Wearable health monitoring device, control method thereof and weight change prediction method

Abstract

The invention discloses a wearable health monitoring device, a control method thereof and a weight change prediction method, and belongs to the technical field of wearable equipment and health monitoring. The wearable health monitoring device comprises a main body, at least five supporting legs, a control module, a data acquisition module and a heating module, an attaching layer is arranged on the side, close to the skin, of the body, the attaching layer is made of a temperature-sensitive material with the viscosity changing along with the temperature, and the control module is used for controlling the heating module to work and adjusting the temperature of the attaching layer, so that the viscosity is adjusted. According to the wearable health monitoring device, dynamic viscosity adjustment can be achieved, wearing stability and comfort are both considered, the problem of skin sensitivity caused by long-term use of a traditional gel patch is avoided, collaborative analysis can be conducted on multi-dimensional physiological data such as the skin moisture content and the body fat layer thickness, and the weight change can be accurately speculated.

Description

Technical Field

[0001] The present invention relates to the technical field of wearable devices and health monitoring, and in particular to a wearable health monitoring device, a control method thereof, and a weight change prediction method. Background Art

[0002] With the rapid development of smart health devices, wearable technology has been widely used to monitor physiological parameters such as heart rate, blood oxygen levels, and step count in real time, providing users with health warnings and personalized recommendations. However, existing devices have significant shortcomings in the following areas: Single-dimensional monitoring: Most devices focus on a single parameter (such as heart rate or step count) and lack collaborative analysis of multi-dimensional physiological data such as skin moisture content and body fat thickness, making it difficult to infer weight trends through data correlation; Lack of intelligent adhesive materials: The adhesive layers of existing devices (such as medical gel patches) are sticky and fixed. Long-term wear can easily lead to a loss of fit due to sweat or skin activity, affecting monitoring accuracy, and forced removal can cause skin discomfort; Sensor technology limitations: Traditional weight monitoring relies on bioimpedance measurement, which is susceptible to interference from ambient humidity and electrode contact status. Moisture detection often uses offline instruments, making continuous monitoring in wearable settings impossible. Therefore, there is an urgent need for a new wearable device that can achieve high-precision, non-invasive, and comfortable long-term weight monitoring through the synergy of multiple sensors combined with intelligent adhesive technology. Summary of the Invention

[0003] The purpose of the present invention is to overcome the shortcomings of the prior art and provide a wearable health monitoring device, a control method thereof, and a weight change prediction method. The wearable health monitoring device can achieve high-precision, non-invasive and comfortable long-term weight change monitoring through the synergy of multiple sensors combined with intelligent bonding technology.

[0004] To achieve the above object, the present invention is implemented by adopting the following technical solutions:

[0005] In a first aspect, the present invention provides a wearable health monitoring device comprising: a main body, at least five legs, a control module, a data acquisition module, and a heating module;

[0006] The support leg is hinged to the side of the main body, and the main body and the support leg form a centrally symmetrical structure. An attachment layer is provided on the side of the main body close to the skin, and the material of the attachment layer is a temperature-sensitive material whose viscosity changes with temperature. The control module is provided on the main body, and the heating module is provided in the attachment layer; the data acquisition module is used to collect skin moisture content, body fat layer thickness, device movement state and tilt angle data and attachment layer temperature, and the control module is used to control the operation of the heating module, adjust the temperature of the attachment layer, thereby adjusting the viscosity, and control the angle between the support leg and the main body, as well as predict weight changes.

[0007] Furthermore, the data acquisition module includes a moisture sensor, a near infrared sensor, a six-dimensional inertial sensor and a temperature sensor;

[0008] The moisture sensor is used to detect the moisture content of the skin, the near-infrared sensor is used to detect the thickness of the body fat layer, the six-dimensional inertial sensor is used to collect six-dimensional motion time series data, and the six-dimensional motion time series data includes three-axis acceleration, three-axis angular velocity and device tilt angle; the temperature sensor is used to detect the temperature of the attachment layer.

[0009] Furthermore, the moisture sensor is a capacitive sensor, the control module includes a main control chip, the moisture sensor is connected to the main control chip through conductive nano-silver wire, and the conductive nano-silver wire is embedded in the support leg through an in-situ 3D printing process.

[0010] Furthermore, the near-infrared sensor includes an infrared light source with a wavelength of 920nm-960nm and a photodetector, wherein the infrared light source is used to emit infrared rays, and the photodetector is used to receive infrared rays.

[0011] Furthermore, the temperature-sensitive material is a thermoresponsive polymer, and the viscosity of the thermoresponsive polymer is 1.2-1.8 N / cm² at a temperature of 23°C-27°C; and the viscosity is 0.2-0.5 N / cm² at a temperature of 28°C-32°C.

[0012] Furthermore, it also includes a communication module connected to the data acquisition module for transmitting skin moisture content and body fat layer thickness to the outside.

[0013] Furthermore, the shell adopts a carbon fiber reinforced polyamide composite material, including a polyamide matrix with a mass fraction of 60%-70% and a chopped carbon fiber with a mass fraction of 30%-40%. The carbon fiber reinforced polyamide composite material has a tensile strength of ≥120MPa, a flexural modulus of ≥5GPa, and a density of ≤1.4g / cm³.

[0014] In a second aspect, the present invention provides a method for predicting weight change, which is implemented based on the wearable health monitoring device, comprising:

[0015] Collect multimodal data, including skin moisture content time series data, body fat layer thickness time series data, and six-dimensional motion time series data;

[0016] Perform time alignment, dynamic window segmentation and noise suppression preprocessing on multimodal data to obtain preprocessed data;

[0017] The pre-processed data is input into the spatiotemporal fusion prediction model, and the spatiotemporal fusion prediction model performs weighted fusion and nonlinear mapping on the pre-processed data to generate a sequence of predicted values of weight changes in the future time period;

[0018] Based on the predicted value sequence, a continuous and smooth weight change curve is generated using a cubic spline interpolation method.

[0019] Furthermore, the spatiotemporal fusion prediction model includes a temporal attention layer, a spatial convolution layer, and a motion gating unit;

[0020] The temporal attention layer is used to capture temporal dependencies;

[0021] The spatial convolution layer is used to fuse multimodal spatial features;

[0022] The motion gating unit is used to calculate the acceleration vector based on the six-dimensional motion time series data, thereby quantifying the real-time motion intensity.

[0023] In a third aspect, the present invention provides a control method for the wearable health monitoring device as described above, comprising:

[0024] The device displacement and the temperature of the attachment layer are obtained in real time. When the device displacement is ≥0.5mm, the heating module is controlled to heat until the temperature of the attachment layer reaches 30°C.

[0025] Adjust the position of the wearable health monitoring device. When the device displacement is ≤0.2mm, keep it stationary and control the heating module to stop working until the temperature of the attachment layer drops to 25°C.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] The wearable health monitoring device provided by the present invention provides an attachment layer made of a temperature-sensitive material whose viscosity changes with temperature. A control module controls the operation of a heating module to adjust the temperature of the attachment layer, thereby adjusting the viscosity. This can achieve dynamic viscosity adjustment, taking into account both wearing stability and comfort, and avoiding the skin sensitivity problems caused by long-term use of traditional gel patches.

[0028] The wearable health monitoring device provided by the present invention, by installing a moisture sensor and a near-infrared sensor, accurately infers weight changes through a deep learning model. It can collaboratively analyze multi-dimensional physiological data such as skin moisture content and body fat layer thickness, and has fewer limitations than the traditional bioimpedance method.

[0029] The wearable health monitoring device provided by the present invention adopts a lightweight shell and can achieve high-precision, non-invasive and comfortable long-term weight change monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 Schematic diagram of the exploded structure of the wearable health monitoring device provided by an embodiment of the present invention;

[0031] Figure 2is a side view schematic diagram of the wearable health monitoring device provided by an embodiment of the present invention;

[0032] Figure 3 is a schematic cross-sectional structural diagram of a wearable health monitoring device provided by an embodiment of the present invention;

[0033] Figure 4 is a schematic cross-sectional structural diagram of a wearable health monitoring device in working state provided by an embodiment of the present invention;

[0034] Figure 5 is a flow chart of a control method for a wearable health monitoring device provided by an embodiment of the present invention;

[0035] Figure 6 1 is a flow chart of a weight change prediction method provided by an embodiment of the present invention.

[0036] In the figure: 1. Touch screen; 2. Upper shell; 3. Moisture sensor; 4. Near-infrared sensor; 5. Bottom shell; 6. Adhesion layer; 7. Charging port; 8. Main control chip; 9. Acceleration sensor; 10. Circuit board; 11. Rotation pair; 12. Support foot. DETAILED DESCRIPTION

[0037] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and are not intended to limit the scope of protection of the present invention.

[0038] Example 1

[0039] This embodiment provides a wearable health monitoring device, such as Figure 1 As shown, it includes: a main body, at least five legs 12, a control module, a data acquisition module and a heating module;

[0040] The support leg 12 is hinged to the side of the main body through a rotating pair 11, and the main body and the support leg 12 form a centrally symmetrical structure. An attachment layer 6 is provided on the side of the main body close to the skin. The material of the attachment layer 6 is a temperature-sensitive material whose viscosity changes with temperature when the support leg 12 is hinged to the side of the main body. The control module is provided on the main body, and the heating module is provided in the attachment layer 6; the control module is used to control the operation of the heating module, adjust the temperature of the attachment layer 6, thereby adjusting the viscosity, and control the angle between the support leg 12 and the main body, as well as predict weight changes; the data acquisition module is used to collect skin moisture content, body fat layer thickness, device displacement and attachment layer 6 temperature.

[0041] The data acquisition module includes a moisture sensor 3, a near-infrared sensor 4, a six-dimensional inertial sensor 9 and a temperature sensor; the moisture sensor 3 is embedded in the support foot 12, and adopts capacitive electrode technology to measure the moisture content in real time by detecting the change of the capacitance value on the skin surface, with a sensitivity of ±0.2%, and can respond to a moisture fluctuation of 0.5%; the near-infrared sensor 4 is integrated at the end of the support foot 12, and includes a 940nm wavelength infrared light source and a high-precision photodetector. Based on the absorption characteristics of fat tissue for near-infrared light, the thickness of the body fat layer is inferred by the attenuation rate of the reflected light intensity, and the detection error is less than 0.05mm; the six-dimensional inertial sensor 9 obtains the six-dimensional motion timing data of the device in real time, and the six-dimensional motion timing data includes three-axis acceleration, three-axis angular velocity and device tilt angle, and transmits it to the control module. The control module adjusts the angle between the support foot and the main body by controlling the rotating pair 11, and at the same time adjusts the contact pressure of each sensor to ensure that the moisture sensor and the near-infrared sensor are always in close contact with the skin to avoid data distortion. Figure 4 Schematic diagram of the cross-sectional structure of the wearable health monitoring device in working state.

[0042] The wearable health monitoring device provided in this embodiment includes an upper shell 2 and a bottom shell 5, both made of a 3D-printed carbon fiber-reinforced polyamide (CF / PA) composite material with excellent strength and flexibility. The CF / PA composite material, which comprises a polyamide matrix with a mass fraction of 60%-70% and chopped carbon fibers with a mass fraction of 30%-40%, is printed using a fused deposition modeling (FDM) process. It exhibits mechanical properties such as a tensile strength of 120 MPa or higher and a flexural modulus of 5 GPa or higher, while maintaining a lightweight density of 1.4 g / cm³ or lower, ensuring both wearing comfort and structural stability.

[0043] In this embodiment, the temperature-sensitive material is a poly(N-isopropylacrylamide)-polyethylene glycol (PNIPAM-PEG) copolymer with a phase transition temperature of 28-30°C. Its viscosity is 1.5 N / cm² (storage modulus G' = 15 kPa) at 25°C, decreasing to 0.3 N / cm² (G' = 3 kPa) at 30°C. The heating module utilizes a 0.1 mm diameter nickel-chromium alloy heating wire with a resistivity of 1.1 Ω / m. Heating power is controlled via pulse width modulation (PWM), achieving a temperature regulation accuracy of ±0.5°C. The heating module consists of nickel-chromium alloy heating wires (0.1 mm diameter) arranged in a serpentine pattern within the attachment layer, with a 2 mm spacing between the wires to ensure uniform temperature distribution. The attachment layer is covered with an insulating, thermally conductive silicone layer (0.5 mm thick) with a heat conduction efficiency of ≥85%. The heating module can operate continuously for ≥72 hours on a single charge, enabling long-term continuous monitoring. It also includes a communication module connected to the data acquisition module for transmitting skin moisture content and body fat layer thickness to the outside.

[0044] The upper shell 2 and the bottom shell 5 are integrally formed by a multi-nozzle 3D printing device, and the specific process is as follows:

[0045] (1) Printing carbon fiber reinforced polyamide matrix (nozzle temperature 275℃), with embedded bionic honeycomb structure (unit size 2mm×2mm), the density is reduced by 30% while the bending strength is ≥110MPa;

[0046] (2) Simultaneously print a nickel-chromium alloy heating circuit (melting point 1425°C) and use laser-assisted sintering technology to achieve interface bonding between the circuit and the substrate, with a resistivity error of ≤5%;

[0047] (3) Print insulating thermal conductive silicone (thermal conductivity ≥ 1.2W / m·K) on the outermost layer with a thickness of 0.5mm to cover the heating circuit.

[0048] After testing, the 3D printed bionic honeycomb structure shell is 41% lighter than the solid structure and has a 20% improvement in impact resistance; the edge peeling force of the gradient attachment layer is reduced by 35%, and the incidence of skin indentation caused by long-term wear is reduced by 60%.

[0049] like Figure 2 As shown, the wearable health monitoring device provided in this embodiment is equipped with a screen 1, through which the user can intuitively view health data such as water content, weight, and body fat. The screen provides real-time monitoring results and also allows the user to set the monitoring mode, adjust the sensitivity, or view historical data.

[0050] like Figure 3 As shown, the control module includes a circuit board 10 and a main control chip 8. The main control chip 8 is integrated on the circuit board 10 and controls the temperature to optimize the bonding state. The main control chip 8 has a built-in spatiotemporal fusion prediction model (STF-Net), which can receive data detected by the moisture sensor 3, the near-infrared sensor 4 and the six-dimensional inertial sensor 9, perform real-time fusion analysis and output weight changes, wherein the moisture sensor is connected to the main control chip via a conductive nanosilver wire (diameter 50-100nm), and the conductive circuit is embedded in the support leg 12 through an in-situ 3D printing process.

[0051] The wearable health monitoring device provided in this embodiment further includes a charging interface 7 for charging the device and transmitting data.

[0052] Example 2

[0053] This embodiment provides a weight change prediction method, which is implemented based on the wearable health monitoring device provided in Example 1. Figure 6 Shown, including:

[0054] Collect multimodal data, including skin moisture content time series data, body fat layer thickness time series data, and six-dimensional motion time series data;

[0055] Perform time alignment, dynamic window segmentation and noise suppression preprocessing on multimodal data to obtain preprocessed data;

[0056] The preprocessed data was input into a spatiotemporal fusion prediction model, which performed weighted fusion and nonlinear mapping on the temporal features to generate a sequence of predicted values for weight changes in the future time period (with a step length of 5 minutes). Based on the predicted value sequence, a continuous and smooth weight change curve was generated using the cubic spline interpolation method.

[0057] The spatiotemporal fusion prediction model includes a temporal attention layer, a spatial convolution layer, and a motion gating unit;

[0058] The temporal attention layer is used to capture temporal dependencies;

[0059] The spatial convolution layer is used to fuse multimodal spatial features;

[0060] The real-time motion intensity data is calculated from the raw acceleration data collected by the six-dimensional inertial sensor, specifically the root mean square (RMS) value of acceleration within a sliding window (window length 1 second), which is used to characterize the user's motion intensity level.

[0061] In this embodiment, the main control chip 8 has a built-in spatiotemporal fusion prediction model (STF-Net), whose network architecture includes:

[0062] Input layer: receives water time series data (100 dimensions), body fat time series data (100 dimensions), and six-dimensional motion time series data (6×100 matrix);

[0063] Spatiotemporal encoding module: It uses an 8-head self-attention mechanism to extract temporal dependencies and fuses multimodal spatial features through a 3D convolution kernel (size 3×3×3, number of channels 64);

[0064] Dynamic compensation module: Dynamically adjusts feature weights according to the motion intensity index. The calculation formula is W=σ(MLP(S))W=σ(MLP(S)), where S is the real-time motion intensity;

[0065] Output layer: The weight change curve for the next hour is predicted using a gated recurrent unit (GRU, 128 hidden nodes), with a step length of 5 minutes and an output range of ±0.5 kg.

[0066] The model training method includes the following steps:

[0067] (1) Data augmentation: Gaussian noise (σ = 0.5%) and random time offset (± 2 seconds) were added to the water and body fat data;

[0068] (2) Two-stage training: pre-training on a static dataset (N=5000), and then fine-tuning on dynamic scene data (N=5000);

[0069] (3) Joint loss optimization: We use weighted mean square error (WMSE) and temporal consistency constraint for joint training, with a weight coefficient of λ = 1 + 0.5S, an AdaMomentum optimizer, and a learning rate exponentially decaying from 0.001 to 0.0001.

[0070] Example 3

[0071] This embodiment provides a control method for the wearable health monitoring device provided in Example 1, such as Figure 5 As shown, 0.5mm is the preset upper limit of displacement and 0.2mm is the preset lower limit of displacement, including:

[0072] The device displacement and the temperature of the attachment layer are obtained in real time. When the device displacement is ≥0.5mm, the heating module is controlled to heat until the temperature of the attachment layer reaches 30°C.

[0073] Adjust the position of the wearable health monitoring device. When the device displacement is ≤0.2mm, keep it stationary and control the heating module to stop working until the temperature of the attachment layer drops to 25°C.

[0074] During actual operation, the main control chip 8 collects the device displacement in real time through the six-dimensional inertial sensor 9. When the device displacement is greater than 0.5mm, the PID control algorithm is started: the error is calculated, which is the difference between the set threshold value of the device displacement and the actual displacement, and the heating power P is adjusted; the heating module outputs the corresponding current to raise the temperature of the temperature-sensitive layer to 30°C (reduced viscosity), control and adjust the angle between the support leg and the main body, and when Δx ≤ 0.2mm, the temperature is lowered to 25°C to restore the viscosity, completing the position adjustment of the wearable health monitoring device.

[0075] In the description of the present invention, it should be understood that the terms "center," "longitudinal," "lateral," "upper," "lower," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer" and the like, indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are used only to explain the relative positional relationships and movement of components in a specific posture. If the specific posture changes, the directional indications will also change accordingly. These terms are intended solely to facilitate the description of the present invention and simplify the description, and are not intended to indicate or imply that the devices or components referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and the like are used for descriptive purposes only and should not be construed to indicate or imply relative importance or to implicitly specify the number of the technical features referred to. Therefore, features designated "first," "second," and the like may explicitly or implicitly include one or more of such features. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0076] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0077] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which are all protected by the present invention.

Claims

1. A wearable health monitoring device, characterized in that: include: Main body, at least five legs, control module, data acquisition module and heating module; The support leg is hinged to the side of the main body, and the main body and the support leg form a centrally symmetrical structure. An attachment layer is provided on the side of the main body close to the skin, and the material of the attachment layer is a temperature-sensitive material whose viscosity changes with temperature. The control module is provided on the main body, and the heating module is provided in the attachment layer; the data acquisition module is used to collect skin moisture content, body fat layer thickness, device movement state and tilt angle data and attachment layer temperature, and the control module is used to control the operation of the heating module, adjust the temperature of the attachment layer, thereby adjusting the viscosity, and control the angle between the support leg and the main body, as well as predict weight changes.

2. The wearable health monitoring device according to claim 1, wherein: The data acquisition module includes a moisture sensor, a near infrared sensor, a six-dimensional inertial sensor and a temperature sensor; The moisture sensor is used to detect the moisture content of the skin, the near-infrared sensor is used to detect the thickness of the body fat layer, the six-dimensional inertial sensor is used to collect six-dimensional motion time series data, and the six-dimensional motion time series data includes three-axis acceleration, three-axis angular velocity and device tilt angle; the temperature sensor is used to detect the temperature of the attachment layer.

3. The wearable health monitoring device according to claim 2, wherein: The moisture sensor is a capacitive sensor, the control module includes a main control chip, the moisture sensor is connected to the main control chip through conductive nano silver wire, and the conductive nano silver wire is embedded in the support leg through an in-situ 3D printing process.

4. The wearable health monitoring device according to claim 2, wherein: The near-infrared sensor includes an infrared light source with a wavelength of 920nm-960nm and a photodetector. The infrared light source is used to emit infrared rays, and the photodetector is used to receive infrared rays.

5. The wearable health monitoring device according to claim 1, wherein: The temperature-sensitive material is a thermoresponsive polymer, and the viscosity of the thermoresponsive polymer is 1.2-1.8 N / cm² at a temperature of 23°C-27°C; and the viscosity is 0.2-0.5 N / cm² at a temperature of 28°C-32°C.

6. The wearable health monitoring device according to claim 1, wherein: It also includes a communication module connected to the data acquisition module for transmitting skin moisture content and body fat layer thickness to the outside.

7. The wearable health monitoring device according to claim 1, wherein: The shell is made of carbon fiber reinforced polyamide composite material, including a polyamide matrix with a mass fraction of 60%-70% and chopped carbon fibers with a mass fraction of 30%-40%. The carbon fiber reinforced polyamide composite material has a tensile strength of ≥120 MPa, a flexural modulus of ≥5 GPa, and a density of ≤1.4 g / cm³.

8. A method for predicting weight change, implemented based on the wearable health monitoring device according to any one of claims 1 to 7, characterized in that: include: Collect multimodal data, including skin moisture content time series data, body fat layer thickness time series data, and six-dimensional motion time series data; Perform time alignment, dynamic window segmentation and noise suppression preprocessing on multimodal data to obtain preprocessed data; The pre-processed data is input into the spatiotemporal fusion prediction model, and the spatiotemporal fusion prediction model performs weighted fusion and nonlinear mapping on the pre-processed data to generate a sequence of predicted values of weight changes in the future time period; Based on the predicted value sequence, a continuous weight change curve is generated using a cubic spline interpolation method.

9. The method for predicting weight change according to claim 1, wherein: The spatiotemporal fusion prediction model includes a temporal attention layer, a spatial convolution layer, and a motion gating unit; The temporal attention layer is used to capture temporal dependencies; The spatial convolution layer is used to fuse multimodal spatial features; The motion gating unit is used to calculate the acceleration vector based on the six-dimensional motion time series data, thereby quantifying the real-time motion intensity.

10. A control method for a wearable health monitoring device according to claims 1-7, characterized in that: include: Acquire the device displacement and the temperature of the attachment layer in real time, and when the device displacement is greater than or equal to a preset displacement upper limit, control the heating module to heat until the temperature of the attachment layer reaches a first temperature value; Adjusting the position of the wearable health monitoring device, and when the displacement of the device is less than or equal to a preset lower displacement limit, keeping the device stationary, and controlling the heating module to stop working until the temperature of the attachment layer drops to a second temperature value; The viscosity of the temperature-sensitive material at the first temperature value is lower than the viscosity at the second temperature value.

Images