Intelligent baby monitoring system and method

Abstract

The invention discloses an intelligent baby monitoring system and method. The system comprises a data acquisition module, a data monitoring module, an AI reasoning module, an intelligent response module and an execution module, the data acquisition module is used for acquiring basic parameter data of a target object based on a plurality of sensors; the data monitoring module is used for acquiring basic parameter data in parallel and judging whether the target object has an abnormal condition or not according to the basic parameter data; the AI reasoning module comprises a crying sound classification model, a sleeping posture recognition model and a sleeping quality analysis model which are respectively used for recognizing crying reasons, sleeping postures and sleeping conditions of the target object; the intelligent response module is used for determining a target response mode according to output results of the data monitoring module and the AI reasoning module and sending the target response mode to the execution module; and the execution module is used for determining a target action according to the target response mode and executing the target action. According to the scheme, the function complexity, the monitoring accuracy and the response intelligence of the system are effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to an intelligent baby monitoring system and method. BACKGROUND

[0002] More and more families are welcoming new babies, and parents' demand for infant sleep health and safety monitoring is becoming more sophisticated. However, infant sleep is unstable, sleep posture is not correct, bedwetting is easy, crying is prominent, and young parents are under heavy work pressure, and long-term care of infants can easily lead to physical and mental exhaustion. Multifunctional baby cribs are intelligent products that respond to the needs of smart homes and sophisticated parenting, but existing baby crib designs are traditional and have outdated functions, and have not fully explored the needs of babies and the pain points of sophisticated parenting.

[0003] Existing multifunctional baby cribs usually rely on a single sensor threshold for routine vital sign monitoring (such as relying only on heart rate to determine sleep posture, and relying only on humidity to determine bedwetting), which can easily result in false positives or false negatives (such as temporary fluctuations in heart rate caused by the baby turning over, which can be misjudged as abnormal sleep posture), thus having low functional accuracy and insufficient intelligence, making it difficult to meet the actual needs of parenting monitoring. SUMMARY

[0004] The present application provides an intelligent baby monitoring system and method, which, on the basis of routine monitoring functions, introduces an AI inference module to analyze the reasons for the baby's crying, accurately identify the sleep posture, and evaluate the sleep quality, while intelligently responding to the monitoring results, effectively improving the functional complexity and monitoring accuracy of the system.

[0005] According to an aspect of the present application, an intelligent baby monitoring system is provided, the system comprising a data acquisition module, a data monitoring module, an AI inference module, an intelligent response module, and an execution module; wherein:

[0006] The data acquisition module is configured to acquire basic parameter data of a target object based on a plurality of sensors; wherein the basic parameters include environmental parameters and vital sign parameters;

[0007] The data monitoring module is configured to acquire the basic parameter data in parallel, and determine whether the target object has an abnormal condition based on the basic parameter data;

[0008] The AI inference module comprises a crying sound classification model, a sleep posture recognition model, and a sleep quality analysis model, the crying sound classification model is configured to identify the reason for the target object's crying, the sleep posture recognition model is configured to identify the sleep posture of the target object, and the sleep quality analysis model is configured to identify the sleep depth of the target object and determine the sleep quality condition based on the sleep depth;

[0009] The intelligent response module is configured to determine a target response mode according to the output results of the data monitoring module and the AI inference module, and send the target response mode to the execution module.

[0010] The execution module is configured to determine a target action according to the target response mode, and execute the target action.

[0011] According to another aspect of the present application, there is provided an intelligent baby monitoring method, the method comprising:

[0012] Basic parameter data of a target object is collected by a plurality of sensors in a data collection module; wherein the basic parameters include environmental parameters and vital sign parameters;

[0013] The data monitoring module is configured to acquire the basic parameter data in parallel, and determine whether the target object has an abnormal condition according to the basic parameter data;

[0014] A crying classification model, a sleep posture recognition model and a sleep quality analysis model in the AI inference module are configured to respectively identify the cause of crying, the sleep posture and the sleep depth of the target object, and the sleep quality analysis model is configured to determine the sleep quality condition of the target object based on the sleep depth;

[0015] The intelligent response module is configured to determine a target response mode according to the output results of the data monitoring module and the AI inference module, and send the target response mode to the execution module;

[0016] The execution module is configured to determine a target action according to the target response mode, and execute the target action.

[0017] According to another aspect of the present application, there is provided an electronic device, the electronic device comprising:

[0018] at least one processor; and,

[0019] a memory in communication with the at least one processor; wherein,

[0020] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the intelligent baby monitoring method according to any one of the embodiments of the present application.

[0021] According to another aspect of the present application, there is provided a computer readable storage medium storing computer instructions for enabling a processor to implement the intelligent baby monitoring method according to any one of the embodiments of the present application when executed by the processor.

[0022] The technical scheme of the embodiment of the present application provides an intelligent baby monitoring system comprising a data acquisition module, a data monitoring module, an AI inference module, an intelligent response module and an execution module; wherein: the data acquisition module is used for acquiring basic parameter data of a target object based on a plurality of sensors; wherein, the basic parameters comprise environmental parameters and vital sign parameters; the data monitoring module is used for acquiring the basic parameter data in parallel, and judging whether the target object has an abnormal condition according to the basic parameter data; the AI inference module comprises a crying sound classification model, a sleep posture recognition model and a sleep quality analysis model, the crying sound classification model is used for identifying the reason for crying of the target object, the sleep posture recognition model is used for identifying the sleep posture of the target object, and the sleep quality analysis model is used for identifying the sleep depth of the target object and determining the sleep quality condition based on the sleep depth; the intelligent response module is used for determining a target response mode according to the output results of the data monitoring module and the AI inference module, and sending the target response mode to the execution module; the execution module is used for determining a target action according to the target response mode, and executing the target action. On the basis of the conventional monitoring function, the present technical scheme combines the AI model to automatically monitor the environment of the baby and the vital signs of the baby in the whole scene of the baby's sleep, safety and health, and intelligently responds to the monitoring results, effectively improves the functional complexity and monitoring accuracy of the system, can reduce the parenting burden of parents, meet the fine parenting needs, and reduce the parenting anxiety; the monitoring function can normally operate when the network is disconnected, thereby guaranteeing the stability, effectiveness and reliability of the system.

[0023] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0025] Figure 1 is a structural schematic diagram of an intelligent baby monitoring system provided according to an embodiment of the present application;

[0026] Figure 2 is a structural schematic diagram of another intelligent baby monitoring system provided according to an embodiment of the present application;

[0027] Figure 3 is a structural schematic diagram of still another intelligent baby monitoring system provided according to an embodiment of the present application;

[0028] Figure 4 This is a flowchart of an intelligent infant monitoring system provided according to an embodiment of the present invention;

[0029] Figure 5 This is a flowchart of an intelligent infant monitoring method provided according to an embodiment of the present invention;

[0030] Figure 6 This is a schematic diagram of the structure of an electronic device that implements an intelligent baby monitoring method according to an embodiment of the present invention. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first," "second," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] Example 1

[0034] Figure 1 This is a schematic diagram of an intelligent infant monitoring system provided in Embodiment 1 of the present invention. This embodiment can be applied to situations where multifunctional intelligent monitoring of infants is required.

[0035] like Figure 1As shown, the system includes a data acquisition module, a data monitoring module, an AI inference module, an intelligent response module, and an execution module. Specifically: the data acquisition module collects basic parameter data of the target object based on multiple sensors; these basic parameters include environmental parameters and vital sign parameters. The data monitoring module acquires the basic parameter data in parallel and determines whether the target object exhibits any abnormalities based on this data. The AI ​​inference module includes a crying sound classification model, a sleeping posture recognition model, and a sleep quality analysis model. The crying sound classification model identifies the cause of the target object's crying, the sleeping posture recognition model identifies the target object's sleeping posture, and the sleep quality analysis model identifies the target object's sleep depth and determines the sleep quality status based on the sleep depth. The intelligent response module determines the target response method based on the outputs of the data monitoring module and the AI ​​inference module and sends the target response method to the execution module. The execution module determines the target action based on the target response method and executes the target action.

[0036] The target object can refer to an infant requiring monitoring. For example, environmental parameters may include temperature, humidity, and light intensity, while vital signs parameters may include body temperature, heart rate, respiration, sound, body movement, and sleeping position. Optionally, the data acquisition module includes a temperature and humidity sensor, a light sensor, a pressure sensor, a millimeter-wave radar, a temperature sensor, a heart rate sensor, a sound sensor, a respiration sensor, and an imaging unit.

[0037] Among them, the temperature and humidity sensor can be used to collect the temperature and humidity of the environment in which the target object is located (such as inside a crib); the light sensor can be used to collect the light intensity of the environment in which the target object is located; the pressure sensor can detect the number of body movements by collecting the pressure distribution of the target object's body in contact with the mattress; the millimeter-wave radar can be used for non-contact body movement monitoring of the target object (avoiding the target object pressing on the sensor); the temperature sensor can be used to monitor the body temperature of the target object; the heart rate sensor can be used to monitor the heart rate of the target object; the sound sensor can be used to collect the sound of the target object; the respiration sensor can be used to monitor the breathing frequency of the target object; and the imaging unit can be used to collect images of the target object's sleeping posture.

[0038] It should be noted that the sensors involved in the data acquisition module can be pre-selected according to functional requirements to ensure the accuracy and stability of data acquisition. For example, the temperature and humidity sensor can be SHT30 (humidity accuracy ±2%RH), the light sensor can be BH1750 (accuracy ±1 lux), the pressure sensor can be FSR402 (accuracy ±0.2kPa, pressure range 0-10kg), the millimeter-wave radar can be RCWL-0516 (24GHz, detection angle 120°, detection distance 0.1-5m), the temperature sensor can be DS18B20 (accuracy ±0.0625℃), the heart rate sensor can be MAX30102 (accuracy ±1bpm), the respiration sensor can be MAX30105 (accuracy ±1 breath / minute), and the imaging unit can be an OV2640 camera (resolution 1920×1080, frame rate 25fps, supports low-light shooting, and can adapt to night scenes).

[0039] In this embodiment, optionally, the system uses the RK3568 as the main control chip. The RK3568 employs a quad-core ARM Cortex-A55 architecture, integrates a dedicated NPU (Neural Processing Unit) with 0.8 TOPS of computing power, supports lightweight AI (Artificial Intelligence) frameworks such as TensorFlow Lite and ONNX Runtime, and features a rich set of interfaces including I2C, SPI, UART, USB, WiFi 5 (802.11ac), and Bluetooth 5.0, serving as the system's computation and control hub. Using the RK3568 as the main control chip in this solution leverages its quad-core A55 architecture and 0.8 TOPS NPU to support parallel processing of multiple sensors and local AI inference, effectively addressing the problem of insufficient computing power in traditional MCUs.

[0040] Specifically, the system uses the RK3568 development board, pre-installed with the Linux 5.10 operating system. It can connect to the SHT30 temperature and humidity sensor, MAX30102 heart rate sensor, MAX30105 respiration sensor, and BH1750 light sensor via the I2C interface; the FSR402 pressure sensor via the SPI interface; the OV2640 1080P camera via the USB 2.0 interface; the RCWL-0516 millimeter-wave radar and ESP8266 WiFi module (as a backup transmission channel) via the UART interface; and a DC motor (to control the baby crib rocking), a stepper motor (to control the raising and lowering of the blackout curtain and the extension and retraction of the side guardrail), a speaker (to play music / voice), and a PTC (Positive Temperature Coefficient) air conditioning module (temperature control range of 18-28℃, power not exceeding 100W) via the GPIO interface. This project utilizes Linux C language for local program development, writing a local control program for the RK3568 to achieve module collaboration. Specifically, it includes a sensor data acquisition program (100ms / cycle), an AI inference invocation program (triggering model inference after receiving data), and an execution module control program (issuing instructions based on the inference results). The local control program employs a multi-threaded design to ensure that all modules run in parallel without blocking.

[0041] The RK3568's specific functions include: 1. Parallel processing of multi-sensor data: It can simultaneously connect to eight types of devices, including temperature and humidity sensors, heart rate sensors, pressure sensors, sound sensors, light sensors, cameras, respiration sensors, and millimeter-wave radar, converting the raw electrical signals collected by the sensors into readable units such as ℃ (body temperature), bpm (heart rate), and dB (sound), ensuring real-time data accuracy; 2. Local AI inference: It utilizes the NPU to accelerate AI model calculations, avoiding reliance on cloud platforms. The response time of core AI functions such as sleep posture recognition and cry classification does not exceed 300ms, and it can still operate normally when the network is disconnected; 3. Module collaborative control: It issues instructions to the execution module based on AI inference results or sensor data. For example, when a prone sleeping position is detected, it can simultaneously trigger an alarm and vibrate the crib; 4. Local data caching: It supports 16GB or more of local storage, automatically caching historical data such as the baby's vital signs, sleep, and crying within 7 days. Data is not lost when the network is disconnected, and it is automatically synchronized to the cloud platform after reconnection.

[0042] The AI ​​inference module deploys various AI models, including a crying sound classification model, a sleeping posture recognition model, and a sleep quality analysis model. These AI models undergo data collection and annotation, model building and optimization, and deployment for practical application. Specifically, the crying classification model employs a hybrid model. During the training phase, over 100,000 infant crying samples labeled with hunger, wetness, discomfort, and drowsiness were collected (the crying samples came from public datasets and anonymous user donations). The samples included infants of different ages (0-12 months) and environmental noise scenarios. The crying classification model was constructed using Python and TensorFlow (the input is the sound feature parameter MFCC, and the output is the probability of four types of crying reasons). The crying classification model was converted to a lightweight format (compressed to less than 5MB) using TensorFlow's lightweight conversion tool to adapt to RK3568 hardware resources. The optimized model was then converted to a format supported by RK3568. After deployment, the MFCC (Mel-Frequency Cepstral Coefficients) features of the crying collected by the sound sensor were extracted in real time, achieving a classification accuracy of no less than 92%, which can distinguish specific reasons for crying.

[0043] The sleep posture recognition model employs a lightweight approach. During training, over 50,000 images labeled with sleep postures (supine (safe), lateral (relatively safe), prone (dangerous), and semi-prone (warning)) were collected (from public datasets and laboratory samples). These images covered various lighting conditions, baby clothing colors, and sleeping angles. The model was constructed using Python and TensorFlow (input: 224×224 pixel image; output: probabilities of the four sleep postures). TensorFlow's lightweight conversion tool was used to convert the model to a lightweight format (compressing the size to under 3MB), removing redundant convolutional layers and limiting the number of parameters to under 2 million to accommodate the RK3568's NPU capabilities. The optimized model was then converted to a format supported by the RK3568. During deployment, the RK3568's ISP (Image Signal Processor) image processing capabilities were utilized to process 1080P camera footage in real time, achieving a sleep posture recognition accuracy of at least 95%, replacing the traditional indirect heart rate assessment method and thus avoiding false alarms.

[0044] The sleep quality analysis model employs a multi-feature fusion model, using four types of data as input features: pressure sensor (number of body movements), heart rate sensor (heart rate fluctuation), respiratory sensor (respiratory rate), and camera (turning over frequency). The model is trained using sleep depth (awake / light sleep / deep sleep / REM) as the label. REM (Rapid Eye Movement) refers to rapid eye movement sleep. The sleep quality analysis model is constructed using Python and XGBoost (inputting the four monitoring features, outputting sleep depth and sleep quality status). The optimized model is converted to a format supported by RK3568. After deployment, it outputs real-time sleep depth (awake / light sleep / deep sleep / REM) and can determine sleep quality status based on the proportion of each sleep depth within a preset time period (e.g., automatically generating a sleep quality score for the previous night at 7 AM every morning). The sleep quality score is calculated by weighting deep sleep (40%), REM (30%), light sleep (20%), and awake sleep (10%), with a maximum score of 10.

[0045] Specifically, the criteria for labeling sleep depth are as follows: (1) Deep sleep: Pressure sensor: ≤1 movement within 5 minutes (body movement determination: pressure change > 5kPa and duration > 500ms); Heart rate sensor: real-time heart rate 120-130bpm, fluctuation range ≤ 3bpm within 1 minute; Respiratory sensor: respiratory rate 30-38 breaths / minute, fluctuation range ≤ 2 breaths / minute within 5 minutes; Camera: no turning over (angle between torso and mattress ≤ 10°); (2) REM: Pressure sensor: ≤1 movement within 5 minutes (muscle relaxation, no large movements); Heart rate sensor: real-time heart rate 125-135bpm (slightly higher than deep sleep, brain active), fluctuation range 3-5bpm within 1 minute; Respiratory sensor: respiratory rate 33-40 breaths / minute (slightly higher than deep sleep), fluctuation range 2-4 breaths / minute within 5 minutes; Camera: no (3) Light sleep: Pressure sensor: 2-5 body movements within 5 minutes (small movements, such as raising hands); Heart rate sensor: real-time heart rate 130-140 bpm, fluctuation range 4-7 bpm in 1 minute; Respiratory sensor: respiratory rate 38-45 breaths / minute, fluctuation range 3-5 breaths / minute in 5 minutes; Camera: 1-2 turns within 5 minutes (small amplitude, trunk angle 30°-45°); (4) Awake: Pressure sensor: ≥8 body movements within 5 minutes (large movements); Heart rate sensor: real-time heart rate >140 bpm, fluctuation range ≥8 bpm in 1 minute; Respiratory sensor: respiratory rate >45 breaths / minute, fluctuation range ≥6 breaths / minute in 5 minutes; Camera: ≥3 turns within 5 minutes, or recognize "sitting up / crying movements". It should be noted that if an intermediate state occurs, the state that is more in the range will be used as the standard (e.g., the data collected by the pressure sensor, heart rate sensor, and breathing sensor all belong to the deep sleep range, but the camera belongs to the light sleep range, because three of them collect data in the deep sleep range, while only one belongs to the light sleep range, so this is judged as a deep sleep state).

[0046] In this embodiment, after acquiring basic parameter data in parallel, the data monitoring module can first synchronize the basic parameter data from different sensors in time, and then determine whether there is any abnormality in the target object based on the synchronized basic parameter data. For example, the specific monitoring functions are as follows: 1. Bedwetting monitoring: A dual verification is performed using an SHT30 temperature and humidity sensor and an FSR402 pressure sensor. The temperature and humidity sensor collects the humidity value inside the crib in real time, and the pressure sensor collects the pressure distribution of the baby's body in contact with the mattress. When the humidity value exceeds the set threshold (relative humidity exceeding 65%) and the pressure distribution shows irregular changes, it can be determined as bedwetting. The data is refreshed every minute. 2. Light intensity monitoring: A BH1750 light sensor collects the light intensity inside the crib blanket in real time. If the monitored value exceeds the system's set range (exceeding 50 lux to avoid strong light affecting sleep), it can be determined as excessive light intensity. 3. Body Movement Monitoring: Pressure sensors record the number of infant body movements, while millimeter-wave radar assists in monitoring non-contact body movements, such as raising arms or kicking legs. If the number of body movements is less than a set value (3 times) within a certain time (5 minutes), the infant can be determined to have entered a sleep state. At this time, data from the camera, pressure sensor, heart rate sensor, and respiration sensor can be integrated and fed into the sleep quality analysis model in the AI ​​inference module. This model identifies the sleep depth and corresponding sleep quality status. 4. Crying Monitoring: Sound sensors (sensitivity not less than -40dB) collect infant sounds in real time. When the sound decibel value exceeds the set range (above 60dB), it can be determined that the infant is crying. The sound data can then be fed into the crying classification model in the AI ​​inference module to identify the cause of the crying. 5. Vital Signs Monitoring: A MAX30102 heart rate sensor is used to monitor the infant's heart rate (normal range 120-160 bpm), a DS18B20 temperature sensor is used to monitor body temperature (normal range 36.5-37.5℃), and a MAX30105 respiratory sensor is used to monitor respiratory rate (normal range 30-60 breaths / minute). Any indicator exceeding the normal range indicates an abnormal vital signs. 6. Sleep Posture Monitoring: A 1080P camera captures real-time images of the infant's sleeping posture, which are then fed into a sleep posture recognition model in the AI ​​inference module. This model identifies the sleep posture (predicting every 30 seconds). If the posture is identified as prone or semi-supine, an abnormal sleep posture is determined.

[0047] In this embodiment, the intelligent response module determines the target response method based on the output results of the data monitoring module and the AI ​​inference module, and sends the target response method to the execution module, which then executes the target action corresponding to the target response method. For example, the target response method includes at least one of playing a lullaby, rocking the crib, raising and lowering the blackout curtain, retractable side rails, adjusting temperature and humidity, providing information reminders, and sound and light alarms. The target action can refer to the execution action used to achieve the target response method. For example, the target action corresponding to playing a lullaby is controlling the speaker to play a lullaby, and the target action corresponding to raising and lowering the blackout curtain is controlling a stepper motor to raise or close the blackout curtain.

[0048] In this embodiment, optionally, the execution module includes a motor drive module, a temperature and humidity control module, and an alarm module. The motor drive module includes a stepper motor, a DC motor, and a reduction gearbox; the temperature and humidity control module includes a PTC air conditioning module and a temperature and humidity controller; and the alarm module includes a speaker, an audio power amplifier, and a light emitter. Specifically, the DC motor, paired with a reduction gearbox (reduction ratio 1:100), ensures stable rocking of the crib (5-8cm); the stepper motor can be a 42-stepper motor, paired with a driver board such as A4988, to achieve precise control of the blackout curtain and side rails; the speaker is connected to an audio power amplifier (such as TDA2822) to ensure adjustable volume and soft sound quality; and the PTC air conditioning module, paired with a temperature and humidity controller, achieves localized temperature and humidity control of the crib.

[0049] It should be noted that this invention abandons the traditional fixed threshold triggering single response mode. It can generate personalized response strategies based on the data monitoring results and AI inference results of the RK3568, combined with the target's historical data (such as past sleep-inducing preferences). For example, for crying responses, differentiated response methods and actions can be executed based on the recognition results of the crying classification model: if the baby is drowsy, the RK3568 retrieves the lullaby with the highest success rate in historical sleep-inducing data (such as Mozart K448), controls the speaker to play it (volume not exceeding 40dB), and simultaneously controls the DC motor to rock the crib at a frequency of 15-20 times / minute (amplitude 5-8cm); if the baby is uncomfortable, an audible and visual alarm is triggered (volume not exceeding 50dB, light is soft warm light), and an emergency reminder is pushed to a mobile device (such as a mobile phone or tablet); if the baby is hungry or wet, a corresponding text reminder is pushed to the mobile device (such as "The baby may be hungry, feeding is recommended"), and soft white noise (volume not exceeding 30dB) is played to soothe the baby.

[0050] For example, for sleep stage responses, the environment can be adjusted based on the sleep depth output by the sleep quality analysis model: during deep sleep, the stepper motor is controlled to close the blackout curtain by 80%, the crib's built-in temperature and humidity control module maintains the temperature at 20-22℃, and all unnecessary prompts are turned off; during light sleep, the DC motor is controlled to gently rock the crib at a frequency of 10 times / minute, and the speaker plays white noise not exceeding 30dB; during REM sleep, rocking is prohibited, and only stable temperature and humidity are maintained.

[0051] For example, in response to abnormal situations, when a dangerous sleeping position (prone position) occurs, in addition to triggering an alarm and sending a notification to the mobile phone, the crib should be controlled to vibrate slightly (1-2 times) to interrupt the dangerous sleeping position; when abnormal vital signs occur (such as body temperature exceeding 38.5℃), navigation information of nearby pediatric hospitals (based on mobile phone positioning) should be sent, and the infant's vital sign history data for the past 24 hours should be synchronized to facilitate doctor's diagnosis; when the infant rolls over to the edge of the crib, the millimeter-wave radar identifies the risk 10-15 seconds in advance, and the RK3568 controls the side guardrail stepper motor to automatically rise (the lifting time does not exceed 1 second) to prevent the infant from falling.

[0052] The technical solution of this invention, based on conventional monitoring functions, combines an AI model to perform multi-functional automatic monitoring of the infant's environment and vital signs across all scenarios of infant sleep, safety, and health, and provides intelligent responses to the monitoring results. This effectively improves the accuracy, timeliness, and effectiveness of infant monitoring, reduces the burden on parents, meets the needs of refined childcare, and reduces parenting anxiety. The monitoring function can operate normally even when the network is offline, thus ensuring the stability and reliability of the system.

[0053] Example 2

[0054] Figure 2 This is a schematic diagram of an intelligent infant monitoring system provided in Embodiment 2 of the present invention. This embodiment is based on the above embodiment and optimized. Specifically, the optimization is as follows: the system further includes a data transmission module, which is used to: encrypt the output results of the data monitoring module and the AI ​​inference module, as well as the basic parameter data, to obtain the target transmission data; determine the target transmission mode according to the current network status; and upload the target transmission data to the target cloud platform based on the target transmission mode.

[0055] The data monitoring module's output can include abnormal situations of the target object, specifically the type of abnormal event (e.g., crying) and its cause (e.g., drowsiness). The AI ​​inference module's output can include the recognition results of the crying classification model, sleeping posture recognition model, and sleep quality analysis model. Target transmitted data can refer to data obtained after encryption. Current network status refers to the network status at the current moment, specifically including good or poor. Target transmission methods can include real-time transmission or delayed transmission. The target cloud platform can be used for data storage (e.g., storing real-time and historical data for 7 days), model update push (pushing update packages to RK3568 when the optimized AI model is released), and abnormal alarm forwarding (forwarding emergency alarm information sent by RK3568 to mobile SMS / APP notifications). Specifically, a cloud service can be built based on the OneNET IoT platform, using the MQTT protocol (QoS level 1, ensuring no message loss) to achieve communication between RK3568 and the target cloud platform.

[0056] In this embodiment, the AES-128 encryption algorithm is used to encrypt the output results and basic parameter data of the data monitoring module and AI inference module, and the current network status is determined after encryption. If the current network status is good, the encrypted target transmission data can be transmitted to the target cloud platform for storage in real time via WiFi or Bluetooth (short-range). If the current network status is poor, the system's built-in storage module can be used to cache the data locally. After the network recovers, the locally cached encrypted data can be automatically transmitted to the target cloud platform for storage, effectively preventing data leakage and loss. The RK3568's built-in storage module can automatically cache historical data for 7 days, including vital sign data every 5 minutes and sleep status data (such as sleep posture and sleep depth) every 30 seconds. Furthermore, the sleeping posture images captured by the camera are only used locally on the RK3568 for AI inference, and the original images are not uploaded; only the classification results of supine / side-lying / prone / semi-prone are uploaded to the target cloud platform to avoid leakage of infant image privacy.

[0057] In this embodiment, optionally, the data transmission module includes a main transmission channel and a backup transmission channel. The main transmission channel uses WiFi or Bluetooth for data transmission, and the backup transmission channel uses WiFi for data transmission.

[0058] For example, the RK3568's built-in WiFi 5 (up to 433Mbps) and Bluetooth 5.0 (10m transmission distance) can be used as the primary transmission channels, while the RK3568's built-in ESP8266 WiFi module (150Mbps) can be used as a backup transmission channel. In this embodiment, the primary transmission channel is used preferentially for data transmission. If an anomaly is detected in the primary transmission channel, the system automatically switches to the backup transmission channel for data transmission. This achieves dual WiFi backup, ensuring uninterrupted data transmission and thus guaranteeing data transmission stability.

[0059] The technical solution of this invention encrypts data through a data transmission module, which can effectively ensure the security of data transmission and avoid data leakage; it determines an appropriate transmission method based on the current network status to improve the efficiency and success rate of data transmission; and it stores system monitoring data and results on a cloud platform to facilitate subsequent data traceability.

[0060] Example 3

[0061] Figure 3 This is a schematic diagram of the structure of an intelligent infant monitoring system provided in Embodiment 3 of the present invention. This embodiment is an optimization based on the aforementioned embodiment. Specifically, the optimization is as follows: the system further includes an information interaction module, which is used to: respond to a data viewing command from the mobile terminal, send the target transmitted data to the mobile terminal so that the mobile terminal can perform intelligent statistical analysis based on the target transmitted data; and respond to a remote control command from the mobile terminal, forward the remote control command to the execution module so that the execution module can execute the remote control command.

[0062] In this embodiment, a WeChat mini-program can be developed using HTML5, CSS3, and JavaScript. A mobile control interface (such as a mobile phone or tablet) can then be developed based on this mini-program, supporting both iOS and Android platforms. It achieves three core functions: real-time monitoring, AI analysis, and remote control. Specifically, the real-time monitoring function allows users to view infant monitoring data at any time, including sensor data, abnormal situation data, and AI inference results. For example, users can view real-time data such as temperature and humidity inside the crib, light intensity, and the infant's heart rate / body temperature / sleeping position. The AI ​​analysis function can display daily / weekly sleep quality scores, sleep depth distribution pie charts (marking the percentage of deep sleep / light sleep / REM sleep), and abnormal event records, such as a prone position warning at 23:00 on May 20th; it can also display 7-day trend curves for heart rate / body temperature / respiratory rate, automatically marking abnormal fluctuation points, such as a body temperature of 37.8℃ at 14:00 on May 21st, which is 0.5℃ higher than the average; it can also calculate the number of times crying each day and the percentage of reasons for crying, such as hunger accounting for 40% and wetness accounting for 30%, and generate sleep / health reports and targeted suggestions, such as frequent crying between 3-4 pm, suggesting feeding 1 hour earlier.

[0063] The remote control function supports personalized settings and allows for remote triggering of sleep-inducing actions, adjusting the opening and closing of blackout curtains, and controlling the temperature of the air conditioning module based on these personalized settings. For example, personalized settings can include: customizing a sleep-inducing scheme with music, rocking frequency, and duration, such as playing ocean waves, rocking 18 times per minute for 5 minutes. The system automatically records the success rate of each scheme, such as scheme A having an 80% success rate, and recommends the optimal scheme. It also supports voice messaging, allowing parents to record soothing messages, such as "Baby, be good, Mommy will be back soon," and send them to the RK3568 via the app, which then controls the speaker to play the messages. Users can add accounts for relatives and friends (such as grandparents) and set permission levels, ranging from viewing data only to controlling the sleep-inducing function. Furthermore, a database designed using MySQL 8.0 stores user information (such as account details, baby's age in months), device data (such as sensor history records, AI inference results, etc.), and operation records (such as remote control commands). A backend interface is written using JSP (Java Server Pages) to enable interaction between the app and the database, such as data querying and command issuance.

[0064] Furthermore, the RK3568 supports a wide range of interface expansions, allowing for the future integration of infant weight sensors, early education projection modules, and more. The AI ​​model can be updated via push notifications from the target cloud platform, such as adding an infant rolling intention recognition function to adapt to the changing needs of infants as they grow.

[0065] Figure 4 This invention provides a flowchart of the operation of an intelligent infant monitoring system. Figure 4As shown, the system first performs power-on initialization, starts the RK3568 main controller, and initializes various core modules (such as the data acquisition module, execution module, and data transmission module). Then, the data detection module collects data from multiple sensors in parallel and monitors the infant's environment and vital signs based on the collected data. Specifically, for bedwetting monitoring, data verification is performed based on humidity data collected by the temperature and humidity sensor and pressure distribution data collected by the pressure sensor to determine if the humidity is greater than 65% and the pressure distribution is irregular; if so, a response is triggered (a bedwetting reminder is pushed to the mobile phone). For light intensity monitoring, data verification is performed based on the light intensity inside the bed collected by the light sensor to determine if the light intensity is greater than 50 lux; if so, a response is triggered (a command is sent to the stepper motor to drive the blackout curtain to close). For vital sign detection, data is collected based on heart rate data from the heart rate sensor, body temperature data from the temperature sensor, and respiratory data from the respiratory sensor. The collected respiratory rate data are verified to determine whether the heart rate meets the requirements of 120-160 bpm, the body temperature meets the requirements of 36.5-37.5℃, and the respiratory rate meets the requirements of 30-60 breaths / min. If any of these requirements are not met, a response is triggered (audio-visual alarm, push notification of abnormal vital signs and detailed abnormal data to the mobile phone, and simultaneous push of navigation to nearby pediatric hospitals); body movement monitoring is performed based on data collected by pressure sensors (counting body movements) and millimeter-wave radar (non-contact body movement); crying monitoring is performed based on sound data collected by sound sensors; and sleep posture monitoring is performed based on sleeping posture images captured by a camera.

[0066] The RK3568 system aggregates all the aforementioned monitoring and response data, and preprocesses the aggregated data, including converting the raw electrical signals into readable units (such as ℃ / bpm / dB) and performing secondary data validity verification (removing sensor fault data). Then, the AI ​​inference module further analyzes the preprocessed data to identify the cause of the infant's crying, sleep posture, sleep depth, and sleep quality. Specifically, for the cause of crying, if it is drowsiness, a soothing response is executed (retrieving the best historical lullaby and controlling the crib to rock via a DC motor); if it is discomfort, an emergency response is executed (audio-visual alarm, push notification to the mobile phone); if it is hunger or wetness, a basic response is executed (push notification to the mobile phone, playing gentle white noise). For sleep posture, if the infant is prone, a danger response is executed (audio-visual alarm, push notification to the mobile phone, controlling the crib to vibrate slightly to interrupt the dangerous sleeping position); if the infant is semi-prone, a warning response is executed (only a notification is pushed to the mobile phone); if the infant is supine or side-lying (safe), only data is recorded.

[0067] The RK3568 locally caches the inference results and related response data of the aforementioned AI model, and uploads the cached data to the target cloud platform for storage via the data transmission module when the network connection is good. The RK3568's information interaction module allows for the execution of mobile phone commands (including data viewing and remote control) to achieve data interaction between the RK3568 and the mobile phone. Furthermore, the system can be configured to perform a "data acquisition-processing-response" process every 100ms.

[0068] In this embodiment, system performance can be verified and targeted optimizations can be performed through functional testing, stability testing, and user experience testing. For example, in functional testing, common infant scenarios (such as prone lying, crying, bedwetting, and fever) can be simulated to verify the AI ​​model's recognition accuracy (target no less than 92%), response speed (target no more than 300ms), and alarm accuracy (target false alarm rate no more than 5%). For instance, simulating an infant lying prone, the test checks whether the sleeping posture recognition model recognizes and triggers an alarm within 300ms, and whether the alarm information is simultaneously pushed to the mobile phone; simulating an infant crying due to hunger, the test checks whether the crying sound classification model accurately recognizes and pushes feeding reminders. In stability testing, the system is run continuously for 72 hours, simulating network interruptions (such as a 2-hour network outage) and voltage fluctuations (180-240V) to test whether local functions (such as AI inference and alarms) are normal, and whether data can be completely retransmitted after reconnecting to the network. Test results require that core functions operate normally during network outages, and that the data retransmission success rate is 100% after reconnecting to the network. In the user experience test, 50 families with infants aged 0-12 months were invited to participate in the test, and feedback was collected to adjust parameters: the frequency of soothing to sleep was optimized to 10-20 times / minute (adjusted according to the infant's acceptance to avoid discomfort caused by excessive frequency), the alarm volume was adjusted to no more than 50dB (to avoid startling the infant), and the APP interface was simplified (the sleep report entry was placed on the homepage, which can be viewed in one step); the AI ​​model was optimized based on feedback, such as adding special crying samples to improve classification accuracy.

[0069] The technical solution of this invention can realize data interaction between the system and the mobile terminal through the information interaction module, which makes it easy for the mobile terminal to keep track of the baby's status in real time and supports personalized remote control, which helps to improve the baby monitoring experience and reduce parenting anxiety.

[0070] Example 4

[0071] Figure 5 This is a flowchart of an intelligent infant monitoring method provided in Embodiment 4 of the present invention. This embodiment is applicable to situations requiring multifunctional intelligent monitoring of infants and can be implemented based on the aforementioned intelligent infant monitoring system. Optionally, the system uses an RK3568 as the main control chip.

[0072] like Figure 5As shown, the method in this embodiment specifically includes the following steps:

[0073] S110 collects basic parameter data of the target object through multiple sensors in the data acquisition module; among which, the basic parameters include environmental parameters and vital signs parameters.

[0074] In this embodiment, optionally, the data acquisition module includes a temperature and humidity sensor, a light sensor, a pressure sensor, a millimeter-wave radar, a temperature sensor, a heart rate sensor, a sound sensor, a respiration sensor, and an imaging unit.

[0075] S120 acquires basic parameter data in parallel through the data monitoring module and determines whether there are any abnormalities in the target object based on the basic parameter data.

[0076] S130 uses the crying classification model, sleeping posture recognition model and sleep quality analysis model in the AI ​​inference module to identify the cause of the target object's crying, sleeping posture and sleep depth respectively, and uses the sleep quality analysis model to determine the target object's sleep quality status based on sleep depth.

[0077] S140 determines the target response method based on the output results of the data monitoring module and the AI ​​inference module through the intelligent response module, and sends the target response method to the execution module.

[0078] In this embodiment, optionally, the execution module includes a motor drive module, a temperature and humidity control module, and an alarm module.

[0079] S150, the execution module determines the target action based on the target response method and executes the target action.

[0080] The technical solution of this invention, based on conventional monitoring functions, combines an AI model to perform multi-functional automatic monitoring of the infant's environment and vital signs across all scenarios of infant sleep, safety, and health, and provides intelligent responses to the monitoring results. This effectively improves the accuracy, timeliness, and effectiveness of infant monitoring, reduces the burden on parents, meets the needs of refined childcare, and reduces parenting anxiety. The monitoring function can operate normally even when the network is offline, thus ensuring the stability and reliability of the system.

[0081] In this embodiment, optionally, the method further includes: encrypting the output results of the data monitoring module and the AI ​​inference module, as well as the basic parameter data, through the data transmission module to obtain target transmission data; determining the target transmission mode based on the current network status; and uploading the target transmission data to the target cloud platform based on the target transmission mode.

[0082] In this embodiment, optionally, the data transmission module includes a main transmission channel and a backup transmission channel. The main transmission channel uses WiFi or Bluetooth for data transmission, and the backup transmission channel uses WiFi for data transmission.

[0083] In this embodiment, optionally, the method further includes: responding to a data viewing instruction from the mobile terminal, sending the target transmission data to the mobile terminal via an information interaction module, so that the mobile terminal performs intelligent statistical analysis based on the target transmission data; and responding to a remote control instruction from the mobile terminal, forwarding the remote control instruction to the execution module via the information interaction module, so that the execution module executes the remote control instruction.

[0084] Example 5

[0085] Figure 6 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0086] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0087] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0088] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as intelligent baby monitoring methods.

[0089] In some embodiments, the intelligent infant monitoring method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the intelligent infant monitoring method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the intelligent infant monitoring method by any other suitable means (e.g., by means of firmware).

[0090] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0091] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0092] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0093] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0094] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0095] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0096] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0097] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An intelligent infant monitoring system, characterized in that, The system includes a data acquisition module, a data monitoring module, an AI inference module, an intelligent response module, and an execution module; wherein: The data acquisition module is used to collect basic parameter data of the target object based on multiple sensors; wherein, the basic parameters include environmental parameters and vital signs parameters; The data monitoring module is used to acquire the basic parameter data in parallel and determine whether there is any abnormality in the target object based on the basic parameter data; The AI ​​inference module includes a crying sound classification model, a sleeping posture recognition model, and a sleep quality analysis model. The crying sound classification model is used to identify the cause of the target object's crying, the sleeping posture recognition model is used to identify the target object's sleeping posture, and the sleep quality analysis model is used to identify the target object's sleep depth and determine the sleep quality status based on the sleep depth. The intelligent response module is used to determine the target response method based on the output results of the data monitoring module and the AI ​​inference module, and send the target response method to the execution module; The execution module is used to determine the target action based on the target response method and execute the target action.

2. The system according to claim 1, characterized in that, The data acquisition module includes a temperature and humidity sensor, a light sensor, a pressure sensor, a millimeter-wave radar, a temperature sensor, a heart rate sensor, a sound sensor, a respiration sensor, and an imaging unit.

3. The system according to claim 1, characterized in that, The execution module includes a motor drive module, a temperature and humidity control module, and an alarm module.

4. The system according to claim 1, characterized in that, The system further includes a data transmission module, which is used for: The outputs of the data monitoring module and the AI ​​inference module, as well as the basic parameter data, are encrypted to obtain the target transmission data. The target transmission method is determined based on the current network status, and the target transmission data is uploaded to the target cloud platform based on the target transmission method.

5. The system according to claim 4, characterized in that, The data transmission module includes a main transmission channel and a backup transmission channel. The main transmission channel uses WiFi or Bluetooth for data transmission, and the backup transmission channel uses WiFi for data transmission.

6. The system according to claim 4, characterized in that, The system further includes an information interaction module, which is used for: In response to a data viewing command from a mobile device, the target transmitted data is sent to the mobile device so that the mobile device can perform intelligent statistical analysis based on the target transmitted data. In response to a remote control command from the mobile terminal, the remote control command is forwarded to the execution module for execution.

7. The system according to any one of claims 1-6, characterized in that, The system uses RK3568 as the main control chip.

8. A smart infant monitoring method, characterized in that, The method includes: The data acquisition module collects basic parameter data of the target object through multiple sensors; wherein, the basic parameters include environmental parameters and vital signs parameters. The basic parameter data is acquired in parallel by the data monitoring module, and the presence of any abnormalities in the target object is determined based on the basic parameter data. The AI ​​inference module uses a crying classification model, a sleeping posture recognition model, and a sleep quality analysis model to identify the cause of the target object's crying, sleeping posture, and sleep depth, respectively. The sleep quality analysis model then determines the target object's sleep quality based on the sleep depth. The intelligent response module determines the target response method based on the output results of the data monitoring module and the AI ​​inference module, and sends the target response method to the execution module. The execution module determines the target action based on the target response method and executes the target action.

9. The method according to claim 8, characterized in that, The method further includes: The data transmission module encrypts the outputs of the data monitoring module and the AI ​​inference module, as well as the basic parameter data, to obtain the target transmission data. The target transmission method is determined based on the current network status, and the target transmission data is uploaded to the target cloud platform based on the target transmission method.

10. The method according to claim 9, characterized in that, The method further includes: In response to a data viewing command from a mobile device, the target transmission data is sent to the mobile device via an information interaction module, enabling the mobile device to perform intelligent statistical analysis based on the target transmission data. In response to the remote control command from the mobile terminal, the remote control command is forwarded to the execution module through the information interaction module, so that the execution module can execute the remote control command.

Images