Intelligent adjusting method and system for self-adaptively adjusting pillow shape based on sleeping posture of user

Abstract

The invention discloses an intelligent adjusting method and system for self-adaptively adjusting a pillow type based on a sleeping posture of a user, belongs to the technical field of intelligent pillow type adjustment, and is used for solving the defects of the prior art in the aspects of support adaptability, adjustment accuracy, data monitoring dimension, interaction capability and the like of an intelligent pillow system. And better sleep experience cannot be provided for the user. The method comprises the following steps: acquiring a pressure distribution matrix of a head and physiological data of a user through a multi-mode perception sensor array; wherein the user physiological data at least comprises respiratory frequency information and cervical curvature information; analyzing the pressure distribution matrix and the physiological data of the user through the edge calculation chip, and identifying the current sleeping posture of the user; according to the current sleeping posture of the user and the cervical vertebra curvature information, adjusting parameters of the intelligent adjusting air bag pillow are determined; and according to the adjusting parameters, the intelligent air pump is controlled to adjust the height and rigidity of the to-be-adjusted air bag.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent pillow shape adjustment, and particularly to an intelligent adjustment method and system for adaptively adjusting the pillow shape based on the user's sleeping posture. Background Art

[0002] In the fields of smart home and health monitoring technologies, intelligent pillow systems, as important tools for improving sleep quality, have received extensive attention and research in recent years. However, there are still many deficiencies in the existing technologies in this field, which are specifically manifested in the following aspects:

[0003] Firstly, due to the limitation of the fixed shape of traditional memory foam or down pillows and other static support materials, they cannot effectively adapt to the dynamic change requirements of the cervical curvature of users in different sleeping postures (such as side lying, supine, etc.). This static support method often leads to the phenomenon of morning neck and shoulder stiffness after users sleep for a long time.

[0004] Secondly, although some existing intelligent pillows attempt to achieve the adjustment of the support force through the method of sectional inflation, most of these products rely on pressure sensors for feedback control. However, due to the accuracy limitation of the pressure sensors, the adjustment of the support force often has a lag phenomenon and cannot respond to the change of the user's sleeping posture in a timely manner.

[0005] Furthermore, there are also limitations in data monitoring for current intelligent pillows on the market. Most products can only monitor the number of times the user turns over. These products ignore the correlation between key physiological indicators such as respiratory rate and heart rate variability and the support quality, resulting in the inability to provide users with a comprehensive and accurate sleep quality assessment.

[0006] Finally, in terms of interaction ability, the sleep reports of existing intelligent pillows mostly stay at the basic statistical level and lack personalized improvement suggestions based on biomechanics. This makes it difficult for users to make targeted adjustments to their sleep habits according to the report content, thus limiting the potential of intelligent pillows in sleep health management.

[0007] In summary, the existing technologies have deficiencies in aspects such as the support adaptability, adjustment accuracy, data monitoring dimension, and interaction ability of intelligent pillow systems. Therefore, it is of great significance to develop an intelligent pillow system that can real-time sense the user's sleeping posture, physiological indicators, and pressure distribution, and achieve personalized spinal alignment and pressure relief by dynamically adjusting the three-dimensional shape and support stiffness of the airbag group for improving the user's sleep quality and constructing a closed-loop of sleep health management. Summary of the Invention

[0008] An embodiment of the present invention provides an intelligent adjustment method and system for adaptively adjusting the pillow shape based on the user's sleeping posture, which is used to solve the following technical problems: The existing technologies have deficiencies in aspects such as the support adaptability, adjustment accuracy, data monitoring dimensions, and interaction capabilities of the intelligent pillow system, and cannot provide a better sleep experience for users.

[0009] The embodiment of the present invention adopts the following technical solutions:

[0010] On the one hand, an embodiment of the present invention provides an intelligent adjustment method for adaptively adjusting the pillow shape based on the user's sleeping posture, which is applied to an intelligent adjustable airbag pillow. The intelligent adjustable airbag pillow at least includes: an edge computing chip, an intelligent air pump, a folding airbag array installed on the pillow base, and a multi-modal sensing sensor array installed on the surface of each folding airbag. The method includes:

[0011] Through the multi-modal sensing sensor array, obtain the pressure distribution matrix of the head and the user's physiological data; wherein, the user's physiological data at least includes respiration frequency information and cervical curvature information;

[0012] Through the edge computing chip, analyze the pressure distribution matrix and the user's physiological data to identify the user's current sleeping posture;

[0013] According to the user's current sleeping posture and the cervical curvature information, determine the adjustment parameters of the intelligent adjustable airbag pillow;

[0014] According to the adjustment parameters, control the intelligent air pump to adjust the height and stiffness of the airbag to be adjusted.

[0015] In a feasible implementation manner, the multi-modal sensing sensor at least includes an embedded fiber Bragg grating sensor, a micro radar chip, and a flexible strain sensor strip;

[0016] Through the multi-modal sensing sensor array, obtaining the pressure distribution matrix of the head and the user's physiological data specifically includes:

[0017] Based on a preset time interval, through the embedded fiber Bragg grating sensor, real-time monitor the pressure values at each folding airbag;

[0018] Form the pressure distribution matrix of the head according to the arrangement of the folding airbags with the pressure values;

[0019] Through the micro radar chip, monitor the respiration frequency information of the user; through the flexible strain sensor strip, sense the cervical curve of the user's contact part with the pillow, and extract the cervical curvature information according to the cervical curve.

[0020] In a feasible implementation manner, extracting the cervical curvature information according to the cervical curve specifically includes:

[0021] A three-dimensional coordinate system of the pillow is established with the center point of the intelligent adjustable airbag pillow as the origin, the long side direction of the pillow as the x-axis, the short side direction as the y-axis, and the direction perpendicular to the plane of the pillow as the z-axis;

[0022] Projecting the cervical vertebra curve sensed by the flexible strain sensor belt onto the XOY plane and the XOZ plane respectively to obtain a cervical vertebra top-view curve and a cervical vertebra side-view curve;

[0023] The first cervical vertebra curvature information is extracted from the cervical vertebra top-view curve, and the second cervical vertebra curvature information is extracted from the cervical vertebra side-view curve, and the cervical vertebra curvature information is jointly constituted.

[0024] In a feasible implementation, the edge computing chip is used to analyze the pressure distribution matrix and the user's physiological data to identify the user's current sleeping position, specifically including:

[0025] Inputting the pressure distribution matrix and the user's physiological data into the edge computing chip to perform fast edge computing; wherein a graph convolutional network is deployed in the edge computing chip;

[0026] Input the pressure distribution matrix into a pre-trained graph convolutional network, and output fuzzy sleeping posture information of the current user; wherein the fuzzy sleeping posture information is supine or side-lying;

[0027] Performing human body dynamics analysis based on the cervical curvature information to identify the user's orientation and body direction;

[0028] According to the orientation and body direction, the fuzzy sleeping posture information is accurately subdivided to determine the accurate sleeping posture information of the current user, thereby obtaining the current sleeping posture of the user.

[0029] In a feasible implementation manner, before determining the adjustment parameters of the intelligent adjustable airbag pillow according to the user's current sleeping posture and the cervical curvature information, the method further includes:

[0030] In the initial period after the intelligent adjustable airbag pillow starts to be used, the corresponding preset support curvature is used for different sleeping positions to initially support the user's cervical spine, and the user's sleep state data of the night is collected; wherein the sleep state data at least includes the number of turning over and the breathing frequency;

[0031] According to the sleep state data, fine-tuning the support curvature of the intelligent adjustable airbag pillow on the basis of the preset support curvature, and collecting the sleep state data of the user after the fine-tuning;

[0032] If the user's sleep state improves, continue to fine-tune the support curvature in accordance with this fine-tuning direction; if the user's sleep state deteriorates, adjust in the opposite direction of this fine-tuning direction.

[0033] Repeat the above process every night until the sleep state data of the user within the initial period reaches the preset condition. Obtain the pillow support curvature at this time, save it as the most suitable cervical curvature of the user, and obtain the target pressure matrix of the folding airbag at this time.

[0034] In a feasible implementation manner, determine the adjustment parameters of the intelligent adjustable airbag pillow according to the user's current sleeping posture and the cervical curvature information, specifically including:

[0035] According to the user's current sleeping posture, retrieve the corresponding most suitable cervical curvature and target pressure matrix.

[0036] Calculate the first mean square error between the user's cervical curvature information and the most suitable cervical curvature.

[0037] Align the head pressure distribution matrix with the pressure-receiving area of the target pressure matrix, and calculate the second mean square error between the elements of the pressure-receiving area.

[0038] According to the minimization of the objective function Iteratively solve for the airbag adjustment amount V of each airbag when both the first mean square error p1 and the second mean square error p2 are at the minimum values. i，j，k ; where i and j are used to refer to the positions of the folding airbags, that is, located in the i-th row and j-th column, and k is used to refer to the height of the folding airbag; λ is the expansion amount difference constraint parameter, TV(V)=∑(|V i+1，j，k -V i，j，k |+|V i，j+1，k -V i，j，k |), representing the expansion amount difference value between adjacent folding airbags. is the air pressure gradient value between adjacent folding airbags. is the mean square error of all air pressure gradient values, and μ is the air pressure gradient constraint parameter.

[0039] According to the airbag adjustment amount V i，j，k , determine the height adjustment parameter and air pressure adjustment parameter of each folding airbag.

[0040] In a feasible implementation manner, control the intelligent air pump to adjust the height and stiffness of the airbag to be adjusted according to the adjustment parameters, specifically including:

[0041] According to the height adjustment parameter, generate a corresponding height control instruction and send it to the intelligent air pump, so that the intelligent air pump controls the corresponding folding airbag to rise or fall.

[0042] According to the air pressure adjustment parameters, generate corresponding stiffness control instructions and send them to the intelligent air pump, so that the intelligent air pump inflates or deflates the corresponding folding airbag to change the air pressure value inside the folding airbag and achieve the stiffness adjustment of the folding airbag.

[0043] In a feasible implementation manner, after controlling the intelligent air pump to adjust the height and stiffness of the airbag to be adjusted according to the adjustment parameters, the method further includes:

[0044] Statistically analyze the pressure distribution change rate of the head pressure distribution matrix within a preset time after adjustment, and count the number of user turnovers and the turnover amplitude according to the pressure distribution change rate;

[0045] Calculate the body movement interference value according to the weighted value of the number of turnovers and the turnover amplitude;

[0046] Calculate the dynamic fitting degree between the user's cervical curvature after adjustment and the most suitable cervical curvature;

[0047] Collect environmental parameters near the pillow through the environmental perception sensors installed in the intelligent adjustable airbag pillow; wherein, the environmental parameters at least include: temperature, humidity, light intensity, noise;

[0048] Determine the current environmental suitability according to the weighted value of the environmental parameters;

[0049] Based on the body movement interference value, the dynamic fitting degree, and the environmental suitability, construct a multi-dimensional sleep quality assessment model;

[0050] Evaluate the user's sleep state through the multi-dimensional sleep quality assessment model;

[0051] If the user's sleep state deteriorates after adjustment, then reduce a preset value on the basis of the adjustment parameters to give the user time to adapt.

[0052] In a feasible implementation manner, after controlling the intelligent air pump to adjust the height and stiffness of the airbag to be adjusted according to the adjustment parameters, the method further includes:

[0053] According to the user's cervical curvature information and the pressure distribution matrix, construct a 3D spine posture animation and a pressure cloud map, and construct a digital twin model of the user's spine based on the 3D spine posture animation and the pressure cloud map;

[0054] Display each intelligent adjustment parameter of the night in the digital twin model, generate a sleep quality report for the night, and display both the digital twin model and the sleep quality report in the user interface.

[0055] On the other hand, an embodiment of the present invention further provides an intelligent adjustment system for adaptively adjusting the pillow shape based on the user's sleeping posture, and the system includes:

[0056] A sleeping posture recognition module, configured to obtain the pressure distribution matrix of the head and the user's physiological data through the multi-modal perception sensor array; wherein, the user's physiological data at least includes breathing frequency information and cervical curvature information; through the edge computing chip, analyze the pressure distribution matrix and the user's physiological data to identify the user's current sleeping posture;

[0057] An intelligent adjustment module, configured to determine the adjustment parameters of the intelligent adjustment airbag pillow according to the user's current sleeping posture and the cervical curvature information; according to the adjustment parameters, control the intelligent air pump to adjust the height and stiffness of the airbag to be adjusted.

[0058] Compared with the prior art, an intelligent adjustment method and system for adaptively adjusting the pillow shape based on the user's sleeping posture provided by an embodiment of the present invention has the following beneficial effects:

[0059] 1. The present invention provides an intelligent adjustment airbag pillow composed of an array of folded airbags and multi-modal perception sensors, which can adjust the shape of the pillow according to the real-time monitored data, provide comfortable support for the user's head and cervical spine, and improve the user's sleep quality. Breaking away from the shape limitation of traditional fixed-shaped pillows, it can more effectively adapt to the dynamic change requirements of the cervical curvature of the user in different sleeping postures, and reduce the phenomenon of morning neck and shoulder stiffness after long-term sleep.

[0060] 2. The present invention forms a multi-modal perception module through fiber Bragg gratings, radar chips and flexible strain sensor belts, which can collect pressure distribution and user physiological data at the same time, greatly improving the accuracy and timeliness of multi-modal data fusion. And the present invention performs edge computing through the edge computing chip, and the data does not need to be uploaded to the cloud, and calculations and instructions can be issued at the pillow end at any time, greatly accelerating the instruction response time, and the pillow shape can be adjusted in time according to the user's sleeping posture.

[0061] 3. The present invention correlates key physiological indicators such as the user's breathing frequency, turning-over times, and cervical curvature with the pillow support quality, providing a comprehensive and accurate sleep quality assessment method for the user.

[0062] 4. The present invention innovatively applies the sleep digital twin technology to achieve precise health management: through a 3D spine dynamics simulation engine driven by multi-source data, combined with a real-time solver, it can accurately simulate and predict the spine dynamics changes during sleep, providing a scientific basis for spine health monitoring and intervention. It provides strong support for the formulation of personalized sleep improvement plans, thus helping to improve the overall sleep quality and health level of users.

[0063] In summary, through the integration of multi-modal perception technology, the optimization of the folding airbag control method, and the innovative application of sleep digital twin technology, this patent not only achieves technological breakthroughs, but also brings multiple beneficial effects such as significant energy conservation and consumption reduction, improved system response speed, and enhanced health monitoring and intervention effects in practical applications, with extremely high practical value and market promotion potential. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. In the drawings:

[0065] Figure 1 It is a flowchart of an intelligent adjustment method for adaptively adjusting the pillow shape based on the user's sleeping posture provided by an embodiment of the present invention;

[0066] Figure 2 It is a schematic structural diagram of an intelligent adjustment airbag pillow provided by an embodiment of the present invention;

[0067] Figure 3 It is a schematic structural diagram of an intelligent adjustment system for adaptively adjusting the pillow shape based on the user's sleeping posture provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0068] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0069] An embodiment of the present invention provides an intelligent adjustment method for adaptively adjusting the pillow shape based on the user's sleeping posture,

[0070] As Figure 1 shown, the intelligent adjustment method for adaptively adjusting the pillow shape based on the user's sleeping posture specifically includes steps S101 - S104:

[0071] S101. Obtain the pressure distribution matrix of the head and the user's physiological data through a multi-modal perception sensor array; wherein, the user's physiological data at least includes respiratory frequency information and cervical curvature information.

[0072] Specifically, this method is applied to an intelligent adjustable airbag pillow proposed by the present invention. The intelligent adjustable airbag pillow at least includes: an edge computing chip, an intelligent air pump, a folding airbag array installed on the pillow base, and a multimodal sensing sensor array installed on the surface of each folding airbag. Figure 2 It is a schematic structural diagram of an intelligent adjustable airbag pillow provided by an embodiment of the present invention. Figure 2 The circular holes in it are the installation positions of the folding airbags, and the rectangular areas are the installation positions of the strip-shaped airbags, which are used to support the user's neck.

[0073] Further, at least the following are included in the above multimodal sensing sensors: an embedded fiber Bragg grating sensor, a micro radar chip, and a flexible strain sensor strip. The embedded fiber optic grating sensor is installed on the surface of the folding airbag to obtain the pressure value of each folding airbag under pressure. The micro radar chip is used for non-contact detection of the breathing frequency. And the flexible strain sensor strip is installed at the position of the strip-shaped airbag in Figure 2 to sense the cervical curvature information of the user.

[0074] Further, based on the above intelligent adjustable airbag pillow, through the multimodal sensing sensor array, a pressure distribution matrix of the head and user physiological data are obtained, specifically including:

[0075] Based on a preset time interval, the pressure values at each folding airbag are monitored in real time through the embedded fiber Bragg grating sensor. The pressure values are formed into a pressure distribution matrix of the head according to the arrangement of the folding airbags. The breathing frequency information of the user is monitored through the micro radar chip; the cervical curve of the contact part between the user and the pillow is sensed through the flexible strain sensor strip, and the cervical curvature information is extracted according to the cervical curve.

[0076] As a feasible implementation manner, extracting the cervical curvature information according to the cervical curve specifically includes:

[0077] Taking the center point of the intelligent adjustable airbag pillow as the origin, the long side direction of the pillow as the x-axis, the short side direction as the y-axis, and the direction perpendicular to the pillow plane as the z-axis, a three-dimensional coordinate system of the pillow is established.

[0078] Then the cervical curves sensed by the flexible strain sensor strip are respectively projected onto the XOY plane and the XOZ plane to obtain the cervical top view curve and the cervical side view curve. The first cervical curvature information is extracted from the cervical top view curve, and the second cervical curvature information is extracted from the cervical side view curve, which together constitute the cervical curvature information. Among them, the first cervical curvature information at least includes information such as the bending direction and curvature value of the cervical top view curve. Similarly, the second cervical curvature information at least includes information such as the bending direction and curvature value of the cervical side view curve.

[0079] S102. Parse the pressure distribution matrix and the user's physiological data through the edge computing chip to identify the user's current sleeping position.

[0080] Specifically, input the pressure distribution matrix and the user's physiological data into the edge computing chip for fast edge computing; among them, a graph convolutional network is deployed in the edge computing chip.

[0081] In one embodiment, the edge computing chip is a customized system-on-chip (SoC), a dual-core Cortex-A72 + NPU, with strong computing power.

[0082] Furthermore, input the pressure distribution matrix into the pre-trained graph convolutional network, and output the fuzzy sleeping position information of the current user; among them, the fuzzy sleeping position information is supine or side lying.

[0083] Furthermore, perform human body dynamics analysis according to the cervical curvature information to identify the user's facing direction and body orientation. According to the facing direction and body orientation, precisely subdivide the fuzzy sleeping position information to determine the precise sleeping position information of the current user and obtain the user's current sleeping position.

[0084] As a feasible implementation method, through a training set composed of different sleeping positions and pressure distribution matrices, pre-train the graph convolutional network so that it can identify whether the current human body is supine or side lying. Then, further accurately identify the directions of the body and the head according to the bending directions and curvatures of the cervical vertebra in the front view and side view. The precise sleeping positions at least include the following multiple situations: the body is supine but the head turns to the left, the body is supine but the head turns to the right, the body is supine and the head faces upward, the body and the head are both side lying to the left, the body and the head are both side lying to the right, the body is side lying to the left but the head faces upward, the body is side lying to the right but the head faces upward.

[0085] S103. Determine the adjustment parameters of the intelligent adjustable airbag pillow according to the user's current sleeping position and the cervical curvature information.

[0086] Specifically, first, within the initial period after the intelligent adjustable airbag pillow starts to be used, for different sleeping positions, respectively use the corresponding preset support curvatures to initially support the user's cervical vertebra, and collect the sleep state data of the user that night; among them, the sleep state data at least includes the number of turnovers and the breathing frequency.

[0087] Furthermore, according to the sleep state data, fine-tune the support curvature of the intelligent adjustable airbag pillow on the basis of the preset support curvature, and collect the sleep state data of the user after fine-tuning. If the user's sleep state improves, continue to fine-tune the support curvature in this fine-tuning direction; if the user's sleep state deteriorates, adjust in the opposite direction of this fine-tuning direction.

[0088] Repeat the above process every night until the sleep state data of the user reaches the preset conditions within the initial period. Obtain the pillow support curvature at this time, save it as the most suitable cervical curvature of the user, and obtain the target pressure matrix of the folding airbag at this time.

[0089] Further, after the initial period ends, every night, according to the user's current sleeping posture, retrieve the corresponding most suitable cervical curvature and the target pressure matrix. Then calculate the first mean square error between the user's cervical curvature information and the most suitable cervical curvature; align the pressure distribution matrix of the head with the compressed area of the target pressure matrix, and calculate the second mean square error between the elements in the compressed area.

[0090] Further, according to the minimization objective function provided by the present invention Iteratively solve for the airbag adjustment amount V of each airbag when both the first mean square error p1 and the second mean square error p2 are at their minimum values i，j，k .

[0091] where i and j are used to refer to the positions of the folding airbags, that is, located in the i-th row and j-th column, and k is used to refer to the height of the folding airbag; λ is the expansion amount difference constraint parameter, TV(V)=∑(|V i+1，j，k -V i，j，k |+|V i，j+1，k -V i，j，k |), representing the expansion amount difference value between adjacent folding airbags, is the air pressure gradient value between adjacent folding airbags, is the mean square error of all air pressure gradient values, and μ is the air pressure gradient constraint parameter.

[0092] Further, the airbag adjustment amount V i，j，k includes two cases. One is the airbag expansion amount, in which case the airbag adjustment amount is positive, and the other is the airbag compression amount, in which case the airbag adjustment amount is negative. According to the airbag expansion amount or compression amount, the height adjustment parameter of each folding airbag can be obtained. And according to the air pressure gradient value constraint between adjacent folding airbags, the air pressure adjustment parameter of each folding airbag can be obtained.

[0093] S104. According to the adjustment parameters, control the intelligent air pump to adjust the height and stiffness of the airbag to be adjusted.

[0094] Specifically, according to the height adjustment parameter, generate a corresponding height control instruction and send it to the intelligent air pump, so that the intelligent air pump controls the folding degree of the corresponding folding airbag, thereby raising or lowering the airbag.

[0095] According to the air pressure adjustment parameter, generate a corresponding stiffness control instruction and send it to the intelligent air pump, so that the intelligent air pump inflates or deflates the corresponding folding airbag to change the air pressure value inside the folding airbag and achieve the stiffness adjustment of the folding airbag.

[0096] Further, after adjusting the airbag, within a preset time after the adjustment, the pressure distribution change rate of the head pressure distribution matrix is statistically analyzed, and the number of user turnovers and the turnover amplitude are statistically analyzed according to the pressure distribution change rate. According to the weighted value of the number of turnovers and the turnover amplitude, the body movement interference value is calculated.

[0097] Then, the dynamic fitting degree between the user's cervical curvature after adjustment and the most suitable cervical curvature is calculated. And by means of the environmental perception sensor installed in the intelligent adjustable airbag pillow, environmental parameters near the pillow are collected; wherein, the environmental parameters at least include: temperature, humidity, light intensity, and noise. According to the weighted value of the environmental parameters, the current environmental suitability is determined.

[0098] Finally, based on the body movement interference value, the dynamic fitting degree, and the environmental suitability, a multi-dimensional sleep quality assessment model is constructed, weighted calculations are performed on various parameters, and the user's sleep state score is obtained. If the user's sleep state score after adjustment decreases, then on the basis of the adjustment parameters, the preset value is decreased to give the user time to adapt.

[0099] As a feasible implementation manner, the present invention further provides an intelligent visual APP. In the APP, according to the user's cervical curvature information and the pressure distribution matrix, a 3D spine posture animation and a pressure cloud map are constructed, and a digital twin model of the user's spine is constructed based on the 3D spine posture animation and the pressure cloud map.

[0100] Then, each intelligent adjustment parameter of that night is displayed in the digital twin model, and a sleep quality report of that night is generated. Both the digital twin model and the sleep quality report are displayed in the user interface, so that the user can intuitively see the changes in the spine during their sleep, as well as the number of adjustments that night and the changes in sleep quality after adjustment, thereby having a more intuitive understanding of their sleep quality and health level.

[0101] In addition, the embodiment of the present invention further provides an intelligent adjustment system for adaptively adjusting the pillow shape based on the user's sleeping posture, as Figure 3 shown. The intelligent adjustment system 300 for adaptively adjusting the pillow shape based on the user's sleeping posture specifically includes:

[0102] A sleeping posture recognition module 310, configured to obtain the pressure distribution matrix of the head and the user's physiological data through the multi-modal perception sensor array; wherein, the user's physiological data at least includes respiratory frequency information and cervical curvature information; and through the edge computing chip, the pressure distribution matrix and the user's physiological data are analyzed to identify the user's current sleeping posture;

[0103] The intelligent adjustment module 320 is configured to determine the adjustment parameters of the intelligent adjustable airbag pillow according to the user's current sleeping posture and the cervical curvature information; and control the intelligent air pump to adjust the height and stiffness of the airbag to be adjusted according to the adjustment parameters.

[0104] It further includes an intelligent adjustable airbag pillow 330, which at least includes: an edge computing chip, an intelligent air pump, a folding airbag array installed on the pillow base, and a multi-modal sensing sensor array installed on the surface of each folding airbag.

[0105] Each embodiment in the present invention is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for the embodiments of the device, equipment, and non-volatile computer storage medium, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiments.

[0106] The specific embodiments of the present invention are described above. Additionally, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0107] The above are only the embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, various changes and modifications can be made to the embodiments of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent adjustment method for adaptively adjusting the pillow shape based on the user's sleeping posture, characterized in that, Applied to an intelligent adjustable airbag pillow, the intelligent adjustable airbag pillow at least includes: an edge computing chip, an intelligent air pump, a folding airbag array installed on the pillow base, and a multimodal sensing sensor array installed on the surface of each folding airbag. The method includes: Obtain the pressure distribution matrix of the head and user physiological data through the multimodal sensing sensor array; wherein, the user physiological data at least includes respiratory frequency information and cervical curvature information; Parse the pressure distribution matrix and the user physiological data through the edge computing chip to identify the user's current sleeping posture; Determine the adjustment parameters of the intelligent adjustable airbag pillow according to the user's current sleeping posture and the cervical curvature information; Control the intelligent air pump to adjust the height and stiffness of the airbag to be adjusted according to the adjustment parameters.

2. The intelligent adjustment method for adaptively adjusting the pillow shape based on the user's sleeping posture according to claim 1, characterized in that, The multimodal sensing sensor at least includes an embedded fiber Bragg grating sensor, a micro radar chip, and a flexible strain sensor strip; Obtain the pressure distribution matrix of the head and user physiological data through the multimodal sensing sensor array, specifically including: Based on a preset time interval, monitor the pressure values at each folding airbag in real time through the embedded fiber Bragg grating sensor; Form the pressure distribution matrix of the head according to the arrangement of the folding airbags with the pressure values; Monitor the respiratory frequency information of the user through the micro radar chip; sense the cervical curve of the user's contact part with the pillow through the flexible strain sensor strip, and extract the cervical curvature information according to the cervical curve.

3. The intelligent adjustment method for adaptively adjusting the pillow shape based on the user's sleeping posture according to claim 2, wherein Extract the cervical curvature information according to the cervical curve, specifically including: Taking the center point of the intelligent adjustable airbag pillow as the origin, the long side direction of the pillow as the x-axis, the short side direction as the y-axis, and the direction perpendicular to the pillow plane as the z-axis, establish a three-dimensional coordinate system of the pillow; Project the cervical curve sensed by the flexible strain sensor strip onto the XOY plane and the XOZ plane respectively to obtain the cervical top view curve and the cervical side view curve; Extract the first cervical curvature information from the cervical top view curve and the second cervical curvature information from the cervical side view curve, and jointly form the cervical curvature information.

4. The intelligent adjustment method for adaptively adjusting the pillow shape based on the user's sleeping posture according to claim 1, wherein Parse the pressure distribution matrix and the user physiological data through the edge computing chip to identify the user's current sleeping posture, specifically including: Input the pressure distribution matrix and the user physiological data into the edge computing chip for fast edge computing; wherein, a graph convolutional network is deployed in the edge computing chip; Input the pressure distribution matrix into the pre-trained graph convolutional network, and output the fuzzy sleeping posture information of the current user; wherein, the fuzzy sleeping posture information is supine or side lying; Conduct human body dynamics analysis according to the cervical curvature information to identify the user's facing direction and body orientation; Precisely subdivide the fuzzy sleeping posture information according to the facing direction and body orientation to determine the precise sleeping posture information of the current user, and obtain the user's current sleeping posture.

5. The intelligent adjustment method for adaptively adjusting the pillow shape based on the user's sleeping posture according to claim 1, characterized in that, Before determining the adjustment parameters of the intelligent adjustable airbag pillow according to the user's current sleeping posture and the cervical curvature information, the method further includes: During the initial period after the intelligent adjustable airbag pillow starts to be used, for different sleeping postures, corresponding preset support curvatures are adopted to initially support the user's cervical spine, and the sleep state data of the user on that night is collected; wherein, the sleep state data at least includes the number of turnovers and the breathing frequency; According to the sleep state data, the support curvature of the intelligent adjustable airbag pillow is finely adjusted on the basis of the preset support curvature, and the sleep state data of the user after fine adjustment is collected; If the user's sleep state improves, the support curvature is continuously finely adjusted in accordance with this fine adjustment direction; if the user's sleep state deteriorates, the adjustment is made in the opposite direction of this fine adjustment direction; Repeat the above process every night until the sleep state data of the user reaches the preset conditions within the initial period, obtain the pillow support curvature at this time, save it as the most suitable cervical curvature of the user, and obtain the target pressure matrix of the folding airbag at this time.

6. The intelligent adjustment method for adaptively adjusting the pillow shape based on the user's sleeping posture according to claim 5, characterized in that, According to the user's current sleeping posture and the cervical curvature information, determine the adjustment parameters of the intelligent adjustable airbag pillow, specifically including: According to the user's current sleeping posture, retrieve the corresponding most suitable cervical curvature and the target pressure matrix; Calculate the first mean square error between the user's cervical curvature information and the most suitable cervical curvature; Align the pressure distribution area of the head pressure distribution matrix with the target pressure matrix, and calculate the second mean square error between the elements of the pressure distribution area; According to the minimized objective function Iteratively solve for the airbag adjustment amount V of each airbag when both the first mean square error p1 and the second mean square error p2 are minimized i,j,k ; where i and j are used to refer to the positions of the folded airbags, that is, located in the i-th row and j-th column, and k is used to refer to the height of the folded airbag; λ is the inflation amount difference constraint parameter, TV(V)=∑(|V i+1,j,k -V i,j,k |+|V i,j+1,k -V i,j,k |), representing the inflation amount difference value between adjacent folded airbags, is the air pressure gradient value between adjacent folded airbags, is the mean square error of all air pressure gradient values, and μ is the air pressure gradient constraint parameter; According to the airbag adjustment amount V i,j,k , determine the height adjustment parameter and the air pressure adjustment parameter of each folded airbag.

7. The intelligent adjustment method for adaptively adjusting the pillow shape based on the user's sleeping posture according to claim 6, wherein, According to the adjustment parameters, control the intelligent air pump to adjust the height and stiffness of the airbag to be adjusted, specifically including: According to the height adjustment parameter, generate a corresponding height control instruction and send it to the intelligent air pump, so that the intelligent air pump controls the corresponding folding airbag to rise or fall; According to the air pressure adjustment parameter, generate a corresponding stiffness control instruction and send it to the intelligent air pump, so that the intelligent air pump inflates or deflates the corresponding folding airbag to change the air pressure value in the folding airbag and realize the stiffness adjustment of the folding airbag.

8. An intelligent adjustment method for adaptively adjusting the pillow shape based on the user's sleeping posture according to claim 1, characterized in that, After controlling the intelligent air pump to adjust the height and stiffness of the airbag to be adjusted according to the adjustment parameters, the method further includes: Statistically analyze the pressure distribution change rate of the head pressure distribution matrix within a preset time after adjustment, and statistically analyze the number of turnovers and the amplitude of turnovers of the user according to the pressure distribution change rate; Calculate the body movement interference value according to the weighted value of the number of turnovers and the amplitude of turnovers; Calculate the dynamic fitting degree between the user's cervical curvature after adjustment and the most suitable cervical curvature; Collect the environmental parameters near the pillow through the environmental perception sensor installed in the intelligent adjustable airbag pillow; wherein, the environmental parameters at least include: temperature, humidity, light intensity, noise; Determine the current environmental suitability according to the weighted value of the environmental parameters; Based on the body movement interference value, the dynamic fitting degree and the environmental suitability, construct a multi-dimensional sleep quality evaluation model; Evaluate the user's sleep state through the multi-dimensional sleep quality evaluation model; If the user's sleep state deteriorates after adjustment, reduce the preset value on the basis of the adjustment parameters to give the user time to adapt.

9. The intelligent adjustment method for adaptively adjusting the pillow shape based on the user's sleeping posture according to claim 1, wherein After controlling the intelligent air pump to adjust the height and stiffness of the airbag to be adjusted according to the adjustment parameter, the method further includes: Constructing a 3D spine posture animation and a pressure nephogram based on the user's cervical curvature information and the pressure distribution matrix, and constructing a digital twin model of the user's spine based on the 3D spine posture animation and the pressure nephogram; Displaying each intelligent adjustment parameter of the night in the digital twin model, generating a sleep quality report for the night, and displaying both the digital twin model and the sleep quality report in the user interface.

10. An intelligent adjustment system for adaptively adjusting the pillow shape based on the user's sleeping posture, characterized in that, The system includes: A sleeping posture recognition module, configured to obtain a pressure distribution matrix of the head and user physiological data through the multi-modal perception sensor array; wherein the user physiological data at least includes breathing frequency information and cervical curvature information; parsing the pressure distribution matrix and the user physiological data through the edge computing chip to identify the user's current sleeping posture; An intelligent adjustment module, configured to determine an adjustment parameter of the intelligent adjustment airbag pillow according to the user's current sleeping posture and the cervical curvature information; and controlling the intelligent air pump to adjust the height and stiffness of the airbag to be adjusted according to the adjustment parameter.

Images