system

Abstract

Provide a system. The present invention includes a data collection means for monitoring the health status of an infant in real time; a data storage means for storing the data acquired by the data collection means in chronological order; an AI analysis means for analyzing the data stored in the data storage means and detecting abnormal patterns or danger signals; a warning generation means for generating a warning message based on the abnormality detected by the AI ​​analysis means; a warning sending means for sending the warning message generated by the warning generating means to a user terminal; a user notification means for implementing measures based on the warning message displayed on the user terminal; A system including:

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] Child abuse often occurs within the home, and detection is often delayed. Young children, in particular, are unable to assert themselves, so signs of abuse can easily go unnoticed unless the adults around them pay close attention. Furthermore, conventional abuse detection technologies struggle with real-time monitoring, making it difficult to respond quickly when an abnormality occurs. Therefore, a system is needed that can monitor the health of young children in real time and quickly issue an alert when an abnormality occurs, prompting appropriate action. [Means for solving the problem]

[0005] The present invention provides a data collection means for monitoring the health status of an infant in real time. The data collection means includes a healthcare device that measures the infant's body temperature, heart rate, movement, and ambient sound volume. It also includes a data storage means that chronologically stores the data acquired by the data collection means. It then includes an AI analysis means that analyzes the data stored in the data storage means and detects abnormal patterns or danger signals. It also includes a warning generation means that generates a warning message based on the abnormality detected by the AI ​​analysis means, and a warning transmission means that transmits this warning message to a user terminal. It also includes a user notification means that implements countermeasures based on the warning message displayed on the user terminal, making it possible to accurately monitor the infant's health status and, if an abnormality occurs, quickly issue a warning to prompt appropriate action.

[0006] "Data collection means" refers to a device or mechanism that measures and collects information on the infant's health status, such as body temperature, heart rate, movement, and ambient sound volume, in real time.

[0007] "Data storage means" refers to a device or mechanism that records and stores data acquired by data collection means in chronological order.

[0008] "AI analysis means" refers to artificial intelligence algorithms and devices or mechanisms that execute them to analyze collected data and detect abnormal patterns or danger signals.

[0009] The "warning generation means" is a device or mechanism that creates an appropriate warning message based on the abnormality detected by the AI ​​analysis means.

[0010] The "warning sending means" is a device or mechanism for sending the generated warning message to the user's terminal.

[0011] The "user notification means" is a device or mechanism that provides guidance to the user to take countermeasures based on the warning message displayed on the user's terminal.

[0012] A "healthcare device" is any device or equipment specifically designed for health care that measures an infant's temperature, heart rate, movement, and ambient sound levels. [Brief explanation of the drawings]

[0013] [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 illustrating 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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] The present invention is a system that monitors the health status of young children in real time and issues warnings to support the early detection and prevention of child abuse. Specific embodiments of this system are described below.

[0035] System Configuration

[0036] This system consists of a data collection means, a data storage means, an AI analysis means, a warning generation means, a warning transmission means, and a user notification means. By linking these means, it is possible to monitor the health status of infants with high accuracy and issue a prompt warning if an abnormality occurs.

[0037] Data collection methods

[0038] The healthcare device attached to the terminal measures the infant's body temperature, heart rate, movement, and ambient sound volume in real time. This device is equipped with precision sensors and has the ability to transmit the measurement data to a server at regular intervals (e.g., every minute).

[0039] Data storage means

[0040] The server receives the measurement data sent from the terminal and stores it in a database in chronological order. The data storage means uses a high-speed database engine, allowing the received data to be efficiently organized and stored.

[0041] AI analysis means

[0042] The server preprocesses the data stored in the database, filling in missing values ​​and removing noise. The preprocessed data is then input into an AI model to detect abnormal patterns and warning signs. The AI ​​model uses machine learning algorithms and is capable of detecting anomalies with high accuracy by comparing them with past data.

[0043] Warning generation means

[0044] The server generates a warning message based on the anomaly detected by the AI ​​analysis method. The warning message includes the type of anomaly, its severity, and appropriate action to take. For example, "Your infant's heart rate is increasing rapidly. Please contact a medical institution immediately."

[0045] Alert sending method

[0046] The server then sends the generated warning message to the user's device, such as a smartphone or tablet, which has the ability to receive and display the message in real time.

[0047] User notification method

[0048] The user receives a warning message on their device and checks its contents. The warning message contains specific countermeasures and instructions, allowing the user to take action promptly. In this way, the user can take appropriate action quickly to protect the health of their child.

[0049] Specific examples

[0050] 1. The terminal measures the infant's body temperature (37.5°C), heart rate (100 BPM), movement (at rest), and ambient sound volume (50 dB) through a healthcare device and sends the data to the server.

[0051] 2. The server stores the received data in a database and performs preprocessing.

[0052] 3. The server inputs the preprocessed data into the AI ​​model and compares it with past data to detect abnormal patterns.

[0053] 4. The server generates a warning message stating, "The infant's heart rate is abnormally high and movement is slow," and sends it to the user's device.

[0054] 5. The user should check the warning message and take appropriate measures by following the instructions provided by the app, such as "Please contact a medical institution immediately."

[0055] In this way, this system monitors the health status of young children in real time and prompts immediate action if any abnormalities are detected, thereby enabling early detection and prevention of child abuse.

[0056] The processing flow will be explained below.

[0057] Step 1:

[0058] The device measures the infant's body temperature, heart rate, movement, and ambient sound volume in real time through a healthcare device attached to the infant. The device collects this data at regular intervals (e.g., every minute) and sends it to a server.

[0059] Step 2:

[0060] The server receives the data sent from the device and stores it in a database in chronological order. The database records the time of reception and the values ​​for each measurement item in detail.

[0061] Step 3:

[0062] The server preprocesses the data stored in the database, including imputing missing data, removing noise, and standardizing the data, and then converts the preprocessed data into a format suitable for analysis.

[0063] Step 4:

[0064] The server then feeds the pre-processed data into an AI model, which uses machine learning algorithms to detect abnormal patterns and warning signs, such as a sudden increase in heart rate or sustained abnormal movements.

[0065] Step 5:

[0066] The server generates a warning message based on the anomaly detected by the AI ​​model. The warning message includes the nature of the anomaly, its severity, and a recommended course of action. For example, a message might be generated such as, "Your infant's heart rate is higher than normal and their movement is reduced. Please contact a medical professional immediately."

[0067] Step 6:

[0068] The server sends the generated warning message to the user's terminal. The warning is sent in real time so that it can be delivered to the user without delay.

[0069] Step 7:

[0070] The user receives a warning message on their device (smartphone app). The user checks the contents of the warning message and reads the detailed information.

[0071] Step 8:

[0072] The user should respond promptly by following the measures and action plans provided in the warning message, for example, by contacting a medical institution immediately and taking appropriate measures as instructed to protect the health of the infant.

[0073] This series of processing steps makes it possible to monitor the infant's health condition in real time, and if an abnormality occurs, to quickly issue an alert and prompt appropriate action.

[0074] Example 1

[0075] 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."

[0076] There is a need to accurately understand the health status of infants and respond quickly when abnormalities occur. However, existing systems often fail to adequately detect abnormalities early due to difficulties in improving data quality and detecting abnormal patterns with high accuracy. Furthermore, when generating warning messages, there is a lack of means to present appropriate responses based on the type and severity of the abnormality, making it difficult for users to respond quickly and appropriately.

[0077] 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.

[0078] In this invention, the server includes a data collection means for monitoring the infant's health condition in real time, a data storage means for storing data acquired by the data collection means in chronological order, a data preprocessing means for preprocessing the data stored in the data storage means to complement missing values ​​and remove noise, an AI analysis means for analyzing the preprocessed data and detecting abnormal patterns and danger signals, a warning generation means for generating a warning message based on an abnormality detected by the AI ​​analysis means, and a warning transmission means for transmitting the warning message generated by the warning generation means to a user terminal. This makes it possible to monitor the infant's health condition with high accuracy and to take prompt and appropriate action when an abnormality occurs.

[0079] The "data collection means" is a device for monitoring the infant's health in real time, and is a means for collecting data such as body temperature, heart rate, movement, and ambient sound volume.

[0080] "Data storage means" refers to a means for storing data acquired by data collection means in chronological order, and a means for efficiently organizing and storing data using a high-speed database engine.

[0081] The "data preprocessing means" is a means for preprocessing the data stored in the data storage means, complementing missing values, removing noise, and improving the quality of the data.

[0082] "AI analysis tools" are tools that analyze pre-processed data and use machine learning algorithms to detect abnormal patterns or red flags.

[0083] The "warning generation means" is a means for generating a warning message based on an anomaly detected by the AI ​​analysis means, and is a means for creating a message including detailed information depending on the type of anomaly and its severity.

[0084] The "warning transmission means" is a means for transmitting the warning message generated by the warning generation means to the user terminal, and is a means for delivering the message in real time.

[0085] The "user notification means" is a means for implementing countermeasures based on the warning message displayed on the user terminal, and is a means for providing instructions for the user to take appropriate action.

[0086] System Configuration

[0087] This invention is a system that monitors the health status of infants in real time, detects abnormalities, and generates and sends warning messages. The main components of the system are data collection means, data storage means, data preprocessing means, AI analysis means, warning generation means, warning transmission means, and user notification means.

[0088] Data collection methods

[0089] The healthcare device attached to the terminal measures the infant's body temperature, heart rate, movement, and ambient sound volume in real time. The device uses Bluetooth Low Energy (BLE) to transmit the data to a server every minute. For example, the device measures and collects data when the infant's body temperature is 37.5°C, heart rate is 100 BPM, movement is stationary, and ambient sound volume is 50 dB.

[0090] Data storage means

[0091] The server receives data sent from the terminal. The received data is given a timestamp and stored in a database in chronological order using a high-speed database engine such as MySQL (registered trademark) or PostgreSQL. This method allows data to be organized and stored efficiently.

[0092] Data preprocessing measures

[0093] The server preprocesses the data stored in the database. This preprocessing involves filling in missing values ​​and removing noise using the Python pandas library. This improves the quality of the data. For example, if missing values ​​are detected, peripheral data is filled in, and noisy data is removed using filtering techniques.

[0094] AI analysis means

[0095] The server then inputs the preprocessed data into an AI model, which uses machine learning libraries such as TENSORFLOW® and PyTorch to compare the data with past data to detect abnormal patterns and warning signs. For example, a sudden increase in heart rate and a lack of movement are considered abnormal.

[0096] Warning generation means

[0097] The server generates a warning message based on the abnormality detected by the AI ​​analysis method. The warning message includes the type of abnormality, its severity, and appropriate measures to take. For example, the message generated may read, "Your infant's heart rate is rapidly increasing. Please contact a medical institution immediately."

[0098] Alert sending method

[0099] The server sends the generated warning messages to the user's device using HTTP or WebSocket, and the messages are displayed in real time on smartphones and tablets, allowing users to receive the warnings immediately.

[0100] User notification method

[0101] The user receives a warning message on their device and checks its contents. The application displays the warning message in a pop-up window, providing specific countermeasures and instructions on how to respond. The user can then take prompt action. For example, they could take appropriate measures by following the instructions to "contact a medical institution immediately."

[0102] Specific examples

[0103] 1. The device measures the infant's body temperature (37.5°C), heart rate (100 BPM), movement (at rest), and ambient sound volume (50 dB) using a healthcare device, and transmits the data to the server via BLE every minute.

[0104] 2. The server stores the received data in a MySQL database, timestamps it, and organizes it.

[0105] 3. The server preprocesses the data using Python's pandas library to impute missing values ​​and remove noise.

[0106] 4. The server feeds the preprocessed data into an AI model powered by TensorFlow to detect abnormal patterns.

[0107] 5. The server generates a warning message stating "Infant's heart rate is abnormally high and movement is persistently low" and includes appropriate responses based on severity.

[0108] 6. The server sends a warning message to the user's smartphone via the HTTP protocol and displays it in real time.

[0109] 7. The user receives a warning message on their smartphone and takes appropriate measures by following the instructions to "contact a medical institution immediately."

[0110] In this way, the invention can monitor the health status of infants with high accuracy, quickly issue an alert when an abnormality occurs, and prompt appropriate measures.

[0111] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0112] Step 1:

[0113] The healthcare device attached to the terminal measures the infant's body temperature, heart rate, movement, and ambient sound volume in real time. Specifically, it collects data on body temperature (37.5°C), heart rate (100 BPM), motion (still), and ambient sound volume (50 dB). This measurement data is sent to a server via Bluetooth Low Energy (BLE) every minute.

[0114] Input: Infant temperature, heart rate, movement, and ambient sound volume data

[0115] Output: Measurement data sent to the server via BLE

[0116] Step 2:

[0117] The server receives the measurement data sent from the device, assigns a timestamp to the received data, and stores it in a database in chronological order using a high-speed database engine such as MySQL or PostgreSQL.

[0118] Input: Measurement data received via BLE

[0119] Output: Measurement data stored in a database with time stamps

[0120] Step 3:

[0121] The server preprocesses the data stored in the database. This preprocessing uses the Python pandas library to fill in missing values ​​and remove noise. For example, when a missing value is detected, it is filled in using the surrounding data, and noisy data is removed using filtering techniques.

[0122] Input: Data stored in a database

[0123] Output: Preprocessed data (after missing value imputation and noise removal)

[0124] Step 4:

[0125] The server then inputs the preprocessed data into an AI model, which uses machine learning libraries like TensorFlow and PyTorch to compare it with past data to detect unusual patterns and warning signs. For example, a spike in heart rate and lack of movement could be identified as an anomaly.

[0126] Input: Preprocessed data

[0127] Output: Detected abnormal patterns and danger signals

[0128] Step 5:

[0129] The server generates a warning message based on the anomaly detected by the AI ​​analysis method. The warning message includes the type of anomaly, its severity, and appropriate action to take. For example, a message such as "Your infant's heart rate is increasing rapidly. Please contact a medical institution immediately."

[0130] Input: Detected abnormal patterns or warning signs

[0131] Output: Generated warning message

[0132] Step 6:

[0133] The server sends the generated warning message to the user's device using HTTP or WebSocket, and the message is displayed in real time on the smartphone or tablet, allowing the user to receive the warning immediately.

[0134] Input: The generated warning message

[0135] Output: The warning message sent to the user's terminal.

[0136] Step 7:

[0137] The user receives a warning message on their device and checks its contents. The application displays a pop-up warning message with specific countermeasures and instructions on how to respond. The user can then take action promptly. For example, they can follow the instructions to "contact a medical institution immediately."

[0138] Input: The warning message sent to the user's terminal.

[0139] Output: User confirmation and prompt action

[0140] (Application example 1)

[0141] 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."

[0142] There is a growing need for systems that can monitor the health of young children in real time and issue immediate warnings when abnormalities occur. However, conventional systems have limitations in the accuracy of anomaly detection and the detail of warning messages, which means that appropriate responses are not taken promptly. There is also a need to improve the performance of AI models for anomaly detection.

[0143] 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.

[0144] In this invention, the server includes a data collection means for monitoring the infant's health condition in real time, a data storage means for chronologically storing data acquired by the data collection means, an AI analysis means for analyzing the data stored in the data storage means and detecting abnormal patterns or danger signals, a warning generation means for generating a warning message based on the abnormality detected by the AI ​​analysis means, a warning transmission means for transmitting the warning message generated by the warning generation means to a user terminal, a user notification means for taking measures based on the warning message displayed on the user terminal, and a learning means for using a prompt sentence in a generative AI model to improve the abnormality detection ability of the AI ​​analysis means. This improves the accuracy of monitoring the infant's health condition, enables appropriate warning messages to be quickly generated and sent, and enables users to respond quickly.

[0145] A "data collection means" is a device or mechanism for measuring an infant's temperature, heart rate, movement, and ambient sound volume and obtaining this data in real time.

[0146] "Data storage means" means a device or system that records and stores data acquired by data collection means in chronological order, with the purpose of storing data efficiently and safely.

[0147] "AI analysis means" means a device or program that utilizes artificial intelligence to analyze data recorded in a data storage means and detect abnormal patterns or danger signals.

[0148] The "warning generation means" is a device or program that generates a warning message based on an abnormality detected by the AI ​​analysis means.

[0149] The "alert sending means" is a communication device or system for sending the generated alert message to the user's terminal.

[0150] The "user notification means" is a device or program that provides guidance or instructions for implementing countermeasures based on the warning message displayed on the user terminal.

[0151] A "generative AI model" is a model that uses artificial intelligence learning algorithms to improve anomaly detection capabilities.

[0152] A "prompt sentence" is a textual sentence used as training data input in a generative AI model to improve the AI's ability to detect anomalies.

[0153] The present invention is a system for monitoring the health status of an infant in real time and issuing a warning if an abnormality occurs. The system includes the following means.

[0154] System Configuration

[0155] The server has a means for collecting data, a means for storing data, a means for analyzing AI, a means for generating warnings, a means for sending warnings, a means for notifying users, and a means for learning using prompt sentences in a generated AI model.

[0156] Data collection methods

[0157] The data collection tool is a healthcare device that measures the infant's temperature, heart rate, movement, and ambient sound volume in real time, and transmits this data to a server over the internet.

[0158] Data storage means

[0159] The server's data storage mechanism stores data received via the Flask API in a MySQL database in chronological order, allowing historical health data to be recorded and later analyzed.

[0160] AI analysis means

[0161] The server preprocesses the stored data, removing noise and imputing missing values. The preprocessed data is then analyzed using a TensorFlow model to detect abnormal patterns and warning signs. This AI analysis method uses a generative AI model to input training data in the form of prompt sentences, improving its anomaly detection capabilities.

[0162] Warning generation means

[0163] The server generates a warning message based on the anomaly detected by the AI ​​analysis method, including the type and severity of the anomaly and guidelines for the user to take immediate action.

[0164] Alert sending method

[0165] The server then sends the generated alert message to the user's smartphone using Firebase Cloud Messaging, allowing the user to receive the alert in real time.

[0166] User notification method

[0167] A warning message will be displayed on the user's smartphone along with specific guidelines for countermeasures. Users can follow these guidelines to quickly implement appropriate countermeasures. This method allows for rapid response to abnormalities in the infant's health.

[0168] Specific examples

[0169] The following is a specific example of how the system works. For example, suppose a healthcare device measures an infant's body temperature of 37.5°C, heart rate of 100 BPM, minimal movement, and ambient sound volume of 50 dB. This data is sent to a server and stored in a MySQL database. An abnormal condition is then detected by a TensorFlow model, which generates a warning message stating, "The infant's heart rate is abnormally high and the infant continues to exhibit minimal movement." This warning message is then sent to the user's smartphone via Firebase Cloud Messaging. The user receives the warning message and specific guidelines, allowing them to promptly contact a medical institution.

[0170] Prompt Sentence Examples

[0171] Below are some example prompts used by the generative AI model:

[0172] Prompt: Create an AI model to monitor the health of infants in real time and detect abnormal patterns or danger signals. Input data consists of body temperature, heart rate, movement, and ambient sound volume, and a warning message should be generated if an abnormality is detected.

[0173] In this way, the present invention can monitor the health condition of an infant with high accuracy, and immediately issue a warning if an abnormality occurs, thereby ensuring the safety of the infant.

[0174] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0175] Step 1:

[0176] The server receives the infant's temperature, heart rate, movement, and ambient sound volume from the healthcare devices in real time via the Internet. The health status data measured from each sensor is sent to the server as input data. The server receives this data using the Flask API.

[0177] Step 2:

[0178] The server stores the received data in a MySQL database in chronological order. The input data is the health status data received by the server, and the output is the database entries stored in chronological order. In this step, the server efficiently stores and organizes the data.

[0179] Step 3:

[0180] The server performs preprocessing on the stored data. This preprocessing includes noise removal and missing value completion. The input data is the stored health status data, and the output data is the preprocessed, clean data. The server performs data cleansing to input into the model.

[0181] Step 4:

[0182] The server inputs the preprocessed data into a TensorFlow model to detect abnormal patterns and danger signals. The input data is the preprocessed health status data, and the output data is a threshold crossing result indicating the presence or absence of abnormal patterns. The server detects abnormalities based on the model output.

[0183] Step 5:

[0184] When an anomaly is detected, the server generates a warning message using a warning generation means. The input data is the anomaly detection result, and the output data is the warning message. The generated warning message includes the type and severity of the anomaly, as well as specific countermeasure guidelines.

[0185] Step 6:

[0186] The server sends the generated warning message to the user's smartphone using Firebase Cloud Messaging. The input data is the warning message, and the output data is a notification to the user's device. The user receives the warning message in real time.

[0187] Step 7:

[0188] The user checks the received warning message and promptly takes measures according to the specific guidelines. The input data is the warning message, and the output is the execution of the measures. The user takes appropriate action, such as contacting a medical institution.

[0189] Step 8:

[0190] The server trains the generative AI model using prompt sentences to improve its anomaly detection capabilities. The input data is the training dataset and prompt sentences, and the output data is the updated AI model. Below is an example of a prompt sentence.

[0191] Prompt: Create an AI model to monitor the health of infants in real time and detect abnormal patterns or danger signals. Input data consists of body temperature, heart rate, movement, and ambient sound volume, and a warning message should be generated if an abnormality is detected.

[0192] 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.

[0193] The present invention is a system that monitors the health status of young children in real time and issues warnings to support the early detection and prevention of child abuse. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system can adjust the content and presentation method of warning messages, enabling more effective responses. A specific embodiment of this system is described below.

[0194] System Configuration

[0195] This system consists of a data collection means, a data storage means, an AI analysis means, a warning generation means, a warning transmission means, a user notification means, and an emotion engine. By linking these means, it is possible to monitor the health status of infants and the emotional state of the user in real time, and to issue a prompt warning if an abnormality occurs.

[0196] Data collection methods

[0197] The healthcare device attached to the terminal measures the infant's body temperature, heart rate, movement, and ambient sound volume in real time. This device is equipped with precise sensors and collects the measurement data at regular intervals (e.g., every minute) and sends it to a server.

[0198] Data storage means

[0199] The server receives data sent from the terminal and stores it in a database in chronological order. The data storage method uses a high-speed database engine, allowing the received data to be organized and stored efficiently.

[0200] AI analysis means

[0201] The server preprocesses the data stored in the database, filling in missing values ​​and removing noise. The preprocessed data is then input into an AI model to detect abnormal patterns and warning signs. The AI ​​model uses machine learning algorithms and is capable of detecting anomalies with high accuracy by comparing them with past data.

[0202] Emotion Engine

[0203] The emotion engine identifies the user's emotional state by analyzing their facial expressions and voice. It uses the device's built-in camera and microphone to collect user emotion data and analyzes it using an AI model.

[0204] Warning generation means

[0205] The server generates a warning message based on the anomaly detected by the AI ​​analysis method and the user's emotional state identified by the emotion engine. The warning message includes the content and severity of the anomaly, as well as recommended actions. For example, if the user is in a tense state, the warning message will be adjusted to use more polite language.

[0206] Alert sending method

[0207] The server then sends the generated warning message to the user's device, such as a smartphone or tablet, which has the ability to receive and display the message in real time.

[0208] User notification method

[0209] The user receives a warning message on their device and checks its contents. The warning message contains specific countermeasures and instructions, allowing the user to take action promptly. In this way, the user can take appropriate action quickly to protect the health of their child.

[0210] Specific examples

[0211] 1. The terminal measures the infant's body temperature (37.5°C), heart rate (100 BPM), movement (at rest), and ambient sound volume (50 dB) through a healthcare device and sends the data to the server.

[0212] 2. The server stores the received data in a database and performs preprocessing.

[0213] 3. The server inputs the preprocessed data into the AI ​​model and compares it with past data to detect abnormal patterns.

[0214] 4. The user's facial expressions and voice are collected through the device's camera and microphone, and analyzed by the emotion engine. For example, the emotion engine determines that the user is nervous.

[0215] 5. The server generates a warning message stating, "Your infant's heart rate is abnormally high and movement is persistent. Please contact a medical professional immediately." The tone of the message is gentler because the user is nervous.

[0216] 6. The server sends this message to the user's terminal.

[0217] 7. The user should check the warning message and take appropriate measures by following the instructions provided by the app, such as "Please contact a medical institution immediately."

[0218] In this way, this system monitors the health status of infants in real time and issues a warning that takes into consideration the user's emotional state if an abnormality occurs, thereby enabling early detection and prevention of child abuse.

[0219] The processing flow will be explained below.

[0220] Step 1:

[0221] The device measures the infant's body temperature, heart rate, movement, and ambient sound volume in real time through a healthcare device attached to the infant. The device collects this data at regular intervals (e.g., every minute) and sends it to a server.

[0222] Step 2:

[0223] The server receives the data sent from the device and stores it in a database in chronological order. The database records the time of reception and the values ​​for each measurement item in detail.

[0224] Step 3:

[0225] The server preprocesses the data stored in the database, including imputing missing data, removing noise, and standardizing the data, and then converts the preprocessed data into a format suitable for analysis.

[0226] Step 4:

[0227] The server then feeds the pre-processed data into an AI model, which uses machine learning algorithms to detect abnormal patterns and warning signs, such as a sudden increase in heart rate or sustained abnormal movements.

[0228] Step 5:

[0229] The device uses an on-board camera and microphone to collect the user's facial expressions and voice to recognize the user's emotions, and transmits the data to a server in real time.

[0230] Step 6:

[0231] The server receives the user's emotion data sent from the terminal and analyzes it with an emotion engine. The emotion engine analyzes the user's facial expressions and voice to identify the user's emotional state (e.g., tension, anxiety, calm, etc.).

[0232] Step 7:

[0233] The server generates a warning message based on the anomaly detected by the AI ​​model and the user's emotional state identified by the emotion engine. The warning message includes the nature of the anomaly, its severity, and a recommended response. For example, if the user is identified as nervous, a message such as "The infant's heart rate is increasing rapidly. Please remain calm and contact a medical institution immediately" is generated.

[0234] Step 8:

[0235] The server sends the generated warning message to the user's terminal. The warning is sent in real time so that it can be delivered to the user without delay.

[0236] Step 9:

[0237] The user receives a warning message on their device (smartphone app). The user checks the contents of the warning message and reads the detailed information.

[0238] Step 10:

[0239] The user should respond promptly by following the measures and action plans provided in the warning message, for example, by contacting a medical institution immediately and taking appropriate measures as instructed to protect the health of the infant.

[0240] By following the steps above, it is possible to monitor the infant's health condition and the user's emotional state in real time, and prompt a prompt and appropriate response if an abnormality occurs.

[0241] Example 2

[0242] 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."

[0243] In recent years, early detection and prevention of child abuse and health problems have become important social issues. In particular, there is a need to monitor the health status of young children in real time and take appropriate action if an abnormality is detected. However, current systems have difficulty not only monitoring the health status but also providing appropriate warning messages that take into account the emotional state of the guardian. Therefore, there is a need for a system that can analyze both the health status of young children and the emotional state of the user in real time and issue appropriate warnings.

[0244] 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 data collection means for monitoring the infant's health condition in real time; a data storage means for chronologically storing data acquired by the data collection means; a data preprocessing means for preprocessing the data stored in the data storage means; an AI analysis means for analyzing the data preprocessed by the data preprocessing means and detecting abnormal patterns or danger signals; an emotion analysis means for collecting a user's facial expressions and voice and identifying their emotional state; a warning generation means for generating a warning message based on the abnormality detected by the AI ​​analysis means and the emotional state identified by the emotion analysis means; a warning transmission means for transmitting the warning message generated by the warning generation means to a user terminal; and a user notification means for implementing measures based on the warning message displayed on the user terminal. This makes it possible to analyze both the infant's health condition and the user's emotional state in real time and issue appropriate warnings.

[0245] "Data collection means" refers to devices or mechanisms for real-time monitoring of the infant's health.

[0246] "Data storage means" refers to a system or device for storing data acquired by the data collection means in chronological order.

[0247] The "data preprocessing means" refers to a device or program for performing preprocessing such as complementing missing values ​​and removing noise on the data stored in the data storage means.

[0248] "AI analysis tools" are systems that use artificial intelligence and machine learning algorithms to analyze pre-processed data and detect abnormal patterns or warning signs.

[0249] The "emotion analysis means" is a device or program for collecting the user's facial expressions and voice and identifying the user's emotional state.

[0250] "Warning generation means" means a program or system for generating a warning message based on the abnormality detected by the AI ​​analysis means and the emotional state identified by the emotion analysis means.

[0251] The "warning transmission means" is a device or program for transmitting the generated warning message to the user terminal.

[0252] The "user notification means" is a means for implementing countermeasures based on the warning message displayed on the user terminal.

[0253] The present invention provides a system and method for monitoring the health status of infants in real time and taking prompt action when an abnormality occurs. The system is composed of a data collection means, a data storage means, a data preprocessing means, an AI analysis means, a sentiment analysis means, a warning generation means, a warning transmission means, and a user notification means.

[0254] Data collection methods

[0255] The terminal collects real-time data such as body temperature, heart rate, movement, and ambient sound volume via a healthcare device attached to the infant. This healthcare device is equipped with precision sensors and provides the measurement data to the terminal at regular intervals (e.g., every minute), which is then transmitted to a server via Bluetooth or Wi-Fi.

[0256] Data storage means

[0257] The server receives the data sent from the device and stores it in a database in chronological order. This database can efficiently organize and store data using a high-speed database engine such as MySQL or PostgreSQL.

[0258] Data preprocessing measures

[0259] The server preprocesses the data stored in the database. This preprocessing includes filling in missing values ​​and removing noise. For example, if there is temporal fluctuation in the heart rate data, it will remove it.

[0260] AI analysis means

[0261] The preprocessed data is input into an AI model built using TensorFlow and PyTorch. The server then analyzes the data using the AI ​​model to detect abnormal patterns and warning signs. This analysis requires high accuracy in detecting anomalies by comparing them with past data.

[0262] Emotion analysis means

[0263] The device collects the user's facial expressions and voice through a camera and microphone. The server inputs the collected emotional data into an AI model to identify the user's emotional state (e.g., tension, anger, relief). This allows the system to respond appropriately according to the user's emotional state.

[0264] Warning generation means

[0265] The server generates a warning message based on the abnormality detected by the AI ​​analysis means and the emotional state identified by the emotion analysis means. The warning message includes the nature of the abnormality, its severity, and recommended actions to take. For example, a message such as "The infant's heart rate is abnormally high and the infant continues to show little movement. Please contact a medical institution immediately." If the user is nervous, the tone of the message is adjusted to a gentler tone.

[0266] Alert sending method

[0267] The server sends the generated warning message to the user's device (e.g., smartphone, tablet), where it is displayed in real time.

[0268] User notification method

[0269] The user checks the warning message on the device and responds promptly based on its contents, for example, by following the instruction to "contact a medical institution immediately." In this way, the user can take prompt and appropriate action to protect the health of the infant.

[0270] Specific examples

[0271] 1. The terminal measures the infant's body temperature (37.5°C), heart rate (100 BPM), movement (at rest), and ambient sound volume (50 dB) through a healthcare device and transmits the data to the server.

[0272] 2. The server stores the received data in a database and performs preprocessing.

[0273] 3. The server inputs the preprocessed data into a TensorFlow AI model and compares it with past data to detect abnormal patterns.

[0274] 4. The user's facial expressions and voice are collected through the device's camera and microphone, and analyzed by the emotion engine. For example, the emotion engine determines that the user is nervous.

[0275] 5. The server generates a warning message stating, "Your infant's heart rate is abnormally high and movement is persistent. Please contact a medical professional immediately." The tone of the message is gentler because the user is nervous.

[0276] 6. The server sends this message to the user's terminal.

[0277] 7. The user should check the warning message and take appropriate measures by following the instructions provided by the app, such as "Please contact a medical institution immediately."

[0278] In this way, this system monitors the health status of young children in real time and issues a warning that takes into account the user's emotional state if an abnormality occurs, thereby supporting the early detection and prevention of child abuse.

[0279] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0280] Step 1: Data collection

[0281] The terminal acquires data from a healthcare device attached to the infant. The terminal collects data such as body temperature, heart rate, movement, and ambient sound volume in real time. For example, the infant's body temperature is 37.5°C, heart rate is 100 BPM, movement is stationary, and ambient sound volume is 50 dB. The device is equipped with precision sensors and provides data to the terminal at regular intervals (e.g., every minute).

[0282] Input: Infant's physical information (temperature, heart rate, movement, sound volume)

[0283] Output: A set of health data (e.g., body temperature 37.5°C, heart rate 100 BPM, resting state, 50 dB)

[0284] Step 2: Send data

[0285] The device sends the acquired data to the server. The device sends the collected data to the server using Bluetooth or Wi-Fi.

[0286] Input: A set of collected health data

[0287] Output: Health data sent to the server

[0288] Step 3: Save data

[0289] The server stores the received data in a database. The server uses a database engine such as MySQL or PostgreSQL to organize and store the data in chronological order.

[0290] Input: Health data sent from the device

[0291] Output: Time series data stored in a database

[0292] Step 4: Data Preprocessing

[0293] The server preprocesses the stored data, filling in missing values ​​and removing noise. For example, if there is a temporal fluctuation in the heart rate data, it removes it.

[0294] Input: Time series data stored in a database

[0295] Output: Preprocessed and clean data

[0296] Step 5: AI analysis

[0297] The server then inputs the preprocessed data into an AI model, built using TensorFlow and PyTorch, that detects abnormal patterns and warning signs, such as identifying abnormal heart rate data.

[0298] Input: Preprocessed and clean data

[0299] Output: Anomaly detection results from the AI ​​model

[0300] Step 6: Sentiment Analysis

[0301] The device collects the user's facial expressions and voice using the device's camera and microphone. For example, the camera can capture the user's nervousness.

[0302] Input: User facial and voice data

[0303] Output: Collected emotion data

[0304] Step 7: Sentiment analysis

[0305] The server inputs the emotional data into an AI model to analyze the user's emotional state, for example, determining whether the user is nervous, angry, relieved, etc.

[0306] Input: Emotion data obtained from the device

[0307] Output: Sentiment analysis result (e.g. "I'm nervous")

[0308] Step 8: Generate warnings

[0309] The server generates a warning message based on the results of anomaly detection and emotion analysis. For example, it creates a warning message such as "The infant's heart rate is abnormally high and the infant's movement is still low. Please contact a medical institution immediately." If the user is nervous, it adjusts the tone of the message to a gentler tone.

[0310] Input: Anomaly detection results, sentiment analysis results

[0311] Output: Adjusted warning message

[0312] Step 9: Send alert

[0313] The server then sends the generated warning message to the user's device, which then sends the warning message to the user's smartphone or tablet in real time.

[0314] Input: Adjusted warning message

[0315] Output: Warning message displayed on the user's terminal

[0316] Step 10: User notification and response

[0317] The user checks the warning message on the device and takes prompt action based on the warning message, for example, by following the instructions to "contact a medical institution."

[0318] Input: The warning message displayed on the user's terminal

[0319] Output: Appropriate user action (e.g., contacting a medical facility)

[0320] (Application example 2)

[0321] 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."

[0322] For the purpose of early detection and prevention of child abuse and health abnormalities, it is necessary to monitor the health status of children in real time and promptly and accurately respond when abnormalities are detected. However, conventional systems are unable to provide warning messages that take the user's emotional state into account, which can lead to delays in appropriate responses. Another challenge is providing warning messages in a format that is easy for users to understand.

[0323] The identification processing by the identification 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: data collection means for monitoring the infant's health condition in real time; data storage means for chronologically storing data acquired by the data collection means; AI analysis means for analyzing the data stored in the data storage means and detecting abnormal patterns or danger signals; emotion analysis means for analyzing the user's emotional state; warning generation means for generating a warning message based on the abnormality detected by the AI ​​analysis means and the user's emotional state identified by the emotion analysis means; warning transmission means for transmitting the warning message generated by the warning generation means to a user terminal; and user notification means for implementing measures based on the warning message displayed on the user terminal. This makes it possible to quickly detect abnormalities in the infant's health condition, provide a warning message that takes into account the user's emotional state, and take prompt and appropriate action.

[0324] "Data collection means" refers to equipment or devices that collect data such as body temperature, heart rate, movement, and ambient sound levels to monitor the infant's health.

[0325] "Data storage means" refers to a storage device or database system for storing collected health data in chronological order.

[0326] "AI analytics" refers to the artificial intelligence models and algorithms used to analyze stored data and detect unusual patterns or red flags.

[0327] "Emotion analysis means" refers to devices or software that process data such as facial expressions and voice in order to analyze the user's emotional state.

[0328] "Warning generation means" refers to a system or software that generates a warning message based on anomalies detected by the AI ​​analysis means and the user's emotional state identified by the emotion analysis means.

[0329] The "warning transmission means" refers to a communication device or software for transmitting the generated warning message to the user terminal.

[0330] "User notification means" refers to a system or application that notifies specific countermeasures or action instructions based on the warning message displayed on the user's terminal.

[0331] This invention is a system that monitors the health condition of infants in real time and generates and sends appropriate warning messages based on the user's emotional state when an abnormality is detected. This system uses the following hardware and software to collect, store, and analyze various data handled and generate warning messages.

[0332] Hardware

[0333] Healthcare devices: devices with sensors to measure the infant's temperature, heart rate, movement, and ambient sound levels

[0334] Camera: Uses the device's camera to collect the user's facial expressions.

[0335] Microphone: Uses the microphone installed on the device to collect the user's voice.

[0336] User devices: devices such as smartphones, tablets, and head-mounted displays (HMDs)

[0337] software

[0338] Data collection module: software that receives data collected from healthcare devices

[0339] Data storage module: Software that stores collected data in a database in chronological order.

[0340] AI analysis module: Software that uses machine learning models to analyze collected and stored data and detect abnormal patterns and danger signals.

[0341] Emotion analysis module: Software that analyzes the user's facial expressions and voice data to identify their emotional state (e.g., emotion recognition model using TensorFlow)

[0342] Alert generation module: Software that generates alert messages based on abnormal data and the user's emotional state

[0343] Alert sending module: Communication software (e.g., Python's smtplib library) for sending generated alert messages to user terminals.

[0344] Specific examples of programs

[0345] Data collection and storage

[0346] The terminal measures the infant's body temperature (e.g., 38.0°C), heart rate (e.g., 120 BPM), movement (e.g., while still), and ambient sound volume (e.g., 55 dB) every minute through the healthcare device and transmits the data to the server, where the data storage module stores the data in a database in chronological order.

[0347] Data analysis

[0348] The server analyzes the stored data using an AI analysis module to detect abnormal patterns (e.g., an abnormally high heart rate). The AI ​​analysis module uses a machine learning model to compare the data with past data to detect abnormalities with high accuracy.

[0349] Emotion analysis

[0350] The device's camera and microphone capture the user's facial expressions and voice data, which are then analyzed by the emotion analysis module. For example, the emotion recognition model can identify when the user is nervous.

[0351] Alert Generation and Transmission

[0352] The server generates a warning message (e.g., "The infant's heart rate is high and movement is slow. Please contact a medical institution immediately.") based on the abnormal data detected by the AI ​​analysis module and the user's emotional state identified by the emotion analysis module. When generating a warning message, the warning generation module adjusts the tone of the message, such as by softening it, if the user is nervous.

[0353] The generated warning message is sent in real time to the user terminal via the warning sending module, allowing the user to check the warning message displayed on the terminal and take appropriate action promptly.

[0354] Examples of prompt statements

[0355] python

[0356] Generate warning message based on health data and user emotion state

[0357] health_data = {

[0358] 'body_temp': 38.0,

[0359] 'heart_rate': 120,

[0360] 'movement': 'static',

[0361] 'ambient_noise': 55

[0362] }

[0363] emotion = 1 Assuming 1 corresponds to 'tense' state

[0364] warning_message = generate_warning_message(health_data, emotion)

[0365] print(warning_message)

[0366] In this way, the present invention monitors the infant's health status in real time and issues warnings that take into account the user's emotional state, enabling quick and appropriate responses to protect the infant's health.

[0367] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0368] Step 1:

[0369] The terminal measures the infant's health data (body temperature, heart rate, movement, and ambient sound volume) every minute through a healthcare device. The input in this step is various sensor data, and the output is the measured health data. Specifically, the acquired data includes body temperature of 38.0°C, heart rate of 120 BPM, movement while stationary, and ambient sound volume of 55 dB.

[0370] Step 2:

[0371] The terminal sends the measured health data to the server. The input in this step is the health data from the healthcare device, which is sent to the server in real time. The output is the health data received by the server.

[0372] Step 3:

[0373] The server uses a data storage module to store the received health data in a database in chronological order. The input in this step is the health data sent from the device, which is then stored in the database. The output is the stored database entry.

[0374] Step 4:

[0375] The server then analyzes the stored data using an AI analysis module to detect abnormal patterns or warning signs. The input for this step is the stored health data, and the output is the detection of abnormal patterns or warning signs. Specifically, a machine learning model is used to compare the data with past data to detect abnormalities, such as an abnormally high heart rate.

[0376] Step 5:

[0377] The device's camera and microphone are used to capture the user's facial expression and voice data. The input in this step is raw data from the camera and microphone, and the output is the user's facial expression and voice data.

[0378] Step 6:

[0379] The server analyzes the acquired user's facial and voice data using an emotion analysis module. The input in this step is the user's facial and voice data, and the output is the user's emotional state (e.g., nervousness). Specifically, an emotion recognition model using TensorFlow is used to identify emotional states such as nervousness, relief, and sadness.

[0380] Step 7:

[0381] The server generates a warning message based on the abnormal data detected by the AI ​​analysis module and the user's emotional state identified by the emotion analysis module. The inputs in this step are abnormal patterns or danger signals and the user's emotional state, and the output is a warning message. Specifically, the server generates a warning such as, "The infant's heart rate is high and movement is low. Please contact a medical institution immediately." The tone of the message is adjusted according to the user's emotional state.

[0382] Step 8:

[0383] The server sends the generated warning message to the user terminal via the warning sending module. The input in this step is the warning message, and the output is the warning message displayed on the user terminal. Specifically, the message is sent in real time so that the user can check it immediately.

[0384] Step 9:

[0385] The user checks the warning message displayed on the device and takes appropriate action promptly. The input in this step is the warning message displayed on the device, and the output is the specific countermeasure action the user takes (e.g., contacting a medical institution).

[0386] 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.

[0387] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0388] 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.

[0389] [Second embodiment]

[0390] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0391] 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.

[0392] 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).

[0393] 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.

[0394] 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.

[0395] 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).

[0396] 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.

[0397] 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.

[0398] 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.

[0399] 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.

[0400] 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.

[0401] 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."

[0402] The present invention is a system that monitors the health status of young children in real time and issues warnings to support the early detection and prevention of child abuse. Specific embodiments of this system are described below.

[0403] System Configuration

[0404] This system consists of a data collection means, a data storage means, an AI analysis means, a warning generation means, a warning transmission means, and a user notification means. By linking these means, it is possible to monitor the health status of infants with high accuracy and issue a prompt warning if an abnormality occurs.

[0405] Data collection methods

[0406] The healthcare device attached to the terminal measures the infant's body temperature, heart rate, movement, and ambient sound volume in real time. This device is equipped with precision sensors and has the ability to transmit the measurement data to a server at regular intervals (e.g., every minute).

[0407] Data storage means

[0408] The server receives the measurement data sent from the terminal and stores it in a database in chronological order. The data storage means uses a high-speed database engine, allowing the received data to be efficiently organized and stored.

[0409] AI analysis means

[0410] The server preprocesses the data stored in the database, filling in missing values ​​and removing noise. The preprocessed data is then input into an AI model to detect abnormal patterns and warning signs. The AI ​​model uses machine learning algorithms and is capable of detecting anomalies with high accuracy by comparing them with past data.

[0411] Warning generation means

[0412] The server generates a warning message based on the anomaly detected by the AI ​​analysis method. The warning message includes the type of anomaly, its severity, and appropriate action to take. For example, "Your infant's heart rate is increasing rapidly. Please contact a medical institution immediately."

[0413] Alert sending method

[0414] The server then sends the generated warning message to the user's device, such as a smartphone or tablet, which has the ability to receive and display the message in real time.

[0415] User notification method

[0416] The user receives a warning message on their device and checks its contents. The warning message contains specific countermeasures and instructions, allowing the user to take action promptly. In this way, the user can take appropriate action quickly to protect the health of their child.

[0417] Specific examples

[0418] 1. The terminal measures the infant's body temperature (37.5°C), heart rate (100 BPM), movement (at rest), and ambient sound volume (50 dB) through a healthcare device and sends the data to the server.

[0419] 2. The server stores the received data in a database and performs preprocessing.

[0420] 3. The server inputs the preprocessed data into the AI ​​model and compares it with past data to detect abnormal patterns.

[0421] 4. The server generates a warning message stating, "The infant's heart rate is abnormally high and movement is slow," and sends it to the user's device.

[0422] 5. The user should check the warning message and take appropriate measures by following the instructions provided by the app, such as "Please contact a medical institution immediately."

[0423] In this way, this system monitors the health status of young children in real time and prompts immediate action if any abnormalities are detected, thereby enabling early detection and prevention of child abuse.

[0424] The processing flow will be explained below.

[0425] Step 1:

[0426] The device measures the infant's body temperature, heart rate, movement, and ambient sound volume in real time through a healthcare device attached to the infant. The device collects this data at regular intervals (e.g., every minute) and sends it to a server.

[0427] Step 2:

[0428] The server receives the data sent from the device and stores it in a database in chronological order. The database records the time of reception and the values ​​for each measurement item in detail.

[0429] Step 3:

[0430] The server preprocesses the data stored in the database, including imputing missing data, removing noise, and standardizing the data, and then converts the preprocessed data into a format suitable for analysis.

[0431] Step 4:

[0432] The server then feeds the pre-processed data into an AI model, which uses machine learning algorithms to detect abnormal patterns and warning signs, such as a sudden increase in heart rate or sustained abnormal movements.

[0433] Step 5:

[0434] The server generates a warning message based on the anomaly detected by the AI ​​model. The warning message includes the nature of the anomaly, its severity, and a recommended course of action. For example, a message might be generated such as, "Your infant's heart rate is higher than normal and their movement is reduced. Please contact a medical professional immediately."

[0435] Step 6:

[0436] The server sends the generated warning message to the user's terminal. The warning is sent in real time so that it can be delivered to the user without delay.

[0437] Step 7:

[0438] The user receives a warning message on their device (smartphone app). The user checks the contents of the warning message and reads the detailed information.

[0439] Step 8:

[0440] The user should respond promptly by following the measures and action plans provided in the warning message, for example, by contacting a medical institution immediately and taking appropriate measures as instructed to protect the health of the infant.

[0441] This series of processing steps makes it possible to monitor the infant's health condition in real time, and if an abnormality occurs, to quickly issue an alert and prompt appropriate action.

[0442] Example 1

[0443] 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."

[0444] There is a need to accurately understand the health status of infants and respond quickly when abnormalities occur. However, existing systems often fail to adequately detect abnormalities early due to difficulties in improving data quality and detecting abnormal patterns with high accuracy. Furthermore, when generating warning messages, there is a lack of means to present appropriate responses based on the type and severity of the abnormality, making it difficult for users to respond quickly and appropriately.

[0445] 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.

[0446] In this invention, the server includes a data collection means for monitoring the infant's health condition in real time, a data storage means for storing data acquired by the data collection means in chronological order, a data preprocessing means for preprocessing the data stored in the data storage means to complement missing values ​​and remove noise, an AI analysis means for analyzing the preprocessed data and detecting abnormal patterns and danger signals, a warning generation means for generating a warning message based on an abnormality detected by the AI ​​analysis means, and a warning transmission means for transmitting the warning message generated by the warning generation means to a user terminal. This makes it possible to monitor the infant's health condition with high accuracy and to take prompt and appropriate action when an abnormality occurs.

[0447] The "data collection means" is a device for monitoring the infant's health in real time, and is a means for collecting data such as body temperature, heart rate, movement, and ambient sound volume.

[0448] "Data storage means" refers to a means for storing data acquired by data collection means in chronological order, and a means for efficiently organizing and storing data using a high-speed database engine.

[0449] The "data preprocessing means" is a means for preprocessing the data stored in the data storage means, complementing missing values, removing noise, and improving the quality of the data.

[0450] "AI analysis tools" are tools that analyze pre-processed data and use machine learning algorithms to detect abnormal patterns or red flags.

[0451] The "warning generation means" is a means for generating a warning message based on an anomaly detected by the AI ​​analysis means, and is a means for creating a message including detailed information depending on the type of anomaly and its severity.

[0452] The "warning transmission means" is a means for transmitting the warning message generated by the warning generation means to the user terminal, and is a means for delivering the message in real time.

[0453] The "user notification means" is a means for implementing countermeasures based on the warning message displayed on the user terminal, and is a means for providing instructions for the user to take appropriate action.

[0454] System Configuration

[0455] This invention is a system that monitors the health status of infants in real time, detects abnormalities, and generates and sends warning messages. The main components of the system are data collection means, data storage means, data preprocessing means, AI analysis means, warning generation means, warning transmission means, and user notification means.

[0456] Data collection methods

[0457] The healthcare device attached to the terminal measures the infant's body temperature, heart rate, movement, and ambient sound volume in real time. The device uses Bluetooth Low Energy (BLE) to transmit the data to a server every minute. For example, the device measures and collects data when the infant's body temperature is 37.5°C, heart rate is 100 BPM, movement is stationary, and ambient sound volume is 50 dB.

[0458] Data storage means

[0459] The server receives the data sent from the device. The received data is given a timestamp and stored in a database in chronological order using a high-speed database engine such as MySQL or PostgreSQL. This method allows the data to be organized and stored efficiently.

[0460] Data preprocessing measures

[0461] The server preprocesses the data stored in the database. This preprocessing involves filling in missing values ​​and removing noise using the Python pandas library. This improves the quality of the data. For example, if missing values ​​are detected, peripheral data is filled in, and noisy data is removed using filtering techniques.

[0462] AI analysis means

[0463] The server then inputs the preprocessed data into an AI model, which uses machine learning libraries such as TensorFlow and PyTorch to compare it with past data to detect abnormal patterns and warning signs. For example, a sudden increase in heart rate and lack of movement would be considered an abnormality.

[0464] Warning generation means

[0465] The server generates a warning message based on the abnormality detected by the AI ​​analysis method. The warning message includes the type of abnormality, its severity, and appropriate measures to take. For example, the message generated may read, "Your infant's heart rate is rapidly increasing. Please contact a medical institution immediately."

[0466] Alert sending method

[0467] The server sends the generated warning messages to the user's device using HTTP or WebSocket, and the messages are displayed in real time on smartphones and tablets, allowing users to receive the warnings immediately.

[0468] User notification method

[0469] The user receives a warning message on their device and checks its contents. The application displays the warning message in a pop-up window, providing specific countermeasures and instructions on how to respond. The user can then take prompt action. For example, they could take appropriate measures by following the instructions to "contact a medical institution immediately."

[0470] Specific examples

[0471] 1. The device measures the infant's body temperature (37.5°C), heart rate (100 BPM), movement (at rest), and ambient sound volume (50 dB) using a healthcare device, and transmits the data to the server via BLE every minute.

[0472] 2. The server stores the received data in a MySQL database, timestamps it, and organizes it.

[0473] 3. The server preprocesses the data using Python's pandas library to impute missing values ​​and remove noise.

[0474] 4. The server feeds the preprocessed data into an AI model powered by TensorFlow to detect abnormal patterns.

[0475] 5. The server generates a warning message stating "Infant's heart rate is abnormally high and movement is persistently low" and includes appropriate responses based on severity.

[0476] 6. The server sends a warning message to the user's smartphone via the HTTP protocol and displays it in real time.

[0477] 7. The user receives a warning message on their smartphone and takes appropriate measures by following the instructions to "contact a medical institution immediately."

[0478] In this way, the invention can monitor the health status of infants with high accuracy, quickly issue an alert when an abnormality occurs, and prompt appropriate measures.

[0479] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0480] Step 1:

[0481] The healthcare device attached to the terminal measures the infant's body temperature, heart rate, movement, and ambient sound volume in real time. Specifically, it collects data on body temperature (37.5°C), heart rate (100 BPM), motion (still), and ambient sound volume (50 dB). This measurement data is sent to a server via Bluetooth Low Energy (BLE) every minute.

[0482] Input: Infant temperature, heart rate, movement, and ambient sound volume data

[0483] Output: Measurement data sent to the server via BLE

[0484] Step 2:

[0485] The server receives the measurement data sent from the device, assigns a timestamp to the received data, and stores it in a database in chronological order using a high-speed database engine such as MySQL or PostgreSQL.

[0486] Input: Measurement data received via BLE

[0487] Output: Measurement data stored in a database with time stamps

[0488] Step 3:

[0489] The server preprocesses the data stored in the database. This preprocessing uses the Python pandas library to fill in missing values ​​and remove noise. For example, when a missing value is detected, it is filled in using the surrounding data, and noisy data is removed using filtering techniques.

[0490] Input: Data stored in a database

[0491] Output: Preprocessed data (after missing value imputation and noise removal)

[0492] Step 4:

[0493] The server then inputs the preprocessed data into an AI model, which uses machine learning libraries like TensorFlow and PyTorch to compare it with past data to detect unusual patterns and warning signs. For example, a spike in heart rate and lack of movement could be identified as an anomaly.

[0494] Input: Preprocessed data

[0495] Output: Detected abnormal patterns and danger signals

[0496] Step 5:

[0497] The server generates a warning message based on the anomaly detected by the AI ​​analysis method. The warning message includes the type of anomaly, its severity, and appropriate action to take. For example, a message such as "Your infant's heart rate is increasing rapidly. Please contact a medical institution immediately."

[0498] Input: Detected abnormal patterns or warning signs

[0499] Output: Generated warning message

[0500] Step 6:

[0501] The server sends the generated warning message to the user's device using HTTP or WebSocket, and the message is displayed in real time on the smartphone or tablet, allowing the user to receive the warning immediately.

[0502] Input: The generated warning message

[0503] Output: The warning message sent to the user's terminal.

[0504] Step 7:

[0505] The user receives a warning message on their device and checks its contents. The application displays a pop-up warning message with specific countermeasures and instructions on how to respond. The user can then take action promptly. For example, they can follow the instructions to "contact a medical institution immediately."

[0506] Input: The warning message sent to the user's terminal.

[0507] Output: User confirmation and prompt action

[0508] (Application example 1)

[0509] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0510] There is a growing need for systems that can monitor the health of young children in real time and issue immediate warnings when abnormalities occur. However, conventional systems have limitations in the accuracy of anomaly detection and the detail of warning messages, which means that appropriate responses are not taken promptly. There is also a need to improve the performance of AI models for anomaly detection.

[0511] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0512] In this invention, the server includes a data collection means for monitoring the infant's health condition in real time, a data storage means for chronologically storing data acquired by the data collection means, an AI analysis means for analyzing the data stored in the data storage means and detecting abnormal patterns or danger signals, a warning generation means for generating a warning message based on the abnormality detected by the AI ​​analysis means, a warning transmission means for transmitting the warning message generated by the warning generation means to a user terminal, a user notification means for taking measures based on the warning message displayed on the user terminal, and a learning means for using a prompt sentence in a generative AI model to improve the abnormality detection ability of the AI ​​analysis means. This improves the accuracy of monitoring the infant's health condition, enables appropriate warning messages to be quickly generated and sent, and enables users to respond quickly.

[0513] A "data collection means" is a device or mechanism for measuring an infant's temperature, heart rate, movement, and ambient sound volume and obtaining this data in real time.

[0514] "Data storage means" means a device or system that records and stores data acquired by data collection means in chronological order, with the purpose of storing data efficiently and safely.

[0515] "AI analysis means" means a device or program that utilizes artificial intelligence to analyze data recorded in a data storage means and detect abnormal patterns or danger signals.

[0516] The "warning generation means" is a device or program that generates a warning message based on an abnormality detected by the AI ​​analysis means.

[0517] The "alert sending means" is a communication device or system for sending the generated alert message to the user's terminal.

[0518] The "user notification means" is a device or program that provides guidance or instructions for implementing countermeasures based on the warning message displayed on the user terminal.

[0519] A "generative AI model" is a model that uses artificial intelligence learning algorithms to improve anomaly detection capabilities.

[0520] A "prompt sentence" is a textual sentence used as training data input in a generative AI model to improve the AI's ability to detect anomalies.

[0521] The present invention is a system for monitoring the health status of an infant in real time and issuing a warning if an abnormality occurs. The system includes the following means.

[0522] System Configuration

[0523] The server has a means for collecting data, a means for storing data, a means for analyzing AI, a means for generating warnings, a means for sending warnings, a means for notifying users, and a means for learning using prompt sentences in a generated AI model.

[0524] Data collection methods

[0525] The data collection tool is a healthcare device that measures the infant's temperature, heart rate, movement, and ambient sound volume in real time, and transmits this data to a server over the internet.

[0526] Data storage means

[0527] The server's data storage mechanism stores data received via the Flask API in a MySQL database in chronological order, allowing historical health data to be recorded and later analyzed.

[0528] AI analysis means

[0529] The server preprocesses the stored data, removing noise and imputing missing values. The preprocessed data is then analyzed using a TensorFlow model to detect abnormal patterns and warning signs. This AI analysis method uses a generative AI model to input training data in the form of prompt sentences, improving its anomaly detection capabilities.

[0530] Warning generation means

[0531] The server generates a warning message based on the anomaly detected by the AI ​​analysis method, including the type and severity of the anomaly and guidelines for the user to take immediate action.

[0532] Alert sending method

[0533] The server then sends the generated alert message to the user's smartphone using Firebase Cloud Messaging, allowing the user to receive the alert in real time.

[0534] User notification method

[0535] A warning message will be displayed on the user's smartphone along with specific guidelines for countermeasures. Users can follow these guidelines to quickly implement appropriate countermeasures. This method allows for rapid response to abnormalities in the infant's health.

[0536] Specific examples

[0537] The following is a specific example of how the system works. For example, suppose a healthcare device measures an infant's body temperature of 37.5°C, heart rate of 100 BPM, minimal movement, and ambient sound volume of 50 dB. This data is sent to a server and stored in a MySQL database. An abnormal condition is then detected by a TensorFlow model, which generates a warning message stating, "The infant's heart rate is abnormally high and the infant continues to exhibit minimal movement." This warning message is then sent to the user's smartphone via Firebase Cloud Messaging. The user receives the warning message and specific guidelines, allowing them to promptly contact a medical institution.

[0538] Prompt Sentence Examples

[0539] Below are some example prompts used by the generative AI model:

[0540] Prompt: Create an AI model to monitor the health of infants in real time and detect abnormal patterns or danger signals. Input data consists of body temperature, heart rate, movement, and ambient sound volume, and a warning message should be generated if an abnormality is detected.

[0541] In this way, the present invention can monitor the health condition of an infant with high accuracy, and immediately issue a warning if an abnormality occurs, thereby ensuring the safety of the infant.

[0542] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0543] Step 1:

[0544] The server receives the infant's temperature, heart rate, movement, and ambient sound volume from the healthcare devices in real time via the Internet. The health status data measured from each sensor is sent to the server as input data. The server receives this data using the Flask API.

[0545] Step 2:

[0546] The server stores the received data in a MySQL database in chronological order. The input data is the health status data received by the server, and the output is the database entries stored in chronological order. In this step, the server efficiently stores and organizes the data.

[0547] Step 3:

[0548] The server performs preprocessing on the stored data. This preprocessing includes noise removal and missing value completion. The input data is the stored health status data, and the output data is the preprocessed, clean data. The server performs data cleansing to input into the model.

[0549] Step 4:

[0550] The server inputs the preprocessed data into a TensorFlow model to detect abnormal patterns and danger signals. The input data is the preprocessed health status data, and the output data is a threshold crossing result indicating the presence or absence of abnormal patterns. The server detects abnormalities based on the model output.

[0551] Step 5:

[0552] When an anomaly is detected, the server generates a warning message using a warning generation means. The input data is the anomaly detection result, and the output data is the warning message. The generated warning message includes the type and severity of the anomaly, as well as specific countermeasure guidelines.

[0553] Step 6:

[0554] The server sends the generated warning message to the user's smartphone using Firebase Cloud Messaging. The input data is the warning message, and the output data is a notification to the user's device. The user receives the warning message in real time.

[0555] Step 7:

[0556] The user checks the received warning message and promptly takes measures according to the specific guidelines. The input data is the warning message, and the output is the execution of the measures. The user takes appropriate action, such as contacting a medical institution.

[0557] Step 8:

[0558] The server trains the generative AI model using prompt sentences to improve its anomaly detection capabilities. The input data is the training dataset and prompt sentences, and the output data is the updated AI model. Below is an example of a prompt sentence.

[0559] Prompt: Create an AI model to monitor the health of infants in real time and detect abnormal patterns or danger signals. Input data consists of body temperature, heart rate, movement, and ambient sound volume, and a warning message should be generated if an abnormality is detected.

[0560] 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.

[0561] The present invention is a system that monitors the health status of young children in real time and issues warnings to support the early detection and prevention of child abuse. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system can adjust the content and presentation method of warning messages, enabling more effective responses. A specific embodiment of this system is described below.

[0562] System Configuration

[0563] This system consists of a data collection means, a data storage means, an AI analysis means, a warning generation means, a warning transmission means, a user notification means, and an emotion engine. By linking these means, it is possible to monitor the health status of infants and the emotional state of the user in real time, and to issue a prompt warning if an abnormality occurs.

[0564] Data collection methods

[0565] The healthcare device attached to the terminal measures the infant's body temperature, heart rate, movement, and ambient sound volume in real time. This device is equipped with precise sensors and collects the measurement data at regular intervals (e.g., every minute) and sends it to a server.

[0566] Data storage means

[0567] The server receives data sent from the terminal and stores it in a database in chronological order. The data storage method uses a high-speed database engine, allowing the received data to be organized and stored efficiently.

[0568] AI analysis means

[0569] The server preprocesses the data stored in the database, filling in missing values ​​and removing noise. The preprocessed data is then input into an AI model to detect abnormal patterns and warning signs. The AI ​​model uses machine learning algorithms and is capable of detecting anomalies with high accuracy by comparing them with past data.

[0570] Emotion Engine

[0571] The emotion engine identifies the user's emotional state by analyzing their facial expressions and voice. It uses the device's built-in camera and microphone to collect user emotion data and analyzes it using an AI model.

[0572] Warning generation means

[0573] The server generates a warning message based on the anomaly detected by the AI ​​analysis method and the user's emotional state identified by the emotion engine. The warning message includes the content and severity of the anomaly, as well as recommended actions. For example, if the user is in a tense state, the warning message will be adjusted to use more polite language.

[0574] Alert sending method

[0575] The server then sends the generated warning message to the user's device, such as a smartphone or tablet, which has the ability to receive and display the message in real time.

[0576] User notification method

[0577] The user receives a warning message on their device and checks its contents. The warning message contains specific countermeasures and instructions, allowing the user to take action promptly. In this way, the user can take appropriate action quickly to protect the health of their child.

[0578] Specific examples

[0579] 1. The terminal measures the infant's body temperature (37.5°C), heart rate (100 BPM), movement (at rest), and ambient sound volume (50 dB) through a healthcare device and sends the data to the server.

[0580] 2. The server stores the received data in a database and performs preprocessing.

[0581] 3. The server inputs the preprocessed data into the AI ​​model and compares it with past data to detect abnormal patterns.

[0582] 4. The user's facial expressions and voice are collected through the device's camera and microphone, and analyzed by the emotion engine. For example, the emotion engine determines that the user is nervous.

[0583] 5. The server generates a warning message stating, "Your infant's heart rate is abnormally high and movement is persistent. Please contact a medical professional immediately." The tone of the message is gentler because the user is nervous.

[0584] 6. The server sends this message to the user's terminal.

[0585] 7. The user should check the warning message and take appropriate measures by following the instructions provided by the app, such as "Please contact a medical institution immediately."

[0586] In this way, this system monitors the health status of infants in real time and issues a warning that takes into consideration the user's emotional state if an abnormality occurs, thereby enabling early detection and prevention of child abuse.

[0587] The processing flow will be explained below.

[0588] Step 1:

[0589] The device measures the infant's body temperature, heart rate, movement, and ambient sound volume in real time through a healthcare device attached to the infant. The device collects this data at regular intervals (e.g., every minute) and sends it to a server.

[0590] Step 2:

[0591] The server receives the data sent from the device and stores it in a database in chronological order. The database records the time of reception and the values ​​for each measurement item in detail.

[0592] Step 3:

[0593] The server preprocesses the data stored in the database, including imputing missing data, removing noise, and standardizing the data, and then converts the preprocessed data into a format suitable for analysis.

[0594] Step 4:

[0595] The server then feeds the pre-processed data into an AI model, which uses machine learning algorithms to detect abnormal patterns and warning signs, such as a sudden increase in heart rate or sustained abnormal movements.

[0596] Step 5:

[0597] The device uses an on-board camera and microphone to collect the user's facial expressions and voice to recognize the user's emotions, and transmits the data to a server in real time.

[0598] Step 6:

[0599] The server receives the user's emotion data sent from the terminal and analyzes it with an emotion engine. The emotion engine analyzes the user's facial expressions and voice to identify the user's emotional state (e.g., tension, anxiety, calm, etc.).

[0600] Step 7:

[0601] The server generates a warning message based on the anomaly detected by the AI ​​model and the user's emotional state identified by the emotion engine. The warning message includes the nature of the anomaly, its severity, and a recommended response. For example, if the user is identified as nervous, a message such as "The infant's heart rate is increasing rapidly. Please remain calm and contact a medical institution immediately" is generated.

[0602] Step 8:

[0603] The server sends the generated warning message to the user's terminal. The warning is sent in real time so that it can be delivered to the user without delay.

[0604] Step 9:

[0605] The user receives a warning message on their device (smartphone app). The user checks the contents of the warning message and reads the detailed information.

[0606] Step 10:

[0607] The user should respond promptly by following the measures and action plans provided in the warning message, for example, by contacting a medical institution immediately and taking appropriate measures as instructed to protect the health of the infant.

[0608] By following the steps above, it is possible to monitor the infant's health condition and the user's emotional state in real time, and prompt a prompt and appropriate response if an abnormality occurs.

[0609] Example 2

[0610] 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."

[0611] In recent years, early detection and prevention of child abuse and health problems have become important social issues. In particular, there is a need to monitor the health status of young children in real time and take appropriate action if an abnormality is detected. However, current systems have difficulty not only monitoring the health status but also providing appropriate warning messages that take into account the emotional state of the guardian. Therefore, there is a need for a system that can analyze both the health status of young children and the emotional state of the user in real time and issue appropriate warnings.

[0612] 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 data collection means for monitoring the infant's health condition in real time; a data storage means for chronologically storing data acquired by the data collection means; a data preprocessing means for preprocessing the data stored in the data storage means; an AI analysis means for analyzing the data preprocessed by the data preprocessing means and detecting abnormal patterns or danger signals; an emotion analysis means for collecting a user's facial expressions and voice and identifying their emotional state; a warning generation means for generating a warning message based on the abnormality detected by the AI ​​analysis means and the emotional state identified by the emotion analysis means; a warning transmission means for transmitting the warning message generated by the warning generation means to a user terminal; and a user notification means for implementing measures based on the warning message displayed on the user terminal. This makes it possible to analyze both the infant's health condition and the user's emotional state in real time and issue appropriate warnings.

[0613] "Data collection means" refers to devices or mechanisms for real-time monitoring of the infant's health.

[0614] "Data storage means" refers to a system or device for storing data acquired by the data collection means in chronological order.

[0615] The "data preprocessing means" refers to a device or program for performing preprocessing such as complementing missing values ​​and removing noise on the data stored in the data storage means.

[0616] "AI analysis tools" are systems that use artificial intelligence and machine learning algorithms to analyze pre-processed data and detect abnormal patterns or warning signs.

[0617] The "emotion analysis means" is a device or program for collecting the user's facial expressions and voice and identifying the user's emotional state.

[0618] "Warning generation means" means a program or system for generating a warning message based on the abnormality detected by the AI ​​analysis means and the emotional state identified by the emotion analysis means.

[0619] The "warning transmission means" is a device or program for transmitting the generated warning message to the user terminal.

[0620] The "user notification means" is a means for implementing countermeasures based on the warning message displayed on the user terminal.

[0621] The present invention provides a system and method for monitoring the health status of infants in real time and taking prompt action when an abnormality occurs. The system is composed of a data collection means, a data storage means, a data preprocessing means, an AI analysis means, a sentiment analysis means, a warning generation means, a warning transmission means, and a user notification means.

[0622] Data collection methods

[0623] The terminal collects real-time data such as body temperature, heart rate, movement, and ambient sound volume via a healthcare device attached to the infant. This healthcare device is equipped with precision sensors and provides the measurement data to the terminal at regular intervals (e.g., every minute), which is then transmitted to a server via Bluetooth or Wi-Fi.

[0624] Data storage means

[0625] The server receives the data sent from the device and stores it in a database in chronological order. This database can efficiently organize and store data using a high-speed database engine such as MySQL or PostgreSQL.

[0626] Data preprocessing measures

[0627] The server preprocesses the data stored in the database. This preprocessing includes filling in missing values ​​and removing noise. For example, if there is temporal fluctuation in the heart rate data, it will remove it.

[0628] AI analysis means

[0629] The preprocessed data is input into an AI model built using TensorFlow and PyTorch. The server then analyzes the data using the AI ​​model to detect abnormal patterns and warning signs. This analysis requires high accuracy in detecting anomalies by comparing them with past data.

[0630] Emotion analysis means

[0631] The device collects the user's facial expressions and voice through a camera and microphone. The server inputs the collected emotional data into an AI model to identify the user's emotional state (e.g., tension, anger, relief). This allows the system to respond appropriately according to the user's emotional state.

[0632] Warning generation means

[0633] The server generates a warning message based on the abnormality detected by the AI ​​analysis means and the emotional state identified by the emotion analysis means. The warning message includes the nature of the abnormality, its severity, and recommended actions to take. For example, a message such as "The infant's heart rate is abnormally high and the infant continues to show little movement. Please contact a medical institution immediately." If the user is nervous, the tone of the message is adjusted to a gentler tone.

[0634] Alert sending method

[0635] The server sends the generated warning message to the user's device (e.g., smartphone, tablet), where it is displayed in real time.

[0636] User notification method

[0637] The user checks the warning message on the device and responds promptly based on its contents, for example, by following the instruction to "contact a medical institution immediately." In this way, the user can take prompt and appropriate action to protect the health of the infant.

[0638] Specific examples

[0639] 1. The terminal measures the infant's body temperature (37.5°C), heart rate (100 BPM), movement (at rest), and ambient sound volume (50 dB) through a healthcare device and transmits the data to the server.

[0640] 2. The server stores the received data in a database and performs preprocessing.

[0641] 3. The server inputs the preprocessed data into a TensorFlow AI model and compares it with past data to detect abnormal patterns.

[0642] 4. The user's facial expressions and voice are collected through the device's camera and microphone, and analyzed by the emotion engine. For example, the emotion engine determines that the user is nervous.

[0643] 5. The server generates a warning message stating, "Your infant's heart rate is abnormally high and movement is persistent. Please contact a medical professional immediately." The tone of the message is gentler because the user is nervous.

[0644] 6. The server sends this message to the user's terminal.

[0645] 7. The user should check the warning message and take appropriate measures by following the instructions provided by the app, such as "Please contact a medical institution immediately."

[0646] In this way, this system monitors the health status of young children in real time and issues a warning that takes into account the user's emotional state if an abnormality occurs, thereby supporting the early detection and prevention of child abuse.

[0647] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0648] Step 1: Data collection

[0649] The terminal acquires data from a healthcare device attached to the infant. The terminal collects data such as body temperature, heart rate, movement, and ambient sound volume in real time. For example, the infant's body temperature is 37.5°C, heart rate is 100 BPM, movement is stationary, and ambient sound volume is 50 dB. The device is equipped with precision sensors and provides data to the terminal at regular intervals (e.g., every minute).

[0650] Input: Infant's physical information (temperature, heart rate, movement, sound volume)

[0651] Output: A set of health data (e.g., body temperature 37.5°C, heart rate 100 BPM, resting state, 50 dB)

[0652] Step 2: Send data

[0653] The device sends the acquired data to the server. The device sends the collected data to the server using Bluetooth or Wi-Fi.

[0654] Input: A set of collected health data

[0655] Output: Health data sent to the server

[0656] Step 3: Save data

[0657] The server stores the received data in a database. The server uses a database engine such as MySQL or PostgreSQL to organize and store the data in chronological order.

[0658] Input: Health data sent from the device

[0659] Output: Time series data stored in a database

[0660] Step 4: Data Preprocessing

[0661] The server preprocesses the stored data, filling in missing values ​​and removing noise. For example, if there is a temporal fluctuation in the heart rate data, it removes it.

[0662] Input: Time series data stored in a database

[0663] Output: Preprocessed and clean data

[0664] Step 5: AI analysis

[0665] The server then inputs the preprocessed data into an AI model, built using TensorFlow and PyTorch, that detects abnormal patterns and warning signs, such as identifying abnormal heart rate data.

[0666] Input: Preprocessed and clean data

[0667] Output: Anomaly detection results from the AI ​​model

[0668] Step 6: Sentiment Analysis

[0669] The device collects the user's facial expressions and voice using the device's camera and microphone. For example, the camera can capture the user's nervousness.

[0670] Input: User facial and voice data

[0671] Output: Collected emotion data

[0672] Step 7: Sentiment analysis

[0673] The server inputs the emotional data into an AI model to analyze the user's emotional state, for example, determining whether the user is nervous, angry, relieved, etc.

[0674] Input: Emotion data obtained from the device

[0675] Output: Sentiment analysis result (e.g. "I'm nervous")

[0676] Step 8: Generate warnings

[0677] The server generates a warning message based on the results of anomaly detection and emotion analysis. For example, it creates a warning message such as "The infant's heart rate is abnormally high and the infant's movement is still low. Please contact a medical institution immediately." If the user is nervous, it adjusts the tone of the message to a gentler tone.

[0678] Input: Anomaly detection results, sentiment analysis results

[0679] Output: Adjusted warning message

[0680] Step 9: Send alert

[0681] The server then sends the generated warning message to the user's device, which then sends the warning message to the user's smartphone or tablet in real time.

[0682] Input: Adjusted warning message

[0683] Output: Warning message displayed on the user's terminal

[0684] Step 10: User notification and response

[0685] The user checks the warning message on the device and takes prompt action based on the warning message, for example, by following the instructions to "contact a medical institution."

[0686] Input: The warning message displayed on the user's terminal

[0687] Output: Appropriate user action (e.g., contacting a medical facility)

[0688] (Application example 2)

[0689] 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."

[0690] For the purpose of early detection and prevention of child abuse and health abnormalities, it is necessary to monitor the health status of children in real time and promptly and accurately respond when abnormalities are detected. However, conventional systems are unable to provide warning messages that take the user's emotional state into account, which can lead to delays in appropriate responses. Another challenge is providing warning messages in a format that is easy for users to understand.

[0691] The identification processing by the identification 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: data collection means for monitoring the infant's health condition in real time; data storage means for chronologically storing data acquired by the data collection means; AI analysis means for analyzing the data stored in the data storage means and detecting abnormal patterns or danger signals; emotion analysis means for analyzing the user's emotional state; warning generation means for generating a warning message based on the abnormality detected by the AI ​​analysis means and the user's emotional state identified by the emotion analysis means; warning transmission means for transmitting the warning message generated by the warning generation means to a user terminal; and user notification means for implementing measures based on the warning message displayed on the user terminal. This makes it possible to quickly detect abnormalities in the infant's health condition, provide a warning message that takes into account the user's emotional state, and take prompt and appropriate action.

[0692] "Data collection means" refers to equipment or devices that collect data such as body temperature, heart rate, movement, and ambient sound levels to monitor the infant's health.

[0693] "Data storage means" refers to a storage device or database system for storing collected health data in chronological order.

[0694] "AI analytics" refers to the artificial intelligence models and algorithms used to analyze stored data and detect unusual patterns or red flags.

[0695] "Emotion analysis means" refers to devices or software that process data such as facial expressions and voice in order to analyze the user's emotional state.

[0696] "Warning generation means" refers to a system or software that generates a warning message based on anomalies detected by the AI ​​analysis means and the user's emotional state identified by the emotion analysis means.

[0697] The "warning transmission means" refers to a communication device or software for transmitting the generated warning message to the user terminal.

[0698] "User notification means" refers to a system or application that notifies specific countermeasures or action instructions based on the warning message displayed on the user's terminal.

[0699] This invention is a system that monitors the health condition of infants in real time and generates and sends appropriate warning messages based on the user's emotional state when an abnormality is detected. This system uses the following hardware and software to collect, store, and analyze various data handled and generate warning messages.

[0700] Hardware

[0701] Healthcare devices: devices with sensors to measure the infant's temperature, heart rate, movement, and ambient sound levels

[0702] Camera: Uses the device's camera to collect the user's facial expressions.

[0703] Microphone: Uses the microphone installed on the device to collect the user's voice.

[0704] User devices: devices such as smartphones, tablets, and head-mounted displays (HMDs)

[0705] software

[0706] Data collection module: software that receives data collected from healthcare devices

[0707] Data storage module: Software that stores collected data in a database in chronological order.

[0708] AI analysis module: Software that uses machine learning models to analyze collected and stored data and detect abnormal patterns and danger signals.

[0709] Emotion analysis module: Software that analyzes the user's facial expressions and voice data to identify their emotional state (e.g., emotion recognition model using TensorFlow)

[0710] Alert generation module: Software that generates alert messages based on abnormal data and the user's emotional state

[0711] Alert sending module: Communication software (e.g., Python's smtplib library) for sending generated alert messages to user terminals.

[0712] Specific examples of programs

[0713] Data collection and storage

[0714] The terminal measures the infant's body temperature (e.g., 38.0°C), heart rate (e.g., 120 BPM), movement (e.g., while still), and ambient sound volume (e.g., 55 dB) every minute through the healthcare device and transmits the data to the server, where the data storage module stores the data in a database in chronological order.

[0715] Data analysis

[0716] The server analyzes the stored data using an AI analysis module to detect abnormal patterns (e.g., an abnormally high heart rate). The AI ​​analysis module uses a machine learning model to compare the data with past data to detect abnormalities with high accuracy.

[0717] Emotion analysis

[0718] The device's camera and microphone capture the user's facial expressions and voice data, which are then analyzed by the emotion analysis module. For example, the emotion recognition model can identify when the user is nervous.

[0719] Alert Generation and Transmission

[0720] The server generates a warning message (e.g., "The infant's heart rate is high and movement is slow. Please contact a medical institution immediately.") based on the abnormal data detected by the AI ​​analysis module and the user's emotional state identified by the emotion analysis module. When generating a warning message, the warning generation module adjusts the tone of the message, such as by softening it, if the user is nervous.

[0721] The generated warning message is sent in real time to the user terminal via the warning sending module, allowing the user to check the warning message displayed on the terminal and take appropriate action promptly.

[0722] Examples of prompt statements

[0723] python

[0724] Generate warning message based on health data and user emotion state

[0725] health_data = {

[0726] 'body_temp': 38.0,

[0727] 'heart_rate': 120,

[0728] 'movement': 'static',

[0729] 'ambient_noise': 55

[0730] }

[0731] emotion = 1 Assuming 1 corresponds to 'tense' state

[0732] warning_message = generate_warning_message(health_data, emotion)

[0733] print(warning_message)

[0734] In this way, the present invention monitors the infant's health status in real time and issues warnings that take into account the user's emotional state, enabling quick and appropriate responses to protect the infant's health.

[0735] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0736] Step 1:

[0737] The terminal measures the infant's health data (body temperature, heart rate, movement, and ambient sound volume) every minute through a healthcare device. The input in this step is various sensor data, and the output is the measured health data. Specifically, the acquired data includes body temperature of 38.0°C, heart rate of 120 BPM, movement while stationary, and ambient sound volume of 55 dB.

[0738] Step 2:

[0739] The terminal sends the measured health data to the server. The input in this step is the health data from the healthcare device, which is sent to the server in real time. The output is the health data received by the server.

[0740] Step 3:

[0741] The server uses a data storage module to store the received health data in a database in chronological order. The input in this step is the health data sent from the device, which is then stored in the database. The output is the stored database entry.

[0742] Step 4:

[0743] The server then analyzes the stored data using an AI analysis module to detect abnormal patterns or warning signs. The input for this step is the stored health data, and the output is the detection of abnormal patterns or warning signs. Specifically, a machine learning model is used to compare the data with past data to detect abnormalities, such as an abnormally high heart rate.

[0744] Step 5:

[0745] The device's camera and microphone are used to capture the user's facial expression and voice data. The input in this step is raw data from the camera and microphone, and the output is the user's facial expression and voice data.

[0746] Step 6:

[0747] The server analyzes the acquired user's facial and voice data using an emotion analysis module. The input in this step is the user's facial and voice data, and the output is the user's emotional state (e.g., nervousness). Specifically, an emotion recognition model using TensorFlow is used to identify emotional states such as nervousness, relief, and sadness.

[0748] Step 7:

[0749] The server generates a warning message based on the abnormal data detected by the AI ​​analysis module and the user's emotional state identified by the emotion analysis module. The inputs in this step are abnormal patterns or danger signals and the user's emotional state, and the output is a warning message. Specifically, the server generates a warning such as, "The infant's heart rate is high and movement is low. Please contact a medical institution immediately." The tone of the message is adjusted according to the user's emotional state.

[0750] Step 8:

[0751] The server sends the generated warning message to the user terminal via the warning sending module. The input in this step is the warning message, and the output is the warning message displayed on the user terminal. Specifically, the message is sent in real time so that the user can check it immediately.

[0752] Step 9:

[0753] The user checks the warning message displayed on the device and takes appropriate action promptly. The input in this step is the warning message displayed on the device, and the output is the specific countermeasure action the user takes (e.g., contacting a medical institution).

[0754] 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.

[0755] 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.

[0756] 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.

[0757] [Third embodiment]

[0758] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0759] 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.

[0760] 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).

[0761] 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.

[0762] 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.

[0763] 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).

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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."

[0770] The present invention is a system that monitors the health status of young children in real time and issues warnings to support the early detection and prevention of child abuse. Specific embodiments of this system are described below.

[0771] System Configuration

[0772] This system consists of a data collection means, a data storage means, an AI analysis means, a warning generation means, a warning transmission means, and a user notification means. By linking these means, it is possible to monitor the health status of infants with high accuracy and issue a prompt warning if an abnormality occurs.

[0773] Data collection methods

[0774] The healthcare device attached to the terminal measures the infant's body temperature, heart rate, movement, and ambient sound volume in real time. This device is equipped with precision sensors and has the ability to transmit the measurement data to a server at regular intervals (e.g., every minute).

[0775] Data storage means

[0776] The server receives the measurement data sent from the terminal and stores it in a database in chronological order. The data storage means uses a high-speed database engine, allowing the received data to be efficiently organized and stored.

[0777] AI analysis means

[0778] The server preprocesses the data stored in the database, filling in missing values ​​and removing noise. The preprocessed data is then input into an AI model to detect abnormal patterns and warning signs. The AI ​​model uses machine learning algorithms and is capable of detecting anomalies with high accuracy by comparing them with past data.

[0779] Warning generation means

[0780] The server generates a warning message based on the anomaly detected by the AI ​​analysis method. The warning message includes the type of anomaly, its severity, and appropriate action to take. For example, "Your infant's heart rate is increasing rapidly. Please contact a medical institution immediately."

[0781] Alert sending method

[0782] The server then sends the generated warning message to the user's device, such as a smartphone or tablet, which has the ability to receive and display the message in real time.

[0783] User notification method

[0784] The user receives a warning message on their device and checks its contents. The warning message contains specific countermeasures and instructions, allowing the user to take action promptly. In this way, the user can take appropriate action quickly to protect the health of their child.

[0785] Specific examples

[0786] 1. The terminal measures the infant's body temperature (37.5°C), heart rate (100 BPM), movement (at rest), and ambient sound volume (50 dB) through a healthcare device and sends the data to the server.

[0787] 2. The server stores the received data in a database and performs preprocessing.

[0788] 3. The server inputs the preprocessed data into the AI ​​model and compares it with past data to detect abnormal patterns.

[0789] 4. The server generates a warning message stating, "The infant's heart rate is abnormally high and movement is slow," and sends it to the user's device.

[0790] 5. The user should check the warning message and take appropriate measures by following the instructions provided by the app, such as "Please contact a medical institution immediately."

[0791] In this way, this system monitors the health status of young children in real time and prompts immediate action if any abnormalities are detected, thereby enabling early detection and prevention of child abuse.

[0792] The processing flow will be explained below.

[0793] Step 1:

[0794] The device measures the infant's body temperature, heart rate, movement, and ambient sound volume in real time through a healthcare device attached to the infant. The device collects this data at regular intervals (e.g., every minute) and sends it to a server.

[0795] Step 2:

[0796] The server receives the data sent from the device and stores it in a database in chronological order. The database records the time of reception and the values ​​for each measurement item in detail.

[0797] Step 3:

[0798] The server preprocesses the data stored in the database, including imputing missing data, removing noise, and standardizing the data, and then converts the preprocessed data into a format suitable for analysis.

[0799] Step 4:

[0800] The server then feeds the pre-processed data into an AI model, which uses machine learning algorithms to detect abnormal patterns and warning signs, such as a sudden increase in heart rate or sustained abnormal movements.

[0801] Step 5:

[0802] The server generates a warning message based on the anomaly detected by the AI ​​model. The warning message includes the nature of the anomaly, its severity, and a recommended course of action. For example, a message might be generated such as, "Your infant's heart rate is higher than normal and their movement is reduced. Please contact a medical professional immediately."

[0803] Step 6:

[0804] The server sends the generated warning message to the user's terminal. The warning is sent in real time so that it can be delivered to the user without delay.

[0805] Step 7:

[0806] The user receives a warning message on their device (smartphone app). The user checks the contents of the warning message and reads the detailed information.

[0807] Step 8:

[0808] The user should respond promptly by following the measures and action plans provided in the warning message, for example, by contacting a medical institution immediately and taking appropriate measures as instructed to protect the health of the infant.

[0809] This series of processing steps makes it possible to monitor the infant's health condition in real time, and if an abnormality occurs, to quickly issue an alert and prompt appropriate action.

[0810] Example 1

[0811] 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."

[0812] There is a need to accurately understand the health status of infants and respond quickly when abnormalities occur. However, existing systems often fail to adequately detect abnormalities early due to difficulties in improving data quality and detecting abnormal patterns with high accuracy. Furthermore, when generating warning messages, there is a lack of means to present appropriate responses based on the type and severity of the abnormality, making it difficult for users to respond quickly and appropriately.

[0813] 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.

[0814] In this invention, the server includes a data collection means for monitoring the infant's health condition in real time, a data storage means for storing data acquired by the data collection means in chronological order, a data preprocessing means for preprocessing the data stored in the data storage means to complement missing values ​​and remove noise, an AI analysis means for analyzing the preprocessed data and detecting abnormal patterns and danger signals, a warning generation means for generating a warning message based on an abnormality detected by the AI ​​analysis means, and a warning transmission means for transmitting the warning message generated by the warning generation means to a user terminal. This makes it possible to monitor the infant's health condition with high accuracy and to take prompt and appropriate action when an abnormality occurs.

[0815] The "data collection means" is a device for monitoring the infant's health in real time, and is a means for collecting data such as body temperature, heart rate, movement, and ambient sound volume.

[0816] "Data storage means" refers to a means for storing data acquired by data collection means in chronological order, and a means for efficiently organizing and storing data using a high-speed database engine.

[0817] The "data preprocessing means" is a means for preprocessing the data stored in the data storage means, complementing missing values, removing noise, and improving the quality of the data.

[0818] "AI analysis tools" are tools that analyze pre-processed data and use machine learning algorithms to detect abnormal patterns or red flags.

[0819] The "warning generation means" is a means for generating a warning message based on an anomaly detected by the AI ​​analysis means, and is a means for creating a message including detailed information depending on the type of anomaly and its severity.

[0820] The "warning transmission means" is a means for transmitting the warning message generated by the warning generation means to the user terminal, and is a means for delivering the message in real time.

[0821] The "user notification means" is a means for implementing countermeasures based on the warning message displayed on the user terminal, and is a means for providing instructions for the user to take appropriate action.

[0822] System Configuration

[0823] This invention is a system that monitors the health status of infants in real time, detects abnormalities, and generates and sends warning messages. The main components of the system are data collection means, data storage means, data preprocessing means, AI analysis means, warning generation means, warning transmission means, and user notification means.

[0824] Data collection methods

[0825] The healthcare device attached to the terminal measures the infant's body temperature, heart rate, movement, and ambient sound volume in real time. The device uses Bluetooth Low Energy (BLE) to transmit the data to a server every minute. For example, the device measures and collects data when the infant's body temperature is 37.5°C, heart rate is 100 BPM, movement is stationary, and ambient sound volume is 50 dB.

[0826] Data storage means

[0827] The server receives the data sent from the device. The received data is given a timestamp and stored in a database in chronological order using a high-speed database engine such as MySQL or PostgreSQL. This method allows the data to be organized and stored efficiently.

[0828] Data preprocessing measures

[0829] The server preprocesses the data stored in the database. This preprocessing involves filling in missing values ​​and removing noise using the Python pandas library. This improves the quality of the data. For example, if missing values ​​are detected, peripheral data is filled in, and noisy data is removed using filtering techniques.

[0830] AI analysis means

[0831] The server then inputs the preprocessed data into an AI model, which uses machine learning libraries such as TensorFlow and PyTorch to compare it with past data to detect abnormal patterns and warning signs. For example, a sudden increase in heart rate and lack of movement would be considered an abnormality.

[0832] Warning generation means

[0833] The server generates a warning message based on the abnormality detected by the AI ​​analysis method. The warning message includes the type of abnormality, its severity, and appropriate measures to take. For example, the message generated may read, "Your infant's heart rate is rapidly increasing. Please contact a medical institution immediately."

[0834] Alert sending method

[0835] The server sends the generated warning messages to the user's device using HTTP or WebSocket, and the messages are displayed in real time on smartphones and tablets, allowing users to receive the warnings immediately.

[0836] User notification method

[0837] The user receives a warning message on their device and checks its contents. The application displays the warning message in a pop-up window, providing specific countermeasures and instructions on how to respond. The user can then take prompt action. For example, they could take appropriate measures by following the instructions to "contact a medical institution immediately."

[0838] Specific examples

[0839] 1. The device measures the infant's body temperature (37.5°C), heart rate (100 BPM), movement (at rest), and ambient sound volume (50 dB) using a healthcare device, and transmits the data to the server via BLE every minute.

[0840] 2. The server stores the received data in a MySQL database, timestamps it, and organizes it.

[0841] 3. The server preprocesses the data using Python's pandas library to impute missing values ​​and remove noise.

[0842] 4. The server feeds the preprocessed data into an AI model powered by TensorFlow to detect abnormal patterns.

[0843] 5. The server generates a warning message stating "Infant's heart rate is abnormally high and movement is persistently low" and includes appropriate responses based on severity.

[0844] 6. The server sends a warning message to the user's smartphone via the HTTP protocol and displays it in real time.

[0845] 7. The user receives a warning message on their smartphone and takes appropriate measures by following the instructions to "contact a medical institution immediately."

[0846] In this way, the invention can monitor the health status of infants with high accuracy, quickly issue an alert when an abnormality occurs, and prompt appropriate measures.

[0847] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0848] Step 1:

[0849] The healthcare device attached to the terminal measures the infant's body temperature, heart rate, movement, and ambient sound volume in real time. Specifically, it collects data on body temperature (37.5°C), heart rate (100 BPM), motion (still), and ambient sound volume (50 dB). This measurement data is sent to a server via Bluetooth Low Energy (BLE) every minute.

[0850] Input: Infant temperature, heart rate, movement, and ambient sound volume data

[0851] Output: Measurement data sent to the server via BLE

[0852] Step 2:

[0853] The server receives the measurement data sent from the device, assigns a timestamp to the received data, and stores it in a database in chronological order using a high-speed database engine such as MySQL or PostgreSQL.

[0854] Input: Measurement data received via BLE

[0855] Output: Measurement data stored in a database with time stamps

[0856] Step 3:

[0857] The server preprocesses the data stored in the database. This preprocessing uses the Python pandas library to fill in missing values ​​and remove noise. For example, when a missing value is detected, it is filled in using the surrounding data, and noisy data is removed using filtering techniques.

[0858] Input: Data stored in a database

[0859] Output: Preprocessed data (after missing value imputation and noise removal)

[0860] Step 4:

[0861] The server then inputs the preprocessed data into an AI model, which uses machine learning libraries like TensorFlow and PyTorch to compare it with past data to detect unusual patterns and warning signs. For example, a spike in heart rate and lack of movement could be identified as an anomaly.

[0862] Input: Preprocessed data

[0863] Output: Detected abnormal patterns and danger signals

[0864] Step 5:

[0865] The server generates a warning message based on the anomaly detected by the AI ​​analysis method. The warning message includes the type of anomaly, its severity, and appropriate action to take. For example, a message such as "Your infant's heart rate is increasing rapidly. Please contact a medical institution immediately."

[0866] Input: Detected abnormal patterns or warning signs

[0867] Output: Generated warning message

[0868] Step 6:

[0869] The server sends the generated warning message to the user's device using HTTP or WebSocket, and the message is displayed in real time on the smartphone or tablet, allowing the user to receive the warning immediately.

[0870] Input: The generated warning message

[0871] Output: The warning message sent to the user's terminal.

[0872] Step 7:

[0873] The user receives a warning message on their device and checks its contents. The application displays a pop-up warning message with specific countermeasures and instructions on how to respond. The user can then take action promptly. For example, they can follow the instructions to "contact a medical institution immediately."

[0874] Input: The warning message sent to the user's terminal.

[0875] Output: User confirmation and prompt action

[0876] (Application example 1)

[0877] 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."

[0878] There is a growing need for systems that can monitor the health of young children in real time and issue immediate warnings when abnormalities occur. However, conventional systems have limitations in the accuracy of anomaly detection and the detail of warning messages, which means that appropriate responses are not taken promptly. There is also a need to improve the performance of AI models for anomaly detection.

[0879] 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.

[0880] In this invention, the server includes a data collection means for monitoring the infant's health condition in real time, a data storage means for chronologically storing data acquired by the data collection means, an AI analysis means for analyzing the data stored in the data storage means and detecting abnormal patterns or danger signals, a warning generation means for generating a warning message based on the abnormality detected by the AI ​​analysis means, a warning transmission means for transmitting the warning message generated by the warning generation means to a user terminal, a user notification means for taking measures based on the warning message displayed on the user terminal, and a learning means for using a prompt sentence in a generative AI model to improve the abnormality detection ability of the AI ​​analysis means. This improves the accuracy of monitoring the infant's health condition, enables appropriate warning messages to be quickly generated and sent, and enables users to respond quickly.

[0881] A "data collection means" is a device or mechanism for measuring an infant's temperature, heart rate, movement, and ambient sound volume and obtaining this data in real time.

[0882] "Data storage means" means a device or system that records and stores data acquired by data collection means in chronological order, with the purpose of storing data efficiently and safely.

[0883] "AI analysis means" means a device or program that utilizes artificial intelligence to analyze data recorded in a data storage means and detect abnormal patterns or danger signals.

[0884] The "warning generation means" is a device or program that generates a warning message based on an abnormality detected by the AI ​​analysis means.

[0885] The "alert sending means" is a communication device or system for sending the generated alert message to the user's terminal.

[0886] The "user notification means" is a device or program that provides guidance or instructions for implementing countermeasures based on the warning message displayed on the user terminal.

[0887] A "generative AI model" is a model that uses artificial intelligence learning algorithms to improve anomaly detection capabilities.

[0888] A "prompt sentence" is a textual sentence used as training data input in a generative AI model to improve the AI's ability to detect anomalies.

[0889] The present invention is a system for monitoring the health status of an infant in real time and issuing a warning if an abnormality occurs. The system includes the following means.

[0890] System Configuration

[0891] The server has a means for collecting data, a means for storing data, a means for analyzing AI, a means for generating warnings, a means for sending warnings, a means for notifying users, and a means for learning using prompt sentences in a generated AI model.

[0892] Data collection methods

[0893] The data collection tool is a healthcare device that measures the infant's temperature, heart rate, movement, and ambient sound volume in real time, and transmits this data to a server over the internet.

[0894] Data storage means

[0895] The server's data storage mechanism stores data received via the Flask API in a MySQL database in chronological order, allowing historical health data to be recorded and later analyzed.

[0896] AI analysis means

[0897] The server preprocesses the stored data, removing noise and imputing missing values. The preprocessed data is then analyzed using a TensorFlow model to detect abnormal patterns and warning signs. This AI analysis method uses a generative AI model to input training data in the form of prompt sentences, improving its anomaly detection capabilities.

[0898] Warning generation means

[0899] The server generates a warning message based on the anomaly detected by the AI ​​analysis method, including the type and severity of the anomaly and guidelines for the user to take immediate action.

[0900] Alert sending method

[0901] The server then sends the generated alert message to the user's smartphone using Firebase Cloud Messaging, allowing the user to receive the alert in real time.

[0902] User notification method

[0903] A warning message will be displayed on the user's smartphone along with specific guidelines for countermeasures. Users can follow these guidelines to quickly implement appropriate countermeasures. This method allows for rapid response to abnormalities in the infant's health.

[0904] Specific examples

[0905] The following is a specific example of how the system works. For example, suppose a healthcare device measures an infant's body temperature of 37.5°C, heart rate of 100 BPM, minimal movement, and ambient sound volume of 50 dB. This data is sent to a server and stored in a MySQL database. An abnormal condition is then detected by a TensorFlow model, which generates a warning message stating, "The infant's heart rate is abnormally high and the infant continues to exhibit minimal movement." This warning message is then sent to the user's smartphone via Firebase Cloud Messaging. The user receives the warning message and specific guidelines, allowing them to promptly contact a medical institution.

[0906] Prompt Sentence Examples

[0907] Below are some example prompts used by the generative AI model:

[0908] Prompt: Create an AI model to monitor the health of infants in real time and detect abnormal patterns or danger signals. Input data consists of body temperature, heart rate, movement, and ambient sound volume, and a warning message should be generated if an abnormality is detected.

[0909] In this way, the present invention can monitor the health condition of an infant with high accuracy, and immediately issue a warning if an abnormality occurs, thereby ensuring the safety of the infant.

[0910] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0911] Step 1:

[0912] The server receives the infant's temperature, heart rate, movement, and ambient sound volume from the healthcare devices in real time via the Internet. The health status data measured from each sensor is sent to the server as input data. The server receives this data using the Flask API.

[0913] Step 2:

[0914] The server stores the received data in a MySQL database in chronological order. The input data is the health status data received by the server, and the output is the database entries stored in chronological order. In this step, the server efficiently stores and organizes the data.

[0915] Step 3:

[0916] The server performs preprocessing on the stored data. This preprocessing includes noise removal and missing value completion. The input data is the stored health status data, and the output data is the preprocessed, clean data. The server performs data cleansing to input into the model.

[0917] Step 4:

[0918] The server inputs the preprocessed data into a TensorFlow model to detect abnormal patterns and danger signals. The input data is the preprocessed health status data, and the output data is a threshold crossing result indicating the presence or absence of abnormal patterns. The server detects abnormalities based on the model output.

[0919] Step 5:

[0920] When an anomaly is detected, the server generates a warning message using a warning generation means. The input data is the anomaly detection result, and the output data is the warning message. The generated warning message includes the type and severity of the anomaly, as well as specific countermeasure guidelines.

[0921] Step 6:

[0922] The server sends the generated warning message to the user's smartphone using Firebase Cloud Messaging. The input data is the warning message, and the output data is a notification to the user's device. The user receives the warning message in real time.

[0923] Step 7:

[0924] The user checks the received warning message and promptly takes measures according to the specific guidelines. The input data is the warning message, and the output is the execution of the measures. The user takes appropriate action, such as contacting a medical institution.

[0925] Step 8:

[0926] The server trains the generative AI model using prompt sentences to improve its anomaly detection capabilities. The input data is the training dataset and prompt sentences, and the output data is the updated AI model. Below is an example of a prompt sentence.

[0927] Prompt: Create an AI model to monitor the health of infants in real time and detect abnormal patterns or danger signals. Input data consists of body temperature, heart rate, movement, and ambient sound volume, and a warning message should be generated if an abnormality is detected.

[0928] 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.

[0929] The present invention is a system that monitors the health status of young children in real time and issues warnings to support the early detection and prevention of child abuse. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system can adjust the content and presentation method of warning messages, enabling more effective responses. A specific embodiment of this system is described below.

[0930] System Configuration

[0931] This system consists of a data collection means, a data storage means, an AI analysis means, a warning generation means, a warning transmission means, a user notification means, and an emotion engine. By linking these means, it is possible to monitor the health status of infants and the emotional state of the user in real time, and to issue a prompt warning if an abnormality occurs.

[0932] Data collection methods

[0933] The healthcare device attached to the terminal measures the infant's body temperature, heart rate, movement, and ambient sound volume in real time. This device is equipped with precise sensors and collects the measurement data at regular intervals (e.g., every minute) and sends it to a server.

[0934] Data storage means

[0935] The server receives data sent from the terminal and stores it in a database in chronological order. The data storage method uses a high-speed database engine, allowing the received data to be organized and stored efficiently.

[0936] AI analysis means

[0937] The server preprocesses the data stored in the database, filling in missing values ​​and removing noise. The preprocessed data is then input into an AI model to detect abnormal patterns and warning signs. The AI ​​model uses machine learning algorithms and is capable of detecting anomalies with high accuracy by comparing them with past data.

[0938] Emotion Engine

[0939] The emotion engine identifies the user's emotional state by analyzing their facial expressions and voice. It uses the device's built-in camera and microphone to collect user emotion data and analyzes it using an AI model.

[0940] Warning generation means

[0941] The server generates a warning message based on the anomaly detected by the AI ​​analysis method and the user's emotional state identified by the emotion engine. The warning message includes the content and severity of the anomaly, as well as recommended actions. For example, if the user is in a tense state, the warning message will be adjusted to use more polite language.

[0942] Alert sending method

[0943] The server then sends the generated warning message to the user's device, such as a smartphone or tablet, which has the ability to receive and display the message in real time.

[0944] User notification method

[0945] The user receives a warning message on their device and checks its contents. The warning message contains specific countermeasures and instructions, allowing the user to take action promptly. In this way, the user can take appropriate action quickly to protect the health of their child.

[0946] Specific examples

[0947] 1. The terminal measures the infant's body temperature (37.5°C), heart rate (100 BPM), movement (at rest), and ambient sound volume (50 dB) through a healthcare device and sends the data to the server.

[0948] 2. The server stores the received data in a database and performs preprocessing.

[0949] 3. The server inputs the preprocessed data into the AI ​​model and compares it with past data to detect abnormal patterns.

[0950] 4. The user's facial expressions and voice are collected through the device's camera and microphone, and analyzed by the emotion engine. For example, the emotion engine determines that the user is nervous.

[0951] 5. The server generates a warning message stating, "Your infant's heart rate is abnormally high and movement is persistent. Please contact a medical professional immediately." The tone of the message is gentler because the user is nervous.

[0952] 6. The server sends this message to the user's terminal.

[0953] 7. The user should check the warning message and take appropriate measures by following the instructions provided by the app, such as "Please contact a medical institution immediately."

[0954] In this way, this system monitors the health status of infants in real time and issues a warning that takes into consideration the user's emotional state if an abnormality occurs, thereby enabling early detection and prevention of child abuse.

[0955] The processing flow will be explained below.

[0956] Step 1:

[0957] The device measures the infant's body temperature, heart rate, movement, and ambient sound volume in real time through a healthcare device attached to the infant. The device collects this data at regular intervals (e.g., every minute) and sends it to a server.

[0958] Step 2:

[0959] The server receives the data sent from the device and stores it in a database in chronological order. The database records the time of reception and the values ​​for each measurement item in detail.

[0960] Step 3:

[0961] The server preprocesses the data stored in the database, including imputing missing data, removing noise, and standardizing the data, and then converts the preprocessed data into a format suitable for analysis.

[0962] Step 4:

[0963] The server then feeds the pre-processed data into an AI model, which uses machine learning algorithms to detect abnormal patterns and warning signs, such as a sudden increase in heart rate or sustained abnormal movements.

[0964] Step 5:

[0965] The device uses an on-board camera and microphone to collect the user's facial expressions and voice to recognize the user's emotions, and transmits the data to a server in real time.

[0966] Step 6:

[0967] The server receives the user's emotion data sent from the terminal and analyzes it with an emotion engine. The emotion engine analyzes the user's facial expressions and voice to identify the user's emotional state (e.g., tension, anxiety, calm, etc.).

[0968] Step 7:

[0969] The server generates a warning message based on the anomaly detected by the AI ​​model and the user's emotional state identified by the emotion engine. The warning message includes the nature of the anomaly, its severity, and a recommended response. For example, if the user is identified as nervous, a message such as "The infant's heart rate is increasing rapidly. Please remain calm and contact a medical institution immediately" is generated.

[0970] Step 8:

[0971] The server sends the generated warning message to the user's terminal. The warning is sent in real time so that it can be delivered to the user without delay.

[0972] Step 9:

[0973] The user receives a warning message on their device (smartphone app). The user checks the contents of the warning message and reads the detailed information.

[0974] Step 10:

[0975] The user should respond promptly by following the measures and action plans provided in the warning message, for example, by contacting a medical institution immediately and taking appropriate measures as instructed to protect the health of the infant.

[0976] By following the steps above, it is possible to monitor the infant's health condition and the user's emotional state in real time, and prompt a prompt and appropriate response if an abnormality occurs.

[0977] Example 2

[0978] 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."

[0979] In recent years, early detection and prevention of child abuse and health problems have become important social issues. In particular, there is a need to monitor the health status of young children in real time and take appropriate action if an abnormality is detected. However, current systems have difficulty not only monitoring the health status but also providing appropriate warning messages that take into account the emotional state of the guardian. Therefore, there is a need for a system that can analyze both the health status of young children and the emotional state of the user in real time and issue appropriate warnings.

[0980] 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 data collection means for monitoring the infant's health condition in real time; a data storage means for chronologically storing data acquired by the data collection means; a data preprocessing means for preprocessing the data stored in the data storage means; an AI analysis means for analyzing the data preprocessed by the data preprocessing means and detecting abnormal patterns or danger signals; an emotion analysis means for collecting a user's facial expressions and voice and identifying their emotional state; a warning generation means for generating a warning message based on the abnormality detected by the AI ​​analysis means and the emotional state identified by the emotion analysis means; a warning transmission means for transmitting the warning message generated by the warning generation means to a user terminal; and a user notification means for implementing measures based on the warning message displayed on the user terminal. This makes it possible to analyze both the infant's health condition and the user's emotional state in real time and issue appropriate warnings.

[0981] "Data collection means" refers to devices or mechanisms for real-time monitoring of the infant's health.

[0982] "Data storage means" refers to a system or device for storing data acquired by the data collection means in chronological order.

[0983] The "data preprocessing means" refers to a device or program for performing preprocessing such as complementing missing values ​​and removing noise on the data stored in the data storage means.

[0984] "AI analysis tools" are systems that use artificial intelligence and machine learning algorithms to analyze pre-processed data and detect abnormal patterns or warning signs.

[0985] The "emotion analysis means" is a device or program for collecting the user's facial expressions and voice and identifying the user's emotional state.

[0986] "Warning generation means" means a program or system for generating a warning message based on the abnormality detected by the AI ​​analysis means and the emotional state identified by the emotion analysis means.

[0987] The "warning transmission means" is a device or program for transmitting the generated warning message to the user terminal.

[0988] The "user notification means" is a means for implementing countermeasures based on the warning message displayed on the user terminal.

[0989] The present invention provides a system and method for monitoring the health status of infants in real time and taking prompt action when an abnormality occurs. The system is composed of a data collection means, a data storage means, a data preprocessing means, an AI analysis means, a sentiment analysis means, a warning generation means, a warning transmission means, and a user notification means.

[0990] Data collection methods

[0991] The terminal collects real-time data such as body temperature, heart rate, movement, and ambient sound volume via a healthcare device attached to the infant. This healthcare device is equipped with precision sensors and provides the measurement data to the terminal at regular intervals (e.g., every minute), which is then transmitted to a server via Bluetooth or Wi-Fi.

[0992] Data storage means

[0993] The server receives the data sent from the device and stores it in a database in chronological order. This database can efficiently organize and store data using a high-speed database engine such as MySQL or PostgreSQL.

[0994] Data preprocessing measures

[0995] The server preprocesses the data stored in the database. This preprocessing includes filling in missing values ​​and removing noise. For example, if there is temporal fluctuation in the heart rate data, it will remove it.

[0996] AI analysis means

[0997] The preprocessed data is input into an AI model built using TensorFlow and PyTorch. The server then analyzes the data using the AI ​​model to detect abnormal patterns and warning signs. This analysis requires high accuracy in detecting anomalies by comparing them with past data.

[0998] Emotion analysis means

[0999] The device collects the user's facial expressions and voice through a camera and microphone. The server inputs the collected emotional data into an AI model to identify the user's emotional state (e.g., tension, anger, relief). This allows the system to respond appropriately according to the user's emotional state.

[1000] Warning generation means

[1001] The server generates a warning message based on the abnormality detected by the AI ​​analysis means and the emotional state identified by the emotion analysis means. The warning message includes the nature of the abnormality, its severity, and recommended actions to take. For example, a message such as "The infant's heart rate is abnormally high and the infant continues to show little movement. Please contact a medical institution immediately." If the user is nervous, the tone of the message is adjusted to a gentler tone.

[1002] Alert sending method

[1003] The server sends the generated warning message to the user's device (e.g., smartphone, tablet), where it is displayed in real time.

[1004] User notification method

[1005] The user checks the warning message on the device and responds promptly based on its contents, for example, by following the instruction to "contact a medical institution immediately." In this way, the user can take prompt and appropriate action to protect the health of the infant.

[1006] Specific examples

[1007] 1. The terminal measures the infant's body temperature (37.5°C), heart rate (100 BPM), movement (at rest), and ambient sound volume (50 dB) through a healthcare device and transmits the data to the server.

[1008] 2. The server stores the received data in a database and performs preprocessing.

[1009] 3. The server inputs the preprocessed data into a TensorFlow AI model and compares it with past data to detect abnormal patterns.

[1010] 4. The user's facial expressions and voice are collected through the device's camera and microphone, and analyzed by the emotion engine. For example, the emotion engine determines that the user is nervous.

[1011] 5. The server generates a warning message stating, "Your infant's heart rate is abnormally high and movement is persistent. Please contact a medical professional immediately." The tone of the message is gentler because the user is nervous.

[1012] 6. The server sends this message to the user's terminal.

[1013] 7. The user should check the warning message and take appropriate measures by following the instructions provided by the app, such as "Please contact a medical institution immediately."

[1014] In this way, this system monitors the health status of young children in real time and issues a warning that takes into account the user's emotional state if an abnormality occurs, thereby supporting the early detection and prevention of child abuse.

[1015] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1016] Step 1: Data collection

[1017] The terminal acquires data from a healthcare device attached to the infant. The terminal collects data such as body temperature, heart rate, movement, and ambient sound volume in real time. For example, the infant's body temperature is 37.5°C, heart rate is 100 BPM, movement is stationary, and ambient sound volume is 50 dB. The device is equipped with precision sensors and provides data to the terminal at regular intervals (e.g., every minute).

[1018] Input: Infant's physical information (temperature, heart rate, movement, sound volume)

[1019] Output: A set of health data (e.g., body temperature 37.5°C, heart rate 100 BPM, resting state, 50 dB)

[1020] Step 2: Send data

[1021] The device sends the acquired data to the server. The device sends the collected data to the server using Bluetooth or Wi-Fi.

[1022] Input: A set of collected health data

[1023] Output: Health data sent to the server

[1024] Step 3: Save data

[1025] The server stores the received data in a database. The server uses a database engine such as MySQL or PostgreSQL to organize and store the data in chronological order.

[1026] Input: Health data sent from the device

[1027] Output: Time series data stored in a database

[1028] Step 4: Data Preprocessing

[1029] The server preprocesses the stored data, filling in missing values ​​and removing noise. For example, if there is a temporal fluctuation in the heart rate data, it removes it.

[1030] Input: Time series data stored in a database

[1031] Output: Preprocessed and clean data

[1032] Step 5: AI analysis

[1033] The server then inputs the preprocessed data into an AI model, built using TensorFlow and PyTorch, that detects abnormal patterns and warning signs, such as identifying abnormal heart rate data.

[1034] Input: Preprocessed and clean data

[1035] Output: Anomaly detection results from the AI ​​model

[1036] Step 6: Sentiment Analysis

[1037] The device collects the user's facial expressions and voice using the device's camera and microphone. For example, the camera can capture the user's nervousness.

[1038] Input: User facial and voice data

[1039] Output: Collected emotion data

[1040] Step 7: Sentiment analysis

[1041] The server inputs the emotional data into an AI model to analyze the user's emotional state, for example, determining whether the user is nervous, angry, relieved, etc.

[1042] Input: Emotion data obtained from the device

[1043] Output: Sentiment analysis result (e.g. "I'm nervous")

[1044] Step 8: Generate warnings

[1045] The server generates a warning message based on the results of anomaly detection and emotion analysis. For example, it creates a warning message such as "The infant's heart rate is abnormally high and the infant's movement is still low. Please contact a medical institution immediately." If the user is nervous, it adjusts the tone of the message to a gentler tone.

[1046] Input: Anomaly detection results, sentiment analysis results

[1047] Output: Adjusted warning message

[1048] Step 9: Send alert

[1049] The server then sends the generated warning message to the user's device, which then sends the warning message to the user's smartphone or tablet in real time.

[1050] Input: Adjusted warning message

[1051] Output: Warning message displayed on the user's terminal

[1052] Step 10: User notification and response

[1053] The user checks the warning message on the device and takes prompt action based on the warning message, for example, by following the instructions to "contact a medical institution."

[1054] Input: The warning message displayed on the user's terminal

[1055] Output: Appropriate user action (e.g., contacting a medical facility)

[1056] (Application example 2)

[1057] 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."

[1058] For the purpose of early detection and prevention of child abuse and health abnormalities, it is necessary to monitor the health status of children in real time and promptly and accurately respond when abnormalities are detected. However, conventional systems are unable to provide warning messages that take the user's emotional state into account, which can lead to delays in appropriate responses. Another challenge is providing warning messages in a format that is easy for users to understand.

[1059] The identification processing by the identification 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: data collection means for monitoring the infant's health condition in real time; data storage means for chronologically storing data acquired by the data collection means; AI analysis means for analyzing the data stored in the data storage means and detecting abnormal patterns or danger signals; emotion analysis means for analyzing the user's emotional state; warning generation means for generating a warning message based on the abnormality detected by the AI ​​analysis means and the user's emotional state identified by the emotion analysis means; warning transmission means for transmitting the warning message generated by the warning generation means to a user terminal; and user notification means for implementing measures based on the warning message displayed on the user terminal. This makes it possible to quickly detect abnormalities in the infant's health condition, provide a warning message that takes into account the user's emotional state, and take prompt and appropriate action.

[1060] "Data collection means" refers to equipment or devices that collect data such as body temperature, heart rate, movement, and ambient sound levels to monitor the infant's health.

[1061] "Data storage means" refers to a storage device or database system for storing collected health data in chronological order.

[1062] "AI analytics" refers to the artificial intelligence models and algorithms used to analyze stored data and detect unusual patterns or red flags.

[1063] "Emotion analysis means" refers to devices or software that process data such as facial expressions and voice in order to analyze the user's emotional state.

[1064] "Warning generation means" refers to a system or software that generates a warning message based on anomalies detected by the AI ​​analysis means and the user's emotional state identified by the emotion analysis means.

[1065] The "warning transmission means" refers to a communication device or software for transmitting the generated warning message to the user terminal.

[1066] "User notification means" refers to a system or application that notifies specific countermeasures or action instructions based on the warning message displayed on the user's terminal.

[1067] This invention is a system that monitors the health condition of infants in real time and generates and sends appropriate warning messages based on the user's emotional state when an abnormality is detected. This system uses the following hardware and software to collect, store, and analyze various data handled and generate warning messages.

[1068] Hardware

[1069] Healthcare devices: devices with sensors to measure the infant's temperature, heart rate, movement, and ambient sound levels

[1070] Camera: Uses the device's camera to collect the user's facial expressions.

[1071] Microphone: Uses the microphone installed on the device to collect the user's voice.

[1072] User devices: devices such as smartphones, tablets, and head-mounted displays (HMDs)

[1073] software

[1074] Data collection module: software that receives data collected from healthcare devices

[1075] Data storage module: Software that stores collected data in a database in chronological order.

[1076] AI analysis module: Software that uses machine learning models to analyze collected and stored data and detect abnormal patterns and danger signals.

[1077] Emotion analysis module: Software that analyzes the user's facial expressions and voice data to identify their emotional state (e.g., emotion recognition model using TensorFlow)

[1078] Alert generation module: Software that generates alert messages based on abnormal data and the user's emotional state

[1079] Alert sending module: Communication software (e.g., Python's smtplib library) for sending generated alert messages to user terminals.

[1080] Specific examples of programs

[1081] Data collection and storage

[1082] The terminal measures the infant's body temperature (e.g., 38.0°C), heart rate (e.g., 120 BPM), movement (e.g., while still), and ambient sound volume (e.g., 55 dB) every minute through the healthcare device and transmits the data to the server, where the data storage module stores the data in a database in chronological order.

[1083] Data analysis

[1084] The server analyzes the stored data using an AI analysis module to detect abnormal patterns (e.g., an abnormally high heart rate). The AI ​​analysis module uses a machine learning model to compare the data with past data to detect abnormalities with high accuracy.

[1085] Emotion analysis

[1086] The device's camera and microphone capture the user's facial expressions and voice data, which are then analyzed by the emotion analysis module. For example, the emotion recognition model can identify when the user is nervous.

[1087] Alert Generation and Transmission

[1088] The server generates a warning message (e.g., "The infant's heart rate is high and movement is slow. Please contact a medical institution immediately.") based on the abnormal data detected by the AI ​​analysis module and the user's emotional state identified by the emotion analysis module. When generating a warning message, the warning generation module adjusts the tone of the message, such as by softening it, if the user is nervous.

[1089] The generated warning message is sent in real time to the user terminal via the warning sending module, allowing the user to check the warning message displayed on the terminal and take appropriate action promptly.

[1090] Examples of prompt statements

[1091] python

[1092] Generate warning message based on health data and user emotion state

[1093] health_data = {

[1094] 'body_temp': 38.0,

[1095] 'heart_rate': 120,

[1096] 'movement': 'static',

[1097] 'ambient_noise': 55

[1098] }

[1099] emotion = 1 Assuming 1 corresponds to 'tense' state

[1100] warning_message = generate_warning_message(health_data, emotion)

[1101] print(warning_message)

[1102] In this way, the present invention monitors the infant's health status in real time and issues warnings that take into account the user's emotional state, enabling quick and appropriate responses to protect the infant's health.

[1103] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1104] Step 1:

[1105] The terminal measures the infant's health data (body temperature, heart rate, movement, and ambient sound volume) every minute through a healthcare device. The input in this step is various sensor data, and the output is the measured health data. Specifically, the acquired data includes body temperature of 38.0°C, heart rate of 120 BPM, movement while stationary, and ambient sound volume of 55 dB.

[1106] Step 2:

[1107] The terminal sends the measured health data to the server. The input in this step is the health data from the healthcare device, which is sent to the server in real time. The output is the health data received by the server.

[1108] Step 3:

[1109] The server uses a data storage module to store the received health data in a database in chronological order. The input in this step is the health data sent from the device, which is then stored in the database. The output is the stored database entry.

[1110] Step 4:

[1111] The server then analyzes the stored data using an AI analysis module to detect abnormal patterns or warning signs. The input for this step is the stored health data, and the output is the detection of abnormal patterns or warning signs. Specifically, a machine learning model is used to compare the data with past data to detect abnormalities, such as an abnormally high heart rate.

[1112] Step 5:

[1113] The device's camera and microphone are used to capture the user's facial expression and voice data. The input in this step is raw data from the camera and microphone, and the output is the user's facial expression and voice data.

[1114] Step 6:

[1115] The server analyzes the acquired user's facial and voice data using an emotion analysis module. The input in this step is the user's facial and voice data, and the output is the user's emotional state (e.g., nervousness). Specifically, an emotion recognition model using TensorFlow is used to identify emotional states such as nervousness, relief, and sadness.

[1116] Step 7:

[1117] The server generates a warning message based on the abnormal data detected by the AI ​​analysis module and the user's emotional state identified by the emotion analysis module. The inputs in this step are abnormal patterns or danger signals and the user's emotional state, and the output is a warning message. Specifically, the server generates a warning such as, "The infant's heart rate is high and movement is low. Please contact a medical institution immediately." The tone of the message is adjusted according to the user's emotional state.

[1118] Step 8:

[1119] The server sends the generated warning message to the user terminal via the warning sending module. The input in this step is the warning message, and the output is the warning message displayed on the user terminal. Specifically, the message is sent in real time so that the user can check it immediately.

[1120] Step 9:

[1121] The user checks the warning message displayed on the device and takes appropriate action promptly. The input in this step is the warning message displayed on the device, and the output is the specific countermeasure action the user takes (e.g., contacting a medical institution).

[1122] 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.

[1123] 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.

[1124] 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.

[1125] [Fourth embodiment]

[1126] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1127] 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.

[1128] 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).

[1129] 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.

[1130] 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.

[1131] 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).

[1132] 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.

[1133] 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.

[1134] 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.

[1135] 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.

[1136] 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.

[1137] 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.

[1138] 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."

[1139] The present invention is a system that monitors the health status of young children in real time and issues warnings to support the early detection and prevention of child abuse. Specific embodiments of this system are described below.

[1140] System Configuration

[1141] This system consists of a data collection means, a data storage means, an AI analysis means, a warning generation means, a warning transmission means, and a user notification means. By linking these means, it is possible to monitor the health status of infants with high accuracy and issue a prompt warning if an abnormality occurs.

[1142] Data collection methods

[1143] The healthcare device attached to the terminal measures the infant's body temperature, heart rate, movement, and ambient sound volume in real time. This device is equipped with precision sensors and has the ability to transmit the measurement data to a server at regular intervals (e.g., every minute).

[1144] Data storage means

[1145] The server receives the measurement data sent from the terminal and stores it in a database in chronological order. The data storage means uses a high-speed database engine, allowing the received data to be efficiently organized and stored.

[1146] AI analysis means

[1147] The server preprocesses the data stored in the database, filling in missing values ​​and removing noise. The preprocessed data is then input into an AI model to detect abnormal patterns and warning signs. The AI ​​model uses machine learning algorithms and is capable of detecting anomalies with high accuracy by comparing them with past data.

[1148] Warning generation means

[1149] The server generates a warning message based on the anomaly detected by the AI ​​analysis method. The warning message includes the type of anomaly, its severity, and appropriate action to take. For example, "Your infant's heart rate is increasing rapidly. Please contact a medical institution immediately."

[1150] Alert sending method

[1151] The server then sends the generated warning message to the user's device, such as a smartphone or tablet, which has the ability to receive and display the message in real time.

[1152] User notification method

[1153] The user receives a warning message on their device and checks its contents. The warning message contains specific countermeasures and instructions, allowing the user to take action promptly. In this way, the user can take appropriate action quickly to protect the health of their child.

[1154] Specific examples

[1155] 1. The terminal measures the infant's body temperature (37.5°C), heart rate (100 BPM), movement (at rest), and ambient sound volume (50 dB) through a healthcare device and sends the data to the server.

[1156] 2. The server stores the received data in a database and performs preprocessing.

[1157] 3. The server inputs the preprocessed data into the AI ​​model and compares it with past data to detect abnormal patterns.

[1158] 4. The server generates a warning message stating, "The infant's heart rate is abnormally high and movement is slow," and sends it to the user's device.

[1159] 5. The user should check the warning message and take appropriate measures by following the instructions provided by the app, such as "Please contact a medical institution immediately."

[1160] In this way, this system monitors the health status of young children in real time and prompts immediate action if any abnormalities are detected, thereby enabling early detection and prevention of child abuse.

[1161] The processing flow will be explained below.

[1162] Step 1:

[1163] The device measures the infant's body temperature, heart rate, movement, and ambient sound volume in real time through a healthcare device attached to the infant. The device collects this data at regular intervals (e.g., every minute) and sends it to a server.

[1164] Step 2:

[1165] The server receives the data sent from the device and stores it in a database in chronological order. The database records the time of reception and the values ​​for each measurement item in detail.

[1166] Step 3:

[1167] The server preprocesses the data stored in the database, including imputing missing data, removing noise, and standardizing the data, and then converts the preprocessed data into a format suitable for analysis.

[1168] Step 4:

[1169] The server then feeds the pre-processed data into an AI model, which uses machine learning algorithms to detect abnormal patterns and warning signs, such as a sudden increase in heart rate or sustained abnormal movements.

[1170] Step 5:

[1171] The server generates a warning message based on the anomaly detected by the AI ​​model. The warning message includes the nature of the anomaly, its severity, and a recommended course of action. For example, a message might be generated such as, "Your infant's heart rate is higher than normal and their movement is reduced. Please contact a medical professional immediately."

[1172] Step 6:

[1173] The server sends the generated warning message to the user's terminal. The warning is sent in real time so that it can be delivered to the user without delay.

[1174] Step 7:

[1175] The user receives a warning message on their device (smartphone app). The user checks the contents of the warning message and reads the detailed information.

[1176] Step 8:

[1177] The user should respond promptly by following the measures and action plans provided in the warning message, for example, by contacting a medical institution immediately and taking appropriate measures as instructed to protect the health of the infant.

[1178] This series of processing steps makes it possible to monitor the infant's health condition in real time, and if an abnormality occurs, to quickly issue an alert and prompt appropriate action.

[1179] Example 1

[1180] 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."

[1181] There is a need to accurately understand the health status of infants and respond quickly when abnormalities occur. However, existing systems often fail to adequately detect abnormalities early due to difficulties in improving data quality and detecting abnormal patterns with high accuracy. Furthermore, when generating warning messages, there is a lack of means to present appropriate responses based on the type and severity of the abnormality, making it difficult for users to respond quickly and appropriately.

[1182] 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.

[1183] In this invention, the server includes a data collection means for monitoring the infant's health condition in real time, a data storage means for storing data acquired by the data collection means in chronological order, a data preprocessing means for preprocessing the data stored in the data storage means to complement missing values ​​and remove noise, an AI analysis means for analyzing the preprocessed data and detecting abnormal patterns and danger signals, a warning generation means for generating a warning message based on an abnormality detected by the AI ​​analysis means, and a warning transmission means for transmitting the warning message generated by the warning generation means to a user terminal. This makes it possible to monitor the infant's health condition with high accuracy and to take prompt and appropriate action when an abnormality occurs.

[1184] The "data collection means" is a device for monitoring the infant's health in real time, and is a means for collecting data such as body temperature, heart rate, movement, and ambient sound volume.

[1185] "Data storage means" refers to a means for storing data acquired by data collection means in chronological order, and a means for efficiently organizing and storing data using a high-speed database engine.

[1186] The "data preprocessing means" is a means for preprocessing the data stored in the data storage means, complementing missing values, removing noise, and improving the quality of the data.

[1187] "AI analysis tools" are tools that analyze pre-processed data and use machine learning algorithms to detect abnormal patterns or red flags.

[1188] The "warning generation means" is a means for generating a warning message based on an anomaly detected by the AI ​​analysis means, and is a means for creating a message including detailed information depending on the type of anomaly and its severity.

[1189] The "warning transmission means" is a means for transmitting the warning message generated by the warning generation means to the user terminal, and is a means for delivering the message in real time.

[1190] The "user notification means" is a means for implementing countermeasures based on the warning message displayed on the user terminal, and is a means for providing instructions for the user to take appropriate action.

[1191] System Configuration

[1192] This invention is a system that monitors the health status of infants in real time, detects abnormalities, and generates and sends warning messages. The main components of the system are data collection means, data storage means, data preprocessing means, AI analysis means, warning generation means, warning transmission means, and user notification means.

[1193] Data collection methods

[1194] The healthcare device attached to the terminal measures the infant's body temperature, heart rate, movement, and ambient sound volume in real time. The device uses Bluetooth Low Energy (BLE) to transmit the data to a server every minute. For example, the device measures and collects data when the infant's body temperature is 37.5°C, heart rate is 100 BPM, movement is stationary, and ambient sound volume is 50 dB.

[1195] Data storage means

[1196] The server receives the data sent from the device. The received data is given a timestamp and stored in a database in chronological order using a high-speed database engine such as MySQL or PostgreSQL. This method allows the data to be organized and stored efficiently.

[1197] Data preprocessing measures

[1198] The server preprocesses the data stored in the database. This preprocessing involves filling in missing values ​​and removing noise using the Python pandas library. This improves the quality of the data. For example, if missing values ​​are detected, peripheral data is filled in, and noisy data is removed using filtering techniques.

[1199] AI analysis means

[1200] The server then inputs the preprocessed data into an AI model, which uses machine learning libraries such as TensorFlow and PyTorch to compare it with past data to detect abnormal patterns and warning signs. For example, a sudden increase in heart rate and lack of movement would be considered an abnormality.

[1201] Warning generation means

[1202] The server generates a warning message based on the abnormality detected by the AI ​​analysis method. The warning message includes the type of abnormality, its severity, and appropriate measures to take. For example, the message generated may read, "Your infant's heart rate is rapidly increasing. Please contact a medical institution immediately."

[1203] Alert sending method

[1204] The server sends the generated warning messages to the user's device using HTTP or WebSocket, and the messages are displayed in real time on smartphones and tablets, allowing users to receive the warnings immediately.

[1205] User notification method

[1206] The user receives a warning message on their device and checks its contents. The application displays the warning message in a pop-up window, providing specific countermeasures and instructions on how to respond. The user can then take prompt action. For example, they could take appropriate measures by following the instructions to "contact a medical institution immediately."

[1207] Specific examples

[1208] 1. The device measures the infant's body temperature (37.5°C), heart rate (100 BPM), movement (at rest), and ambient sound volume (50 dB) using a healthcare device, and transmits the data to the server via BLE every minute.

[1209] 2. The server stores the received data in a MySQL database, timestamps it, and organizes it.

[1210] 3. The server preprocesses the data using Python's pandas library to impute missing values ​​and remove noise.

[1211] 4. The server feeds the preprocessed data into an AI model powered by TensorFlow to detect abnormal patterns.

[1212] 5. The server generates a warning message stating "Infant's heart rate is abnormally high and movement is persistently low" and includes appropriate responses based on severity.

[1213] 6. The server sends a warning message to the user's smartphone via the HTTP protocol and displays it in real time.

[1214] 7. The user receives a warning message on their smartphone and takes appropriate measures by following the instructions to "contact a medical institution immediately."

[1215] In this way, the invention can monitor the health status of infants with high accuracy, quickly issue an alert when an abnormality occurs, and prompt appropriate measures.

[1216] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1217] Step 1:

[1218] The healthcare device attached to the terminal measures the infant's body temperature, heart rate, movement, and ambient sound volume in real time. Specifically, it collects data on body temperature (37.5°C), heart rate (100 BPM), motion (still), and ambient sound volume (50 dB). This measurement data is sent to a server via Bluetooth Low Energy (BLE) every minute.

[1219] Input: Infant temperature, heart rate, movement, and ambient sound volume data

[1220] Output: Measurement data sent to the server via BLE

[1221] Step 2:

[1222] The server receives the measurement data sent from the device, assigns a timestamp to the received data, and stores it in a database in chronological order using a high-speed database engine such as MySQL or PostgreSQL.

[1223] Input: Measurement data received via BLE

[1224] Output: Measurement data stored in a database with time stamps

[1225] Step 3:

[1226] The server preprocesses the data stored in the database. This preprocessing uses the Python pandas library to fill in missing values ​​and remove noise. For example, when a missing value is detected, it is filled in using the surrounding data, and noisy data is removed using filtering techniques.

[1227] Input: Data stored in a database

[1228] Output: Preprocessed data (after missing value imputation and noise removal)

[1229] Step 4:

[1230] The server then inputs the preprocessed data into an AI model, which uses machine learning libraries like TensorFlow and PyTorch to compare it with past data to detect unusual patterns and warning signs. For example, a spike in heart rate and lack of movement could be identified as an anomaly.

[1231] Input: Preprocessed data

[1232] Output: Detected abnormal patterns and danger signals

[1233] Step 5:

[1234] The server generates a warning message based on the anomaly detected by the AI ​​analysis method. The warning message includes the type of anomaly, its severity, and appropriate action to take. For example, a message such as "Your infant's heart rate is increasing rapidly. Please contact a medical institution immediately."

[1235] Input: Detected abnormal patterns or warning signs

[1236] Output: Generated warning message

[1237] Step 6:

[1238] The server sends the generated warning message to the user's device using HTTP or WebSocket, and the message is displayed in real time on the smartphone or tablet, allowing the user to receive the warning immediately.

[1239] Input: The generated warning message

[1240] Output: The warning message sent to the user's terminal.

[1241] Step 7:

[1242] The user receives a warning message on their device and checks its contents. The application displays a pop-up warning message with specific countermeasures and instructions on how to respond. The user can then take action promptly. For example, they can follow the instructions to "contact a medical institution immediately."

[1243] Input: The warning message sent to the user's terminal.

[1244] Output: User confirmation and prompt action

[1245] (Application example 1)

[1246] 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."

[1247] There is a growing need for systems that can monitor the health of young children in real time and issue immediate warnings when abnormalities occur. However, conventional systems have limitations in the accuracy of anomaly detection and the detail of warning messages, which means that appropriate responses are not taken promptly. There is also a need to improve the performance of AI models for anomaly detection.

[1248] 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.

[1249] In this invention, the server includes a data collection means for monitoring the infant's health condition in real time, a data storage means for chronologically storing data acquired by the data collection means, an AI analysis means for analyzing the data stored in the data storage means and detecting abnormal patterns or danger signals, a warning generation means for generating a warning message based on the abnormality detected by the AI ​​analysis means, a warning transmission means for transmitting the warning message generated by the warning generation means to a user terminal, a user notification means for taking measures based on the warning message displayed on the user terminal, and a learning means for using a prompt sentence in a generative AI model to improve the abnormality detection ability of the AI ​​analysis means. This improves the accuracy of monitoring the infant's health condition, enables appropriate warning messages to be quickly generated and sent, and enables users to respond quickly.

[1250] A "data collection means" is a device or mechanism for measuring an infant's temperature, heart rate, movement, and ambient sound volume and obtaining this data in real time.

[1251] "Data storage means" means a device or system that records and stores data acquired by data collection means in chronological order, with the purpose of storing data efficiently and safely.

[1252] "AI analysis means" means a device or program that utilizes artificial intelligence to analyze data recorded in a data storage means and detect abnormal patterns or danger signals.

[1253] The "warning generation means" is a device or program that generates a warning message based on an abnormality detected by the AI ​​analysis means.

[1254] The "alert sending means" is a communication device or system for sending the generated alert message to the user's terminal.

[1255] The "user notification means" is a device or program that provides guidance or instructions for implementing countermeasures based on the warning message displayed on the user terminal.

[1256] A "generative AI model" is a model that uses artificial intelligence learning algorithms to improve anomaly detection capabilities.

[1257] A "prompt sentence" is a textual sentence used as training data input in a generative AI model to improve the AI's ability to detect anomalies.

[1258] The present invention is a system for monitoring the health status of an infant in real time and issuing a warning if an abnormality occurs. The system includes the following means.

[1259] System Configuration

[1260] The server has a means for collecting data, a means for storing data, a means for analyzing AI, a means for generating warnings, a means for sending warnings, a means for notifying users, and a means for learning using prompt sentences in a generated AI model.

[1261] Data collection methods

[1262] The data collection tool is a healthcare device that measures the infant's temperature, heart rate, movement, and ambient sound volume in real time, and transmits this data to a server over the internet.

[1263] Data storage means

[1264] The server's data storage mechanism stores data received via the Flask API in a MySQL database in chronological order, allowing historical health data to be recorded and later analyzed.

[1265] AI analysis means

[1266] The server preprocesses the stored data, removing noise and imputing missing values. The preprocessed data is then analyzed using a TensorFlow model to detect abnormal patterns and warning signs. This AI analysis method uses a generative AI model to input training data in the form of prompt sentences, improving its anomaly detection capabilities.

[1267] Warning generation means

[1268] The server generates a warning message based on the anomaly detected by the AI ​​analysis method, including the type and severity of the anomaly and guidelines for the user to take immediate action.

[1269] Alert sending method

[1270] The server then sends the generated alert message to the user's smartphone using Firebase Cloud Messaging, allowing the user to receive the alert in real time.

[1271] User notification method

[1272] A warning message will be displayed on the user's smartphone along with specific guidelines for countermeasures. Users can follow these guidelines to quickly implement appropriate countermeasures. This method allows for rapid response to abnormalities in the infant's health.

[1273] Specific examples

[1274] The following is a specific example of how the system works. For example, suppose a healthcare device measures an infant's body temperature of 37.5°C, heart rate of 100 BPM, minimal movement, and ambient sound volume of 50 dB. This data is sent to a server and stored in a MySQL database. An abnormal condition is then detected by a TensorFlow model, which generates a warning message stating, "The infant's heart rate is abnormally high and the infant continues to exhibit minimal movement." This warning message is then sent to the user's smartphone via Firebase Cloud Messaging. The user receives the warning message and specific guidelines, allowing them to promptly contact a medical institution.

[1275] Prompt Sentence Examples

[1276] Below are some example prompts used by the generative AI model:

[1277] Prompt: Create an AI model to monitor the health of infants in real time and detect abnormal patterns or danger signals. Input data consists of body temperature, heart rate, movement, and ambient sound volume, and a warning message should be generated if an abnormality is detected.

[1278] In this way, the present invention can monitor the health condition of an infant with high accuracy, and immediately issue a warning if an abnormality occurs, thereby ensuring the safety of the infant.

[1279] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1280] Step 1:

[1281] The server receives the infant's temperature, heart rate, movement, and ambient sound volume from the healthcare devices in real time via the Internet. The health status data measured from each sensor is sent to the server as input data. The server receives this data using the Flask API.

[1282] Step 2:

[1283] The server stores the received data in a MySQL database in chronological order. The input data is the health status data received by the server, and the output is the database entries stored in chronological order. In this step, the server efficiently stores and organizes the data.

[1284] Step 3:

[1285] The server performs preprocessing on the stored data. This preprocessing includes noise removal and missing value completion. The input data is the stored health status data, and the output data is the preprocessed, clean data. The server performs data cleansing to input into the model.

[1286] Step 4:

[1287] The server inputs the preprocessed data into a TensorFlow model to detect abnormal patterns and danger signals. The input data is the preprocessed health status data, and the output data is a threshold crossing result indicating the presence or absence of abnormal patterns. The server detects abnormalities based on the model output.

[1288] Step 5:

[1289] When an anomaly is detected, the server generates a warning message using a warning generation means. The input data is the anomaly detection result, and the output data is the warning message. The generated warning message includes the type and severity of the anomaly, as well as specific countermeasure guidelines.

[1290] Step 6:

[1291] The server sends the generated warning message to the user's smartphone using Firebase Cloud Messaging. The input data is the warning message, and the output data is a notification to the user's device. The user receives the warning message in real time.

[1292] Step 7:

[1293] The user checks the received warning message and promptly takes measures according to the specific guidelines. The input data is the warning message, and the output is the execution of the measures. The user takes appropriate action, such as contacting a medical institution.

[1294] Step 8:

[1295] The server trains the generative AI model using prompt sentences to improve its anomaly detection capabilities. The input data is the training dataset and prompt sentences, and the output data is the updated AI model. Below is an example of a prompt sentence.

[1296] Prompt: Create an AI model to monitor the health of infants in real time and detect abnormal patterns or danger signals. Input data consists of body temperature, heart rate, movement, and ambient sound volume, and a warning message should be generated if an abnormality is detected.

[1297] 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.

[1298] The present invention is a system that monitors the health status of young children in real time and issues warnings to support the early detection and prevention of child abuse. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system can adjust the content and presentation method of warning messages, enabling more effective responses. A specific embodiment of this system is described below.

[1299] System Configuration

[1300] This system consists of a data collection means, a data storage means, an AI analysis means, a warning generation means, a warning transmission means, a user notification means, and an emotion engine. By linking these means, it is possible to monitor the health status of infants and the emotional state of the user in real time, and to issue a prompt warning if an abnormality occurs.

[1301] Data collection methods

[1302] The healthcare device attached to the terminal measures the infant's body temperature, heart rate, movement, and ambient sound volume in real time. This device is equipped with precise sensors and collects the measurement data at regular intervals (e.g., every minute) and sends it to a server.

[1303] Data storage means

[1304] The server receives data sent from the terminal and stores it in a database in chronological order. The data storage method uses a high-speed database engine, allowing the received data to be organized and stored efficiently.

[1305] AI analysis means

[1306] The server preprocesses the data stored in the database, filling in missing values ​​and removing noise. The preprocessed data is then input into an AI model to detect abnormal patterns and warning signs. The AI ​​model uses machine learning algorithms and is capable of detecting anomalies with high accuracy by comparing them with past data.

[1307] Emotion Engine

[1308] The emotion engine identifies the user's emotional state by analyzing their facial expressions and voice. It uses the device's built-in camera and microphone to collect user emotion data and analyzes it using an AI model.

[1309] Warning generation means

[1310] The server generates a warning message based on the anomaly detected by the AI ​​analysis method and the user's emotional state identified by the emotion engine. The warning message includes the content and severity of the anomaly, as well as recommended actions. For example, if the user is in a tense state, the warning message will be adjusted to use more polite language.

[1311] Alert sending method

[1312] The server then sends the generated warning message to the user's device, such as a smartphone or tablet, which has the ability to receive and display the message in real time.

[1313] User notification method

[1314] The user receives a warning message on their device and checks its contents. The warning message contains specific countermeasures and instructions, allowing the user to take action promptly. In this way, the user can take appropriate action quickly to protect the health of their child.

[1315] Specific examples

[1316] 1. The terminal measures the infant's body temperature (37.5°C), heart rate (100 BPM), movement (at rest), and ambient sound volume (50 dB) through a healthcare device and sends the data to the server.

[1317] 2. The server stores the received data in a database and performs preprocessing.

[1318] 3. The server inputs the preprocessed data into the AI ​​model and compares it with past data to detect abnormal patterns.

[1319] 4. The user's facial expressions and voice are collected through the device's camera and microphone, and analyzed by the emotion engine. For example, the emotion engine determines that the user is nervous.

[1320] 5. The server generates a warning message stating, "Your infant's heart rate is abnormally high and movement is persistent. Please contact a medical professional immediately." The tone of the message is gentler because the user is nervous.

[1321] 6. The server sends this message to the user's terminal.

[1322] 7. The user should check the warning message and take appropriate measures by following the instructions provided by the app, such as "Please contact a medical institution immediately."

[1323] In this way, this system monitors the health status of infants in real time and issues a warning that takes into consideration the user's emotional state if an abnormality occurs, thereby enabling early detection and prevention of child abuse.

[1324] The processing flow will be explained below.

[1325] Step 1:

[1326] The device measures the infant's body temperature, heart rate, movement, and ambient sound volume in real time through a healthcare device attached to the infant. The device collects this data at regular intervals (e.g., every minute) and sends it to a server.

[1327] Step 2:

[1328] The server receives the data sent from the device and stores it in a database in chronological order. The database records the time of reception and the values ​​for each measurement item in detail.

[1329] Step 3:

[1330] The server preprocesses the data stored in the database, including imputing missing data, removing noise, and standardizing the data, and then converts the preprocessed data into a format suitable for analysis.

[1331] Step 4:

[1332] The server then feeds the pre-processed data into an AI model, which uses machine learning algorithms to detect abnormal patterns and warning signs, such as a sudden increase in heart rate or sustained abnormal movements.

[1333] Step 5:

[1334] The device uses an on-board camera and microphone to collect the user's facial expressions and voice to recognize the user's emotions, and transmits the data to a server in real time.

[1335] Step 6:

[1336] The server receives the user's emotion data sent from the terminal and analyzes it with an emotion engine. The emotion engine analyzes the user's facial expressions and voice to identify the user's emotional state (e.g., tension, anxiety, calm, etc.).

[1337] Step 7:

[1338] The server generates a warning message based on the anomaly detected by the AI ​​model and the user's emotional state identified by the emotion engine. The warning message includes the nature of the anomaly, its severity, and a recommended response. For example, if the user is identified as nervous, a message such as "The infant's heart rate is increasing rapidly. Please remain calm and contact a medical institution immediately" is generated.

[1339] Step 8:

[1340] The server sends the generated warning message to the user's terminal. The warning is sent in real time so that it can be delivered to the user without delay.

[1341] Step 9:

[1342] The user receives a warning message on their device (smartphone app). The user checks the contents of the warning message and reads the detailed information.

[1343] Step 10:

[1344] The user should respond promptly by following the measures and action plans provided in the warning message, for example, by contacting a medical institution immediately and taking appropriate measures as instructed to protect the health of the infant.

[1345] By following the steps above, it is possible to monitor the infant's health condition and the user's emotional state in real time, and prompt a prompt and appropriate response if an abnormality occurs.

[1346] Example 2

[1347] 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."

[1348] In recent years, early detection and prevention of child abuse and health problems have become important social issues. In particular, there is a need to monitor the health status of young children in real time and take appropriate action if an abnormality is detected. However, current systems have difficulty not only monitoring the health status but also providing appropriate warning messages that take into account the emotional state of the guardian. Therefore, there is a need for a system that can analyze both the health status of young children and the emotional state of the user in real time and issue appropriate warnings.

[1349] 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 data collection means for monitoring the infant's health condition in real time; a data storage means for chronologically storing data acquired by the data collection means; a data preprocessing means for preprocessing the data stored in the data storage means; an AI analysis means for analyzing the data preprocessed by the data preprocessing means and detecting abnormal patterns or danger signals; an emotion analysis means for collecting a user's facial expressions and voice and identifying their emotional state; a warning generation means for generating a warning message based on the abnormality detected by the AI ​​analysis means and the emotional state identified by the emotion analysis means; a warning transmission means for transmitting the warning message generated by the warning generation means to a user terminal; and a user notification means for implementing measures based on the warning message displayed on the user terminal. This makes it possible to analyze both the infant's health condition and the user's emotional state in real time and issue appropriate warnings.

[1350] "Data collection means" refers to devices or mechanisms for real-time monitoring of the infant's health.

[1351] "Data storage means" refers to a system or device for storing data acquired by the data collection means in chronological order.

[1352] The "data preprocessing means" refers to a device or program for performing preprocessing such as complementing missing values ​​and removing noise on the data stored in the data storage means.

[1353] "AI analysis tools" are systems that use artificial intelligence and machine learning algorithms to analyze pre-processed data and detect abnormal patterns or warning signs.

[1354] The "emotion analysis means" is a device or program for collecting the user's facial expressions and voice and identifying the user's emotional state.

[1355] "Warning generation means" means a program or system for generating a warning message based on the abnormality detected by the AI ​​analysis means and the emotional state identified by the emotion analysis means.

[1356] The "warning transmission means" is a device or program for transmitting the generated warning message to the user terminal.

[1357] The "user notification means" is a means for implementing countermeasures based on the warning message displayed on the user terminal.

[1358] The present invention provides a system and method for monitoring the health status of infants in real time and taking prompt action when an abnormality occurs. The system is composed of a data collection means, a data storage means, a data preprocessing means, an AI analysis means, a sentiment analysis means, a warning generation means, a warning transmission means, and a user notification means.

[1359] Data collection methods

[1360] The terminal collects real-time data such as body temperature, heart rate, movement, and ambient sound volume via a healthcare device attached to the infant. This healthcare device is equipped with precision sensors and provides the measurement data to the terminal at regular intervals (e.g., every minute), which is then transmitted to a server via Bluetooth or Wi-Fi.

[1361] Data storage means

[1362] The server receives the data sent from the device and stores it in a database in chronological order. This database can efficiently organize and store data using a high-speed database engine such as MySQL or PostgreSQL.

[1363] Data preprocessing measures

[1364] The server preprocesses the data stored in the database. This preprocessing includes filling in missing values ​​and removing noise. For example, if there is temporal fluctuation in the heart rate data, it will remove it.

[1365] AI analysis means

[1366] The preprocessed data is input into an AI model built using TensorFlow and PyTorch. The server then analyzes the data using the AI ​​model to detect abnormal patterns and warning signs. This analysis requires high accuracy in detecting anomalies by comparing them with past data.

[1367] Emotion analysis means

[1368] The device collects the user's facial expressions and voice through a camera and microphone. The server inputs the collected emotional data into an AI model to identify the user's emotional state (e.g., tension, anger, relief). This allows the system to respond appropriately according to the user's emotional state.

[1369] Warning generation means

[1370] The server generates a warning message based on the abnormality detected by the AI ​​analysis means and the emotional state identified by the emotion analysis means. The warning message includes the nature of the abnormality, its severity, and recommended actions to take. For example, a message such as "The infant's heart rate is abnormally high and the infant continues to show little movement. Please contact a medical institution immediately." If the user is nervous, the tone of the message is adjusted to a gentler tone.

[1371] Alert sending method

[1372] The server sends the generated warning message to the user's device (e.g., smartphone, tablet), where it is displayed in real time.

[1373] User notification method

[1374] The user checks the warning message on the device and responds promptly based on its contents, for example, by following the instruction to "contact a medical institution immediately." In this way, the user can take prompt and appropriate action to protect the health of the infant.

[1375] Specific examples

[1376] 1. The terminal measures the infant's body temperature (37.5°C), heart rate (100 BPM), movement (at rest), and ambient sound volume (50 dB) through a healthcare device and transmits the data to the server.

[1377] 2. The server stores the received data in a database and performs preprocessing.

[1378] 3. The server inputs the preprocessed data into a TensorFlow AI model and compares it with past data to detect abnormal patterns.

[1379] 4. The user's facial expressions and voice are collected through the device's camera and microphone, and analyzed by the emotion engine. For example, the emotion engine determines that the user is nervous.

[1380] 5. The server generates a warning message stating, "Your infant's heart rate is abnormally high and movement is persistent. Please contact a medical professional immediately." The tone of the message is gentler because the user is nervous.

[1381] 6. The server sends this message to the user's terminal.

[1382] 7. The user should check the warning message and take appropriate measures by following the instructions provided by the app, such as "Please contact a medical institution immediately."

[1383] In this way, this system monitors the health status of young children in real time and issues a warning that takes into account the user's emotional state if an abnormality occurs, thereby supporting the early detection and prevention of child abuse.

[1384] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1385] Step 1: Data collection

[1386] The terminal acquires data from a healthcare device attached to the infant. The terminal collects data such as body temperature, heart rate, movement, and ambient sound volume in real time. For example, the infant's body temperature is 37.5°C, heart rate is 100 BPM, movement is stationary, and ambient sound volume is 50 dB. The device is equipped with precision sensors and provides data to the terminal at regular intervals (e.g., every minute).

[1387] Input: Infant's physical information (temperature, heart rate, movement, sound volume)

[1388] Output: A set of health data (e.g., body temperature 37.5°C, heart rate 100 BPM, resting state, 50 dB)

[1389] Step 2: Send data

[1390] The device sends the acquired data to the server. The device sends the collected data to the server using Bluetooth or Wi-Fi.

[1391] Input: A set of collected health data

[1392] Output: Health data sent to the server

[1393] Step 3: Save data

[1394] The server stores the received data in a database. The server uses a database engine such as MySQL or PostgreSQL to organize and store the data in chronological order.

[1395] Input: Health data sent from the device

[1396] Output: Time series data stored in a database

[1397] Step 4: Data Preprocessing

[1398] The server preprocesses the stored data, filling in missing values ​​and removing noise. For example, if there is a temporal fluctuation in the heart rate data, it removes it.

[1399] Input: Time series data stored in a database

[1400] Output: Preprocessed and clean data

[1401] Step 5: AI analysis

[1402] The server then inputs the preprocessed data into an AI model, built using TensorFlow and PyTorch, that detects abnormal patterns and warning signs, such as identifying abnormal heart rate data.

[1403] Input: Preprocessed and clean data

[1404] Output: Anomaly detection results from the AI ​​model

[1405] Step 6: Sentiment Analysis

[1406] The device collects the user's facial expressions and voice using the device's camera and microphone. For example, the camera can capture the user's nervousness.

[1407] Input: User facial and voice data

[1408] Output: Collected emotion data

[1409] Step 7: Sentiment analysis

[1410] The server inputs the emotional data into an AI model to analyze the user's emotional state, for example, determining whether the user is nervous, angry, relieved, etc.

[1411] Input: Emotion data obtained from the device

[1412] Output: Sentiment analysis result (e.g. "I'm nervous")

[1413] Step 8: Generate warnings

[1414] The server generates a warning message based on the results of anomaly detection and emotion analysis. For example, it creates a warning message such as "The infant's heart rate is abnormally high and the infant's movement is still low. Please contact a medical institution immediately." If the user is nervous, it adjusts the tone of the message to a gentler tone.

[1415] Input: Anomaly detection results, sentiment analysis results

[1416] Output: Adjusted warning message

[1417] Step 9: Send alert

[1418] The server then sends the generated warning message to the user's device, which then sends the warning message to the user's smartphone or tablet in real time.

[1419] Input: Adjusted warning message

[1420] Output: Warning message displayed on the user's terminal

[1421] Step 10: User notification and response

[1422] The user checks the warning message on the device and takes prompt action based on the warning message, for example, by following the instructions to "contact a medical institution."

[1423] Input: The warning message displayed on the user's terminal

[1424] Output: Appropriate user action (e.g., contacting a medical facility)

[1425] (Application example 2)

[1426] 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."

[1427] For the purpose of early detection and prevention of child abuse and health abnormalities, it is necessary to monitor the health status of children in real time and promptly and accurately respond when abnormalities are detected. However, conventional systems are unable to provide warning messages that take the user's emotional state into account, which can lead to delays in appropriate responses. Another challenge is providing warning messages in a format that is easy for users to understand.

[1428] The identification processing by the identification 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: data collection means for monitoring the infant's health condition in real time; data storage means for chronologically storing data acquired by the data collection means; AI analysis means for analyzing the data stored in the data storage means and detecting abnormal patterns or danger signals; emotion analysis means for analyzing the user's emotional state; warning generation means for generating a warning message based on the abnormality detected by the AI ​​analysis means and the user's emotional state identified by the emotion analysis means; warning transmission means for transmitting the warning message generated by the warning generation means to a user terminal; and user notification means for implementing measures based on the warning message displayed on the user terminal. This makes it possible to quickly detect abnormalities in the infant's health condition, provide a warning message that takes into account the user's emotional state, and take prompt and appropriate action.

[1429] "Data collection means" refers to equipment or devices that collect data such as body temperature, heart rate, movement, and ambient sound levels to monitor the infant's health.

[1430] "Data storage means" refers to a storage device or database system for storing collected health data in chronological order.

[1431] "AI analytics" refers to the artificial intelligence models and algorithms used to analyze stored data and detect unusual patterns or red flags.

[1432] "Emotion analysis means" refers to devices or software that process data such as facial expressions and voice in order to analyze the user's emotional state.

[1433] "Warning generation means" refers to a system or software that generates a warning message based on anomalies detected by the AI ​​analysis means and the user's emotional state identified by the emotion analysis means.

[1434] The "warning transmission means" refers to a communication device or software for transmitting the generated warning message to the user terminal.

[1435] "User notification means" refers to a system or application that notifies specific countermeasures or action instructions based on the warning message displayed on the user's terminal.

[1436] This invention is a system that monitors the health condition of infants in real time and generates and sends appropriate warning messages based on the user's emotional state when an abnormality is detected. This system uses the following hardware and software to collect, store, and analyze various data handled and generate warning messages.

[1437] Hardware

[1438] Healthcare devices: devices with sensors to measure the infant's temperature, heart rate, movement, and ambient sound levels

[1439] Camera: Uses the device's camera to collect the user's facial expressions.

[1440] Microphone: Uses the microphone installed on the device to collect the user's voice.

[1441] User devices: devices such as smartphones, tablets, and head-mounted displays (HMDs)

[1442] software

[1443] Data collection module: software that receives data collected from healthcare devices

[1444] Data storage module: Software that stores collected data in a database in chronological order.

[1445] AI analysis module: Software that uses machine learning models to analyze collected and stored data and detect abnormal patterns and danger signals.

[1446] Emotion analysis module: Software that analyzes the user's facial expressions and voice data to identify their emotional state (e.g., emotion recognition model using TensorFlow)

[1447] Alert generation module: Software that generates alert messages based on abnormal data and the user's emotional state

[1448] Alert sending module: Communication software (e.g., Python's smtplib library) for sending generated alert messages to user terminals.

[1449] Specific examples of programs

[1450] Data collection and storage

[1451] The terminal measures the infant's body temperature (e.g., 38.0°C), heart rate (e.g., 120 BPM), movement (e.g., while still), and ambient sound volume (e.g., 55 dB) every minute through the healthcare device and transmits the data to the server, where the data storage module stores the data in a database in chronological order.

[1452] Data analysis

[1453] The server analyzes the stored data using an AI analysis module to detect abnormal patterns (e.g., an abnormally high heart rate). The AI ​​analysis module uses a machine learning model to compare the data with past data to detect abnormalities with high accuracy.

[1454] Emotion analysis

[1455] The device's camera and microphone capture the user's facial expressions and voice data, which are then analyzed by the emotion analysis module. For example, the emotion recognition model can identify when the user is nervous.

[1456] Alert Generation and Transmission

[1457] The server generates a warning message (e.g., "The infant's heart rate is high and movement is slow. Please contact a medical institution immediately.") based on the abnormal data detected by the AI ​​analysis module and the user's emotional state identified by the emotion analysis module. When generating a warning message, the warning generation module adjusts the tone of the message, such as by softening it, if the user is nervous.

[1458] The generated warning message is sent in real time to the user terminal via the warning sending module, allowing the user to check the warning message displayed on the terminal and take appropriate action promptly.

[1459] Examples of prompt statements

[1460] python

[1461] Generate warning message based on health data and user emotion state

[1462] health_data = {

[1463] 'body_temp': 38.0,

[1464] 'heart_rate': 120,

[1465] 'movement': 'static',

[1466] 'ambient_noise': 55

[1467] }

[1468] emotion = 1 Assuming 1 corresponds to 'tense' state

[1469] warning_message = generate_warning_message(health_data, emotion)

[1470] print(warning_message)

[1471] In this way, the present invention monitors the infant's health status in real time and issues warnings that take into account the user's emotional state, enabling quick and appropriate responses to protect the infant's health.

[1472] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1473] Step 1:

[1474] The terminal measures the infant's health data (body temperature, heart rate, movement, and ambient sound volume) every minute through a healthcare device. The input in this step is various sensor data, and the output is the measured health data. Specifically, the acquired data includes body temperature of 38.0°C, heart rate of 120 BPM, movement while stationary, and ambient sound volume of 55 dB.

[1475] Step 2:

[1476] The terminal sends the measured health data to the server. The input in this step is the health data from the healthcare device, which is sent to the server in real time. The output is the health data received by the server.

[1477] Step 3:

[1478] The server uses a data storage module to store the received health data in a database in chronological order. The input in this step is the health data sent from the device, which is then stored in the database. The output is the stored database entry.

[1479] Step 4:

[1480] The server then analyzes the stored data using an AI analysis module to detect abnormal patterns or warning signs. The input for this step is the stored health data, and the output is the detection of abnormal patterns or warning signs. Specifically, a machine learning model is used to compare the data with past data to detect abnormalities, such as an abnormally high heart rate.

[1481] Step 5:

[1482] The device's camera and microphone are used to capture the user's facial expression and voice data. The input in this step is raw data from the camera and microphone, and the output is the user's facial expression and voice data.

[1483] Step 6:

[1484] The server analyzes the acquired user's facial and voice data using an emotion analysis module. The input in this step is the user's facial and voice data, and the output is the user's emotional state (e.g., nervousness). Specifically, an emotion recognition model using TensorFlow is used to identify emotional states such as nervousness, relief, and sadness.

[1485] Step 7:

[1486] The server generates a warning message based on the abnormal data detected by the AI ​​analysis module and the user's emotional state identified by the emotion analysis module. The inputs in this step are abnormal patterns or danger signals and the user's emotional state, and the output is a warning message. Specifically, the server generates a warning such as, "The infant's heart rate is high and movement is low. Please contact a medical institution immediately." The tone of the message is adjusted according to the user's emotional state.

[1487] Step 8:

[1488] The server sends the generated warning message to the user terminal via the warning sending module. The input in this step is the warning message, and the output is the warning message displayed on the user terminal. Specifically, the message is sent in real time so that the user can check it immediately.

[1489] Step 9:

[1490] The user checks the warning message displayed on the device and takes appropriate action promptly. The input in this step is the warning message displayed on the device, and the output is the specific countermeasure action the user takes (e.g., contacting a medical institution).

[1491] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1492] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1493] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1494] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1495] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1496] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1497] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1498] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1499] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1500] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1501] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1502] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1503] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1504] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1505] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1506] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1507] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1508] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1509] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1510] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1511] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1512] The following is further disclosed regarding the above embodiment.

[1513] (Claim 1)

[1514] a data collection tool for real-time monitoring of infant health status;

[1515] a data storage means for storing the data acquired by the data collection means in chronological order;

[1516] an AI analysis means for analyzing the data stored in the data storage means and detecting abnormal patterns or danger signals;

[1517] a warning generation means for generating a warning message based on the abnormality detected by the AI ​​analysis means;

[1518] a warning sending means for sending the warning message generated by the warning generating means to a user terminal;

[1519] a user notification means for implementing measures based on the warning message displayed on the user terminal;

[1520] A system including:

[1521] (Claim 2)

[1522] 10. The system of claim 1, wherein the data collection means includes healthcare devices that measure the infant's temperature, heart rate, movement, and ambient sound volume.

[1523] (Claim 3)

[1524] 2. The system according to claim 1, wherein the warning generating means includes means for generating detailed information about the warning message based on the type of abnormality and its severity.

[1525] (Claim 4)

[1526] 2. The system according to claim 1, wherein the AI ​​analysis means includes a preprocessing means for removing missing values ​​and noise from the data.

[1527] "Example 1"

[1528] (Claim 1)

[1529] a data collection tool for real-time monitoring of infant health status;

[1530] a data storage means for storing the data acquired by the data collection means in chronological order;

[1531] a data preprocessing means for preprocessing the data stored in the data storage means, and for complementing missing values ​​and removing noise;

[1532] an AI analysis means for analyzing the data preprocessed by the data preprocessing means and detecting abnormal patterns or danger signals;

[1533] a warning generation means for generating a warning message based on the abnormality detected by the AI ​​analysis means;

[1534] a warning sending means for sending the warning message generated by the warning generating means to a user terminal;

[1535] a user notification means for implementing measures based on the warning message displayed on the user terminal;

[1536] A system including:

[1537] (Claim 2)

[1538] 10. The system of claim 1, wherein the data collection means includes healthcare devices that measure the infant's temperature, heart rate, movement, and ambient sound volume.

[1539] (Claim 3)

[1540] 2. The system according to claim 1, wherein the warning generating means includes means for generating detailed information about the warning message based on the type of abnormality and its severity.

[1541] "Application Example 1"

[1542] (Claim 1)

[1543] a data collection tool for real-time monitoring of infant health status;

[1544] a data storage means for storing the data acquired by the data collection means in chronological order;

[1545] an AI analysis means for analyzing the data stored in the data storage means and detecting abnormal patterns or danger signals;

[1546] a warning generation means for generating a warning message based on the abnormality detected by the AI ​​analysis means;

[1547] a warning sending means for sending the warning message generated by the warning generating means to a user terminal;

[1548] a user notification means for implementing measures based on the warning message displayed on the user terminal;

[1549] A learning means for learning using a prompt sentence in a generative AI model to improve the anomaly detection capability of the AI ​​analysis means;

[1550] A system including:

[1551] (Claim 2)

[1552] 10. The system of claim 1, wherein the data collection means includes healthcare devices that measure the infant's temperature, heart rate, movement, and ambient sound volume.

[1553] (Claim 3)

[1554] 2. The system according to claim 1, wherein the warning generating means includes means for generating detailed information of a warning message based on the type of abnormality and its severity, and for presenting a guideline for enabling a user to take a prompt action.

[1555] "Example 2: Combining Emotion Engines"

[1556] (Claim 1)

[1557] a data collection tool for real-time monitoring of infant health status;

[1558] a data storage means for storing the data acquired by the data collection means in chronological order;

[1559] a data preprocessing means for preprocessing the data stored in the data storage means;

[1560] an AI analysis means for analyzing the data preprocessed by the data preprocessing means and detecting abnormal patterns or danger signals;

[1561] emotion analysis means for collecting facial expressions and voices of a user and identifying the user's emotional state;

[1562] a warning generation means for generating a warning message based on the abnormality detected by the AI ​​analysis means and the emotional state identified by the emotion analysis means;

[1563] a warning sending means for sending the warning message generated by the warning generating means to a user terminal;

[1564] a user notification means for implementing measures based on the warning message displayed on the user terminal;

[1565] A system including:

[1566] (Claim 2)

[1567] 10. The system of claim 1, wherein the data collection means includes healthcare devices that measure the infant's temperature, heart rate, movement, and ambient sound volume.

[1568] (Claim 3)

[1569] 2. The system according to claim 1, wherein the warning generating means generates detailed information for the warning message based on the type of abnormality and its severity, and further includes means for adjusting the content of the message depending on the emotional state.

[1570] "Application example 2 when combining emotion engines"

[1571] (Claim 1)

[1572] a data collection tool for real-time monitoring of infant health status;

[1573] a data storage means for storing the data acquired by the data collection means in chronological order;

[1574] an AI analysis means for analyzing the data stored in the data storage means and detecting abnormal patterns or danger signals;

[1575] emotion analysis means for analyzing the emotional state of a user;

[1576] a warning generation means for generating a warning message based on the abnormality detected by the AI ​​analysis means and the emotional state of the user identified by the emotion analysis means;

[1577] a warning sending means for sending the warning message generated by the warning generating means to a user terminal;

[1578] a user notification means for implementing measures based on the warning message displayed on the user terminal;

[1579] A system including:

[1580] (Claim 2)

[1581] 10. The system of claim 1, wherein the data collection means includes healthcare devices that measure the infant's temperature, heart rate, movement, and ambient sound volume.

[1582] (Claim 3)

[1583] 2. The system of claim 1, wherein the warning generating means includes means for generating detailed information of a warning message based on the type of anomaly, its severity, and the user's emotional state. [Explanation of symbols]

[1584] 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 data collection tool for real-time monitoring of infant health status; a data storage means for storing the data acquired by the data collection means in chronological order; an AI analysis means for analyzing the data stored in the data storage means and detecting abnormal patterns or danger signals; a warning generation means for generating a warning message based on the abnormality detected by the AI ​​analysis means; a warning sending means for sending the warning message generated by the warning generating means to a user terminal; a user notification means for implementing measures based on the warning message displayed on the user terminal; A system including:

2. 10. The system of claim 1, wherein the data collection means includes healthcare devices that measure the infant's temperature, heart rate, movement, and ambient sound volume.

3. 2. The system according to claim 1, wherein the warning generating means includes means for generating detailed information about the warning message based on the type of abnormality and its severity.

4. The system according to claim 1 , wherein the AI ​​analysis means includes a preprocessing means for removing missing values ​​and noise from the data.

Images