Early warning method and device based on nursing requirements, medium and intelligent wearable product

Abstract

The invention discloses an early warning method and device based on nursing requirements, a medium and a smart wearable product, and relates to the technical field of smart home / smart home, and the early warning method based on nursing requirements comprises the steps: detecting the physiological feature data of a target user through a millimeter wave radar, and obtaining the physiological feature data of the target user; detecting first temperature and humidity data and posture data of the target user through an auxiliary sensor module; and based on the physiological feature data, the first temperature and humidity data and the posture data, predicting a nursing demand value of the target user through a nursing prediction model, generating early warning information when the nursing demand value is greater than a preset threshold, and sending the early warning information to at least one terminal device. The method is different from a traditional single sensor detection scheme, through multi-dimensional data fusion, the prediction accuracy is improved, the false alarm rate is reduced, the problem of nursing response delay existing in a traditional scheme is solved, timely response in a complex environment is ensured, and the use experience of a user is improved.

Description

Technical Field

[0001] This application relates to the field of smart home / intelligent family, and more specifically, to a method, device, medium, and smart wearable product for early warning based on care needs. Background Technology

[0002] In today's rapidly developing society and economy, with an ever-accelerating pace of life, families are placing increasing demands on the meticulousness of childcare. Infants and toddlers are the focus of family attention, and every stage of their growth is closely watched by parents; among these, the care of their physiological state is a crucial aspect of daily childcare.

[0003] Currently, the traditional and common method for caring for the physiological needs of infants and young children is diaper care, which relies on humidity sensors. However, traditional diaper care methods only trigger an alarm after detecting a need for physiological care, resulting in a delayed response. Summary of the Invention

[0004] This application provides a method, device, medium, and smart wearable product for early warning based on nursing needs, in order to solve the technical problem that traditional diaper care solutions rely on humidity sensors to detect diaper status, resulting in a delayed nursing response.

[0005] Firstly, this application provides an early warning method based on nursing needs, comprising:

[0006] The target user's physiological characteristic data is detected by millimeter-wave radar, and the target user's first temperature and humidity data and posture data are detected by auxiliary sensor modules.

[0007] Based on the physiological characteristic data, the first temperature and humidity data, and the posture data, the nursing needs of the target user are predicted by a nursing prediction model.

[0008] If the nursing need value exceeds a preset threshold, an early warning message is generated and sent to at least one terminal device.

[0009] Optionally, the step of predicting the nursing needs of the target user based on the physiological characteristic data, the first temperature and humidity data, and the posture data using a nursing prediction model includes:

[0010] Feature extraction is performed on the physiological characteristic data to obtain the temporal characteristics of the target user, and the temporal characteristics include at least one of respiratory rate change rate, peak body movement amplitude, and intestinal peristalsis cycle;

[0011] Feature extraction is performed on the first temperature and humidity data and the posture data to obtain the body position features and temperature and humidity features of the target user;

[0012] Based on the time-series features, the body position features, and the temperature and humidity features, the nursing prediction model predicts the nursing needs of the target user.

[0013] Optionally, the method further includes:

[0014] Acquire historical physiological characteristic data, historical temperature and humidity data, and historical posture data of historical users;

[0015] Feature extraction was performed on the historical physiological data to obtain the rate of change of respiratory rate, peak body movement amplitude, and intestinal peristalsis cycle of the historical user.

[0016] Feature extraction is performed on the historical temperature and humidity data and the historical posture data to obtain the body position characteristics and temperature and humidity characteristics of the historical user.

[0017] The deep learning model is trained based on the respiratory rate change rate, the peak amplitude of body movement, the intestinal peristalsis cycle, the body position characteristics, and the temperature and humidity characteristics to obtain the nursing prediction model.

[0018] Optionally, the method further includes:

[0019] Based on the nursing needs value and the preset threshold, the target early warning strategy for the early warning information is determined;

[0020] Sending the warning information to at least one terminal device includes:

[0021] According to the target early warning strategy, the early warning information is sent to at least one terminal device.

[0022] Optionally, the preset threshold includes a first preset threshold, a second preset threshold, and a third preset threshold; determining the target early warning strategy for the early warning information based on the nursing need value and the preset threshold includes:

[0023] If the nursing need value is greater than the first preset threshold and less than the second preset threshold, the target early warning strategy is determined to be a level one early warning strategy.

[0024] If the nursing need value is greater than the second preset threshold and less than the third preset threshold, the target early warning strategy is determined to be a level two early warning strategy.

[0025] If the nursing need value is greater than the third preset threshold, the target early warning strategy is determined to be a level three early warning strategy.

[0026] Wherein, the first preset threshold is less than the second preset threshold, the second preset threshold is less than the third preset threshold; the warning intensity of the first-level warning strategy is less than that of the second-level warning strategy, and the warning intensity of the second-level warning strategy is less than that of the third-level warning strategy.

[0027] Optionally, the step of predicting the nursing needs of the target user based on the physiological characteristic data, the first temperature and humidity data, and the posture data using a nursing prediction model includes:

[0028] Obtain the historical first temperature and humidity data of the historical user and the historical second temperature and humidity data of the environment where the historical user is located;

[0029] A mapping relationship between the first historical temperature and humidity data and the second historical temperature and humidity data is established based on a support vector regression model.

[0030] Obtain the second temperature and humidity data of the environment where the target user is located;

[0031] Based on the mapping relationship and the second temperature and humidity data, the first temperature and humidity data is corrected to obtain temperature and humidity corrected data.

[0032] Based on the physiological characteristic data, the temperature and humidity correction data, and the posture data, the nursing needs of the target user are predicted using a nursing prediction model.

[0033] Secondly, this application provides an early warning device based on nursing needs, comprising:

[0034] The detection module is used to detect the physiological characteristic data of the target user through millimeter-wave radar, and to detect the first temperature and humidity data and posture data of the target user through an auxiliary sensor module.

[0035] The processing module is used to predict the nursing needs of the target user based on the physiological characteristic data, the first temperature and humidity data, and the posture data through a nursing prediction model.

[0036] The processing module is also used to generate an early warning message when the nursing demand value is greater than a preset threshold, and send the early warning message to at least one terminal device.

[0037] Optionally, the processing module is further configured to extract features from the physiological feature data to obtain the temporal features of the target user, wherein the temporal features include at least one of the respiratory rate change rate, peak body movement amplitude, and intestinal peristalsis cycle.

[0038] The processing module is further configured to extract features from the first temperature and humidity data and the posture data to obtain the body position features and temperature and humidity features of the target user.

[0039] The processing module is further configured to predict the nursing needs of the target user based on the time-series features, the body position features, and the temperature and humidity features using the nursing prediction model.

[0040] Optionally, the early warning device based on care needs may further include: an acquisition module.

[0041] The acquisition module is used to acquire historical physiological characteristic data, historical temperature and humidity data, and historical posture data of historical users.

[0042] The processing module is also used to extract features from the historical physiological data to obtain the respiratory rate change rate, peak body movement amplitude, and intestinal peristalsis cycle of the historical user.

[0043] The processing module is also used to extract features from the historical temperature and humidity data and the historical posture data to obtain the body position features and temperature and humidity features of the historical user.

[0044] The processing module is also used to train the deep learning model based on the respiratory rate change rate, the peak value of body movement amplitude, the intestinal peristalsis cycle, the body position characteristics, and the temperature and humidity characteristics to obtain the nursing prediction model.

[0045] Optionally, the early warning device based on care needs may further include a determination module.

[0046] The determining module is used to determine the target early warning strategy for the early warning information based on the nursing need value and the preset threshold.

[0047] The processing module is further configured to send the warning information to at least one terminal device in accordance with the target warning strategy.

[0048] Optionally, the determining module is further configured to determine the target early warning strategy as a level one early warning strategy when the nursing demand value is greater than the first preset threshold and less than the second preset threshold.

[0049] The determining module is further configured to determine the target early warning strategy as a secondary early warning strategy when the nursing demand value is greater than the second preset threshold and less than the third preset threshold.

[0050] The determining module is further configured to determine the target early warning strategy as a level three early warning strategy when the nursing demand value is greater than the third preset threshold.

[0051] Wherein, the first preset threshold is less than the second preset threshold, the second preset threshold is less than the third preset threshold; the warning intensity of the first-level warning strategy is less than that of the second-level warning strategy, and the warning intensity of the second-level warning strategy is less than that of the third-level warning strategy.

[0052] Optionally, the acquisition module is further configured to acquire historical first temperature and humidity data of historical users and historical second temperature and humidity data of the environment in which the historical users are located.

[0053] The processing module is also used to establish a mapping relationship between the historical first temperature and humidity data and the historical second temperature and humidity data based on a support vector regression model.

[0054] The acquisition module is also used to acquire second temperature and humidity data of the environment in which the target user is located.

[0055] The processing module is further configured to correct the first temperature and humidity data based on the mapping relationship and the second temperature and humidity data to obtain corrected temperature and humidity data.

[0056] The processing module is also used to predict the nursing needs of the target user based on the physiological characteristic data, the temperature and humidity correction data, and the posture data using a nursing prediction model.

[0057] Thirdly, this application provides a smart wearable product, including: a smart wearable product body, a sensor module, and a communication module;

[0058] The sensor module includes a millimeter-wave radar sensor and an auxiliary sensor module. The millimeter-wave radar sensor is used to detect the physiological characteristics of the target user. The auxiliary sensor module includes a flexible pressure sensor and a temperature and humidity sensor. The flexible pressure sensor is attached to the surface of the smart wearable product body and is used to detect changes in the body position of the target user. The temperature and humidity sensor is attached to the smart wearable product body and is used to detect the temperature and humidity information of the smart wearable product.

[0059] The communication module is used to send the generated early warning information to at least one terminal device;

[0060] The smart wearable product is used to predict the care needs value of the target user, generate the warning information, and send the warning information to the at least one terminal device by employing the care needs-based early warning method as described in the first aspect and various possible implementations of the first aspect.

[0061] Fourthly, this application provides a computer-readable storage medium having a computer-executable program stored thereon, which, when executed by a processor, is used to implement the care-needs-based early warning method as described in the first aspect and various possible implementations of the first aspect.

[0062] Fifthly, this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0063] The memory stores computer-executed instructions;

[0064] The processor executes computer execution instructions stored in the memory to implement the care-needs-based early warning method as described in the first aspect and various possible implementations of the first aspect above.

[0065] Sixthly, this application provides a program product including a computer program that, when executed by a processor, implements the care-needs-based early warning method as described above.

[0066] This application provides a nursing need-based early warning method, device, medium, and smart wearable product. It detects the target user's physiological characteristic data using millimeter-wave radar, and detects the target user's initial temperature and humidity data and posture data using an auxiliary sensor module. Based on the physiological characteristic data, the initial temperature and humidity data, and the posture data, a nursing prediction model predicts the target user's nursing need value. If the nursing need value exceeds a preset threshold, an early warning message is generated and sent to at least one terminal device. This method differs from traditional single-sensor detection schemes by using multi-dimensional data fusion to improve prediction accuracy and reduce false alarm rates. It solves the nursing response delay problem existing in traditional schemes, ensuring timely response in complex environments and improving the user experience. Attached Figure Description

[0067] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0068] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0069] Figure 1 A schematic diagram of the hardware environment for the early warning method based on nursing needs provided in this application;

[0070] Figure 2A flowchart illustrating the nursing needs-based early warning method provided in this application. Figure 1 ;

[0071] Figure 3 A flowchart illustrating the nursing needs-based early warning method provided in this application. Figure 2 ;

[0072] Figure 4 A schematic diagram of the structure of the early warning device based on nursing needs provided in this application;

[0073] Figure 5 This is a schematic diagram of the structure of an electronic device provided in this application. Detailed Implementation

[0074] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0075] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application 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 the embodiments of this application 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.

[0076] According to one aspect of the embodiments of this application, a pre-warning method based on care needs is provided. This pre-warning method based on care needs is widely applicable to whole-house intelligent digital control application scenarios such as smart homes, smart home ecosystems, and intelligence house ecosystems. Optionally, in this embodiment, the above-mentioned pre-warning method based on care needs can be applied to, for example... Figure 1 The hardware environment shown consists of terminal device 102 and server 104. For example... Figure 1As shown, server 104 is connected to terminal device 102 via a network and can be used to provide services (such as application services) to the terminal or clients installed on the terminal. A database can be set up on the server or independently of the server to provide data storage services for server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data processing services for server 104.

[0077] The aforementioned network may include, but is not limited to, at least one of the following: wired network, wireless network. The aforementioned wired network may include, but is not limited to, at least one of the following: wide area network, metropolitan area network, local area network. The aforementioned wireless network may include, but is not limited to, at least one of the following: Wi-Fi (Wireless Fidelity), Bluetooth. The terminal device 102 may not be limited to PC, mobile phone, tablet computer, smart air conditioner, smart range hood, smart refrigerator, smart oven, smart stove, smart washing machine, smart water heater, smart washing equipment, smart dishwasher, smart projector, smart TV, smart clothes rack, smart curtains, smart audio-visual equipment, smart socket, smart speaker, smart speaker box, smart fresh air equipment, smart kitchen and bathroom equipment, smart bathroom equipment, smart robot vacuum cleaner, smart window cleaning robot, smart mopping robot, smart air purifier, smart steam oven, smart microwave oven, smart water heater, smart air purifier, smart water dispenser, smart door lock, etc.

[0078] First, the terms used in this application will be explained.

[0079] LSTM: Long Short-Term Memory, is a special type of Recurrent Neural Network (RNN) designed to address the vanishing and exploding gradient problems that traditional RNNs encounter when processing long sequences of data. It is better able to capture and learn long-term dependencies in sequence data.

[0080] BLE: Bluetooth Low Energy, also known as Bluetooth Smart, is a variant of Bluetooth technology specifically designed for short-range wireless communication applications that require low power consumption, low data rates, and long battery life.

[0081] BLE 5.3 protocol: It is a specific version of BLE technology, which represents further optimization and improvement in functionality, performance and security in the evolution of Bluetooth technology.

[0082] Mesh: A mesh network is a distributed network structure formed by multiple nodes interconnected wirelessly or via wired means. Unlike traditional star or tree networks, each node in a mesh network can not only receive and send data, but also act as a repeater to forward data, forming a multi-hop communication path.

[0083] GATT Protocol: Generic Attribute Profile, or GATT for short, is a core component of the BLE protocol stack. It defines a standard framework for data exchange between devices, is built on ATT (Attribute Protocol), and uses a layered structure to organize data, enabling efficient communication between BLE devices.

[0084] Adaptive Frequency Hopping (AFH) is a wireless communication technology that dynamically adjusts the transmission frequency by analyzing channel quality in real time, aiming to avoid interference and maintain stable communication.

[0085] Zigbee protocol: It is a low-power, short-range wireless communication protocol based on the IEEE 802.15.4 standard. It is designed for Internet of Things (IoT) devices and features low power consumption, low cost, strong self-organizing network capability, large network capacity, and high security. It is widely used in smart homes, industrial automation, healthcare, smart cities and other fields.

[0086] Wavelet thresholding denoising algorithm: It is a signal denoising method based on wavelet transform. By thresholding the coefficients in the wavelet domain, it effectively separates the signal from the noise.

[0087] AES-128 is a symmetric encryption algorithm that uses a 128-bit key length and is an implementation of the Advanced Encryption Standard (AES).

[0088] In today's rapidly developing society and economy, with an ever-accelerating pace of life, families are placing increasing demands on the meticulousness of childcare. Infants and toddlers are the focus of family attention, and every stage of their growth is closely watched by parents; among these, the care of their physiological state is a crucial aspect of daily childcare.

[0089] With the advancement of urban development, various outdoor venues suitable for infants and toddlers, such as parks and children's play areas in shopping malls, are increasing, and parents are taking their infants and toddlers out more frequently. However, the outdoor environment is complex and changeable, quite different from the relatively stable indoor environment, which makes it difficult for parents to provide timely and effective care for their infants' physiological needs in outdoor settings.

[0090] Currently, the traditional and common approach to caring for infants' physiological needs (such as urination and defecation) is to use a diaper care solution that relies on humidity sensors. This solution involves placing a humidity sensor in the diaper to detect changes in its humidity. When an infant defecates, urine or feces will change the humidity of the diaper. When the humidity of the diaper reaches a preset threshold, the sensor triggers an alarm mechanism, which then alerts the parents through a connected device (such as a mobile application or a dedicated receiver) to inform them that the infant may need physiological care.

[0091] However, traditional diaper care solutions rely on humidity sensors to detect the diaper's condition, triggering an alarm only when a physiological condition requiring care is detected, resulting in a delayed care response. In daily life, this delayed response can easily lead to contamination of infants' clothing or skin irritation due to prolonged contact with urine or feces, thus affecting the health and comfort of infants.

[0092] In addition, in complex outdoor environments (such as parks, shopping malls, playgrounds, etc.), the environment is complex and changeable, and the temperature and humidity will change frequently. In addition, infants and young children are active and change their body positions frequently, such as quickly changing from sitting to running. When the humidity sensor is affected by changes in ambient temperature and humidity and changes in the infant's body position, it is prone to misjudgment, resulting in inaccurate alarms.

[0093] In a smart home environment, parents are often multitasking, such as preparing meals in the kitchen, handling work in the study, and doing housework on the balcony. At the same time, the separation of indoor spaces (such as different rooms) may cause them to be some distance away from their infants and toddlers. Current traditional solutions for the care of infants and toddlers' physiological conditions, even in relatively stable indoor temperature and humidity environments, have relatively simple alarm signal transmission methods (such as relying solely on local device prompts). When parents are focused on their tasks or are in different rooms, they may easily miss alarm information, or after noticing an alarm, they may be unable to respond to the infant's physiological needs in a timely manner due to being preoccupied with other tasks or spatial barriers. This affects the timeliness of care and makes it difficult to meet the precision requirements of family childcare.

[0094] This application provides a nursing needs-based early warning method aimed at addressing the aforementioned technical problems of existing technologies. This method utilizes multimodal sensors, such as millimeter-wave radar, flexible pressure sensors, and temperature and humidity sensors, to collect physiological signals (respiratory rate, body acceleration, intestinal peristalsis cycle) and environmental parameters (body position, diaper humidity) of infants and young children. It then combines these with edge computing models (such as LSTM neural networks) to extract temporal features, enabling early prediction of nursing (defecation) events. Furthermore, it establishes a direct connection network between the terminal, mobile phone, and watch using the BLE 5.3 protocol, and combines a dynamic wake-up strategy (millimeter-wave radar body movement detection triggering BLE wake-up) with Mesh networking to achieve low-power real-time early warning. This method differs from traditional single-sensor detection schemes by improving prediction accuracy and reducing false alarm rates through multi-dimensional data fusion. It solves the problems of nursing response delays, signal blind spots, insufficient battery life, and difficulties in multi-device collaboration inherent in traditional solutions, ensuring timely response in complex environments and improving the user experience.

[0095] This application also provides a smart wearable product, in which the early warning method based on care needs is applied. The smart wearable product includes: a smart wearable product body, a sensor module, and a communication module.

[0096] The sensor module includes a millimeter-wave radar sensor and an auxiliary sensor module. The millimeter-wave radar sensor is used to detect the physiological characteristics of the target user. The auxiliary sensor module includes a flexible pressure sensor and a temperature and humidity sensor. The flexible pressure sensor is attached to the surface of the smart wearable product and is used to detect changes in the target user's body position. The temperature and humidity sensor is attached to the smart wearable product and is used to detect the temperature and humidity information of the smart wearable product. The communication module is used to send the generated warning information to at least one terminal device.

[0097] The smart wearable product is also equipped with a control module. During the use of the smart wearable product, the control module adopts the care need-based early warning method in the following embodiments to predict the care need value of the target user, generate early warning information, and send the early warning information to at least one terminal device, thereby alerting specific personnel (such as the target user's parents) whether the target user has a care need and the urgency of the care required if a care need exists.

[0098] For example, the smart wearable product can be a smart diaper. The sensor module of the smart wearable product is integrated from multiple sensors, specifically a millimeter-wave radar sensor, a flexible pressure sensor, and a temperature and humidity sensor. The millimeter-wave radar is embedded inside the smart diaper (5-10cm below the infant's navel) and uses a 60GHz millimeter-wave radar (such as the TI IWR6843, 15mm×15mm in size) to penetrate clothing and detect micro-vibrations of the abdominal wall, collecting the infant's respiratory rate (0.2-0.5Hz) and body acceleration (m / s²). The flexible pressure sensor is attached to the surface of the diaper to detect changes in the infant's position (sitting / standing / lying down). The temperature and humidity sensor is attached near the diaper to detect the temperature and humidity of the internal microenvironment of the smart diaper.

[0099] The communication module uses a BLE5.3 chip, supports a transmission distance of 200 meters (in open areas), and has a sleep power consumption of 0.5μA. It connects directly to mobile phones and watches via the GATT protocol. It can establish a Mesh network for multiple smart devices, such as supporting simultaneous connection of 3 devices. When the network is disconnected, it can run an alert based on the local model parameters of the watch (offline mode can last for 2 hours).

[0100] For the power management of this smart diaper, a button battery (100mAh) can be used to maintain stable battery life; in addition, an energy recovery module can be set up to use thermoelectric generators to replenish 5mAh of power per day and extend battery life.

[0101] This smart wearable product uses multimodal sensors to detect signs of intestinal peristalsis in advance through physiological signals, rather than relying on changes in diaper condition afterward. Combined with changes in the infant's posture and actual temperature and humidity, it can detect the infant's need for care in real time, thereby improving the accuracy of predicting the infant's care needs.

[0102] In addition, the distance between the millimeter-wave radar and the BLE antenna is no less than 10mm, with a 0.3mm aluminum-magnesium alloy shielding layer added in between. Electromagnetic simulation using CST (Computer Simulation Technology) ensures an interference suppression ratio greater than 60dB. Bluetooth Adaptive Frequency Hopping (AFH) technology is adopted to avoid 2.4GHz Wi-Fi channels in real time (avoiding a total of 11 interference channels), enhancing the environmental adaptability of this smart wearable product. Utilizing the 200-meter transmission distance and Mesh networking capability of the BLE5.3 chip, the signal blind spot problem of traditional solutions (such as underground parking garages and elevators) is solved. Even when the network is down, offline early warning can still be achieved through local edge computing.

[0103] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0104] Figure 2 A flowchart illustrating the early warning method based on nursing needs provided in this application embodiment. Figure 1 The execution entity in this embodiment can be, for example, the control module of a smart wearable product. Figure 2 As shown, the early warning method based on nursing needs provided in this embodiment includes:

[0105] S201: Detects physiological characteristic data of the target user through millimeter-wave radar, and detects the target user's initial temperature and humidity data and attitude data through auxiliary sensor modules.

[0106] Among them, physiological characteristic data is used to quantify the physiological state of the target user, the first temperature and humidity data is used to reflect the physical quantity of the internal microenvironment state of the smart wearable product, and the posture data is used to describe the relative position and movement pattern of the target user in space.

[0107] In this embodiment, the smart wearable product is equipped with a sensor module. During the use of the smart wearable product by the target user, the sensor module can detect the target user's physiological characteristic data, first temperature and humidity data, and posture data. The physiological characteristic data includes, for example, physiological signals such as the target user's respiratory rate, body acceleration, and intestinal peristalsis cycle. The first temperature and humidity data includes, for example, the temperature and humidity information of the internal microenvironment of the smart diaper. The posture data includes, for example, the target user's current action mode (sitting / standing / lying down) and changes in the target user's actions.

[0108] For example, the target user's physiological characteristic data is detected by millimeter-wave radar, and the target user's first temperature and humidity data is detected by the temperature and humidity sensor in the auxiliary sensor module, and the target user's posture data is detected by the flexible pressure sensor in the auxiliary sensor module; specifically, the physiological characteristic data acquired at this time is: "respiratory rate of 12-20 times / min, intestinal peristalsis cycle of 3-5 times / min", the first temperature and humidity data is: "humidity of smart diaper area is 40%RH-60%RH, temperature is 25℃", and the posture data is "frequent leg kicking (amplitude greater than 10cm, frequency greater than 2 times / s), trunk twisting angle greater than 30° (attempting to break free from diaper restraint)".

[0109] In some embodiments, for the sensor module in a smart product, an ultrasonic sensor can be used to replace the millimeter-wave radar to detect the physiological characteristics of the target user, and the Zigbee protocol can be used to replace the BLE protocol used by the communication module to support larger device networks.

[0110] S202: Based on physiological characteristic data, primary temperature and humidity data, and posture data, the nursing prediction model is used to predict the nursing needs of the target user.

[0111] S203: If the nursing demand value exceeds a preset threshold, generate an early warning message and send the early warning message to at least one terminal device.

[0112] Among them, the nursing need value is used to indicate the predicted probability that the target user needs nursing care, the nursing prediction model is used to predict the possibility of the target user experiencing a nursing event, and the early warning information is used to alert relevant personnel that the target user has experienced a nursing event. The preset threshold can be, for example, 0.65.

[0113] Understandably, the nursing prediction model utilizes machine learning technology, combined with user physiological characteristic data, posture data, and initial temperature and humidity data of the product's internal microenvironment detected during the use of smart wearable products, to comprehensively construct a predictive model. This nursing prediction model can comprehensively predict the probability of nursing events occurring in target users through multimodal data, thereby providing early warnings to caregivers (such as parents of infants and caregivers of the elderly) to replace smart wearable products; among these nursing events, for example, is urination or defecation for infants. This application does not impose any special restrictions on the types of nursing events.

[0114] The physiological characteristic data, temperature and humidity data, and posture data acquired at that time are input into the nursing prediction model. Based on the real-time situation of the current target user, the nursing needs value of the target user is predicted, and it is determined whether the nursing needs value is greater than the preset threshold.

[0115] Understandably, the preset threshold is a boundary value for the probability of a nursing event occurring for the target user. If the nursing demand value obtained in a given instance is greater than the preset threshold, it indicates that the current target user is more likely to experience a nursing event. In this case, an early warning measure for the nursing event is triggered to provide advance warning to the caregiver. If the nursing demand value obtained in a given instance is not greater than the preset threshold, it indicates that the current target user is less likely to experience a nursing event. In this case, the sensor module continuously detects the target user's physiological characteristic data, temperature and humidity data, and posture data, and repeatedly determines whether the target user's nursing demand value is greater than the preset threshold, thereby achieving dynamic response to nursing events and improving the detection efficiency of nursing events.

[0116] If the nursing demand value exceeds a preset threshold, an early warning message is generated and sent to at least one terminal device to prompt the relevant caregiver of the target user to promptly check and replace the smart wearable product worn by the target user.

[0117] In this embodiment, the smart wearable product and multiple terminal devices are in a mesh network and are communicatively connected. The smart wearable product acquires the target user's physiological signals (respiratory rate, body acceleration, intestinal peristalsis cycle) and environmental parameters (body position, diaper humidity) in real time to predict the target user's care needs. When the care needs exceed a preset threshold, the control module of the smart wearable product generates an early warning message and sends it to at least one corresponding terminal device, thereby achieving early warning based on the target user's care needs. This application does not impose any special restrictions on the location of the control module.

[0118] For example, the physiological characteristic data acquired in this instance are: "respiratory rate 12-20 breaths / min, intestinal peristalsis cycle 3-5 times / min", the first temperature and humidity data are: "humidity of the smart diaper area 40%RH-60%RH, temperature 25℃", and the posture data are: "frequent leg kicking (amplitude greater than 10cm, frequency greater than 2 times / s), trunk twisting angle greater than 30° (attempting to break free from the diaper)". These are input into the nursing prediction model, resulting in a corresponding nursing demand value of 0.8. Since this nursing demand value is greater than the preset threshold of 0.65, the target user is more likely to experience a nursing event. The control module of the smart wearable product generates a warning message: "A nursing demand is expected within 6 minutes, please handle it promptly," and sends this warning message to multiple terminal devices connected to the smart diaper (e.g., smartphones, smartwatches, smart TVs, smart refrigerators, etc.). This application does not impose any special restrictions on the terminal devices.

[0119] In some embodiments, the preset threshold is set based on a combination of factors.

[0120] For example, a large amount of historical data related to the care of target users is collected, including but not limited to care time, frequency, physical condition (such as age, health status, dietary habits, etc.) and environmental factors (such as temperature, humidity, etc.). By conducting in-depth analysis of the collected historical data, statistical methods and machine learning algorithms are used to comprehensively determine the patterns and characteristics of care events. Then, combined with the data distribution, a suitable value is determined as a preset threshold so that the threshold can accurately reflect the probability boundary of care events occurring in target users.

[0121] In other embodiments, the preset threshold can be dynamically set by the nursing prediction model, or it can be set autonomously by the caregiver of the target user. It can also be dynamically adjusted according to the characteristics of the target user (such as age, health status, and lifestyle habits) to achieve personalized prediction.

[0122] This embodiment provides a nursing needs-based early warning control method that detects the target user's physiological characteristic data using millimeter-wave radar, and detects the target user's first temperature and humidity data and posture data using an auxiliary sensor module. Based on the physiological characteristic data, the first temperature and humidity data, and the posture data, a nursing prediction model predicts the target user's nursing needs. If the nursing needs value exceeds a preset threshold, an early warning message is generated and sent to at least one terminal device. This method differs from traditional single-sensor detection schemes by using multi-dimensional data fusion to improve prediction accuracy and reduce false alarm rates. It solves the nursing response delay problem existing in traditional schemes, ensures timely response in complex environments, and improves the user experience.

[0123] Figure 3 A flowchart illustrating the early warning method based on nursing needs provided in this application embodiment. Figure 2 .like Figure 3 As shown, in this embodiment... Figure 2 Based on the embodiments, the early warning method based on nursing needs is described in detail. The early warning method based on nursing needs shown in this embodiment includes:

[0124] S301: Detects physiological characteristic data of the target user through millimeter-wave radar, and detects the target user's initial temperature and humidity data and attitude data through auxiliary sensor modules.

[0125] Step S301 is similar to step S201 above, and will not be repeated here.

[0126] S302: Extract features from physiological characteristic data to obtain the temporal characteristics of the target user.

[0127] S303: Extract features from the first temperature and humidity data and posture data to obtain the target user's body position features and temperature and humidity features.

[0128] S304: Based on time-series characteristics, body position characteristics, and temperature and humidity characteristics, the nursing prediction model predicts the nursing needs of the target user.

[0129] Understandably, feature extraction is performed on data detected by different sensors in order to convert the raw data detected by the sensors into data information that is strongly correlated with nursing events. Since the actual data information acquired by the sensors includes interference information such as environmental noise and motion artifacts, it is necessary to extract features from the acquired physiological feature data, temperature and humidity data, and posture data in order to improve the accuracy of nursing event identification.

[0130] Among them, time-series features are used to reflect the dynamic changes of physiological characteristic data in the time dimension. Time-series features include at least one of the following: respiratory rate change rate, peak body movement amplitude, and intestinal peristalsis cycle; body position features are used to describe the correlation between changes in the target user's body position and nursing events; and temperature and humidity features are used to describe the temperature and humidity changes in the internal microenvironment of smart wearable products.

[0131] For example, feature extraction is performed on physiological characteristic data to obtain the temporal features of the target user, and feature extraction is performed on the first temperature and humidity data and posture data to obtain the body position features and temperature and humidity features of the target user. Specifically, a wavelet threshold denoising algorithm is used to preprocess the acquired raw sensor data (such as respiratory rate range, humidity range, etc.) to filter out high-frequency noise generated by clothing friction. Then, key features are extracted from the preprocessed data to obtain key features (such as mean, mutation rate, classification) corresponding to different sensor data. The extracted temporal features, body position features, and temperature and humidity features are input into the nursing prediction model to predict the nursing needs value of the target user to be 0.8.

[0132] In some embodiments, the nursing prediction model is constructed based on usage data from multiple historical users, specifically including: acquiring historical physiological characteristic data, historical temperature and humidity data, and historical posture data of historical users; extracting features from the historical physiological characteristic data to obtain the respiratory rate of change, peak body movement amplitude, and intestinal peristalsis cycle of historical users; extracting features from the historical temperature and humidity data and historical posture data to obtain the body position characteristics and temperature and humidity characteristics of historical users; and training a deep learning model based on the respiratory rate of change, peak body movement amplitude, intestinal peristalsis cycle, body position characteristics, and temperature and humidity characteristics to obtain the nursing prediction model.

[0133] Understandably, the nursing prediction model is built based on multi-source historical data, which includes, but is not limited to, the physiological signals of historical users (such as respiratory rate, intestinal peristalsis cycle, peak body movement amplitude), environmental signals (such as humidity and temperature of the microenvironment inside the smart diaper), behavioral signals (such as leg kicking frequency, trunk twisting angle, and crying sound frequency), and the time information of each nursing care session for historical users. This application does not impose any special restrictions on the training data for the nursing prediction model.

[0134] Historical physiological characteristics, historical temperature and humidity data, and historical posture data of historical users are obtained. Based on multi-source historical data, time series features and statistical features before and after the occurrence of user nursing events are extracted. A deep learning model is then used for training to finally obtain the nursing prediction model.

[0135] For example, an LSTM and attention mechanism network can be used, with a 10-dimensional feature vector as the input layer (time window of 5 minutes) and a 0-1 probability value as the output layer (not less than 0.8 is judged as a high-risk nursing event) to build a nursing prediction model.

[0136] In addition, attention mechanisms can be used to focus on key signal segments (such as the intestinal peristalsis cycle T), thereby strengthening the weight of key signal segments and improving the model's ability to identify nursing needs.

[0137] In some embodiments, historical first temperature and humidity data of historical users and historical second temperature and humidity data of the environment in which historical users are located are obtained; a mapping relationship between the historical first temperature and humidity data and the historical second temperature and humidity data is established based on a support vector regression model; second temperature and humidity data of the environment in which the target user is located are obtained; the first temperature and humidity data is corrected based on the mapping relationship and the second temperature and humidity data to obtain temperature and humidity corrected data; and the nursing needs of the target user are predicted by a nursing prediction model based on physiological characteristic data, temperature and humidity corrected data and posture data.

[0138] The second temperature and humidity data is used to indicate the temperature and humidity information of the external environment in which the target user is located.

[0139] It is understandable that during the actual use of smart wearable products by target users, the constant changes in the external environment's temperature and humidity will also affect the initial temperature and humidity data obtained by the smart wearable product, which may easily lead to distortion of the initial temperature and humidity data, thereby affecting the accuracy of the care needs value.

[0140] For example, when the external humidity rises suddenly (such as when a sunny day turns into a rainy day), the nursing prediction model may misinterpret the change in environmental humidity as a change in the temperature and humidity of the internal microenvironment of the smart diaper, thus triggering a false alarm.

[0141] Therefore, by combining the second temperature and humidity data of the target user's environment acquired in real time, the first temperature and humidity data is corrected, and the corrected temperature and humidity data, i.e., the temperature and humidity corrected data, is used to predict the probability value of nursing events.

[0142] For example, historical temperature and humidity data of the user and historical temperature and humidity data of the user's environment are obtained. A support vector regression model is used to capture the nonlinear coupling relationship between environmental factors and diaper humidity through linear regression and structural risk minimization in high-dimensional space, thereby establishing a mapping relationship between the historical first temperature and humidity data and the historical second temperature and humidity data. That is, a dynamic coupling relationship is established between the ambient temperature and humidity and the temperature and humidity of the microenvironment inside the smart diaper. Based on this dynamic coupling relationship, the compensation amount of the current first temperature and humidity data can be calculated in real time. The sum of the first temperature and humidity data and the compensation amount is calculated, and the result is determined as the temperature and humidity correction data for the current time. The temperature and humidity correction data, physiological characteristic data, and posture data are input into the nursing prediction model to predict the nursing needs of the current target user.

[0143] In other embodiments, when using a nursing prediction model to predict the probability of nursing events, the real-time acquired second temperature and humidity data can be combined to correct the real-time acquired first temperature and humidity data, thereby obtaining a more accurate prediction result.

[0144] It is understandable that a nonlinear mapping relationship between historical second temperature and humidity data and historical first temperature and humidity data can be established by using a support vector regression model, and then the real-time acquired second temperature and humidity data can be used to predict the corrected first temperature and humidity data, thereby eliminating the masking of physiological signals by environmental interference.

[0145] During the training of the nursing prediction model, it is also necessary to combine the second historical temperature and humidity data with the first historical temperature and humidity data, as well as the nonlinear mapping relationship between the two, to integrate multi-source historical data, capture the complete signal of physiological and environmental interaction, and accurately quantify the impact of the environment on physiology, thereby improving the prediction accuracy of the model.

[0146] S305: Generate an early warning message when the nursing demand value exceeds a preset threshold.

[0147] S306: Based on nursing needs and preset thresholds, determine the target early warning strategy for early warning information.

[0148] S307: In accordance with the target early warning strategy, send the early warning information to at least one terminal device.

[0149] Among them, the early warning strategy is used to indicate the prompting mode of the early warning information, and the target early warning strategy is used to indicate the prediction strategy to be executed in the current instance.

[0150] Understandably, nursing needs values ​​are calculated using a nursing prediction model based on multi-dimensional information such as the target user's physiological characteristics, posture data, and temperature and humidity correction data.

[0151] The preset threshold is the criterion for judging nursing events. When the calculated nursing need value exceeds the preset threshold, it means that the target user may have a nursing need. At this time, the early warning strategy needs to be activated. When the nursing need value is greater than the preset threshold, the early warning strategy needs to be further divided according to different nursing need values. This can more accurately reflect the urgency and probability of the nursing event, allowing caregivers to take appropriate measures according to the level of the early warning.

[0152] In some embodiments, the preset thresholds include a first preset threshold, a second preset threshold, and a third preset threshold; when the nursing demand value is greater than the first preset threshold and less than the second preset threshold, the target early warning strategy is determined to be a level one early warning strategy; when the nursing demand value is greater than the second preset threshold and less than the third preset threshold, the target early warning strategy is determined to be a level two early warning strategy; when the nursing demand value is greater than the third preset threshold, the target early warning strategy is determined to be a level three early warning strategy.

[0153] Wherein, the first preset threshold is less than the second preset threshold, and the second preset threshold is less than the third preset threshold; the warning intensity of the first-level warning strategy is less than that of the second-level warning strategy, and the warning intensity of the second-level warning strategy is less than that of the third-level warning strategy; the first preset threshold can be, for example, 0.65, the second preset threshold can be, for example, 0.8, and the third preset threshold can be, for example, 0.95.

[0154] Understandably, based on the first, second, and third preset thresholds, multiple preset threshold ranges can be determined, and the nursing needs values ​​corresponding to different preset threshold ranges are different. In other words, the probability of a nursing event occurring for the target user is different under different preset threshold ranges. Therefore, different early warning strategies are provided for different preset threshold ranges.

[0155] For the preset threshold range consisting of the first preset threshold and the second preset threshold, the probability of a nursing event occurring for the target user is low to medium (e.g., 0.65-0.8). At this time, a first-level early warning strategy can be adopted. The purpose of this first-level early warning strategy is to awaken the caregiver's attention in advance, so as to respond to the target user's need to replace the smart wearable product in a timely manner.

[0156] For the preset threshold range consisting of the second and third preset thresholds, the probability of a nursing event occurring for the target user is low to medium (e.g., 0.8-0.95). In this case, a two-level early warning strategy can be adopted. The purpose of this two-level early warning strategy is to quickly remind caregivers and allow time for replacing smart wearable products.

[0157] For cases where the probability of a nursing event occurring for the target user exceeds the preset threshold range defined by the third preset threshold, the probability is low to medium (e.g., exceeding 0.95). In such cases, a three-level early warning strategy can be adopted. The purpose of this three-level early warning strategy is to remind caregivers that an emergency response is needed to prevent clothing contamination due to delayed response.

[0158] If the nursing demand value exceeds a preset threshold, an early warning message is generated; based on the nursing demand value and the first, second, and third preset thresholds, an early warning strategy corresponding to the preset threshold range in which the current nursing demand value falls is determined, and the corresponding early warning strategy is determined as the target early warning strategy. The early warning message is sent to at least one terminal device according to the target early warning strategy determined for the current time.

[0159] For example, a first-level warning strategy could be: "Watch vibrates (for 3 seconds, in silent mode)"; a second-level warning strategy could be: "Pop-up window on mobile phone, voice prompt ("Baby is about to defecate and needs care, please prepare a diaper")"; and a third-level warning strategy could be: "Mobile phone alarm, headphone prompt ("Baby is about to defecate and needs care, please prepare a diaper", requires pairing with Bluetooth headphones), and flashing of smart lights."

[0160] In some embodiments, the communication module of the smart wearable device is configured to be dynamically woken up. When the millimeter-wave radar in the sensor module detects body movement, the communication module is woken up, thereby reducing the average power consumption of the communication module to 0.5μA and extending the battery life to more than 7 days.

[0161] In some embodiments, when transmitting physiological characteristics of a target user between different modules, encryption and dynamic key mechanisms can be used to ensure data transmission security.

[0162] For example, AES-128 is used to encrypt physiological characteristic data, and the Bluetooth transmission key is dynamically changed every 10 minutes.

[0163] This embodiment provides a nursing need-based early warning method that detects the physiological characteristic data of a target user using millimeter-wave radar, and detects the target user's first temperature and humidity data and posture data using an auxiliary sensor module. Feature extraction is performed on the physiological characteristic data to obtain the target user's temporal characteristics. Then, feature extraction is performed on the first temperature and humidity data and posture data to obtain the target user's body position characteristics and temperature and humidity characteristics. Based on the temporal characteristics, body position characteristics, and temperature and humidity characteristics, a nursing prediction model predicts the target user's nursing need value. If the nursing need value exceeds a preset threshold, an early warning message is generated. Based on the nursing need value and the preset threshold, a target early warning strategy is determined, and the early warning message is sent to at least one terminal device according to the target early warning strategy. This method differs from traditional single-sensor detection schemes by using multi-dimensional data fusion to improve prediction accuracy and reduce false alarm rates. It solves the nursing response delay problem existing in traditional schemes, overcomes the limitations of traditional humidity detection-based post-event alarms, and avoids interference from complex environments on nursing need-based early warnings. This not only improves the applicability of smart wearable products in complex environments but also enhances the user experience.

[0164] Figure 4 This is a structural schematic diagram of the early warning device based on nursing needs provided in this application. Figure 4 As shown, this application provides an early warning device based on nursing needs, the early warning device 400 based on nursing needs includes:

[0165] The detection module 401 is used to detect the physiological characteristic data of the target user through millimeter-wave radar, and to detect the first temperature and humidity data and attitude data of the target user through an auxiliary sensor module.

[0166] The processing module 402 is used to predict the nursing needs of the target user based on physiological characteristic data, first temperature and humidity data and posture data through a nursing prediction model.

[0167] The processing module 402 is also used to generate an early warning message when the nursing demand value is greater than a preset threshold, and send the early warning message to at least one terminal device.

[0168] Optionally, the processing module 402 is also used to extract features from the physiological feature data to obtain the temporal features of the target user. The temporal features include at least one of the respiratory rate change rate, peak body movement amplitude, and intestinal peristalsis cycle.

[0169] The processing module 402 is also used to extract features from the first temperature and humidity data and posture data to obtain the target user's body position features and temperature and humidity features.

[0170] The processing module 402 is also used to predict the nursing needs of the target user based on time-series features, body position features, and temperature and humidity features through a nursing prediction model.

[0171] Optionally, the early warning device based on care needs also includes: acquisition module 403.

[0172] The acquisition module 403 is used to acquire historical physiological characteristic data, historical temperature and humidity data, and historical posture data of historical users.

[0173] The processing module 402 is also used to extract features from historical physiological characteristic data to obtain the rate of change of respiratory rate, peak body movement amplitude, and intestinal peristalsis cycle of historical users.

[0174] The processing module 402 is also used to extract features from historical temperature and humidity data and historical posture data to obtain the posture features and temperature and humidity features of historical users.

[0175] The processing module 402 is also used to train the deep learning model based on the rate of change of respiratory rate, peak amplitude of body movement, intestinal peristalsis cycle, body position characteristics and temperature and humidity characteristics to obtain a nursing prediction model.

[0176] Optionally, the early warning device based on care needs also includes: determination module 404.

[0177] The determination module 404 is used to determine the target early warning strategy for early warning information based on nursing demand values ​​and preset thresholds.

[0178] The processing module 402 is also used to send the warning information to at least one terminal device in accordance with the target warning strategy.

[0179] Optionally, the determining module 404 is further configured to determine the target early warning strategy as a level one early warning strategy when the nursing demand value is greater than a first preset threshold and less than a second preset threshold.

[0180] The determination module 404 is also used to determine the target early warning strategy as a secondary early warning strategy when the nursing demand value is greater than the second preset threshold and less than the third preset threshold.

[0181] The determination module 404 is also used to determine the target early warning strategy as a level three early warning strategy when the nursing demand value is greater than the third preset threshold.

[0182] Among them, the first preset threshold is less than the second preset threshold, and the second preset threshold is less than the third preset threshold; the warning intensity of the first-level warning strategy is less than that of the second-level warning strategy, and the warning intensity of the second-level warning strategy is less than that of the third-level warning strategy.

[0183] Optionally, the acquisition module 403 is also used to acquire the historical first temperature and humidity data of the historical user and the historical second temperature and humidity data of the environment where the historical user is located.

[0184] The processing module 402 is also used to establish a mapping relationship between the first historical temperature and humidity data and the second historical temperature and humidity data based on the support vector regression model.

[0185] The acquisition module 403 is also used to acquire the second temperature and humidity data of the environment where the target user is located.

[0186] The processing module 402 is also used to correct the first temperature and humidity data based on the mapping relationship and the second temperature and humidity data to obtain temperature and humidity corrected data.

[0187] The processing module 402 is also used to predict the nursing needs of the target user based on physiological characteristic data, temperature and humidity correction data and posture data through a nursing prediction model.

[0188] Figure 5 This is a schematic diagram of the structure of an electronic device provided in this application. Figure 5 As shown, this application provides an electronic device 500, which includes: a receiver 501, a transmitter 502, a processor 503, and a memory 504.

[0189] Receiver 501 is used to receive instructions and data;

[0190] Transmitter 502 is used to send commands and data;

[0191] Memory 504 is used to store instructions executed by the computer;

[0192] The processor 503 is used to execute computer execution instructions stored in the memory 504 to implement the various steps performed by the early warning method based on nursing needs in the above embodiments. For details, please refer to the relevant descriptions in the foregoing embodiments of the early warning method based on nursing needs.

[0193] Optionally, the memory 504 can be either standalone or integrated with the processor 503.

[0194] When the memory 504 is set up independently, the electronic device also includes a bus for connecting the memory 504 and the processor 503.

[0195] The implementation principle and technical effects of the electronic device provided in this embodiment can be found in the foregoing embodiments, and will not be repeated here.

[0196] This application also provides a computer-readable storage medium storing a computer-executable program, which, when executed by a processor, implements the method of any of the foregoing embodiments.

[0197] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the method of any of the foregoing embodiments.

[0198] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed.

[0199] The integrated modules described above, implemented as software functional modules, can be stored in a computer-readable storage medium. These software functional modules, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods of the various embodiments of this application.

[0200] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the application can be directly manifested as being executed by a hardware processor, or executed by a combination of hardware and software modules within the processor. The memory may include high-speed RAM, and may also include non-volatile memory (NVM), such as at least one disk storage device, and may also be a USB flash drive, external hard drive, read-only memory, disk, or optical disc, etc.

[0201] The aforementioned storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0202] An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Alternatively, the storage medium can be an integral part of the processor. Both the processor and the storage medium can reside in application-specific integrated circuits (ASICs). Alternatively, the processor and storage medium can exist as discrete components in an electronic device or host device.

[0203] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0204] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0205] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods of the various embodiments of this application.

[0206] The above are merely preferred embodiments of this application. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for early warning based on nursing needs, characterized in that, The method includes: The target user's physiological characteristic data is detected by millimeter-wave radar, and the target user's first temperature and humidity data and posture data are detected by auxiliary sensor modules. Based on the physiological characteristic data, the first temperature and humidity data, and the posture data, the nursing needs of the target user are predicted by a nursing prediction model. If the nursing need value exceeds a preset threshold, an early warning message is generated and sent to at least one terminal device.

2. The method according to claim 1, characterized in that, The step of predicting the nursing needs of the target user based on the physiological characteristic data, the first temperature and humidity data, and the posture data using a nursing prediction model includes: Feature extraction is performed on the physiological characteristic data to obtain the temporal characteristics of the target user, and the temporal characteristics include at least one of respiratory rate change rate, peak body movement amplitude, and intestinal peristalsis cycle; Feature extraction is performed on the first temperature and humidity data and the posture data to obtain the body position features and temperature and humidity features of the target user; Based on the time-series features, the body position features, and the temperature and humidity features, the nursing prediction model predicts the nursing needs of the target user.

3. The method according to claim 2, characterized in that, The method further includes: Acquire historical physiological characteristic data, historical temperature and humidity data, and historical posture data of historical users; Feature extraction was performed on the historical physiological data to obtain the rate of change of respiratory rate, peak body movement amplitude, and intestinal peristalsis cycle of the historical user. Feature extraction is performed on the historical temperature and humidity data and the historical posture data to obtain the body position characteristics and temperature and humidity characteristics of the historical user. The deep learning model is trained based on the respiratory rate change rate, the peak amplitude of body movement, the intestinal peristalsis cycle, the body position characteristics, and the temperature and humidity characteristics to obtain the nursing prediction model.

4. The method according to claim 1, characterized in that, The method further includes: Based on the nursing needs value and the preset threshold, the target early warning strategy for the early warning information is determined; Sending the warning information to at least one terminal device includes: According to the target early warning strategy, the early warning information is sent to at least one terminal device.

5. The method according to claim 2, characterized in that, The preset thresholds include a first preset threshold, a second preset threshold, and a third preset threshold; the step of determining the target early warning strategy for the early warning information based on the nursing need value and the preset thresholds includes: If the nursing need value is greater than the first preset threshold and less than the second preset threshold, the target early warning strategy is determined to be a level one early warning strategy. If the nursing need value is greater than the second preset threshold and less than the third preset threshold, the target early warning strategy is determined to be a level two early warning strategy. If the nursing need value is greater than the third preset threshold, the target early warning strategy is determined to be a level three early warning strategy. Wherein, the first preset threshold is less than the second preset threshold, the second preset threshold is less than the third preset threshold; the warning intensity of the first-level warning strategy is less than that of the second-level warning strategy, and the warning intensity of the second-level warning strategy is less than that of the third-level warning strategy.

6. The method according to claim 1, characterized in that, The step of predicting the nursing needs of the target user based on the physiological characteristic data, the first temperature and humidity data, and the posture data using a nursing prediction model includes: Obtain the historical first temperature and humidity data of the historical user and the historical second temperature and humidity data of the environment where the historical user is located; A mapping relationship between the first historical temperature and humidity data and the second historical temperature and humidity data is established based on a support vector regression model. Obtain the second temperature and humidity data of the environment where the target user is located; Based on the mapping relationship and the second temperature and humidity data, the first temperature and humidity data is corrected to obtain temperature and humidity corrected data. Based on the physiological characteristic data, the temperature and humidity correction data, and the posture data, the nursing needs of the target user are predicted using a nursing prediction model.

7. A smart wearable product, characterized in that, include: The smart wearable product itself, sensor module, and communication module; The sensor module includes a millimeter-wave radar sensor and an auxiliary sensor module. The millimeter-wave radar sensor is used to detect the physiological characteristics of the target user. The auxiliary sensor module includes a flexible pressure sensor and a temperature and humidity sensor. The flexible pressure sensor is attached to the surface of the smart wearable product body and is used to detect changes in the body position of the target user. The temperature and humidity sensor is attached to the smart wearable product body and is used to detect the temperature and humidity information of the smart wearable product. The communication module is used to send the generated early warning information to at least one terminal device; The smart wearable product is used to predict the care needs of the target user using the method described in any one of claims 1-6, generate the warning information, and send the warning information to the at least one terminal device.

8. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the method of any one of claims 1 to 6 through the computer program.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the method of any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images