System

Abstract

A system is provided.SOLUTION: A system comprising: a terminal including a sensor that detects a motion of a baby, a crying voice, a room temperature, a humidity, and an intensity of illumination; a server that receives and stores data transmitted from the terminal; a unit that learns a sleep pattern of the baby using an artificial intelligence model installed in the server and proposes an optimal method of putting the baby to sleep and an optimal environment setting; SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Sleep problems in newborns and young children are a major challenge for parents. This can make it difficult for parents to accurately understand their baby's sleep patterns and find appropriate ways to respond. Furthermore, lack of sleep and stress among parents can have a negative impact on the entire family, increasing negative child-rearing experiences. There is a need to solve these problems and create an environment where parents and children can get healthy sleep in peace. [Means for solving the problem]

[0005] The present invention is a system that includes a terminal equipped with sensors that detect a baby's movements, crying, room temperature, humidity, and lighting intensity; a server that receives and stores data transmitted from the terminal; and a system that uses an artificial intelligence model installed on the server to learn a baby's sleep patterns and propose optimal methods for putting the baby to sleep and environmental settings. Furthermore, the system includes a means for notifying the parent of suggestions from the server via their smartphone, retraining the artificial intelligence model with feedback data from the parent, and improving the model's accuracy, thereby achieving healthy sleep for the baby and reducing parental stress. Furthermore, by notifying the parent in real time using a low-latency communication protocol, the system allows for a prompt response when the baby exhibits specific behaviors.

[0006] The "terminal" is a device equipped with sensors that detect the baby's movements, crying, room temperature, humidity, lighting intensity, etc., and collects data and sends it to a server.

[0007] A "server" is a computer system that receives and stores data sent from a terminal, and is a device that analyzes the data and runs artificial intelligence models.

[0008] An "artificial intelligence model" is an algorithm and machine learning framework that learns a baby's sleep patterns and suggests optimal methods and environmental settings for putting the baby to sleep.

[0009] A "sleep pattern" is a collection of data that indicates the temporal behavior and characteristics of a baby's sleep.

[0010] The "optimal sleep method" is the behavior or setting that helps a baby fall asleep most quickly, based on the baby's individual sleep patterns and environment.

[0011] "Environmental settings" are adjusted conditions such as room temperature, humidity, lighting intensity, and music to help babies sleep comfortably.

[0012] The "notification means" refers to a communication method or device for transmitting suggestions from the server to the parent's smartphone.

[0013] "Feedback" is information that parents report on the results of acting on a suggestion and send back to the system.

[0014] "Model accuracy improvement" is the process of retraining an AI model based on feedback data to improve the accuracy of future suggestions.

[0015] A "low-latency communication protocol" is a communication technology that minimizes the time it takes to send and receive data and transmits information in real time. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10]1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] This invention relates to a smart baby monitor system that learns the sleep patterns of newborns and infants and suggests optimal methods and environments for putting them to sleep. This system aims to support parents and children in achieving healthy sleep, reducing stress and increasing positive experiences in child-rearing.

[0038] This system mainly consists of three components: the terminal, the server, and the user's smartphone.

[0039] Terminal

[0040] The device is equipped with sensors that detect the baby's movements, crying, room temperature, humidity, and light intensity. The data collected from these sensors is sent to a server in real time. The device also has the ability to collect and transmit biometric data such as the baby's heart rate and breathing patterns.

[0041] server

[0042] The server receives data sent from the device and stores it with a timestamp. This stored data is analyzed by an artificial intelligence model and used to learn the baby's sleep patterns. The server compares past data with new data and suggests optimal sleep methods and environmental settings for each individual baby. These suggestions include specific actions (e.g., adjusting the room temperature, playing sleep-inducing music, or giving the baby milk).

[0043] User's smartphone

[0044] The user's smartphone receives suggestions from the server in real time. When the baby exhibits a specific behavior, a notification from the server is sent to the smartphone, suggesting an appropriate response. The user also inputs the results of their actions in response to the suggestions as feedback through the smartphone app. This feedback is sent back to the server and used to improve the accuracy of the artificial intelligence model.

[0045] Specific examples

[0046] Example 1: Analysis and suggestions for general sleep patterns

[0047] Device: Detects when your baby wakes up frequently during the night.

[0048] Server: Compares with past data and finds that the individual is waking up more often than usual. This is considered abnormal.

[0049] Server: Notices that the temperature is below normal and generates a suggestion to increase the room temperature by 1 degree.

[0050] Device: Suggestions are sent to the parent's smartphone.

[0051] User: The parent increases the temperature as suggested and the baby wakes up less often.

[0052] Example 2: Real-time cry analysis and advice

[0053] Device: Detects when a baby starts crying.

[0054] Server: Analyzes the crying data and identifies "hunger" trends from past data.

[0055] Server: Generates the advice "Maybe he's hungry. Please give him some milk."

[0056] Device: Advice is sent to the parent's smartphone.

[0057] User: The parent feeds the baby, and then the baby stops crying.

[0058] In this way, through the process of data collection, analysis, suggestion generation, real-time notifications, and feedback collection, the system provides comprehensive support to help parents and children achieve safe and healthy sleep.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] The device uses sensors to detect the baby's movements, crying, room temperature, humidity, light intensity, heart rate, breathing pattern, etc. The collected data is then sent to a server at specific intervals (e.g., every second).

[0062] Step 2:

[0063] The server receives data sent from the terminal in real time, timestamps it, and stores it in a database. This storage process uses a distributed database to ensure data redundancy and increase reliability.

[0064] Step 3:

[0065] The server performs an initial analysis of the received data. At this stage, it performs exploratory data analysis (EDA) to check the data for normality and the presence of missing values. It also performs data cleaning and normalization as needed.

[0066] Step 4:

[0067] The server's AI model uses the initial analyzed data to learn the baby's sleep patterns. It analyzes past and new data using techniques such as deep learning to extract features (such as a tendency for the baby to cry at certain times of the day).

[0068] Step 5:

[0069] The server then suggests optimal sleep patterns and environmental settings based on the learned sleep patterns. These suggestions include specific actions (e.g., setting the room temperature to 22 degrees, playing soft music, giving milk, etc.) and converts them into a data format that can be sent to the parent's smartphone.

[0070] Step 6:

[0071] The device sends real-time suggestions from the server to the parent's smartphone. When the baby exhibits certain behaviors (crying, rapid movements, etc.), it detects them and promptly notifies the parent based on the measured data and the latest suggestions from the server. A low-latency communication protocol is used to minimize the time lag in this process.

[0072] Step 7:

[0073] The user responds to the suggestions sent to their smartphone, such as gently patting the baby's back, playing music, or preparing milk.

[0074] Step 8:

[0075] Users input the results of their actions as feedback data through a smartphone app, and this feedback is sent to the server.

[0076] Step 9:

[0077] The server then retrains the AI ​​model using the received feedback data, improving the model's accuracy with a new dataset that includes the feedback data, and retrains it to improve the effectiveness of future suggestions.

[0078] Through these steps, the system provides comprehensive support to improve sleep for parents and babies and reduce parental burden.

[0079] Example 1

[0080] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0081] In today's childcare environment, it is difficult to accurately understand the sleep patterns of newborns and young children and recommend optimal methods and environments for putting them to sleep. Many parents are unable to detect their baby's crying or abnormalities in real time, which can delay appropriate responses. In addition, there is a lack of systems that effectively incorporate feedback to improve the accuracy of sleep pattern analysis. This can increase stress in childcare and have a negative impact on the health of both parents and children.

[0082] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0083] In this invention, the server includes a means for generating a prompt message suggesting a specific action based on the results of data analysis, a means for sending the prompt message to the user's smartphone, and a means including a smartphone application for inputting feedback on the suggestion made by the user. This makes it possible to accurately grasp a baby's sleep patterns and suggest optimal measures in real time, thereby reducing stress in childcare and supporting the health of parents and children.

[0084] "Baby movements" refers to the physical displacements that occur when a baby moves their arms, legs, or body.

[0085] "Cry" refers to the sounds that babies make to indicate discomfort or needs.

[0086] "Room temperature" refers to the temperature of the air in the room where the baby is.

[0087] "Humidity" refers to the percentage of moisture in the air in the baby's environment.

[0088] "Lighting intensity" refers to the brightness of the lights in the room where the baby is.

[0089] "Sensors" refer to devices that detect baby movement, crying, room temperature, humidity, and lighting intensity.

[0090] "Terminal" refers to a device that includes sensors and collects data on the baby's movements and environment and transmits it to a server.

[0091] "Server" refers to a device that receives, stores, and analyzes data sent from a terminal.

[0092] "Artificial intelligence model" refers to an algorithm that analyzes data received from the device, learns the baby's sleep patterns, and generates optimal suggestions.

[0093] "Prompt sentence" refers to a sentence that suggests specific actions to the user based on the results of data analysis by the server.

[0094] "Feedback" refers to data that reports to the server the results and effects of actions taken by a user based on a suggestion.

[0095] "Smartphone" refers to a mobile information terminal that allows users to receive notifications from the server and enter feedback.

[0096] MODE FOR CARRYING OUT THE INVENTION

[0097] The present invention relates to a smart baby monitor system that analyzes the sleep patterns of newborns and infants in real time and suggests optimal methods for putting them to sleep and environmental settings. The system is composed of a terminal, a server, and the user's smartphone.

[0098] Terminal

[0099] The device is equipped with various sensors (e.g., accelerometer, microphone, temperature and humidity sensor, and light sensor) to detect the baby's movements, crying, room temperature, humidity, and light intensity. The data collected from these sensors is sent to a server in real time. The device also has the ability to collect biometric data such as the baby's heart rate and breathing pattern and send it with a timestamp.

[0100] server

[0101] The server receives data sent from the device and stores it in a cloud database (e.g., Amazon RDS or Google Cloud Firestore). The received data is analyzed by an artificial intelligence model implemented in Python (e.g., TensorFlow or PyTorch), which learns the baby's sleep patterns. The server compares past data with new data and suggests optimal sleep methods and environment settings for each individual baby. These suggestions are formatted as prompts and sent to the user's smartphone.

[0102] User's smartphone

[0103] The user's smartphone receives suggestions from the server in real time and displays them as notifications. The user then takes specific actions based on the suggestions and sends the results of their actions as feedback to the server via the smartphone application. This feedback is then used to improve the accuracy of the AI ​​model.

[0104] Specific examples

[0105] Example 1: Analysis and suggestions for general sleep patterns

[0106] Device: Detects when your baby wakes up frequently during the night.

[0107] Server: Compares with past data and finds that the individual is waking up more often than usual. This is considered abnormal.

[0108] Server: Notices that the temperature is below normal and generates a prompt saying "The room temperature is low, please turn the heating up by one degree."

[0109] User's smartphone: The suggestion is sent to the parent's smartphone.

[0110] User: The parent increases the temperature as suggested and the baby wakes up less often.

[0111] Example 2: Real-time cry analysis and advice

[0112] Device: Detects when a baby starts crying.

[0113] Server: Analyzes the crying data and identifies "hunger" trends from past data.

[0114] Server: Generates the prompt "Maybe he's hungry. Please give him some milk."

[0115] User's smartphone: Advice is sent to the parent's smartphone.

[0116] User: The parent feeds the baby, and then the baby stops crying.

[0117] In this way, through the process of data collection, analysis, suggestion generation, real-time notifications, and feedback collection, the system provides comprehensive support to help parents and children achieve safe and healthy sleep.

[0118] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0119] Step 1: Collect data

[0120] The device collects data using various sensors to detect the baby's movements, crying, room temperature, humidity, and lighting intensity. These sensors include an accelerometer, microphone, temperature and humidity sensor, and light sensor. The collected data is time-stamped in real time and sent to a server via Wi-Fi or Bluetooth. The input is the sensor measurement data, and the output is a time-stamped data packet. For example, if the temperature in a baby's room is 21°C and the baby starts crying, the device will collect the temperature data and crying data from the microphone.

[0121] Step 2: Save your data

[0122] The server receives data sent from the device. The received data is stored as is in a cloud database (for example, Amazon RDS or Google Cloud Firestore). The input is a time-stamped data packet, and the output is a data entry stored in the database. For example, the room temperature data of 21°C and the crying sound data are stored in the database.

[0123] Step 3: Analyze the data

[0124] The server analyzes the information stored in the database using an AI model implemented in Python (for example, TensorFlow or PyTorch). Here, the model learns the baby's sleep patterns and performs anomaly detection and pattern recognition. The input is the stored data entry, and the output is the analysis result. For example, the AI ​​model analyzes the baby's crying data and determines that the baby is hungry.

[0125] Step 4: Generate proposals

[0126] The server generates a prompt sentence based on the analysis result. The generated prompt sentence is sent to the user's smartphone. The input is the analysis result, and the output is the prompt sentence. For example, a generated prompt sentence might be "He might be hungry. Please give him some milk."

[0127] Step 5: Proposal Notification

[0128] The user's smartphone receives the prompt sentence sent from the server in real time and displays it as a notification. The input is the prompt sentence, and the output is the smartphone notification. For example, the smartphone may display a notification saying, "The baby may be hungry. Please give him some milk."

[0129] Step 6: Implementing the proposal

[0130] The user performs the suggested action based on the notification from the smartphone. The input is the notification from the smartphone, and the output is the user's specific action, for example, the user feeding the baby.

[0131] Step 7: Provide feedback

[0132] The user inputs the results of their actions based on the suggestions as feedback through a smartphone application. The input is the result of the user's actions, and the output is feedback data. For example, the user might input, "After I gave the baby milk, the baby stopped crying."

[0133] Step 8: Saving feedback and improving the model

[0134] The server receives feedback data from users and stores it in a database. It then retrains the AI ​​model based on the feedback data to improve the model's accuracy. The input is the feedback data, and the output is an improved AI model. For example, it learns more about the crying patterns of babies when they are hungry.

[0135] Through this series of processing steps, the system can monitor the baby's environment and condition in real time and suggest optimal responses to parents.

[0136] (Application example 1)

[0137] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0138] Conventional baby monitors are designed for use at home and do not provide sufficient support for parents and babies when they are out and about or in a physical store. In particular, it is difficult for parents to immediately respond to their baby's comfort and behavior in a store, which can lead to problems such as parents shortening their shopping time if the baby is uncomfortable. The objective of this invention is to provide a more comfortable environment for parents and children by monitoring baby movements, crying, and environmental data in a physical store and proposing optimal responses in real time.

[0139] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0140] In this invention, the server includes a terminal equipped with sensors that detect the baby's movements, crying, room temperature, humidity, and lighting intensity, a means for receiving and storing data transmitted from the terminal, a means for learning the baby's sleep patterns using an artificial intelligence model installed in the server and proposing optimal methods for putting the baby to sleep and environmental settings, a means for notifying the parent's smartphone of the suggestions from the server, a means for re-learning the artificial intelligence model using feedback data from the parent to improve model accuracy, and a means for monitoring the baby's movements, crying, and indoor environment with sensors installed in specific areas of the store and proposing appropriate responses to the parent in real time. This makes it possible to propose optimal environmental settings and actions to ensure the baby's comfort in the physical store.

[0141] "Movement" is data that detects changes in the position of the baby's entire body or parts of it.

[0142] "Crying" is data that collects the sounds made when a baby cries.

[0143] "Room temperature" is data indicating the temperature of the room where the baby is.

[0144] "Humidity" is data that indicates the amount of moisture in the air in the room where the baby is.

[0145] "Lighting intensity" is data that indicates the brightness of the room where the baby is.

[0146] The "sensors" are devices that detect baby movements, crying, room temperature, humidity, and lighting intensity.

[0147] A "terminal" is a device equipped with sensors that collects and transmits this data.

[0148] A "server" is a device that receives and stores data sent from a terminal.

[0149] An "artificial intelligence model" is software that contains algorithms that analyze and learn from collected data.

[0150] "Sleep patterns" are a collection of data that indicates the times and conditions during which a baby sleeps.

[0151] The "suggestion method" is a system that uses an artificial intelligence model to inform parents of the optimal way to put their baby to sleep and the optimal environment settings.

[0152] The "means of notification" is a mechanism that sends suggestions from the server to the parent's smartphone.

[0153] "Feedback Data" is information provided by parents regarding actual outcomes of their responses.

[0154] A "low latency communication protocol" is a communication technology for quickly transmitting data in real time.

[0155] A "specific behavior" is a specific state or behavior exhibited by a baby.

[0156] A "specific area" refers to a specific location within a physical store where a baby is located.

[0157] "Environmental settings" are environmental conditions such as temperature, humidity, and lighting that are adjusted to take into account the baby's comfort.

[0158] "Response" refers to appropriate actions and measures taken by parents in response to the baby's condition and environment.

[0159] A "suggestion" is a specific action plan generated by the server to improve the baby's comfort.

[0160] This invention is a system that monitors baby movements, crying, room temperature, humidity, lighting intensity, etc. in a physical store to support a baby's comfortable stay. This system consists of the following elements.

[0161] Hardware Configuration

[0162] Terminal: A terminal equipped with sensors that detect the baby's movements, crying, room temperature, humidity, and light intensity. This terminal is placed in a specific area where the baby is.

[0163] Server: Hardware that receives and stores data sent from sensor terminals and is equipped with an artificial intelligence model.

[0164] User's smartphone: This is the parent's smartphone, which is the device that receives suggestions from the server in real time.

[0165] Software Configuration

[0166] Data collection and management system: Software that collects data from sensors in real time and sends it to a server.

[0167] Artificial intelligence model: An algorithm installed on the server that learns and analyzes the baby's sleep patterns and comfort based on collected data. For example, TensorFlow or PyTorch is used.

[0168] Notification system: Software that sends server-generated suggestions to parents' smartphones. Notification platforms such as Firebase are used for this purpose.

[0169] User feedback system: This is an application that allows parents to input their responses to suggestions and send them back to the server.

[0170] Processing Description

[0171] First, sensor devices placed in specific areas where babies are present collect real-time environmental data, such as movement, crying, room temperature, humidity, and lighting intensity. This data is sent from the devices to a server and stored as time-series data. An artificial intelligence model installed on the server analyzes the collected data and suggests environmental settings for the baby's comfort and appropriate response actions.

[0172] Suggestions include, for example, "Your baby is crying, so please hold him / her" or "It's a little hot here, so please move to a cooler place." These suggestions are sent to the parent's smartphone in real time, allowing the parent to take action based on the notification to improve the baby's comfort.

[0173] In addition, parents can input their actual behavior into the smartphone app as feedback, which is then sent back to the server. This feedback data is then used again as training data for the AI ​​model, improving its accuracy.

[0174] Specific examples

[0175] For example, suppose a baby starts crying in a physical store. The sensor device detects this crying and sends the data to the server. The server compares it with past data and determines that the baby is crying because it is hungry. It then generates a suggestion that says, "The baby may be hungry. Please give him some milk," and sends a notification to the parent's smartphone. If the parent follows this suggestion and gives him some milk, the baby will calm down and stop crying. The parent can then provide feedback on this response, further improving the system's accuracy.

[0176] Prompt Sentence Examples

[0177] "An application that analyzes data on the crying, movements, room temperature, humidity, and lighting intensity of newborns and infants, and suggests the best way for parents to respond. For example, if a baby is crying because it is sleepy, the system will notify the parent, 'Your baby seems sleepy. Please hold him / her and try to calm him / her down.'"

[0178] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0179] Step 1:

[0180] The device detects the baby's movements, crying, room temperature, humidity, and lighting intensity. The input is real-time data from each sensor, which is processed and summarized within the device and then sent to the server. The output is a data packet sent to the server.

[0181] Step 2:

[0182] The server receives data sent from the device and stores it as time-series data. The input is the data packet sent from the device, which is stored in the database. The output is the data stored in the database.

[0183] Step 3:

[0184] The server analyzes the stored data using an artificial intelligence model to determine the baby's condition. During this process, data analysis algorithms using, for example, TensorFlow or PyTorch are executed. The input is time-series data stored in the database, which is used to analyze the baby's current condition and patterns. The output is a judgment result regarding the baby's condition.

[0185] Step 4:

[0186] The server generates an appropriate suggestion based on the analysis results. For example, if it determines that the reason the baby is crying is "sleepy," it generates the suggestion "The baby seems sleepy. Please hold him and calm him down." The input is the judgment result in step 3, and the output is the generated suggestion.

[0187] Step 5:

[0188] The server notifies the parent's smartphone of the generated suggestions. The input is the suggestion content, and the output is the notification sent to the parent's smartphone. This process uses a notification platform such as Firebase.

[0189] Step 6:

[0190] The user receives a notification on their smartphone and performs the suggested action. The input is the suggested notification displayed on the smartphone, and the output is the user's action. Specifically, the user responds according to the notification, such as holding the baby or feeding it.

[0191] Step 7:

[0192] The user inputs the results of their actual actions into the smartphone app as feedback. The input is the user's actions, which are sent to the server in an input format such as a form. The output is the feedback data sent to the server.

[0193] Step 8:

[0194] The server retrains the AI ​​model using the received feedback data to improve the model's accuracy. The input is the feedback data sent by the user, which is integrated with the existing training data to update the model. The output is an AI model with improved accuracy.

[0195] The above are the specific processing steps for carrying out the invention.

[0196] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0197] The present invention relates to a smart baby monitor system for supporting the sleep of newborns and young children, and aims to provide more effective suggestions by recognizing the user's emotions and using that feedback. This system provides support for parents and children to achieve healthy sleep, reducing stress and increasing positive experiences in childcare.

[0198] Components

[0199] This system mainly consists of four components: the terminal, the server, the user's smartphone, and the emotion engine.

[0200] Terminal

[0201] The device is equipped with sensors that detect the baby's movements, crying, room temperature, humidity, light intensity, heart rate, breathing patterns, etc. The data collected from these sensors is sent to a server in real time.

[0202] server

[0203] The server receives data sent from the device in real time and stores it in a database with a timestamp. This storage process uses a distributed database to ensure data redundancy and increase reliability. The received data is analyzed by an artificial intelligence model, which learns the baby's sleep patterns and suggests optimal methods and environmental settings for putting the baby to sleep. These suggestions include specific actions (e.g., adjusting the room temperature, playing sleep-inducing music, or giving the baby milk).

[0204] User's smartphone

[0205] The user's smartphone receives suggestions from the server in real time. When the baby exhibits a specific behavior, a notification from the server is sent to the smartphone, suggesting an appropriate response. The user also inputs the results of their actions in response to the suggestions as feedback through the smartphone app. This feedback is sent back to the server and used to improve the accuracy of the artificial intelligence model.

[0206] Emotion Engine

[0207] The emotion engine analyzes the user's voice, facial expressions, text input, etc. to recognize the user's emotions. This emotional information is used to adjust the content of suggestions. For example, if the user is feeling very stressed, it will provide suggestions that are easier than usual or have a relaxing effect. The emotional information is also sent to the server as feedback data and used to train the artificial intelligence model.

[0208] Specific examples

[0209] Example 1: Analysis and suggestions for general sleep patterns

[0210] Device: Detects when your baby wakes up frequently during the night.

[0211] Server: Compares with past data and finds that the individual is waking up more often than usual. This is considered abnormal.

[0212] Server: Notices that the temperature is below normal and generates a suggestion to increase the room temperature by 1 degree.

[0213] Emotion engine: Determines that the user's stress level is high and includes an additional suggestion to "play relaxing music."

[0214] Device: Suggestions are sent to the parent's smartphone.

[0215] User: The parent follows the suggestions to turn up the temperature and play music, and the baby wakes up less often.

[0216] Example 2: Real-time cry analysis and advice

[0217] Device: Detects when a baby starts crying.

[0218] Server: Analyzes the crying data and identifies "hunger" trends from past data.

[0219] Server: Generates the advice "Maybe he's hungry. Please give him some milk."

[0220] Emotion engine: Recognizes the user's emotions and omits detailed advice on how to feed the baby if the emotional information is positive.

[0221] Device: Advice is sent to the parent's smartphone.

[0222] User: The parent feeds the baby, and then the baby stops crying.

[0223] In this way, through the process of data collection, analysis, suggestion generation, real-time notifications, emotion recognition, and feedback collection, the system provides comprehensive support for parents and children to achieve safe and healthy sleep.

[0224] The processing flow will be explained below.

[0225] Step 1:

[0226] The device uses sensors to detect the baby's movements, crying, room temperature, humidity, light intensity, heart rate, breathing patterns, etc. This data is then sent to a server at intervals of one second.

[0227] Step 2:

[0228] The server receives data sent from the terminal in real time, timestamps it, and stores it in a database. It performs an initial analysis of the received data to check for normality and the presence of missing values.

[0229] Step 3:

[0230] The server's artificial intelligence model uses the pre-processed data to learn the baby's sleep patterns, including past data, and uses deep learning techniques to analyze the patterns and extract features.

[0231] Step 4:

[0232] The emotion engine receives data from the user's smartphone, such as the user's voice, facial expressions, and text input, and analyzes the user's emotions based on this data to identify their current emotional state.

[0233] Step 5:

[0234] The server combines the learned sleep patterns with emotional data from the emotion engine to suggest optimal sleep methods and environmental settings. For example, it generates specific actions such as setting the temperature in the baby's room to 22 degrees and playing calming music. If the user is feeling stressed, the suggestions are adjusted to be simpler and less burdensome.

[0235] Step 6:

[0236] The device sends real-time suggestions from the server to the parent's smartphone. If the baby starts crying or shows abnormal behavior, the device will quickly notify the parent based on the detected data. A low-latency communication protocol is used to minimize processing time lag.

[0237] Step 7:

[0238] The user performs the suggested actions on their smartphone and then inputs the results as feedback through the smartphone app, including the effect the action had on the baby and the user's own emotional state.

[0239] Step 8:

[0240] The server receives the feedback data and retrains the artificial intelligence model based on it, including new datasets to continually improve the accuracy of its suggestions.

[0241] Step 9:

[0242] The emotion engine again analyzes the user's emotional state and provides feedback to the server's learning process, allowing it to generate more effective suggestions that also take the user's emotional state into account.

[0243] Through these steps, the system provides comprehensive support for parents and children to achieve safe and healthy sleep, and by taking the user's emotions into consideration, it provides detailed and effective childcare support.

[0244] Example 2

[0245] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0246] In today's world, there is a need for effective systems to support baby sleep, but existing systems are unable to properly monitor the baby's condition or provide appropriate responses to parents' emotions and stress levels.To achieve healthy sleep for parents and children, reduce parenting stress, and increase positive parenting experiences, a system with more advanced data analysis and emotional feedback capabilities is needed.

[0247] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a terminal equipped with sensors that detect the baby's movements, crying, room temperature, humidity, and lighting intensity, a means for receiving and storing data transmitted from the terminal, a means for learning the baby's sleep patterns using an artificial intelligence model installed in the server and proposing optimal methods for putting the baby to sleep and environmental settings, a means for notifying the parent's smartphone of the suggestions from the server, a means for re-learning the artificial intelligence model using feedback data from the parent and improving model accuracy, and a means for analyzing the user's emotions and adjusting the suggestions. This makes it possible to analyze the baby's condition and the parent's emotions in real time and make optimal suggestions based on the results.

[0248] The "terminal" is a device equipped with sensors that detect the baby's movements, crying, room temperature, humidity, and lighting intensity.

[0249] A "server" is a computing system that receives and stores data sent from a terminal, and analyzes and processes the data using artificial intelligence models.

[0250] "Artificial intelligence model" refers to the machine learning algorithm used to learn a baby's sleep patterns and suggest optimal methods and settings for putting the baby to sleep.

[0251] "Sleep patterns" refers to behavioral data and the analysis results that show a baby's sleep habits and tendencies.

[0252] "Environmental settings" refer to conditions such as room temperature, humidity, and lighting that are necessary to support a baby's sleep.

[0253] A "smartphone" is a mobile device that receives suggestions and allows parents to enter feedback.

[0254] "Feedback data" is information entered by parents as the results of their actions and their impressions regarding the suggestions.

[0255] An "emotion engine" is a system that analyzes the user's voice, facial expressions, text input, etc. to recognize the user's emotions.

[0256] "Adjusting suggestions" is the process by which the emotion engine appropriately changes the content of suggestions based on the user's emotions.

[0257] This invention relates to a smart baby monitor system for supporting the sleep of newborns and young children. In particular, it aims to provide more effective suggestions by recognizing the user's emotions and utilizing that feedback. This system provides support for parents and children to achieve healthy sleep, reducing stress and increasing positive experiences in childcare.

[0258] Components

[0259] The system mainly consists of the following components: the terminal, the server, the user's smartphone, and the emotion engine.

[0260] Terminal

[0261] The device is equipped with sensors that detect the baby's movements, crying, room temperature, humidity, light intensity, heart rate, breathing patterns, etc. The device collects the baby's behavior and environmental data in real time and transmits it to a server via Wi-Fi or Bluetooth, allowing for a detailed understanding of the baby's current condition.

[0262] server

[0263] The server receives data sent from the device in real time and stores it in a database with a timestamp. This storage process uses a distributed database (e.g., Cassandra or MongoDB) to ensure data redundancy and increase reliability. The received data is analyzed using an artificial intelligence model (e.g., TensorFlow or PyTorch) to learn the baby's sleep patterns and suggest optimal ways to put the baby to sleep and environmental settings. These suggestions include specific actions (e.g., adjusting the room temperature, playing sleep music, or giving the baby milk).

[0264] User's smartphone

[0265] The user's smartphone receives suggestions from the server in real time. If the baby exhibits a specific behavior, a notification from the server is sent to the smartphone, suggesting an appropriate response. The user also inputs the results of their actions in response to the suggestions as feedback through the smartphone app. This feedback is sent back to the server and used to improve the accuracy of the artificial intelligence model.

[0266] Emotion Engine

[0267] The emotion engine analyzes the user's voice, facial expressions, text input, etc. to recognize the user's emotions. This emotional information is used to adjust the content of suggestions. For example, if the user is feeling very stressed, it will provide simpler actions than usual or suggestions with a relaxing effect. Emotional information is also sent to the server as feedback data and used to train the artificial intelligence model.

[0268] Specific examples

[0269] Example 1: Analysis and suggestions for general sleep patterns

[0270] Device: Detects when your baby wakes up frequently during the night.

[0271] Server: Compares with past data and finds that the individual is waking up more often than usual. This is considered abnormal.

[0272] Server: Notices that the temperature is below normal and generates a suggestion to increase the room temperature by 1 degree.

[0273] Emotion engine: Determines that the user's stress level is high and includes an additional suggestion to "play relaxing music."

[0274] Device: Suggestions are sent to the parent's smartphone.

[0275] User: The parent follows the suggestions to turn up the temperature and play music, and the baby wakes up less often.

[0276] Example 2: Real-time cry analysis and advice

[0277] Device: Detects when a baby starts crying.

[0278] Server: Analyzes the crying data and identifies "hunger" trends from past data.

[0279] Server: Generates the advice "Maybe he's hungry. Please give him some milk."

[0280] Emotion engine: Recognizes the user's emotions and omits detailed advice on how to feed the baby if the emotional information is positive.

[0281] Device: Advice is sent to the parent's smartphone.

[0282] User: The parent feeds the baby, and then the baby stops crying.

[0283] Prompt Sentence Examples

[0284] Below is an example of an input prompt sentence for the generative AI model.

[0285] "Generate an algorithm that analyzes baby crying data to determine whether or not a baby is hungry."

[0286] "Create a program that analyzes your baby's sleep patterns and suggests the best way to get them to sleep."

[0287] "How can I analyze user sentiment and tailor my suggestions?"

[0288] In this way, through the process of data collection, analysis, suggestion generation, real-time notifications, emotion recognition, and feedback collection, the system provides comprehensive support for parents and children to achieve safe and healthy sleep.

[0289] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0290] Step 1: Collect data

[0291] Description: The device detects your baby's movements, crying, room temperature, humidity, light intensity, heart rate, breathing patterns, and more.

[0292] Input: Various baby sensor data (movement, crying, room temperature, etc.).

[0293] Output: Various detected data is stored in the terminal in real time.

[0294] Specific operation: The baby's movements and environmental conditions are measured using sensors, and this data is temporarily stored in the device's internal memory.

[0295] Step 2: Sending data

[0296] Description: The device sends collected data to the server.

[0297] Input: Various sensor data stored inside the device.

[0298] Output: Various sensor data sent to the server.

[0299] Specific operation: Data collected on the device is sent to a server using Wi-Fi or Bluetooth.

[0300] Step 3: Save your data

[0301] Description: The server saves the received data in the database.

[0302] Input: Sensor data and timestamp sent from the device.

[0303] Output: Sensor data stored in a database.

[0304] Specific operation: The received data is stored in a distributed database (e.g., Cassandra, MongoDB) along with a timestamp.

[0305] Step 4: Analyze the data

[0306] Description: The server analyzes the stored data using artificial intelligence models.

[0307] Input: Sensor data stored in a database.

[0308] Output: Analysis results (baby's sleep patterns, abnormality detection, etc.).

[0309] What it does: It uses AI models such as TensorFlow and PyTorch to analyze data in the database, learn the baby's sleep patterns, and generate alerts if any abnormalities are detected.

[0310] Step 5: Generate proposals

[0311] Description: The server will suggest specific actions based on the analysis results.

[0312] Input: Analysis results (sleep patterns, abnormal conditions, etc.).

[0313] Output: Suggestions (adjust temperature, play music, etc.).

[0314] Specific actions: Based on the analysis results, specific suggestions for proper care of the baby (e.g., raising the room temperature by 1 degree, playing relaxing music, etc.) are generated.

[0315] Step 6: Sentiment Analysis

[0316] Description: The emotion engine analyzes the user's emotions.

[0317] Input: User voice, facial expressions, and text input.

[0318] Output: User's emotional state (e.g. stress level).

[0319] Specific operation: Uses voice and facial expression analysis software to analyze the user's emotions in real time and determine their current emotional state.

[0320] Step 7: Adjust the proposal

[0321] Description: The sentiment engine tailors suggestions based on the user's sentiment.

[0322] Input: User's emotional state, original suggestion.

[0323] Output: The adjusted proposal.

[0324] Specific actions: Depending on the user's stress level, the original suggestions are adjusted and additional suggestions, such as simple actions or relaxation effects, are generated as needed.

[0325] Step 8: Proposal Notification

[0326] Description: The server notifies the user of the offer on their smartphone.

[0327] Input: The adjusted proposal.

[0328] Output: Notification sent to the user's smartphone.

[0329] Specific operation: The proposal is sent to the user's smartphone using push notifications or in-app notifications.

[0330] Step 9: Gather feedback

[0331] Description: User enters feedback on a suggestion.

[0332] Input: Feedback data from users.

[0333] Output: Feedback data sent to the server.

[0334] Specific operation: Through the smartphone app, the user inputs the results and impressions of the actions taken in accordance with the suggestions, and sends these to the server.

[0335] Step 10: Analyze feedback

[0336] Description: The server receives feedback from users and uses it to improve artificial intelligence models.

[0337] Input: Feedback data.

[0338] Output: Updated artificial intelligence model, improved analysis accuracy.

[0339] Specific operation: The collected feedback data is analyzed and used as training data for the AI ​​model to improve its accuracy.

[0340] (Application example 2)

[0341] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0342] Conventional baby monitor systems are limited to monitoring a baby's sleep and health, and lack comprehensive home security or personalized responses to the user's emotions. In particular, it is difficult to detect suspicious movements or sounds, often causing anxiety and stress for parents. There is a need to resolve these situations, improve home safety, and provide a sense of security for both babies and parents.

[0343] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a terminal equipped with sensors that detect the baby's movements, crying, room temperature, humidity, and lighting intensity, a means for receiving and storing data transmitted from the terminal, a means for learning the baby's sleep patterns using an AI model and suggesting optimal sleep-training methods and environmental settings, a means for detecting suspicious movements and sounds in the home and notifying the user in real time, a means for recognizing the user's emotions and providing appropriate advice according to the situation, and a means for retraining the AI ​​model with feedback data from parents to improve the model accuracy. This makes it possible to not only manage the baby's health but also provide comprehensive home security and increase parents' sense of security.

[0344] "Baby movement" refers to the baby moving around in and around the crib.

[0345] "Crying" refers to the sounds that babies make, especially the sounds they make when crying.

[0346] "Room temperature" refers to the temperature of the air in the room where the baby is.

[0347] "Humidity" refers to the percentage of moisture in the air in the baby's room.

[0348] "Lighting intensity" refers to the intensity of the light in the room where the baby is.

[0349] "Sensors" refer to devices that detect baby movement, crying, room temperature, humidity, and lighting intensity.

[0350] "Terminal" refers to a device that has multiple sensors and collects and transmits data.

[0351] "Server" refers to a computer system that receives, stores, and analyzes data sent from a terminal.

[0352] "Artificial intelligence model" refers to machine learning algorithms and neural networks used to learn and analyze data.

[0353] "Sleep pattern" refers to a baby's sleep rhythm and cyclical behavioral patterns.

[0354] The "best sleep method" refers to the most effective way to get your baby to sleep steadily.

[0355] "Environmental setting" refers to adjusting room temperature, humidity, etc. to keep the baby comfortable.

[0356] "Real-time notification" refers to a method of notifying users as soon as data is detected.

[0357] "User emotion" refers to the emotional state of the parents or administrators using the system.

[0358] "Advice" refers to providing suggestions or suggestions to the user.

[0359] "Feedback data" refers to information that is useful for improving and adjusting the system, such as responses and impressions from users.

[0360] A "low latency communication protocol" refers to a communication protocol that allows for rapid data exchange.

[0361] This invention is a smart baby monitor and security system for the purpose of managing baby health and improving home security. This system uses the hardware and software shown below and is composed of a device connected to various sensors, a server that receives and analyzes data, and a user's smartphone that receives notifications.

[0362] Components

[0363] Terminal

[0364] The device is equipped with sensors that detect baby movements, crying, room temperature, humidity, and lighting intensity, as well as suspicious movements and sounds within the home. The data collected from these sensors is sent to a server in real time.

[0365] server

[0366] The server receives data sent from the device in real time and stores it in a database with a timestamp. This storage process uses a distributed database to ensure data redundancy and increase reliability. The received data is analyzed using artificial intelligence models such as TensorFlow and Keras to learn the baby's sleep patterns and the home situation. This information is used to generate optimal sleep methods, environmental settings, and home security recommendations.

[0367] User's smartphone

[0368] The user's smartphone receives suggestions and warnings from the server in real time. If the baby exhibits a specific behavior or if suspicious movements or sounds are detected in the home, a notification is sent from the server to the smartphone, suggesting appropriate responses. The user also inputs feedback about the results of their actions and their thoughts on the suggestions through the smartphone app. This feedback is sent back to the server and used to improve the accuracy of the artificial intelligence model.

[0369] Emotion Engine

[0370] The emotion engine analyzes the user's voice, facial expressions, text input, etc. to recognize the user's emotions. This emotional information is used to adjust the content of suggestions. For example, if the user is feeling very stressed, it will recommend suggestions that will have a relaxing effect or simple actions. The emotional information is also sent to the server as feedback data and used to train the artificial intelligence model.

[0371] Specific examples

[0372] 1. Analysis and suggestions of general sleep patterns

[0373] Device: Detects when your baby wakes up frequently during the night.

[0374] Server: Conducts comparative analysis with past data to determine if you tend to wake up more often than usual.

[0375] Server: Notices that the temperature is below normal and generates a suggestion to increase the room temperature by 1 degree.

[0376] Emotion Engine: Determines that the user's stress level is high and includes an additional suggestion to "play relaxing music."

[0377] Device: Suggestions are sent to the parent's smartphone.

[0378] User: The parent follows the suggestions to increase the temperature and play music, and the baby wakes up less often.

[0379] 2. Home security monitoring and notification

[0380] Device: Detects suspicious activity in your home at night.

[0381] Server: Using machine learning models, analyzes suspicious movements that differ from those of babies or pets.

[0382] Server: Generates an immediate alert notification if any suspicious activity is detected.

[0383] Emotion engine: If the user feels anxious, it provides advice with specific steps, such as "call the police."

[0384] Device: Sends a warning notification to the parent's smartphone.

[0385] User: Parents should check the warning notice and take action if necessary, such as reporting the incident to the police.

[0386] Example prompts to be input to the generative AI model

[0387] "Generate a model that can identify suspicious activity in the video captured by the camera. The output should return 1 if there is activity, and 0 if there is not."

[0388] As described above, this system aims to manage baby's health and improve home security through a comprehensive process of data collection, analysis, suggestion generation, real-time notification, emotion recognition, and feedback collection, providing an environment where parents and children can feel safe.

[0389] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0390] Step 1:

[0391] The device collects this data using sensors that detect baby movements, crying, room temperature, humidity, light intensity, and any suspicious movements or sounds.

[0392] Input: Baby movements, crying, room temperature, humidity, lighting intensity, suspicious movements and sounds

[0393] Data processing: Converting the data collected by sensors into a digital format.

[0394] Output: Various data in digital format

[0395] Step 2:

[0396] The terminal transmits the collected data to the server in real time.

[0397] Input: Various digital data

[0398] Data processing: Data is converted into packet format and encrypted for transmission.

[0399] Output: Encrypted data packet sent to the server

[0400] Step 3:

[0401] The server receives the data sent from the terminal and stores it in a database along with a timestamp.

[0402] Input: Encrypted data packet

[0403] Data processing: The data is decrypted, a timestamp is added, and it is saved in the database.

[0404] Output: Saved database entries

[0405] Step 4:

[0406] The server analyzes the stored data using artificial intelligence models.

[0407] Input: Data retrieved from a database

[0408] Data Computing: Using TensorFlow and Keras, we feed data into machine learning models to analyze baby's sleep patterns and household situations.

[0409] Output: Analysis results (baby's sleep patterns, environment settings, suspicious movements and sounds detected)

[0410] Step 5:

[0411] Based on the analysis results, the server generates optimal sleep methods, environmental settings, and home security suggestions.

[0412] Input: Analysis results

[0413] Data calculation: Based on the analysis results, an algorithm is executed to generate specific action suggestions.

[0414] Output: Specific action suggestions

[0415] Step 6:

[0416] The emotion engine analyzes the user's voice and text input to recognize the user's emotions.

[0417] Input: User voice or text input

[0418] Data Computing: Runs algorithms that analyze emotions using speech recognition and natural language processing.

[0419] Output: User's emotional state

[0420] Step 7:

[0421] The server adjusts the content of the suggestions based on the user's emotional state.

[0422] Input: User's emotional state, specific action suggestions

[0423] Data calculations: Executes algorithms that modify or emphasize suggestions depending on the user's emotions.

[0424] Output: Tailored action suggestions

[0425] Step 8:

[0426] The server notifies the user's smartphone of the generated suggestions in real time.

[0427] Input: Adjusted action proposal

[0428] Data Computation: The proposal is converted into a text message format and sent using a low-latency communication protocol.

[0429] Output: Notification displayed on the user's smartphone

[0430] Step 9:

[0431] Users input their feedback on the results of their actions and their thoughts on the suggestions via a smartphone app.

[0432] Input: User feedback information

[0433] Data calculation: Feedback information is collected as text data and sent to the server.

[0434] Output: Feedback data sent to the server

[0435] Step 10:

[0436] The server retrains the artificial intelligence model using the feedback data to improve the model accuracy.

[0437] Input: Feedback data

[0438] Data Computation: Runs algorithms that use feedback data to retrain artificial intelligence models.

[0439] Output: Updated artificial intelligence model

[0440] Through these steps, the system provides comprehensive support for baby health management and home security, providing a safe and secure environment for parents.

[0441] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0442] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0443] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0444] [Second embodiment]

[0445] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0446] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0447] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0448] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0449] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0450] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0451] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0452] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0453] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0454] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0455] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0456] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0457] This invention relates to a smart baby monitor system that learns the sleep patterns of newborns and infants and suggests optimal methods and environments for putting them to sleep. This system aims to support parents and children in achieving healthy sleep, reducing stress and increasing positive experiences in child-rearing.

[0458] This system mainly consists of three components: the terminal, the server, and the user's smartphone.

[0459] Terminal

[0460] The device is equipped with sensors that detect the baby's movements, crying, room temperature, humidity, and light intensity. The data collected from these sensors is sent to a server in real time. The device also has the ability to collect and transmit biometric data such as the baby's heart rate and breathing patterns.

[0461] server

[0462] The server receives data sent from the device and stores it with a timestamp. This stored data is analyzed by an artificial intelligence model and used to learn the baby's sleep patterns. The server compares past data with new data and suggests optimal sleep methods and environmental settings for each individual baby. These suggestions include specific actions (e.g., adjusting the room temperature, playing sleep-inducing music, or giving the baby milk).

[0463] User's smartphone

[0464] The user's smartphone receives suggestions from the server in real time. When the baby exhibits a specific behavior, a notification from the server is sent to the smartphone, suggesting an appropriate response. The user also inputs the results of their actions in response to the suggestions as feedback through the smartphone app. This feedback is sent back to the server and used to improve the accuracy of the artificial intelligence model.

[0465] Specific examples

[0466] Example 1: Analysis and suggestions for general sleep patterns

[0467] Device: Detects when your baby wakes up frequently during the night.

[0468] Server: Compares with past data and finds that the individual is waking up more often than usual. This is considered abnormal.

[0469] Server: Notices that the temperature is below normal and generates a suggestion to increase the room temperature by 1 degree.

[0470] Device: Suggestions are sent to the parent's smartphone.

[0471] User: The parent increases the temperature as suggested and the baby wakes up less often.

[0472] Example 2: Real-time cry analysis and advice

[0473] Device: Detects when a baby starts crying.

[0474] Server: Analyzes the crying data and identifies "hunger" trends from past data.

[0475] Server: Generates the advice "Maybe he's hungry. Please give him some milk."

[0476] Device: Advice is sent to the parent's smartphone.

[0477] User: The parent feeds the baby, and then the baby stops crying.

[0478] In this way, through the process of data collection, analysis, suggestion generation, real-time notifications, and feedback collection, the system provides comprehensive support to help parents and children achieve safe and healthy sleep.

[0479] The processing flow will be explained below.

[0480] Step 1:

[0481] The device uses sensors to detect the baby's movements, crying, room temperature, humidity, light intensity, heart rate, breathing pattern, etc. The collected data is then sent to a server at specific intervals (e.g., every second).

[0482] Step 2:

[0483] The server receives data sent from the terminal in real time, timestamps it, and stores it in a database. This storage process uses a distributed database to ensure data redundancy and increase reliability.

[0484] Step 3:

[0485] The server performs an initial analysis of the received data. At this stage, it performs exploratory data analysis (EDA) to check the data for normality and the presence of missing values. It also performs data cleaning and normalization as needed.

[0486] Step 4:

[0487] The server's AI model uses the initial analyzed data to learn the baby's sleep patterns. It analyzes past and new data using techniques such as deep learning to extract features (such as a tendency for the baby to cry at certain times of the day).

[0488] Step 5:

[0489] The server then suggests optimal sleep patterns and environmental settings based on the learned sleep patterns. These suggestions include specific actions (e.g., setting the room temperature to 22 degrees, playing soft music, giving milk, etc.) and converts them into a data format that can be sent to the parent's smartphone.

[0490] Step 6:

[0491] The device sends real-time suggestions from the server to the parent's smartphone. When the baby exhibits certain behaviors (crying, rapid movements, etc.), it detects them and promptly notifies the parent based on the measured data and the latest suggestions from the server. A low-latency communication protocol is used to minimize the time lag in this process.

[0492] Step 7:

[0493] The user responds to the suggestions sent to their smartphone, such as gently patting the baby's back, playing music, or preparing milk.

[0494] Step 8:

[0495] Users input the results of their actions as feedback data through a smartphone app, and this feedback is sent to the server.

[0496] Step 9:

[0497] The server then retrains the AI ​​model using the received feedback data, improving the model's accuracy with a new dataset that includes the feedback data, and retrains it to improve the effectiveness of future suggestions.

[0498] Through these steps, the system provides comprehensive support to improve sleep for parents and babies and reduce parental burden.

[0499] Example 1

[0500] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0501] In today's childcare environment, it is difficult to accurately understand the sleep patterns of newborns and young children and recommend optimal methods and environments for putting them to sleep. Many parents are unable to detect their baby's crying or abnormalities in real time, which can delay appropriate responses. In addition, there is a lack of systems that effectively incorporate feedback to improve the accuracy of sleep pattern analysis. This can increase stress in childcare and have a negative impact on the health of both parents and children.

[0502] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0503] In this invention, the server includes a means for generating a prompt message suggesting a specific action based on the results of data analysis, a means for sending the prompt message to the user's smartphone, and a means including a smartphone application for inputting feedback on the suggestion made by the user. This makes it possible to accurately grasp a baby's sleep patterns and suggest optimal measures in real time, thereby reducing stress in childcare and supporting the health of parents and children.

[0504] "Baby movements" refers to the physical displacements that occur when a baby moves their arms, legs, or body.

[0505] "Cry" refers to the sounds that babies make to indicate discomfort or needs.

[0506] "Room temperature" refers to the temperature of the air in the room where the baby is.

[0507] "Humidity" refers to the percentage of moisture in the air in the baby's environment.

[0508] "Lighting intensity" refers to the brightness of the lights in the room where the baby is.

[0509] "Sensors" refer to devices that detect baby movement, crying, room temperature, humidity, and lighting intensity.

[0510] "Terminal" refers to a device that includes sensors and collects data on the baby's movements and environment and transmits it to a server.

[0511] "Server" refers to a device that receives, stores, and analyzes data sent from a terminal.

[0512] "Artificial intelligence model" refers to an algorithm that analyzes data received from the device, learns the baby's sleep patterns, and generates optimal suggestions.

[0513] "Prompt sentence" refers to a sentence that suggests specific actions to the user based on the results of data analysis by the server.

[0514] "Feedback" refers to data that reports to the server the results and effects of actions taken by a user based on a suggestion.

[0515] "Smartphone" refers to a mobile information terminal that allows users to receive notifications from the server and enter feedback.

[0516] MODE FOR CARRYING OUT THE INVENTION

[0517] The present invention relates to a smart baby monitor system that analyzes the sleep patterns of newborns and infants in real time and suggests optimal methods for putting them to sleep and environmental settings. The system is composed of a terminal, a server, and the user's smartphone.

[0518] Terminal

[0519] The device is equipped with various sensors (e.g., accelerometer, microphone, temperature and humidity sensor, and light sensor) to detect the baby's movements, crying, room temperature, humidity, and light intensity. The data collected from these sensors is sent to a server in real time. The device also has the ability to collect biometric data such as the baby's heart rate and breathing pattern and send it with a timestamp.

[0520] server

[0521] The server receives data sent from the device and stores it in a cloud database (e.g., Amazon RDS or Google Cloud Firestore). The received data is analyzed by an artificial intelligence model implemented in Python (e.g., TensorFlow or PyTorch), which learns the baby's sleep patterns. The server compares past data with new data and suggests optimal sleep methods and environment settings for each individual baby. These suggestions are formatted as prompts and sent to the user's smartphone.

[0522] User's smartphone

[0523] The user's smartphone receives suggestions from the server in real time and displays them as notifications. The user then takes specific actions based on the suggestions and sends the results of their actions as feedback to the server via the smartphone application. This feedback is then used to improve the accuracy of the AI ​​model.

[0524] Specific examples

[0525] Example 1: Analysis and suggestions for general sleep patterns

[0526] Device: Detects when your baby wakes up frequently during the night.

[0527] Server: Compares with past data and finds that the individual is waking up more often than usual. This is considered abnormal.

[0528] Server: Notices that the temperature is below normal and generates a prompt saying "The room temperature is low, please turn the heating up by one degree."

[0529] User's smartphone: The suggestion is sent to the parent's smartphone.

[0530] User: The parent increases the temperature as suggested and the baby wakes up less often.

[0531] Example 2: Real-time cry analysis and advice

[0532] Device: Detects when a baby starts crying.

[0533] Server: Analyzes the crying data and identifies "hunger" trends from past data.

[0534] Server: Generates the prompt "Maybe he's hungry. Please give him some milk."

[0535] User's smartphone: Advice is sent to the parent's smartphone.

[0536] User: The parent feeds the baby, and then the baby stops crying.

[0537] In this way, through the process of data collection, analysis, suggestion generation, real-time notifications, and feedback collection, the system provides comprehensive support to help parents and children achieve safe and healthy sleep.

[0538] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0539] Step 1: Collect data

[0540] The device collects data using various sensors to detect the baby's movements, crying, room temperature, humidity, and lighting intensity. These sensors include an accelerometer, microphone, temperature and humidity sensor, and light sensor. The collected data is time-stamped in real time and sent to a server via Wi-Fi or Bluetooth. The input is the sensor measurement data, and the output is a time-stamped data packet. For example, if the temperature in a baby's room is 21°C and the baby starts crying, the device will collect the temperature data and crying data from the microphone.

[0541] Step 2: Save your data

[0542] The server receives data sent from the device. The received data is stored as is in a cloud database (for example, Amazon RDS or Google Cloud Firestore). The input is a time-stamped data packet, and the output is a data entry stored in the database. For example, the room temperature data of 21°C and the crying sound data are stored in the database.

[0543] Step 3: Analyze the data

[0544] The server analyzes the information stored in the database using an AI model implemented in Python (for example, TensorFlow or PyTorch). Here, the model learns the baby's sleep patterns and performs anomaly detection and pattern recognition. The input is the stored data entry, and the output is the analysis result. For example, the AI ​​model analyzes the baby's crying data and determines that the baby is hungry.

[0545] Step 4: Generate proposals

[0546] The server generates a prompt sentence based on the analysis result. The generated prompt sentence is sent to the user's smartphone. The input is the analysis result, and the output is the prompt sentence. For example, a generated prompt sentence might be "He might be hungry. Please give him some milk."

[0547] Step 5: Proposal Notification

[0548] The user's smartphone receives the prompt sentence sent from the server in real time and displays it as a notification. The input is the prompt sentence, and the output is the smartphone notification. For example, the smartphone may display a notification saying, "The baby may be hungry. Please give him some milk."

[0549] Step 6: Implementing the proposal

[0550] The user performs the suggested action based on the notification from the smartphone. The input is the notification from the smartphone, and the output is the user's specific action, for example, the user feeding the baby.

[0551] Step 7: Provide feedback

[0552] The user inputs the results of their actions based on the suggestions as feedback through a smartphone application. The input is the result of the user's actions, and the output is feedback data. For example, the user might input, "After I gave the baby milk, the baby stopped crying."

[0553] Step 8: Saving feedback and improving the model

[0554] The server receives feedback data from users and stores it in a database. It then retrains the AI ​​model based on the feedback data to improve the model's accuracy. The input is the feedback data, and the output is an improved AI model. For example, it learns more about the crying patterns of babies when they are hungry.

[0555] Through this series of processing steps, the system can monitor the baby's environment and condition in real time and suggest optimal responses to parents.

[0556] (Application example 1)

[0557] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0558] Conventional baby monitors are designed for use at home and do not provide sufficient support for parents and babies when they are out and about or in a physical store. In particular, it is difficult for parents to immediately respond to their baby's comfort and behavior in a store, which can lead to problems such as parents shortening their shopping time if the baby is uncomfortable. The objective of this invention is to provide a more comfortable environment for parents and children by monitoring baby movements, crying, and environmental data in a physical store and proposing optimal responses in real time.

[0559] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0560] In this invention, the server includes a terminal equipped with sensors that detect the baby's movements, crying, room temperature, humidity, and lighting intensity, a means for receiving and storing data transmitted from the terminal, a means for learning the baby's sleep patterns using an artificial intelligence model installed in the server and proposing optimal methods for putting the baby to sleep and environmental settings, a means for notifying the parent's smartphone of the suggestions from the server, a means for re-learning the artificial intelligence model using feedback data from the parent to improve model accuracy, and a means for monitoring the baby's movements, crying, and indoor environment with sensors installed in specific areas of the store and proposing appropriate responses to the parent in real time. This makes it possible to propose optimal environmental settings and actions to ensure the baby's comfort in the physical store.

[0561] "Movement" is data that detects changes in the position of the baby's entire body or parts of it.

[0562] "Crying" is data that collects the sounds made when a baby cries.

[0563] "Room temperature" is data indicating the temperature of the room where the baby is.

[0564] "Humidity" is data that indicates the amount of moisture in the air in the room where the baby is.

[0565] "Lighting intensity" is data that indicates the brightness of the room where the baby is.

[0566] The "sensors" are devices that detect baby movements, crying, room temperature, humidity, and lighting intensity.

[0567] A "terminal" is a device equipped with sensors that collects and transmits this data.

[0568] A "server" is a device that receives and stores data sent from a terminal.

[0569] An "artificial intelligence model" is software that contains algorithms that analyze and learn from collected data.

[0570] "Sleep patterns" are a collection of data that indicates the times and conditions during which a baby sleeps.

[0571] The "suggestion method" is a system that uses an artificial intelligence model to inform parents of the optimal way to put their baby to sleep and the optimal environment settings.

[0572] The "means of notification" is a mechanism that sends suggestions from the server to the parent's smartphone.

[0573] "Feedback Data" is information provided by parents regarding actual outcomes of their responses.

[0574] A "low latency communication protocol" is a communication technology for quickly transmitting data in real time.

[0575] A "specific behavior" is a specific state or behavior exhibited by a baby.

[0576] A "specific area" refers to a specific location within a physical store where a baby is located.

[0577] "Environmental settings" are environmental conditions such as temperature, humidity, and lighting that are adjusted to take into account the baby's comfort.

[0578] "Response" refers to appropriate actions and measures taken by parents in response to the baby's condition and environment.

[0579] A "suggestion" is a specific action plan generated by the server to improve the baby's comfort.

[0580] This invention is a system that monitors baby movements, crying, room temperature, humidity, lighting intensity, etc. in a physical store to support a baby's comfortable stay. This system consists of the following elements.

[0581] Hardware Configuration

[0582] Terminal: A terminal equipped with sensors that detect the baby's movements, crying, room temperature, humidity, and light intensity. This terminal is placed in a specific area where the baby is.

[0583] Server: Hardware that receives and stores data sent from sensor terminals and is equipped with an artificial intelligence model.

[0584] User's smartphone: This is the parent's smartphone, which is the device that receives suggestions from the server in real time.

[0585] Software Configuration

[0586] Data collection and management system: Software that collects data from sensors in real time and sends it to a server.

[0587] Artificial intelligence model: An algorithm installed on the server that learns and analyzes the baby's sleep patterns and comfort based on collected data. For example, TensorFlow or PyTorch is used.

[0588] Notification system: Software that sends server-generated suggestions to parents' smartphones. Notification platforms such as Firebase are used for this purpose.

[0589] User feedback system: This is an application that allows parents to input their responses to suggestions and send them back to the server.

[0590] Processing Description

[0591] First, sensor devices placed in specific areas where babies are present collect real-time environmental data, such as movement, crying, room temperature, humidity, and lighting intensity. This data is sent from the devices to a server and stored as time-series data. An artificial intelligence model installed on the server analyzes the collected data and suggests environmental settings for the baby's comfort and appropriate response actions.

[0592] Suggestions include, for example, "Your baby is crying, so please hold him / her" or "It's a little hot here, so please move to a cooler place." These suggestions are sent to the parent's smartphone in real time, allowing the parent to take action based on the notification to improve the baby's comfort.

[0593] In addition, parents can input their actual behavior into the smartphone app as feedback, which is then sent back to the server. This feedback data is then used again as training data for the AI ​​model, improving its accuracy.

[0594] Specific examples

[0595] For example, suppose a baby starts crying in a physical store. The sensor device detects this crying and sends the data to the server. The server compares it with past data and determines that the baby is crying because it is hungry. It then generates a suggestion that says, "The baby may be hungry. Please give him some milk," and sends a notification to the parent's smartphone. If the parent follows this suggestion and gives him some milk, the baby will calm down and stop crying. The parent can then provide feedback on this response, further improving the system's accuracy.

[0596] Prompt Sentence Examples

[0597] "An application that analyzes data on the crying, movements, room temperature, humidity, and lighting intensity of newborns and infants, and suggests the best way for parents to respond. For example, if a baby is crying because it is sleepy, the system will notify the parent, 'Your baby seems sleepy. Please hold him / her and try to calm him / her down.'"

[0598] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0599] Step 1:

[0600] The device detects the baby's movements, crying, room temperature, humidity, and lighting intensity. The input is real-time data from each sensor, which is processed and summarized within the device and then sent to the server. The output is a data packet sent to the server.

[0601] Step 2:

[0602] The server receives data sent from the device and stores it as time-series data. The input is the data packet sent from the device, which is stored in the database. The output is the data stored in the database.

[0603] Step 3:

[0604] The server analyzes the stored data using an artificial intelligence model to determine the baby's condition. During this process, data analysis algorithms using, for example, TensorFlow or PyTorch are executed. The input is time-series data stored in the database, which is used to analyze the baby's current condition and patterns. The output is a judgment result regarding the baby's condition.

[0605] Step 4:

[0606] The server generates an appropriate suggestion based on the analysis results. For example, if it determines that the reason the baby is crying is "sleepy," it generates the suggestion "The baby seems sleepy. Please hold him and calm him down." The input is the judgment result in step 3, and the output is the generated suggestion.

[0607] Step 5:

[0608] The server notifies the parent's smartphone of the generated suggestions. The input is the suggestion content, and the output is the notification sent to the parent's smartphone. This process uses a notification platform such as Firebase.

[0609] Step 6:

[0610] The user receives a notification on their smartphone and performs the suggested action. The input is the suggested notification displayed on the smartphone, and the output is the user's action. Specifically, the user responds according to the notification, such as holding the baby or feeding it.

[0611] Step 7:

[0612] The user inputs the results of their actual actions into the smartphone app as feedback. The input is the user's actions, which are sent to the server in an input format such as a form. The output is the feedback data sent to the server.

[0613] Step 8:

[0614] The server retrains the AI ​​model using the received feedback data to improve the model's accuracy. The input is the feedback data sent by the user, which is integrated with the existing training data to update the model. The output is an AI model with improved accuracy.

[0615] The above are the specific processing steps for carrying out the invention.

[0616] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0617] The present invention relates to a smart baby monitor system for supporting the sleep of newborns and young children, and aims to provide more effective suggestions by recognizing the user's emotions and using that feedback. This system provides support for parents and children to achieve healthy sleep, reducing stress and increasing positive experiences in childcare.

[0618] Components

[0619] This system mainly consists of four components: the terminal, the server, the user's smartphone, and the emotion engine.

[0620] Terminal

[0621] The device is equipped with sensors that detect the baby's movements, crying, room temperature, humidity, light intensity, heart rate, breathing patterns, etc. The data collected from these sensors is sent to a server in real time.

[0622] server

[0623] The server receives data sent from the device in real time and stores it in a database with a timestamp. This storage process uses a distributed database to ensure data redundancy and increase reliability. The received data is analyzed by an artificial intelligence model, which learns the baby's sleep patterns and suggests optimal methods and environmental settings for putting the baby to sleep. These suggestions include specific actions (e.g., adjusting the room temperature, playing sleep-inducing music, or giving the baby milk).

[0624] User's smartphone

[0625] The user's smartphone receives suggestions from the server in real time. When the baby exhibits a specific behavior, a notification from the server is sent to the smartphone, suggesting an appropriate response. The user also inputs the results of their actions in response to the suggestions as feedback through the smartphone app. This feedback is sent back to the server and used to improve the accuracy of the artificial intelligence model.

[0626] Emotion Engine

[0627] The emotion engine analyzes the user's voice, facial expressions, text input, etc. to recognize the user's emotions. This emotional information is used to adjust the content of suggestions. For example, if the user is feeling very stressed, it will provide suggestions that are easier than usual or have a relaxing effect. The emotional information is also sent to the server as feedback data and used to train the artificial intelligence model.

[0628] Specific examples

[0629] Example 1: Analysis and suggestions for general sleep patterns

[0630] Device: Detects when your baby wakes up frequently during the night.

[0631] Server: Compares with past data and finds that the individual is waking up more often than usual. This is considered abnormal.

[0632] Server: Notices that the temperature is below normal and generates a suggestion to increase the room temperature by 1 degree.

[0633] Emotion engine: Determines that the user's stress level is high and includes an additional suggestion to "play relaxing music."

[0634] Device: Suggestions are sent to the parent's smartphone.

[0635] User: The parent follows the suggestions to turn up the temperature and play music, and the baby wakes up less often.

[0636] Example 2: Real-time cry analysis and advice

[0637] Device: Detects when a baby starts crying.

[0638] Server: Analyzes the crying data and identifies "hunger" trends from past data.

[0639] Server: Generates the advice "Maybe he's hungry. Please give him some milk."

[0640] Emotion engine: Recognizes the user's emotions and omits detailed advice on how to feed the baby if the emotional information is positive.

[0641] Device: Advice is sent to the parent's smartphone.

[0642] User: The parent feeds the baby, and then the baby stops crying.

[0643] In this way, through the process of data collection, analysis, suggestion generation, real-time notifications, emotion recognition, and feedback collection, the system provides comprehensive support for parents and children to achieve safe and healthy sleep.

[0644] The processing flow will be explained below.

[0645] Step 1:

[0646] The device uses sensors to detect the baby's movements, crying, room temperature, humidity, light intensity, heart rate, breathing patterns, etc. This data is then sent to a server at intervals of one second.

[0647] Step 2:

[0648] The server receives data sent from the terminal in real time, timestamps it, and stores it in a database. It performs an initial analysis of the received data to check for normality and the presence of missing values.

[0649] Step 3:

[0650] The server's artificial intelligence model uses the pre-processed data to learn the baby's sleep patterns, including past data, and uses deep learning techniques to analyze the patterns and extract features.

[0651] Step 4:

[0652] The emotion engine receives data from the user's smartphone, such as the user's voice, facial expressions, and text input, and analyzes the user's emotions based on this data to identify their current emotional state.

[0653] Step 5:

[0654] The server combines the learned sleep patterns with emotional data from the emotion engine to suggest optimal sleep methods and environmental settings. For example, it generates specific actions such as setting the temperature in the baby's room to 22 degrees and playing calming music. If the user is feeling stressed, the suggestions are adjusted to be simpler and less burdensome.

[0655] Step 6:

[0656] The device sends real-time suggestions from the server to the parent's smartphone. If the baby starts crying or shows abnormal behavior, the device will quickly notify the parent based on the detected data. A low-latency communication protocol is used to minimize processing time lag.

[0657] Step 7:

[0658] The user performs the suggested actions on their smartphone and then inputs the results as feedback through the smartphone app, including the effect the action had on the baby and the user's own emotional state.

[0659] Step 8:

[0660] The server receives the feedback data and retrains the artificial intelligence model based on it, including new datasets to continually improve the accuracy of its suggestions.

[0661] Step 9:

[0662] The emotion engine again analyzes the user's emotional state and provides feedback to the server's learning process, allowing it to generate more effective suggestions that also take the user's emotional state into account.

[0663] Through these steps, the system provides comprehensive support for parents and children to achieve safe and healthy sleep, and by taking the user's emotions into consideration, it provides detailed and effective childcare support.

[0664] Example 2

[0665] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0666] In today's world, there is a need for effective systems to support baby sleep, but existing systems are unable to properly monitor the baby's condition or provide appropriate responses to parents' emotions and stress levels.To achieve healthy sleep for parents and children, reduce parenting stress, and increase positive parenting experiences, a system with more advanced data analysis and emotional feedback capabilities is needed.

[0667] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a terminal equipped with sensors that detect the baby's movements, crying, room temperature, humidity, and lighting intensity, a means for receiving and storing data transmitted from the terminal, a means for learning the baby's sleep patterns using an artificial intelligence model installed in the server and proposing optimal methods for putting the baby to sleep and environmental settings, a means for notifying the parent's smartphone of the suggestions from the server, a means for re-learning the artificial intelligence model using feedback data from the parent and improving model accuracy, and a means for analyzing the user's emotions and adjusting the suggestions. This makes it possible to analyze the baby's condition and the parent's emotions in real time and make optimal suggestions based on the results.

[0668] The "terminal" is a device equipped with sensors that detect the baby's movements, crying, room temperature, humidity, and lighting intensity.

[0669] A "server" is a computing system that receives and stores data sent from a terminal, and analyzes and processes the data using artificial intelligence models.

[0670] "Artificial intelligence model" refers to the machine learning algorithm used to learn a baby's sleep patterns and suggest optimal methods and settings for putting the baby to sleep.

[0671] "Sleep patterns" refers to behavioral data and the analysis results that show a baby's sleep habits and tendencies.

[0672] "Environmental settings" refer to conditions such as room temperature, humidity, and lighting that are necessary to support a baby's sleep.

[0673] A "smartphone" is a mobile device that receives suggestions and allows parents to enter feedback.

[0674] "Feedback data" is information entered by parents as the results of their actions and their impressions regarding the suggestions.

[0675] An "emotion engine" is a system that analyzes the user's voice, facial expressions, text input, etc. to recognize the user's emotions.

[0676] "Adjusting suggestions" is the process by which the emotion engine appropriately changes the content of suggestions based on the user's emotions.

[0677] This invention relates to a smart baby monitor system for supporting the sleep of newborns and young children. In particular, it aims to provide more effective suggestions by recognizing the user's emotions and utilizing that feedback. This system provides support for parents and children to achieve healthy sleep, reducing stress and increasing positive experiences in childcare.

[0678] Components

[0679] The system mainly consists of the following components: the terminal, the server, the user's smartphone, and the emotion engine.

[0680] Terminal

[0681] The device is equipped with sensors that detect the baby's movements, crying, room temperature, humidity, light intensity, heart rate, breathing patterns, etc. The device collects the baby's behavior and environmental data in real time and transmits it to a server via Wi-Fi or Bluetooth, allowing for a detailed understanding of the baby's current condition.

[0682] server

[0683] The server receives data sent from the device in real time and stores it in a database with a timestamp. This storage process uses a distributed database (e.g., Cassandra or MongoDB) to ensure data redundancy and increase reliability. The received data is analyzed using an artificial intelligence model (e.g., TensorFlow or PyTorch) to learn the baby's sleep patterns and suggest optimal ways to put the baby to sleep and environmental settings. These suggestions include specific actions (e.g., adjusting the room temperature, playing sleep music, or giving the baby milk).

[0684] User's smartphone

[0685] The user's smartphone receives suggestions from the server in real time. If the baby exhibits a specific behavior, a notification from the server is sent to the smartphone, suggesting an appropriate response. The user also inputs the results of their actions in response to the suggestions as feedback through the smartphone app. This feedback is sent back to the server and used to improve the accuracy of the artificial intelligence model.

[0686] Emotion Engine

[0687] The emotion engine analyzes the user's voice, facial expressions, text input, etc. to recognize the user's emotions. This emotional information is used to adjust the content of suggestions. For example, if the user is feeling very stressed, it will provide simpler actions than usual or suggestions with a relaxing effect. Emotional information is also sent to the server as feedback data and used to train the artificial intelligence model.

[0688] Specific examples

[0689] Example 1: Analysis and suggestions for general sleep patterns

[0690] Device: Detects when your baby wakes up frequently during the night.

[0691] Server: Compares with past data and finds that the individual is waking up more often than usual. This is considered abnormal.

[0692] Server: Notices that the temperature is below normal and generates a suggestion to increase the room temperature by 1 degree.

[0693] Emotion engine: Determines that the user's stress level is high and includes an additional suggestion to "play relaxing music."

[0694] Device: Suggestions are sent to the parent's smartphone.

[0695] User: The parent follows the suggestions to turn up the temperature and play music, and the baby wakes up less often.

[0696] Example 2: Real-time cry analysis and advice

[0697] Device: Detects when a baby starts crying.

[0698] Server: Analyzes the crying data and identifies "hunger" trends from past data.

[0699] Server: Generates the advice "Maybe he's hungry. Please give him some milk."

[0700] Emotion engine: Recognizes the user's emotions and omits detailed advice on how to feed the baby if the emotional information is positive.

[0701] Device: Advice is sent to the parent's smartphone.

[0702] User: The parent feeds the baby, and then the baby stops crying.

[0703] Prompt Sentence Examples

[0704] Below is an example of an input prompt sentence for the generative AI model.

[0705] "Generate an algorithm that analyzes baby crying data to determine whether or not a baby is hungry."

[0706] "Create a program that analyzes your baby's sleep patterns and suggests the best way to get them to sleep."

[0707] "How can I analyze user sentiment and tailor my suggestions?"

[0708] In this way, through the process of data collection, analysis, suggestion generation, real-time notifications, emotion recognition, and feedback collection, the system provides comprehensive support for parents and children to achieve safe and healthy sleep.

[0709] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0710] Step 1: Collect data

[0711] Description: The device detects your baby's movements, crying, room temperature, humidity, light intensity, heart rate, breathing patterns, and more.

[0712] Input: Various baby sensor data (movement, crying, room temperature, etc.).

[0713] Output: Various detected data is stored in the terminal in real time.

[0714] Specific operation: The baby's movements and environmental conditions are measured using sensors, and this data is temporarily stored in the device's internal memory.

[0715] Step 2: Sending data

[0716] Description: The device sends collected data to the server.

[0717] Input: Various sensor data stored inside the device.

[0718] Output: Various sensor data sent to the server.

[0719] Specific operation: Data collected on the device is sent to a server using Wi-Fi or Bluetooth.

[0720] Step 3: Save your data

[0721] Description: The server saves the received data in the database.

[0722] Input: Sensor data and timestamp sent from the device.

[0723] Output: Sensor data stored in a database.

[0724] Specific operation: The received data is stored in a distributed database (e.g., Cassandra, MongoDB) along with a timestamp.

[0725] Step 4: Analyze the data

[0726] Description: The server analyzes the stored data using artificial intelligence models.

[0727] Input: Sensor data stored in a database.

[0728] Output: Analysis results (baby's sleep patterns, abnormality detection, etc.).

[0729] What it does: It uses AI models such as TensorFlow and PyTorch to analyze data in the database, learn the baby's sleep patterns, and generate alerts if any abnormalities are detected.

[0730] Step 5: Generate proposals

[0731] Description: The server will suggest specific actions based on the analysis results.

[0732] Input: Analysis results (sleep patterns, abnormal conditions, etc.).

[0733] Output: Suggestions (adjust temperature, play music, etc.).

[0734] Specific actions: Based on the analysis results, specific suggestions for proper care of the baby (e.g., raising the room temperature by 1 degree, playing relaxing music, etc.) are generated.

[0735] Step 6: Sentiment Analysis

[0736] Description: The emotion engine analyzes the user's emotions.

[0737] Input: User voice, facial expressions, and text input.

[0738] Output: User's emotional state (e.g. stress level).

[0739] Specific operation: Uses voice and facial expression analysis software to analyze the user's emotions in real time and determine their current emotional state.

[0740] Step 7: Adjust the proposal

[0741] Description: The sentiment engine tailors suggestions based on the user's sentiment.

[0742] Input: User's emotional state, original suggestion.

[0743] Output: The adjusted proposal.

[0744] Specific actions: Depending on the user's stress level, the original suggestions are adjusted and additional suggestions, such as simple actions or relaxation effects, are generated as needed.

[0745] Step 8: Proposal Notification

[0746] Description: The server notifies the user of the offer on their smartphone.

[0747] Input: The adjusted proposal.

[0748] Output: Notification sent to the user's smartphone.

[0749] Specific operation: The proposal is sent to the user's smartphone using push notifications or in-app notifications.

[0750] Step 9: Gather feedback

[0751] Description: User enters feedback on a suggestion.

[0752] Input: Feedback data from users.

[0753] Output: Feedback data sent to the server.

[0754] Specific operation: Through the smartphone app, the user inputs the results and impressions of the actions taken in accordance with the suggestions, and sends these to the server.

[0755] Step 10: Analyze feedback

[0756] Description: The server receives feedback from users and uses it to improve artificial intelligence models.

[0757] Input: Feedback data.

[0758] Output: Updated artificial intelligence model, improved analysis accuracy.

[0759] Specific operation: The collected feedback data is analyzed and used as training data for the AI ​​model to improve its accuracy.

[0760] (Application example 2)

[0761] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0762] Conventional baby monitor systems are limited to monitoring a baby's sleep and health, and lack comprehensive home security or personalized responses to the user's emotions. In particular, it is difficult to detect suspicious movements or sounds, often causing anxiety and stress for parents. There is a need to resolve these situations, improve home safety, and provide a sense of security for both babies and parents.

[0763] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a terminal equipped with sensors that detect the baby's movements, crying, room temperature, humidity, and lighting intensity, a means for receiving and storing data transmitted from the terminal, a means for learning the baby's sleep patterns using an AI model and suggesting optimal sleep-training methods and environmental settings, a means for detecting suspicious movements and sounds in the home and notifying the user in real time, a means for recognizing the user's emotions and providing appropriate advice according to the situation, and a means for retraining the AI ​​model with feedback data from parents to improve the model accuracy. This makes it possible to not only manage the baby's health but also provide comprehensive home security and increase parents' sense of security.

[0764] "Baby movement" refers to the baby moving around in and around the crib.

[0765] "Crying" refers to the sounds that babies make, especially the sounds they make when crying.

[0766] "Room temperature" refers to the temperature of the air in the room where the baby is.

[0767] "Humidity" refers to the percentage of moisture in the air in the baby's room.

[0768] "Lighting intensity" refers to the intensity of the light in the room where the baby is.

[0769] "Sensors" refer to devices that detect baby movement, crying, room temperature, humidity, and lighting intensity.

[0770] "Terminal" refers to a device that has multiple sensors and collects and transmits data.

[0771] "Server" refers to a computer system that receives, stores, and analyzes data sent from a terminal.

[0772] "Artificial intelligence model" refers to machine learning algorithms and neural networks used to learn and analyze data.

[0773] "Sleep pattern" refers to a baby's sleep rhythm and cyclical behavioral patterns.

[0774] The "best sleep method" refers to the most effective way to get your baby to sleep steadily.

[0775] "Environmental setting" refers to adjusting room temperature, humidity, etc. to keep the baby comfortable.

[0776] "Real-time notification" refers to a method of notifying users as soon as data is detected.

[0777] "User emotion" refers to the emotional state of the parents or administrators using the system.

[0778] "Advice" refers to providing suggestions or suggestions to the user.

[0779] "Feedback data" refers to information that is useful for improving and adjusting the system, such as responses and impressions from users.

[0780] A "low latency communication protocol" refers to a communication protocol that allows for rapid data exchange.

[0781] This invention is a smart baby monitor and security system for the purpose of managing baby health and improving home security. This system uses the hardware and software shown below and is composed of a device connected to various sensors, a server that receives and analyzes data, and a user's smartphone that receives notifications.

[0782] Components

[0783] Terminal

[0784] The device is equipped with sensors that detect baby movements, crying, room temperature, humidity, and lighting intensity, as well as suspicious movements and sounds within the home. The data collected from these sensors is sent to a server in real time.

[0785] server

[0786] The server receives data sent from the device in real time and stores it in a database with a timestamp. This storage process uses a distributed database to ensure data redundancy and increase reliability. The received data is analyzed using artificial intelligence models such as TensorFlow and Keras to learn the baby's sleep patterns and the home situation. This information is used to generate optimal sleep methods, environmental settings, and home security recommendations.

[0787] User's smartphone

[0788] The user's smartphone receives suggestions and warnings from the server in real time. If the baby exhibits a specific behavior or if suspicious movements or sounds are detected in the home, a notification is sent from the server to the smartphone, suggesting appropriate responses. The user also inputs feedback about the results of their actions and their thoughts on the suggestions through the smartphone app. This feedback is sent back to the server and used to improve the accuracy of the artificial intelligence model.

[0789] Emotion Engine

[0790] The emotion engine analyzes the user's voice, facial expressions, text input, etc. to recognize the user's emotions. This emotional information is used to adjust the content of suggestions. For example, if the user is feeling very stressed, it will recommend suggestions that will have a relaxing effect or simple actions. The emotional information is also sent to the server as feedback data and used to train the artificial intelligence model.

[0791] Specific examples

[0792] 1. Analysis and suggestions of general sleep patterns

[0793] Device: Detects when your baby wakes up frequently during the night.

[0794] Server: Conducts comparative analysis with past data to determine if you tend to wake up more often than usual.

[0795] Server: Notices that the temperature is below normal and generates a suggestion to increase the room temperature by 1 degree.

[0796] Emotion Engine: Determines that the user's stress level is high and includes an additional suggestion to "play relaxing music."

[0797] Device: Suggestions are sent to the parent's smartphone.

[0798] User: The parent follows the suggestions to increase the temperature and play music, and the baby wakes up less often.

[0799] 2. Home security monitoring and notification

[0800] Device: Detects suspicious activity in your home at night.

[0801] Server: Using machine learning models, analyzes suspicious movements that differ from those of babies or pets.

[0802] Server: Generates an immediate alert notification if any suspicious activity is detected.

[0803] Emotion engine: If the user feels anxious, it provides advice with specific steps, such as "call the police."

[0804] Device: Sends a warning notification to the parent's smartphone.

[0805] User: Parents should check the warning notice and take action if necessary, such as reporting the incident to the police.

[0806] Example prompts to be input to the generative AI model

[0807] "Generate a model that can identify suspicious activity in the video captured by the camera. The output should return 1 if there is activity, and 0 if there is not."

[0808] As described above, this system aims to manage baby's health and improve home security through a comprehensive process of data collection, analysis, suggestion generation, real-time notification, emotion recognition, and feedback collection, providing an environment where parents and children can feel safe.

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

[0810] Step 1:

[0811] The device collects this data using sensors that detect baby movements, crying, room temperature, humidity, light intensity, and any suspicious movements or sounds.

[0812] Input: Baby movements, crying, room temperature, humidity, lighting intensity, suspicious movements and sounds

[0813] Data processing: Converting the data collected by sensors into a digital format.

[0814] Output: Various data in digital format

[0815] Step 2:

[0816] The terminal transmits the collected data to the server in real time.

[0817] Input: Various digital data

[0818] Data processing: Data is converted into packet format and encrypted for transmission.

[0819] Output: Encrypted data packet sent to the server

[0820] Step 3:

[0821] The server receives the data sent from the terminal and stores it in a database along with a timestamp.

[0822] Input: Encrypted data packet

[0823] Data processing: The data is decrypted, a timestamp is added, and it is saved in the database.

[0824] Output: Saved database entries

[0825] Step 4:

[0826] The server analyzes the stored data using artificial intelligence models.

[0827] Input: Data retrieved from a database

[0828] Data Computing: Using TensorFlow and Keras, we feed data into machine learning models to analyze baby's sleep patterns and household situations.

[0829] Output: Analysis results (baby's sleep patterns, environment settings, suspicious movements and sounds detected)

[0830] Step 5:

[0831] Based on the analysis results, the server generates optimal sleep methods, environmental settings, and home security suggestions.

[0832] Input: Analysis results

[0833] Data calculation: Based on the analysis results, an algorithm is executed to generate specific action suggestions.

[0834] Output: Specific action suggestions

[0835] Step 6:

[0836] The emotion engine analyzes the user's voice and text input to recognize the user's emotions.

[0837] Input: User voice or text input

[0838] Data Computing: Runs algorithms that analyze emotions using speech recognition and natural language processing.

[0839] Output: User's emotional state

[0840] Step 7:

[0841] The server adjusts the content of the suggestions based on the user's emotional state.

[0842] Input: User's emotional state, specific action suggestions

[0843] Data calculations: Executes algorithms that modify or emphasize suggestions depending on the user's emotions.

[0844] Output: Tailored action suggestions

[0845] Step 8:

[0846] The server notifies the user's smartphone of the generated suggestions in real time.

[0847] Input: Adjusted action proposal

[0848] Data Computation: The proposal is converted into a text message format and sent using a low-latency communication protocol.

[0849] Output: Notification displayed on the user's smartphone

[0850] Step 9:

[0851] Users input their feedback on the results of their actions and their thoughts on the suggestions via a smartphone app.

[0852] Input: User feedback information

[0853] Data calculation: Feedback information is collected as text data and sent to the server.

[0854] Output: Feedback data sent to the server

[0855] Step 10:

[0856] The server retrains the artificial intelligence model using the feedback data to improve the model accuracy.

[0857] Input: Feedback data

[0858] Data Computation: Runs algorithms that use feedback data to retrain artificial intelligence models.

[0859] Output: Updated artificial intelligence model

[0860] Through these steps, the system provides comprehensive support for baby health management and home security, providing a safe and secure environment for parents.

[0861] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0862] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0863] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0864] [Third embodiment]

[0865] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0866] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0867] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0868] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0869] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0870] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0871] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0872] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0873] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0874] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0875] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0876] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0877] This invention relates to a smart baby monitor system that learns the sleep patterns of newborns and infants and suggests optimal methods and environments for putting them to sleep. This system aims to support parents and children in achieving healthy sleep, reducing stress and increasing positive experiences in child-rearing.

[0878] This system mainly consists of three components: the terminal, the server, and the user's smartphone.

[0879] Terminal

[0880] The device is equipped with sensors that detect the baby's movements, crying, room temperature, humidity, and light intensity. The data collected from these sensors is sent to a server in real time. The device also has the ability to collect and transmit biometric data such as the baby's heart rate and breathing patterns.

[0881] server

[0882] The server receives data sent from the device and stores it with a timestamp. This stored data is analyzed by an artificial intelligence model and used to learn the baby's sleep patterns. The server compares past data with new data and suggests optimal sleep methods and environmental settings for each individual baby. These suggestions include specific actions (e.g., adjusting the room temperature, playing sleep-inducing music, or giving the baby milk).

[0883] User's smartphone

[0884] The user's smartphone receives suggestions from the server in real time. When the baby exhibits a specific behavior, a notification from the server is sent to the smartphone, suggesting an appropriate response. The user also inputs the results of their actions in response to the suggestions as feedback through the smartphone app. This feedback is sent back to the server and used to improve the accuracy of the artificial intelligence model.

[0885] Specific examples

[0886] Example 1: Analysis and suggestions for general sleep patterns

[0887] Device: Detects when your baby wakes up frequently during the night.

[0888] Server: Compares with past data and finds that the individual is waking up more often than usual. This is considered abnormal.

[0889] Server: Notices that the temperature is below normal and generates a suggestion to increase the room temperature by 1 degree.

[0890] Device: Suggestions are sent to the parent's smartphone.

[0891] User: The parent increases the temperature as suggested and the baby wakes up less often.

[0892] Example 2: Real-time cry analysis and advice

[0893] Device: Detects when a baby starts crying.

[0894] Server: Analyzes the crying data and identifies "hunger" trends from past data.

[0895] Server: Generates the advice "Maybe he's hungry. Please give him some milk."

[0896] Device: Advice is sent to the parent's smartphone.

[0897] User: The parent feeds the baby, and then the baby stops crying.

[0898] In this way, through the process of data collection, analysis, suggestion generation, real-time notifications, and feedback collection, the system provides comprehensive support to help parents and children achieve safe and healthy sleep.

[0899] The processing flow will be explained below.

[0900] Step 1:

[0901] The device uses sensors to detect the baby's movements, crying, room temperature, humidity, light intensity, heart rate, breathing pattern, etc. The collected data is then sent to a server at specific intervals (e.g., every second).

[0902] Step 2:

[0903] The server receives data sent from the terminal in real time, timestamps it, and stores it in a database. This storage process uses a distributed database to ensure data redundancy and increase reliability.

[0904] Step 3:

[0905] The server performs an initial analysis of the received data. At this stage, it performs exploratory data analysis (EDA) to check the data for normality and the presence of missing values. It also performs data cleaning and normalization as needed.

[0906] Step 4:

[0907] The server's AI model uses the initial analyzed data to learn the baby's sleep patterns. It analyzes past and new data using techniques such as deep learning to extract features (such as a tendency for the baby to cry at certain times of the day).

[0908] Step 5:

[0909] The server then suggests optimal sleep patterns and environmental settings based on the learned sleep patterns. These suggestions include specific actions (e.g., setting the room temperature to 22 degrees, playing soft music, giving milk, etc.) and converts them into a data format that can be sent to the parent's smartphone.

[0910] Step 6:

[0911] The device sends real-time suggestions from the server to the parent's smartphone. When the baby exhibits certain behaviors (crying, rapid movements, etc.), it detects them and promptly notifies the parent based on the measured data and the latest suggestions from the server. A low-latency communication protocol is used to minimize the time lag in this process.

[0912] Step 7:

[0913] The user responds to the suggestions sent to their smartphone, such as gently patting the baby's back, playing music, or preparing milk.

[0914] Step 8:

[0915] Users input the results of their actions as feedback data through a smartphone app, and this feedback is sent to the server.

[0916] Step 9:

[0917] The server then retrains the AI ​​model using the received feedback data, improving the model's accuracy with a new dataset that includes the feedback data, and retrains it to improve the effectiveness of future suggestions.

[0918] Through these steps, the system provides comprehensive support to improve sleep for parents and babies and reduce parental burden.

[0919] Example 1

[0920] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0921] In today's childcare environment, it is difficult to accurately understand the sleep patterns of newborns and young children and recommend optimal methods and environments for putting them to sleep. Many parents are unable to detect their baby's crying or abnormalities in real time, which can delay appropriate responses. In addition, there is a lack of systems that effectively incorporate feedback to improve the accuracy of sleep pattern analysis. This can increase stress in childcare and have a negative impact on the health of both parents and children.

[0922] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0923] In this invention, the server includes a means for generating a prompt message suggesting a specific action based on the results of data analysis, a means for sending the prompt message to the user's smartphone, and a means including a smartphone application for inputting feedback on the suggestion made by the user. This makes it possible to accurately grasp a baby's sleep patterns and suggest optimal measures in real time, thereby reducing stress in childcare and supporting the health of parents and children.

[0924] "Baby movements" refers to the physical displacements that occur when a baby moves their arms, legs, or body.

[0925] "Cry" refers to the sounds that babies make to indicate discomfort or needs.

[0926] "Room temperature" refers to the temperature of the air in the room where the baby is.

[0927] "Humidity" refers to the percentage of moisture in the air in the baby's environment.

[0928] "Lighting intensity" refers to the brightness of the lights in the room where the baby is.

[0929] "Sensors" refer to devices that detect baby movement, crying, room temperature, humidity, and lighting intensity.

[0930] "Terminal" refers to a device that includes sensors and collects data on the baby's movements and environment and transmits it to a server.

[0931] "Server" refers to a device that receives, stores, and analyzes data sent from a terminal.

[0932] "Artificial intelligence model" refers to an algorithm that analyzes data received from the device, learns the baby's sleep patterns, and generates optimal suggestions.

[0933] "Prompt sentence" refers to a sentence that suggests specific actions to the user based on the results of data analysis by the server.

[0934] "Feedback" refers to data that reports to the server the results and effects of actions taken by a user based on a suggestion.

[0935] "Smartphone" refers to a mobile information terminal that allows users to receive notifications from the server and enter feedback.

[0936] MODE FOR CARRYING OUT THE INVENTION

[0937] The present invention relates to a smart baby monitor system that analyzes the sleep patterns of newborns and infants in real time and suggests optimal methods for putting them to sleep and environmental settings. The system is composed of a terminal, a server, and the user's smartphone.

[0938] Terminal

[0939] The device is equipped with various sensors (e.g., accelerometer, microphone, temperature and humidity sensor, and light sensor) to detect the baby's movements, crying, room temperature, humidity, and light intensity. The data collected from these sensors is sent to a server in real time. The device also has the ability to collect biometric data such as the baby's heart rate and breathing pattern and send it with a timestamp.

[0940] server

[0941] The server receives data sent from the device and stores it in a cloud database (e.g., Amazon RDS or Google Cloud Firestore). The received data is analyzed by an artificial intelligence model implemented in Python (e.g., TensorFlow or PyTorch), which learns the baby's sleep patterns. The server compares past data with new data and suggests optimal sleep methods and environment settings for each individual baby. These suggestions are formatted as prompts and sent to the user's smartphone.

[0942] User's smartphone

[0943] The user's smartphone receives suggestions from the server in real time and displays them as notifications. The user then takes specific actions based on the suggestions and sends the results of their actions as feedback to the server via the smartphone application. This feedback is then used to improve the accuracy of the AI ​​model.

[0944] Specific examples

[0945] Example 1: Analysis and suggestions for general sleep patterns

[0946] Device: Detects when your baby wakes up frequently during the night.

[0947] Server: Compares with past data and finds that the individual is waking up more often than usual. This is considered abnormal.

[0948] Server: Notices that the temperature is below normal and generates a prompt saying "The room temperature is low, please turn the heating up by one degree."

[0949] User's smartphone: The suggestion is sent to the parent's smartphone.

[0950] User: The parent increases the temperature as suggested and the baby wakes up less often.

[0951] Example 2: Real-time cry analysis and advice

[0952] Device: Detects when a baby starts crying.

[0953] Server: Analyzes the crying data and identifies "hunger" trends from past data.

[0954] Server: Generates the prompt "Maybe he's hungry. Please give him some milk."

[0955] User's smartphone: Advice is sent to the parent's smartphone.

[0956] User: The parent feeds the baby, and then the baby stops crying.

[0957] In this way, through the process of data collection, analysis, suggestion generation, real-time notifications, and feedback collection, the system provides comprehensive support to help parents and children achieve safe and healthy sleep.

[0958] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0959] Step 1: Collect data

[0960] The device collects data using various sensors to detect the baby's movements, crying, room temperature, humidity, and lighting intensity. These sensors include an accelerometer, microphone, temperature and humidity sensor, and light sensor. The collected data is time-stamped in real time and sent to a server via Wi-Fi or Bluetooth. The input is the sensor measurement data, and the output is a time-stamped data packet. For example, if the temperature in a baby's room is 21°C and the baby starts crying, the device will collect the temperature data and crying data from the microphone.

[0961] Step 2: Save your data

[0962] The server receives data sent from the device. The received data is stored as is in a cloud database (for example, Amazon RDS or Google Cloud Firestore). The input is a time-stamped data packet, and the output is a data entry stored in the database. For example, the room temperature data of 21°C and the crying sound data are stored in the database.

[0963] Step 3: Analyze the data

[0964] The server analyzes the information stored in the database using an AI model implemented in Python (for example, TensorFlow or PyTorch). Here, the model learns the baby's sleep patterns and performs anomaly detection and pattern recognition. The input is the stored data entry, and the output is the analysis result. For example, the AI ​​model analyzes the baby's crying data and determines that the baby is hungry.

[0965] Step 4: Generate proposals

[0966] The server generates a prompt sentence based on the analysis result. The generated prompt sentence is sent to the user's smartphone. The input is the analysis result, and the output is the prompt sentence. For example, a generated prompt sentence might be "He might be hungry. Please give him some milk."

[0967] Step 5: Proposal Notification

[0968] The user's smartphone receives the prompt sentence sent from the server in real time and displays it as a notification. The input is the prompt sentence, and the output is the smartphone notification. For example, the smartphone may display a notification saying, "The baby may be hungry. Please give him some milk."

[0969] Step 6: Implementing the proposal

[0970] The user performs the suggested action based on the notification from the smartphone. The input is the notification from the smartphone, and the output is the user's specific action, for example, the user feeding the baby.

[0971] Step 7: Provide feedback

[0972] The user inputs the results of their actions based on the suggestions as feedback through a smartphone application. The input is the result of the user's actions, and the output is feedback data. For example, the user might input, "After I gave the baby milk, the baby stopped crying."

[0973] Step 8: Saving feedback and improving the model

[0974] The server receives feedback data from users and stores it in a database. It then retrains the AI ​​model based on the feedback data to improve the model's accuracy. The input is the feedback data, and the output is an improved AI model. For example, it learns more about the crying patterns of babies when they are hungry.

[0975] Through this series of processing steps, the system can monitor the baby's environment and condition in real time and suggest optimal responses to parents.

[0976] (Application example 1)

[0977] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0978] Conventional baby monitors are designed for use at home and do not provide sufficient support for parents and babies when they are out and about or in a physical store. In particular, it is difficult for parents to immediately respond to their baby's comfort and behavior in a store, which can lead to problems such as parents shortening their shopping time if the baby is uncomfortable. The objective of this invention is to provide a more comfortable environment for parents and children by monitoring baby movements, crying, and environmental data in a physical store and proposing optimal responses in real time.

[0979] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0980] In this invention, the server includes a terminal equipped with sensors that detect the baby's movements, crying, room temperature, humidity, and lighting intensity, a means for receiving and storing data transmitted from the terminal, a means for learning the baby's sleep patterns using an artificial intelligence model installed in the server and proposing optimal methods for putting the baby to sleep and environmental settings, a means for notifying the parent's smartphone of the suggestions from the server, a means for re-learning the artificial intelligence model using feedback data from the parent to improve model accuracy, and a means for monitoring the baby's movements, crying, and indoor environment with sensors installed in specific areas of the store and proposing appropriate responses to the parent in real time. This makes it possible to propose optimal environmental settings and actions to ensure the baby's comfort in the physical store.

[0981] "Movement" is data that detects changes in the position of the baby's entire body or parts of it.

[0982] "Crying" is data that collects the sounds made when a baby cries.

[0983] "Room temperature" is data indicating the temperature of the room where the baby is.

[0984] "Humidity" is data that indicates the amount of moisture in the air in the room where the baby is.

[0985] "Lighting intensity" is data that indicates the brightness of the room where the baby is.

[0986] The "sensors" are devices that detect baby movements, crying, room temperature, humidity, and lighting intensity.

[0987] A "terminal" is a device equipped with sensors that collects and transmits this data.

[0988] A "server" is a device that receives and stores data sent from a terminal.

[0989] An "artificial intelligence model" is software that contains algorithms that analyze and learn from collected data.

[0990] "Sleep patterns" are a collection of data that indicates the times and conditions during which a baby sleeps.

[0991] The "suggestion method" is a system that uses an artificial intelligence model to inform parents of the optimal way to put their baby to sleep and the optimal environment settings.

[0992] The "means of notification" is a mechanism that sends suggestions from the server to the parent's smartphone.

[0993] "Feedback Data" is information provided by parents regarding actual outcomes of their responses.

[0994] A "low latency communication protocol" is a communication technology for quickly transmitting data in real time.

[0995] A "specific behavior" is a specific state or behavior exhibited by a baby.

[0996] A "specific area" refers to a specific location within a physical store where a baby is located.

[0997] "Environmental settings" are environmental conditions such as temperature, humidity, and lighting that are adjusted to take into account the baby's comfort.

[0998] "Response" refers to appropriate actions and measures taken by parents in response to the baby's condition and environment.

[0999] A "suggestion" is a specific action plan generated by the server to improve the baby's comfort.

[1000] This invention is a system that monitors baby movements, crying, room temperature, humidity, lighting intensity, etc. in a physical store to support a baby's comfortable stay. This system consists of the following elements.

[1001] Hardware Configuration

[1002] Terminal: A terminal equipped with sensors that detect the baby's movements, crying, room temperature, humidity, and light intensity. This terminal is placed in a specific area where the baby is.

[1003] Server: Hardware that receives and stores data sent from sensor terminals and is equipped with an artificial intelligence model.

[1004] User's smartphone: This is the parent's smartphone, which is the device that receives suggestions from the server in real time.

[1005] Software Configuration

[1006] Data collection and management system: Software that collects data from sensors in real time and sends it to a server.

[1007] Artificial intelligence model: An algorithm installed on the server that learns and analyzes the baby's sleep patterns and comfort based on collected data. For example, TensorFlow or PyTorch is used.

[1008] Notification system: Software that sends server-generated suggestions to parents' smartphones. Notification platforms such as Firebase are used for this purpose.

[1009] User feedback system: This is an application that allows parents to input their responses to suggestions and send them back to the server.

[1010] Processing Description

[1011] First, sensor devices placed in specific areas where babies are present collect real-time environmental data, such as movement, crying, room temperature, humidity, and lighting intensity. This data is sent from the devices to a server and stored as time-series data. An artificial intelligence model installed on the server analyzes the collected data and suggests environmental settings for the baby's comfort and appropriate response actions.

[1012] Suggestions include, for example, "Your baby is crying, so please hold him / her" or "It's a little hot here, so please move to a cooler place." These suggestions are sent to the parent's smartphone in real time, allowing the parent to take action based on the notification to improve the baby's comfort.

[1013] In addition, parents can input their actual behavior into the smartphone app as feedback, which is then sent back to the server. This feedback data is then used again as training data for the AI ​​model, improving its accuracy.

[1014] Specific examples

[1015] For example, suppose a baby starts crying in a physical store. The sensor device detects this crying and sends the data to the server. The server compares it with past data and determines that the baby is crying because it is hungry. It then generates a suggestion that says, "The baby may be hungry. Please give him some milk," and sends a notification to the parent's smartphone. If the parent follows this suggestion and gives him some milk, the baby will calm down and stop crying. The parent can then provide feedback on this response, further improving the system's accuracy.

[1016] Prompt Sentence Examples

[1017] "An application that analyzes data on the crying, movements, room temperature, humidity, and lighting intensity of newborns and infants, and suggests the best way for parents to respond. For example, if a baby is crying because it is sleepy, the system will notify the parent, 'Your baby seems sleepy. Please hold him / her and try to calm him / her down.'"

[1018] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1019] Step 1:

[1020] The device detects the baby's movements, crying, room temperature, humidity, and lighting intensity. The input is real-time data from each sensor, which is processed and summarized within the device and then sent to the server. The output is a data packet sent to the server.

[1021] Step 2:

[1022] The server receives data sent from the device and stores it as time-series data. The input is the data packet sent from the device, which is stored in the database. The output is the data stored in the database.

[1023] Step 3:

[1024] The server analyzes the stored data using an artificial intelligence model to determine the baby's condition. During this process, data analysis algorithms using, for example, TensorFlow or PyTorch are executed. The input is time-series data stored in the database, which is used to analyze the baby's current condition and patterns. The output is a judgment result regarding the baby's condition.

[1025] Step 4:

[1026] The server generates an appropriate suggestion based on the analysis results. For example, if it determines that the reason the baby is crying is "sleepy," it generates the suggestion "The baby seems sleepy. Please hold him and calm him down." The input is the judgment result in step 3, and the output is the generated suggestion.

[1027] Step 5:

[1028] The server notifies the parent's smartphone of the generated suggestions. The input is the suggestion content, and the output is the notification sent to the parent's smartphone. This process uses a notification platform such as Firebase.

[1029] Step 6:

[1030] The user receives a notification on their smartphone and performs the suggested action. The input is the suggested notification displayed on the smartphone, and the output is the user's action. Specifically, the user responds according to the notification, such as holding the baby or feeding it.

[1031] Step 7:

[1032] The user inputs the results of their actual actions into the smartphone app as feedback. The input is the user's actions, which are sent to the server in an input format such as a form. The output is the feedback data sent to the server.

[1033] Step 8:

[1034] The server retrains the AI ​​model using the received feedback data to improve the model's accuracy. The input is the feedback data sent by the user, which is integrated with the existing training data to update the model. The output is an AI model with improved accuracy.

[1035] The above are the specific processing steps for carrying out the invention.

[1036] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1037] The present invention relates to a smart baby monitor system for supporting the sleep of newborns and young children, and aims to provide more effective suggestions by recognizing the user's emotions and using that feedback. This system provides support for parents and children to achieve healthy sleep, reducing stress and increasing positive experiences in childcare.

[1038] Components

[1039] This system mainly consists of four components: the terminal, the server, the user's smartphone, and the emotion engine.

[1040] Terminal

[1041] The device is equipped with sensors that detect the baby's movements, crying, room temperature, humidity, light intensity, heart rate, breathing patterns, etc. The data collected from these sensors is sent to a server in real time.

[1042] server

[1043] The server receives data sent from the device in real time and stores it in a database with a timestamp. This storage process uses a distributed database to ensure data redundancy and increase reliability. The received data is analyzed by an artificial intelligence model, which learns the baby's sleep patterns and suggests optimal methods and environmental settings for putting the baby to sleep. These suggestions include specific actions (e.g., adjusting the room temperature, playing sleep-inducing music, or giving the baby milk).

[1044] User's smartphone

[1045] The user's smartphone receives suggestions from the server in real time. When the baby exhibits a specific behavior, a notification from the server is sent to the smartphone, suggesting an appropriate response. The user also inputs the results of their actions in response to the suggestions as feedback through the smartphone app. This feedback is sent back to the server and used to improve the accuracy of the artificial intelligence model.

[1046] Emotion Engine

[1047] The emotion engine analyzes the user's voice, facial expressions, text input, etc. to recognize the user's emotions. This emotional information is used to adjust the content of suggestions. For example, if the user is feeling very stressed, it will provide suggestions that are easier than usual or have a relaxing effect. The emotional information is also sent to the server as feedback data and used to train the artificial intelligence model.

[1048] Specific examples

[1049] Example 1: Analysis and suggestions for general sleep patterns

[1050] Device: Detects when your baby wakes up frequently during the night.

[1051] Server: Compares with past data and finds that the individual is waking up more often than usual. This is considered abnormal.

[1052] Server: Notices that the temperature is below normal and generates a suggestion to increase the room temperature by 1 degree.

[1053] Emotion engine: Determines that the user's stress level is high and includes an additional suggestion to "play relaxing music."

[1054] Device: Suggestions are sent to the parent's smartphone.

[1055] User: The parent follows the suggestions to turn up the temperature and play music, and the baby wakes up less often.

[1056] Example 2: Real-time cry analysis and advice

[1057] Device: Detects when a baby starts crying.

[1058] Server: Analyzes the crying data and identifies "hunger" trends from past data.

[1059] Server: Generates the advice "Maybe he's hungry. Please give him some milk."

[1060] Emotion engine: Recognizes the user's emotions and omits detailed advice on how to feed the baby if the emotional information is positive.

[1061] Device: Advice is sent to the parent's smartphone.

[1062] User: The parent feeds the baby, and then the baby stops crying.

[1063] In this way, through the process of data collection, analysis, suggestion generation, real-time notifications, emotion recognition, and feedback collection, the system provides comprehensive support for parents and children to achieve safe and healthy sleep.

[1064] The processing flow will be explained below.

[1065] Step 1:

[1066] The device uses sensors to detect the baby's movements, crying, room temperature, humidity, light intensity, heart rate, breathing patterns, etc. This data is then sent to a server at intervals of one second.

[1067] Step 2:

[1068] The server receives data sent from the terminal in real time, timestamps it, and stores it in a database. It performs an initial analysis of the received data to check for normality and the presence of missing values.

[1069] Step 3:

[1070] The server's artificial intelligence model uses the pre-processed data to learn the baby's sleep patterns, including past data, and uses deep learning techniques to analyze the patterns and extract features.

[1071] Step 4:

[1072] The emotion engine receives data from the user's smartphone, such as the user's voice, facial expressions, and text input, and analyzes the user's emotions based on this data to identify their current emotional state.

[1073] Step 5:

[1074] The server combines the learned sleep patterns with emotional data from the emotion engine to suggest optimal sleep methods and environmental settings. For example, it generates specific actions such as setting the temperature in the baby's room to 22 degrees and playing calming music. If the user is feeling stressed, the suggestions are adjusted to be simpler and less burdensome.

[1075] Step 6:

[1076] The device sends real-time suggestions from the server to the parent's smartphone. If the baby starts crying or shows abnormal behavior, the device will quickly notify the parent based on the detected data. A low-latency communication protocol is used to minimize processing time lag.

[1077] Step 7:

[1078] The user performs the suggested actions on their smartphone and then inputs the results as feedback through the smartphone app, including the effect the action had on the baby and the user's own emotional state.

[1079] Step 8:

[1080] The server receives the feedback data and retrains the artificial intelligence model based on it, including new datasets to continually improve the accuracy of its suggestions.

[1081] Step 9:

[1082] The emotion engine again analyzes the user's emotional state and provides feedback to the server's learning process, allowing it to generate more effective suggestions that also take the user's emotional state into account.

[1083] Through these steps, the system provides comprehensive support for parents and children to achieve safe and healthy sleep, and by taking the user's emotions into consideration, it provides detailed and effective childcare support.

[1084] Example 2

[1085] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1086] In today's world, there is a need for effective systems to support baby sleep, but existing systems are unable to properly monitor the baby's condition or provide appropriate responses to parents' emotions and stress levels.To achieve healthy sleep for parents and children, reduce parenting stress, and increase positive parenting experiences, a system with more advanced data analysis and emotional feedback capabilities is needed.

[1087] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a terminal equipped with sensors that detect the baby's movements, crying, room temperature, humidity, and lighting intensity, a means for receiving and storing data transmitted from the terminal, a means for learning the baby's sleep patterns using an artificial intelligence model installed in the server and proposing optimal methods for putting the baby to sleep and environmental settings, a means for notifying the parent's smartphone of the suggestions from the server, a means for re-learning the artificial intelligence model using feedback data from the parent and improving model accuracy, and a means for analyzing the user's emotions and adjusting the suggestions. This makes it possible to analyze the baby's condition and the parent's emotions in real time and make optimal suggestions based on the results.

[1088] The "terminal" is a device equipped with sensors that detect the baby's movements, crying, room temperature, humidity, and lighting intensity.

[1089] A "server" is a computing system that receives and stores data sent from a terminal, and analyzes and processes the data using artificial intelligence models.

[1090] "Artificial intelligence model" refers to the machine learning algorithm used to learn a baby's sleep patterns and suggest optimal methods and settings for putting the baby to sleep.

[1091] "Sleep patterns" refers to behavioral data and the analysis results that show a baby's sleep habits and tendencies.

[1092] "Environmental settings" refer to conditions such as room temperature, humidity, and lighting that are necessary to support a baby's sleep.

[1093] A "smartphone" is a mobile device that receives suggestions and allows parents to enter feedback.

[1094] "Feedback data" is information entered by parents as the results of their actions and their impressions regarding the suggestions.

[1095] An "emotion engine" is a system that analyzes the user's voice, facial expressions, text input, etc. to recognize the user's emotions.

[1096] "Adjusting suggestions" is the process by which the emotion engine appropriately changes the content of suggestions based on the user's emotions.

[1097] This invention relates to a smart baby monitor system for supporting the sleep of newborns and young children. In particular, it aims to provide more effective suggestions by recognizing the user's emotions and utilizing that feedback. This system provides support for parents and children to achieve healthy sleep, reducing stress and increasing positive experiences in childcare.

[1098] Components

[1099] The system mainly consists of the following components: the terminal, the server, the user's smartphone, and the emotion engine.

[1100] Terminal

[1101] The device is equipped with sensors that detect the baby's movements, crying, room temperature, humidity, light intensity, heart rate, breathing patterns, etc. The device collects the baby's behavior and environmental data in real time and transmits it to a server via Wi-Fi or Bluetooth, allowing for a detailed understanding of the baby's current condition.

[1102] server

[1103] The server receives data sent from the device in real time and stores it in a database with a timestamp. This storage process uses a distributed database (e.g., Cassandra or MongoDB) to ensure data redundancy and increase reliability. The received data is analyzed using an artificial intelligence model (e.g., TensorFlow or PyTorch) to learn the baby's sleep patterns and suggest optimal ways to put the baby to sleep and environmental settings. These suggestions include specific actions (e.g., adjusting the room temperature, playing sleep music, or giving the baby milk).

[1104] User's smartphone

[1105] The user's smartphone receives suggestions from the server in real time. If the baby exhibits a specific behavior, a notification from the server is sent to the smartphone, suggesting an appropriate response. The user also inputs the results of their actions in response to the suggestions as feedback through the smartphone app. This feedback is sent back to the server and used to improve the accuracy of the artificial intelligence model.

[1106] Emotion Engine

[1107] The emotion engine analyzes the user's voice, facial expressions, text input, etc. to recognize the user's emotions. This emotional information is used to adjust the content of suggestions. For example, if the user is feeling very stressed, it will provide simpler actions than usual or suggestions with a relaxing effect. Emotional information is also sent to the server as feedback data and used to train the artificial intelligence model.

[1108] Specific examples

[1109] Example 1: Analysis and suggestions for general sleep patterns

[1110] Device: Detects when your baby wakes up frequently during the night.

[1111] Server: Compares with past data and finds that the individual is waking up more often than usual. This is considered abnormal.

[1112] Server: Notices that the temperature is below normal and generates a suggestion to increase the room temperature by 1 degree.

[1113] Emotion engine: Determines that the user's stress level is high and includes an additional suggestion to "play relaxing music."

[1114] Device: Suggestions are sent to the parent's smartphone.

[1115] User: The parent follows the suggestions to turn up the temperature and play music, and the baby wakes up less often.

[1116] Example 2: Real-time cry analysis and advice

[1117] Device: Detects when a baby starts crying.

[1118] Server: Analyzes the crying data and identifies "hunger" trends from past data.

[1119] Server: Generates the advice "Maybe he's hungry. Please give him some milk."

[1120] Emotion engine: Recognizes the user's emotions and omits detailed advice on how to feed the baby if the emotional information is positive.

[1121] Device: Advice is sent to the parent's smartphone.

[1122] User: The parent feeds the baby, and then the baby stops crying.

[1123] Prompt Sentence Examples

[1124] Below is an example of an input prompt sentence for the generative AI model.

[1125] "Generate an algorithm that analyzes baby crying data to determine whether or not a baby is hungry."

[1126] "Create a program that analyzes your baby's sleep patterns and suggests the best way to get them to sleep."

[1127] "How can I analyze user sentiment and tailor my suggestions?"

[1128] In this way, through the process of data collection, analysis, suggestion generation, real-time notifications, emotion recognition, and feedback collection, the system provides comprehensive support for parents and children to achieve safe and healthy sleep.

[1129] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1130] Step 1: Collect data

[1131] Description: The device detects your baby's movements, crying, room temperature, humidity, light intensity, heart rate, breathing patterns, and more.

[1132] Input: Various baby sensor data (movement, crying, room temperature, etc.).

[1133] Output: Various detected data is stored in the terminal in real time.

[1134] Specific operation: The baby's movements and environmental conditions are measured using sensors, and this data is temporarily stored in the device's internal memory.

[1135] Step 2: Sending data

[1136] Description: The device sends collected data to the server.

[1137] Input: Various sensor data stored inside the device.

[1138] Output: Various sensor data sent to the server.

[1139] Specific operation: Data collected on the device is sent to a server using Wi-Fi or Bluetooth.

[1140] Step 3: Save your data

[1141] Description: The server saves the received data in the database.

[1142] Input: Sensor data and timestamp sent from the device.

[1143] Output: Sensor data stored in a database.

[1144] Specific operation: The received data is stored in a distributed database (e.g., Cassandra, MongoDB) along with a timestamp.

[1145] Step 4: Analyze the data

[1146] Description: The server analyzes the stored data using artificial intelligence models.

[1147] Input: Sensor data stored in a database.

[1148] Output: Analysis results (baby's sleep patterns, abnormality detection, etc.).

[1149] What it does: It uses AI models such as TensorFlow and PyTorch to analyze data in the database, learn the baby's sleep patterns, and generate alerts if any abnormalities are detected.

[1150] Step 5: Generate proposals

[1151] Description: The server will suggest specific actions based on the analysis results.

[1152] Input: Analysis results (sleep patterns, abnormal conditions, etc.).

[1153] Output: Suggestions (adjust temperature, play music, etc.).

[1154] Specific actions: Based on the analysis results, specific suggestions for proper care of the baby (e.g., raising the room temperature by 1 degree, playing relaxing music, etc.) are generated.

[1155] Step 6: Sentiment Analysis

[1156] Description: The emotion engine analyzes the user's emotions.

[1157] Input: User voice, facial expressions, and text input.

[1158] Output: User's emotional state (e.g. stress level).

[1159] Specific operation: Uses voice and facial expression analysis software to analyze the user's emotions in real time and determine their current emotional state.

[1160] Step 7: Adjust the proposal

[1161] Description: The sentiment engine tailors suggestions based on the user's sentiment.

[1162] Input: User's emotional state, original suggestion.

[1163] Output: The adjusted proposal.

[1164] Specific actions: Depending on the user's stress level, the original suggestions are adjusted and additional suggestions, such as simple actions or relaxation effects, are generated as needed.

[1165] Step 8: Proposal Notification

[1166] Description: The server notifies the user of the offer on their smartphone.

[1167] Input: The adjusted proposal.

[1168] Output: Notification sent to the user's smartphone.

[1169] Specific operation: The proposal is sent to the user's smartphone using push notifications or in-app notifications.

[1170] Step 9: Gather feedback

[1171] Description: User enters feedback on a suggestion.

[1172] Input: Feedback data from users.

[1173] Output: Feedback data sent to the server.

[1174] Specific operation: Through the smartphone app, the user inputs the results and impressions of the actions taken in accordance with the suggestions, and sends these to the server.

[1175] Step 10: Analyze feedback

[1176] Description: The server receives feedback from users and uses it to improve artificial intelligence models.

[1177] Input: Feedback data.

[1178] Output: Updated artificial intelligence model, improved analysis accuracy.

[1179] Specific operation: The collected feedback data is analyzed and used as training data for the AI ​​model to improve its accuracy.

[1180] (Application example 2)

[1181] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1182] Conventional baby monitor systems are limited to monitoring a baby's sleep and health, and lack comprehensive home security or personalized responses to the user's emotions. In particular, it is difficult to detect suspicious movements or sounds, often causing anxiety and stress for parents. There is a need to resolve these situations, improve home safety, and provide a sense of security for both babies and parents.

[1183] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a terminal equipped with sensors that detect the baby's movements, crying, room temperature, humidity, and lighting intensity, a means for receiving and storing data transmitted from the terminal, a means for learning the baby's sleep patterns using an AI model and suggesting optimal sleep-training methods and environmental settings, a means for detecting suspicious movements and sounds in the home and notifying the user in real time, a means for recognizing the user's emotions and providing appropriate advice according to the situation, and a means for retraining the AI ​​model with feedback data from parents to improve the model accuracy. This makes it possible to not only manage the baby's health but also provide comprehensive home security and increase parents' sense of security.

[1184] "Baby movement" refers to the baby moving around in and around the crib.

[1185] "Crying" refers to the sounds that babies make, especially the sounds they make when crying.

[1186] "Room temperature" refers to the temperature of the air in the room where the baby is.

[1187] "Humidity" refers to the percentage of moisture in the air in the baby's room.

[1188] "Lighting intensity" refers to the intensity of the light in the room where the baby is.

[1189] "Sensors" refer to devices that detect baby movement, crying, room temperature, humidity, and lighting intensity.

[1190] "Terminal" refers to a device that has multiple sensors and collects and transmits data.

[1191] "Server" refers to a computer system that receives, stores, and analyzes data sent from a terminal.

[1192] "Artificial intelligence model" refers to machine learning algorithms and neural networks used to learn and analyze data.

[1193] "Sleep pattern" refers to a baby's sleep rhythm and cyclical behavioral patterns.

[1194] The "best sleep method" refers to the most effective way to get your baby to sleep steadily.

[1195] "Environmental setting" refers to adjusting room temperature, humidity, etc. to keep the baby comfortable.

[1196] "Real-time notification" refers to a method of notifying users as soon as data is detected.

[1197] "User emotion" refers to the emotional state of the parents or administrators using the system.

[1198] "Advice" refers to providing suggestions or suggestions to the user.

[1199] "Feedback data" refers to information that is useful for improving and adjusting the system, such as responses and impressions from users.

[1200] A "low latency communication protocol" refers to a communication protocol that allows for rapid data exchange.

[1201] This invention is a smart baby monitor and security system for the purpose of managing baby health and improving home security. This system uses the hardware and software shown below and is composed of a device connected to various sensors, a server that receives and analyzes data, and a user's smartphone that receives notifications.

[1202] Components

[1203] Terminal

[1204] The device is equipped with sensors that detect baby movements, crying, room temperature, humidity, and lighting intensity, as well as suspicious movements and sounds within the home. The data collected from these sensors is sent to a server in real time.

[1205] server

[1206] The server receives data sent from the device in real time and stores it in a database with a timestamp. This storage process uses a distributed database to ensure data redundancy and increase reliability. The received data is analyzed using artificial intelligence models such as TensorFlow and Keras to learn the baby's sleep patterns and the home situation. This information is used to generate optimal sleep methods, environmental settings, and home security recommendations.

[1207] User's smartphone

[1208] The user's smartphone receives suggestions and warnings from the server in real time. If the baby exhibits a specific behavior or if suspicious movements or sounds are detected in the home, a notification is sent from the server to the smartphone, suggesting appropriate responses. The user also inputs feedback about the results of their actions and their thoughts on the suggestions through the smartphone app. This feedback is sent back to the server and used to improve the accuracy of the artificial intelligence model.

[1209] Emotion Engine

[1210] The emotion engine analyzes the user's voice, facial expressions, text input, etc. to recognize the user's emotions. This emotional information is used to adjust the content of suggestions. For example, if the user is feeling very stressed, it will recommend suggestions that will have a relaxing effect or simple actions. The emotional information is also sent to the server as feedback data and used to train the artificial intelligence model.

[1211] Specific examples

[1212] 1. Analysis and suggestions of general sleep patterns

[1213] Device: Detects when your baby wakes up frequently during the night.

[1214] Server: Conducts comparative analysis with past data to determine if you tend to wake up more often than usual.

[1215] Server: Notices that the temperature is below normal and generates a suggestion to increase the room temperature by 1 degree.

[1216] Emotion Engine: Determines that the user's stress level is high and includes an additional suggestion to "play relaxing music."

[1217] Device: Suggestions are sent to the parent's smartphone.

[1218] User: The parent follows the suggestions to increase the temperature and play music, and the baby wakes up less often.

[1219] 2. Home security monitoring and notification

[1220] Device: Detects suspicious activity in your home at night.

[1221] Server: Using machine learning models, analyzes suspicious movements that differ from those of babies or pets.

[1222] Server: Generates an immediate alert notification if any suspicious activity is detected.

[1223] Emotion engine: If the user feels anxious, it provides advice with specific steps, such as "call the police."

[1224] Device: Sends a warning notification to the parent's smartphone.

[1225] User: Parents should check the warning notice and take action if necessary, such as reporting the incident to the police.

[1226] Example prompts to be input to the generative AI model

[1227] "Generate a model that can identify suspicious activity in the video captured by the camera. The output should return 1 if there is activity, and 0 if there is not."

[1228] As described above, this system aims to manage baby's health and improve home security through a comprehensive process of data collection, analysis, suggestion generation, real-time notification, emotion recognition, and feedback collection, providing an environment where parents and children can feel safe.

[1229] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1230] Step 1:

[1231] The device collects this data using sensors that detect baby movements, crying, room temperature, humidity, light intensity, and any suspicious movements or sounds.

[1232] Input: Baby movements, crying, room temperature, humidity, lighting intensity, suspicious movements and sounds

[1233] Data processing: Converting the data collected by sensors into a digital format.

[1234] Output: Various data in digital format

[1235] Step 2:

[1236] The terminal transmits the collected data to the server in real time.

[1237] Input: Various digital data

[1238] Data processing: Data is converted into packet format and encrypted for transmission.

[1239] Output: Encrypted data packet sent to the server

[1240] Step 3:

[1241] The server receives the data sent from the terminal and stores it in a database along with a timestamp.

[1242] Input: Encrypted data packet

[1243] Data processing: The data is decrypted, a timestamp is added, and it is saved in the database.

[1244] Output: Saved database entries

[1245] Step 4:

[1246] The server analyzes the stored data using artificial intelligence models.

[1247] Input: Data retrieved from a database

[1248] Data Computing: Using TensorFlow and Keras, we feed data into machine learning models to analyze baby's sleep patterns and household situations.

[1249] Output: Analysis results (baby's sleep patterns, environment settings, suspicious movements and sounds detected)

[1250] Step 5:

[1251] Based on the analysis results, the server generates optimal sleep methods, environmental settings, and home security suggestions.

[1252] Input: Analysis results

[1253] Data calculation: Based on the analysis results, an algorithm is executed to generate specific action suggestions.

[1254] Output: Specific action suggestions

[1255] Step 6:

[1256] The emotion engine analyzes the user's voice and text input to recognize the user's emotions.

[1257] Input: User voice or text input

[1258] Data Computing: Runs algorithms that analyze emotions using speech recognition and natural language processing.

[1259] Output: User's emotional state

[1260] Step 7:

[1261] The server adjusts the content of the suggestions based on the user's emotional state.

[1262] Input: User's emotional state, specific action suggestions

[1263] Data calculations: Executes algorithms that modify or emphasize suggestions depending on the user's emotions.

[1264] Output: Tailored action suggestions

[1265] Step 8:

[1266] The server notifies the user's smartphone of the generated suggestions in real time.

[1267] Input: Adjusted action proposal

[1268] Data Computation: The proposal is converted into a text message format and sent using a low-latency communication protocol.

[1269] Output: Notification displayed on the user's smartphone

[1270] Step 9:

[1271] Users input their feedback on the results of their actions and their thoughts on the suggestions via a smartphone app.

[1272] Input: User feedback information

[1273] Data calculation: Feedback information is collected as text data and sent to the server.

[1274] Output: Feedback data sent to the server

[1275] Step 10:

[1276] The server retrains the artificial intelligence model using the feedback data to improve the model accuracy.

[1277] Input: Feedback data

[1278] Data Computation: Runs algorithms that use feedback data to retrain artificial intelligence models.

[1279] Output: Updated artificial intelligence model

[1280] Through these steps, the system provides comprehensive support for baby health management and home security, providing a safe and secure environment for parents.

[1281] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1282] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1283] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1284] [Fourth embodiment]

[1285] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1286] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1287] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1288] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1289] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1290] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1291] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1292] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1293] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1294] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1295] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1296] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1297] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1298] This invention relates to a smart baby monitor system that learns the sleep patterns of newborns and infants and suggests optimal methods and environments for putting them to sleep. This system aims to support parents and children in achieving healthy sleep, reducing stress and increasing positive experiences in child-rearing.

[1299] This system mainly consists of three components: the terminal, the server, and the user's smartphone.

[1300] Terminal

[1301] The device is equipped with sensors that detect the baby's movements, crying, room temperature, humidity, and light intensity. The data collected from these sensors is sent to a server in real time. The device also has the ability to collect and transmit biometric data such as the baby's heart rate and breathing patterns.

[1302] server

[1303] The server receives data sent from the device and stores it with a timestamp. This stored data is analyzed by an artificial intelligence model and used to learn the baby's sleep patterns. The server compares past data with new data and suggests optimal sleep methods and environmental settings for each individual baby. These suggestions include specific actions (e.g., adjusting the room temperature, playing sleep-inducing music, or giving the baby milk).

[1304] User's smartphone

[1305] The user's smartphone receives suggestions from the server in real time. When the baby exhibits a specific behavior, a notification from the server is sent to the smartphone, suggesting an appropriate response. The user also inputs the results of their actions in response to the suggestions as feedback through the smartphone app. This feedback is sent back to the server and used to improve the accuracy of the artificial intelligence model.

[1306] Specific examples

[1307] Example 1: Analysis and suggestions for general sleep patterns

[1308] Device: Detects when your baby wakes up frequently during the night.

[1309] Server: Compares with past data and finds that the individual is waking up more often than usual. This is considered abnormal.

[1310] Server: Notices that the temperature is below normal and generates a suggestion to increase the room temperature by 1 degree.

[1311] Device: Suggestions are sent to the parent's smartphone.

[1312] User: The parent increases the temperature as suggested and the baby wakes up less often.

[1313] Example 2: Real-time cry analysis and advice

[1314] Device: Detects when a baby starts crying.

[1315] Server: Analyzes the crying data and identifies "hunger" trends from past data.

[1316] Server: Generates the advice "Maybe he's hungry. Please give him some milk."

[1317] Device: Advice is sent to the parent's smartphone.

[1318] User: The parent feeds the baby, and then the baby stops crying.

[1319] In this way, through the process of data collection, analysis, suggestion generation, real-time notifications, and feedback collection, the system provides comprehensive support to help parents and children achieve safe and healthy sleep.

[1320] The processing flow will be explained below.

[1321] Step 1:

[1322] The device uses sensors to detect the baby's movements, crying, room temperature, humidity, light intensity, heart rate, breathing pattern, etc. The collected data is then sent to a server at specific intervals (e.g., every second).

[1323] Step 2:

[1324] The server receives data sent from the terminal in real time, timestamps it, and stores it in a database. This storage process uses a distributed database to ensure data redundancy and increase reliability.

[1325] Step 3:

[1326] The server performs an initial analysis of the received data. At this stage, it performs exploratory data analysis (EDA) to check the data for normality and the presence of missing values. It also performs data cleaning and normalization as needed.

[1327] Step 4:

[1328] The server's AI model uses the initial analyzed data to learn the baby's sleep patterns. It analyzes past and new data using techniques such as deep learning to extract features (such as a tendency for the baby to cry at certain times of the day).

[1329] Step 5:

[1330] The server then suggests optimal sleep patterns and environmental settings based on the learned sleep patterns. These suggestions include specific actions (e.g., setting the room temperature to 22 degrees, playing soft music, giving milk, etc.) and converts them into a data format that can be sent to the parent's smartphone.

[1331] Step 6:

[1332] The device sends real-time suggestions from the server to the parent's smartphone. When the baby exhibits certain behaviors (crying, rapid movements, etc.), it detects them and promptly notifies the parent based on the measured data and the latest suggestions from the server. A low-latency communication protocol is used to minimize the time lag in this process.

[1333] Step 7:

[1334] The user responds to the suggestions sent to their smartphone, such as gently patting the baby's back, playing music, or preparing milk.

[1335] Step 8:

[1336] Users input the results of their actions as feedback data through a smartphone app, and this feedback is sent to the server.

[1337] Step 9:

[1338] The server then retrains the AI ​​model using the received feedback data, improving the model's accuracy with a new dataset that includes the feedback data, and retrains it to improve the effectiveness of future suggestions.

[1339] Through these steps, the system provides comprehensive support to improve sleep for parents and babies and reduce parental burden.

[1340] Example 1

[1341] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1342] In today's childcare environment, it is difficult to accurately understand the sleep patterns of newborns and young children and recommend optimal methods and environments for putting them to sleep. Many parents are unable to detect their baby's crying or abnormalities in real time, which can delay appropriate responses. In addition, there is a lack of systems that effectively incorporate feedback to improve the accuracy of sleep pattern analysis. This can increase stress in childcare and have a negative impact on the health of both parents and children.

[1343] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1344] In this invention, the server includes a means for generating a prompt message suggesting a specific action based on the results of data analysis, a means for sending the prompt message to the user's smartphone, and a means including a smartphone application for inputting feedback on the suggestion made by the user. This makes it possible to accurately grasp a baby's sleep patterns and suggest optimal measures in real time, thereby reducing stress in childcare and supporting the health of parents and children.

[1345] "Baby movements" refers to the physical displacements that occur when a baby moves their arms, legs, or body.

[1346] "Cry" refers to the sounds that babies make to indicate discomfort or needs.

[1347] "Room temperature" refers to the temperature of the air in the room where the baby is.

[1348] "Humidity" refers to the percentage of moisture in the air in the baby's environment.

[1349] "Lighting intensity" refers to the brightness of the lights in the room where the baby is.

[1350] "Sensors" refer to devices that detect baby movement, crying, room temperature, humidity, and lighting intensity.

[1351] "Terminal" refers to a device that includes sensors and collects data on the baby's movements and environment and transmits it to a server.

[1352] "Server" refers to a device that receives, stores, and analyzes data sent from a terminal.

[1353] "Artificial intelligence model" refers to an algorithm that analyzes data received from the device, learns the baby's sleep patterns, and generates optimal suggestions.

[1354] "Prompt sentence" refers to a sentence that suggests specific actions to the user based on the results of data analysis by the server.

[1355] "Feedback" refers to data that reports to the server the results and effects of actions taken by a user based on a suggestion.

[1356] "Smartphone" refers to a mobile information terminal that allows users to receive notifications from the server and enter feedback.

[1357] MODE FOR CARRYING OUT THE INVENTION

[1358] The present invention relates to a smart baby monitor system that analyzes the sleep patterns of newborns and infants in real time and suggests optimal methods for putting them to sleep and environmental settings. The system is composed of a terminal, a server, and the user's smartphone.

[1359] Terminal

[1360] The device is equipped with various sensors (e.g., accelerometer, microphone, temperature and humidity sensor, and light sensor) to detect the baby's movements, crying, room temperature, humidity, and light intensity. The data collected from these sensors is sent to a server in real time. The device also has the ability to collect biometric data such as the baby's heart rate and breathing pattern and send it with a timestamp.

[1361] server

[1362] The server receives data sent from the device and stores it in a cloud database (e.g., Amazon RDS or Google Cloud Firestore). The received data is analyzed by an artificial intelligence model implemented in Python (e.g., TensorFlow or PyTorch), which learns the baby's sleep patterns. The server compares past data with new data and suggests optimal sleep methods and environment settings for each individual baby. These suggestions are formatted as prompts and sent to the user's smartphone.

[1363] User's smartphone

[1364] The user's smartphone receives suggestions from the server in real time and displays them as notifications. The user then takes specific actions based on the suggestions and sends the results of their actions as feedback to the server via the smartphone application. This feedback is then used to improve the accuracy of the AI ​​model.

[1365] Specific examples

[1366] Example 1: Analysis and suggestions for general sleep patterns

[1367] Device: Detects when your baby wakes up frequently during the night.

[1368] Server: Compares with past data and finds that the individual is waking up more often than usual. This is considered abnormal.

[1369] Server: Notices that the temperature is below normal and generates a prompt saying "The room temperature is low, please turn the heating up by one degree."

[1370] User's smartphone: The suggestion is sent to the parent's smartphone.

[1371] User: The parent increases the temperature as suggested and the baby wakes up less often.

[1372] Example 2: Real-time cry analysis and advice

[1373] Device: Detects when a baby starts crying.

[1374] Server: Analyzes the crying data and identifies "hunger" trends from past data.

[1375] Server: Generates the prompt "Maybe he's hungry. Please give him some milk."

[1376] User's smartphone: Advice is sent to the parent's smartphone.

[1377] User: The parent feeds the baby, and then the baby stops crying.

[1378] In this way, through the process of data collection, analysis, suggestion generation, real-time notifications, and feedback collection, the system provides comprehensive support to help parents and children achieve safe and healthy sleep.

[1379] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1380] Step 1: Collect data

[1381] The device collects data using various sensors to detect the baby's movements, crying, room temperature, humidity, and lighting intensity. These sensors include an accelerometer, microphone, temperature and humidity sensor, and light sensor. The collected data is time-stamped in real time and sent to a server via Wi-Fi or Bluetooth. The input is the sensor measurement data, and the output is a time-stamped data packet. For example, if the temperature in a baby's room is 21°C and the baby starts crying, the device will collect the temperature data and crying data from the microphone.

[1382] Step 2: Save your data

[1383] The server receives data sent from the device. The received data is stored as is in a cloud database (for example, Amazon RDS or Google Cloud Firestore). The input is a time-stamped data packet, and the output is a data entry stored in the database. For example, the room temperature data of 21°C and the crying sound data are stored in the database.

[1384] Step 3: Analyze the data

[1385] The server analyzes the information stored in the database using an AI model implemented in Python (for example, TensorFlow or PyTorch). Here, the model learns the baby's sleep patterns and performs anomaly detection and pattern recognition. The input is the stored data entry, and the output is the analysis result. For example, the AI ​​model analyzes the baby's crying data and determines that the baby is hungry.

[1386] Step 4: Generate proposals

[1387] The server generates a prompt sentence based on the analysis result. The generated prompt sentence is sent to the user's smartphone. The input is the analysis result, and the output is the prompt sentence. For example, a generated prompt sentence might be "He might be hungry. Please give him some milk."

[1388] Step 5: Proposal Notification

[1389] The user's smartphone receives the prompt sentence sent from the server in real time and displays it as a notification. The input is the prompt sentence, and the output is the smartphone notification. For example, the smartphone may display a notification saying, "The baby may be hungry. Please give him some milk."

[1390] Step 6: Implementing the proposal

[1391] The user performs the suggested action based on the notification from the smartphone. The input is the notification from the smartphone, and the output is the user's specific action, for example, the user feeding the baby.

[1392] Step 7: Provide feedback

[1393] The user inputs the results of their actions based on the suggestions as feedback through a smartphone application. The input is the result of the user's actions, and the output is feedback data. For example, the user might input, "After I gave the baby milk, the baby stopped crying."

[1394] Step 8: Saving feedback and improving the model

[1395] The server receives feedback data from users and stores it in a database. It then retrains the AI ​​model based on the feedback data to improve the model's accuracy. The input is the feedback data, and the output is an improved AI model. For example, it learns more about the crying patterns of babies when they are hungry.

[1396] Through this series of processing steps, the system can monitor the baby's environment and condition in real time and suggest optimal responses to parents.

[1397] (Application example 1)

[1398] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1399] Conventional baby monitors are designed for use at home and do not provide sufficient support for parents and babies when they are out and about or in a physical store. In particular, it is difficult for parents to immediately respond to their baby's comfort and behavior in a store, which can lead to problems such as parents shortening their shopping time if the baby is uncomfortable. The objective of this invention is to provide a more comfortable environment for parents and children by monitoring baby movements, crying, and environmental data in a physical store and proposing optimal responses in real time.

[1400] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1401] In this invention, the server includes a terminal equipped with sensors that detect the baby's movements, crying, room temperature, humidity, and lighting intensity, a means for receiving and storing data transmitted from the terminal, a means for learning the baby's sleep patterns using an artificial intelligence model installed in the server and proposing optimal methods for putting the baby to sleep and environmental settings, a means for notifying the parent's smartphone of the suggestions from the server, a means for re-learning the artificial intelligence model using feedback data from the parent to improve model accuracy, and a means for monitoring the baby's movements, crying, and indoor environment with sensors installed in specific areas of the store and proposing appropriate responses to the parent in real time. This makes it possible to propose optimal environmental settings and actions to ensure the baby's comfort in the physical store.

[1402] "Movement" is data that detects changes in the position of the baby's entire body or parts of it.

[1403] "Crying" is data that collects the sounds made when a baby cries.

[1404] "Room temperature" is data indicating the temperature of the room where the baby is.

[1405] "Humidity" is data that indicates the amount of moisture in the air in the room where the baby is.

[1406] "Lighting intensity" is data that indicates the brightness of the room where the baby is.

[1407] The "sensors" are devices that detect baby movements, crying, room temperature, humidity, and lighting intensity.

[1408] A "terminal" is a device equipped with sensors that collects and transmits this data.

[1409] A "server" is a device that receives and stores data sent from a terminal.

[1410] An "artificial intelligence model" is software that contains algorithms that analyze and learn from collected data.

[1411] "Sleep patterns" are a collection of data that indicates the times and conditions during which a baby sleeps.

[1412] The "suggestion method" is a system that uses an artificial intelligence model to inform parents of the optimal way to put their baby to sleep and the optimal environment settings.

[1413] The "means of notification" is a mechanism that sends suggestions from the server to the parent's smartphone.

[1414] "Feedback Data" is information provided by parents regarding actual outcomes of their responses.

[1415] A "low latency communication protocol" is a communication technology for quickly transmitting data in real time.

[1416] A "specific behavior" is a specific state or behavior exhibited by a baby.

[1417] A "specific area" refers to a specific location within a physical store where a baby is located.

[1418] "Environmental settings" are environmental conditions such as temperature, humidity, and lighting that are adjusted to take into account the baby's comfort.

[1419] "Response" refers to appropriate actions and measures taken by parents in response to the baby's condition and environment.

[1420] A "suggestion" is a specific action plan generated by the server to improve the baby's comfort.

[1421] This invention is a system that monitors baby movements, crying, room temperature, humidity, lighting intensity, etc. in a physical store to support a baby's comfortable stay. This system consists of the following elements.

[1422] Hardware Configuration

[1423] Terminal: A terminal equipped with sensors that detect the baby's movements, crying, room temperature, humidity, and light intensity. This terminal is placed in a specific area where the baby is.

[1424] Server: Hardware that receives and stores data sent from sensor terminals and is equipped with an artificial intelligence model.

[1425] User's smartphone: This is the parent's smartphone, which is the device that receives suggestions from the server in real time.

[1426] Software Configuration

[1427] Data collection and management system: Software that collects data from sensors in real time and sends it to a server.

[1428] Artificial intelligence model: An algorithm installed on the server that learns and analyzes the baby's sleep patterns and comfort based on collected data. For example, TensorFlow or PyTorch is used.

[1429] Notification system: Software that sends server-generated suggestions to parents' smartphones. Notification platforms such as Firebase are used for this purpose.

[1430] User feedback system: This is an application that allows parents to input their responses to suggestions and send them back to the server.

[1431] Processing Description

[1432] First, sensor devices placed in specific areas where babies are present collect real-time environmental data, such as movement, crying, room temperature, humidity, and lighting intensity. This data is sent from the devices to a server and stored as time-series data. An artificial intelligence model installed on the server analyzes the collected data and suggests environmental settings for the baby's comfort and appropriate response actions.

[1433] Suggestions include, for example, "Your baby is crying, so please hold him / her" or "It's a little hot here, so please move to a cooler place." These suggestions are sent to the parent's smartphone in real time, allowing the parent to take action based on the notification to improve the baby's comfort.

[1434] In addition, parents can input their actual behavior into the smartphone app as feedback, which is then sent back to the server. This feedback data is then used again as training data for the AI ​​model, improving its accuracy.

[1435] Specific examples

[1436] For example, suppose a baby starts crying in a physical store. The sensor device detects this crying and sends the data to the server. The server compares it with past data and determines that the baby is crying because it is hungry. It then generates a suggestion that says, "The baby may be hungry. Please give him some milk," and sends a notification to the parent's smartphone. If the parent follows this suggestion and gives him some milk, the baby will calm down and stop crying. The parent can then provide feedback on this response, further improving the system's accuracy.

[1437] Prompt Sentence Examples

[1438] "An application that analyzes data on the crying, movements, room temperature, humidity, and lighting intensity of newborns and infants, and suggests the best way for parents to respond. For example, if a baby is crying because it is sleepy, the system will notify the parent, 'Your baby seems sleepy. Please hold him / her and try to calm him / her down.'"

[1439] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1440] Step 1:

[1441] The device detects the baby's movements, crying, room temperature, humidity, and lighting intensity. The input is real-time data from each sensor, which is processed and summarized within the device and then sent to the server. The output is a data packet sent to the server.

[1442] Step 2:

[1443] The server receives data sent from the device and stores it as time-series data. The input is the data packet sent from the device, which is stored in the database. The output is the data stored in the database.

[1444] Step 3:

[1445] The server analyzes the stored data using an artificial intelligence model to determine the baby's condition. During this process, data analysis algorithms using, for example, TensorFlow or PyTorch are executed. The input is time-series data stored in the database, which is used to analyze the baby's current condition and patterns. The output is a judgment result regarding the baby's condition.

[1446] Step 4:

[1447] The server generates an appropriate suggestion based on the analysis results. For example, if it determines that the reason the baby is crying is "sleepy," it generates the suggestion "The baby seems sleepy. Please hold him and calm him down." The input is the judgment result in step 3, and the output is the generated suggestion.

[1448] Step 5:

[1449] The server notifies the parent's smartphone of the generated suggestions. The input is the suggestion content, and the output is the notification sent to the parent's smartphone. This process uses a notification platform such as Firebase.

[1450] Step 6:

[1451] The user receives a notification on their smartphone and performs the suggested action. The input is the suggested notification displayed on the smartphone, and the output is the user's action. Specifically, the user responds according to the notification, such as holding the baby or feeding it.

[1452] Step 7:

[1453] The user inputs the results of their actual actions into the smartphone app as feedback. The input is the user's actions, which are sent to the server in an input format such as a form. The output is the feedback data sent to the server.

[1454] Step 8:

[1455] The server retrains the AI ​​model using the received feedback data to improve the model's accuracy. The input is the feedback data sent by the user, which is integrated with the existing training data to update the model. The output is an AI model with improved accuracy.

[1456] The above are the specific processing steps for carrying out the invention.

[1457] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1458] The present invention relates to a smart baby monitor system for supporting the sleep of newborns and young children, and aims to provide more effective suggestions by recognizing the user's emotions and using that feedback. This system provides support for parents and children to achieve healthy sleep, reducing stress and increasing positive experiences in childcare.

[1459] Components

[1460] This system mainly consists of four components: the terminal, the server, the user's smartphone, and the emotion engine.

[1461] Terminal

[1462] The device is equipped with sensors that detect the baby's movements, crying, room temperature, humidity, light intensity, heart rate, breathing patterns, etc. The data collected from these sensors is sent to a server in real time.

[1463] server

[1464] The server receives data sent from the device in real time and stores it in a database with a timestamp. This storage process uses a distributed database to ensure data redundancy and increase reliability. The received data is analyzed by an artificial intelligence model, which learns the baby's sleep patterns and suggests optimal methods and environmental settings for putting the baby to sleep. These suggestions include specific actions (e.g., adjusting the room temperature, playing sleep-inducing music, or giving the baby milk).

[1465] User's smartphone

[1466] The user's smartphone receives suggestions from the server in real time. When the baby exhibits a specific behavior, a notification from the server is sent to the smartphone, suggesting an appropriate response. The user also inputs the results of their actions in response to the suggestions as feedback through the smartphone app. This feedback is sent back to the server and used to improve the accuracy of the artificial intelligence model.

[1467] Emotion Engine

[1468] The emotion engine analyzes the user's voice, facial expressions, text input, etc. to recognize the user's emotions. This emotional information is used to adjust the content of suggestions. For example, if the user is feeling very stressed, it will provide suggestions that are easier than usual or have a relaxing effect. The emotional information is also sent to the server as feedback data and used to train the artificial intelligence model.

[1469] Specific examples

[1470] Example 1: Analysis and suggestions for general sleep patterns

[1471] Device: Detects when your baby wakes up frequently during the night.

[1472] Server: Compares with past data and finds that the individual is waking up more often than usual. This is considered abnormal.

[1473] Server: Notices that the temperature is below normal and generates a suggestion to increase the room temperature by 1 degree.

[1474] Emotion engine: Determines that the user's stress level is high and includes an additional suggestion to "play relaxing music."

[1475] Device: Suggestions are sent to the parent's smartphone.

[1476] User: The parent follows the suggestions to turn up the temperature and play music, and the baby wakes up less often.

[1477] Example 2: Real-time cry analysis and advice

[1478] Device: Detects when a baby starts crying.

[1479] Server: Analyzes the crying data and identifies "hunger" trends from past data.

[1480] Server: Generates the advice "Maybe he's hungry. Please give him some milk."

[1481] Emotion engine: Recognizes the user's emotions and omits detailed advice on how to feed the baby if the emotional information is positive.

[1482] Device: Advice is sent to the parent's smartphone.

[1483] User: The parent feeds the baby, and then the baby stops crying.

[1484] In this way, through the process of data collection, analysis, suggestion generation, real-time notifications, emotion recognition, and feedback collection, the system provides comprehensive support for parents and children to achieve safe and healthy sleep.

[1485] The processing flow will be explained below.

[1486] Step 1:

[1487] The device uses sensors to detect the baby's movements, crying, room temperature, humidity, light intensity, heart rate, breathing patterns, etc. This data is then sent to a server at intervals of one second.

[1488] Step 2:

[1489] The server receives data sent from the terminal in real time, timestamps it, and stores it in a database. It performs an initial analysis of the received data to check for normality and the presence of missing values.

[1490] Step 3:

[1491] The server's artificial intelligence model uses the pre-processed data to learn the baby's sleep patterns, including past data, and uses deep learning techniques to analyze the patterns and extract features.

[1492] Step 4:

[1493] The emotion engine receives data from the user's smartphone, such as the user's voice, facial expressions, and text input, and analyzes the user's emotions based on this data to identify their current emotional state.

[1494] Step 5:

[1495] The server combines the learned sleep patterns with emotional data from the emotion engine to suggest optimal sleep methods and environmental settings. For example, it generates specific actions such as setting the temperature in the baby's room to 22 degrees and playing calming music. If the user is feeling stressed, the suggestions are adjusted to be simpler and less burdensome.

[1496] Step 6:

[1497] The device sends real-time suggestions from the server to the parent's smartphone. If the baby starts crying or shows abnormal behavior, the device will quickly notify the parent based on the detected data. A low-latency communication protocol is used to minimize processing time lag.

[1498] Step 7:

[1499] The user performs the suggested actions on their smartphone and then inputs the results as feedback through the smartphone app, including the effect the action had on the baby and the user's own emotional state.

[1500] Step 8:

[1501] The server receives the feedback data and retrains the artificial intelligence model based on it, including new datasets to continually improve the accuracy of its suggestions.

[1502] Step 9:

[1503] The emotion engine again analyzes the user's emotional state and provides feedback to the server's learning process, allowing it to generate more effective suggestions that also take the user's emotional state into account.

[1504] Through these steps, the system provides comprehensive support for parents and children to achieve safe and healthy sleep, and by taking the user's emotions into consideration, it provides detailed and effective childcare support.

[1505] Example 2

[1506] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1507] In today's world, there is a need for effective systems to support baby sleep, but existing systems are unable to properly monitor the baby's condition or provide appropriate responses to parents' emotions and stress levels.To achieve healthy sleep for parents and children, reduce parenting stress, and increase positive parenting experiences, a system with more advanced data analysis and emotional feedback capabilities is needed.

[1508] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a terminal equipped with sensors that detect the baby's movements, crying, room temperature, humidity, and lighting intensity, a means for receiving and storing data transmitted from the terminal, a means for learning the baby's sleep patterns using an artificial intelligence model installed in the server and proposing optimal methods for putting the baby to sleep and environmental settings, a means for notifying the parent's smartphone of the suggestions from the server, a means for re-learning the artificial intelligence model using feedback data from the parent and improving model accuracy, and a means for analyzing the user's emotions and adjusting the suggestions. This makes it possible to analyze the baby's condition and the parent's emotions in real time and make optimal suggestions based on the results.

[1509] The "terminal" is a device equipped with sensors that detect the baby's movements, crying, room temperature, humidity, and lighting intensity.

[1510] A "server" is a computing system that receives and stores data sent from a terminal, and analyzes and processes the data using artificial intelligence models.

[1511] "Artificial intelligence model" refers to the machine learning algorithm used to learn a baby's sleep patterns and suggest optimal methods and settings for putting the baby to sleep.

[1512] "Sleep patterns" refers to behavioral data and the analysis results that show a baby's sleep habits and tendencies.

[1513] "Environmental settings" refer to conditions such as room temperature, humidity, and lighting that are necessary to support a baby's sleep.

[1514] A "smartphone" is a mobile device that receives suggestions and allows parents to enter feedback.

[1515] "Feedback data" is information entered by parents as the results of their actions and their impressions regarding the suggestions.

[1516] An "emotion engine" is a system that analyzes the user's voice, facial expressions, text input, etc. to recognize the user's emotions.

[1517] "Adjusting suggestions" is the process by which the emotion engine appropriately changes the content of suggestions based on the user's emotions.

[1518] This invention relates to a smart baby monitor system for supporting the sleep of newborns and young children. In particular, it aims to provide more effective suggestions by recognizing the user's emotions and utilizing that feedback. This system provides support for parents and children to achieve healthy sleep, reducing stress and increasing positive experiences in childcare.

[1519] Components

[1520] The system mainly consists of the following components: the terminal, the server, the user's smartphone, and the emotion engine.

[1521] Terminal

[1522] The device is equipped with sensors that detect the baby's movements, crying, room temperature, humidity, light intensity, heart rate, breathing patterns, etc. The device collects the baby's behavior and environmental data in real time and transmits it to a server via Wi-Fi or Bluetooth, allowing for a detailed understanding of the baby's current condition.

[1523] server

[1524] The server receives data sent from the device in real time and stores it in a database with a timestamp. This storage process uses a distributed database (e.g., Cassandra or MongoDB) to ensure data redundancy and increase reliability. The received data is analyzed using an artificial intelligence model (e.g., TensorFlow or PyTorch) to learn the baby's sleep patterns and suggest optimal ways to put the baby to sleep and environmental settings. These suggestions include specific actions (e.g., adjusting the room temperature, playing sleep music, or giving the baby milk).

[1525] User's smartphone

[1526] The user's smartphone receives suggestions from the server in real time. If the baby exhibits a specific behavior, a notification from the server is sent to the smartphone, suggesting an appropriate response. The user also inputs the results of their actions in response to the suggestions as feedback through the smartphone app. This feedback is sent back to the server and used to improve the accuracy of the artificial intelligence model.

[1527] Emotion Engine

[1528] The emotion engine analyzes the user's voice, facial expressions, text input, etc. to recognize the user's emotions. This emotional information is used to adjust the content of suggestions. For example, if the user is feeling very stressed, it will provide simpler actions than usual or suggestions with a relaxing effect. Emotional information is also sent to the server as feedback data and used to train the artificial intelligence model.

[1529] Specific examples

[1530] Example 1: Analysis and suggestions for general sleep patterns

[1531] Device: Detects when your baby wakes up frequently during the night.

[1532] Server: Compares with past data and finds that the individual is waking up more often than usual. This is considered abnormal.

[1533] Server: Notices that the temperature is below normal and generates a suggestion to increase the room temperature by 1 degree.

[1534] Emotion engine: Determines that the user's stress level is high and includes an additional suggestion to "play relaxing music."

[1535] Device: Suggestions are sent to the parent's smartphone.

[1536] User: The parent follows the suggestions to turn up the temperature and play music, and the baby wakes up less often.

[1537] Example 2: Real-time cry analysis and advice

[1538] Device: Detects when a baby starts crying.

[1539] Server: Analyzes the crying data and identifies "hunger" trends from past data.

[1540] Server: Generates the advice "Maybe he's hungry. Please give him some milk."

[1541] Emotion engine: Recognizes the user's emotions and omits detailed advice on how to feed the baby if the emotional information is positive.

[1542] Device: Advice is sent to the parent's smartphone.

[1543] User: The parent feeds the baby, and then the baby stops crying.

[1544] Prompt Sentence Examples

[1545] Below is an example of an input prompt sentence for the generative AI model.

[1546] "Generate an algorithm that analyzes baby crying data to determine whether or not a baby is hungry."

[1547] "Create a program that analyzes your baby's sleep patterns and suggests the best way to get them to sleep."

[1548] "How can I analyze user sentiment and tailor my suggestions?"

[1549] In this way, through the process of data collection, analysis, suggestion generation, real-time notifications, emotion recognition, and feedback collection, the system provides comprehensive support for parents and children to achieve safe and healthy sleep.

[1550] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1551] Step 1: Collect data

[1552] Description: The device detects your baby's movements, crying, room temperature, humidity, light intensity, heart rate, breathing patterns, and more.

[1553] Input: Various baby sensor data (movement, crying, room temperature, etc.).

[1554] Output: Various detected data is stored in the terminal in real time.

[1555] Specific operation: The baby's movements and environmental conditions are measured using sensors, and this data is temporarily stored in the device's internal memory.

[1556] Step 2: Sending data

[1557] Description: The device sends collected data to the server.

[1558] Input: Various sensor data stored inside the device.

[1559] Output: Various sensor data sent to the server.

[1560] Specific operation: Data collected on the device is sent to a server using Wi-Fi or Bluetooth.

[1561] Step 3: Save your data

[1562] Description: The server saves the received data in the database.

[1563] Input: Sensor data and timestamp sent from the device.

[1564] Output: Sensor data stored in a database.

[1565] Specific operation: The received data is stored in a distributed database (e.g., Cassandra, MongoDB) along with a timestamp.

[1566] Step 4: Analyze the data

[1567] Description: The server analyzes the stored data using artificial intelligence models.

[1568] Input: Sensor data stored in a database.

[1569] Output: Analysis results (baby's sleep patterns, abnormality detection, etc.).

[1570] What it does: It uses AI models such as TensorFlow and PyTorch to analyze data in the database, learn the baby's sleep patterns, and generate alerts if any abnormalities are detected.

[1571] Step 5: Generate proposals

[1572] Description: The server will suggest specific actions based on the analysis results.

[1573] Input: Analysis results (sleep patterns, abnormal conditions, etc.).

[1574] Output: Suggestions (adjust temperature, play music, etc.).

[1575] Specific actions: Based on the analysis results, specific suggestions for proper care of the baby (e.g., raising the room temperature by 1 degree, playing relaxing music, etc.) are generated.

[1576] Step 6: Sentiment Analysis

[1577] Description: The emotion engine analyzes the user's emotions.

[1578] Input: User voice, facial expressions, and text input.

[1579] Output: User's emotional state (e.g. stress level).

[1580] Specific operation: Uses voice and facial expression analysis software to analyze the user's emotions in real time and determine their current emotional state.

[1581] Step 7: Adjust the proposal

[1582] Description: The sentiment engine tailors suggestions based on the user's sentiment.

[1583] Input: User's emotional state, original suggestion.

[1584] Output: The adjusted proposal.

[1585] Specific actions: Depending on the user's stress level, the original suggestions are adjusted and additional suggestions, such as simple actions or relaxation effects, are generated as needed.

[1586] Step 8: Proposal Notification

[1587] Description: The server notifies the user of the offer on their smartphone.

[1588] Input: The adjusted proposal.

[1589] Output: Notification sent to the user's smartphone.

[1590] Specific operation: The proposal is sent to the user's smartphone using push notifications or in-app notifications.

[1591] Step 9: Gather feedback

[1592] Description: User enters feedback on a suggestion.

[1593] Input: Feedback data from users.

[1594] Output: Feedback data sent to the server.

[1595] Specific operation: Through the smartphone app, the user inputs the results and impressions of the actions taken in accordance with the suggestions, and sends these to the server.

[1596] Step 10: Analyze feedback

[1597] Description: The server receives feedback from users and uses it to improve artificial intelligence models.

[1598] Input: Feedback data.

[1599] Output: Updated artificial intelligence model, improved analysis accuracy.

[1600] Specific operation: The collected feedback data is analyzed and used as training data for the AI ​​model to improve its accuracy.

[1601] (Application example 2)

[1602] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1603] Conventional baby monitor systems are limited to monitoring a baby's sleep and health, and lack comprehensive home security or personalized responses to the user's emotions. In particular, it is difficult to detect suspicious movements or sounds, often causing anxiety and stress for parents. There is a need to resolve these situations, improve home safety, and provide a sense of security for both babies and parents.

[1604] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a terminal equipped with sensors that detect the baby's movements, crying, room temperature, humidity, and lighting intensity, a means for receiving and storing data transmitted from the terminal, a means for learning the baby's sleep patterns using an AI model and suggesting optimal sleep-training methods and environmental settings, a means for detecting suspicious movements and sounds in the home and notifying the user in real time, a means for recognizing the user's emotions and providing appropriate advice according to the situation, and a means for retraining the AI ​​model with feedback data from parents to improve the model accuracy. This makes it possible to not only manage the baby's health but also provide comprehensive home security and increase parents' sense of security.

[1605] "Baby movement" refers to the baby moving around in and around the crib.

[1606] "Crying" refers to the sounds that babies make, especially the sounds they make when crying.

[1607] "Room temperature" refers to the temperature of the air in the room where the baby is.

[1608] "Humidity" refers to the percentage of moisture in the air in the baby's room.

[1609] "Lighting intensity" refers to the intensity of the light in the room where the baby is.

[1610] "Sensors" refer to devices that detect baby movement, crying, room temperature, humidity, and lighting intensity.

[1611] "Terminal" refers to a device that has multiple sensors and collects and transmits data.

[1612] "Server" refers to a computer system that receives, stores, and analyzes data sent from a terminal.

[1613] "Artificial intelligence model" refers to machine learning algorithms and neural networks used to learn and analyze data.

[1614] "Sleep pattern" refers to a baby's sleep rhythm and cyclical behavioral patterns.

[1615] The "best sleep method" refers to the most effective way to get your baby to sleep steadily.

[1616] "Environmental setting" refers to adjusting room temperature, humidity, etc. to keep the baby comfortable.

[1617] "Real-time notification" refers to a method of notifying users as soon as data is detected.

[1618] "User emotion" refers to the emotional state of the parents or administrators using the system.

[1619] "Advice" refers to providing suggestions or suggestions to the user.

[1620] "Feedback data" refers to information that is useful for improving and adjusting the system, such as responses and impressions from users.

[1621] A "low latency communication protocol" refers to a communication protocol that allows for rapid data exchange.

[1622] This invention is a smart baby monitor and security system for the purpose of managing baby health and improving home security. This system uses the hardware and software shown below and is composed of a device connected to various sensors, a server that receives and analyzes data, and a user's smartphone that receives notifications.

[1623] Components

[1624] Terminal

[1625] The device is equipped with sensors that detect baby movements, crying, room temperature, humidity, and lighting intensity, as well as suspicious movements and sounds within the home. The data collected from these sensors is sent to a server in real time.

[1626] server

[1627] The server receives data sent from the device in real time and stores it in a database with a timestamp. This storage process uses a distributed database to ensure data redundancy and increase reliability. The received data is analyzed using artificial intelligence models such as TensorFlow and Keras to learn the baby's sleep patterns and the home situation. This information is used to generate optimal sleep methods, environmental settings, and home security recommendations.

[1628] User's smartphone

[1629] The user's smartphone receives suggestions and warnings from the server in real time. If the baby exhibits a specific behavior or if suspicious movements or sounds are detected in the home, a notification is sent from the server to the smartphone, suggesting appropriate responses. The user also inputs feedback about the results of their actions and their thoughts on the suggestions through the smartphone app. This feedback is sent back to the server and used to improve the accuracy of the artificial intelligence model.

[1630] Emotion Engine

[1631] The emotion engine analyzes the user's voice, facial expressions, text input, etc. to recognize the user's emotions. This emotional information is used to adjust the content of suggestions. For example, if the user is feeling very stressed, it will recommend suggestions that will have a relaxing effect or simple actions. The emotional information is also sent to the server as feedback data and used to train the artificial intelligence model.

[1632] Specific examples

[1633] 1. Analysis and suggestions of general sleep patterns

[1634] Device: Detects when your baby wakes up frequently during the night.

[1635] Server: Conducts comparative analysis with past data to determine if you tend to wake up more often than usual.

[1636] Server: Notices that the temperature is below normal and generates a suggestion to increase the room temperature by 1 degree.

[1637] Emotion Engine: Determines that the user's stress level is high and includes an additional suggestion to "play relaxing music."

[1638] Device: Suggestions are sent to the parent's smartphone.

[1639] User: The parent follows the suggestions to increase the temperature and play music, and the baby wakes up less often.

[1640] 2. Home security monitoring and notification

[1641] Device: Detects suspicious activity in your home at night.

[1642] Server: Using machine learning models, analyzes suspicious movements that differ from those of babies or pets.

[1643] Server: Generates an immediate alert notification if any suspicious activity is detected.

[1644] Emotion engine: If the user feels anxious, it provides advice with specific steps, such as "call the police."

[1645] Device: Sends a warning notification to the parent's smartphone.

[1646] User: Parents should check the warning notice and take action if necessary, such as reporting the incident to the police.

[1647] Example prompts to be input to the generative AI model

[1648] "Generate a model that can identify suspicious activity in the video captured by the camera. The output should return 1 if there is activity, and 0 if there is not."

[1649] As described above, this system aims to manage baby's health and improve home security through a comprehensive process of data collection, analysis, suggestion generation, real-time notification, emotion recognition, and feedback collection, providing an environment where parents and children can feel safe.

[1650] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1651] Step 1:

[1652] The device collects this data using sensors that detect baby movements, crying, room temperature, humidity, light intensity, and any suspicious movements or sounds.

[1653] Input: Baby movements, crying, room temperature, humidity, lighting intensity, suspicious movements and sounds

[1654] Data processing: Converting the data collected by sensors into a digital format.

[1655] Output: Various data in digital format

[1656] Step 2:

[1657] The terminal transmits the collected data to the server in real time.

[1658] Input: Various digital data

[1659] Data processing: Data is converted into packet format and encrypted for transmission.

[1660] Output: Encrypted data packet sent to the server

[1661] Step 3:

[1662] The server receives the data sent from the terminal and stores it in a database along with a timestamp.

[1663] Input: Encrypted data packet

[1664] Data processing: The data is decrypted, a timestamp is added, and it is saved in the database.

[1665] Output: Saved database entries

[1666] Step 4:

[1667] The server analyzes the stored data using artificial intelligence models.

[1668] Input: Data retrieved from a database

[1669] Data Computing: Using TensorFlow and Keras, we feed data into machine learning models to analyze baby's sleep patterns and household situations.

[1670] Output: Analysis results (baby's sleep patterns, environment settings, suspicious movements and sounds detected)

[1671] Step 5:

[1672] Based on the analysis results, the server generates optimal sleep methods, environmental settings, and home security suggestions.

[1673] Input: Analysis results

[1674] Data calculation: Based on the analysis results, an algorithm is executed to generate specific action suggestions.

[1675] Output: Specific action suggestions

[1676] Step 6:

[1677] The emotion engine analyzes the user's voice and text input to recognize the user's emotions.

[1678] Input: User voice or text input

[1679] Data Computing: Runs algorithms that analyze emotions using speech recognition and natural language processing.

[1680] Output: User's emotional state

[1681] Step 7:

[1682] The server adjusts the content of the suggestions based on the user's emotional state.

[1683] Input: User's emotional state, specific action suggestions

[1684] Data calculations: Executes algorithms that modify or emphasize suggestions depending on the user's emotions.

[1685] Output: Tailored action suggestions

[1686] Step 8:

[1687] The server notifies the user's smartphone of the generated suggestions in real time.

[1688] Input: Adjusted action proposal

[1689] Data Computation: The proposal is converted into a text message format and sent using a low-latency communication protocol.

[1690] Output: Notification displayed on the user's smartphone

[1691] Step 9:

[1692] Users input their feedback on the results of their actions and their thoughts on the suggestions via a smartphone app.

[1693] Input: User feedback information

[1694] Data calculation: Feedback information is collected as text data and sent to the server.

[1695] Output: Feedback data sent to the server

[1696] Step 10:

[1697] The server retrains the artificial intelligence model using the feedback data to improve the model accuracy.

[1698] Input: Feedback data

[1699] Data Computation: Runs algorithms that use feedback data to retrain artificial intelligence models.

[1700] Output: Updated artificial intelligence model

[1701] Through these steps, the system provides comprehensive support for baby health management and home security, providing a safe and secure environment for parents.

[1702] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1703] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1704] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1705] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1706] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1707] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1708] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1709] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1710] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1711] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1712] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1713] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1714] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1715] 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.

[1716] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1717] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1718] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1719] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1720] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1721] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1722] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1723] The following is further disclosed regarding the above embodiment.

[1724] (Claim 1)

[1725] A device equipped with sensors that detect baby movements, crying, room temperature, humidity, and lighting intensity.

[1726] a server that receives and stores data transmitted from the terminal;

[1727] A means for learning the baby's sleep patterns using an artificial intelligence model installed in the server and proposing optimal methods for putting the baby to sleep and environmental settings;

[1728] a means for notifying a parent's smartphone of a proposal from the server;

[1729] a means for re-learning the AI ​​model using the feedback data from the parents to improve the accuracy of the model;

[1730] A system including:

[1731] (Claim 2)

[1732] The device is characterized by comprising a means for collecting biological data such as the baby's heart rate and breathing pattern and transmitting the data to a server.

[1733] 10. The system of claim 1.

[1734] (Claim 3)

[1735] The device is characterized by comprising a means for using a low-latency communication protocol to notify the parent's smartphone in real time when the baby exhibits a specific behavior.

[1736] 10. The system of claim 1.

[1737] "Example 1"

[1738] (Claim 1)

[1739] A device equipped with sensors that detect baby movements, crying, room temperature, humidity, and lighting intensity.

[1740] a server that receives and stores data transmitted from the terminal;

[1741] A means for learning the baby's sleep patterns using an artificial intelligence model installed in the server and proposing optimal methods for putting the baby to sleep and environmental settings;

[1742] a means for notifying a parent's smartphone of a proposal from the server;

[1743] a means for re-learning the AI ​​model using the feedback data from the parents to improve the accuracy of the model;

[1744] A means for generating prompts that suggest specific actions based on the analysis of the data;

[1745] means for transmitting the prompt sentence to a user's smartphone;

[1746] means including a smartphone application for a user to input feedback on the implemented suggestions;

[1747] A system including:

[1748] (Claim 2)

[1749] The device is characterized by comprising a means for collecting biological data such as the baby's heart rate and breathing pattern and transmitting the data to a server.

[1750] 10. The system of claim 1.

[1751] (Claim 3)

[1752] The device is characterized by comprising a means for using a low-latency communication protocol to notify the parent's smartphone in real time when the baby exhibits a specific behavior.

[1753] 10. The system of claim 1.

[1754] "Application Example 1"

[1755] (Claim 1)

[1756] A device equipped with sensors that detect baby movements, crying, room temperature, humidity, and lighting intensity.

[1757] a server that receives and stores data transmitted from the terminal;

[1758] A means for learning the baby's sleep patterns using an artificial intelligence model installed in the server and proposing optimal methods for putting the baby to sleep and environmental settings;

[1759] a means for notifying a parent's smartphone of a proposal from the server;

[1760] a means for re-learning the AI ​​model using the feedback data from the parents to improve the accuracy of the model;

[1761] Sensors installed in specific areas of the store will monitor the baby's movements, crying, and indoor environment, and suggest appropriate responses to parents in real time.

[1762] A system including:

[1763] (Claim 2)

[1764] 2. The system of claim 1, further comprising means for collecting and transmitting to a server biometric data such as the baby's heart rate and breathing pattern.

[1765] (Claim 3)

[1766] 2. The system of claim 1, further comprising means for using a low-latency communication protocol to notify the parent's smartphone in real time when the baby exhibits a specific behavior.

[1767] "Example 2: Combining Emotion Engines"

[1768] (Claim 1)

[1769] A device equipped with sensors that detect baby movements, crying, room temperature, humidity, and lighting intensity.

[1770] a server that receives and stores data transmitted from the terminal;

[1771] A means for learning the baby's sleep patterns using an artificial intelligence model installed in the server and proposing optimal methods for putting the baby to sleep and environmental settings;

[1772] a means for notifying a parent's smartphone of a proposal from the server;

[1773] a means for re-learning the AI ​​model using the feedback data from the parents to improve the accuracy of the model;

[1774] means for analyzing user sentiment and adjusting said suggestions;

[1775] A system including:

[1776] (Claim 2)

[1777] The device is characterized by comprising a means for collecting biological data such as the baby's heart rate and breathing pattern and transmitting the data to a server.

[1778] 10. The system of claim 1.

[1779] (Claim 3)

[1780] The device is characterized by comprising a means for using a low-latency communication protocol to notify the parent's smartphone in real time when the baby exhibits a specific behavior.

[1781] 10. The system of claim 1.

[1782] "Application example 2 when combining emotion engines"

[1783] (Claim 1)

[1784] A device equipped with sensors that detect baby movements, crying, room temperature, humidity, and lighting intensity.

[1785] a server that receives and stores data transmitted from the terminal;

[1786] A means for learning the baby's sleep patterns using an artificial intelligence model installed in the server and proposing optimal methods for putting the baby to sleep and environmental settings;

[1787] a means for notifying a parent's smartphone of a proposal from the server;

[1788] A means to detect suspicious movements and sounds in the home and notify you in real time,

[1789] A means for recognizing the user's emotions and providing appropriate advice according to the situation;

[1790] a means for re-learning the AI ​​model using the feedback data from the parents to improve the accuracy of the model;

[1791] A system including:

[1792] (Claim 2)

[1793] 2. The system of claim 1, further comprising means for collecting and transmitting to a server biometric data such as the baby's heart rate and breathing pattern.

[1794] (Claim 3)

[1795] A means of using a low-latency communication protocol to notify parents' smartphones in real time when their baby exhibits certain behaviors;

[1796] 10. The system of claim 1, further comprising means for using a low latency communication protocol to provide real-time notification in the event of detection of suspicious activity or sounds within the home. [Explanation of symbols]

[1797] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A device equipped with sensors that detect baby movements, crying, room temperature, humidity, and lighting intensity. a server that receives and stores data transmitted from the terminal; A means for learning the baby's sleep patterns using an artificial intelligence model installed in the server and proposing optimal methods for putting the baby to sleep and environmental settings; a means for notifying a parent's smartphone of a proposal from the server; a means for re-learning the AI ​​model using the feedback data from the parents to improve the accuracy of the model; A system including:

2. The device is characterized by comprising a means for collecting biological data such as the baby's heart rate and breathing pattern and transmitting the data to a server. The system of claim 1 .

3. The device is characterized by comprising a means for using a low-latency communication protocol to notify the parent's smartphone in real time when the baby exhibits a specific behavior. The system of claim 1 .

Images