MATTRESS ADJUSTMENT DEVICE AND METHOD BASED ON SPINAL CURVATURE

Abstract

The application discloses a mattress adjustment device based on spinal curvature, including: a flexible sensor module integrated into the surface of a mattress and configured to collect a physiological data from a user, wherein the flexible sensor module includes multiple flexible resistive or piezoelectric sensors; a control module electrically connected to the flexible sensor module, and configured to receive and process the physiological data to generate an adjustment instruction, wherein the control module includes an embedded microprocessor, which includes a depth neural network model and a feedback loop unit; a multi-segment adjustment module including multiple independent adjustment units distributed in different areas inside the mattress, each of which is connected to the control module and is capable of independently adjusting the height or softness of different areas of the mattress based on the adjustment instruction.

Description

TECHNICAL FIELD

The present disclosure relates to a technical field of intelligent mattress adjustment, and more particularly to a mattress adjustment device based on spinal curvature.

BACKGROUND

In recent years, with the development of sensor technology, artificial intelligence and material science, the field of smart mattresses has made significant progress, and the main functions of the smart mattresses on the market at present are focused on adjusting the softness and hardness, temperature control and simple posture monitoring, etc., but these technological means are often unable to meet the personalized spine health needs. The physiological curvature of the human spine varies according to age, gender, body type and sleeping posture, especially during long sleep, because the mattress cannot dynamically adapt to the natural curve of the spine, which may lead to localized spinal pressure, muscle tension or impeded blood circulation. This situation not only affects the user's sleep quality, but may also exacerbate the risk of cervical spondylosis, lumbar disc herniation and other spine-related diseases in long-term use.

In addition, the traditional mattress adjustment method mainly relies on the user's subjective experience to make manual adjustments, such as softness and hardness adjustments and angle adjustments, and lacks the ability of precise, physiological feedback-based intelligent optimization. This type of adjustment is difficult to optimize for the real-time state of the user's spine, which is especially insufficient for users with special needs (e.g., patients with spinal diseases or people in need of rehabilitation).

Therefore, the development of a mattress adjustment device that can automatically sense and continuously respond to changes in the physiological curvature of the user's spine with an intelligent adjustment mechanism by combining real-time data feedback has become an urgent problem to be solved.

SUMMARY

The present disclosure is described in the following sections by various embodiments. However, it should be understood that the disclosure can be implemented in various forms and is not limited to the specific embodiment provided herein.

A first aspect of the present application proposes a mattress adjustment device based on spinal curvature, comprising:

• • a flexible sensor module integrated into the surface of a mattress and configured to collect a physiological data from a user, the physiological data comprises a spinal curvature, a pressure distribution, and a user position information, wherein the flexible sensor module comprises multiple flexible resistive or piezoelectric sensors;
  • a control module electrically connected to the flexible sensor module, and configured to receive and process the physiological data to generate an adjustment instruction, wherein the control module comprises an embedded microprocessor, which comprises a depth neural network model and a feedback loop unit;
  • a multi-segment adjustment module comprising multiple independent adjustment units distributed in different areas inside the mattress, each of which is connected to the control module and is capable of independently adjusting the height or softness of different areas of the mattress based on the adjustment instruction;
  • wherein the deep neural network model is configured to acquire the physiological data and generate the adjustment instruction based on a preset spinal curvature model; the feedback loop unit is configured to adjust the weights of the deep neural network model based on the long and short-term memory network.

Further, the flexible resistive or piezoelectric sensors are arranged in an array on the surface of the mattress and are connected to the control module through a signal amplifier and an analog-to-digital converter.

Further, the deep neural network model acquires the physiological data and generate the adjustment instruction based on the preset spinal curvature model, comprising:

• • acquiring the physiological data collected by the flexible sensor module and pre-processed by the signal amplifier and the analog-to-digital converter;
  • performing feature extraction to obtain a spinal curvature feature, comparing the spinal curvature feature with the preset spinal curvature model, and obtaining a spinal curvature deviation value;
  • calculating the height or softness adjustment value of each different area of the mattress based on the spinal curvature deviation value through a feedback control error algorithm;
  • generating the adjustment instruction by combining the height or softness adjustment value of each different area of the mattress.

Further, after the multi-segment adjustment module adjusts the height or softness of different areas of the mattress based on the adjustment instruction, the deep neural network model again performs feature extraction on the updated physiological data to obtain the spinal curvature feature of each mattress area, and compares it with the target spinal curvature of the corresponding mattress area in the preset physiological model to obtain an adjustment error;

• • if the adjustment error exceeds a threshold value, the deep neural network model regenerates the adjustment instruction.

Further, the feedback control error algorithm uses a PID controller.

Further, the control module comprising a personalization unit configured to be capable of adjusting the height or softness of the mattress based on a personalization parameter entered by the user, or generating the adjustment instruction based on a user-defined adjustment algorithm.

Further, the multi-segment adjustment module comprises a pneumatic system, or a hydraulic driving system, or an electric lifting system; each adjustment unit comprises an independent motor or air pump for adjusting the height or softness of the mattress;

• • wherein the pneumatic system comprises a plurality of electric airbags, a control master valve, and a plurality of airbag control valves, which is used in conjunction with the adjustment units comprising the air pump.

Further, the multi-segment adjustment module adopts multi layers acoustic material and a vibration-damping structure to minimize noise and vibration during the adjustment process.

Further, the mattress adjustment device based on spinal curvature further comprises a wireless communication module configured to transmit the physiological data and an adjustment result to an external device, to present a current spinal curvature status and a real-time adjustment data to the user, the user can realize remote monitoring and provide a feedback information, and the wireless communication module transmits the user feedback information to the control module.

A second aspect of the present application proposes a mattress adjustment method based on spinal curvature, the method is based on the mattress adjustment device, and comprise:

• • collecting a physiological data of a user, comprising a spinal curvature, a pressure distribution, and a user position information, through a flexible sensor module integrated into the surface of a mattress, wherein the flexible sensor module comprises multiple flexible resistive or piezoelectric sensors;
  • receiving and processing the physiological data to generate an adjustment instruction, through a control module electrically connected to the flexible sensor module, wherein the control module comprises an embedded microprocessor, which comprises a depth neural network model and a feedback loop unit;
  • independently adjusting the height or softness of different areas of the mattress based on the adjustment instruction through a multi-segment adjustment module comprising multiple independent adjustment units distributed in different areas inside the mattress, each of which is connected to the control module;
  • wherein the deep neural network model is configured to acquire the physiological data and generate the adjustment instruction based on a preset spinal curvature model; the feedback loop unit is configured to adjust the weights of the deep neural network model based on the long and short-term memory network.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly explain the technical solutions in the present disclosure or the prior art, drawings required in the embodiments or the prior art will be briefly described below. Obviously, the drawings in the following description are some embodiments of the present disclosure. For those skilled in the art, other drawings may be obtained from these drawings without any creative effort.

FIG. 1 shows a schematic diagram of an overall device structure of a mattress adjustment device based on spinal curvature provided by the present application;

FIG. 2 shows a schematic diagram of a sectional view of a multi-segment adjustment module of a mattress adjustment device based on spinal curvature provided in the present application.

DETAILED DESCRIPTION OF THE EMBODIMENTS

The present application proposes a mattress adjustment device and method based on spinal curvature, and in order to describe the present application more specifically, the technical solutions of the present application are described in detail below in connection with the accompanying drawings and specific embodiments, and it should be understood that the specific embodiments described herein are only for explaining the present application, and are not intended to limit the present application. Based on the embodiments in this application, all other embodiments obtained by a person of ordinary skill in the art without making creative labor fall within the scope of protection of this application.

A first aspect of the present application proposes a mattress adjustment device based on spinal curvature, the overall structure of which is shown schematically in FIG. 1, and specifically comprising:

• • a flexible sensor module integrated into the surface of a mattress and configured to collect a physiological data from a user, the physiological data comprises a spinal curvature, a pressure distribution, and a user position information, wherein the flexible sensor module comprises multiple flexible resistive or piezoelectric sensors;
  • wherein, by embedding the flexible sensor module as a whole into the surface of the mattress, the stability of the sensor in contact with the user is ensured, and the measurement accuracy is improved; flexible materials usually have excellent mechanical flexibility, stretchability and durability, and by adopting flexible sensors made of flexible materials, the flexible sensor module is able to adapt to the deformation of the surface of the mattress and the movement of the user's body, so as to achieve the effect of tightly adhering to the user's back and spine. The effect of the flexible sensor module is to adapt to the deformation of the mattress surface and the movement of the user's body, so as to closely fit the user's back and spine, and better collect the user's physiological data;
  • wherein the spinal curvature is used to help assess whether the user's posture is in accordance with ergonomic standards, preventing spinal problems caused by poor sleeping posture; the pressure distribution is used to detect the pressure distribution of the user's body in contact with the surface of the mattress, identify the size of the pressure borne by different parts of the body, and determine whether it is necessary to adjust the hardness or support of the mattress in order to improve the sleeping experience; the user position information is used to allow the flexible sensor to detect the user's position in the mattress through the change in the pressure of the contact point area changes to detect the specific location of the user on the mattress and changes in body position, which can monitor in real time whether the user is in a normal sleep position and provide safety reminders, such as preventing the elderly or children from accidentally falling;
  • wherein the flexible resistive sensor measures physiological data based on changes in resistance caused by changes in pressure, and when pressure is applied to the flexible resistive material, its electrical conductivity changes, which in turn changes the resistance value, and this change corresponds to the pressure value. The selection of flexible resistive sensors has the advantages of low cost, easy integration and suitable for large area applications;
  • wherein the flexible piezoelectric sensor measures physiological data based on the piezoelectric effect, when the user's body applies pressure or deformation effect, under mechanical stress, the flexible piezoelectric material generates an electrical signal, this signal corresponds to the pressure value, and the selected flexible piezoelectric sensor has the advantage of high sensitivity, which is particularly suitable for capturing dynamic pressure changes;

Further, the user may adopt a combination of the two types of sensors to form a dense detection network to realize comprehensive monitoring of the entire mattress.

In one embodiment, the flexible resistive or piezoelectric sensors are arranged in an array on the surface of the mattress and are connected to the control module through a signal amplifier and an analog-to-digital converter;

• • wherein the signal amplifier is used to enhance the strength of the electrical signal output from the sensor for subsequent processing and analysis. For example, the signal generated by a flexible resistive sensor may be weak and needs to be boosted by the amplifier to a usable voltage or current range, and the charge signal generated by a flexible piezoelectric sensor also needs to be enhanced by the amplifier to reduce signal attenuation or interference;
  • wherein the analog-to-digital converter is used to convert the analog signal output from the sensor, such as continuously changing voltage or current, into a digital signal for easy processing and storage by the control module, wherein the higher the resolution of the analog-to-digital converter, the more delicate the sampling data is, and the more accurately it can reflect changes in pressure and position, and wherein the sampling rate of the analog-to-digital converter determines the frequency of signal updating, which is required to satisfy the needs of real-time monitoring.

In one embodiment, the flexible resistive or piezoelectric sensors can adjust their own sensitivity to changes in the user's weight and body size;

• • wherein by adjusting the sensitivity of the flexible sensor module, it can be adapted to the changes in weight and body size of different users to achieve more accurate spinal curvature monitoring. Specifically, for light weight users, the sensitivity needs to be increased to detect subtle pressure changes; for heavy weight users, the sensitivity needs to be decreased to avoid signal saturation or distortion; for uniform pressure distribution, the sensitivity needs to be low; and for localized pressure application, the sensitivity needs to be increased to capture pressure changes in small areas.
  • a control module electrically connected to the flexible sensor module, and configured to receive and process the physiological data to generate an adjustment instruction, wherein the control module comprises an embedded microprocessor, which comprises a depth neural network model and a feedback loop unit;
  • wherein the embedded microprocessor is compact and easy to integrate with the flexible sensor module, which is suitable for space-constrained scenarios, such as inside the mattress of the present application. The embedded microprocessor is typically designed for low power consumption.

In one embodiment, the deep neural network model acquires the physiological data and generate the adjustment instruction based on the preset spinal curvature model, comprising:

• • acquiring the physiological data collected by the flexible sensor module and pre-processed by the signal amplifier and the analog-to-digital converter;
  • performing feature extraction to obtain a spinal curvature feature, comparing the spinal curvature feature with the preset spinal curvature model, and obtaining a spinal curvature deviation value;
  • calculating the height or softness adjustment value of each different area of the mattress based on the spinal curvature deviation value through a feedback control error algorithm;
  • generating the adjustment instruction by combining the height or softness adjustment value of each different area of the mattress;

In one embodiment, the feedback control error algorithm uses a PID (Proportion Integration Differentiation) controller. Alternatively, the feedback control error algorithm may also include a back-propagation algorithm or a gradient descent method for reducing the error from a preset value.

Wherein the PID controller includes a proportional unit (P), an integral unit (I) and a differential unit (D), the proportional unit (P) can make a quick response to the error and reduce the response time of the device, when the user changes the posture or the curvature of the spine changes, so that the PID controller can quickly adjust the height or softness of the mattress to provide instant support; the integral unit (I) can eliminate the device's steady state error to ensure that the device finally reaches the target value, when there is a small error due to small fluctuations in the pneumatic or hydraulic system, so that the PID controller can be gradually corrected to ensure that the mattress finally reaches the ideal state of support; differential unit (D) can predict the trend of the change of the error, inhibit the device's oscillation and overshooting phenomenon.

In one embodiment, the deep neural network model is configured to acquire the physiological data and generate the adjustment instruction based on a preset spinal curvature model; the feedback loop unit is configured to adjust the weights of the deep neural network model based on the long and short-term memory network;

In one embodiment, after the multi-segment adjustment module adjusts the height or softness of different areas of the mattress based on the adjustment instruction, the deep neural network model again performs feature extraction on the updated physiological data to obtain the spinal curvature feature of each mattress area, and compares it with the target spinal curvature of the corresponding mattress area in the preset physiological model to obtain an adjustment error;

• • if the adjustment error exceeds a threshold value, the deep neural network model regenerates the adjustment instruction;

In one embodiment, the control module comprising a personalization unit configured to be capable of adjusting the height or softness of the mattress based on a personalization parameter entered by the user, or generating the adjustment instruction based on a user-defined adjustment algorithm;

• • a multi-segment adjustment module comprising multiple independent adjustment units distributed in different areas inside the mattress, each of which is connected to the control module and is capable of independently adjusting the height or softness of different areas of the mattress based on the adjustment instruction; the schematic diagram of a sectional view of a multi-segment adjustment module is shown in FIG. 2;

In one embodiment, the multi-segment adjustment module comprises a pneumatic system, or a hydraulic driving system, or an electric lifting system; each adjustment unit comprises an independent motor or air pump for adjusting the height or softness of the mattress;

• • wherein the pneumatic system comprises a plurality of electric airbags, a control master valve, and a plurality of airbag control valves, which is used in conjunction with the adjustment units comprising the air pump.

And hydraulic driving system or an electric lifting system is used in conjunction with the adjustment units comprising the motor.

Specifically, the electric airbag in the pneumatic system is used to directly adjust the height or softness of the mattress through expansion or contraction; the control master valve is used to regulate the airflow between the air pump and the electric airbag, to control the overall air pressure of the pneumatic system, to ensure the stable operation of the system; the airbag control valve is used to accurately regulate the air pressure of the individual electric airbags, which is used in conjunction with the control master valve, to realize the independent control of each airbag.

In one embodiment, the multi-segment adjustment module adopts multi layers acoustic material and a vibration-damping structure to minimize noise and vibration during the adjustment process

In one embodiment, the mattress adjustment device based on spinal curvature further comprises a wireless communication module configured to transmit the physiological data and an adjustment result to an external device, to present a current spinal curvature status and a real-time adjustment data to the user, the user can realize remote monitoring and provide a feedback information, and the wireless communication module transmits the user feedback information to the control module.

The second aspect of the present application proposes a mattress adjustment method based on spinal curvature, the method is based on the mattress adjustment device, and comprise:

• • collecting a physiological data of a user, comprising a spinal curvature, a pressure distribution, and a user position information, through a flexible sensor module integrated into the surface of a mattress, wherein the flexible sensor module comprises multiple flexible resistive or piezoelectric sensors;
  • receiving and processing the physiological data to generate an adjustment instruction, through a control module electrically connected to the flexible sensor module, wherein the control module comprises an embedded microprocessor, which comprises a depth neural network model and a feedback loop unit;
  • independently adjusting the height or softness of different areas of the mattress based on the adjustment instruction through a multi-segment adjustment module comprising multiple independent adjustment units distributed in different areas inside the mattress, each of which is connected to the control module;
  • wherein the deep neural network model is configured to acquire the physiological data and generate the adjustment instruction based on a preset spinal curvature model; the feedback loop unit is configured to adjust the weights of the deep neural network model based on the long and short-term memory network.

The foregoing is only a preferred embodiment of the present application, and is not intended to limit the present application, and the person skilled in the art should be able to realize that many examples can exist according to the basic method principles provided in the present application in combination with the actual situation, which should all be within the scope of protection of the present application without paying sufficient creative labor.

In the description of the present specification, reference is made to the terms “an embodiment”, “some embodiments”, “example”, “specific example”, or “a specific example”, “some examples”, “exemplary”, “specific examples”, or “some examples”, etc. are described to mean that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic expressions of the above terms are not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. Moreover, without contradicting each other, those skilled in the art may combine and combine different embodiments or examples and features of different embodiments or examples described herein.

It is also noted that in this specification, relational terms such as first and second are used only to distinguish one entity or operation from another, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Furthermore, the terms “including”, “comprising”, or any other variant thereof, are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus comprising a set of elements includes not only those elements, but also other elements not expressly listed, or other elements not expressly listed for the purpose of such a process, method, article, or apparatus. elements, or which are inherent to such process, method, article or equipment.

Claims

1. A mattress adjustment device based on spinal curvature, comprising:

a flexible sensor module integrated into the surface of a mattress and configured to collect a physiological data from a user, the physiological data comprises a spinal curvature, a pressure distribution, and a user position information, wherein the flexible sensor module comprises multiple flexible resistive or piezoelectric sensors;

a control module electrically connected to the flexible sensor module, and configured to receive and process the physiological data to generate an adjustment instruction, wherein the control module comprises an embedded microprocessor, which comprises a depth neural network model and a feedback loop unit;

a multi-segment adjustment module comprising multiple independent adjustment units distributed in different areas inside the mattress, each of which is connected to the control module and is capable of independently adjusting the height or softness of different areas of the mattress based on the adjustment instruction;

wherein the deep neural network model is configured to acquire the physiological data and generate the adjustment instruction based on a preset spinal curvature model; the feedback loop unit is configured to adjust the weights of the deep neural network model based on the long and short-term memory network.

2. The mattress adjustment device based on spinal curvature of claim 1, wherein the flexible resistive or piezoelectric sensors are arranged in an array on the surface of the mattress and are connected to the control module through a signal amplifier and an analog-to-digital converter.

3. The mattress adjustment device based on spinal curvature of claim 1, wherein the deep neural network model acquires the physiological data and generate the adjustment instruction based on the preset spinal curvature model, comprising:

acquiring the physiological data collected by the flexible sensor module and pre-processed by the signal amplifier and the analog-to-digital converter;

performing feature extraction to obtain a spinal curvature feature, comparing the spinal curvature feature with the preset spinal curvature model, and obtaining a spinal curvature deviation value;

calculating the height or softness adjustment value of each different area of the mattress based on the spinal curvature deviation value through a feedback control error algorithm;

generating the adjustment instruction by combining the height or softness adjustment value of each different area of the mattress.

4. The mattress adjustment device based on spinal curvature of claim 3, wherein after the multi-segment adjustment module adjusts the height or softness of different areas of the mattress based on the adjustment instruction, the deep neural network model again performs feature extraction on the updated physiological data to obtain the spinal curvature feature of each mattress area, and compares it with the target spinal curvature of the corresponding mattress area in the preset physiological model to obtain an adjustment error;

if the adjustment error exceeds a threshold value, the deep neural network model regenerates the adjustment instruction.

5. The mattress adjustment device based on spinal curvature of claim 3, wherein the feedback control error algorithm uses a PID controller.

6. The mattress adjustment device based on spinal curvature of claim 1, wherein the control module comprising a personalization unit configured to be capable of adjusting the height or softness of the mattress based on a personalization parameter entered by the user, or generating the adjustment instruction based on a user-defined adjustment algorithm.

7. The mattress adjustment device based on spinal curvature of claim 1, wherein the multi-segment adjustment module comprises a pneumatic system, or a hydraulic driving system, or an electric lifting system; each adjustment unit comprises an independent motor or air pump for adjusting the height or softness of the mattress;

wherein the pneumatic system comprises a plurality of electric airbags, a control master valve, and a plurality of airbag control valves, which is used in conjunction with the adjustment units comprising the air pump.

8. The mattress adjustment device based on spinal curvature of claim 1, wherein the multi-segment adjustment module adopts multi layers acoustic material and a vibration-damping structure to minimize noise and vibration during the adjustment process.

9. The mattress adjustment device based on spinal curvature of claim 1, wherein the mattress adjustment device based on spinal curvature further comprises a wireless communication module configured to transmit the physiological data and an adjustment result to an external device, to present a current spinal curvature status and a real-time adjustment data to the user, the user can realize remote monitoring and provide a feedback information, and the wireless communication module transmits the user feedback information to the control module.

10. A mattress adjustment method based on spinal curvature, the method is based on the mattress adjustment device of claim 1, and comprise:

collecting a physiological data of a user, comprising a spinal curvature, a pressure distribution, and a user position information, through a flexible sensor module integrated into the surface of a mattress, wherein the flexible sensor module comprises multiple flexible resistive or piezoelectric sensors;

receiving and processing the physiological data to generate an adjustment instruction, through a control module electrically connected to the flexible sensor module, wherein the control module comprises an embedded microprocessor, which comprises a depth neural network model and a feedback loop unit;

independently adjusting the height or softness of different areas of the mattress based on the adjustment instruction through a multi-segment adjustment module comprising multiple independent adjustment units distributed in different areas inside the mattress, each of which is connected to the control module;

wherein the deep neural network model is configured to acquire the physiological data and generate the adjustment instruction based on a preset spinal curvature model; the feedback loop unit is configured to adjust the weights of the deep neural network model based on the long and short-term memory network.