system

Abstract

We provide the system. [Solution] A means for inputting childcare data, A means of saving the entered childcare data to a database, A means of analyzing stored childcare data, A means for generating advice based on the analysis results, A means of presenting the generated advice, A system that includes this.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventional childcare record applications mainly function to simply record data, lacking means to effectively utilize the recorded data. Also, parents during childcare are busy and there is a need for an easy way to record, but currently there is not enough corresponding solution. As a result, it has become difficult for parents to grasp the baby's health condition and living pattern in detail and take appropriate measures.

Means for Solving the Problems

[0005] The present invention solves the above problems by providing a system that includes means for inputting childcare data, means for storing the input childcare data in a database, means for analyzing the stored childcare data, means for generating advice based on the analysis results, and means for presenting the generated advice. In the present invention, data can be easily input by voice input, and furthermore, a generating AI can analyze the input data and provide advice to parents in a conversational format. As a result, parents will be able to more easily notice subtle changes in their babies and take appropriate action quickly.

[0006] "Childcare data" refers to information related to the baby's lifestyle and health (e.g., frequency of urination and bowel movements, amount of milk consumed, sleep duration).

[0007] "Means of input" refers to the methods by which users provide childcare data to the system (such as keyboard input, voice input, or touch input).

[0008] A "database" refers to an information system used to store and manage childcare data.

[0009] "Means of storage" refers to the methods and processes for recording entered childcare data in a database.

[0010] "Means of analysis" refers to methods and algorithms for analyzing stored childcare data to evaluate the baby's health status and lifestyle patterns.

[0011] "Means of generation" refers to the methods and processes for creating advice provided to the user based on the analysis results.

[0012] "Advice" refers to specific suggestions and advice regarding the baby's health and childcare, based on the analysis results.

[0013] "Means of presentation" refers to the methods and processes for notifying and displaying the generated advice to the user. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0017] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0035] This invention is a childcare support system that assists parents through the management and analysis of childcare data. This system consists of a series of processes that input, store, and analyze childcare data and provide appropriate advice.

[0036] Users input childcare data using devices such as smartphones and tablets. This data includes the number of times the baby urinates and defecates, the amount of milk consumed, and the amount of sleep. Users can input data not only by text but also by voice. For example, they can use voice commands such as "The baby drank 200ml of milk today" or "The baby slept for 2 hours."

[0037] The terminal temporarily stores the input data (including voice data), and in the case of voice input, it uses a speech recognition engine to convert the voice data into text data. It then sends the converted text data to the server.

[0038] The server parses the received text data and converts it into the appropriate data format. It then stores this data in a database. For example, it might store data such as "200ml" and "2023-10-01 10:00" in the "Milk Intake" table of the database.

[0039] The analysis engine on the server periodically retrieves and analyzes the stored data. The analysis engine uses machine learning algorithms to analyze the data and understand the baby's health status and lifestyle patterns. For example, it detects abnormalities if the amount of milk consumed is less than usual or if the frequency of urination decreases.

[0040] Based on the analysis, the generating AI produces appropriate advice. This advice includes specific instructions such as, "It's best to give 220ml of milk next time," or "The baby is sleeping longer than usual, so wake them up occasionally."

[0041] The generated advice is sent from the server to the device. The device notifies the user of the received advice. When the user opens the application, the advice is displayed in a chat format. This allows parents to receive important information without having to frequently check the app.

[0042] Furthermore, users can input and submit questions about childcare data into their devices. The server analyzes the user's questions, and a generating AI produces appropriate answers. For example, if a user asks, "Is it a problem that my baby isn't gaining weight?", the generating AI will produce an answer such as, "Based on the current data, there doesn't seem to be a major problem with the growth curve. However, please consult a doctor if necessary," and send this to the device.

[0043] In this way, the system of the present invention can effectively manage childcare data and provide appropriate advice to parents, thereby reducing the burden of childcare and supporting the health management of babies.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] Users input childcare data through applications on their smartphones or tablets. For voice input, they use voice commands such as "The baby peed" or "The baby drank 200ml of milk."

[0047] Step 2:

[0048] The device temporarily stores the voice data entered by the user. In the case of voice input, the speech recognition engine within the device converts the voice data into text data. In this step, the speech recognition model analyzes the voice and converts it into appropriate text.

[0049] Step 3:

[0050] The terminal sends the converted text data to the server. HTTP or HTTPS is used as the communication protocol, and the data is encrypted to ensure security.

[0051] Step 4:

[0052] The server receives the text data and converts it into the appropriate data format. For example, it converts data such as "The baby slept for 2 hours" to correspond to the "Sleep Time" field.

[0053] Step 5:

[0054] The server saves the converted data to a database. During this process, it records the data in the appropriate table depending on the type of data (milk intake, sleep duration, urine, feces, etc.).

[0055] Step 6:

[0056] The server periodically retrieves childcare data stored in the database and sends it to the analysis engine. Scheduled tasks are often used for this step.

[0057] Step 7:

[0058] The analysis engine uses machine learning algorithms to analyze stored data and understand the baby's health status and lifestyle patterns. For example, it can detect abnormalities if the baby is drinking less milk than usual or urinating less frequently.

[0059] Step 8:

[0060] The AI ​​generates appropriate advice based on the analysis results. The content of the advice is customized according to the analysis results. For example, it may generate specific instructions such as, "It would be good to give 220ml of milk next time."

[0061] Step 9:

[0062] The server sends the generated advice to the device. Real-time notification technologies (e.g., push notifications) are used for this transmission.

[0063] Step 10:

[0064] The device receives advice and notifies the user. When the user opens the application, the advice is displayed in a chat format. This allows the user to receive important information without having to frequently check the app.

[0065] Step 11:

[0066] Users can also enter and submit further questions about childcare data on their device. For example, they might ask, "Is it a problem if my baby isn't gaining weight?"

[0067] Step 12:

[0068] The terminal sends the user's question to the server. The content of the question is also encrypted and transmitted securely.

[0069] Step 13:

[0070] The server analyzes the user's question, and the AI ​​generates an appropriate answer. For example, it might generate an answer such as, "Based on the current data, there don't seem to be any major problems with the growth curve, but please consult a doctor if necessary."

[0071] Step 14:

[0072] The server sends the generated response to the terminal. Since real-time response is required, the data is transferred quickly.

[0073] Step 15:

[0074] The device displays the received responses to the user. It allows for chat-style communication, resolving the user's questions and concerns.

[0075] (Example 1)

[0076] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0077] In modern parenting, manually managing parenting data is cumbersome for parents, making it difficult to continuously collect and analyze data to receive appropriate advice. Furthermore, there are limited means of obtaining quick and accurate answers to parenting questions. This leads to difficulties in receiving appropriate parenting support, increasing the burden of childcare.

[0078] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0079] In this invention, the server includes means for inputting childcare data, means for temporarily holding the input childcare data and analyzing it as needed, means for storing the analyzed data in a database, means for periodically analyzing the stored childcare data and detecting anomalies or specific patterns, a generative AI model that generates advice based on the analysis results, and means for presenting the generated advice. This enables efficient management of childcare data, continuous analysis, and the provision of appropriate advice.

[0080] "Childcare data" refers to records of a baby's health and lifestyle patterns, specifically including the number of times they urinate and defecate, the amount of milk they consume, and their sleep duration.

[0081] "Input method" refers to the interface that allows users to input childcare data using electronic devices such as smartphones and tablets, and enables both text input and voice input.

[0082] "Means for temporarily storing and analyzing as needed" refers to a device or software that has the function of temporarily storing childcare data entered by the user and performing initial analysis, such as converting audio data into text.

[0083] "Means of storing in a database" refers to a system or software for long-term storage of received and analyzed childcare data, such as a relational database management system (RDBMS).

[0084] "Means for periodically analyzing and detecting anomalies or specific patterns" refers to software or systems that periodically retrieve and analyze stored childcare data to detect anomalies or patterns. Specifically, this includes machine learning algorithms and analysis engines.

[0085] A "generative AI model" is an artificial intelligence model that generates appropriate advice based on analyzed childcare data, and it operates using natural language processing and machine learning technologies.

[0086] The "means of presentation" refer to an interface for informing users of the generated advice and answers, and it has the function of displaying them in a chat format through a smartphone or tablet application.

[0087] Modes for carrying out the invention

[0088] This invention is a childcare support system that assists parents through the management and analysis of childcare data. This system consists of a series of processes that input, store, and analyze childcare data and provide appropriate advice.

[0089] Input methods for childcare data

[0090] Users input childcare data using devices such as smartphones and tablets. This data includes the number of times the baby urinates and defecates, the amount of milk consumed, and the amount of sleep. Users can input data not only by text but also by voice. For example, users can use voice commands such as "The baby drank 200ml of milk today" or "The baby slept for 2 hours."

[0091] Audio data conversion

[0092] The device temporarily stores the input data (including voice data) and, in the case of voice input, uses a speech recognition engine to convert the voice data into text data. Specifically, it uses the Google® Speech Recognition API. For example, the voice data "The baby slept for 2 hours" is converted into the text data "The baby slept for 2 hours".

[0093] Sending data

[0094] The device sends the converted text data to the server. This transmission uses the HTTPS protocol. For example, the data "I drank 200ml of milk" is sent to the server.

[0095] Data storage

[0096] The server parses the received text data and converts it into the appropriate data format. This data is then stored in a database. MySQL® is used for the database. For example, the "Milk Intake" table in the database stores data such as "200ml" and "2023-10-01 10:00".

[0097] Data analysis

[0098] The analysis engine on the server periodically retrieves and analyzes the stored data. The analysis engine utilizes TENSORFLOW® and analyzes the data using machine learning algorithms. For example, it detects abnormalities if milk intake is lower than normal or if the frequency of urination decreases.

[0099] Generating advice

[0100] Based on the analysis, the AI ​​model generates appropriate advice. This advice includes specific instructions such as, "It's best to give 220ml of milk next time," or "The baby has been sleeping longer than usual, so please wake them up occasionally." The generated advice is sent from the server to the terminal.

[0101] Offering advice

[0102] The device notifies the user of any advice received. When the user opens the application, the advice is displayed in a chat format. This allows the user to receive important information without having to frequently check the app.

[0103] Questions and Answers

[0104] Furthermore, users can input and submit questions about childcare data on their devices. The server analyzes the user's questions, and a generative AI model generates appropriate answers. For example, if a user asks, "Is it a problem that my baby isn't gaining weight?", the generative AI model will generate an answer such as, "Based on the current data, there doesn't seem to be a major problem with the growth curve. However, please consult a doctor if necessary," and send this to the device.

[0105] Example of a prompt

[0106] An example of a prompt message is, "What advice should I give if my baby's milk intake is lower than normal?" In this way, the system of the present invention can effectively manage childcare data and provide appropriate advice to parents, thereby reducing the burden of childcare and supporting the health management of babies.

[0107] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0108] Step 1:

[0109] The user enters childcare data.

[0110] Users input childcare data (e.g., the number of times the baby urinates and defecates, the amount of milk consumed, sleep duration, etc.) using their smartphones or tablets. Both text and voice input are available. For example, users can use voice commands such as "The baby drank 200ml of milk today" or "The baby slept for 2 hours."

[0111] Step 2:

[0112] The device temporarily stores childcare data and converts any audio data into text data.

[0113] Input: Voice or text data entered by the user.

[0114] The device temporarily stores the input data in memory. In the case of voice input, the device uses its built-in speech recognition engine (such as Google Speech Recognition API) to convert the voice into text data. For example, the voice data "The baby slept for two hours" is converted into the text data "The baby slept for two hours".

[0115] Output: Converted text data.

[0116] Step 3:

[0117] The terminal sends the converted data to the server using the HTTPS protocol.

[0118] Input: Childcare data converted to text.

[0119] The device sends the converted text data to the server. For example, it sends the data "I drank 200ml of milk" to the server.

[0120] Output: Text data sent to the server.

[0121] Step 4:

[0122] The server receives the data, parses it, converts it to the appropriate data format, and then stores it in the database.

[0123] Input: Text data sent to the server.

[0124] The server analyzes the received data and converts it into an appropriate data format, such as "Milk Intake" and "2023-10-01 10:00". This data is then saved to a database (such as MySQL). For example, it might be saved in the "Milk Intake" table of the database as "200ml" and "2023-10-01 10:00".

[0125] Output: Data stored in the database.

[0126] Step 5:

[0127] The server periodically retrieves and analyzes the stored data to detect anomalies or specific patterns.

[0128] Input: Childcare data stored in the database.

[0129] The server's analysis engine (such as TensorFlow) periodically retrieves and analyzes the stored data. Using machine learning algorithms, it analyzes the data to detect anomalies and specific patterns, such as when milk intake is lower than normal or when the frequency of urination decreases.

[0130] Output: Analysis results (data anomalies or specific patterns).

[0131] Step 6:

[0132] The AI ​​generates advice based on the analysis results, and the server sends it to the terminal.

[0133] Input: Analysis results.

[0134] The AI ​​model generates appropriate advice based on the analysis results. For example, it includes specific instructions such as, "It's best to give 220ml of milk next time," or "The baby is sleeping longer than usual, so wake them up occasionally." The generated advice is sent from the server to the terminal.

[0135] Output: Advice sent to the terminal.

[0136] Step 7:

[0137] The device notifies the user with advice.

[0138] Input: Advice sent from the server.

[0139] The device notifies the user of any advice it receives. If the application is open, the advice is displayed in a chat format. For example, a notification might say, "It's best to give 220ml of milk next time."

[0140] Output: Advice displayed to the user.

[0141] Step 8:

[0142] The user enters questions about childcare data, the server analyzes the data, generates answers, and sends them to the device.

[0143] Input: Question from the user.

[0144] The user enters questions about childcare data into their device and sends them to the server. The server analyzes the received questions and generates appropriate answers using a generative AI model (e.g., GPT-4®). For example, in response to the question, "Is it a problem if my baby isn't gaining weight?", the server generates the answer, "Based on the current data, there doesn't seem to be a major problem with the growth curve. However, please consult a doctor if necessary," and sends this answer to the device.

[0145] Output: The response sent to the terminal.

[0146] (Application Example 1)

[0147] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0148] In childcare, parents are required to constantly monitor their baby's health and daily routines and respond appropriately. However, it is difficult to efficiently input childcare data without much effort and to receive appropriate advice based on that data in real time. Furthermore, conventional systems often require frequent use of smartphones or tablets, which can be a significant burden for parents.

[0149] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0150] In this invention, the server includes means for inputting childcare data using speech recognition, means for transmitting text data generated based on speech recognition to the server, and means for displaying advice received from the server on a next-generation display device. This streamlines the input of childcare data and enables the receipt of appropriate advice in real time via speech input and a next-generation display device.

[0151] - "Childcare data" refers to information related to the baby's health and lifestyle patterns. Specifically, this includes the frequency of urination and bowel movements, milk intake, and sleep duration.

[0152] "Speech recognition" refers to a technology that acquires speech data and converts it into text data. By analyzing information that users input verbally, it can reduce the effort required for manual data entry.

[0153] "Next-generation display devices" refer to devices that utilize mobile display technology, such as smart glasses. This allows users to receive information visually in real time.

[0154] "Advice" refers to specific instructions and suggestions generated based on the analysis of childcare data. This allows parents to manage their baby's health and reduce the burden of childcare.

[0155] A "server" refers to a computer system that stores, analyzes, and provides generated advice over a network. The server's role is to analyze data sent by users, generate appropriate advice, and send it to the user's device.

[0156] A "database" is a system for efficiently storing and managing childcare data. The stored data is later used for analysis.

[0157] "Voice input" is a method of inputting data as voice using a device such as a microphone. This eliminates the need for users to manually enter childcare data.

[0158] "Real-time" refers to a situation where the delay between entering data and receiving results is extremely short. This allows users to receive advice quickly.

[0159] A "dialogue format" is a method where questions and answers are presented as a series of exchanges. This is convenient when parents are entering questions related to childcare.

[0160] This invention is a childcare support system that assists parents through the management and analysis of childcare data. This system allows users to efficiently input childcare data and receive appropriate advice based on that data in real time.

[0161] Users input childcare data using next-generation display devices such as smart glasses or tablets. This data is entered via voice input, allowing them to use voice commands such as "The baby slept for 2 hours" or "The baby drank 200ml of milk." The voice input is converted into text data using a speech recognition system.

[0162] The converted text data is sent to a server via the internet. The server analyzes the received data and converts it into the appropriate data format. This data is then stored in a database. For example, the "Milk Intake" table will store data such as "200ml" and "2023-10-01 10:00".

[0163] The analysis engine on the server periodically retrieves and analyzes stored data. The analysis is performed using machine learning algorithms to understand the baby's health status and lifestyle patterns. For example, it detects abnormalities if the amount of milk consumed is less than usual or if the frequency of urination decreases.

[0164] Based on the analysis results, the AI ​​generates appropriate advice. Examples of advice include specific instructions such as "It's best to give 220ml of milk next time" or "The baby has slept longer than usual, so please wake them up occasionally." The generated advice is sent from the server to the user's device and displayed on the screen of a next-generation display device. This allows users to receive important information in real time without having to frequently check their device.

[0165] Furthermore, users can input and submit questions about childcare data via voice. The server receives the questions, analyzes them, and a generating AI produces appropriate answers. For example, if a user asks, "Is it a problem that my baby isn't gaining weight?", the generating AI will produce an answer such as, "Based on the current data, there doesn't seem to be a major problem with the growth curve. However, please consult a doctor if necessary," and send this to the user's device.

[0166] The following is an example of a prompt message:

[0167] "If the user inputs 'The baby has slept for two hours' via voice, it is converted to text and sent to the server. The server analyzes the data and generates advice such as, 'The baby has slept longer than usual, so please wake them up for a while,' which is then displayed on the smart glasses' screen."

[0168] This system utilizes a speech recognition system, generative AI, machine learning models, and a database, and the hardware used includes smart glasses, tablets, and servers. The software employs speech recognition libraries and machine learning algorithms. Combining these elements enables efficient management of childcare data and the provision of appropriate advice.

[0169] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0170] Step 1:

[0171] The user wears a next-generation display device (such as smart glasses) and inputs childcare data by voice. For example, they can voice-input "The baby slept for two hours." This voice input is captured via the device's microphone.

[0172] Input: Audio data

[0173] Output: Audio data

[0174] Step 2:

[0175] The device converts voice input into text data using a speech recognition system. For example, the voice input "The baby slept for two hours" is converted into the text data "The baby slept for two hours."

[0176] Input: Audio data

[0177] Output: Text data

[0178] Step 3:

[0179] The converted text data is sent to the server via the internet. The server receives this text data and stores it in a database. For example, data such as "2 hours" and "2023-10-01 10:00" will be stored in the "Sleep Time" table.

[0180] Input: Text data

[0181] Output: Saved data

[0182] Step 4:

[0183] The analysis engine on the server periodically retrieves and analyzes the stored data. The analysis engine uses machine learning algorithms to understand the baby's health status and lifestyle patterns. For example, it can detect characteristics such as "the baby is sleeping for longer periods than usual."

[0184] Input: Saved data

[0185] Output: Analysis results

[0186] Step 5:

[0187] Based on the analysis results, the generating AI produces appropriate advice. For example, the generating AI might produce specific instructions such as, "The baby is sleeping longer than usual, so please wake him up at an appropriate time."

[0188] Input: Analysis results

[0189] Output: Generated advice

[0190] Step 6:

[0191] The server sends the generated advice to the user's device. The device displays the received advice on a next-generation display device. This allows the user to receive advice in real time through smart glasses.

[0192] Input: Generated advice

[0193] Output: Advice displayed on the screen

[0194] Step 7:

[0195] Furthermore, users can input questions about childcare data using voice input. These questions are converted into text data by a voice recognition system and sent to the server. The server analyzes the questions, and a generation AI generates appropriate answers.

[0196] Input: Audio data (question), Text data (question)

[0197] Output: Analysis results, generated answers

[0198] Step 8:

[0199] The server sends the generated answers to the user's device. The device displays the received answers on a next-generation display device. This allows the user to receive answers to questions about childcare in real time.

[0200] Input: Generated answer

[0201] Output: Answer displayed on the screen

[0202] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0203] This invention is a childcare support system that assists parents through the management and analysis of childcare data. This system consists of a series of processes that input, store, and analyze childcare data, and generate and present appropriate advice. Furthermore, this invention provides support that is tailored to the user's emotions by incorporating an emotion engine that recognizes the user's emotions and reflects that emotion data in the advice generation process.

[0204] Users input childcare data using devices such as smartphones and tablets. This data includes the number of times the baby urinates and defecates, the amount of milk consumed, and the amount of sleep. In addition to text input, users can also input data using voice input. For example, they can use voice commands such as "The baby drank 200ml of milk today" or "The baby slept for 2 hours."

[0205] The terminal temporarily stores the input data (including voice data), and in the case of voice input, it uses a speech recognition engine to convert the voice data into text data. The converted text data is then sent to the server.

[0206] The server parses the received text data and converts it into the appropriate data format. This data is then stored in the database. For example, the "Milk Intake" field in the database will store data such as "200ml" and "2023-10-01 10:00".

[0207] The analysis engine on the server periodically retrieves and analyzes the stored data. The analysis engine uses machine learning algorithms to analyze the data and understand the baby's health status and lifestyle patterns. For example, it can detect abnormalities if the amount of milk consumed is less than usual or if the frequency of urination decreases.

[0208] Based on the analysis results, the AI ​​generates appropriate advice. For example, it might suggest giving 220ml of milk next time, or wake the baby up as they are sleeping longer than usual.

[0209] Furthermore, the system includes an emotion engine that recognizes emotions from the user's voice and input. The emotion engine analyzes the user's input data and voice tone to identify the user's emotional state (e.g., stress, joy, fatigue).

[0210] The emotional information of the user, recognized by the emotion engine, is reflected in the advice generation process by the generative AI. For example, if the emotion engine determines that the user is feeling stressed, the generative AI will generate advice that includes gentle words such as, "It's important to take a rest and not push yourself too hard."

[0211] The generated advice is sent from the server to the device. The device notifies the user of the received advice. When the user opens the application, the advice is displayed in a chat format. This allows the user to receive important information without having to frequently check the app.

[0212] Furthermore, users can input and submit questions about childcare data on their device. For example, they might ask, "Is it a problem if my baby isn't gaining weight?" The emotion engine also analyzes the user's emotional state when they ask the question, and the AI ​​generates an answer that is tailored to that emotional state.

[0213] In this way, the system of the present invention can effectively manage childcare data and provide appropriate advice to parents, thereby reducing the burden of childcare and supporting the health management of babies, as well as providing support that is sensitive to the user's emotions.

[0214] The following describes the processing flow.

[0215] Step 1:

[0216] Users input childcare data using a smartphone or tablet application. When using the voice input function, they might say things like, "The baby pooped," or "The baby drank 200ml of milk."

[0217] Step 2:

[0218] The device temporarily stores voice and text input data from the user. In the case of voice input, the voice data is analyzed by a speech recognition engine and converted into text data.

[0219] Step 3:

[0220] The terminal sends the converted text data to the server. The communication protocol used is either HTTP or HTTPS, and the data is encrypted.

[0221] Step 4:

[0222] The server parses the received text data and converts it into the appropriate data format. This data is then stored in the database. For example, data such as "The baby slept for 2 hours" is converted to a format corresponding to the "sleep time" field and recorded.

[0223] Step 5:

[0224] The server periodically retrieves childcare data from the database and sends it to the analysis engine. A scheduled task is used to execute the process at regular intervals.

[0225] Step 6:

[0226] The analysis engine uses machine learning algorithms to analyze stored childcare data and understand the baby's health status and lifestyle patterns. For example, it can detect abnormalities if the baby is drinking less milk than usual or if the frequency of urination decreases.

[0227] Step 7:

[0228] The analysis engine sends information about the baby's health status to the AI ​​based on the analysis results.

[0229] Step 8:

[0230] The AI ​​generates appropriate advice based on the analysis results. For example, it can generate specific instructions such as, "It would be good to give 220ml of milk next time," or "The baby is sleeping longer than usual, so wake them up at a moderate time."

[0231] Step 9:

[0232] The emotion engine analyzes the user's voice and input to identify their emotional state (e.g., stress, joy, fatigue). For example, it might determine that a user is stressed based on their tone of voice and word choice.

[0233] Step 10:

[0234] The generating AI adjusts the content of its advice based on emotional information from the emotion engine. For example, if it determines that the user is feeling stressed, it will add gentle words such as, "It's important to take a rest and not push yourself too hard."

[0235] Step 11:

[0236] The server sends the generated advice to the device. Real-time notification technologies such as push notifications are used.

[0237] Step 12:

[0238] The device receives advice and notifies the user. If the user opens the application, the advice is displayed in a chat format.

[0239] Step 13:

[0240] Users can also input and submit further questions about childcare data on their device. For example, they might ask, "Is it a problem if my baby isn't gaining weight?"

[0241] Step 14:

[0242] The terminal sends the user's question to the server. The question content is also encrypted and transmitted securely.

[0243] Step 15:

[0244] The server analyzes the user's question, and the generation AI generates an appropriate answer.

[0245] Step 16:

[0246] The emotion engine analyzes the user's emotional state when they ask a question and provides an AI-powered response that matches the user's emotions. For example, it might respond with something like, "Based on the current data, there are no major problems with the growth curve, but please consult a doctor if necessary."

[0247] Step 17:

[0248] The server sends the generated response to the terminal. The response is transmitted quickly.

[0249] Step 18:

[0250] The device displays the received responses to the user. It allows for chat-style communication, resolving the user's questions and concerns.

[0251] Through this process, the present invention can effectively manage childcare data, understand the baby's health status, and provide advice that is sensitive to the parents' emotions, thereby reducing the burden of childcare.

[0252] (Example 2)

[0253] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0254] Traditional childcare support systems focus solely on inputting, storing, and analyzing childcare data, lacking support that considers user emotions and providing appropriate advice. This makes it difficult to alleviate the stress and anxiety experienced by parents during childcare, and can lead to inconsistent health management of babies. Furthermore, the lack of convenient data input methods such as voice input and the provision of conversational answers to questions highlight the need for improved user experience.

[0255] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0256] In this invention, the server includes means for converting childcare data into text data using a speech recognition engine, means for storing the text data in a database, and means for analyzing the stored childcare data using an analysis engine. This allows users to easily input childcare data via voice input, and enables the data to be effectively stored and analyzed, as well as providing appropriate advice that is sensitive to the user's emotions.

[0257] "Childcare data" refers to information about a baby's childcare, such as the frequency of urination and defecation, milk intake, and sleep duration.

[0258] A "speech recognition engine" is a technology or software that converts spoken audio data from a user into text data.

[0259] "Text data" refers to character information converted by a speech recognition engine.

[0260] A "database" is a digital system for managing and processing stored childcare data.

[0261] An "analysis engine" is a technology or software used to analyze stored childcare data and detect abnormalities or patterns.

[0262] A "generative AI model" is a machine learning algorithm that generates optimal advice based on the results of an analysis engine.

[0263] An "emotion engine" is a technology or software that analyzes a user's emotional data and incorporates it into the generated advice.

[0264] A "user terminal" refers to a device, such as a smartphone or tablet, that a user uses to input childcare data or receive advice.

[0265] A "notification" is an alert or message that conveys generated advice to the user's device.

[0266] This invention relates to a childcare support system that uses a user terminal such as a smartphone or tablet to input childcare data, analyzes and stores that data on a server, generates appropriate advice using a generated AI model, and then provides that advice to the user. Specific embodiments of the system are shown below.

[0267] First, users input childcare data using a device such as a smartphone or tablet. This data includes the number of times the baby urinates and defecates, the amount of milk consumed, and the amount of sleep. Users can use both text and voice input. For example, if a user inputs data using a voice command such as "The baby drank 200ml of milk today," the device uses a speech recognition engine such as the Google Cloud Speech-to-Text API to convert the voice data into text data.

[0268] The terminal sends the converted text data to the server. The server parses the received text data and saves it to a database (e.g., MySQL) to store data such as "200ml" and "2023-10-01 10:00" in the "Milk Intake" field.

[0269] Next, the analysis engine on the server (e.g., a machine learning model using TensorFlow) periodically retrieves and analyzes the stored data. For example, it can detect abnormalities if milk intake is lower than normal or if the frequency of urination decreases.

[0270] Based on the analysis results, the server generates appropriate advice using a generative AI model (e.g., OpenAI®'s GPT-4). For example, it might suggest, "It would be good to give 220ml of milk next time." Furthermore, the system includes an emotion engine (e.g., Affectiva's emotion recognition API) that analyzes the user's input data and voice tone to identify their emotional state (e.g., stress, joy, fatigue). For example, if the emotion engine determines that the user is stressed, the generative AI model will generate advice with gentle words such as, "It's important to rest and not push yourself too hard."

[0271] The generated advice is sent from the server to the device, and the device notifies the user of the received advice. For example, it might use the smartphone's notification function to display, "It would be good to give 220ml of milk at the next feeding time." If the user opens the application, the advice will be displayed in a chat format, and they can also ask additional questions.

[0272] As a concrete example, if a user enters the question, "Is it a problem if my baby isn't gaining weight?", the server analyzes the received question and uses a generative AI model to generate an appropriate answer. At this time, the user's emotional state is also analyzed by the emotion engine, so an answer that is sensitive to their feelings is provided. For example, an answer such as, "Don't worry too much, let's wait and see until the next checkup," might be generated.

[0273] Example of a prompt:

[0274] Prompt: What should I do if my baby is drinking less milk than usual?

[0275] Advice: If your baby is drinking less milk than usual, you can try giving them a slightly larger amount (220ml) at the next feeding. Also, carefully observe your baby's reactions and feed them without forcing them.

[0276] As described above, the system of the present invention can effectively manage childcare data, provide appropriate advice to parents, reduce the burden of childcare, support the health management of babies, and also provide support that conforms to the emotions of users.

[0277] The flow of the specific process in Example 2 will be described with reference to FIG. 13.

[0278] Step 1:

[0279] The user inputs childcare data using an application on a smartphone or tablet. There are two input methods: text input and voice input. For example, when using a voice command such as "200 ml of milk was drunk today", the user performs voice input. The input voice data is passed to the terminal.

[0280] Input: Voice data (e.g., "200 ml of milk was drunk today")

[0281] Output: Voice data (held in the terminal)

[0282] Specific operations:

[0283] 1. The user taps the voice input button of the application.

[0284] 2. The user says "200 ml of milk was drunk today".

[0285] 3. The terminal records the voice data.

[0286] Step 2:

[0287] The terminal temporarily holds the input voice data in the memory and uses a voice recognition engine (e.g., Google Cloud Speech-to-Text API) to convert the voice data into text data.

[0288] Input: Voice data

[0289] Output: Text data (Example: "I drank 200ml of milk today")

[0290] Specific actions:

[0291] 1. The device calls the Google Cloud Speech-to-Text API.

[0292] 2. The audio data is converted into text data.

[0293] 3. The terminal temporarily saves the converted text data to memory.

[0294] Step 3:

[0295] The terminal sends the converted text data to the server. A timestamp is also added to the text data at this time.

[0296] Input: Text data (Example: "I drank 200ml of milk today")

[0297] Output: Text data (with timestamp, sent to server)

[0298] Specific actions:

[0299] 1. The device adds a timestamp to the text data (e.g., "2023-10-01 10:00").

[0300] 2. The terminal sends text data to the server.

[0301] Step 4:

[0302] The server parses the received text data and converts it into the appropriate data format. It then saves the parsed data to a database (e.g., MySQL).

[0303] Input: Text data (with timestamp)

[0304] Output: Formatted data (saved in the database)

[0305] Specific operations:

[0306] 1. The server analyzes the text data (e.g., converts it to "Milk intake: 200ml, Date and time: 2023-10-01 10:00").

[0307] 2. The server saves the analyzed data in the database.

[0308] Step 5:

[0309] The analysis engine on the server (e.g., a machine learning model using TensorFlow) periodically retrieves the saved data for analysis. In the analysis, it detects fluctuations in each childcare data item and determines whether there are any abnormalities.

[0310] Input: Childcare data saved in the database

[0311] Output: Analysis results (abnormality detection information, pattern information)

[0312] Specific operations:

[0313] 1. The analysis engine on the server retrieves data from the database.

[0314] 2. The analysis engine analyzes the data and detects abnormalities and patterns.

[0315] 3. The analysis results are retained within the server.

[0316] Step 6:

[0317] Based on the analysis results, the server generates appropriate advice using a generative AI model (e.g., OpenAI's GPT-4). It also analyzes the user's emotional state using an emotion engine (e.g., Affectiva's emotion recognition API) and incorporates this into the advice.

[0318] Input: Analysis results, user sentiment data

[0319] Output: Generated advice

[0320] Specific actions:

[0321] 1. The server calls the generated AI model based on the analysis results.

[0322] 2. The generative AI model generates appropriate advice.

[0323] 3. The emotion engine analyzes the user's emotional state and reflects it in the advice (e.g., "It's important to take a rest and not push yourself too hard").

[0324] Step 7:

[0325] The generated advice is sent from the server to the terminal.

[0326] Input: Generated advice

[0327] Output: Advice (sent to terminal)

[0328] Specific actions:

[0329] 1. The server formats and sends the generated advice to the terminal.

[0330] Step 8:

[0331] The device notifies the user of the advice it receives. For example, it might use the smartphone's notification function to display a message such as, "It would be good to give your baby 220ml of milk at the next feeding time."

[0332] Input: Advice sent from the server

[0333] Output: Advice notified to the user

[0334] Specific actions:

[0335] 1. The device receives the advice and displays an alert using the notification function.

[0336] 2. When the user opens the application, advice is displayed in a chat format.

[0337] Step 9:

[0338] Users can enter and submit questions about childcare data. For example, they might enter and submit a question such as, "Is it a problem if my baby isn't gaining weight?"

[0339] Input: User's question (text data)

[0340] Output: Question data (sent to the server)

[0341] Specific actions:

[0342] 1. The user enters a question within the application.

[0343] 2. The terminal sends the question data to the server.

[0344] Step 10:

[0345] The server analyzes the received question and generates an appropriate answer using an AI model. The emotion engine simultaneously analyzes the user's emotional state and incorporates it into the answer.

[0346] Input: User question data, user sentiment data

[0347] Output: Generated answer

[0348] Specific actions:

[0349] 1. The server analyzes the received question.

[0350] 2. The generative AI model generates an appropriate answer.

[0351] 3. The emotion engine analyzes the user's emotional state and reflects it in the response (e.g., "Don't worry too much, let's wait and see until the next check-up").

[0352] 4. The generated response is sent to the device and the user is notified.

[0353] This allows for a smooth process from inputting childcare data to providing advice and answering user questions.

[0354] (Application Example 2)

[0355] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0356] Parents raising young children need to manage detailed data to understand their baby's health and daily routines. However, manually entering and analyzing this data is extremely time-consuming and often stressful. Furthermore, it is difficult to obtain quick and accurate answers to parenting concerns and questions. Moreover, advice that does not take parents' feelings into consideration fails to alleviate their psychological burden. To address these challenges, a system is needed that automates the input, storage, and analysis of parenting data, as well as the generation and presentation of advice, providing appropriate support that is sensitive to parents' emotions.

[0357] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0358] In this invention, the server includes means for inputting childcare data, means for storing the input childcare data in a database, means for analyzing the stored childcare data, means for generating advice based on the analysis results, means for presenting the generated advice, means for analyzing the user's emotions and reflecting the analysis results in the advice generation process, and means for inputting questions into the application and presenting answers in an interactive format. This enables efficient management of childcare data and support that is sensitive to the parents' emotions.

[0359] "Childcare data" refers to data that includes information such as the amount of milk a baby drinks, their sleep duration, and how often their diapers are changed.

[0360] A "database" is a system for systematically storing and managing childcare data.

[0361] "Analysis means" refers to technical means for analyzing stored childcare data to understand the baby's health status and lifestyle patterns.

[0362] An "advice generation method" is a technical means that generates specific instructions and recommendations for parents based on the analysis results.

[0363] "Presentation method" refers to a method or system for informing parents of the generated advice.

[0364] "Emotional analysis methods" are technologies that analyze a user's emotions from their voice and text data and incorporate the analysis results into the advice provided.

[0365] A "dialogue-based approach" is a technical means that provides answers to user questions in a natural, conversational format through an application.

[0366] The "smartphone notification function" is a feature that notifies parents in real time of advice and important information generated on the smartphone.

[0367] This invention is a system that provides efficient management of childcare data and support that is sensitive to the emotions of parents. The system consists of the following elements:

[0368] 1. User's terminal

[0369] Users input baby care data using their smartphones or tablets. This data includes information such as the baby's milk intake, sleep duration, and diaper change frequency. Voice input is also possible; for example, data can be entered using voice commands such as "The baby drank 200ml of milk today." A speech recognition engine (e.g., Google Speech-to-Text API) is used to convert the voice into text data.

[0370] 2. Server

[0371] The input data is temporarily held on the device and then sent to the server. The server uses Node.js, converts the received data into the appropriate format, and stores it in a MongoDB database. The server periodically analyzes the stored data and generates necessary advice. TensorFlow.js is used for data analysis, and based on the analysis results, a generative AI (e.g., OpenAI API) generates advice.

[0372] 3. Emotion analysis

[0373] TensorFlow.js is used to analyze the user's emotions from their voice and input. The results of the emotion analysis are reflected in the prompts sent to the generating AI, resulting in more empathetic advice. For example, if the analysis indicates that the user is stressed, the advice will include gentle words such as, "It's important to take a rest and not push yourself too hard."

[0374] 4. Offering advice

[0375] The generated advice is sent back to the user's device from the server. The advice and important information are then notified in real time using the smartphone's notification function. Therefore, users do not need to frequently check the app and can receive important information at the appropriate time.

[0376] 5. Question and Answer Session in an Dialogue Format

[0377] The application includes a chatbot function, allowing users to input questions about childcare and receive answers in a conversational format. The user's emotional state at the time of questioning is also analyzed, and a corresponding response is provided by the AI.

[0378] Specific example

[0379] For example, if a user enters the question, "Is it a problem if my baby isn't gaining weight?", the emotion analysis engine analyzes the user's stress level and, based on that, generates a gentle response such as, "While consulting with experts is important, every baby grows at their own pace, so please don't worry too much."

[0380] Example of a prompt

[0381] The baby's latest milk intake is 200ml. The parents are feeling stressed. Please advise on the appropriate amount of milk for the next feeding and provide some reassuring advice.

[0382] In this way, the present invention enables efficient management and analysis of childcare data, provides emotionally supportive advice, and reduces the burden on parents during childcare.

[0383] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0384] Step 1:

[0385] The user enters childcare data.

[0386] How it works: The user opens the application on their smartphone and enters childcare data such as the baby's milk intake, sleep duration, and diaper change frequency in text or voice. For voice input, the Google Speech-to-Text API is used to convert the speech to text.

[0387] Input: Milk intake, sleep duration, diaper change frequency

[0388] Output: Childcare data in text format

[0389] Step 2:

[0390] The terminal temporarily stores the entered data and sends it to the server.

[0391] Operation: Data is saved to the device's local storage and sent to a Node.js server in real time. The server receives the data and converts it to the appropriate format.

[0392] Input: Childcare data in text format

[0393] Output: Sending data to the server

[0394] Step 3:

[0395] The server saves the received data to the database.

[0396] Operation: Received data is saved to a MongoDB database. The database stores various data about the baby, along with the date and time.

[0397] Input: Childcare data in text format

[0398] Output: Childcare data stored in the database

[0399] Step 4:

[0400] The server periodically analyzes the stored data.

[0401] Operation: Uses TensorFlow.js to analyze stored data. Detects trends in milk intake and changes in sleep duration to identify anomalies.

[0402] Input: Childcare data stored in the database

[0403] Output: Analysis results (e.g., abnormal milk intake)

[0404] Step 5:

[0405] The server generates advice based on the analysis results.

[0406] Operation: Sends analysis results to the OpenAI API and generates appropriate advice using the generated AI model. Creates prompt messages and sends them to the AI.

[0407] Input: Analysis results

[0408] Output: Generated advice (text format)

[0409] Step 6:

[0410] The server notifies the smartphone of the generated advice.

[0411] Operation: Generated advice is sent to the device and the parent is notified using the smartphone's notification function.

[0412] Input: Generated advice

[0413] Output: Notification to smartphone

[0414] Step 7:

[0415] It analyzes emotions based on user input data and voice.

[0416] Operation: Uses TensorFlow.js to analyze the user's emotional state from speech and text. Reflects the analysis results in prompts and sends them to the generating AI.

[0417] Input: User's voice or text

[0418] Output: Emotion analysis results

[0419] Step 8:

[0420] Generates emotion-based advice.

[0421] Operation: Incorporates user sentiment analysis results into prompts and generates emotion-responsive advice using the OpenAI API.

[0422] Input: Sentiment analysis results, prompt text

[0423] Output: Emotional response advice (text format)

[0424] Step 9:

[0425] It accepts user questions and provides answers in a conversational format.

[0426] Operation: Uses the application's chatbot function to receive questions from users about childcare. Generates prompts, including sentiment analysis, and creates answers using the OpenAI API.

[0427] Input: User's question (text format), sentiment analysis results

[0428] Output: Dialogue-style response (text format)

[0429] In this way, the present invention functions as a system that provides efficient management of childcare data and support that is sensitive to the emotions of parents.

[0430] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0431] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0432] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0433] [Second Embodiment]

[0434] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0435] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0436] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0437] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0438] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0439] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0440] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0441] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0442] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0443] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0444] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0445] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0446] This invention is a childcare support system that assists parents through the management and analysis of childcare data. This system consists of a series of processes that input, store, and analyze childcare data and provide appropriate advice.

[0447] Users input childcare data using devices such as smartphones and tablets. This data includes the number of times the baby urinates and defecates, the amount of milk consumed, and the amount of sleep. Users can input data not only by text but also by voice. For example, they can use voice commands such as "The baby drank 200ml of milk today" or "The baby slept for 2 hours."

[0448] The terminal temporarily stores the input data (including voice data), and in the case of voice input, it uses a speech recognition engine to convert the voice data into text data. It then sends the converted text data to the server.

[0449] The server parses the received text data and converts it into the appropriate data format. It then stores this data in a database. For example, it might store data such as "200ml" and "2023-10-01 10:00" in the "Milk Intake" table of the database.

[0450] The analysis engine on the server periodically retrieves and analyzes the stored data. The analysis engine uses machine learning algorithms to analyze the data and understand the baby's health status and lifestyle patterns. For example, it detects abnormalities if the amount of milk consumed is less than usual or if the frequency of urination decreases.

[0451] Based on the analysis, the generating AI produces appropriate advice. This advice includes specific instructions such as, "It's best to give 220ml of milk next time," or "The baby is sleeping longer than usual, so wake them up occasionally."

[0452] The generated advice is sent from the server to the device. The device notifies the user of the received advice. When the user opens the application, the advice is displayed in a chat format. This allows parents to receive important information without having to frequently check the app.

[0453] Furthermore, users can input and submit questions about childcare data into their devices. The server analyzes the user's questions, and a generating AI produces appropriate answers. For example, if a user asks, "Is it a problem that my baby isn't gaining weight?", the generating AI will produce an answer such as, "Based on the current data, there doesn't seem to be a major problem with the growth curve. However, please consult a doctor if necessary," and send this to the device.

[0454] In this way, the system of the present invention can effectively manage childcare data and provide appropriate advice to parents, thereby reducing the burden of childcare and supporting the health management of babies.

[0455] The following describes the processing flow.

[0456] Step 1:

[0457] Users input childcare data through applications on their smartphones or tablets. For voice input, they use voice commands such as "The baby peed" or "The baby drank 200ml of milk."

[0458] Step 2:

[0459] The device temporarily stores the voice data entered by the user. In the case of voice input, the speech recognition engine within the device converts the voice data into text data. In this step, the speech recognition model analyzes the voice and converts it into appropriate text.

[0460] Step 3:

[0461] The terminal sends the converted text data to the server. HTTP or HTTPS is used as the communication protocol, and the data is encrypted to ensure security.

[0462] Step 4:

[0463] The server receives the text data and converts it into the appropriate data format. For example, it converts data such as "The baby slept for 2 hours" to correspond to the "Sleep Time" field.

[0464] Step 5:

[0465] The server saves the converted data to a database. During this process, it records the data in the appropriate table depending on the type of data (milk intake, sleep duration, urine, feces, etc.).

[0466] Step 6:

[0467] The server periodically retrieves childcare data stored in the database and sends it to the analysis engine. Scheduled tasks are often used for this step.

[0468] Step 7:

[0469] The analysis engine uses machine learning algorithms to analyze stored data and understand the baby's health status and lifestyle patterns. For example, it can detect abnormalities if the baby is drinking less milk than usual or urinating less frequently.

[0470] Step 8:

[0471] The AI ​​generates appropriate advice based on the analysis results. The content of the advice is customized according to the analysis results. For example, it may generate specific instructions such as, "It would be good to give 220ml of milk next time."

[0472] Step 9:

[0473] The server sends the generated advice to the device. Real-time notification technologies (e.g., push notifications) are used for this transmission.

[0474] Step 10:

[0475] The device receives advice and notifies the user. When the user opens the application, the advice is displayed in a chat format. This allows the user to receive important information without having to frequently check the app.

[0476] Step 11:

[0477] Users can also enter and submit further questions about childcare data on their device. For example, they might ask, "Is it a problem if my baby isn't gaining weight?"

[0478] Step 12:

[0479] The terminal sends the user's question to the server. The content of the question is also encrypted and transmitted securely.

[0480] Step 13:

[0481] The server analyzes the user's question, and the AI ​​generates an appropriate answer. For example, it might generate an answer such as, "Based on the current data, there don't seem to be any major problems with the growth curve, but please consult a doctor if necessary."

[0482] Step 14:

[0483] The server sends the generated response to the terminal. Since real-time response is required, the data is transferred quickly.

[0484] Step 15:

[0485] The device displays the received responses to the user. It allows for chat-style communication, resolving the user's questions and concerns.

[0486] (Example 1)

[0487] Next, we will describe Example 1. 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".

[0488] In modern parenting, manually managing parenting data is cumbersome for parents, making it difficult to continuously collect and analyze data to receive appropriate advice. Furthermore, there are limited means of obtaining quick and accurate answers to parenting questions. This leads to difficulties in receiving appropriate parenting support, increasing the burden of childcare.

[0489] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0490] In this invention, the server includes means for inputting childcare data, means for temporarily holding the input childcare data and analyzing it as needed, means for storing the analyzed data in a database, means for periodically analyzing the stored childcare data and detecting anomalies or specific patterns, a generative AI model that generates advice based on the analysis results, and means for presenting the generated advice. This enables efficient management of childcare data, continuous analysis, and the provision of appropriate advice.

[0491] "Childcare data" refers to records of a baby's health and lifestyle patterns, specifically including the number of times they urinate and defecate, the amount of milk they consume, and their sleep duration.

[0492] "Input method" refers to the interface that allows users to input childcare data using electronic devices such as smartphones and tablets, and enables both text input and voice input.

[0493] "Means for temporarily storing and analyzing as needed" refers to a device or software that has the function of temporarily storing childcare data entered by the user and performing initial analysis, such as converting audio data into text.

[0494] "Means of storing in a database" refers to a system or software for long-term storage of received and analyzed childcare data, such as a relational database management system (RDBMS).

[0495] "Means for periodically analyzing and detecting anomalies or specific patterns" refers to software or systems that periodically retrieve and analyze stored childcare data to detect anomalies or patterns. Specifically, this includes machine learning algorithms and analysis engines.

[0496] A "generative AI model" is an artificial intelligence model that generates appropriate advice based on analyzed childcare data, and it operates using natural language processing and machine learning technologies.

[0497] The "means of presentation" refer to an interface for informing users of the generated advice and answers, and it has the function of displaying them in a chat format through a smartphone or tablet application.

[0498] Modes for carrying out the invention

[0499] This invention is a childcare support system that assists parents through the management and analysis of childcare data. This system consists of a series of processes that input, store, and analyze childcare data and provide appropriate advice.

[0500] Input methods for childcare data

[0501] Users input childcare data using devices such as smartphones and tablets. This data includes the number of times the baby urinates and defecates, the amount of milk consumed, and the amount of sleep. Users can input data not only by text but also by voice. For example, users can use voice commands such as "The baby drank 200ml of milk today" or "The baby slept for 2 hours."

[0502] Audio data conversion

[0503] The device temporarily stores the input data (including voice data) and, in the case of voice input, uses a speech recognition engine to convert the voice data into text data. Specifically, it uses the Google Speech Recognition API. For example, the voice data "The baby slept for 2 hours" is converted into the text data "The baby slept for 2 hours".

[0504] Sending data

[0505] The device sends the converted text data to the server. This transmission uses the HTTPS protocol. For example, the data "I drank 200ml of milk" is sent to the server.

[0506] Data storage

[0507] The server parses the received text data and converts it into the appropriate data format. This data is then stored in a database. MySQL is used for the database. For example, the "Milk Intake" table in the database stores data such as "200ml" and "2023-10-01 10:00".

[0508] Data analysis

[0509] The analysis engine on the server periodically retrieves and analyzes the stored data. The analysis engine utilizes TensorFlow and employs machine learning algorithms to analyze the data. For example, it detects abnormalities if milk intake is lower than normal or if the frequency of urination decreases.

[0510] Generating advice

[0511] Based on the analysis, the AI ​​model generates appropriate advice. This advice includes specific instructions such as, "It's best to give 220ml of milk next time," or "The baby has been sleeping longer than usual, so please wake them up occasionally." The generated advice is sent from the server to the terminal.

[0512] Offering advice

[0513] The device notifies the user of any advice received. When the user opens the application, the advice is displayed in a chat format. This allows the user to receive important information without having to frequently check the app.

[0514] Questions and Answers

[0515] Furthermore, users can input and submit questions about childcare data on their devices. The server analyzes the user's questions, and a generative AI model generates appropriate answers. For example, if a user asks, "Is it a problem that my baby isn't gaining weight?", the generative AI model will generate an answer such as, "Based on the current data, there doesn't seem to be a major problem with the growth curve. However, please consult a doctor if necessary," and send this to the device.

[0516] Example of a prompt

[0517] An example of a prompt message is, "What advice should I give if my baby's milk intake is lower than normal?" In this way, the system of the present invention can effectively manage childcare data and provide appropriate advice to parents, thereby reducing the burden of childcare and supporting the health management of babies.

[0518] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0519] Step 1:

[0520] The user enters childcare data.

[0521] Users input childcare data (e.g., the number of times the baby urinates and defecates, the amount of milk consumed, sleep duration, etc.) using their smartphones or tablets. Both text and voice input are available. For example, users can use voice commands such as "The baby drank 200ml of milk today" or "The baby slept for 2 hours."

[0522] Step 2:

[0523] The device temporarily stores childcare data and converts any audio data into text data.

[0524] Input: Voice or text data entered by the user.

[0525] The device temporarily stores the input data in memory. In the case of voice input, the device uses its built-in speech recognition engine (such as Google Speech Recognition API) to convert the voice into text data. For example, the voice data "The baby slept for two hours" is converted into the text data "The baby slept for two hours".

[0526] Output: Converted text data.

[0527] Step 3:

[0528] The terminal sends the converted data to the server using the HTTPS protocol.

[0529] Input: Childcare data converted to text.

[0530] The device sends the converted text data to the server. For example, it sends the data "I drank 200ml of milk" to the server.

[0531] Output: Text data sent to the server.

[0532] Step 4:

[0533] The server receives the data, parses it, converts it to the appropriate data format, and then stores it in the database.

[0534] Input: Text data sent to the server.

[0535] The server analyzes the received data and converts it into an appropriate data format, such as "Milk Intake" and "2023-10-01 10:00". This data is then saved to a database (such as MySQL). For example, it might be saved in the "Milk Intake" table of the database as "200ml" and "2023-10-01 10:00".

[0536] Output: Data stored in the database.

[0537] Step 5:

[0538] The server periodically retrieves and analyzes the stored data to detect anomalies or specific patterns.

[0539] Input: Childcare data stored in the database.

[0540] The server's analysis engine (such as TensorFlow) periodically retrieves and analyzes the stored data. Using machine learning algorithms, it analyzes the data to detect anomalies and specific patterns, such as when milk intake is lower than normal or when the frequency of urination decreases.

[0541] Output: Analysis results (data anomalies or specific patterns).

[0542] Step 6:

[0543] The AI ​​generates advice based on the analysis results, and the server sends it to the terminal.

[0544] Input: Analysis results.

[0545] The AI ​​model generates appropriate advice based on the analysis results. For example, it includes specific instructions such as, "It's best to give 220ml of milk next time," or "The baby is sleeping longer than usual, so wake them up occasionally." The generated advice is sent from the server to the terminal.

[0546] Output: Advice sent to the terminal.

[0547] Step 7:

[0548] The device notifies the user with advice.

[0549] Input: Advice sent from the server.

[0550] The device notifies the user of any advice it receives. If the application is open, the advice is displayed in a chat format. For example, a notification might say, "It's best to give 220ml of milk next time."

[0551] Output: Advice displayed to the user.

[0552] Step 8:

[0553] The user enters questions about childcare data, the server analyzes the data, generates answers, and sends them to the device.

[0554] Input: Question from the user.

[0555] The user enters questions about childcare data into their device and sends them to the server. The server analyzes the received questions and generates appropriate answers using a generative AI model (such as GPT-4). For example, in response to the question, "Is it a problem if my baby's weight isn't increasing?", the server generates the answer, "Based on the current data, there doesn't seem to be a major problem with the growth curve. However, please consult a doctor if necessary," and sends this answer to the device.

[0556] Output: The response sent to the terminal.

[0557] (Application Example 1)

[0558] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0559] In childcare, parents are required to constantly monitor their baby's health and daily routines and respond appropriately. However, it is difficult to efficiently input childcare data without much effort and to receive appropriate advice based on that data in real time. Furthermore, conventional systems often require frequent use of smartphones or tablets, which can be a significant burden for parents.

[0560] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0561] In this invention, the server includes means for inputting childcare data using speech recognition, means for transmitting text data generated based on speech recognition to the server, and means for displaying advice received from the server on a next-generation display device. This streamlines the input of childcare data and enables the receipt of appropriate advice in real time via speech input and a next-generation display device.

[0562] - "Childcare data" refers to information related to the baby's health and lifestyle patterns. Specifically, this includes the frequency of urination and bowel movements, milk intake, and sleep duration.

[0563] "Speech recognition" refers to a technology that acquires speech data and converts it into text data. By analyzing information that users input verbally, it can reduce the effort required for manual data entry.

[0564] "Next-generation display devices" refer to devices that utilize mobile display technology, such as smart glasses. This allows users to receive information visually in real time.

[0565] "Advice" refers to specific instructions and suggestions generated based on the analysis of childcare data. This allows parents to manage their baby's health and reduce the burden of childcare.

[0566] A "server" refers to a computer system that stores, analyzes, and provides generated advice over a network. The server's role is to analyze data sent by users, generate appropriate advice, and send it to the user's device.

[0567] A "database" is a system for efficiently storing and managing childcare data. The stored data is later used for analysis.

[0568] "Voice input" is a method of inputting data as voice using a device such as a microphone. This eliminates the need for users to manually enter childcare data.

[0569] "Real-time" refers to a situation where the delay between entering data and receiving results is extremely short. This allows users to receive advice quickly.

[0570] A "dialogue format" is a method where questions and answers are presented as a series of exchanges. This is convenient when parents are entering questions related to childcare.

[0571] This invention is a childcare support system that assists parents through the management and analysis of childcare data. This system allows users to efficiently input childcare data and receive appropriate advice based on that data in real time.

[0572] Users input childcare data using next-generation display devices such as smart glasses or tablets. This data is entered via voice input, allowing them to use voice commands such as "The baby slept for 2 hours" or "The baby drank 200ml of milk." The voice input is converted into text data using a speech recognition system.

[0573] The converted text data is sent to a server via the internet. The server analyzes the received data and converts it into the appropriate data format. This data is then stored in a database. For example, the "Milk Intake" table will store data such as "200ml" and "2023-10-01 10:00".

[0574] The analysis engine on the server periodically retrieves and analyzes stored data. The analysis is performed using machine learning algorithms to understand the baby's health status and lifestyle patterns. For example, it detects abnormalities if the amount of milk consumed is less than usual or if the frequency of urination decreases.

[0575] Based on the analysis results, the AI ​​generates appropriate advice. Examples of advice include specific instructions such as "It's best to give 220ml of milk next time" or "The baby has slept longer than usual, so please wake them up occasionally." The generated advice is sent from the server to the user's device and displayed on the screen of a next-generation display device. This allows users to receive important information in real time without having to frequently check their device.

[0576] Furthermore, users can input and submit questions about childcare data via voice. The server receives the questions, analyzes them, and a generating AI produces appropriate answers. For example, if a user asks, "Is it a problem that my baby isn't gaining weight?", the generating AI will produce an answer such as, "Based on the current data, there doesn't seem to be a major problem with the growth curve. However, please consult a doctor if necessary," and send this to the user's device.

[0577] The following is an example of a prompt message:

[0578] "If the user inputs 'The baby has slept for two hours' via voice, it is converted to text and sent to the server. The server analyzes the data and generates advice such as, 'The baby has slept longer than usual, so please wake them up for a while,' which is then displayed on the smart glasses' screen."

[0579] This system utilizes a speech recognition system, generative AI, machine learning models, and a database, and the hardware used includes smart glasses, tablets, and servers. The software employs speech recognition libraries and machine learning algorithms. Combining these elements enables efficient management of childcare data and the provision of appropriate advice.

[0580] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0581] Step 1:

[0582] The user wears a next-generation display device (such as smart glasses) and inputs childcare data by voice. For example, they can voice-input "The baby slept for two hours." This voice input is captured via the device's microphone.

[0583] Input: Audio data

[0584] Output: Audio data

[0585] Step 2:

[0586] The device converts voice input into text data using a speech recognition system. For example, the voice input "The baby slept for two hours" is converted into the text data "The baby slept for two hours."

[0587] Input: Audio data

[0588] Output: Text data

[0589] Step 3:

[0590] The converted text data is sent to the server via the internet. The server receives this text data and stores it in a database. For example, data such as "2 hours" and "2023-10-01 10:00" will be stored in the "Sleep Time" table.

[0591] Input: Text data

[0592] Output: Saved data

[0593] Step 4:

[0594] The analysis engine on the server periodically retrieves and analyzes the stored data. The analysis engine uses machine learning algorithms to understand the baby's health status and lifestyle patterns. For example, it can detect characteristics such as "the baby is sleeping for longer periods than usual."

[0595] Input: Saved data

[0596] Output: Analysis results

[0597] Step 5:

[0598] Based on the analysis results, the generating AI produces appropriate advice. For example, the generating AI might produce specific instructions such as, "The baby is sleeping longer than usual, so please wake him up at an appropriate time."

[0599] Input: Analysis results

[0600] Output: Generated advice

[0601] Step 6:

[0602] The server sends the generated advice to the user's device. The device displays the received advice on a next-generation display device. This allows the user to receive advice in real time through smart glasses.

[0603] Input: Generated advice

[0604] Output: Advice displayed on the screen

[0605] Step 7:

[0606] Furthermore, users can input questions about childcare data using voice input. These questions are converted into text data by a voice recognition system and sent to the server. The server analyzes the questions, and a generation AI generates appropriate answers.

[0607] Input: Audio data (question), Text data (question)

[0608] Output: Analysis results, generated answers

[0609] Step 8:

[0610] The server sends the generated answers to the user's device. The device displays the received answers on a next-generation display device. This allows the user to receive answers to questions about childcare in real time.

[0611] Input: Generated answer

[0612] Output: Answer displayed on the screen

[0613] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0614] This invention is a childcare support system that assists parents through the management and analysis of childcare data. This system consists of a series of processes that input, store, and analyze childcare data, and generate and present appropriate advice. Furthermore, this invention provides support that is tailored to the user's emotions by incorporating an emotion engine that recognizes the user's emotions and reflects that emotion data in the advice generation process.

[0615] Users input childcare data using devices such as smartphones and tablets. This data includes the number of times the baby urinates and defecates, the amount of milk consumed, and the amount of sleep. In addition to text input, users can also input data using voice input. For example, they can use voice commands such as "The baby drank 200ml of milk today" or "The baby slept for 2 hours."

[0616] The terminal temporarily stores the input data (including voice data), and in the case of voice input, it uses a speech recognition engine to convert the voice data into text data. The converted text data is then sent to the server.

[0617] The server parses the received text data and converts it into the appropriate data format. This data is then stored in the database. For example, the "Milk Intake" field in the database will store data such as "200ml" and "2023-10-01 10:00".

[0618] The analysis engine on the server periodically retrieves and analyzes the stored data. The analysis engine uses machine learning algorithms to analyze the data and understand the baby's health status and lifestyle patterns. For example, it can detect abnormalities if the amount of milk consumed is less than usual or if the frequency of urination decreases.

[0619] Based on the analysis results, the AI ​​generates appropriate advice. For example, it might suggest giving 220ml of milk next time, or wake the baby up as they are sleeping longer than usual.

[0620] Furthermore, the system includes an emotion engine that recognizes emotions from the user's voice and input. The emotion engine analyzes the user's input data and voice tone to identify the user's emotional state (e.g., stress, joy, fatigue).

[0621] The emotional information of the user, recognized by the emotion engine, is reflected in the advice generation process by the generative AI. For example, if the emotion engine determines that the user is feeling stressed, the generative AI will generate advice that includes gentle words such as, "It's important to take a rest and not push yourself too hard."

[0622] The generated advice is sent from the server to the device. The device notifies the user of the received advice. When the user opens the application, the advice is displayed in a chat format. This allows the user to receive important information without having to frequently check the app.

[0623] Furthermore, users can input and submit questions about childcare data on their device. For example, they might ask, "Is it a problem if my baby isn't gaining weight?" The emotion engine also analyzes the user's emotional state when they ask the question, and the AI ​​generates an answer that is tailored to that emotional state.

[0624] In this way, the system of the present invention can effectively manage childcare data and provide appropriate advice to parents, thereby reducing the burden of childcare and supporting the health management of babies, as well as providing support that is sensitive to the user's emotions.

[0625] The following describes the processing flow.

[0626] Step 1:

[0627] Users input childcare data using a smartphone or tablet application. When using the voice input function, they might say things like, "The baby pooped," or "The baby drank 200ml of milk."

[0628] Step 2:

[0629] The device temporarily stores voice and text input data from the user. In the case of voice input, the voice data is analyzed by a speech recognition engine and converted into text data.

[0630] Step 3:

[0631] The terminal sends the converted text data to the server. The communication protocol used is either HTTP or HTTPS, and the data is encrypted.

[0632] Step 4:

[0633] The server parses the received text data and converts it into the appropriate data format. This data is then stored in the database. For example, data such as "The baby slept for 2 hours" is converted to a format corresponding to the "sleep time" field and recorded.

[0634] Step 5:

[0635] The server periodically retrieves childcare data from the database and sends it to the analysis engine. A scheduled task is used to execute the process at regular intervals.

[0636] Step 6:

[0637] The analysis engine uses machine learning algorithms to analyze stored childcare data and understand the baby's health status and lifestyle patterns. For example, it can detect abnormalities if the baby is drinking less milk than usual or if the frequency of urination decreases.

[0638] Step 7:

[0639] The analysis engine sends information about the baby's health status to the AI ​​based on the analysis results.

[0640] Step 8:

[0641] The AI ​​generates appropriate advice based on the analysis results. For example, it can generate specific instructions such as, "It would be good to give 220ml of milk next time," or "The baby is sleeping longer than usual, so wake them up at a moderate time."

[0642] Step 9:

[0643] The emotion engine analyzes the user's voice and input to identify their emotional state (e.g., stress, joy, fatigue). For example, it might determine that a user is stressed based on their tone of voice and word choice.

[0644] Step 10:

[0645] The generating AI adjusts the content of its advice based on emotional information from the emotion engine. For example, if it determines that the user is feeling stressed, it will add gentle words such as, "It's important to take a rest and not push yourself too hard."

[0646] Step 11:

[0647] The server sends the generated advice to the device. Real-time notification technologies such as push notifications are used.

[0648] Step 12:

[0649] The device receives advice and notifies the user. If the user opens the application, the advice is displayed in a chat format.

[0650] Step 13:

[0651] Users can also input and submit further questions about childcare data on their device. For example, they might ask, "Is it a problem if my baby isn't gaining weight?"

[0652] Step 14:

[0653] The terminal sends the user's question to the server. The question content is also encrypted and transmitted securely.

[0654] Step 15:

[0655] The server analyzes the user's question, and the generation AI generates an appropriate answer.

[0656] Step 16:

[0657] The emotion engine analyzes the user's emotional state when they ask a question and provides an AI-powered response that matches the user's emotions. For example, it might respond with something like, "Based on the current data, there are no major problems with the growth curve, but please consult a doctor if necessary."

[0658] Step 17:

[0659] The server sends the generated response to the terminal. The response is transmitted quickly.

[0660] Step 18:

[0661] The device displays the received responses to the user. It allows for chat-style communication, resolving the user's questions and concerns.

[0662] Through this process, the present invention can effectively manage childcare data, understand the baby's health status, and provide advice that is sensitive to the parents' emotions, thereby reducing the burden of childcare.

[0663] (Example 2)

[0664] Next, we will describe Example 2. 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".

[0665] Traditional childcare support systems focus solely on inputting, storing, and analyzing childcare data, lacking support that considers user emotions and providing appropriate advice. This makes it difficult to alleviate the stress and anxiety experienced by parents during childcare, and can lead to inconsistent health management of babies. Furthermore, the lack of convenient data input methods such as voice input and the provision of conversational answers to questions highlight the need for improved user experience.

[0666] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0667] In this invention, the server includes means for converting childcare data into text data using a speech recognition engine, means for storing the text data in a database, and means for analyzing the stored childcare data using an analysis engine. This allows users to easily input childcare data via voice input, and enables the data to be effectively stored and analyzed, as well as providing appropriate advice that is sensitive to the user's emotions.

[0668] "Childcare data" refers to information about a baby's childcare, such as the frequency of urination and defecation, milk intake, and sleep duration.

[0669] A "speech recognition engine" is a technology or software that converts spoken audio data from a user into text data.

[0670] "Text data" refers to character information converted by a speech recognition engine.

[0671] A "database" is a digital system for managing and processing stored childcare data.

[0672] An "analysis engine" is a technology or software used to analyze stored childcare data and detect abnormalities or patterns.

[0673] A "generative AI model" is a machine learning algorithm that generates optimal advice based on the results of an analysis engine.

[0674] An "emotion engine" is a technology or software that analyzes a user's emotional data and incorporates it into the generated advice.

[0675] A "user terminal" refers to a device, such as a smartphone or tablet, that a user uses to input childcare data or receive advice.

[0676] A "notification" is an alert or message that conveys generated advice to the user's device.

[0677] This invention relates to a childcare support system that uses a user terminal such as a smartphone or tablet to input childcare data, analyzes and stores that data on a server, generates appropriate advice using a generated AI model, and then provides that advice to the user. Specific embodiments of the system are shown below.

[0678] First, users input childcare data using a device such as a smartphone or tablet. This data includes the number of times the baby urinates and defecates, the amount of milk consumed, and the amount of sleep. Users can use both text and voice input. For example, if a user inputs data using a voice command such as "The baby drank 200ml of milk today," the device uses a speech recognition engine such as the Google Cloud Speech-to-Text API to convert the voice data into text data.

[0679] The terminal sends the converted text data to the server. The server parses the received text data and saves it to a database (e.g., MySQL) to store data such as "200ml" and "2023-10-01 10:00" in the "Milk Intake" field.

[0680] Next, the analysis engine on the server (e.g., a machine learning model using TensorFlow) periodically retrieves and analyzes the stored data. For example, it can detect abnormalities if milk intake is lower than normal or if the frequency of urination decreases.

[0681] Based on the analysis results, the server generates appropriate advice using a generative AI model (e.g., OpenAI's GPT-4). For example, it might suggest, "It would be good to give 220ml of milk next time." Furthermore, the system includes an emotion engine (e.g., Affectiva's emotion recognition API) that analyzes the user's input data and voice tone to identify their emotional state (e.g., stress, joy, fatigue). For example, if the emotion engine determines that the user is stressed, the generative AI model will generate advice with gentle words such as, "It's important to rest and not push yourself too hard."

[0682] The generated advice is sent from the server to the device, and the device notifies the user of the received advice. For example, it might use the smartphone's notification function to display, "It would be good to give 220ml of milk at the next feeding time." If the user opens the application, the advice will be displayed in a chat format, and they can also ask additional questions.

[0683] As a concrete example, if a user enters the question, "Is it a problem if my baby isn't gaining weight?", the server analyzes the received question and uses a generative AI model to generate an appropriate answer. At this time, the user's emotional state is also analyzed by the emotion engine, so an answer that is sensitive to their feelings is provided. For example, an answer such as, "Don't worry too much, let's wait and see until the next checkup," might be generated.

[0684] Example of a prompt:

[0685] Prompt: What should I do if my baby is drinking less milk than usual?

[0686] Advice: If your baby is drinking less milk than usual, you can try giving them a slightly larger amount (220ml) at the next feeding. Also, carefully observe your baby's reactions and feed them without forcing them.

[0687] As described above, the system of the present invention can effectively manage childcare data and provide appropriate advice to parents, thereby reducing the burden of childcare and supporting the health management of babies, as well as providing support that is sensitive to the user's emotions.

[0688] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0689] Step 1:

[0690] Users input childcare data using a smartphone or tablet application. There are two input methods: text input and voice input. For example, when using a voice command such as "The baby drank 200ml of milk today," the user inputs it using voice. The entered voice data is then sent to the device.

[0691] Input: Voice data (Example: "I drank 200ml of milk today")

[0692] Output: Audio data (stored on the device)

[0693] Specific actions:

[0694] 1. The user taps the voice input button in the app.

[0695] 2. The user says, "I drank 200ml of milk today."

[0696] 3. The device records the audio data.

[0697] Step 2:

[0698] The device temporarily stores the input audio data in memory and uses a speech recognition engine (e.g., Google Cloud Speech-to-Text API) to convert the audio data into text data.

[0699] Input: Audio data

[0700] Output: Text data (Example: "I drank 200ml of milk today")

[0701] Specific actions:

[0702] 1. The device calls the Google Cloud Speech-to-Text API.

[0703] 2. The audio data is converted into text data.

[0704] 3. The terminal temporarily saves the converted text data to memory.

[0705] Step 3:

[0706] The terminal sends the converted text data to the server. A timestamp is also added to the text data at this time.

[0707] Input: Text data (Example: "I drank 200ml of milk today")

[0708] Output: Text data (with timestamp, sent to server)

[0709] Specific actions:

[0710] 1. The device adds a timestamp to the text data (e.g., "2023-10-01 10:00").

[0711] 2. The terminal sends text data to the server.

[0712] Step 4:

[0713] The server parses the received text data and converts it into the appropriate data format. It then saves the parsed data to a database (e.g., MySQL).

[0714] Input: Text data (with timestamp)

[0715] Output: Formatted data (saved in database)

[0716] Specific actions:

[0717] 1. The server parses the text data (e.g., converts it to "Milk intake: 200ml, Date and time: 2023-10-01 10:00").

[0718] 2. The server saves the analyzed data to the database.

[0719] Step 5:

[0720] The analysis engine on the server (e.g., a machine learning model using TensorFlow) periodically retrieves and analyzes the stored data. The analysis detects changes in each childcare data item and determines whether or not there are any abnormalities.

[0721] Input: Childcare data stored in the database

[0722] Output: Analysis results (anomaly detection information, pattern information)

[0723] Specific actions:

[0724] 1. The server's analysis engine retrieves data from the database.

[0725] 2. The analysis engine analyzes the data and detects anomalies and patterns.

[0726] 3. The analysis results are stored on the server.

[0727] Step 6:

[0728] Based on the analysis results, the server generates appropriate advice using a generative AI model (e.g., OpenAI's GPT-4). It also analyzes the user's emotional state using an emotion engine (e.g., Affectiva's emotion recognition API) and incorporates this into the advice.

[0729] Input: Analysis results, user sentiment data

[0730] Output: Generated advice

[0731] Specific actions:

[0732] 1. The server calls the generated AI model based on the analysis results.

[0733] 2. The generative AI model generates appropriate advice.

[0734] 3. The emotion engine analyzes the user's emotional state and reflects it in the advice (e.g., "It's important to take a rest and not push yourself too hard").

[0735] Step 7:

[0736] The generated advice is sent from the server to the terminal.

[0737] Input: Generated advice

[0738] Output: Advice (sent to terminal)

[0739] Specific actions:

[0740] 1. The server formats and sends the generated advice to the terminal.

[0741] Step 8:

[0742] The device notifies the user of the advice it receives. For example, it might use the smartphone's notification function to display a message such as, "It would be good to give your baby 220ml of milk at the next feeding time."

[0743] Input: Advice sent from the server

[0744] Output: Advice notified to the user

[0745] Specific actions:

[0746] 1. The device receives the advice and displays an alert using the notification function.

[0747] 2. When the user opens the application, advice is displayed in a chat format.

[0748] Step 9:

[0749] Users can enter and submit questions about childcare data. For example, they might enter and submit a question such as, "Is it a problem if my baby isn't gaining weight?"

[0750] Input: User's question (text data)

[0751] Output: Question data (sent to the server)

[0752] Specific actions:

[0753] 1. The user enters a question within the application.

[0754] 2. The terminal sends the question data to the server.

[0755] Step 10:

[0756] The server analyzes the received question and generates an appropriate answer using an AI model. The emotion engine simultaneously analyzes the user's emotional state and incorporates it into the answer.

[0757] Input: User question data, user sentiment data

[0758] Output: Generated answer

[0759] Specific actions:

[0760] 1. The server analyzes the received question.

[0761] 2. The generative AI model generates an appropriate answer.

[0762] 3. The emotion engine analyzes the user's emotional state and reflects it in the response (e.g., "Don't worry too much, let's wait and see until the next check-up").

[0763] 4. The generated response is sent to the device and the user is notified.

[0764] This allows for a smooth process from inputting childcare data to providing advice and answering user questions.

[0765] (Application Example 2)

[0766] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0767] Parents raising young children need to manage detailed data to understand their baby's health and daily routines. However, manually entering and analyzing this data is extremely time-consuming and often stressful. Furthermore, it is difficult to obtain quick and accurate answers to parenting concerns and questions. Moreover, advice that does not take parents' feelings into consideration fails to alleviate their psychological burden. To address these challenges, a system is needed that automates the input, storage, and analysis of parenting data, as well as the generation and presentation of advice, providing appropriate support that is sensitive to parents' emotions.

[0768] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0769] In this invention, the server includes means for inputting childcare data, means for storing the input childcare data in a database, means for analyzing the stored childcare data, means for generating advice based on the analysis results, means for presenting the generated advice, means for analyzing the user's emotions and reflecting the analysis results in the advice generation process, and means for inputting questions into the application and presenting answers in an interactive format. This enables efficient management of childcare data and support that is sensitive to the parents' emotions.

[0770] "Childcare data" refers to data that includes information such as the amount of milk a baby drinks, their sleep duration, and how often their diapers are changed.

[0771] A "database" is a system for systematically storing and managing childcare data.

[0772] "Analysis means" refers to technical means for analyzing stored childcare data to understand the baby's health status and lifestyle patterns.

[0773] An "advice generation method" is a technical means that generates specific instructions and recommendations for parents based on the analysis results.

[0774] "Presentation method" refers to a method or system for informing parents of the generated advice.

[0775] "Emotional analysis methods" are technologies that analyze a user's emotions from their voice and text data and incorporate the analysis results into the advice provided.

[0776] A "dialogue-based approach" is a technical means that provides answers to user questions in a natural, conversational format through an application.

[0777] The "smartphone notification function" is a feature that notifies parents in real time of advice and important information generated on the smartphone.

[0778] This invention is a system that provides efficient management of childcare data and support that is sensitive to the emotions of parents. The system consists of the following elements:

[0779] 1. User's terminal

[0780] Users input baby care data using their smartphones or tablets. This data includes information such as the baby's milk intake, sleep duration, and diaper change frequency. Voice input is also possible; for example, data can be entered using voice commands such as "The baby drank 200ml of milk today." A speech recognition engine (e.g., Google Speech-to-Text API) is used to convert the voice into text data.

[0781] 2. Server

[0782] The input data is temporarily held on the device and then sent to the server. The server uses Node.js, converts the received data into the appropriate format, and stores it in a MongoDB database. The server periodically analyzes the stored data and generates necessary advice. TensorFlow.js is used for data analysis, and based on the analysis results, a generative AI (e.g., OpenAI API) generates advice.

[0783] 3. Emotion analysis

[0784] TensorFlow.js is used to analyze the user's emotions from their voice and input. The results of the emotion analysis are reflected in the prompts sent to the generating AI, resulting in more empathetic advice. For example, if the analysis indicates that the user is stressed, the advice will include gentle words such as, "It's important to take a rest and not push yourself too hard."

[0785] 4. Offering advice

[0786] The generated advice is sent back to the user's device from the server. The advice and important information are then notified in real time using the smartphone's notification function. Therefore, users do not need to frequently check the app and can receive important information at the appropriate time.

[0787] 5. Question and Answer Session in an Dialogue Format

[0788] The application includes a chatbot function, allowing users to input questions about childcare and receive answers in a conversational format. The user's emotional state at the time of questioning is also analyzed, and a corresponding response is provided by the AI.

[0789] Specific example

[0790] For example, if a user enters the question, "Is it a problem if my baby isn't gaining weight?", the emotion analysis engine analyzes the user's stress level and, based on that, generates a gentle response such as, "While consulting with experts is important, every baby grows at their own pace, so please don't worry too much."

[0791] Example of a prompt

[0792] The baby's latest milk intake is 200ml. The parents are feeling stressed. Please advise on the appropriate amount of milk for the next feeding and provide some reassuring advice.

[0793] In this way, the present invention enables efficient management and analysis of childcare data, provides emotionally supportive advice, and reduces the burden on parents during childcare.

[0794] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0795] Step 1:

[0796] The user enters childcare data.

[0797] How it works: The user opens the application on their smartphone and enters childcare data such as the baby's milk intake, sleep duration, and diaper change frequency in text or voice. For voice input, the Google Speech-to-Text API is used to convert the speech to text.

[0798] Input: Milk intake, sleep duration, diaper change frequency

[0799] Output: Childcare data in text format

[0800] Step 2:

[0801] The terminal temporarily stores the entered data and sends it to the server.

[0802] Operation: Data is saved to the device's local storage and sent to a Node.js server in real time. The server receives the data and converts it to the appropriate format.

[0803] Input: Childcare data in text format

[0804] Output: Sending data to the server

[0805] Step 3:

[0806] The server saves the received data to the database.

[0807] Operation: Received data is saved to a MongoDB database. The database stores various data about the baby, along with the date and time.

[0808] Input: Childcare data in text format

[0809] Output: Childcare data stored in the database

[0810] Step 4:

[0811] The server periodically analyzes the stored data.

[0812] Operation: Uses TensorFlow.js to analyze stored data. Detects trends in milk intake and changes in sleep duration to identify anomalies.

[0813] Input: Childcare data stored in the database

[0814] Output: Analysis results (e.g., abnormal milk intake)

[0815] Step 5:

[0816] The server generates advice based on the analysis results.

[0817] Operation: Sends analysis results to the OpenAI API and generates appropriate advice using the generated AI model. Creates prompt messages and sends them to the AI.

[0818] Input: Analysis results

[0819] Output: Generated advice (text format)

[0820] Step 6:

[0821] The server notifies the smartphone of the generated advice.

[0822] Operation: Generated advice is sent to the device and the parent is notified using the smartphone's notification function.

[0823] Input: Generated advice

[0824] Output: Notification to smartphone

[0825] Step 7:

[0826] It analyzes emotions based on user input data and voice.

[0827] Operation: Uses TensorFlow.js to analyze the user's emotional state from speech and text. Reflects the analysis results in prompts and sends them to the generating AI.

[0828] Input: User's voice or text

[0829] Output: Emotion analysis results

[0830] Step 8:

[0831] Generates emotion-based advice.

[0832] Operation: Incorporates user sentiment analysis results into prompts and generates emotion-responsive advice using the OpenAI API.

[0833] Input: Sentiment analysis results, prompt text

[0834] Output: Emotional response advice (text format)

[0835] Step 9:

[0836] It accepts user questions and provides answers in a conversational format.

[0837] Operation: Uses the application's chatbot function to receive questions from users about childcare. Generates prompts, including sentiment analysis, and creates answers using the OpenAI API.

[0838] Input: User's question (text format), sentiment analysis results

[0839] Output: Dialogue-style response (text format)

[0840] In this way, the present invention functions as a system that provides efficient management of childcare data and support that is sensitive to the emotions of parents.

[0841] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0842] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0843] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0844] [Third Embodiment]

[0845] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0846] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0847] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0848] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0849] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0850] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0851] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0852] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0853] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0854] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0855] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0856] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0857] This invention is a childcare support system that assists parents through the management and analysis of childcare data. This system consists of a series of processes that input, store, and analyze childcare data and provide appropriate advice.

[0858] Users input childcare data using devices such as smartphones and tablets. This data includes the number of times the baby urinates and defecates, the amount of milk consumed, and the amount of sleep. Users can input data not only by text but also by voice. For example, they can use voice commands such as "The baby drank 200ml of milk today" or "The baby slept for 2 hours."

[0859] The terminal temporarily stores the input data (including voice data), and in the case of voice input, it uses a speech recognition engine to convert the voice data into text data. It then sends the converted text data to the server.

[0860] The server parses the received text data and converts it into the appropriate data format. It then stores this data in a database. For example, it might store data such as "200ml" and "2023-10-01 10:00" in the "Milk Intake" table of the database.

[0861] The analysis engine on the server periodically retrieves and analyzes the stored data. The analysis engine uses machine learning algorithms to analyze the data and understand the baby's health status and lifestyle patterns. For example, it detects abnormalities if the amount of milk consumed is less than usual or if the frequency of urination decreases.

[0862] Based on the analysis, the generating AI produces appropriate advice. This advice includes specific instructions such as, "It's best to give 220ml of milk next time," or "The baby is sleeping longer than usual, so wake them up occasionally."

[0863] The generated advice is sent from the server to the device. The device notifies the user of the received advice. When the user opens the application, the advice is displayed in a chat format. This allows parents to receive important information without having to frequently check the app.

[0864] Furthermore, users can input and submit questions about childcare data into their devices. The server analyzes the user's questions, and a generating AI produces appropriate answers. For example, if a user asks, "Is it a problem that my baby isn't gaining weight?", the generating AI will produce an answer such as, "Based on the current data, there doesn't seem to be a major problem with the growth curve. However, please consult a doctor if necessary," and send this to the device.

[0865] In this way, the system of the present invention can effectively manage childcare data and provide appropriate advice to parents, thereby reducing the burden of childcare and supporting the health management of babies.

[0866] The following describes the processing flow.

[0867] Step 1:

[0868] Users input childcare data through applications on their smartphones or tablets. For voice input, they use voice commands such as "The baby peed" or "The baby drank 200ml of milk."

[0869] Step 2:

[0870] The device temporarily stores the voice data entered by the user. In the case of voice input, the speech recognition engine within the device converts the voice data into text data. In this step, the speech recognition model analyzes the voice and converts it into appropriate text.

[0871] Step 3:

[0872] The terminal sends the converted text data to the server. HTTP or HTTPS is used as the communication protocol, and the data is encrypted to ensure security.

[0873] Step 4:

[0874] The server receives the text data and converts it into the appropriate data format. For example, it converts data such as "The baby slept for 2 hours" to correspond to the "Sleep Time" field.

[0875] Step 5:

[0876] The server saves the converted data to a database. During this process, it records the data in the appropriate table depending on the type of data (milk intake, sleep duration, urine, feces, etc.).

[0877] Step 6:

[0878] The server periodically retrieves childcare data stored in the database and sends it to the analysis engine. Scheduled tasks are often used for this step.

[0879] Step 7:

[0880] The analysis engine uses machine learning algorithms to analyze stored data and understand the baby's health status and lifestyle patterns. For example, it can detect abnormalities if the baby is drinking less milk than usual or urinating less frequently.

[0881] Step 8:

[0882] The AI ​​generates appropriate advice based on the analysis results. The content of the advice is customized according to the analysis results. For example, it may generate specific instructions such as, "It would be good to give 220ml of milk next time."

[0883] Step 9:

[0884] The server sends the generated advice to the device. Real-time notification technologies (e.g., push notifications) are used for this transmission.

[0885] Step 10:

[0886] The device receives advice and notifies the user. When the user opens the application, the advice is displayed in a chat format. This allows the user to receive important information without having to frequently check the app.

[0887] Step 11:

[0888] Users can also enter and submit further questions about childcare data on their device. For example, they might ask, "Is it a problem if my baby isn't gaining weight?"

[0889] Step 12:

[0890] The terminal sends the user's question to the server. The content of the question is also encrypted and transmitted securely.

[0891] Step 13:

[0892] The server analyzes the user's question, and the AI ​​generates an appropriate answer. For example, it might generate an answer such as, "Based on the current data, there don't seem to be any major problems with the growth curve, but please consult a doctor if necessary."

[0893] Step 14:

[0894] The server sends the generated response to the terminal. Since real-time response is required, the data is transferred quickly.

[0895] Step 15:

[0896] The device displays the received responses to the user. It allows for chat-style communication, resolving the user's questions and concerns.

[0897] (Example 1)

[0898] Next, we will describe Example 1. 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."

[0899] In modern parenting, manually managing parenting data is cumbersome for parents, making it difficult to continuously collect and analyze data to receive appropriate advice. Furthermore, there are limited means of obtaining quick and accurate answers to parenting questions. This leads to difficulties in receiving appropriate parenting support, increasing the burden of childcare.

[0900] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0901] In this invention, the server includes means for inputting childcare data, means for temporarily holding the input childcare data and analyzing it as needed, means for storing the analyzed data in a database, means for periodically analyzing the stored childcare data and detecting anomalies or specific patterns, a generative AI model that generates advice based on the analysis results, and means for presenting the generated advice. This enables efficient management of childcare data, continuous analysis, and the provision of appropriate advice.

[0902] "Childcare data" refers to records of a baby's health and lifestyle patterns, specifically including the number of times they urinate and defecate, the amount of milk they consume, and their sleep duration.

[0903] "Input method" refers to the interface that allows users to input childcare data using electronic devices such as smartphones and tablets, and enables both text input and voice input.

[0904] "Means for temporarily storing and analyzing as needed" refers to a device or software that has the function of temporarily storing childcare data entered by the user and performing initial analysis, such as converting audio data into text.

[0905] "Means of storing in a database" refers to a system or software for long-term storage of received and analyzed childcare data, such as a relational database management system (RDBMS).

[0906] "Means for periodically analyzing and detecting anomalies or specific patterns" refers to software or systems that periodically retrieve and analyze stored childcare data to detect anomalies or patterns. Specifically, this includes machine learning algorithms and analysis engines.

[0907] A "generative AI model" is an artificial intelligence model that generates appropriate advice based on analyzed childcare data, and it operates using natural language processing and machine learning technologies.

[0908] The "means of presentation" refer to an interface for informing users of the generated advice and answers, and it has the function of displaying them in a chat format through a smartphone or tablet application.

[0909] Modes for carrying out the invention

[0910] This invention is a childcare support system that assists parents through the management and analysis of childcare data. This system consists of a series of processes that input, store, and analyze childcare data and provide appropriate advice.

[0911] Input methods for childcare data

[0912] Users input childcare data using devices such as smartphones and tablets. This data includes the number of times the baby urinates and defecates, the amount of milk consumed, and the amount of sleep. Users can input data not only by text but also by voice. For example, users can use voice commands such as "The baby drank 200ml of milk today" or "The baby slept for 2 hours."

[0913] Audio data conversion

[0914] The device temporarily stores the input data (including voice data) and, in the case of voice input, uses a speech recognition engine to convert the voice data into text data. Specifically, it uses the Google Speech Recognition API. For example, the voice data "The baby slept for 2 hours" is converted into the text data "The baby slept for 2 hours".

[0915] Sending data

[0916] The device sends the converted text data to the server. This transmission uses the HTTPS protocol. For example, the data "I drank 200ml of milk" is sent to the server.

[0917] Data storage

[0918] The server parses the received text data and converts it into the appropriate data format. This data is then stored in a database. MySQL is used for the database. For example, the "Milk Intake" table in the database stores data such as "200ml" and "2023-10-01 10:00".

[0919] Data analysis

[0920] The analysis engine on the server periodically retrieves and analyzes the stored data. The analysis engine utilizes TensorFlow and employs machine learning algorithms to analyze the data. For example, it detects abnormalities if milk intake is lower than normal or if the frequency of urination decreases.

[0921] Generating advice

[0922] Based on the analysis, the AI ​​model generates appropriate advice. This advice includes specific instructions such as, "It's best to give 220ml of milk next time," or "The baby has been sleeping longer than usual, so please wake them up occasionally." The generated advice is sent from the server to the terminal.

[0923] Offering advice

[0924] The device notifies the user of any advice received. When the user opens the application, the advice is displayed in a chat format. This allows the user to receive important information without having to frequently check the app.

[0925] Questions and Answers

[0926] Furthermore, users can input and submit questions about childcare data on their devices. The server analyzes the user's questions, and a generative AI model generates appropriate answers. For example, if a user asks, "Is it a problem that my baby isn't gaining weight?", the generative AI model will generate an answer such as, "Based on the current data, there doesn't seem to be a major problem with the growth curve. However, please consult a doctor if necessary," and send this to the device.

[0927] Example of a prompt

[0928] An example of a prompt message is, "What advice should I give if my baby's milk intake is lower than normal?" In this way, the system of the present invention can effectively manage childcare data and provide appropriate advice to parents, thereby reducing the burden of childcare and supporting the health management of babies.

[0929] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0930] Step 1:

[0931] The user enters childcare data.

[0932] Users input childcare data (e.g., the number of times the baby urinates and defecates, the amount of milk consumed, sleep duration, etc.) using their smartphones or tablets. Both text and voice input are available. For example, users can use voice commands such as "The baby drank 200ml of milk today" or "The baby slept for 2 hours."

[0933] Step 2:

[0934] The device temporarily stores childcare data and converts any audio data into text data.

[0935] Input: Voice or text data entered by the user.

[0936] The device temporarily stores the input data in memory. In the case of voice input, the device uses its built-in speech recognition engine (such as Google Speech Recognition API) to convert the voice into text data. For example, the voice data "The baby slept for two hours" is converted into the text data "The baby slept for two hours".

[0937] Output: Converted text data.

[0938] Step 3:

[0939] The terminal sends the converted data to the server using the HTTPS protocol.

[0940] Input: Childcare data converted to text.

[0941] The device sends the converted text data to the server. For example, it sends the data "I drank 200ml of milk" to the server.

[0942] Output: Text data sent to the server.

[0943] Step 4:

[0944] The server receives the data, parses it, converts it to the appropriate data format, and then stores it in the database.

[0945] Input: Text data sent to the server.

[0946] The server analyzes the received data and converts it into an appropriate data format, such as "Milk Intake" and "2023-10-01 10:00". This data is then saved to a database (such as MySQL). For example, it might be saved in the "Milk Intake" table of the database as "200ml" and "2023-10-01 10:00".

[0947] Output: Data stored in the database.

[0948] Step 5:

[0949] The server periodically retrieves and analyzes the stored data to detect anomalies or specific patterns.

[0950] Input: Childcare data stored in the database.

[0951] The server's analysis engine (such as TensorFlow) periodically retrieves and analyzes the stored data. Using machine learning algorithms, it analyzes the data to detect anomalies and specific patterns, such as when milk intake is lower than normal or when the frequency of urination decreases.

[0952] Output: Analysis results (data anomalies or specific patterns).

[0953] Step 6:

[0954] The AI ​​generates advice based on the analysis results, and the server sends it to the terminal.

[0955] Input: Analysis results.

[0956] The AI ​​model generates appropriate advice based on the analysis results. For example, it includes specific instructions such as, "It's best to give 220ml of milk next time," or "The baby is sleeping longer than usual, so wake them up occasionally." The generated advice is sent from the server to the terminal.

[0957] Output: Advice sent to the terminal.

[0958] Step 7:

[0959] The device notifies the user with advice.

[0960] Input: Advice sent from the server.

[0961] The device notifies the user of any advice it receives. If the application is open, the advice is displayed in a chat format. For example, a notification might say, "It's best to give 220ml of milk next time."

[0962] Output: Advice displayed to the user.

[0963] Step 8:

[0964] The user enters questions about childcare data, the server analyzes the data, generates answers, and sends them to the device.

[0965] Input: Question from the user.

[0966] The user enters questions about childcare data into their device and sends them to the server. The server analyzes the received questions and generates appropriate answers using a generative AI model (such as GPT-4). For example, in response to the question, "Is it a problem if my baby's weight isn't increasing?", the server generates the answer, "Based on the current data, there doesn't seem to be a major problem with the growth curve. However, please consult a doctor if necessary," and sends this answer to the device.

[0967] Output: The response sent to the terminal.

[0968] (Application Example 1)

[0969] Next, we will explain Application Example 1. In the following explanation, 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."

[0970] In childcare, parents are required to constantly monitor their baby's health and daily routines and respond appropriately. However, it is difficult to efficiently input childcare data without much effort and to receive appropriate advice based on that data in real time. Furthermore, conventional systems often require frequent use of smartphones or tablets, which can be a significant burden for parents.

[0971] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0972] In this invention, the server includes means for inputting childcare data using speech recognition, means for transmitting text data generated based on speech recognition to the server, and means for displaying advice received from the server on a next-generation display device. This streamlines the input of childcare data and enables the receipt of appropriate advice in real time via speech input and a next-generation display device.

[0973] - "Childcare data" refers to information related to the baby's health and lifestyle patterns. Specifically, this includes the frequency of urination and bowel movements, milk intake, and sleep duration.

[0974] "Speech recognition" refers to a technology that acquires speech data and converts it into text data. By analyzing information that users input verbally, it can reduce the effort required for manual data entry.

[0975] "Next-generation display devices" refer to devices that utilize mobile display technology, such as smart glasses. This allows users to receive information visually in real time.

[0976] "Advice" refers to specific instructions and suggestions generated based on the analysis of childcare data. This allows parents to manage their baby's health and reduce the burden of childcare.

[0977] A "server" refers to a computer system that stores, analyzes, and provides generated advice over a network. The server's role is to analyze data sent by users, generate appropriate advice, and send it to the user's device.

[0978] A "database" is a system for efficiently storing and managing childcare data. The stored data is later used for analysis.

[0979] "Voice input" is a method of inputting data as voice using a device such as a microphone. This eliminates the need for users to manually enter childcare data.

[0980] "Real-time" refers to a situation where the delay between entering data and receiving results is extremely short. This allows users to receive advice quickly.

[0981] A "dialogue format" is a method where questions and answers are presented as a series of exchanges. This is convenient when parents are entering questions related to childcare.

[0982] This invention is a childcare support system that assists parents through the management and analysis of childcare data. This system allows users to efficiently input childcare data and receive appropriate advice based on that data in real time.

[0983] Users input childcare data using next-generation display devices such as smart glasses or tablets. This data is entered via voice input, allowing them to use voice commands such as "The baby slept for 2 hours" or "The baby drank 200ml of milk." The voice input is converted into text data using a speech recognition system.

[0984] The converted text data is sent to a server via the internet. The server analyzes the received data and converts it into the appropriate data format. This data is then stored in a database. For example, the "Milk Intake" table will store data such as "200ml" and "2023-10-01 10:00".

[0985] The analysis engine on the server periodically retrieves and analyzes stored data. The analysis is performed using machine learning algorithms to understand the baby's health status and lifestyle patterns. For example, it detects abnormalities if the amount of milk consumed is less than usual or if the frequency of urination decreases.

[0986] Based on the analysis results, the AI ​​generates appropriate advice. Examples of advice include specific instructions such as "It's best to give 220ml of milk next time" or "The baby has slept longer than usual, so please wake them up occasionally." The generated advice is sent from the server to the user's device and displayed on the screen of a next-generation display device. This allows users to receive important information in real time without having to frequently check their device.

[0987] Furthermore, users can input and submit questions about childcare data via voice. The server receives the questions, analyzes them, and a generating AI produces appropriate answers. For example, if a user asks, "Is it a problem that my baby isn't gaining weight?", the generating AI will produce an answer such as, "Based on the current data, there doesn't seem to be a major problem with the growth curve. However, please consult a doctor if necessary," and send this to the user's device.

[0988] The following is an example of a prompt message:

[0989] "If the user inputs 'The baby has slept for two hours' via voice, it is converted to text and sent to the server. The server analyzes the data and generates advice such as, 'The baby has slept longer than usual, so please wake them up for a while,' which is then displayed on the smart glasses' screen."

[0990] This system utilizes a speech recognition system, generative AI, machine learning models, and a database, and the hardware used includes smart glasses, tablets, and servers. The software employs speech recognition libraries and machine learning algorithms. Combining these elements enables efficient management of childcare data and the provision of appropriate advice.

[0991] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0992] Step 1:

[0993] The user wears a next-generation display device (such as smart glasses) and inputs childcare data by voice. For example, they can voice-input "The baby slept for two hours." This voice input is captured via the device's microphone.

[0994] Input: Audio data

[0995] Output: Audio data

[0996] Step 2:

[0997] The device converts voice input into text data using a speech recognition system. For example, the voice input "The baby slept for two hours" is converted into the text data "The baby slept for two hours."

[0998] Input: Audio data

[0999] Output: Text data

[1000] Step 3:

[1001] The converted text data is sent to the server via the internet. The server receives this text data and stores it in a database. For example, data such as "2 hours" and "2023-10-01 10:00" will be stored in the "Sleep Time" table.

[1002] Input: Text data

[1003] Output: Saved data

[1004] Step 4:

[1005] The analysis engine on the server periodically retrieves and analyzes the stored data. The analysis engine uses machine learning algorithms to understand the baby's health status and lifestyle patterns. For example, it can detect characteristics such as "the baby is sleeping for longer periods than usual."

[1006] Input: Saved data

[1007] Output: Analysis results

[1008] Step 5:

[1009] Based on the analysis results, the generating AI produces appropriate advice. For example, the generating AI might produce specific instructions such as, "The baby is sleeping longer than usual, so please wake him up at an appropriate time."

[1010] Input: Analysis results

[1011] Output: Generated advice

[1012] Step 6:

[1013] The server sends the generated advice to the user's device. The device displays the received advice on a next-generation display device. This allows the user to receive advice in real time through smart glasses.

[1014] Input: Generated advice

[1015] Output: Advice displayed on the screen

[1016] Step 7:

[1017] Furthermore, users can input questions about childcare data using voice input. These questions are converted into text data by a voice recognition system and sent to the server. The server analyzes the questions, and a generation AI generates appropriate answers.

[1018] Input: Audio data (question), Text data (question)

[1019] Output: Analysis results, generated answers

[1020] Step 8:

[1021] The server sends the generated answers to the user's device. The device displays the received answers on a next-generation display device. This allows the user to receive answers to questions about childcare in real time.

[1022] Input: Generated answer

[1023] Output: Answer displayed on the screen

[1024] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1025] This invention is a childcare support system that assists parents through the management and analysis of childcare data. This system consists of a series of processes that input, store, and analyze childcare data, and generate and present appropriate advice. Furthermore, this invention provides support that is tailored to the user's emotions by incorporating an emotion engine that recognizes the user's emotions and reflects that emotion data in the advice generation process.

[1026] Users input childcare data using devices such as smartphones and tablets. This data includes the number of times the baby urinates and defecates, the amount of milk consumed, and the amount of sleep. In addition to text input, users can also input data using voice input. For example, they can use voice commands such as "The baby drank 200ml of milk today" or "The baby slept for 2 hours."

[1027] The terminal temporarily stores the input data (including voice data), and in the case of voice input, it uses a speech recognition engine to convert the voice data into text data. The converted text data is then sent to the server.

[1028] The server parses the received text data and converts it into the appropriate data format. This data is then stored in the database. For example, the "Milk Intake" field in the database will store data such as "200ml" and "2023-10-01 10:00".

[1029] The analysis engine on the server periodically retrieves and analyzes the stored data. The analysis engine uses machine learning algorithms to analyze the data and understand the baby's health status and lifestyle patterns. For example, it can detect abnormalities if the amount of milk consumed is less than usual or if the frequency of urination decreases.

[1030] Based on the analysis results, the AI ​​generates appropriate advice. For example, it might suggest giving 220ml of milk next time, or wake the baby up as they are sleeping longer than usual.

[1031] Furthermore, the system includes an emotion engine that recognizes emotions from the user's voice and input. The emotion engine analyzes the user's input data and voice tone to identify the user's emotional state (e.g., stress, joy, fatigue).

[1032] The emotional information of the user, recognized by the emotion engine, is reflected in the advice generation process by the generative AI. For example, if the emotion engine determines that the user is feeling stressed, the generative AI will generate advice that includes gentle words such as, "It's important to take a rest and not push yourself too hard."

[1033] The generated advice is sent from the server to the device. The device notifies the user of the received advice. When the user opens the application, the advice is displayed in a chat format. This allows the user to receive important information without having to frequently check the app.

[1034] Furthermore, users can input and submit questions about childcare data on their device. For example, they might ask, "Is it a problem if my baby isn't gaining weight?" The emotion engine also analyzes the user's emotional state when they ask the question, and the AI ​​generates an answer that is tailored to that emotional state.

[1035] In this way, the system of the present invention can effectively manage childcare data and provide appropriate advice to parents, thereby reducing the burden of childcare and supporting the health management of babies, as well as providing support that is sensitive to the user's emotions.

[1036] The following describes the processing flow.

[1037] Step 1:

[1038] Users input childcare data using a smartphone or tablet application. When using the voice input function, they might say things like, "The baby pooped," or "The baby drank 200ml of milk."

[1039] Step 2:

[1040] The device temporarily stores voice and text input data from the user. In the case of voice input, the voice data is analyzed by a speech recognition engine and converted into text data.

[1041] Step 3:

[1042] The terminal sends the converted text data to the server. The communication protocol used is either HTTP or HTTPS, and the data is encrypted.

[1043] Step 4:

[1044] The server parses the received text data and converts it into the appropriate data format. This data is then stored in the database. For example, data such as "The baby slept for 2 hours" is converted to a format corresponding to the "sleep time" field and recorded.

[1045] Step 5:

[1046] The server periodically retrieves childcare data from the database and sends it to the analysis engine. A scheduled task is used to execute the process at regular intervals.

[1047] Step 6:

[1048] The analysis engine uses machine learning algorithms to analyze stored childcare data and understand the baby's health status and lifestyle patterns. For example, it can detect abnormalities if the baby is drinking less milk than usual or if the frequency of urination decreases.

[1049] Step 7:

[1050] The analysis engine sends information about the baby's health status to the AI ​​based on the analysis results.

[1051] Step 8:

[1052] The AI ​​generates appropriate advice based on the analysis results. For example, it can generate specific instructions such as, "It would be good to give 220ml of milk next time," or "The baby is sleeping longer than usual, so wake them up at a moderate time."

[1053] Step 9:

[1054] The emotion engine analyzes the user's voice and input to identify their emotional state (e.g., stress, joy, fatigue). For example, it might determine that a user is stressed based on their tone of voice and word choice.

[1055] Step 10:

[1056] The generating AI adjusts the content of its advice based on emotional information from the emotion engine. For example, if it determines that the user is feeling stressed, it will add gentle words such as, "It's important to take a rest and not push yourself too hard."

[1057] Step 11:

[1058] The server sends the generated advice to the device. Real-time notification technologies such as push notifications are used.

[1059] Step 12:

[1060] The device receives advice and notifies the user. If the user opens the application, the advice is displayed in a chat format.

[1061] Step 13:

[1062] Users can also input and submit further questions about childcare data on their device. For example, they might ask, "Is it a problem if my baby isn't gaining weight?"

[1063] Step 14:

[1064] The terminal sends the user's question to the server. The question content is also encrypted and transmitted securely.

[1065] Step 15:

[1066] The server analyzes the user's question, and the generation AI generates an appropriate answer.

[1067] Step 16:

[1068] The emotion engine analyzes the user's emotional state when they ask a question and provides an AI-powered response that matches the user's emotions. For example, it might respond with something like, "Based on the current data, there are no major problems with the growth curve, but please consult a doctor if necessary."

[1069] Step 17:

[1070] The server sends the generated response to the terminal. The response is transmitted quickly.

[1071] Step 18:

[1072] The device displays the received responses to the user. It allows for chat-style communication, resolving the user's questions and concerns.

[1073] Through this process, the present invention can effectively manage childcare data, understand the baby's health status, and provide advice that is sensitive to the parents' emotions, thereby reducing the burden of childcare.

[1074] (Example 2)

[1075] Next, we will describe Example 2. 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."

[1076] Traditional childcare support systems focus solely on inputting, storing, and analyzing childcare data, lacking support that considers user emotions and providing appropriate advice. This makes it difficult to alleviate the stress and anxiety experienced by parents during childcare, and can lead to inconsistent health management of babies. Furthermore, the lack of convenient data input methods such as voice input and the provision of conversational answers to questions highlight the need for improved user experience.

[1077] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1078] In this invention, the server includes means for converting childcare data into text data using a speech recognition engine, means for storing the text data in a database, and means for analyzing the stored childcare data using an analysis engine. This allows users to easily input childcare data via voice input, and enables the data to be effectively stored and analyzed, as well as providing appropriate advice that is sensitive to the user's emotions.

[1079] "Childcare data" refers to information about a baby's childcare, such as the frequency of urination and defecation, milk intake, and sleep duration.

[1080] A "speech recognition engine" is a technology or software that converts spoken audio data from a user into text data.

[1081] "Text data" refers to character information converted by a speech recognition engine.

[1082] A "database" is a digital system for managing and processing stored childcare data.

[1083] An "analysis engine" is a technology or software used to analyze stored childcare data and detect abnormalities or patterns.

[1084] A "generative AI model" is a machine learning algorithm that generates optimal advice based on the results of an analysis engine.

[1085] An "emotion engine" is a technology or software that analyzes a user's emotional data and incorporates it into the generated advice.

[1086] A "user terminal" refers to a device, such as a smartphone or tablet, that a user uses to input childcare data or receive advice.

[1087] A "notification" is an alert or message that conveys generated advice to the user's device.

[1088] This invention relates to a childcare support system that uses a user terminal such as a smartphone or tablet to input childcare data, analyzes and stores that data on a server, generates appropriate advice using a generated AI model, and then provides that advice to the user. Specific embodiments of the system are shown below.

[1089] First, users input childcare data using a device such as a smartphone or tablet. This data includes the number of times the baby urinates and defecates, the amount of milk consumed, and the amount of sleep. Users can use both text and voice input. For example, if a user inputs data using a voice command such as "The baby drank 200ml of milk today," the device uses a speech recognition engine such as the Google Cloud Speech-to-Text API to convert the voice data into text data.

[1090] The terminal sends the converted text data to the server. The server parses the received text data and saves it to a database (e.g., MySQL) to store data such as "200ml" and "2023-10-01 10:00" in the "Milk Intake" field.

[1091] Next, the analysis engine on the server (e.g., a machine learning model using TensorFlow) periodically retrieves and analyzes the stored data. For example, it can detect abnormalities if milk intake is lower than normal or if the frequency of urination decreases.

[1092] Based on the analysis results, the server generates appropriate advice using a generative AI model (e.g., OpenAI's GPT-4). For example, it might suggest, "It would be good to give 220ml of milk next time." Furthermore, the system includes an emotion engine (e.g., Affectiva's emotion recognition API) that analyzes the user's input data and voice tone to identify their emotional state (e.g., stress, joy, fatigue). For example, if the emotion engine determines that the user is stressed, the generative AI model will generate advice with gentle words such as, "It's important to rest and not push yourself too hard."

[1093] The generated advice is sent from the server to the device, and the device notifies the user of the received advice. For example, it might use the smartphone's notification function to display, "It would be good to give 220ml of milk at the next feeding time." If the user opens the application, the advice will be displayed in a chat format, and they can also ask additional questions.

[1094] As a concrete example, if a user enters the question, "Is it a problem if my baby isn't gaining weight?", the server analyzes the received question and uses a generative AI model to generate an appropriate answer. At this time, the user's emotional state is also analyzed by the emotion engine, so an answer that is sensitive to their feelings is provided. For example, an answer such as, "Don't worry too much, let's wait and see until the next checkup," might be generated.

[1095] Example of a prompt:

[1096] Prompt: What should I do if my baby is drinking less milk than usual?

[1097] Advice: If your baby is drinking less milk than usual, you can try giving them a slightly larger amount (220ml) at the next feeding. Also, carefully observe your baby's reactions and feed them without forcing them.

[1098] As described above, the system of the present invention can effectively manage childcare data and provide appropriate advice to parents, thereby reducing the burden of childcare and supporting the health management of babies, as well as providing support that is sensitive to the user's emotions.

[1099] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1100] Step 1:

[1101] Users input childcare data using a smartphone or tablet application. There are two input methods: text input and voice input. For example, when using a voice command such as "The baby drank 200ml of milk today," the user inputs it using voice. The entered voice data is then sent to the device.

[1102] Input: Voice data (Example: "I drank 200ml of milk today")

[1103] Output: Audio data (stored on the device)

[1104] Specific actions:

[1105] 1. The user taps the voice input button in the app.

[1106] 2. The user says, "I drank 200ml of milk today."

[1107] 3. The device records the audio data.

[1108] Step 2:

[1109] The device temporarily stores the input audio data in memory and uses a speech recognition engine (e.g., Google Cloud Speech-to-Text API) to convert the audio data into text data.

[1110] Input: Audio data

[1111] Output: Text data (Example: "I drank 200ml of milk today")

[1112] Specific actions:

[1113] 1. The device calls the Google Cloud Speech-to-Text API.

[1114] 2. The audio data is converted into text data.

[1115] 3. The terminal temporarily saves the converted text data to memory.

[1116] Step 3:

[1117] The terminal sends the converted text data to the server. A timestamp is also added to the text data at this time.

[1118] Input: Text data (Example: "I drank 200ml of milk today")

[1119] Output: Text data (with timestamp, sent to server)

[1120] Specific actions:

[1121] 1. The device adds a timestamp to the text data (e.g., "2023-10-01 10:00").

[1122] 2. The terminal sends text data to the server.

[1123] Step 4:

[1124] The server parses the received text data and converts it into the appropriate data format. It then saves the parsed data to a database (e.g., MySQL).

[1125] Input: Text data (with timestamp)

[1126] Output: Formatted data (saved in database)

[1127] Specific actions:

[1128] 1. The server parses the text data (e.g., converts it to "Milk intake: 200ml, Date and time: 2023-10-01 10:00").

[1129] 2. The server saves the analyzed data to the database.

[1130] Step 5:

[1131] The analysis engine on the server (e.g., a machine learning model using TensorFlow) periodically retrieves and analyzes the stored data. The analysis detects changes in each childcare data item and determines whether or not there are any abnormalities.

[1132] Input: Childcare data stored in the database

[1133] Output: Analysis results (anomaly detection information, pattern information)

[1134] Specific actions:

[1135] 1. The server's analysis engine retrieves data from the database.

[1136] 2. The analysis engine analyzes the data and detects anomalies and patterns.

[1137] 3. The analysis results are stored on the server.

[1138] Step 6:

[1139] Based on the analysis results, the server generates appropriate advice using a generative AI model (e.g., OpenAI's GPT-4). It also analyzes the user's emotional state using an emotion engine (e.g., Affectiva's emotion recognition API) and incorporates this into the advice.

[1140] Input: Analysis results, user sentiment data

[1141] Output: Generated advice

[1142] Specific actions:

[1143] 1. The server calls the generated AI model based on the analysis results.

[1144] 2. The generative AI model generates appropriate advice.

[1145] 3. The emotion engine analyzes the user's emotional state and reflects it in the advice (e.g., "It's important to take a rest and not push yourself too hard").

[1146] Step 7:

[1147] The generated advice is sent from the server to the terminal.

[1148] Input: Generated advice

[1149] Output: Advice (sent to terminal)

[1150] Specific actions:

[1151] 1. The server formats and sends the generated advice to the terminal.

[1152] Step 8:

[1153] The device notifies the user of the advice it receives. For example, it might use the smartphone's notification function to display a message such as, "It would be good to give your baby 220ml of milk at the next feeding time."

[1154] Input: Advice sent from the server

[1155] Output: Advice notified to the user

[1156] Specific actions:

[1157] 1. The device receives the advice and displays an alert using the notification function.

[1158] 2. When the user opens the application, advice is displayed in a chat format.

[1159] Step 9:

[1160] Users can enter and submit questions about childcare data. For example, they might enter and submit a question such as, "Is it a problem if my baby isn't gaining weight?"

[1161] Input: User's question (text data)

[1162] Output: Question data (sent to the server)

[1163] Specific actions:

[1164] 1. The user enters a question within the application.

[1165] 2. The terminal sends the question data to the server.

[1166] Step 10:

[1167] The server analyzes the received question and generates an appropriate answer using an AI model. The emotion engine simultaneously analyzes the user's emotional state and incorporates it into the answer.

[1168] Input: User question data, user sentiment data

[1169] Output: Generated answer

[1170] Specific actions:

[1171] 1. The server analyzes the received question.

[1172] 2. The generative AI model generates an appropriate answer.

[1173] 3. The emotion engine analyzes the user's emotional state and reflects it in the response (e.g., "Don't worry too much, let's wait and see until the next check-up").

[1174] 4. The generated response is sent to the device and the user is notified.

[1175] This allows for a smooth process from inputting childcare data to providing advice and answering user questions.

[1176] (Application Example 2)

[1177] Next, we will explain application example 2. In the following explanation, 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."

[1178] Parents raising young children need to manage detailed data to understand their baby's health and daily routines. However, manually entering and analyzing this data is extremely time-consuming and often stressful. Furthermore, it is difficult to obtain quick and accurate answers to parenting concerns and questions. Moreover, advice that does not take parents' feelings into consideration fails to alleviate their psychological burden. To address these challenges, a system is needed that automates the input, storage, and analysis of parenting data, as well as the generation and presentation of advice, providing appropriate support that is sensitive to parents' emotions.

[1179] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1180] In this invention, the server includes means for inputting childcare data, means for storing the input childcare data in a database, means for analyzing the stored childcare data, means for generating advice based on the analysis results, means for presenting the generated advice, means for analyzing the user's emotions and reflecting the analysis results in the advice generation process, and means for inputting questions into the application and presenting answers in an interactive format. This enables efficient management of childcare data and support that is sensitive to the parents' emotions.

[1181] "Childcare data" refers to data that includes information such as the amount of milk a baby drinks, their sleep duration, and how often their diapers are changed.

[1182] A "database" is a system for systematically storing and managing childcare data.

[1183] "Analysis means" refers to technical means for analyzing stored childcare data to understand the baby's health status and lifestyle patterns.

[1184] An "advice generation method" is a technical means that generates specific instructions and recommendations for parents based on the analysis results.

[1185] "Presentation method" refers to a method or system for informing parents of the generated advice.

[1186] "Emotional analysis methods" are technologies that analyze a user's emotions from their voice and text data and incorporate the analysis results into the advice provided.

[1187] A "dialogue-based approach" is a technical means that provides answers to user questions in a natural, conversational format through an application.

[1188] The "smartphone notification function" is a feature that notifies parents in real time of advice and important information generated on the smartphone.

[1189] This invention is a system that provides efficient management of childcare data and support that is sensitive to the emotions of parents. The system consists of the following elements:

[1190] 1. User's terminal

[1191] Users input baby care data using their smartphones or tablets. This data includes information such as the baby's milk intake, sleep duration, and diaper change frequency. Voice input is also possible; for example, data can be entered using voice commands such as "The baby drank 200ml of milk today." A speech recognition engine (e.g., Google Speech-to-Text API) is used to convert the voice into text data.

[1192] 2. Server

[1193] The input data is temporarily held on the device and then sent to the server. The server uses Node.js, converts the received data into the appropriate format, and stores it in a MongoDB database. The server periodically analyzes the stored data and generates necessary advice. TensorFlow.js is used for data analysis, and based on the analysis results, a generative AI (e.g., OpenAI API) generates advice.

[1194] 3. Emotion analysis

[1195] TensorFlow.js is used to analyze the user's emotions from their voice and input. The results of the emotion analysis are reflected in the prompts sent to the generating AI, resulting in more empathetic advice. For example, if the analysis indicates that the user is stressed, the advice will include gentle words such as, "It's important to take a rest and not push yourself too hard."

[1196] 4. Offering advice

[1197] The generated advice is sent back to the user's device from the server. The advice and important information are then notified in real time using the smartphone's notification function. Therefore, users do not need to frequently check the app and can receive important information at the appropriate time.

[1198] 5. Question and Answer Session in an Dialogue Format

[1199] The application includes a chatbot function, allowing users to input questions about childcare and receive answers in a conversational format. The user's emotional state at the time of questioning is also analyzed, and a corresponding response is provided by the AI.

[1200] Specific example

[1201] For example, if a user enters the question, "Is it a problem if my baby isn't gaining weight?", the emotion analysis engine analyzes the user's stress level and, based on that, generates a gentle response such as, "While consulting with experts is important, every baby grows at their own pace, so please don't worry too much."

[1202] Example of a prompt

[1203] The baby's latest milk intake is 200ml. The parents are feeling stressed. Please advise on the appropriate amount of milk for the next feeding and provide some reassuring advice.

[1204] In this way, the present invention enables efficient management and analysis of childcare data, provides emotionally supportive advice, and reduces the burden on parents during childcare.

[1205] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1206] Step 1:

[1207] The user enters childcare data.

[1208] How it works: The user opens the application on their smartphone and enters childcare data such as the baby's milk intake, sleep duration, and diaper change frequency in text or voice. For voice input, the Google Speech-to-Text API is used to convert the speech to text.

[1209] Input: Milk intake, sleep duration, diaper change frequency

[1210] Output: Childcare data in text format

[1211] Step 2:

[1212] The terminal temporarily stores the entered data and sends it to the server.

[1213] Operation: Data is saved to the device's local storage and sent to a Node.js server in real time. The server receives the data and converts it to the appropriate format.

[1214] Input: Childcare data in text format

[1215] Output: Sending data to the server

[1216] Step 3:

[1217] The server saves the received data to the database.

[1218] Operation: Received data is saved to a MongoDB database. The database stores various data about the baby, along with the date and time.

[1219] Input: Childcare data in text format

[1220] Output: Childcare data stored in the database

[1221] Step 4:

[1222] The server periodically analyzes the stored data.

[1223] Operation: Uses TensorFlow.js to analyze stored data. Detects trends in milk intake and changes in sleep duration to identify anomalies.

[1224] Input: Childcare data stored in the database

[1225] Output: Analysis results (e.g., abnormal milk intake)

[1226] Step 5:

[1227] The server generates advice based on the analysis results.

[1228] Operation: Sends analysis results to the OpenAI API and generates appropriate advice using the generated AI model. Creates prompt messages and sends them to the AI.

[1229] Input: Analysis results

[1230] Output: Generated advice (text format)

[1231] Step 6:

[1232] The server notifies the smartphone of the generated advice.

[1233] Operation: Generated advice is sent to the device and the parent is notified using the smartphone's notification function.

[1234] Input: Generated advice

[1235] Output: Notification to smartphone

[1236] Step 7:

[1237] It analyzes emotions based on user input data and voice.

[1238] Operation: Uses TensorFlow.js to analyze the user's emotional state from speech and text. Reflects the analysis results in prompts and sends them to the generating AI.

[1239] Input: User's voice or text

[1240] Output: Emotion analysis results

[1241] Step 8:

[1242] Generates emotion-based advice.

[1243] Operation: Incorporates user sentiment analysis results into prompts and generates emotion-responsive advice using the OpenAI API.

[1244] Input: Sentiment analysis results, prompt text

[1245] Output: Emotional response advice (text format)

[1246] Step 9:

[1247] It accepts user questions and provides answers in a conversational format.

[1248] Operation: Uses the application's chatbot function to receive questions from users about childcare. Generates prompts, including sentiment analysis, and creates answers using the OpenAI API.

[1249] Input: User's question (text format), sentiment analysis results

[1250] Output: Dialogue-style response (text format)

[1251] In this way, the present invention functions as a system that provides efficient management of childcare data and support that is sensitive to the emotions of parents.

[1252] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1253] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1254] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1255] [Fourth Embodiment]

[1256] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1257] As shown in Figure 7, the 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.

[1258] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1259] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1260] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1261] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1262] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1263] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1264] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1265] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1266] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1267] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1268] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1269] This invention is a childcare support system that assists parents through the management and analysis of childcare data. This system consists of a series of processes that input, store, and analyze childcare data and provide appropriate advice.

[1270] Users input childcare data using devices such as smartphones and tablets. This data includes the number of times the baby urinates and defecates, the amount of milk consumed, and the amount of sleep. Users can input data not only by text but also by voice. For example, they can use voice commands such as "The baby drank 200ml of milk today" or "The baby slept for 2 hours."

[1271] The terminal temporarily stores the input data (including voice data), and in the case of voice input, it uses a speech recognition engine to convert the voice data into text data. It then sends the converted text data to the server.

[1272] The server parses the received text data and converts it into the appropriate data format. It then stores this data in a database. For example, it might store data such as "200ml" and "2023-10-01 10:00" in the "Milk Intake" table of the database.

[1273] The analysis engine on the server periodically retrieves and analyzes the stored data. The analysis engine uses machine learning algorithms to analyze the data and understand the baby's health status and lifestyle patterns. For example, it detects abnormalities if the amount of milk consumed is less than usual or if the frequency of urination decreases.

[1274] Based on the analysis, the generating AI produces appropriate advice. This advice includes specific instructions such as, "It's best to give 220ml of milk next time," or "The baby is sleeping longer than usual, so wake them up occasionally."

[1275] The generated advice is sent from the server to the device. The device notifies the user of the received advice. When the user opens the application, the advice is displayed in a chat format. This allows parents to receive important information without having to frequently check the app.

[1276] Furthermore, users can input and submit questions about childcare data into their devices. The server analyzes the user's questions, and a generating AI produces appropriate answers. For example, if a user asks, "Is it a problem that my baby isn't gaining weight?", the generating AI will produce an answer such as, "Based on the current data, there doesn't seem to be a major problem with the growth curve. However, please consult a doctor if necessary," and send this to the device.

[1277] In this way, the system of the present invention can effectively manage childcare data and provide appropriate advice to parents, thereby reducing the burden of childcare and supporting the health management of babies.

[1278] The following describes the processing flow.

[1279] Step 1:

[1280] Users input childcare data through applications on their smartphones or tablets. For voice input, they use voice commands such as "The baby peed" or "The baby drank 200ml of milk."

[1281] Step 2:

[1282] The device temporarily stores the voice data entered by the user. In the case of voice input, the speech recognition engine within the device converts the voice data into text data. In this step, the speech recognition model analyzes the voice and converts it into appropriate text.

[1283] Step 3:

[1284] The terminal sends the converted text data to the server. HTTP or HTTPS is used as the communication protocol, and the data is encrypted to ensure security.

[1285] Step 4:

[1286] The server receives the text data and converts it into the appropriate data format. For example, it converts data such as "The baby slept for 2 hours" to correspond to the "Sleep Time" field.

[1287] Step 5:

[1288] The server saves the converted data to a database. During this process, it records the data in the appropriate table depending on the type of data (milk intake, sleep duration, urine, feces, etc.).

[1289] Step 6:

[1290] The server periodically retrieves childcare data stored in the database and sends it to the analysis engine. Scheduled tasks are often used for this step.

[1291] Step 7:

[1292] The analysis engine uses machine learning algorithms to analyze stored data and understand the baby's health status and lifestyle patterns. For example, it can detect abnormalities if the baby is drinking less milk than usual or urinating less frequently.

[1293] Step 8:

[1294] The AI ​​generates appropriate advice based on the analysis results. The content of the advice is customized according to the analysis results. For example, it may generate specific instructions such as, "It would be good to give 220ml of milk next time."

[1295] Step 9:

[1296] The server sends the generated advice to the device. Real-time notification technologies (e.g., push notifications) are used for this transmission.

[1297] Step 10:

[1298] The device receives advice and notifies the user. When the user opens the application, the advice is displayed in a chat format. This allows the user to receive important information without having to frequently check the app.

[1299] Step 11:

[1300] Users can also enter and submit further questions about childcare data on their device. For example, they might ask, "Is it a problem if my baby isn't gaining weight?"

[1301] Step 12:

[1302] The terminal sends the user's question to the server. The content of the question is also encrypted and transmitted securely.

[1303] Step 13:

[1304] The server analyzes the user's question, and the AI ​​generates an appropriate answer. For example, it might generate an answer such as, "Based on the current data, there don't seem to be any major problems with the growth curve, but please consult a doctor if necessary."

[1305] Step 14:

[1306] The server sends the generated response to the terminal. Since real-time response is required, the data is transferred quickly.

[1307] Step 15:

[1308] The device displays the received responses to the user. It allows for chat-style communication, resolving the user's questions and concerns.

[1309] (Example 1)

[1310] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1311] In modern parenting, manually managing parenting data is cumbersome for parents, making it difficult to continuously collect and analyze data to receive appropriate advice. Furthermore, there are limited means of obtaining quick and accurate answers to parenting questions. This leads to difficulties in receiving appropriate parenting support, increasing the burden of childcare.

[1312] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1313] In this invention, the server includes means for inputting childcare data, means for temporarily holding the input childcare data and analyzing it as needed, means for storing the analyzed data in a database, means for periodically analyzing the stored childcare data and detecting anomalies or specific patterns, a generative AI model that generates advice based on the analysis results, and means for presenting the generated advice. This enables efficient management of childcare data, continuous analysis, and the provision of appropriate advice.

[1314] "Childcare data" refers to records of a baby's health and lifestyle patterns, specifically including the number of times they urinate and defecate, the amount of milk they consume, and their sleep duration.

[1315] "Input method" refers to the interface that allows users to input childcare data using electronic devices such as smartphones and tablets, and enables both text input and voice input.

[1316] "Means for temporarily storing and analyzing as needed" refers to a device or software that has the function of temporarily storing childcare data entered by the user and performing initial analysis, such as converting audio data into text.

[1317] "Means of storing in a database" refers to a system or software for long-term storage of received and analyzed childcare data, such as a relational database management system (RDBMS).

[1318] "Means for periodically analyzing and detecting anomalies or specific patterns" refers to software or systems that periodically retrieve and analyze stored childcare data to detect anomalies or patterns. Specifically, this includes machine learning algorithms and analysis engines.

[1319] A "generative AI model" is an artificial intelligence model that generates appropriate advice based on analyzed childcare data, and it operates using natural language processing and machine learning technologies.

[1320] The "means of presentation" refer to an interface for informing users of the generated advice and answers, and it has the function of displaying them in a chat format through a smartphone or tablet application.

[1321] Modes for carrying out the invention

[1322] This invention is a childcare support system that assists parents through the management and analysis of childcare data. This system consists of a series of processes that input, store, and analyze childcare data and provide appropriate advice.

[1323] Input methods for childcare data

[1324] Users input childcare data using devices such as smartphones and tablets. This data includes the number of times the baby urinates and defecates, the amount of milk consumed, and the amount of sleep. Users can input data not only by text but also by voice. For example, users can use voice commands such as "The baby drank 200ml of milk today" or "The baby slept for 2 hours."

[1325] Audio data conversion

[1326] The device temporarily stores the input data (including voice data) and, in the case of voice input, uses a speech recognition engine to convert the voice data into text data. Specifically, it uses the Google Speech Recognition API. For example, the voice data "The baby slept for 2 hours" is converted into the text data "The baby slept for 2 hours".

[1327] Sending data

[1328] The device sends the converted text data to the server. This transmission uses the HTTPS protocol. For example, the data "I drank 200ml of milk" is sent to the server.

[1329] Data storage

[1330] The server parses the received text data and converts it into the appropriate data format. This data is then stored in a database. MySQL is used for the database. For example, the "Milk Intake" table in the database stores data such as "200ml" and "2023-10-01 10:00".

[1331] Data analysis

[1332] The analysis engine on the server periodically retrieves and analyzes the stored data. The analysis engine utilizes TensorFlow and employs machine learning algorithms to analyze the data. For example, it detects abnormalities if milk intake is lower than normal or if the frequency of urination decreases.

[1333] Generating advice

[1334] Based on the analysis, the AI ​​model generates appropriate advice. This advice includes specific instructions such as, "It's best to give 220ml of milk next time," or "The baby has been sleeping longer than usual, so please wake them up occasionally." The generated advice is sent from the server to the terminal.

[1335] Offering advice

[1336] The device notifies the user of any advice received. When the user opens the application, the advice is displayed in a chat format. This allows the user to receive important information without having to frequently check the app.

[1337] Questions and Answers

[1338] Furthermore, users can input and submit questions about childcare data on their devices. The server analyzes the user's questions, and a generative AI model generates appropriate answers. For example, if a user asks, "Is it a problem that my baby isn't gaining weight?", the generative AI model will generate an answer such as, "Based on the current data, there doesn't seem to be a major problem with the growth curve. However, please consult a doctor if necessary," and send this to the device.

[1339] Example of a prompt

[1340] An example of a prompt message is, "What advice should I give if my baby's milk intake is lower than normal?" In this way, the system of the present invention can effectively manage childcare data and provide appropriate advice to parents, thereby reducing the burden of childcare and supporting the health management of babies.

[1341] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1342] Step 1:

[1343] The user enters childcare data.

[1344] Users input childcare data (e.g., the number of times the baby urinates and defecates, the amount of milk consumed, sleep duration, etc.) using their smartphones or tablets. Both text and voice input are available. For example, users can use voice commands such as "The baby drank 200ml of milk today" or "The baby slept for 2 hours."

[1345] Step 2:

[1346] The device temporarily stores childcare data and converts any audio data into text data.

[1347] Input: Voice or text data entered by the user.

[1348] The device temporarily stores the input data in memory. In the case of voice input, the device uses its built-in speech recognition engine (such as Google Speech Recognition API) to convert the voice into text data. For example, the voice data "The baby slept for two hours" is converted into the text data "The baby slept for two hours".

[1349] Output: Converted text data.

[1350] Step 3:

[1351] The terminal sends the converted data to the server using the HTTPS protocol.

[1352] Input: Childcare data converted to text.

[1353] The device sends the converted text data to the server. For example, it sends the data "I drank 200ml of milk" to the server.

[1354] Output: Text data sent to the server.

[1355] Step 4:

[1356] The server receives the data, parses it, converts it to the appropriate data format, and then stores it in the database.

[1357] Input: Text data sent to the server.

[1358] The server analyzes the received data and converts it into an appropriate data format, such as "Milk Intake" and "2023-10-01 10:00". This data is then saved to a database (such as MySQL). For example, it might be saved in the "Milk Intake" table of the database as "200ml" and "2023-10-01 10:00".

[1359] Output: Data stored in the database.

[1360] Step 5:

[1361] The server periodically retrieves and analyzes the stored data to detect anomalies or specific patterns.

[1362] Input: Childcare data stored in the database.

[1363] The server's analysis engine (such as TensorFlow) periodically retrieves and analyzes the stored data. Using machine learning algorithms, it analyzes the data to detect anomalies and specific patterns, such as when milk intake is lower than normal or when the frequency of urination decreases.

[1364] Output: Analysis results (data anomalies or specific patterns).

[1365] Step 6:

[1366] The AI ​​generates advice based on the analysis results, and the server sends it to the terminal.

[1367] Input: Analysis results.

[1368] The AI ​​model generates appropriate advice based on the analysis results. For example, it includes specific instructions such as, "It's best to give 220ml of milk next time," or "The baby is sleeping longer than usual, so wake them up occasionally." The generated advice is sent from the server to the terminal.

[1369] Output: Advice sent to the terminal.

[1370] Step 7:

[1371] The device notifies the user with advice.

[1372] Input: Advice sent from the server.

[1373] The device notifies the user of any advice it receives. If the application is open, the advice is displayed in a chat format. For example, a notification might say, "It's best to give 220ml of milk next time."

[1374] Output: Advice displayed to the user.

[1375] Step 8:

[1376] The user enters questions about childcare data, the server analyzes the data, generates answers, and sends them to the device.

[1377] Input: Question from the user.

[1378] The user enters questions about childcare data into their device and sends them to the server. The server analyzes the received questions and generates appropriate answers using a generative AI model (such as GPT-4). For example, in response to the question, "Is it a problem if my baby's weight isn't increasing?", the server generates the answer, "Based on the current data, there doesn't seem to be a major problem with the growth curve. However, please consult a doctor if necessary," and sends this answer to the device.

[1379] Output: The response sent to the terminal.

[1380] (Application Example 1)

[1381] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1382] In childcare, parents are required to constantly monitor their baby's health and daily routines and respond appropriately. However, it is difficult to efficiently input childcare data without much effort and to receive appropriate advice based on that data in real time. Furthermore, conventional systems often require frequent use of smartphones or tablets, which can be a significant burden for parents.

[1383] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1384] In this invention, the server includes means for inputting childcare data using speech recognition, means for transmitting text data generated based on speech recognition to the server, and means for displaying advice received from the server on a next-generation display device. This streamlines the input of childcare data and enables the receipt of appropriate advice in real time via speech input and a next-generation display device.

[1385] - "Childcare data" refers to information related to the baby's health and lifestyle patterns. Specifically, this includes the frequency of urination and bowel movements, milk intake, and sleep duration.

[1386] "Speech recognition" refers to a technology that acquires speech data and converts it into text data. By analyzing information that users input verbally, it can reduce the effort required for manual data entry.

[1387] "Next-generation display devices" refer to devices that utilize mobile display technology, such as smart glasses. This allows users to receive information visually in real time.

[1388] "Advice" refers to specific instructions and suggestions generated based on the analysis of childcare data. This allows parents to manage their baby's health and reduce the burden of childcare.

[1389] A "server" refers to a computer system that stores, analyzes, and provides generated advice over a network. The server's role is to analyze data sent by users, generate appropriate advice, and send it to the user's device.

[1390] A "database" is a system for efficiently storing and managing childcare data. The stored data is later used for analysis.

[1391] "Voice input" is a method of inputting data as voice using a device such as a microphone. This eliminates the need for users to manually enter childcare data.

[1392] "Real-time" refers to a situation where the delay between entering data and receiving results is extremely short. This allows users to receive advice quickly.

[1393] A "dialogue format" is a method where questions and answers are presented as a series of exchanges. This is convenient when parents are entering questions related to childcare.

[1394] This invention is a childcare support system that assists parents through the management and analysis of childcare data. This system allows users to efficiently input childcare data and receive appropriate advice based on that data in real time.

[1395] Users input childcare data using next-generation display devices such as smart glasses or tablets. This data is entered via voice input, allowing them to use voice commands such as "The baby slept for 2 hours" or "The baby drank 200ml of milk." The voice input is converted into text data using a speech recognition system.

[1396] The converted text data is sent to a server via the internet. The server analyzes the received data and converts it into the appropriate data format. This data is then stored in a database. For example, the "Milk Intake" table will store data such as "200ml" and "2023-10-01 10:00".

[1397] The analysis engine on the server periodically retrieves and analyzes stored data. The analysis is performed using machine learning algorithms to understand the baby's health status and lifestyle patterns. For example, it detects abnormalities if the amount of milk consumed is less than usual or if the frequency of urination decreases.

[1398] Based on the analysis results, the AI ​​generates appropriate advice. Examples of advice include specific instructions such as "It's best to give 220ml of milk next time" or "The baby has slept longer than usual, so please wake them up occasionally." The generated advice is sent from the server to the user's device and displayed on the screen of a next-generation display device. This allows users to receive important information in real time without having to frequently check their device.

[1399] Furthermore, users can input and submit questions about childcare data via voice. The server receives the questions, analyzes them, and a generating AI produces appropriate answers. For example, if a user asks, "Is it a problem that my baby isn't gaining weight?", the generating AI will produce an answer such as, "Based on the current data, there doesn't seem to be a major problem with the growth curve. However, please consult a doctor if necessary," and send this to the user's device.

[1400] The following is an example of a prompt message:

[1401] "If the user inputs 'The baby has slept for two hours' via voice, it is converted to text and sent to the server. The server analyzes the data and generates advice such as, 'The baby has slept longer than usual, so please wake them up for a while,' which is then displayed on the smart glasses' screen."

[1402] This system utilizes a speech recognition system, generative AI, machine learning models, and a database, and the hardware used includes smart glasses, tablets, and servers. The software employs speech recognition libraries and machine learning algorithms. Combining these elements enables efficient management of childcare data and the provision of appropriate advice.

[1403] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1404] Step 1:

[1405] The user wears a next-generation display device (such as smart glasses) and inputs childcare data by voice. For example, they can voice-input "The baby slept for two hours." This voice input is captured via the device's microphone.

[1406] Input: Audio data

[1407] Output: Audio data

[1408] Step 2:

[1409] The device converts voice input into text data using a speech recognition system. For example, the voice input "The baby slept for two hours" is converted into the text data "The baby slept for two hours."

[1410] Input: Audio data

[1411] Output: Text data

[1412] Step 3:

[1413] The converted text data is sent to the server via the internet. The server receives this text data and stores it in a database. For example, data such as "2 hours" and "2023-10-01 10:00" will be stored in the "Sleep Time" table.

[1414] Input: Text data

[1415] Output: Saved data

[1416] Step 4:

[1417] The analysis engine on the server periodically retrieves and analyzes the stored data. The analysis engine uses machine learning algorithms to understand the baby's health status and lifestyle patterns. For example, it can detect characteristics such as "the baby is sleeping for longer periods than usual."

[1418] Input: Saved data

[1419] Output: Analysis results

[1420] Step 5:

[1421] Based on the analysis results, the generating AI produces appropriate advice. For example, the generating AI might produce specific instructions such as, "The baby is sleeping longer than usual, so please wake him up at an appropriate time."

[1422] Input: Analysis results

[1423] Output: Generated advice

[1424] Step 6:

[1425] The server sends the generated advice to the user's device. The device displays the received advice on a next-generation display device. This allows the user to receive advice in real time through smart glasses.

[1426] Input: Generated advice

[1427] Output: Advice displayed on the screen

[1428] Step 7:

[1429] Furthermore, users can input questions about childcare data using voice input. These questions are converted into text data by a voice recognition system and sent to the server. The server analyzes the questions, and a generation AI generates appropriate answers.

[1430] Input: Audio data (question), Text data (question)

[1431] Output: Analysis results, generated answers

[1432] Step 8:

[1433] The server sends the generated answers to the user's device. The device displays the received answers on a next-generation display device. This allows the user to receive answers to questions about childcare in real time.

[1434] Input: Generated answer

[1435] Output: Answer displayed on the screen

[1436] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1437] This invention is a childcare support system that assists parents through the management and analysis of childcare data. This system consists of a series of processes that input, store, and analyze childcare data, and generate and present appropriate advice. Furthermore, this invention provides support that is tailored to the user's emotions by incorporating an emotion engine that recognizes the user's emotions and reflects that emotion data in the advice generation process.

[1438] Users input childcare data using devices such as smartphones and tablets. This data includes the number of times the baby urinates and defecates, the amount of milk consumed, and the amount of sleep. In addition to text input, users can also input data using voice input. For example, they can use voice commands such as "The baby drank 200ml of milk today" or "The baby slept for 2 hours."

[1439] The terminal temporarily stores the input data (including voice data), and in the case of voice input, it uses a speech recognition engine to convert the voice data into text data. The converted text data is then sent to the server.

[1440] The server parses the received text data and converts it into the appropriate data format. This data is then stored in the database. For example, the "Milk Intake" field in the database will store data such as "200ml" and "2023-10-01 10:00".

[1441] The analysis engine on the server periodically retrieves and analyzes the stored data. The analysis engine uses machine learning algorithms to analyze the data and understand the baby's health status and lifestyle patterns. For example, it can detect abnormalities if the amount of milk consumed is less than usual or if the frequency of urination decreases.

[1442] Based on the analysis results, the AI ​​generates appropriate advice. For example, it might suggest giving 220ml of milk next time, or wake the baby up as they are sleeping longer than usual.

[1443] Furthermore, the system includes an emotion engine that recognizes emotions from the user's voice and input. The emotion engine analyzes the user's input data and voice tone to identify the user's emotional state (e.g., stress, joy, fatigue).

[1444] The emotional information of the user, recognized by the emotion engine, is reflected in the advice generation process by the generative AI. For example, if the emotion engine determines that the user is feeling stressed, the generative AI will generate advice that includes gentle words such as, "It's important to take a rest and not push yourself too hard."

[1445] The generated advice is sent from the server to the device. The device notifies the user of the received advice. When the user opens the application, the advice is displayed in a chat format. This allows the user to receive important information without having to frequently check the app.

[1446] Furthermore, users can input and submit questions about childcare data on their device. For example, they might ask, "Is it a problem if my baby isn't gaining weight?" The emotion engine also analyzes the user's emotional state when they ask the question, and the AI ​​generates an answer that is tailored to that emotional state.

[1447] In this way, the system of the present invention can effectively manage childcare data and provide appropriate advice to parents, thereby reducing the burden of childcare and supporting the health management of babies, as well as providing support that is sensitive to the user's emotions.

[1448] The following describes the processing flow.

[1449] Step 1:

[1450] Users input childcare data using a smartphone or tablet application. When using the voice input function, they might say things like, "The baby pooped," or "The baby drank 200ml of milk."

[1451] Step 2:

[1452] The device temporarily stores voice and text input data from the user. In the case of voice input, the voice data is analyzed by a speech recognition engine and converted into text data.

[1453] Step 3:

[1454] The terminal sends the converted text data to the server. The communication protocol used is either HTTP or HTTPS, and the data is encrypted.

[1455] Step 4:

[1456] The server parses the received text data and converts it into the appropriate data format. This data is then stored in the database. For example, data such as "The baby slept for 2 hours" is converted to a format corresponding to the "sleep time" field and recorded.

[1457] Step 5:

[1458] The server periodically retrieves childcare data from the database and sends it to the analysis engine. A scheduled task is used to execute the process at regular intervals.

[1459] Step 6:

[1460] The analysis engine uses machine learning algorithms to analyze stored childcare data and understand the baby's health status and lifestyle patterns. For example, it can detect abnormalities if the baby is drinking less milk than usual or if the frequency of urination decreases.

[1461] Step 7:

[1462] The analysis engine sends information about the baby's health status to the AI ​​based on the analysis results.

[1463] Step 8:

[1464] The AI ​​generates appropriate advice based on the analysis results. For example, it can generate specific instructions such as, "It would be good to give 220ml of milk next time," or "The baby is sleeping longer than usual, so wake them up at a moderate time."

[1465] Step 9:

[1466] The emotion engine analyzes the user's voice and input to identify their emotional state (e.g., stress, joy, fatigue). For example, it might determine that a user is stressed based on their tone of voice and word choice.

[1467] Step 10:

[1468] The generating AI adjusts the content of its advice based on emotional information from the emotion engine. For example, if it determines that the user is feeling stressed, it will add gentle words such as, "It's important to take a rest and not push yourself too hard."

[1469] Step 11:

[1470] The server sends the generated advice to the device. Real-time notification technologies such as push notifications are used.

[1471] Step 12:

[1472] The device receives advice and notifies the user. If the user opens the application, the advice is displayed in a chat format.

[1473] Step 13:

[1474] Users can also input and submit further questions about childcare data on their device. For example, they might ask, "Is it a problem if my baby isn't gaining weight?"

[1475] Step 14:

[1476] The terminal sends the user's question to the server. The question content is also encrypted and transmitted securely.

[1477] Step 15:

[1478] The server analyzes the user's question, and the generation AI generates an appropriate answer.

[1479] Step 16:

[1480] The emotion engine analyzes the user's emotional state when they ask a question and provides an AI-powered response that matches the user's emotions. For example, it might respond with something like, "Based on the current data, there are no major problems with the growth curve, but please consult a doctor if necessary."

[1481] Step 17:

[1482] The server sends the generated response to the terminal. The response is transmitted quickly.

[1483] Step 18:

[1484] The device displays the received responses to the user. It allows for chat-style communication, resolving the user's questions and concerns.

[1485] Through this process, the present invention can effectively manage childcare data, understand the baby's health status, and provide advice that is sensitive to the parents' emotions, thereby reducing the burden of childcare.

[1486] (Example 2)

[1487] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1488] Traditional childcare support systems focus solely on inputting, storing, and analyzing childcare data, lacking support that considers user emotions and providing appropriate advice. This makes it difficult to alleviate the stress and anxiety experienced by parents during childcare, and can lead to inconsistent health management of babies. Furthermore, the lack of convenient data input methods such as voice input and the provision of conversational answers to questions highlight the need for improved user experience.

[1489] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1490] In this invention, the server includes means for converting childcare data into text data using a speech recognition engine, means for storing the text data in a database, and means for analyzing the stored childcare data using an analysis engine. This allows users to easily input childcare data via voice input, and enables the data to be effectively stored and analyzed, as well as providing appropriate advice that is sensitive to the user's emotions.

[1491] "Childcare data" refers to information about a baby's childcare, such as the frequency of urination and defecation, milk intake, and sleep duration.

[1492] A "speech recognition engine" is a technology or software that converts spoken audio data from a user into text data.

[1493] "Text data" refers to character information converted by a speech recognition engine.

[1494] A "database" is a digital system for managing and processing stored childcare data.

[1495] An "analysis engine" is a technology or software used to analyze stored childcare data and detect abnormalities or patterns.

[1496] A "generative AI model" is a machine learning algorithm that generates optimal advice based on the results of an analysis engine.

[1497] An "emotion engine" is a technology or software that analyzes a user's emotional data and incorporates it into the generated advice.

[1498] A "user terminal" refers to a device, such as a smartphone or tablet, that a user uses to input childcare data or receive advice.

[1499] A "notification" is an alert or message that conveys generated advice to the user's device.

[1500] This invention relates to a childcare support system that uses a user terminal such as a smartphone or tablet to input childcare data, analyzes and stores that data on a server, generates appropriate advice using a generated AI model, and then provides that advice to the user. Specific embodiments of the system are shown below.

[1501] First, users input childcare data using a device such as a smartphone or tablet. This data includes the number of times the baby urinates and defecates, the amount of milk consumed, and the amount of sleep. Users can use both text and voice input. For example, if a user inputs data using a voice command such as "The baby drank 200ml of milk today," the device uses a speech recognition engine such as the Google Cloud Speech-to-Text API to convert the voice data into text data.

[1502] The terminal sends the converted text data to the server. The server parses the received text data and saves it to a database (e.g., MySQL) to store data such as "200ml" and "2023-10-01 10:00" in the "Milk Intake" field.

[1503] Next, the analysis engine on the server (e.g., a machine learning model using TensorFlow) periodically retrieves and analyzes the stored data. For example, it can detect abnormalities if milk intake is lower than normal or if the frequency of urination decreases.

[1504] Based on the analysis results, the server generates appropriate advice using a generative AI model (e.g., OpenAI's GPT-4). For example, it might suggest, "It would be good to give 220ml of milk next time." Furthermore, the system includes an emotion engine (e.g., Affectiva's emotion recognition API) that analyzes the user's input data and voice tone to identify their emotional state (e.g., stress, joy, fatigue). For example, if the emotion engine determines that the user is stressed, the generative AI model will generate advice with gentle words such as, "It's important to rest and not push yourself too hard."

[1505] The generated advice is sent from the server to the device, and the device notifies the user of the received advice. For example, it might use the smartphone's notification function to display, "It would be good to give 220ml of milk at the next feeding time." If the user opens the application, the advice will be displayed in a chat format, and they can also ask additional questions.

[1506] As a concrete example, if a user enters the question, "Is it a problem if my baby isn't gaining weight?", the server analyzes the received question and uses a generative AI model to generate an appropriate answer. At this time, the user's emotional state is also analyzed by the emotion engine, so an answer that is sensitive to their feelings is provided. For example, an answer such as, "Don't worry too much, let's wait and see until the next checkup," might be generated.

[1507] Example of a prompt:

[1508] Prompt: What should I do if my baby is drinking less milk than usual?

[1509] Advice: If your baby is drinking less milk than usual, you can try giving them a slightly larger amount (220ml) at the next feeding. Also, carefully observe your baby's reactions and feed them without forcing them.

[1510] As described above, the system of the present invention can effectively manage childcare data and provide appropriate advice to parents, thereby reducing the burden of childcare and supporting the health management of babies, as well as providing support that is sensitive to the user's emotions.

[1511] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1512] Step 1:

[1513] Users input childcare data using a smartphone or tablet application. There are two input methods: text input and voice input. For example, when using a voice command such as "The baby drank 200ml of milk today," the user inputs it using voice. The entered voice data is then sent to the device.

[1514] Input: Voice data (Example: "I drank 200ml of milk today")

[1515] Output: Audio data (stored on the device)

[1516] Specific actions:

[1517] 1. The user taps the voice input button in the app.

[1518] 2. The user says, "I drank 200ml of milk today."

[1519] 3. The device records the audio data.

[1520] Step 2:

[1521] The device temporarily stores the input audio data in memory and uses a speech recognition engine (e.g., Google Cloud Speech-to-Text API) to convert the audio data into text data.

[1522] Input: Audio data

[1523] Output: Text data (Example: "I drank 200ml of milk today")

[1524] Specific actions:

[1525] 1. The device calls the Google Cloud Speech-to-Text API.

[1526] 2. The audio data is converted into text data.

[1527] 3. The terminal temporarily saves the converted text data to memory.

[1528] Step 3:

[1529] The terminal sends the converted text data to the server. A timestamp is also added to the text data at this time.

[1530] Input: Text data (Example: "I drank 200ml of milk today")

[1531] Output: Text data (with timestamp, sent to server)

[1532] Specific actions:

[1533] 1. The device adds a timestamp to the text data (e.g., "2023-10-01 10:00").

[1534] 2. The terminal sends text data to the server.

[1535] Step 4:

[1536] The server parses the received text data and converts it into the appropriate data format. It then saves the parsed data to a database (e.g., MySQL).

[1537] Input: Text data (with timestamp)

[1538] Output: Formatted data (saved in database)

[1539] Specific actions:

[1540] 1. The server parses the text data (e.g., converts it to "Milk intake: 200ml, Date and time: 2023-10-01 10:00").

[1541] 2. The server saves the analyzed data to the database.

[1542] Step 5:

[1543] The analysis engine on the server (e.g., a machine learning model using TensorFlow) periodically retrieves and analyzes the stored data. The analysis detects changes in each childcare data item and determines whether or not there are any abnormalities.

[1544] Input: Childcare data stored in the database

[1545] Output: Analysis results (anomaly detection information, pattern information)

[1546] Specific actions:

[1547] 1. The server's analysis engine retrieves data from the database.

[1548] 2. The analysis engine analyzes the data and detects anomalies and patterns.

[1549] 3. The analysis results are stored on the server.

[1550] Step 6:

[1551] Based on the analysis results, the server generates appropriate advice using a generative AI model (e.g., OpenAI's GPT-4). It also analyzes the user's emotional state using an emotion engine (e.g., Affectiva's emotion recognition API) and incorporates this into the advice.

[1552] Input: Analysis results, user sentiment data

[1553] Output: Generated advice

[1554] Specific actions:

[1555] 1. The server calls the generated AI model based on the analysis results.

[1556] 2. The generative AI model generates appropriate advice.

[1557] 3. The emotion engine analyzes the user's emotional state and reflects it in the advice (e.g., "It's important to take a rest and not push yourself too hard").

[1558] Step 7:

[1559] The generated advice is sent from the server to the terminal.

[1560] Input: Generated advice

[1561] Output: Advice (sent to terminal)

[1562] Specific actions:

[1563] 1. The server formats and sends the generated advice to the terminal.

[1564] Step 8:

[1565] The device notifies the user of the advice it receives. For example, it might use the smartphone's notification function to display a message such as, "It would be good to give your baby 220ml of milk at the next feeding time."

[1566] Input: Advice sent from the server

[1567] Output: Advice notified to the user

[1568] Specific actions:

[1569] 1. The device receives the advice and displays an alert using the notification function.

[1570] 2. When the user opens the application, advice is displayed in a chat format.

[1571] Step 9:

[1572] Users can enter and submit questions about childcare data. For example, they might enter and submit a question such as, "Is it a problem if my baby isn't gaining weight?"

[1573] Input: User's question (text data)

[1574] Output: Question data (sent to the server)

[1575] Specific actions:

[1576] 1. The user enters a question within the application.

[1577] 2. The terminal sends the question data to the server.

[1578] Step 10:

[1579] The server analyzes the received question and generates an appropriate answer using an AI model. The emotion engine simultaneously analyzes the user's emotional state and incorporates it into the answer.

[1580] Input: User question data, user sentiment data

[1581] Output: Generated answer

[1582] Specific actions:

[1583] 1. The server analyzes the received question.

[1584] 2. The generative AI model generates an appropriate answer.

[1585] 3. The emotion engine analyzes the user's emotional state and reflects it in the response (e.g., "Don't worry too much, let's wait and see until the next check-up").

[1586] 4. The generated response is sent to the device and the user is notified.

[1587] This allows for a smooth process from inputting childcare data to providing advice and answering user questions.

[1588] (Application Example 2)

[1589] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1590] Parents raising young children need to manage detailed data to understand their baby's health and daily routines. However, manually entering and analyzing this data is extremely time-consuming and often stressful. Furthermore, it is difficult to obtain quick and accurate answers to parenting concerns and questions. Moreover, advice that does not take parents' feelings into consideration fails to alleviate their psychological burden. To address these challenges, a system is needed that automates the input, storage, and analysis of parenting data, as well as the generation and presentation of advice, providing appropriate support that is sensitive to parents' emotions.

[1591] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1592] In this invention, the server includes means for inputting childcare data, means for storing the input childcare data in a database, means for analyzing the stored childcare data, means for generating advice based on the analysis results, means for presenting the generated advice, means for analyzing the user's emotions and reflecting the analysis results in the advice generation process, and means for inputting questions into the application and presenting answers in an interactive format. This enables efficient management of childcare data and support that is sensitive to the parents' emotions.

[1593] "Childcare data" refers to data that includes information such as the amount of milk a baby drinks, their sleep duration, and how often their diapers are changed.

[1594] A "database" is a system for systematically storing and managing childcare data.

[1595] "Analysis means" refers to technical means for analyzing stored childcare data to understand the baby's health status and lifestyle patterns.

[1596] An "advice generation method" is a technical means that generates specific instructions and recommendations for parents based on the analysis results.

[1597] "Presentation method" refers to a method or system for informing parents of the generated advice.

[1598] "Emotional analysis methods" are technologies that analyze a user's emotions from their voice and text data and incorporate the analysis results into the advice provided.

[1599] A "dialogue-based approach" is a technical means that provides answers to user questions in a natural, conversational format through an application.

[1600] The "smartphone notification function" is a feature that notifies parents in real time of advice and important information generated on the smartphone.

[1601] This invention is a system that provides efficient management of childcare data and support that is sensitive to the emotions of parents. The system consists of the following elements:

[1602] 1. User's terminal

[1603] Users input baby care data using their smartphones or tablets. This data includes information such as the baby's milk intake, sleep duration, and diaper change frequency. Voice input is also possible; for example, data can be entered using voice commands such as "The baby drank 200ml of milk today." A speech recognition engine (e.g., Google Speech-to-Text API) is used to convert the voice into text data.

[1604] 2. Server

[1605] The input data is temporarily held on the device and then sent to the server. The server uses Node.js, converts the received data into the appropriate format, and stores it in a MongoDB database. The server periodically analyzes the stored data and generates necessary advice. TensorFlow.js is used for data analysis, and based on the analysis results, a generative AI (e.g., OpenAI API) generates advice.

[1606] 3. Emotion analysis

[1607] TensorFlow.js is used to analyze the user's emotions from their voice and input. The results of the emotion analysis are reflected in the prompts sent to the generating AI, resulting in more empathetic advice. For example, if the analysis indicates that the user is stressed, the advice will include gentle words such as, "It's important to take a rest and not push yourself too hard."

[1608] 4. Offering advice

[1609] The generated advice is sent back to the user's device from the server. The advice and important information are then notified in real time using the smartphone's notification function. Therefore, users do not need to frequently check the app and can receive important information at the appropriate time.

[1610] 5. Question and Answer Session in an Dialogue Format

[1611] The application includes a chatbot function, allowing users to input questions about childcare and receive answers in a conversational format. The user's emotional state at the time of questioning is also analyzed, and a corresponding response is provided by the AI.

[1612] Specific example

[1613] For example, if a user enters the question, "Is it a problem if my baby isn't gaining weight?", the emotion analysis engine analyzes the user's stress level and, based on that, generates a gentle response such as, "While consulting with experts is important, every baby grows at their own pace, so please don't worry too much."

[1614] Example of a prompt

[1615] The baby's latest milk intake is 200ml. The parents are feeling stressed. Please advise on the appropriate amount of milk for the next feeding and provide some reassuring advice.

[1616] In this way, the present invention enables efficient management and analysis of childcare data, provides emotionally supportive advice, and reduces the burden on parents during childcare.

[1617] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1618] Step 1:

[1619] The user enters childcare data.

[1620] How it works: The user opens the application on their smartphone and enters childcare data such as the baby's milk intake, sleep duration, and diaper change frequency in text or voice. For voice input, the Google Speech-to-Text API is used to convert the speech to text.

[1621] Input: Milk intake, sleep duration, diaper change frequency

[1622] Output: Childcare data in text format

[1623] Step 2:

[1624] The terminal temporarily stores the entered data and sends it to the server.

[1625] Operation: Data is saved to the device's local storage and sent to a Node.js server in real time. The server receives the data and converts it to the appropriate format.

[1626] Input: Childcare data in text format

[1627] Output: Sending data to the server

[1628] Step 3:

[1629] The server saves the received data to the database.

[1630] Operation: Received data is saved to a MongoDB database. The database stores various data about the baby, along with the date and time.

[1631] Input: Childcare data in text format

[1632] Output: Childcare data stored in the database

[1633] Step 4:

[1634] The server periodically analyzes the stored data.

[1635] Operation: Uses TensorFlow.js to analyze stored data. Detects trends in milk intake and changes in sleep duration to identify anomalies.

[1636] Input: Childcare data stored in the database

[1637] Output: Analysis results (e.g., abnormal milk intake)

[1638] Step 5:

[1639] The server generates advice based on the analysis results.

[1640] Operation: Sends analysis results to the OpenAI API and generates appropriate advice using the generated AI model. Creates prompt messages and sends them to the AI.

[1641] Input: Analysis results

[1642] Output: Generated advice (text format)

[1643] Step 6:

[1644] The server notifies the smartphone of the generated advice.

[1645] Operation: Generated advice is sent to the device and the parent is notified using the smartphone's notification function.

[1646] Input: Generated advice

[1647] Output: Notification to smartphone

[1648] Step 7:

[1649] It analyzes emotions based on user input data and voice.

[1650] Operation: Uses TensorFlow.js to analyze the user's emotional state from speech and text. Reflects the analysis results in prompts and sends them to the generating AI.

[1651] Input: User's voice or text

[1652] Output: Emotion analysis results

[1653] Step 8:

[1654] Generates emotion-based advice.

[1655] Operation: Incorporates user sentiment analysis results into prompts and generates emotion-responsive advice using the OpenAI API.

[1656] Input: Sentiment analysis results, prompt text

[1657] Output: Emotional response advice (text format)

[1658] Step 9:

[1659] It accepts user questions and provides answers in a conversational format.

[1660] Operation: Uses the application's chatbot function to receive questions from users about childcare. Generates prompts, including sentiment analysis, and creates answers using the OpenAI API.

[1661] Input: User's question (text format), sentiment analysis results

[1662] Output: Dialogue-style response (text format)

[1663] In this way, the present invention functions as a system that provides efficient management of childcare data and support that is sensitive to the emotions of parents.

[1664] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1665] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1666] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1667] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1668] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1669] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1670] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1671] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1672] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1673] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1674] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1675] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1676] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1677] 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.

[1678] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1679] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1680] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1681] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1682] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1683] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1684] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1685] The following is further disclosed regarding the embodiments described above.

[1686] (Claim 1)

[1687] Methods for inputting childcare data,

[1688] A means of saving the entered childcare data to a database,

[1689] A means of analyzing stored childcare data,

[1690] A means for generating advice based on the analysis results,

[1691] A means of presenting the generated advice,

[1692] A system that includes this.

[1693] (Claim 2)

[1694] The system according to claim 1, which inputs childcare data by voice input.

[1695] (Claim 3)

[1696] The system according to claim 1, which takes questions about childcare data as input and presents answers to those questions in a conversational format.

[1697] "Example 1"

[1698] (Claim 1)

[1699] Methods for inputting childcare data,

[1700] A means for temporarily storing the entered childcare data and analyzing it as needed,

[1701] A means of saving the analyzed data to a database,

[1702] A means of periodically analyzing stored childcare data to detect abnormalities or specific patterns,

[1703] A generative AI model that generates advice based on the analysis results,

[1704] A means of presenting the generated advice,

[1705] A system that includes this.

[1706] (Claim 2)

[1707] The system according to claim 1, which inputs childcare data by voice input.

[1708] (Claim 3)

[1709] The system according to claim 1, which takes questions about childcare data as input and presents answers to those questions in a conversational format.

[1710] "Application Example 1"

[1711] (Claim 1)

[1712] Methods for inputting childcare data,

[1713] A means of saving the entered childcare data to a database,

[1714] A means of analyzing stored childcare data,

[1715] A means for generating advice based on the analysis results,

[1716] A means of presenting the generated advice,

[1717] A method for inputting childcare data using voice recognition,

[1718] A means for sending text data generated based on speech recognition to a server,

[1719] A means of displaying advice received from a server on a next-generation display device,

[1720] A system that includes this.

[1721] (Claim 2)

[1722] The system according to claim 1, which inputs childcare data via voice input and displays the data in real time on a next-generation display device.

[1723] (Claim 3)

[1724] The system according to claim 1, which takes questions about childcare data as input and displays answers to those questions in a conversational format.

[1725] "Example 2 of combining an emotion engine"

[1726] (Claim 1)

[1727] Methods for inputting childcare data,

[1728] A means for converting input childcare data into text data using a speech recognition engine,

[1729] Methods for saving text data to a database,

[1730] A means of analyzing stored childcare data using an analysis engine,

[1731] A means for generating advice using a generative AI model based on the analysis results,

[1732] A means of incorporating user sentiment data into advice,

[1733] A means of sending the generated advice to the user's terminal for notification,

[1734] A system that includes this.

[1735] (Claim 2)

[1736] The system according to claim 1, comprising means for inputting childcare data by voice input, and converting the input voice data into text data.

[1737] (Claim 3)

[1738] The system according to claim 1, which takes questions about childcare data as input, generates answers to those questions using a generation AI model, and presents them in a conversational format.

[1739] "Application example 2 when combining with an emotional engine"

[1740] (Claim 1)

[1741] Methods for inputting childcare data,

[1742] A means of saving the entered childcare data to a database,

[1743] A means of analyzing stored childcare data,

[1744] A means for generating advice based on the analysis results,

[1745] A means of presenting the generated advice,

[1746] A means of analyzing user emotions and reflecting the analysis results in the advice generation process,

[1747] A means of inputting questions into an application and presenting answers in an interactive format,

[1748] A system that includes this.

[1749] (Claim 2)

[1750] The system according to claim 1, which inputs childcare data by voice input.

[1751] (Claim 3)

[1752] The system according to claim 1, which presents advice generated based on the analysis results using the notification function of a smartphone. [Explanation of Symbols]

[1753] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Methods for inputting childcare data, A means of saving the entered childcare data to a database, A means of analyzing stored childcare data, A means for generating advice based on the analysis results, A means of presenting the generated advice, A system that includes this.

2. The system according to claim 1, which inputs childcare data by voice input.

3. The system according to claim 1, which takes questions about childcare data as input and presents answers to those questions in a dialogue format.

Images