major keywords) and the emotion engine results (user emotions). The server makes the appropriate API calls to establish communication with the AGI model.

[1096] Step 7:

[1097] The AGI model references expert knowledge bases and past data to generate optimal advice. For example, it generates main advice such as, "There are various causes of nighttime crying, but it is important to create a good bedtime and environment for your baby. For example, it is a good idea to set a consistent bedtime and let your baby sleep in a quiet environment." It also generates emotional advice, taking into account emotion recognition results, such as, "It is important to create time for the mother to relax together."

[1098] Step 8:

[1099] The server receives the advice generated by the AGI model, converts it into a format suitable for the user, temporarily stores the advice, and prepares a response for the user device.

[1100] Step 9:

[1101] The server sends an HTTP response containing the advice to the user's device, which then encodes the response in the appropriate protocol and communicates.

[1102] Step 10:

[1103] The device receives the HTTP response and displays the advice on the user's screen. The device analyzes the received data and displays it in a format that is easy for the user to understand.

[1104] Step 11:

[1105] When the user selects a local community participation option, the terminal sends a request to the server. For example, the user selects an option saying "I want to join a local childcare support group."

[1106] Step 12:

[1107] The server checks the user's location and past participation history to search for appropriate community groups. The server then checks the database to identify the most suitable group for the user.

[1108] Step 13:

[1109] The server adds the user to the community group it finds and sends an HTTP response to the terminal indicating that the user has joined. The server then updates the database as needed and notifies the user of the results.

[1110] Step 14:

[1111] The device receives the HTTP response and displays a message indicating participation on the user's screen. The device also provides an access link to the community group, allowing users to easily join.

[1112] Example 2

[1113] 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."

[1114] In addition to providing appropriate childcare advice in real time, there is a need to build a support system that reduces the emotional anxiety and stress experienced by users while raising children and improves the quality of childcare. However, existing systems have issues in that they do not provide advice that takes into account the user's emotional state or sufficiently collaborate with effective local communities.

[1115] 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.

[1116] In this invention, the server includes means for receiving questions about child-rearing entered by users, means for analyzing the questions and extracting key keywords, means for generating advice based on the extracted keywords using expert knowledge, means for recognizing the user's emotional state and adjusting the advice content, means for sending the generated advice to the corresponding user, and means for adding the user to an appropriate community group through collaboration with a local community. This allows users to receive professional and reliable child-rearing advice in real time and also to receive customized support tailored to their own emotional state. In addition, collaboration with the local community allows users to obtain further information and support related to child-rearing, improving the quality of child-rearing and reducing users' anxiety and stress.

[1117] 1. "User" refers to a person who inputs a parenting question.

[1118] 2. "Questions about childcare" refers to problems or inquiries related to childcare that users enter into the system.

[1119] 3. "Means for receiving" refers to a component that has the function of receiving question data sent from a user via a network.

[1120] 4. "Means of analyzing and extracting key keywords" refers to the process of analyzing the content of the question using natural language processing technology, etc., to find important information and keywords.

[1121] 5. "Means for generating advice using expert knowledge" refers to a function for creating specific advice in response to a user's question by referring to an expert's knowledge base or past data.

[1122] 6. "Means for recognizing the user's emotional state and tailoring advice content" refers to the process of analyzing the user's emotions from the content of the question and customizing advice based on the recognized emotions.

[1123] 7. "Means for sending the generated advice to the corresponding user" refers to the function for sending the created advice to the user's terminal via the Internet.

[1124] 8. "Means for adding users to appropriate community groups through collaboration with local communities" refers to a system function that uses the user's local information to appropriately collaborate with the local community in which the user wishes to join.

[1125] 9. "System" refers to the entire information processing device including the above means.

[1126] The present invention is a system that provides accurate advice in real time in response to questions about child rearing and further adjusts the content of the advice by recognizing the emotional state of the user, and is implemented as follows.

[1127] This system includes a device used by the user, a server that analyzes questions about childcare and generates advice, an emotion engine that recognizes the user's emotions, and a function for linking with local communities. Specifically, the system uses the following hardware and software:

[1128] Hardware and software used

[1129] Device: A device through which a user inputs questions about childcare, including smartphones, tablets, and personal computers.

[1130] Server: Analyzes questions, generates advice, recognizes emotions, sends advice, and collaborates with the local community. Specifically, a cloud server equipped with a high-performance processor and large memory capacity is used.

[1131] Multimodal AI: An AI engine used to analyze question content and extract key keywords. It uses natural language processing technology and a BERT-based model.

[1132] Emotion engine: Software that recognizes the user's emotions from the content of the question. Emotion analysis algorithms identify emotions such as "anxiety" and "stress."

[1133] Generative AI model: Uses AGI (artificial general intelligence) to generate advice based on the question, referencing expert knowledge bases and past data to provide optimal advice.

[1134] Specific examples

[1135] For example, consider a case where a user wants to ask a question about their 6-month-old baby crying at night. The user opens a device app, enters "What can I do about my 6-month-old baby crying at night?" into the input field, and presses the send button. This question is sent as an HTTP request to the server, and the server receives the request.

[1136] The server passes the question data to the multimodal AI, which analyzes the question and extracts keywords such as "6 months old" and "night crying." At the same time, the emotion engine identifies the emotion "anxiety" from the question. Based on these analysis results and emotion recognition results, the server sends a request to the AGI model.

[1137] Based on the questions, the AGI model generates specific advice about the causes of nighttime crying and countermeasures. For example, the model might generate advice such as, "There are various causes of nighttime crying, but it is important to create a good sleeping environment for your baby." Taking the user's emotions into consideration, the model also provides additional advice such as, "It is important to create time for the mother to relax together."

[1138] Finally, the generated advice is sent from the server to the user's device, and the user receives the advice through the app. If the user wishes, they can also be added to an appropriate community group via a local community linkage function, allowing them to receive support from local support groups.

[1139] As described above, this system allows users to receive professional and reliable child-rearing advice in real time, and also allows them to receive support tailored to their own emotional state. Furthermore, by connecting with the local community, users can obtain further information and support related to child-rearing, improving the quality of child-rearing and reducing users' anxiety and stress.

[1140] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1141] System program processing flow

[1142] Step 1: User enters question and submits

[1143] Specific behavior:

[1144] A user opens a device app, types a question such as "What should I do about my 6-month-old baby crying at night?", and presses the send button.

[1145] Input: Parenting questions entered by the user.

[1146] Data processing / data calculation:

[1147] The device application receives the user's question as text data.

[1148] The system converts the question into an HTTP request format and adds metadata (e.g., user ID, timestamp).

[1149] Output: The generated HTTP request is sent to the server.

[1150] Step 2: Question analysis and emotion recognition

[1151] Specific behavior:

[1152] The server receives the HTTP request and extracts the question data from the request body.

[1153] Input: HTTP request (question data) sent from the terminal.

[1154] Data processing / data calculation:

[1155] The server sends the question data to the multimodal AI, which uses natural language processing technology to analyze the question text and extract key keywords (e.g., "6 months old" or "night crying"). At the same time, the emotion engine recognizes the user's emotion (e.g., "anxiety") from the question content.

[1156] Output: Analyzed keyword data and emotion recognition results (emotion data).

[1157] Step 3: Generate and refine advice

[1158] Specific behavior:

[1159] The server sends the analysis results (keyword data and emotion data) to the AGI model as a request.

[1160] The AGI model references expert knowledge bases and past data to generate appropriate advice.

[1161] Input: Parsed keyword data and sentiment data.

[1162] Data processing / data calculation:

[1163] Using keywords such as "6 months old" and "night crying," the AGI model generates basic advice such as, "There are various causes of night crying, but it is important to create a good sleeping environment for your baby." At the same time, it also generates additional advice that takes into consideration emotions, such as, "It is important to create time for the mother to relax together," based on emotional data.

[1164] Output: Optimized advice data.

[1165] Step 4: Submitting Advice

[1166] Specific behavior:

[1167] The server transmits the generated advice to the user's terminal.

[1168] The device receives the advice and displays it on the app's user interface.

[1169] Input: Optimized advice data.

[1170] Data processing / data calculation:

[1171] Advice data is encrypted and sent over a secure channel (SSL / TLS). The device decrypts the data and converts it into a format for display in the user interface.

[1172] Output: The advice displayed to the user.

[1173] Step 5: Engage with local communities

[1174] Specific behavior:

[1175] The user selects the local community participation option on the device settings screen.

[1176] Optional data is sent from the terminal to the server.

[1177] The server searches for an appropriate community group based on the user's local area information and adds the user to it.

[1178] Input: Community participation options data, local information.

[1179] Data processing / data calculation:

[1180] The server retrieves the user's location information from the database, searches for matching community groups, and adds the user to the appropriate group based on the search results.

[1181] Output: Details of the community groups the user has joined.

[1182] This easy-to-follow process allows users to receive real-time parenting advice and customized support based on their emotional state, while also enabling them to access further parenting information and support from their local community.

[1183] (Application example 2)

[1184] 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."

[1185] Conventional childcare support systems can only provide uniform advice to users' questions, making it difficult to provide personalized support that takes into account specific emotional states. Furthermore, they lack connections with local communities, limiting the means by which users can receive personalized support. Furthermore, they lack a function to recommend childcare products and services, making it difficult for users to obtain the information they need in a centralized location.

[1186] 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.

[1187] In this invention, the server includes means for receiving questions about childcare input by a user, means for analyzing the questions and extracting key keywords, means for generating advice based on the extracted keywords and using expert knowledge, means for sending the generated advice to the corresponding user, means for recognizing the user's emotional state, means for adjusting the content of the advice based on the recognized emotional state, means for adding the user to an appropriate community group through collaboration with a local community, and means for recommending related childcare products and services. This makes it possible to provide appropriate advice according to the user's individual emotional state, strengthen collaboration with the local community, and improve user convenience through the recommendation of childcare products and services.

[1188] "User" refers to an individual or organization who uses this system to input questions about childcare and receive advice.

[1189] "Question" refers to a specific question or issue regarding childcare, and is information that is entered into the system and transmitted to the server.

[1190] "Keywords" are important words and phrases extracted during the question analysis process, and refer to the information that forms the basis for generating advice.

[1191] "Expert knowledge" refers to information based on specialized understanding and experience in child-rearing, a database required for the system to generate optimal advice.

[1192] "Advice" refers to parenting recommendations and solutions generated by the system and provided to the user.

[1193] "Emotional state" refers to the psychological or emotional state the user is in when asking a question, and includes specific emotions such as anxiety or stress.

[1194] A "local community" refers to a group that is part of the local community to which the user belongs and that exchanges information and provides support regarding childcare.

[1195] A "community group" is a group of users who share common interests or goals, and is formed to provide support, particularly regarding childcare.

[1196] "Related childcare products and services" refers to childcare-related products and services that the system recommends based on the content of the question and the user's emotional state.

[1197] The following describes an embodiment of the present invention.

[1198] System Overview

[1199] The system receives questions about childcare input from users, analyzes the questions to extract key keywords, and generates advice using expert knowledge. It also recognizes the user's emotional state, adjusts the advice, and recommends childcare products and services related to the advice. It also has a function for linking with local communities.

[1200] Hardware and Software Configuration

[1201] 1. User Device

[1202] The user device is a smartphone or tablet, and a dedicated childcare application is installed on it. The user uses this device to input and submit questions.

[1203] Example: Smartphone (Android, iOS)

[1204] 2. Server

[1205] The server performs multiple functions, including receiving questions, parsing, generating advice, recognizing emotional states, searching community groups, and recommending childcare products. The following software is mainly used:

[1206] Question analysis: Text analysis engines (e.g. NLTK, SpaCy)

[1207] Emotion Recognition: Emotion engine (e.g. Google Cloud Natural Language API)

[1208] Advice generation: Generative AI models (e.g., GPT-3)

[1209] Community Collaboration: Regional Information Database

[1210] Baby Product Recommendation: Recommendation Systems (e.g., Collaborative Filtering)

[1211] Data processing and calculation explanation

[1212] The server receives question data sent from the user's device and extracts key keywords using a text analysis engine. Based on the extracted keywords and emotion recognition results, it sends a request for advice generation to the generative AI model. The generative AI model references expert knowledge bases and past data to generate optimal advice. The content of the advice is adjusted according to the recognized emotional state, and is finally sent to the user's device. Related childcare products and services are also recommended. By linking with local communities, appropriate community groups are searched for and users are added.

[1213] Specific examples

[1214] The user enters a question: "What should I do if my 6-month-old baby cries at night?" This question is sent to the server via an HTTP request. The server receives the question data and analyzes it using a text analysis engine. The main keywords "6 months old" and "crying at night" are extracted, and the emotion engine recognizes the emotion "anxiety." A generative AI model (e.g., GPT-3) then generates emotion-sensitive advice such as "There are various causes of night crying, but it is important to create a good environment," along with "It is important for the mother to spend time relaxing together." This advice is then sent to the user's device along with recommendations for related childcare products and services.

[1215] Prompt Sentence Examples

[1216] A user has asked the question, "What should I do about my 6-month-old baby crying at night?" The user is worried. Please provide appropriate advice and suggest baby products related to night crying.

[1217] In this way, the system can provide appropriate advice based on the user's individual emotional state and recommendations for childcare products and services, improving convenience and quality of support.

[1218] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1219] Step 1:

[1220] The user enters a question about childcare through a dedicated application and presses the send button. The question is specific, such as, "What should I do if my 6-month-old baby cries at night?" The user's device sends this question data to the server as an HTTP request.

[1221] Input: The question text entered by the user

[1222] Output: The question data in the form of an HTTP request sent to the server

[1223] Step 2:

[1224] The server analyzes the question data received from the user using a text analysis engine (e.g., NLTK, SpaCy). Here, key keywords such as "6 months old" and "night crying" are extracted from the question.

[1225] Input: Question data in HTTP request format

[1226] Output: Extracted keywords (e.g., "6 months old", "night crying")

[1227] Step 3:

[1228] The server uses an emotion recognition engine (e.g., Google Cloud Natural Language API) to analyze the emotional state of the user's question, in this case identifying whether the user is feeling emotions such as "anxiety" or "stress."

[1229] Input: Question data in HTTP request format

[1230] Output: Perceived emotional state (e.g., "anxiety")

[1231] Step 4:

[1232] The server sends a request for advice generation to a generative AI model (e.g., GPT-3) based on the extracted keywords and the recognized emotional state. The generative AI model then refers to an expert knowledge base and past data to generate appropriate advice.

[1233] Input: extracted keywords and recognized emotional states

[1234] Output: Generated advice text (e.g., "There are various causes of nighttime crying, but it is important to create a good environment. It is also important for the mother to spend time relaxing together.")

[1235] Step 5:

[1236] Based on the generated advice, the server uses a recommendation system (e.g., Collaborative Filtering) to recommend relevant childcare products and services, taking into account the user's past history and general data in the process.

[1237] Input: Generated advice text

[1238] Output: A list of recommended childcare products and services (e.g., specific toys or relaxation items)

[1239] Step 6:

[1240] The server sends the generated advice and a list of recommended childcare products and services to the user's device, which receives this information and displays it in a dedicated application.

[1241] Input: Generated advice text, recommended childcare products and services list

[1242] Output: Advice and product / service information displayed on the user's device

[1243] Step 7:

[1244] If the user selects the local community participation option, the server will search for an appropriate community group based on the user's local information and add the user to it. After that, the user can obtain further information and support through support and interaction with the community group.

[1245] Input: Request to join local community, user's local information

[1246] Output: Community group information to which the user was added

[1247] 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.

[1248] 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.

[1249] 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.

[1250] [Fourth embodiment]

[1251] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1252] 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.

[1253] 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).

[1254] 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.

[1255] 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.

[1256] 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).

[1257] 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.

[1258] 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.

[1259] 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.

[1260] 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.

[1261] 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.

[1262] 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.

[1263] 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."

[1264] The present invention is a system that allows users to input questions about child-rearing, receive advice from experts in real time, and even receive child-rearing support in collaboration with local communities.

[1265] System Overview

[1266] This system includes a device used by the user, a server that analyzes questions about childcare and generates advice, and expert knowledge and information provided based on that advice. Furthermore, it will build a support network among users through collaboration with the local community.

[1267] Program processing

[1268] User inputs and submits questions

[1269] A user inputs a question about childcare through a mobile or web app and presses the send button. For example, the user inputs a question such as, "What should I do if my 6-month-old baby cries at night?" This question is sent from the device to the server.

[1270] Question Analysis

[1271] The server receives the question sent by the user. The question data is sent to the multimodal AI, which analyzes the question. For example, it extracts key keywords such as "6 months old" and "night crying."

[1272] Generating Advice

[1273] Based on the analysis results, the server uses the extracted keywords to send a request for advice to the AGI model. The AGI model then references a knowledge base of experts and past data to generate optimal advice. For example, it might generate advice such as, "There are many causes of nighttime crying, but it's important to create a good bedtime and environment for your baby. For example, it would be a good idea to set a consistent bedtime and let your baby sleep in a quiet environment."

[1274] Sending Advice

[1275] The server sends the generated advice to the user's terminal, which receives the advice and displays it on the screen.

[1276] Collaboration with local communities

[1277] When a user selects the local community participation option, a request is sent from the device to the server. The server searches for an appropriate community group based on the user's local information and past participation history, and adds the user. The user can then obtain more information and support through support and interaction from the community group.

[1278] Specific examples and applications

[1279] For example, the following is a specific example of a user asking about their 6-month-old baby crying at night.

[1280] 1. User inputs and submits question

[1281] The user enters a question into the app: "What should I do if my 6-month-old baby cries at night?" and submits it.

[1282] The device sends the question data to the server as an HTTP request.

[1283] 2. Question Analysis

[1284] The server receives the question data and performs text analysis.

[1285] Multimodal AI analyzes the question and extracts the keywords "6 months old" and "night crying."

[1286] 3. Generating Advice

[1287] The server sends a request to the AGI model using the extracted keywords.

[1288] The AGI model generates advice such as, "There are many causes of nighttime crying, but it is important to create a good sleeping environment for your baby."

[1289] 4. Submitting Advice

[1290] The server transmits the generated advice to the user's terminal.

[1291] The terminal receives the advice and displays it on the user screen.

[1292] 5. Collaboration with local communities

[1293] The user selects the local community participation option.

[1294] The server searches for an appropriate community group based on the user's area information and adds the user to it.

[1295] Users can get further support through participation in community groups.

[1296] The system allows users to receive reliable childcare information and expert advice in real time, and also strengthens connections with the local community, providing comprehensive support to reduce stress and anxiety related to childcare.

[1297] The processing flow will be explained below.

[1298] Step 1:

[1299] A user opens a mobile or web app, types a parenting question, and hits submit. For example, a user types a question like, "What should I do about my 6-month-old baby crying at night?"

[1300] Step 2:

[1301] The device creates an HTTP request with the entered question data and sends it to the server. The device then packages the data in the required format and initiates communication with the server.

[1302] Step 3:

[1303] The server receives the HTTP request and converts the question data into a format suitable for analysis. The server temporarily stores the received data and prepares it in a format suitable for analysis.

[1304] Step 4:

[1305] The server sends the question data to a multimodal AI model, which analyzes the question content. The AI ​​model then performs text analysis to extract key keywords such as "6 months old" and "night crying."

[1306] Step 5:

[1307] The server sends a request to the AGI model to generate advice based on the extracted keywords, and the server makes the appropriate API calls to establish communication with the AGI model.

[1308] Step 6:

[1309] The AGI model will refer to a knowledge base of experts and past data to generate optimal advice. For example, it might say, "There are many causes of nighttime crying, but it's important to create a good bedtime and environment for your baby. For example, it would be a good idea to set a consistent bedtime and let your baby sleep in a quiet environment."

[1310] Step 7:

[1311] The server receives the advice generated by the AGI model, converts it into a format suitable for the user, temporarily stores the advice, and prepares a response for the user device.

[1312] Step 8:

[1313] The server sends an HTTP response containing the advice to the user's device, which then encodes the response in the appropriate protocol and communicates.

[1314] Step 9:

[1315] The device receives the HTTP response and displays the advice on the user's screen. The device analyzes the received data and displays it in a format that is easy for the user to understand.

[1316] Step 10:

[1317] The user selects a local community participation option and sends a request from the terminal to the server. For example, the user selects an option saying "I want to join a local childcare support group."

[1318] Step 11:

[1319] The server checks the user's location and past participation history to search for appropriate community groups. The server then checks the database to identify the most suitable group for the user.

[1320] Step 12:

[1321] The server adds the user to the community group it finds and sends an HTTP response to the terminal indicating that the user has joined. The server then updates the database as needed and notifies the user of the results.

[1322] Step 13:

[1323] The device receives the HTTP response and displays a message indicating participation on the user's screen. The device also provides an access link to the community group, allowing users to easily join.

[1324] Example 1

[1325] 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."

[1326] Questions and consultations about childcare are diverse, making it difficult to provide appropriate advice quickly. Furthermore, there is a lack of collaboration and information sharing with local communities, making it difficult to build a support network among users. The present invention aims to solve these problems, enabling users to receive reliable advice quickly and strengthening collaboration with local communities.

[1327] 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.

[1328] In this invention, the server includes means for receiving questions about child-rearing input by a user, means for analyzing the questions and extracting key keywords, means for generating advice using an advanced knowledge base based on the extracted keywords, means for sending the generated advice to a corresponding user, means for adding the user to an appropriate community group by linking with a local community, means for receiving questions from the user through a dedicated application, and means for analyzing the user's questions using multimodal artificial intelligence. This allows the user to receive reliable advice quickly and makes it easier to receive support through linkage with the local community.

[1329] "User" refers to a person who uses the system by inputting questions about childcare.

[1330] A "question" refers to text data that a user enters to obtain information or advice about childcare.

[1331] "Server" refers to a computer system that receives questions from users and performs analysis and advice generation.

[1332] "Multimodal artificial intelligence" refers to algorithms that analyze multiple data formats to extract key keywords.

[1333] "Expert knowledge base" refers to a database containing expert knowledge and historical data on childcare.

[1334] "Advice" refers to answers or suggestions generated based on a user's question.

[1335] "Local community" refers to a support network built for each area where a user lives.

[1336] "Specialized application" refers to software that allows a user to enter questions and receive answers.

[1337] An "advanced knowledge base" refers to a database that contains more comprehensive and detailed information than an expert knowledge base.

[1338] A "generative artificial intelligence model" refers to an algorithm that uses expert knowledge bases and past data to generate optimal advice.

[1339] "Key keywords" refer to words and phrases extracted from a user's question that are important for generating advice.

[1340] "Community groups" refer to small groups within a local community that support each other.

[1341] The present invention is a system that allows users to input questions about childcare and receive necessary advice in real time. This system is composed of a user terminal, a server, an advanced knowledge base, and links with local communities.

[1342] Overall system configuration

[1343] User terminal

[1344] Users use a device such as a smartphone or PC to input questions about childcare through a dedicated application. This device includes a question input form, a submit button, and an interface for displaying advice.

[1345] server

[1346] The server receives questions sent by users, analyzes the questions, generates advice, and finally sends the advice to the corresponding users. The server implements a multimodal AI model and a generative AI model.

[1347] Data processing and calculation

[1348] Receiving and parsing questions

[1349] The server receives questions sent from user devices. For example, if a user sends a question such as, "What should I do if my 6-month-old baby cries at night?", the server analyzes the question using multimodal artificial intelligence. Through the analysis, key keywords such as "6-month-old" and "crying at night" are extracted.

[1350] Generating Advice

[1351] Based on the analysis results, the server inputs the extracted keywords into the generative AI model as a prompt sentence. The following is an example of such a prompt sentence:

[1352] TXT

[1353] "What causes a 6-month-old baby to cry at night and what can I do about it?"

[1354] Based on this prompt, the generative AI model will refer to a knowledge base of childcare experts and past data to generate optimal advice. For example, it might generate advice such as, "There are many causes of nighttime crying, but it's important to create a good bedtime and environment for your baby. For example, it's a good idea to set a consistent bedtime and let your baby sleep in a quiet environment."

[1355] Sending Advice

[1356] The generated advice is transmitted from the server to the user terminal, and the transmitted advice is displayed on the user terminal so that the user can confirm it.

[1357] Collaboration with local communities

[1358] If the user selects the local community participation option, a request is sent from the user's terminal to the server. The server searches for an appropriate community group based on the user's local information and past participation history, and adds the user to the appropriate community group. The user can obtain further support and information through the community group.

[1359] Specific hardware and software

[1360] The specific hardware used in this system includes a smartphone, a PC, and a server, while the software and algorithms used include a dedicated application, the HTTP protocol, the JSON format, multimodal artificial intelligence, and a generative artificial intelligence model.

[1361] This system will enable users to receive quick and reliable childcare advice, and will also enable them to receive multifaceted support through collaboration with the local community.

[1362] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1363] Step 1: User enters question

[1364] The user opens a dedicated application on a smartphone or PC.

[1365] The user enters questions about childcare into the application's input form.

[1366] Example input: "What can I do about my 6-month-old baby crying at night?"

[1367] Input: Text data related to childcare.

[1368] Output: Question data ready to be sent.

[1369] Step 2: Submit your question

[1370] The user confirms the entered question by pressing the send button.

[1371] The terminal sends the question data to the server as an HTTP request.

[1372] What happens: The device packages the data into JSON format and establishes an internet connection to send it to the server.

[1373] Input: The question data that the user entered and pressed submit.

[1374] Output: The query data sent to the server.

[1375] Step 3: Receiving and parsing the question

[1376] The server receives a question sent by a user.

[1377] The server analyzes the received question data using multimodal artificial intelligence.

[1378] How it works: The text analysis engine breaks down the question and extracts key keywords such as "6 months old" and "night crying."

[1379] Input: Question data submitted by the user.

[1380] Output: Extracted main keywords.

[1381] Step 4: Generating Advice

[1382] The server inputs the extracted keywords as prompt sentences into the generative artificial intelligence model.

[1383] The generative artificial intelligence model generates advice based on the prompt sentence.

[1384] Example prompt: "What causes my 6-month-old baby to cry at night and what can I do about it?"

[1385] How it works: The generative artificial intelligence model references expert knowledge bases and past data to generate appropriate advice.

[1386] Input: A prompt sentence based on the extracted main keywords.

[1387] Output: The generated advice.

[1388] Step 5: Submitting Advice

[1389] The server transmits the generated advice to the user's terminal.

[1390] Specific operation: Advice data is packaged in JSON format as an HTTP response and sent to the user's device.

[1391] Input: The generated advice.

[1392] Output: Advice data sent to the user's device.

[1393] Step 6: Receive and view advice

[1394] The terminal receives the advice sent from the server.

[1395] The terminal displays the received advice on the screen.

[1396] What it does: The application parses the advice data, formats it in a user-friendly format, and displays it.

[1397] Input: Advice data sent by the server.

[1398] Output: Advice displayed on the user's terminal.

[1399] Step 7: Engage with local communities

[1400] The user selects the local community participation option within the application.

[1401] The terminal sends the request to the server.

[1402] The server searches for an appropriate community group based on the user's area information and past participation history, and adds the user to that group.

[1403] What it does: Analyzes the user's location, identifies the most suitable community group, and adds the user.

[1404] Input: A request to join a local community and the user's local information.

[1405] Output: Notification that the user has been added to the appropriate community group.

[1406] (Application example 1)

[1407] 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."

[1408] Obtaining appropriate and prompt advice on child-rearing-related questions is a major challenge for parents. Obtaining expert advice is often time-consuming and costly, making it difficult to respond in real time. Furthermore, a lack of collaboration with local communities means that parents are unable to share information or provide support to each other. This leads to increased anxiety and stress about child-rearing.

[1409] 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.

[1410] In this invention, the server includes means for receiving questions about child-rearing input by users, means for analyzing the questions and extracting key keywords, means for generating advice using an artificial intelligence model based on the extracted keywords, means for sending the generated advice to corresponding users, means for adding users to appropriate community groups through collaboration with local communities, means for users to input and send questions through a dedicated application, and means for enhancing the advice content by referring to a knowledge base of experts. This allows users to obtain expert advice in real time and further enables them to receive mutual support through collaboration with the local community.

[1411] The "means for receiving questions about child-rearing entered by the user" is a function that allows the user to enter questions or problems about child-rearing via a terminal such as a smartphone or computer and send them to the server.

[1412] The "means for analyzing the question and extracting key keywords" is a software function for analyzing the content of the question and identifying and extracting important keywords.

[1413] The "means for generating advice using an artificial intelligence model based on extracted keywords" is a system for generating optimal advice using artificial intelligence, using extracted keywords as input.

[1414] The "means for transmitting the generated advice to the corresponding user" is a communication function for transmitting the generated advice to the user's terminal and displaying it.

[1415] The "means for adding a user to an appropriate community group through collaboration with local communities" is a system for searching for the most suitable community group based on the user's local information and adding the user to that group.

[1416] "Means for users to input and send questions via a dedicated application" refers to a function that allows users to input questions via a dedicated application and send them to the server.

[1417] "Means for enhancing advice content by referencing an expert knowledge base" refers to a system that uses expert knowledge and past data to improve the accuracy and usefulness of the advice generated.

[1418] This invention is a system that analyzes user questions related to childcare and provides expert advice in real time. Furthermore, it enables mutual support through collaboration with local communities. Specific embodiments are described below.

[1419] Hardware and software used

[1420] Hardware: Smartphone (user device), computer (server)

[1421] Software: Dedicated application (user side), Django (server side), OpenAI GPT-3 (artificial intelligence model)

[1422] Processing flow and data processing

[1423] 1. User question input: A user uses a dedicated application installed on a smartphone to input a question about childcare. For example, they input a question such as, "What should I do if my 6-month-old baby cries at night?"

[1424] 2. Submit Question: When the user presses the submit question button, the question data is sent from the application to the server as an HTTP POST request.

[1425] 3. Question analysis: The server analyzes the received question data. Specifically, it uses an artificial intelligence model based on OpenAI GPT-3 to analyze the text of the question and extract key keywords. For example, keywords such as "6 months old" and "night crying" are extracted.

[1426] 4. Advice generation: Based on the extracted keywords, a request is sent again to OpenAI GPT-3 to generate appropriate advice. An example of generated advice might be, "There are various causes of nighttime crying, but it is important to create a good bedtime and environment for your baby. For example, it would be a good idea to set a consistent bedtime and let your baby sleep in a quiet environment."

[1427] Example prompt sentence:

[1428] Extract key parenting keywords from the following questions:

[1429] Question: 'What can I do about my 6-month-old baby crying at night?'

[1430] keyword:

[1431] Example prompt sentence:

[1432] Offer parenting advice based on the following keywords:

[1433] Keywords: '6 months old, night crying'

[1434] advice:

[1435] 5. Sending advice: The generated advice is sent from the server to the user's smartphone and displayed on the application.

[1436] 6. Collaboration with local communities: If a user selects the local community participation option, the server will search for and add the user to appropriate community groups based on the user's area of ​​residence, allowing the user to share information and receive support from other parents in the same area.

[1437] This allows users to receive reliable advice in real time, and also enables them to receive mutual support through collaboration with local communities.

[1438] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1439] Step 1:

[1440] The user uses a dedicated application to input questions about childcare, such as, "What should I do if my 6-month-old baby cries at night?" The input data is saved in text format.

[1441] Step 2:

[1442] When the user presses the "Send" button, a dedicated application on the device sends the question entered by the user to the server as an HTTP POST request. The input data is sent to the server as text data.

[1443] Step 3:

[1444] The server analyzes the received HTTP POST request, extracts the question text, and starts the analysis process based on the received text data. Specifically, it generates an API request to perform text analysis.

[1445] Step 4:

[1446] The server calls the OpenAI GPT-3 API and sends the question text as a prompt. This prompt includes instructions for extracting key keywords. For example, it could be in the format "Please extract key parenting keywords from the following question: Question: 'What should I do if my 6-month-old baby cries at night?' Keywords: "

[1447] Step 5:

[1448] The GPT-3 model analyzes the input prompt and extracts key keywords, such as "6 months old" and "night crying." The server receives the extracted results and stores them as data.

[1449] Step 6:

[1450] The server then calls the GPT-3 API again and sends a prompt to generate advice based on the extracted keywords. The prompt contains instructions for generating advice content. For example, it could be in the format "Please provide parenting advice based on the following keywords: Keywords: '6 months old, night crying' Advice: "

[1451] Step 7:

[1452] The GPT-3 model generates appropriate advice based on the prompt and returns it to the server. This output includes specific advice such as, "There are various causes of nighttime crying, but it is important to create a good bedtime and environment for your baby. For example, it would be a good idea to set a consistent bedtime and let your baby sleep in a quiet environment."

[1453] Step 8:

[1454] The server receives the generated advice and sends it to the user's device. The advice is returned as an HTTP response and displayed on the screen by a dedicated application.

[1455] Step 9:

[1456] When the user selects the local community participation option, a request is sent from the terminal to the server, and the request includes information about the user's local area.

[1457] Step 10:

[1458] The server searches for appropriate community groups based on the user's location information and adds the user to them, allowing them to share information and receive support from other parents in their area.

[1459] 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.

[1460] The present invention is a system that provides accurate advice in real time in response to questions about child rearing, and further adjusts the content of the advice by recognizing the emotional state of the user. Details of this system will be described below.

[1461] System Overview

[1462] This system includes a device used by the user, a server that analyzes questions about childcare and generates advice, an emotion engine that recognizes the user's emotions, and a function for linking with local communities. Specifically, it has the following functions:

[1463] 1. User inputs and submits question

[1464] The user enters a question about childcare into the device and presses the send button. For example, the user enters a question such as, "What should I do if my 6-month-old baby cries at night?" This question is sent from the device to the server.

[1465] 2. Question Analysis and Emotion Recognition

[1466] The server receives the question sent by the user. The question data is sent to the multimodal AI, which analyzes the question. At the same time, the emotion engine recognizes the user's emotions from the question. For example, emotions such as "anxiety" or "stress" are identified.

[1467] 3. Advice Generation and Adjustment

[1468] Based on the analysis results and the emotion engine results, the server sends a request to the AGI model to generate advice. The AGI model then references a knowledge base of experts and past data to generate optimal advice. The generated advice is adjusted according to the user's emotions. For example, in addition to basic advice such as "There are various causes of nighttime crying, but it is important to organize the baby's bedtime and environment," emotional advice such as "It is important for the mother to take time to relax together" is also added.

[1469] 4. Submitting Advice

[1470] The server sends the generated advice to the user's terminal, which receives the advice and displays it on the screen.

[1471] 5. Collaboration with local communities

[1472] When a user selects the local community participation option, a request is sent from the device to the server. The server searches for an appropriate community group based on the user's local information and past participation history, and adds the user. The user can then obtain more information and support through support and interaction from the community group.

[1473] Specific examples and applications

[1474] For example, the following is a specific example of a case where a user asks a question about their 6-month-old baby's crying at night, and the emotion engine recognizes the user's "anxiety."

[1475] 1. User inputs and submits question

[1476] The user enters a question into the app: "What should I do if my 6-month-old baby cries at night?" and submits it.

[1477] The device sends the question data to the server as an HTTP request.

[1478] 2. Question Analysis and Emotion Recognition

[1479] The server receives the question data and performs text analysis.

[1480] Multimodal AI analyzes the question and extracts the keywords "6 months old" and "night crying."

[1481] The emotion engine recognizes the user's "anxiety" from the content of the question.

[1482] 3. Advice Generation and Adjustment

[1483] The server sends a request to the AGI model using the extracted keywords and emotion recognition results.

[1484] The AGI model generates advice such as, "There are various causes of nighttime crying, but it is important to create a good sleeping environment and time for the baby to sleep," along with emotionally sensitive advice such as, "It is important to create time for the mother to relax together."

[1485] 4. Submitting Advice

[1486] The server transmits the generated advice to the user's terminal.

[1487] The terminal receives the advice and displays it on the user screen.

[1488] 5. Collaboration with local communities

[1489] The user selects the local community participation option.

[1490] The server searches for an appropriate community group based on the user's area information and adds the user to it.

[1491] Users can get further support through participation in community groups.

[1492] The system allows users to receive reliable childcare information and expert advice in real time, as well as customized support tailored to their emotional state. By strengthening connections with the local community, the system can reduce anxiety and stress related to childcare and improve the quality of childcare.

[1493] The processing flow will be explained below.

[1494] Step 1:

[1495] A user opens a mobile or web app, types a parenting question, and hits submit. For example, a user types a question like, "What should I do about my 6-month-old baby crying at night?"

[1496] Step 2:

[1497] The device creates an HTTP request with the entered question data and sends it to the server. The device then packages the data in the required format and initiates communication with the server.

[1498] Step 3:

[1499] The server receives the HTTP request and retrieves the query data. The server temporarily stores the received data and converts it into a format suitable for analysis.

[1500] Step 4:

[1501] The server sends the question data to the multimodal AI model, which analyzes the question content. At the same time, the emotion engine recognizes the user's emotions from the question data.

[1502] Step 5:

[1503] The emotion engine analyzes the question data and identifies the user's emotions, such as "anxiety" or "stress." The emotion recognition results are returned to the server.

[1504] Step 6:

[1505] The server sends a request to the AGI model to generate advice based on the analysis results (major keywords) and the emotion engine results (user emotions). The server makes the appropriate API calls to establish communication with the AGI model.

[1506] Step 7:

[1507] The AGI model references expert knowledge bases and past data to generate optimal advice. For example, it generates main advice such as, "There are various causes of nighttime crying, but it is important to create a good bedtime and environment for your baby. For example, it is a good idea to set a consistent bedtime and let your baby sleep in a quiet environment." It also generates emotional advice, taking into account emotion recognition results, such as, "It is important to create time for the mother to relax together."

[1508] Step 8:

[1509] The server receives the advice generated by the AGI model, converts it into a format suitable for the user, temporarily stores the advice, and prepares a response for the user device.

[1510] Step 9:

[1511] The server sends an HTTP response containing the advice to the user's device, which then encodes the response in the appropriate protocol and communicates.

[1512] Step 10:

[1513] The device receives the HTTP response and displays the advice on the user's screen. The device analyzes the received data and displays it in a format that is easy for the user to understand.

[1514] Step 11:

[1515] When the user selects a local community participation option, the terminal sends a request to the server. For example, the user selects an option saying "I want to join a local childcare support group."

[1516] Step 12:

[1517] The server checks the user's location and past participation history to search for appropriate community groups. The server then checks the database to identify the most suitable group for the user.

[1518] Step 13:

[1519] The server adds the user to the community group it finds and sends an HTTP response to the terminal indicating that the user has joined. The server then updates the database as needed and notifies the user of the results.

[1520] Step 14:

[1521] The device receives the HTTP response and displays a message indicating participation on the user's screen. The device also provides an access link to the community group, allowing users to easily join.

[1522] Example 2

[1523] 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."

[1524] In addition to providing appropriate childcare advice in real time, there is a need to build a support system that reduces the emotional anxiety and stress experienced by users while raising children and improves the quality of childcare. However, existing systems have issues in that they do not provide advice that takes into account the user's emotional state or sufficiently collaborate with effective local communities.

[1525] 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.

[1526] In this invention, the server includes means for receiving questions about child-rearing entered by users, means for analyzing the questions and extracting key keywords, means for generating advice based on the extracted keywords using expert knowledge, means for recognizing the user's emotional state and adjusting the advice content, means for sending the generated advice to the corresponding user, and means for adding the user to an appropriate community group through collaboration with a local community. This allows users to receive professional and reliable child-rearing advice in real time and also to receive customized support tailored to their own emotional state. In addition, collaboration with the local community allows users to obtain further information and support related to child-rearing, improving the quality of child-rearing and reducing users' anxiety and stress.

[1527] 1. "User" refers to a person who inputs a parenting question.

[1528] 2. "Questions about childcare" refers to problems or inquiries related to childcare that users enter into the system.

[1529] 3. "Means for receiving" refers to a component that has the function of receiving question data sent from a user via a network.

[1530] 4. "Means of analyzing and extracting key keywords" refers to the process of analyzing the content of the question using natural language processing technology, etc., to find important information and keywords.

[1531] 5. "Means for generating advice using expert knowledge" refers to a function for creating specific advice in response to a user's question by referring to an expert's knowledge base or past data.

[1532] 6. "Means for recognizing the user's emotional state and tailoring advice content" refers to the process of analyzing the user's emotions from the content of the question and customizing advice based on the recognized emotions.

[1533] 7. "Means for sending the generated advice to the corresponding user" refers to the function for sending the created advice to the user's terminal via the Internet.

[1534] 8. "Means for adding users to appropriate community groups through collaboration with local communities" refers to a system function that uses the user's local information to appropriately collaborate with the local community in which the user wishes to join.

[1535] 9. "System" refers to the entire information processing device including the above means.

[1536] The present invention is a system that provides accurate advice in real time in response to questions about child rearing and further adjusts the content of the advice by recognizing the emotional state of the user, and is implemented as follows.

[1537] This system includes a device used by the user, a server that analyzes questions about childcare and generates advice, an emotion engine that recognizes the user's emotions, and a function for linking with local communities. Specifically, the system uses the following hardware and software:

[1538] Hardware and software used

[1539] Device: A device through which a user inputs questions about childcare, including smartphones, tablets, and personal computers.

[1540] Server: Analyzes questions, generates advice, recognizes emotions, sends advice, and collaborates with the local community. Specifically, a cloud server equipped with a high-performance processor and large memory capacity is used.

[1541] Multimodal AI: An AI engine used to analyze question content and extract key keywords. It uses natural language processing technology and a BERT-based model.

[1542] Emotion engine: Software that recognizes the user's emotions from the content of the question. Emotion analysis algorithms identify emotions such as "anxiety" and "stress."

[1543] Generative AI model: Uses AGI (artificial general intelligence) to generate advice based on the question, referencing expert knowledge bases and past data to provide optimal advice.

[1544] Specific examples

[1545] For example, consider a case where a user wants to ask a question about their 6-month-old baby crying at night. The user opens a device app, enters "What can I do about my 6-month-old baby crying at night?" into the input field, and presses the send button. This question is sent as an HTTP request to the server, and the server receives the request.

[1546] The server passes the question data to the multimodal AI, which analyzes the question and extracts keywords such as "6 months old" and "night crying." At the same time, the emotion engine identifies the emotion "anxiety" from the question. Based on these analysis results and emotion recognition results, the server sends a request to the AGI model.

[1547] Based on the questions, the AGI model generates specific advice about the causes of nighttime crying and countermeasures. For example, the model might generate advice such as, "There are various causes of nighttime crying, but it is important to create a good sleeping environment for your baby." Taking the user's emotions into consideration, the model also provides additional advice such as, "It is important to create time for the mother to relax together."

[1548] Finally, the generated advice is sent from the server to the user's device, and the user receives the advice through the app. If the user wishes, they can also be added to an appropriate community group via a local community linkage function, allowing them to receive support from local support groups.

[1549] As described above, this system allows users to receive professional and reliable child-rearing advice in real time, and also allows them to receive support tailored to their own emotional state. Furthermore, by connecting with the local community, users can obtain further information and support related to child-rearing, improving the quality of child-rearing and reducing users' anxiety and stress.

[1550] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1551] System program processing flow

[1552] Step 1: User enters question and submits

[1553] Specific behavior:

[1554] A user opens a device app, types a question such as "What should I do about my 6-month-old baby crying at night?", and presses the send button.

[1555] Input: Parenting questions entered by the user.

[1556] Data processing / data calculation:

[1557] The device application receives the user's question as text data.

[1558] The system converts the question into an HTTP request format and adds metadata (e.g., user ID, timestamp).

[1559] Output: The generated HTTP request is sent to the server.

[1560] Step 2: Question analysis and emotion recognition

[1561] Specific behavior:

[1562] The server receives the HTTP request and extracts the question data from the request body.

[1563] Input: HTTP request (question data) sent from the terminal.

[1564] Data processing / data calculation:

[1565] The server sends the question data to the multimodal AI, which uses natural language processing technology to analyze the question text and extract key keywords (e.g., "6 months old" or "night crying"). At the same time, the emotion engine recognizes the user's emotion (e.g., "anxiety") from the question content.

[1566] Output: Analyzed keyword data and emotion recognition results (emotion data).

[1567] Step 3: Generate and refine advice

[1568] Specific behavior:

[1569] The server sends the analysis results (keyword data and emotion data) to the AGI model as a request.

[1570] The AGI model references expert knowledge bases and past data to generate appropriate advice.

[1571] Input: Parsed keyword data and sentiment data.

[1572] Data processing / data calculation:

[1573] Using keywords such as "6 months old" and "night crying," the AGI model generates basic advice such as, "There are various causes of night crying, but it is important to create a good sleeping environment for your baby." At the same time, it also generates additional advice that takes into consideration emotions, such as, "It is important to create time for the mother to relax together," based on emotional data.

[1574] Output: Optimized advice data.

[1575] Step 4: Submitting Advice

[1576] Specific behavior:

[1577] The server transmits the generated advice to the user's terminal.

[1578] The device receives the advice and displays it on the app's user interface.

[1579] Input: Optimized advice data.

[1580] Data processing / data calculation:

[1581] Advice data is encrypted and sent over a secure channel (SSL / TLS). The device decrypts the data and converts it into a format for display in the user interface.

[1582] Output: The advice displayed to the user.

[1583] Step 5: Engage with local communities

[1584] Specific behavior:

[1585] The user selects the local community participation option on the device settings screen.

[1586] Optional data is sent from the terminal to the server.

[1587] The server searches for an appropriate community group based on the user's local area information and adds the user to it.

[1588] Input: Community participation options data, local information.

[1589] Data processing / data calculation:

[1590] The server retrieves the user's location information from the database, searches for matching community groups, and adds the user to the appropriate group based on the search results.

[1591] Output: Details of the community groups the user has joined.

[1592] This easy-to-follow process allows users to receive real-time parenting advice and customized support based on their emotional state, while also enabling them to access further parenting information and support from their local community.

[1593] (Application example 2)

[1594] 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."

[1595] Conventional childcare support systems can only provide uniform advice to users' questions, making it difficult to provide personalized support that takes into account specific emotional states. Furthermore, they lack connections with local communities, limiting the means by which users can receive personalized support. Furthermore, they lack a function to recommend childcare products and services, making it difficult for users to obtain the information they need in a centralized location.

[1596] 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.

[1597] In this invention, the server includes means for receiving questions about childcare input by a user, means for analyzing the questions and extracting key keywords, means for generating advice based on the extracted keywords and using expert knowledge, means for sending the generated advice to the corresponding user, means for recognizing the user's emotional state, means for adjusting the content of the advice based on the recognized emotional state, means for adding the user to an appropriate community group through collaboration with a local community, and means for recommending related childcare products and services. This makes it possible to provide appropriate advice according to the user's individual emotional state, strengthen collaboration with the local community, and improve user convenience through the recommendation of childcare products and services.

[1598] "User" refers to an individual or organization who uses this system to input questions about childcare and receive advice.

[1599] "Question" refers to a specific question or issue regarding childcare, and is information that is entered into the system and transmitted to the server.

[1600] "Keywords" are important words and phrases extracted during the question analysis process, and refer to the information that forms the basis for generating advice.

[1601] "Expert knowledge" refers to information based on specialized understanding and experience in child-rearing, a database required for the system to generate optimal advice.

[1602] "Advice" refers to parenting recommendations and solutions generated by the system and provided to the user.

[1603] "Emotional state" refers to the psychological or emotional state the user is in when asking a question, and includes specific emotions such as anxiety or stress.

[1604] A "local community" refers to a group that is part of the local community to which the user belongs and that exchanges information and provides support regarding childcare.

[1605] A "community group" is a group of users who share common interests or goals, and is formed to provide support, particularly regarding childcare.

[1606] "Related childcare products and services" refers to childcare-related products and services that the system recommends based on the content of the question and the user's emotional state.

[1607] The following describes an embodiment of the present invention.

[1608] System Overview

[1609] The system receives questions about childcare input from users, analyzes the questions to extract key keywords, and generates advice using expert knowledge. It also recognizes the user's emotional state, adjusts the advice, and recommends childcare products and services related to the advice. It also has a function for linking with local communities.

[1610] Hardware and Software Configuration

[1611] 1. User Device

[1612] The user device is a smartphone or tablet, and a dedicated childcare application is installed on it. The user uses this device to input and submit questions.

[1613] Example: Smartphone (Android, iOS)

[1614] 2. Server

[1615] The server performs multiple functions, including receiving questions, parsing, generating advice, recognizing emotional states, searching community groups, and recommending childcare products. The following software is mainly used:

[1616] Question analysis: Text analysis engines (e.g. NLTK, SpaCy)

[1617] Emotion Recognition: Emotion engine (e.g. Google Cloud Natural Language API)

[1618] Advice generation: Generative AI models (e.g., GPT-3)

[1619] Community Collaboration: Regional Information Database

[1620] Baby Product Recommendation: Recommendation Systems (e.g., Collaborative Filtering)

[1621] Data processing and calculation explanation

[1622] The server receives question data sent from the user's device and extracts key keywords using a text analysis engine. Based on the extracted keywords and emotion recognition results, it sends a request for advice generation to the generative AI model. The generative AI model references expert knowledge bases and past data to generate optimal advice. The content of the advice is adjusted according to the recognized emotional state, and is finally sent to the user's device. Related childcare products and services are also recommended. By linking with local communities, appropriate community groups are searched for and users are added.

[1623] Specific examples

[1624] The user enters a question: "What should I do if my 6-month-old baby cries at night?" This question is sent to the server via an HTTP request. The server receives the question data and analyzes it using a text analysis engine. The main keywords "6 months old" and "crying at night" are extracted, and the emotion engine recognizes the emotion "anxiety." A generative AI model (e.g., GPT-3) then generates emotion-sensitive advice such as "There are various causes of night crying, but it is important to create a good environment," along with "It is important for the mother to spend time relaxing together." This advice is then sent to the user's device along with recommendations for related childcare products and services.

[1625] Prompt Sentence Examples

[1626] A user has asked the question, "What should I do about my 6-month-old baby crying at night?" The user is worried. Please provide appropriate advice and suggest baby products related to night crying.

[1627] In this way, the system can provide appropriate advice based on the user's individual emotional state and recommendations for childcare products and services, improving convenience and quality of support.

[1628] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1629] Step 1:

[1630] The user enters a question about childcare through a dedicated application and presses the send button. The question is specific, such as, "What should I do if my 6-month-old baby cries at night?" The user's device sends this question data to the server as an HTTP request.

[1631] Input: The question text entered by the user

[1632] Output: The question data in the form of an HTTP request sent to the server

[1633] Step 2:

[1634] The server analyzes the question data received from the user using a text analysis engine (e.g., NLTK, SpaCy). Here, key keywords such as "6 months old" and "night crying" are extracted from the question.

[1635] Input: Question data in HTTP request format

[1636] Output: Extracted keywords (e.g., "6 months old", "night crying")

[1637] Step 3:

[1638] The server uses an emotion recognition engine (e.g., Google Cloud Natural Language API) to analyze the emotional state of the user's question, in this case identifying whether the user is feeling emotions such as "anxiety" or "stress."

[1639] Input: Question data in HTTP request format

[1640] Output: Perceived emotional state (e.g., "anxiety")

[1641] Step 4:

[1642] The server sends a request for advice generation to a generative AI model (e.g., GPT-3) based on the extracted keywords and the recognized emotional state. The generative AI model then refers to an expert knowledge base and past data to generate appropriate advice.

[1643] Input: extracted keywords and recognized emotional states

[1644] Output: Generated advice text (e.g., "There are various causes of nighttime crying, but it is important to create a good environment. It is also important for the mother to spend time relaxing together.")

[1645] Step 5:

[1646] Based on the generated advice, the server uses a recommendation system (e.g., Collaborative Filtering) to recommend relevant childcare products and services, taking into account the user's past history and general data in the process.

[1647] Input: Generated advice text

[1648] Output: A list of recommended childcare products and services (e.g., specific toys or relaxation items)

[1649] Step 6:

[1650] The server sends the generated advice and a list of recommended childcare products and services to the user's device, which receives this information and displays it in a dedicated application.

[1651] Input: Generated advice text, recommended childcare products and services list

[1652] Output: Advice and product / service information displayed on the user's device

[1653] Step 7:

[1654] If the user selects the local community participation option, the server will search for an appropriate community group based on the user's local information and add the user to it. After that, the user can obtain further information and support through support and interaction with the community group.

[1655] Input: Request to join local community, user's local information

[1656] Output: Community group information to which the user was added

[1657] 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.

[1658] 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.

[1659] 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.

[1660] 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.

[1661] 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.

[1662] 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.

[1663] 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).

[1664] 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.

[1665] 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."

[1666] 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.

[1667] 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).

[1668] 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.

[1669] 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.

[1670] 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.

[1671] 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.

[1672] 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.

[1673] 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.

[1674] 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.

[1675] 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.

[1676] 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.

[1677] 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.

[1678] The following is further disclosed regarding the above embodiment.

[1679] (Claim 1)

[1680] means for receiving a user-entered parenting question;

[1681] means for analyzing the question and extracting key keywords;

[1682] a means for generating advice using expert knowledge based on the extracted keywords;

[1683] means for transmitting the generated advice to a corresponding user;

[1684] A means to connect with local communities and add users to appropriate community groups;

[1685] A system including:

[1686] (Claim 2)

[1687] 10. The system of claim 1, wherein the system receives a query from a user through a dedicated application.

[1688] (Claim 3)

[1689] 10. The system of claim 1, wherein multimodal AI is used to analyze user questions.

[1690] (Claim 4)

[1691] 2. The system of claim 1, which uses general artificial intelligence to generate advice based on expert knowledge.

[1692] (Claim 5)

[1693] 10. The system of claim 1, wherein the generated advice is transmitted to the user in real time.

[1694] (Claim 6)

[1695] 10. The system of claim 1, further comprising means for adding a user to an appropriate community group based on the user's location information.

[1696] "Example 1"

[1697] (Claim 1)

[1698] means for receiving a user-entered parenting question;

[1699] means for analyzing the question and extracting key keywords;

[1700] a means for generating advice using an advanced knowledge base based on the extracted keywords;

[1701] means for transmitting the generated advice to a corresponding user;

[1702] A means to connect with local communities and add users to appropriate community groups;

[1703] means for receiving a question from a user through a dedicated application;

[1704] a means for analyzing a user's question using multimodal artificial intelligence;

[1705] A system including:

[1706] (Claim 2)

[1707] 10. The system of claim 1, wherein the system receives a query from a user through a dedicated application.

[1708] (Claim 3)

[1709] 10. The system of claim 1, wherein the system generates advice in response to a user's question using a generative artificial intelligence model.

[1710] "Application Example 1"

[1711] (Claim 1)

[1712] means for receiving a user-entered parenting question;

[1713] means for analyzing the question and extracting key keywords;

[1714] a means for generating advice using an artificial intelligence model based on the extracted keywords;

[1715] means for transmitting the generated advice to a corresponding user;

[1716] A means to connect with local communities and add users to appropriate community groups;

[1717] A means for a user to input and send a question through a dedicated application;

[1718] A means to enhance advice by referencing a knowledge base of experts;

[1719] A system including:

[1720] (Claim 2)

[1721] 10. The system of claim 1, wherein the system receives a query from a user through a dedicated application.

[1722] (Claim 3)

[1723] 10. The system of claim 1, wherein the system uses multimodal artificial intelligence to analyze the user's question.

[1724] "Example 2: Combining Emotion Engines"

[1725] (Claim 1)

[1726] means for receiving a user-entered parenting question;

[1727] means for analyzing the question and extracting key keywords;

[1728] a means for generating advice using expert knowledge based on the extracted keywords;

[1729] means for recognizing the emotional state of the user and adjusting the advice content;

[1730] means for transmitting the generated advice to a corresponding user;

[1731] a means for linking with local communities to add users to appropriate community groups;

[1732] A system including:

[1733] (Claim 2)

[1734] 10. The system of claim 1, wherein the system receives a query from a user through a dedicated application.

[1735] (Claim 3)

[1736] 10. The system of claim 1, wherein multimodal AI is used to analyze user questions.

[1737] "Application example 2 when combining emotion engines"

[1738] (Claim 1)

[1739] means for receiving a user-entered parenting question;

[1740] means for analyzing the question and extracting key keywords;

[1741] a means for generating advice using expert knowledge based on the extracted keywords;

[1742] means for transmitting the generated advice to a corresponding user;

[1743] means for recognizing the emotional state of a user;

[1744] a means for tailoring advice content based on the perceived emotional state;

[1745] A means to connect with local communities and add users to appropriate community groups;

[1746] a means of recommending relevant childcare products and services;

[1747] A system including:

[1748] (Claim 2)

[1749] 10. The system of claim 1, wherein the system receives a query from a user through a dedicated application.

[1750] (Claim 3)

[1751] 10. The system of claim 1, wherein multimodal AI is used to analyze user questions. [Explanation of symbols]

[1752] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving a user-entered parenting question; means for analyzing the question and extracting key keywords; a means for generating advice using expert knowledge based on the extracted keywords; means for transmitting the generated advice to a corresponding user; A means to connect with local communities and add users to appropriate community groups; A system including:

2. The system of claim 1 , wherein the system receives a query from a user through a dedicated application.

3. 10. The system of claim 1, wherein the system analyzes user questions using multimodal AI.

4. 2. The system according to claim 1, wherein the system uses general artificial intelligence to generate advice based on expert knowledge.

5. 10. The system of claim 1, wherein the generated advice is transmitted to the user in real time.

6. 10. The system of claim 1, further comprising means for adding a user to an appropriate community group based on the user's location information.

Images