A home textile recommendation method and system based on child health data monitoring analysis

Abstract

The present application relates to the technical field of biomechanical measurement and analysis, and particularly relates to a home textile recommendation method and system based on child health data monitoring and analysis. The method comprises the following steps: collecting an original point cloud coordinate set of a child's sleeping posture; extracting a cervical curvature parameter group according to the cervical curvature parameter group of the extracted skeleton key point spatial distribution map; performing cervical vertebra and body position analysis according to the cervical curvature parameter group to obtain cervical curvature-body position holographic data; collecting a static pressure baseline data set according to the cervical curvature-body position holographic data; performing body position-pressure correlation analysis according to the static pressure baseline data set to obtain a body position-pressure mapping relationship table; and generating a pressure distribution index atlas according to the body position-pressure mapping relationship table. The present application realizes high-precision, full-process and personalized health home textile recommendation by comprehensively collecting and analyzing the sign data, pressure distribution and physiological curvature change of children in a natural sleep state.

Description

Technical Field

[0001] This invention relates to the field of biomechanical measurement and analysis technology, and in particular to a method and system for recommending home textiles based on monitoring and analysis of children's health data. Background Technology

[0002] Current home textile products often use uniform sizes or rough age groups, ignoring the individual differences in children's growth and development. Recommendation methods often rely on parents' subjective experience, questionnaires, or single static parameters such as height and weight, making it difficult to achieve dynamic, detailed analysis and precise matching of children's physical signs and health conditions.

[0003] Most home textile recommendations still rely on two-dimensional measurements or planar data, or even just visual observation, lacking high-precision data collection methods such as three-dimensional scanning and skeletal modeling. This makes it impossible to fully reflect children's actual sleeping posture, cervical curvature, and related health indicators, resulting in insufficient accuracy and scientific rigor in the recommendations.

[0004] Existing methods generally only perform single-point, static pressure measurements, which cannot dynamically reflect the pressure transfer and force changes caused by changes in a child's body position during sleep. This can easily lead to missed detection of health risks such as excessive local pressure and insufficient support, and cannot provide a scientific and reasonable basis for selecting home textiles for children.

[0005] In summary, the existing technologies for home textile recommendations suffer from a lack of detailed health data to support them, making it difficult to achieve scientific and accurate matching, a problem that urgently needs to be addressed. Summary of the Invention

[0006] Therefore, it is necessary to provide a method and system for recommending home textiles based on children's health data monitoring and analysis to solve at least one of the above-mentioned technical problems.

[0007] To achieve the above objectives, a method for recommending home textiles based on children's health data monitoring and analysis includes the following steps:

[0008] Step S1: Collect the original point cloud coordinate set of the child's sleeping posture; extract the cervical curvature parameter set based on the cervical curvature parameter set extracted from the spatial distribution map of the skeletal key points; perform cervical spine and body position analysis based on the cervical curvature parameter set to obtain cervical curvature-body position holographic data;

[0009] Step S2: Collect a static pressure baseline dataset based on cervical curvature-postural holographic data; perform postural-pressure correlation analysis based on the static pressure baseline dataset to obtain a postural-pressure mapping table; generate a pressure distribution index map based on the postural-pressure mapping table.

[0010] Step S3: Quantify the curvature-support effect based on the pressure distribution index map to obtain the curvature deviation index set; analyze the pressure-curvature response relationship between the curvature deviation index set and the pressure distribution index map to obtain the curvature recovery adaptation factor.

[0011] Step S4: Obtain pillow material performance data; calculate the biomechanical support index table based on the pillow material performance data and curvature recovery adaptation factor; make personalized pillow support recommendations based on the biomechanical support index table to obtain a set of recommended support parameters.

[0012] This invention collects raw point cloud coordinates of children's sleeping positions, extracts cervical curvature parameter sets, and performs cervical spine and body position analysis to obtain cervical curvature-body position holographic data. Its advantages are: by acquiring three-dimensional point cloud data of children in their natural sleeping positions through multi-angle optical scanning, it avoids the subjectivity and limitations of traditional two-dimensional measurements, achieving objective, comprehensive, and high-precision measurement of children's head and neck morphology. Extracting key skeletal points and constructing cervical curvature parameter sets quantifies the physiological curvature of the cervical spine, providing a foundation for subsequent curvature analysis and evaluation. Cervical spine and body position analysis establishes the correlation between cervical curvature and different sleeping positions, helping to understand the impact of different positions on cervical spine health. The final generated cervical curvature-body position holographic data comprehensively and accurately reflects children's cervical spine health status and sleeping habits, providing a reliable data foundation for subsequent stress analysis and personalized recommendations. Based on a static pressure baseline dataset collected using cervical curvature-posture holographic data, a postural-pressure correlation analysis was performed to generate a pressure distribution index map. The benefits are as follows: Through a pressure sensor array, the pressure distribution between the child's head and neck and the bedding can be monitored in real time, enabling dynamic and detailed analysis of the stress situation, avoiding the limitations of traditional methods that only perform single-point static measurements. The static pressure baseline dataset provides pressure data for different contact areas, helping to assess the stress situation in different areas. The postural-pressure correlation analysis establishes a mapping relationship between changes in posture and pressure distribution, enabling understanding of the changing patterns of pressure distribution under different sleeping positions and identifying potential pressure concentration points and areas of insufficient pressure. The generated pressure distribution index map visualizes the pressure distribution information, intuitively showing the pressure status of each area, providing crucial input information for subsequent quantification of curvature-support effects and personalized recommendations, and facilitating a comprehensive assessment of children's sleeping posture and stress situation. This study quantifies the curvature-support effect based on a pressure distribution index map and analyzes the pressure-curvature response relationship to obtain a curvature recovery fitting factor. The beneficial effects are as follows: By establishing age-stage standards and an ideal curvature model, an objective assessment of the cervical curvature recovery effect in children is achieved, avoiding the bias of subjective evaluation. Measurement of dynamic curvature change trajectories reflects the actual impact of pillows / bedding on cervical curvature recovery. The calculation of the curvature deviation index set quantifies the difference between actual and ideal cervical curvature, aiding in the assessment of support effectiveness. Analysis of the pressure-curvature response relationship reveals the intrinsic link between pressure distribution and changes in cervical curvature, providing a scientific basis for understanding the impact of pillows / bedding on cervical health. The final curvature recovery fitting factor comprehensively considers curvature recovery degree, pressure-curvature response characteristics, and age-stage features, quantifying the degree of matching between pillows / bedding and children's cervical health needs. This provides a crucial basis for personalized recommendations, helping to select the most suitable pillows / bedding for children and promoting healthy cervical development.By acquiring pillow material performance data, calculating a biomechanical support index table, and providing personalized pillow support recommendations, a set of recommended support parameters is generated. The benefits are as follows: Establishing a pillow material performance database provides a comprehensive understanding of the mechanical properties of various materials, laying the foundation for selecting suitable materials. The calculation of the biomechanical support index table comprehensively considers factors such as material performance, head and neck biomechanical parameters, support force, sleeping posture, and stability, quantifying the support effect of different pillows on children's cervical spine and providing a scientific basis for personalized recommendations. Pillow shape parameter optimization allows for the design of optimal pillow height, curvature, edge transition angle, and support area width based on individual differences in children, improving pillow comfort and support effectiveness. Material combination scheme design allows for the selection of appropriate materials based on the support needs of different areas, achieving differentiated support and improving the overall performance of the pillow. The final generated set of recommended support parameters includes pillow height range, material type and combination ratio, hardness zoning design, shape design parameters, and usage suggestions, providing users with a comprehensive, personalized, and actionable pillow selection plan, which helps improve children's sleep quality and promote cervical spine health. Therefore, this invention provides a home textile recommendation method based on children's health data monitoring and analysis. By introducing a process of three-dimensional health sign modeling, dynamic mapping of zoned pressure, cervical curvature recovery modeling, and multi-parameter intelligent recommendation, it comprehensively collects and analyzes children's vital sign data, pressure distribution, and physiological curvature changes during natural sleep. This achieves high-precision, full-process, and personalized health home textile recommendations, effectively solving the prominent problems of insufficient personalization, rough data collection, and unscientific pressure analysis in existing technologies, and improving the health adaptability and scientific nature of children's home textile products.

[0013] Preferably, the present invention also provides a home textile recommendation system based on children's health data monitoring and analysis, used to execute the home textile recommendation method based on children's health data monitoring and analysis as described above, the home textile recommendation system based on children's health data monitoring and analysis comprising:

[0014] The three-dimensional modeling module for vital signs is used to collect the original point cloud coordinate set of children's sleeping postures; the cervical curvature parameter set is extracted based on the cervical curvature parameter set extracted from the spatial distribution map of key skeletal points; the cervical spine and body position are analyzed based on the cervical curvature parameter set to obtain cervical curvature-body position holographic data.

[0015] The partitioned pressure mapping module is used to collect static pressure baseline datasets based on cervical curvature-postural holographic data; perform postural-pressure correlation analysis based on the static pressure baseline datasets to obtain a postural-pressure mapping relationship table; and generate a pressure distribution index map based on the postural-pressure mapping relationship table.

[0016] The curvature restoration modeling module is used to quantify the curvature-support effect based on the pressure distribution index map to obtain the curvature deviation index set; and to analyze the pressure-curvature response relationship between the curvature deviation index set and the pressure distribution index map to obtain the curvature restoration adaptation factor.

[0017] The support matching reasoning module is used to acquire pillow material performance data; calculate the biomechanical support index table based on the pillow material performance data and curvature recovery adaptation factor; and make personalized pillow support recommendations based on the biomechanical support index table to obtain a set of recommended support parameters.

[0018] This invention provides a home textile recommendation system based on children's health data monitoring and analysis. Through modules such as three-dimensional modeling of vital signs, zoned pressure mapping, curvature recovery modeling, and support matching reasoning, it constructs a complete solution from data collection and analysis to recommendation. With children's health data at its core, the system performs multi-dimensional health assessments and scientific support matching, achieving personalized and precise home textile product recommendations. It can improve children's sleep quality, promote healthy cervical spine development, and has the advantages of high integration, automation, and scalability, ultimately providing users with comprehensive and easy-to-understand recommendation solutions. Attached Figure Description

[0019] Figure 1 This is a flowchart illustrating the steps of a home textile recommendation method based on monitoring and analyzing children's health data.

[0020] Figure 2 This is a detailed flowchart illustrating the implementation steps of step S1 in this invention.

[0021] The objectives, features, and advantages of this invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] The technical method of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0023] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0024] It should be understood that although the terms "first," "second," etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are used merely to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0025] In this embodiment of the invention, reference Figure 1 The diagram shown is a flowchart illustrating the steps of the home textile recommendation method based on children's health data monitoring and analysis according to the present invention. In this example, the home textile recommendation method based on children's health data monitoring and analysis includes the following steps:

[0026] Step S1: Collect the original point cloud coordinate set of the child's sleeping posture; extract the cervical curvature parameter set based on the cervical curvature parameter set extracted from the spatial distribution map of the skeletal key points; perform cervical spine and body position analysis based on the cervical curvature parameter set to obtain cervical curvature-body position holographic data;

[0027] In this embodiment of the invention, the original point cloud coordinate set of a child's sleeping posture is collected, the cervical curvature parameter set is extracted, and cervical spine and body position analysis is performed to finally obtain cervical curvature-body position holographic data. First, a 3D optical scanner is used to scan the child's natural sleeping posture from multiple angles to obtain the original point cloud coordinate set. After filtering and head and neck extraction, the point cloud data is used to automatically identify and mark key skeletal points using a pre-trained convolutional neural network (CNN) model combined with manual correction, forming a spatial distribution map of key skeletal points. Based on the key points, the trajectory of the cervical spine centerline is extracted, and the three-plane curvature distribution map, key segment angle values, curve morphology feature set, curvature standard deviation value, cervical spine stress distribution map, and curvature dynamic change characteristics are calculated and integrated to obtain the cervical curvature parameter set. Finally, combining the spatial distribution map of key skeletal points and the cervical curvature parameter set, head and neck ratio and multi-dimensional posture angle measurement analysis are performed. All parameters are fused and standardized, and age-related reference standards are established by grouping by age to generate complete cervical curvature-body position holographic data.

[0028] Step S2: Collect a static pressure baseline dataset based on cervical curvature-postural holographic data; perform postural-pressure correlation analysis based on the static pressure baseline dataset to obtain a postural-pressure mapping table; generate a pressure distribution index map based on the postural-pressure mapping table.

[0029] In this embodiment of the invention, a static pressure baseline dataset is collected based on cervical curvature-positional holographic data. Position-pressure correlation analysis is then performed to generate a pressure distribution index map. First, based on the child's sleeping posture in the cervical curvature-positional holographic data, the child is placed on a pressure sensor test bed, and the pressure distribution between the head and neck and the bedding is measured to obtain a contact area division map. Then, under different positions, a static pressure baseline dataset is collected, recording the pressure value, contact area, and pressure center location. Simultaneously, a dynamic pressure change sequence is monitored, recording pressure changes during positional changes. Pressure uniformity is calculated to obtain a pressure uniformity distribution matrix. Next, the dynamic pressure change sequence is time-synchronized and spatially registered with the cervical curvature-positional holographic data to establish a position-pressure mapping relationship. The characteristic patterns of pressure distribution under different positions are analyzed, pressure transfer trajectories and pressure response delays are calculated, and a position-pressure mapping relationship table is constructed. Finally, the pressure peak value is identified, the correspondence between the pressure peak value and the key anatomical structures of the cervical spine is analyzed, a pressure peak value distribution feature map is generated, and the comprehensive pressure distribution index is calculated by comprehensively considering the pressure uniformity, body position-pressure mapping relationship and pressure peak value distribution, and a pressure distribution index map is generated.

[0030] Step S3: Quantify the curvature-support effect based on the pressure distribution index map to obtain the curvature deviation index set; analyze the pressure-curvature response relationship between the curvature deviation index set and the pressure distribution index map to obtain the curvature recovery adaptation factor.

[0031] In this embodiment of the invention, the curvature-support effect is quantified based on the pressure distribution index map, and the pressure-curvature response relationship is analyzed to ultimately obtain the curvature recovery adaptation factor. First, based on the pressure distribution index map and cervical curvature-postural holographic data, a cervical spine development stage reference standard is established according to age groups, and an ideal curvature model is constructed as a benchmark for evaluating the degree of cervical curvature recovery. Next, children use the pillow / bedding to be tested, and changes in cervical curvature are recorded in real time, along with corresponding changes in pressure distribution, to obtain the dynamic curvature change trajectory. Through numerical comparison, the deviation between the actual cervical curvature and the ideal curvature model is calculated, generating a curvature deviation index set. Then, pressure and cervical curvature data are simultaneously acquired at high frequency, processed through time window segmentation, and the influence of pressure on cervical curvature is analyzed. A pressure-curvature mapping function is established, and time delay characteristic analysis is performed to generate a pressure-curvature response matrix. Finally, based on the curvature deviation index set and the pressure-curvature response matrix, a comprehensive scoring system for cervical curvature recovery is established, a curvature recovery score table is calculated, and a multidimensional adaptation factor calculation model is constructed by comprehensively considering the curvature recovery score, pressure-curvature response characteristics and age staging characteristics to generate curvature recovery adaptation factors.

[0032] Step S4: Obtain pillow material performance data; calculate the biomechanical support index table based on the pillow material performance data and curvature recovery adaptation factor; make personalized pillow support recommendations based on the biomechanical support index table to obtain a set of recommended support parameters;

[0033] In this embodiment of the invention, pillow material performance data is acquired, a biomechanical support index table is calculated, and personalized pillow support recommendations are made to ultimately obtain a set of recommended support parameters. First, a pillow material performance database is constructed, collecting mechanical property parameters of different materials and performing material rebound response analysis to obtain a material rebound characteristic evaluation table. Then, biomechanical parameters of children's head and neck are collected, and a regional ideal support force table is calculated. Next, a set of material support force curves is measured, a regional support matching index is calculated, and posture difference analysis is performed to obtain a posture support correction coefficient. Combined with sleep posture ratio monitoring analysis, a sleep posture time ratio table is obtained, and the support stability coefficient is evaluated. Finally, the biomechanical support index is comprehensively calculated to obtain a biomechanical support index table. Based on the biomechanical support index table and curvature recovery adaptation factor, pillow morphological parameters are optimized to obtain morphological parameter combinations. Based on the morphological parameter combinations and the biomechanical support index table, pillow materials are combined to obtain material combination schemes, and then a personalized adjustment parameter table is calculated. Finally, the morphological parameter combinations, material combination schemes, and personalized adjustment parameter tables are integrated to generate a set of recommended support parameters.

[0034] As an example of the present invention, reference is made to... Figure 2 As shown, in this example, step S1 includes:

[0035] Step S11: Acquire the child's natural sleeping posture using a high-speed camera and perform multi-angle optical scanning on the child's natural sleeping posture to obtain the original point cloud coordinate set;

[0036] In this embodiment of the invention, to obtain the child's natural sleeping posture, it is necessary to ensure that the child is relaxed and avoid excessive tension or discomfort. The operator should guide the child to adopt their habitual sleeping posture and record this posture. To reduce environmental interference, the scanning environment should maintain stable lighting, suitable temperature, and provide a quiet scanning space. Multi-angle optical scanning of the child's natural sleeping posture is performed to obtain the original point cloud coordinate set. A 3D optical scanner equipped with structured light or laser scanning technology is used to scan the child from four orthogonal directions (front, back, left, right) and the top. The minimum measurement accuracy of the scanner must reach 0.5mm. Each scan generates original point cloud data containing X, Y, and Z three-dimensional coordinates. To improve data integrity, the relative position between the scanner and the child must be kept stable during the scanning process to avoid data loss due to the child's slight movements. After scanning, the point cloud data from the four directions are registered and fused to generate complete point cloud data of the child's head and neck. The original point cloud coordinate set is represented as P={(x i yi , z i )|i=1,2,…,N}, where N is the total number of point clouds.

[0037] Step S12: Locate the skeletal key points in the original point cloud coordinate set and draw a spatial distribution map of the skeletal key points;

[0038] In this embodiment of the invention, skeletal keypoint localization is performed on the original point cloud coordinate set to obtain a spatial distribution map of skeletal keypoints. An automatic skeletal keypoint localization algorithm based on computer vision is employed. First, the point cloud data is filtered to remove noise points. Then, a point cloud segmentation algorithm is used to identify and extract the point cloud data of the head and neck region. Next, a pre-trained convolutional neural network (CNN) model is applied to detect keypoints in the head and neck point cloud data. Keypoints include: C1 vertebral body, C2 vertebral body, C3 vertebral body, C4 vertebral body, C5 vertebral body, C6 vertebral body, C7 vertebral body, skull base, mandibular angle, acromion, etc. The CNN model needs to be trained on a large amount of children's head and neck point cloud data to ensure localization accuracy. To improve localization accuracy, manual correction can be combined. The spatial distribution map of skeletal keypoints can be represented as K={(x k y k , z k ,k)|k=1,2,…,M}, where M is the total number of keypoints and k represents the keypoint type.

[0039] Step S13: Extract the cervical curvature parameter set from the spatial distribution map of skeletal key points;

[0040] In this embodiment of the invention, the cervical curvature parameter set is extracted from the spatial distribution map of skeletal key points. Based on the spatial distribution map of skeletal key points, the cervical spine centerline trajectory is extracted. Key points from C1 to C7 vertebrae are connected to obtain a three-dimensional coordinate sequence of the cervical spine centerline. This sequence is smoothed to eliminate noise. A spline interpolation algorithm is used to fit the cervical spine centerline to obtain a continuous cervical spine centerline trajectory. Multi-plane curvature calculation is performed on the cervical spine centerline trajectory to obtain a three-plane curvature distribution map. The curvature of the cervical spine centerline is calculated in the coronal, sagittal, and horizontal planes respectively. The curvature calculation formula is κ=∣r″(t)×r′(t)∣ / ∣r′(t)∣³, where r(t) represents the parametric equation of the cervical spine centerline trajectory, and r′(t) and r″(t) represent its first and second derivatives, respectively. The angle values ​​of key segments in the three-plane curvature distribution map are measured. The curvature angles of cervical vertebrae C2-C7 in the sagittal plane, the angles of C1-C2, and C6-C7 are measured. Based on the cervical spine centerline trajectory and key segment angles, curve length and morphology measurements are performed to obtain a curve morphology feature set. The total length of the cervical spine centerline, the length of each segment, and the symmetry of the cervical curve are calculated. Standard curve deviation analysis is performed on the curve morphology feature set to obtain the standard deviation of curvature. The actual cervical curve is compared with the standard cervical curve, the Euclidean distance between corresponding points is calculated, and the root mean square error (RMSE) is obtained as the standard deviation of curvature. Stress distribution is estimated based on the standard deviation of curvature to obtain a cervical spine stress distribution map. A three-dimensional model of the pediatric head and neck bones and muscles is established based on the finite element analysis (FEA) method. Cervical curvature parameters are input as boundary conditions into the FEA model to simulate the stress on the cervical spine, and a cervical spine stress distribution map is output. Dynamic change characteristics are measured based on the cervical spine centerline trajectory and curve morphology feature set to obtain the dynamic change characteristics of curvature. Repeat the above steps under different sleeping positions to obtain cervical curvature parameters under different sleeping positions. Construct a set of cervical curvature parameters based on the three-plane curvature distribution map, key segment angle values, curve morphology feature set, curvature standard deviation value, cervical spine stress distribution map, and curvature dynamic change characteristics.

[0041] Step S14: Perform head and neck ratio measurement and analysis based on the spatial distribution map of key skeletal points and the cervical curvature parameter set to obtain head and neck biomechanical ratio data;

[0042] In this embodiment of the invention, head-neck ratio measurement and analysis are performed based on the spatial distribution map of key skeletal points and the cervical curvature parameter set to obtain head-neck biomechanical ratio data. The relative position of the head weight distribution center and the cervical spine support point is measured. Based on the spatial distribution map of key skeletal points, the position of the head's center of mass is determined, and the coordinates of the head's center of gravity are calculated. The cervical spine support point is measured, and the coordinates of the cervical spine support center are calculated. The horizontal and vertical distances between the head's center of gravity and the cervical spine support center are calculated. Based on the cervical curvature parameter set, the support area of ​​the cervical spine is calculated. The proportional relationship between head weight and cervical spine support force is calculated. Based on age-grouped children, growth and development reference values ​​for head-neck ratios are established. The head-neck biomechanical ratio data includes: head center of gravity coordinates, cervical spine support center coordinates, horizontal distance, vertical distance, support area, and weight ratio.

[0043] Step S15: Based on the cervical curvature parameter set and head-neck biomechanical ratio data, measure the multidimensional angle parameters of the head-to-bed angle, the angle between the cervical spine and the shoulder line, and the angle between the cervical spine axis and the horizontal plane, and construct a multidimensional posture angle matrix.

[0044] In this embodiment of the invention, based on cervical curvature parameter sets and head-neck biomechanical proportion data, multidimensional angle parameters such as the angle between the head and the bed surface, the angle between the line connecting the cervical spine and the shoulder, and the angle between the cervical spine axis and the horizontal plane are measured to construct a multidimensional posture angle matrix. The angle between the head and the bed surface is measured. Based on the spatial distribution map of skeletal key points, the highest point of the head and the contact point with the bed surface are determined, and the angle between the head and the bed surface is calculated. The angle between the line connecting the cervical spine and the shoulder is measured. Based on the spatial distribution map of skeletal key points, the positions of the C7 vertebral body and the acromion are determined, and the angle between the line connecting the cervical spine and the shoulder is calculated. The angle between the cervical spine axis and the horizontal plane is measured. The cervical spine axis is constructed using the key points of the C1-C7 vertebral bodies, and the angle between this axis and the horizontal plane is calculated. The multidimensional posture angle matrix is ​​represented as A=[α 11 α 12 α 13 ;α 21 α 22 α 23 ;...;α n1 α n2 α n3 ], where α i1 α represents the angle between the head and the bed surface in the i-th posture. i2 α represents the angle between the line connecting the cervical spine and shoulder in the i-th posture. i3 The angle between the cervical spine axis and the horizontal plane is represented by the i-th posture, and n represents the total number of postures.

[0045] Step S16: Perform holographic data integration and standardization on the cervical curvature parameter group and the multidimensional posture angle matrix to obtain cervical curvature-position holographic data.

[0046] In this embodiment of the invention, cervical curvature parameter sets and multidimensional posture angle matrices are holographically integrated and standardized to obtain cervical curvature-posture holographic data. The cervical curvature parameter sets, head-neck biomechanical proportion data, and multidimensional posture angle matrix are fused. The dimensions and data formats are unified. The data is standardized to eliminate the influence of dimensions. The Z-score standardization method is used to convert each parameter into a value with a mean of 0 and a standard deviation of 1. Data is classified according to children's age groups (0-3 years, 3-6 years, 6-10 years, 10-16 years) to establish age-related reference standards. The cervical curvature-posture holographic data is represented as H={(C, L, A)|C∈cervical curvature parameter sets, L∈head-neck biomechanical proportion data, A∈multidimensional posture angle matrix}.

[0047] Preferably, the cervical curvature parameter set extracted from the spatial distribution map of skeletal key points in step S13 includes:

[0048] Extract the cervical spine centerline trajectory from the spatial distribution map of key skeletal points;

[0049] Multi-plane curvature calculations were performed on the trajectory of the cervical spine centerline to obtain a three-plane curvature distribution map.

[0050] Measure the angle values ​​of key segments in the three-plane curvature distribution diagram;

[0051] Based on the cervical spine centerline trajectory and key segment angle values, the curve length and morphology are measured to obtain a curve morphology feature set;

[0052] Standard curve deviation analysis is performed on the curve morphology feature set to obtain the standard deviation value of curvature;

[0053] Stress distribution is estimated based on the standard deviation of curvature to obtain a stress distribution map of the cervical spine;

[0054] Dynamic change characteristics of curvature are obtained by measuring the dynamic change characteristics of the cervical spine centerline trajectory and curve morphology feature set.

[0055] A set of cervical curvature parameters is constructed based on the three-plane curvature distribution map, key segment angle values, curve morphology feature set, curvature standard deviation value, cervical spine stress distribution map, and curvature dynamic change characteristics.

[0056] In this embodiment of the invention, the cervical spine centerline trajectory is extracted based on the spatial distribution map of key skeletal points. Key points from C1 to C7 vertebrae are connected to form a point sequence in three-dimensional space. This point sequence is denoted as P = {P1, P2, ..., P7}, where P... i =(x i y i , z iLet P represent the coordinates of the key point of the i-th vertebra. A cubic B-spline curve is used to fit P to obtain a smooth cervical spine centerline trajectory. The parametric equation of the B-spline curve is C(t) = ∑ i N i , p (t)P i , where N i , p (t) is the B-spline basis function, and p is the order of the B-spline curve, usually p=3. The parametric equation of the cervical spine centerline trajectory is calculated as C(t)=(x(t), y(t), z(t)), where t is a parameter with a value range of [0, 1].

[0057] Multiplanar curvature calculations were performed on the trajectory of the cervical spine centerline to obtain a three-plane curvature distribution map. The curvature of the cervical spine centerline was calculated in the coronal, sagittal, and transverse planes, respectively.

[0058] The formula for calculating the coronal curvature κc(t) is: κc(t) = |x″(t)y′(t) The formula for calculating the sagittal curvature κs(t) is x′(t)y″(t)∣ / (x′(t)²+y′(t)²)³ / ². The formula for calculating the cross-sectional curvature κh(t) is x′(t)z″(t)∣ / (x′(t)²+z′(t)²)³ / ². y′(t)z″(t)∣ / (y′(t)²+z′(t)²)³ / ². Where x′(t), y′(t), z′(t) and x″(t), y″(t), z″(t) are the first and second derivatives of C(t), respectively. The curvature distributions of the three planes are calculated as κc(t), κs(t), and κh(t).

[0059] Measure the angle values ​​of key segments in the three-plane curvature distribution map. Identify the key segments of the cervical spine curve, including the C1-C2, C2-C7, and C6-C7 segments. Locate the corresponding positions of the C1, C2, and C7 vertebral bodies on the sagittal curvature distribution map κs(t). Calculate the angle α of the C1-C2 segment. 12 The calculation method is as follows: connect points C1 and C2, and calculate the angle between the line connecting them and the horizontal line. Calculate the angle α of segment C2-C7. 27 The calculation method is as follows: connect points C2 and C7, and calculate the angle between the line connecting them and the horizontal line. Calculate the angle α of the segment C6-C7. 67 The calculation method is as follows: connect points C6 and C7, and calculate the angle between the line connecting them and the horizontal line. The angle value of the key segment is α. 12 α 27 α 67 .

[0060] The length and shape of the curve are measured based on the trajectory of the cervical spine centerline and the angle values ​​of key segments to obtain a curve shape feature set. The total length L of the cervical spine centerline is calculated. This is done using the integral formula L = ∫0¹∣C′(t)∣dt, where C′(t) is the first derivative of C(t). The lengths L of segments C1-C2, C2-C7, and C6-C7 are also calculated. 12 L 27 L 67 The symmetry of the cervical spine curve is calculated based on the trajectory of the cervical spine centerline. The calculation method involves projecting the trajectory of the cervical spine centerline onto the sagittal plane and calculating its symmetry about the y-axis. The curve morphology feature set includes: total length L, and segment lengths L... 12 L 27 L 67 Symmetry index.

[0061] A standard curve deviation analysis was performed on the curve morphology feature set to obtain the standard deviation value of curvature. A standard curve model of the cervical spine in children was established. The standard curve model is an average cervical spine curve model based on age and gender, obtained from statistical analysis of a large number of children's cervical spine data. The actual cervical spine curve was compared with the standard cervical spine curve. n equally spaced points were selected on the cervical spine centerline trajectory. The vertical distance d from each point to the standard curve was calculated. i Calculate the standard deviation of curvature RMSE = √(∑ i d i ² / n).

[0062] Stress distribution was estimated based on the standard deviation of curvature to obtain a cervical spine stress distribution map. A three-dimensional model of the child's head and neck bones and muscles was established using the finite element analysis (FEA) method. The model's geometry was reconstructed from CT or MRI scan data. Material properties were set according to the child's physiological characteristics. The cervical spine centerline trajectory and the standard deviation of curvature were input as boundary conditions into the FEA model. Constraints were set to simulate the free movement of the child's head in the horizontal plane. FEA calculations were performed to obtain the cervical spine stress distribution map. The stress distribution map shows the magnitude and distribution of stress in various parts of the cervical spine.

[0063] The dynamic changes in cervical curvature are measured based on the cervical spine centerline trajectory and curve morphology feature set to obtain the dynamic changes in curvature. The above steps are repeated under different sleeping positions to obtain cervical curvature parameters for each position. The cervical curvature of children is measured in different sleeping positions, including supine and lateral. For each sleeping position, the above steps are repeated to obtain the cervical spine centerline trajectory, curvature distribution, key segment angle values, curve length, morphological characteristics, and standard deviation of curvature. The changes in these parameters under different sleeping positions are compared to obtain the dynamic changes in curvature. For example, the difference in the angles of segments C2-C7 is calculated between supine and lateral positions to reflect the influence of sleeping position on cervical curvature.

[0064] A cervical curvature parameter set was constructed based on the three-plane curvature distribution map, key segment angle values, curve morphology feature set, curvature standard deviation value, cervical spine stress distribution map, and dynamic curvature change characteristics. The cervical curvature parameter set includes: three-plane curvature distribution maps κc(t), κs(t), κh(t), and key segment angle values ​​α. 12 α 27 α 67 Curve length and shape measurement results L, L 12 L 27 L 67 Symmetry index, curvature standard deviation (RMSE), cervical spine stress distribution map, and dynamic changes under different sleeping positions.

[0065] Preferably, step S2 includes the following steps:

[0066] Step S21: Accurately measure the contact area based on the cervical curvature-body position holographic data to obtain a contact area division map;

[0067] Step S22: Collect static pressure baseline dataset based on the contact area division diagram;

[0068] Step S23: Monitor the dynamic pressure change sequence based on the static pressure baseline dataset and contact area division map;

[0069] Step S24: Calculate the pressure uniformity based on the dynamic pressure change sequence and the static pressure baseline dataset to obtain the pressure uniformity distribution matrix;

[0070] Step S25: Perform position-pressure correlation analysis on the dynamic pressure change sequence and cervical curvature-position holographic data to obtain a position-pressure mapping table;

[0071] Step S26: Analyze the peak pressure distribution based on the body position-pressure mapping table and the pressure uniformity distribution matrix to obtain a peak pressure distribution characteristic map;

[0072] Step S27: Calculate the pressure distribution index map based on the pressure uniformity distribution matrix, the body position-pressure mapping table, and the pressure peak distribution characteristic map.

[0073] In this embodiment of the invention, the contact area is accurately measured based on cervical curvature-positional holographic data to obtain a contact area division map. The child is placed on a test bed equipped with high-density pressure sensors. The pressure sensors are capacitive or piezoresistive, with a sensor spacing of less than 1 cm and a measurement accuracy greater than 0.1 kPa. Based on the child's sleeping posture recorded in the cervical curvature-positional holographic data, the child is guided to maintain different positions such as supine and lateral. Pressure distribution data between the head and neck and the mattress / pillow is collected in real time using a pressure sensor array. Contact areas are identified based on the pressure data. A pressure threshold is set, and areas with pressure values ​​greater than the threshold are defined as contact areas. The contact area division map includes the headrest contact area, neck support area, and shoulder transition area. An image segmentation algorithm is used to process the pressure distribution data, identify and mark the boundaries of different areas. The area of ​​each contact area is calculated. The contact area division map can be represented as C = { (x i y i area i zone i )|i=1,2,…,N}, where x i y i The area represents the center coordinates of the contact region. i Indicates the contact area, zone i Indicates the area type (headrest, neck, shoulder).

[0074] Static pressure baseline datasets were collected based on contact area mapping. These datasets were collected while the child maintained a stable sleeping position. The data acquisition time was 30 seconds. For each region in the contact area mapping, the pressure value, contact area, and pressure center location were recorded. Pressure values ​​were measured directly using a pressure sensor. The contact area was calculated based on the contact area mapping. The pressure center location was calculated using the formula (x_c, y_c) = (∑ i p i x i / ∑ i p i , ∑ i p i y i / ∑ i p i ), where p i The pressure value measured by each sensor, (x i y i ) represents the sensor location. The static pressure baseline dataset is represented as S={(zone i p i area i , x_c i y_c i )|i=1,2,…,M}, where zone iIndicates the region type, p i The area represents the average pressure value. i Represents the contact area, (x_c i y_c i ) represents the coordinates of the pressure center, and M is the total number of contact areas.

[0075] Dynamic pressure change sequences were monitored based on a static pressure baseline dataset and contact area delineation map. Children were guided to perform natural positional changes on the testing bed, such as from supine to lateral. Pressure changes throughout the process were recorded using a high-frequency sampling pressure sensor array (sampling frequency greater than 20Hz). Pressure values ​​from each sensor were continuously monitored during positional changes. The pressure value from each sensor was recorded at each sampling time. Sensor data were mapped to contact areas according to the contact area delineation map. The dynamic pressure change sequence is represented as D={(t j zone i p ij )|i=1,2,…,M;j=1,2,…,T}, wheret j Indicates the sampling time, zone i Indicates the region type, p ij Indicates at time t j zone i The average pressure value, where T is the total sampling time.

[0076] Pressure uniformity is calculated based on the dynamic pressure variation sequence and static pressure baseline dataset to obtain the pressure uniformity distribution matrix. For each contact area, the uniformity coefficient of the pressure distribution is calculated. The variance of the pressure distribution is calculated as σ² = ∑ i (p i p )² / n, where p i For each sensor's pressure value, p Let n be the average pressure value and n be the number of sensors. Calculate the pressure peak-to-valley ratio, which is the ratio of the maximum pressure value to the minimum pressure value. The pressure uniformity coefficient U = 1. σ² / σ_max², where σ_max² is the maximum variance. The pressure uniformity distribution matrix is ​​represented as U=[U 11 U 12 U 13 ;U 21 U 22 U 23 ;…;U m1 U m2 U m3 ], where U ij This represents the pressure uniformity of the j-th region under the i-th posture.

[0077] A position-pressure correlation analysis was performed on the dynamic pressure change sequence and cervical curvature-positional holographic data to obtain a position-pressure mapping table. The dynamic pressure change sequence D and the cervical curvature-positional holographic data H were synchronized in time. Different data were matched based on timestamps. Spatial coordinate mapping transformation was performed on the synchronized data to map pressure data to the coordinates of key skeletal points. Linear interpolation or nearest neighbor interpolation methods were used to map pressure data onto the coordinates of key skeletal points. Standard body positions were extracted. Supine, left lateral, and right lateral positions were defined. The child's position was identified based on the cervical curvature-positional holographic data. The pressure transfer trajectory was calculated. During position changes, the change in the pressure center was tracked to obtain the movement trajectory of the pressure center. The pressure response delay was calculated. The time required for the pressure in each region to reach a stable state after a position change was calculated. The influence coefficient of position change was calculated. The degree of influence of different positions on the average pressure in each region was calculated. The position-pressure mapping table is represented as M={(pose i zone j p ij trajectory ij delay ij coefficient ij )|i=1,2,…,N;j=1,2,…,M}, where pose i Indicates body position, zone j Indicates the region type, p ij Indicates the body position / pose i lower zone j average pressure value, trajectory ij Represents the zone during body position changes. j Pressure transfer trajectory, delay ij Indicates a zone j Pressure response delay, coefficient ij This represents the coefficient of influence of body position changes.

[0078] Pressure peak distribution analysis was performed based on the body position-pressure mapping table and pressure uniformity distribution matrix to obtain a pressure peak distribution feature map. The location of pressure peak points was identified. The point with the highest pressure value was found in the pressure distribution data. The region where the pressure peak point was located was determined based on the contact area division map. The correspondence between pressure peak points and key cervical spine anatomical structures was analyzed. The distance between pressure peak points and key cervical spine points was determined based on the spatial distribution map of key skeletal points. The potential impact of pressure peaks on cervical spine physiological curvature was assessed. Based on the location of pressure peak points and cervical spine curvature parameters, the impact of pressure peaks on cervical spine curvature was evaluated. The pressure peak distribution feature map is represented as F={(zone i peaki ,location i distance i influence i )|i=1,2,…,M}, where zone i Indicates the region type, peak i Indicates peak pressure, location i Indicates the location of the peak point, distance i Indicates the distance between the peak point and the key point of the cervical spine, influence i This indicates the degree to which peak pressure affects the curvature of the cervical spine.

[0079] The pressure distribution index is calculated based on the pressure uniformity distribution matrix, the body position-pressure mapping table, and the pressure peak distribution characteristic map. A multidimensional pressure assessment index system is established, comprehensively considering pressure uniformity, body position-pressure mapping, and pressure peak distribution. Weighting coefficients are set, with different factors weighted according to the age characteristics of the children. The comprehensive pressure distribution index is calculated. The calculation formula can be a weighted average or other suitable calculation method. The calculation results are visualized as a color-coded map. The pressure distribution index map is represented as G={(x i y i index i color i )|i=1,2,…,N}, where x i y i Indicates position coordinates, index i Indicates the pressure distribution index, color i Indicates color.

[0080] Of particular importance is that the acquisition of the static pressure baseline dataset in step S22 specifically involves:

[0081] Based on the contact area division diagram, posture stabilization guidance data acquisition is performed to obtain a standard posture record table;

[0082] Collect raw pressure data matrix according to the standard posture recording table;

[0083] Extract the regional pressure feature table from the original pressure data matrix;

[0084] Calculate the pressure uniformity distribution map based on the regional pressure characteristic table;

[0085] Pressure gradient analysis was performed on the pressure uniformity distribution map to obtain the pressure gradient distribution map;

[0086] Based on the pressure gradient distribution map, the pressure mapping of anatomical structures is performed to obtain the anatomical pressure correspondence table;

[0087] The pressure data were standardized according to the anatomical pressure correspondence table to obtain the static pressure baseline dataset;

[0088] In this embodiment of the invention, posture stabilization guidance data acquisition is performed based on a contact area division diagram to obtain a standard posture record table. According to the contact area division diagram C={(x i y i area i zone i Guide children to maintain a stable posture using a visual guidance system or voice prompts. Use a 30-second recording time to guide children in maintaining standard sleeping positions such as supine and lateral decubitus. Record the child's position on the testing bed, such as supine or lateral decubitus. Record the contact area division for each position. The standard posture recording table is represented as P = {(pose)} | i = 1, 2, ..., N}. i time i zone i )|i=1,2,…,M}, where pose i Indicates the gesture type, time i Indicates the collection time, zone i Indicates the contact area.

[0089] The raw pressure data matrix was acquired according to the standard posture recording table. Raw pressure data was acquired using a pressure sensor array under each standard posture. The acquisition frequency was set to above 20Hz. The pressure sensor array consisted of multiple pressure sensors, each corresponding to one data point. The pressure value of each sensor at each sampling time was recorded. The raw pressure data matrix is ​​represented as R=[r 11 r 12 …r 1k ;r 21 r 22 …r 2k ;…;r n1 r n2 …r nk ], where r ij Let represent the pressure value of the j-th sensor at the i-th sampling time, n represent the total number of samplings, and k represent the total number of sensors.

[0090] Extract the regional pressure characteristic table from the raw pressure data matrix. Based on the contact area division map, map the pressure sensor data to the contact areas. Calculate the average pressure value, maximum pressure value, minimum pressure value, and pressure standard deviation for each contact area. The regional pressure characteristic table is represented as T={(zone...} i p i p_max i p_min i , σ i)|i=1,2,…,M}, where zone i Indicates the region type, p i p_max represents the average pressure value. i p_min represents the maximum pressure value. i σ represents the minimum pressure value. i This represents the standard deviation of pressure.

[0091] Calculate the pressure uniformity distribution map based on the regional pressure characteristic table. Calculate the pressure uniformity for each contact area. Use the variance calculation method to calculate the variance σ² of the pressure distribution. The formula for calculating pressure uniformity is U=1 σ² / σ_max², where σ_max² is the maximum variance. The pressure uniformity distribution is represented as U={(x i y i U i )|i=1,2,…,N}, where x i y i U represents the center coordinates of the contact area. i Indicates pressure uniformity.

[0092] Pressure gradient analysis is performed on the pressure uniformity distribution map to obtain the pressure gradient distribution map. The direction and magnitude of the pressure gradient are calculated. The Sobel operator or Prewitt operator is used to calculate the gradient of the pressure distribution. The gradient direction indicates the direction of the fastest pressure change, and the gradient magnitude indicates the rate of pressure change. The pressure gradient distribution map is represented as G={(x i y i gradient_magnitude i gradient_direction i )|i=1,2,…,N}, where x i y i The gradient_magnitude represents the center coordinates of the contact area. i Indicates the magnitude of the pressure gradient, gradient_direction i Indicates the direction of the pressure gradient.

[0093] Anatomical pressure mapping is performed based on the pressure gradient distribution map to obtain an anatomical pressure correspondence table. Based on the spatial distribution map of key skeletal points, pressure gradients are mapped to anatomical structures. The direction and magnitude of the pressure gradient are mapped to anatomical structures such as the cervical spine and shoulder. For example, the direction of the pressure gradient is compared to the cervical spine axis. The anatomical pressure correspondence table is represented as A={(zone i gradient_magnitude i gradient_directioni anatomical_structure i )|i=1,2,…,M}, where zone i Indicates the region type, gradient_magnitude i Indicates the magnitude of the pressure gradient, gradient_direction i Indicates the direction of the pressure gradient, anatomical_structure i This indicates the corresponding anatomical structure.

[0094] The pressure data was standardized according to the anatomical pressure correspondence table to obtain a static pressure baseline dataset. The pressure data was standardized to eliminate the influence of dimensions. The Z-score standardization method was used to convert each feature into a value with a mean of 0 and a standard deviation of 1. The static pressure baseline dataset is represented as S={(zone ... i p _std i p_max_std i p_min_std i σ_std i )|i=1,2,…,M}, where zone i Indicates the region type, p _std i p_max_std represents the standardized average pressure value. i p_min_std represents the standardized maximum pressure value. i σ_std represents the standardized minimum pressure value. i This represents the standard deviation of pressure after standardization.

[0095] Preferably, the position-pressure correlation analysis in step S25 includes:

[0096] Time-series synchronization processing was performed on the dynamic pressure change sequence and cervical curvature-postural holographic data to obtain time-synchronized data pairs.

[0097] Perform spatial coordinate mapping transformation on the time synchronization data pairs to obtain the spatial corresponding mapping matrix;

[0098] Standard postural state extraction was performed on the spatial correspondence mapping matrix and time synchronization data pairs to obtain standard postural pressure characteristics;

[0099] The pressure transfer trajectory is calculated based on the pressure characteristics of the standard body position, resulting in a set of pressure transfer trajectories;

[0100] Pressure response time delay was measured on the pressure transfer trajectory set to obtain a regional pressure response time delay table;

[0101] Calculate the influence coefficient of body position change based on the regional pressure response time delay table and pressure transfer trajectory set;

[0102] Construct a body position-pressure mapping table based on the body position change influence coefficient table.

[0103] In this embodiment of the invention, time-series synchronization processing is performed on the dynamic pressure change sequence and cervical curvature-posture holographic data to obtain time-synchronized data pairs. The dynamic pressure change sequence D = {(t...} j zone i p ij The cervical curvature-postural holographic data is H={(C, L, A)}, where i=1, 2, ..., M; j=1, 2, ..., T. The timestamp for the dynamic pressure change sequence is t. j The timestamps of the cervical curvature-positional holographic data were recorded by the scanner. A linear interpolation method was used to interpolate the timestamps of the cervical curvature-positional holographic data to align them with the timestamps of the dynamic pressure change sequence. If the sampling frequency of the cervical curvature-positional holographic data was lower than that of the dynamic pressure change sequence, the cervical curvature-positional holographic data was upsampled. If the sampling frequency of the cervical curvature-positional holographic data was higher than that of the dynamic pressure change sequence, the dynamic pressure change sequence was downsampled. Time-synchronized data pairs are represented as {(t...} j D j H j )}, where D j Indicates at time t j Dynamic pressure change sequence data, H j Indicates at time t j Cervical curvature-postural holographic data.

[0104] Spatial coordinate mapping transformation is performed on the time-synchronized data pairs to obtain the spatial mapping matrix. The dynamic pressure change sequence data is then compared with the spatial distribution map of skeletal key points K={(x... k y k , z k Spatial mapping is performed on the {k)|k=1,2,…,M}. For each time t… j The position of each pressure sensor in space is determined. A coordinate transformation matrix is ​​used to map the pressure sensor coordinates to the skeletal keypoint coordinate system. The coordinate transformation matrix is ​​determined by the scanner calibration results. The spatial mapping matrix is ​​represented as M=[m 11 m 12 …m 1k ;m 21 m 22 …m 2k ;…;m n1 m n2 …m nk ], where mij Indicates at time t i The j-th pressure sensor is mapped to the spatial coordinates of the skeletal key point k.

[0105] Standard posture features are extracted from the spatial correspondence mapping matrix and time-synchronized data pairs to obtain standard posture pressure features. Standard postures are defined, such as supine, left lateral, and right lateral. Based on cervical curvature-postural holographic data, the child's posture at each moment is identified. Pressure features of the standard postures are extracted. For each standard posture, the mean pressure value, maximum pressure value, minimum pressure value, and pressure standard deviation are calculated. The standard posture pressure feature is represented as P={(pose...} i zone j p ij p_max ij p_min ij , σ ij )|i=1,2,…,N;j=1,2,…,M}, where pose i Indicates body position, zone j Indicates the region type, p ij p_max represents the average pressure value. ij p_min represents the maximum pressure value. ij σ represents the minimum pressure value. ij This represents the standard deviation of pressure.

[0106] Pressure transfer trajectories are calculated based on the pressure characteristics of the standard body position, resulting in a set of pressure transfer trajectories. During body position changes, the change in the pressure center is tracked. The position of the pressure center at each moment is calculated using the formula (x_c, y_c) = (∑ i p i x i / ∑ i p i , ∑ i p i y i / ∑ i p i ), where p i For each sensor's pressure value, (x i y i (pose) represents the sensor position. Connecting the pressure center forms a pressure transfer trajectory. The pressure transfer trajectory set is represented as T = {(pose)} i trajectory i )|i=1,2,…,N}, where pose i Indicates body position, trajectory i This represents the trajectory of the center of pressure during a change in body position.

[0107] Pressure response time delays were measured on the pressure transfer trajectory set to obtain a regional pressure response time delay table. The time required for the pressure in each region to reach a steady state after a change in body position was measured. A criterion for reaching a steady state was defined, for example, a pressure change of less than 5%. For each region, the time for the pressure to reach a steady state was calculated. The regional pressure response time delay table is represented as D = {(zone ...} i delay i )|i=1,2,…,M}, where zone i Indicates the region type, delay i This indicates the pressure response delay.

[0108] Calculate the body position change influence coefficient table based on the regional pressure response time delay table and pressure transfer trajectory set. Calculate the degree of influence of different body positions on the average pressure of each region. For each region, calculate the average pressure difference under different body positions. Calculate the body position change influence coefficient. The body position change influence coefficient is expressed as C={(pose...} i zone j coefficient ij )|i=1,2,…,N;j=1,2,…,M}, where pose i Indicates body position, zone j Indicates the region type, coefficient ij This represents the coefficient of influence of body position changes.

[0109] A position-pressure mapping table is constructed based on the table of influence coefficients for positional changes. The position-pressure mapping table M is constructed. This table includes position, region, mean pressure, pressure transfer trajectory, pressure response delay, and the influence coefficient of positional changes. The position-pressure mapping table is represented as M = {(pose...} i zone j p ij trajectory ij delay ij coefficient ij )|i=1,2,…,N;j=1,2,…,M}, where pose i Indicates body position, zone j Indicates the region type, p ij Mean pressure, trajectory ij Indicates the pressure transfer trajectory, delay ij Indicates pressure response delay, coefficient ij This represents the coefficient of influence of body position changes.

[0110] Preferably, the curvature-support effect quantification in step S3 includes:

[0111] Based on the pressure distribution index map and cervical curvature-postural holographic data, an age staging standard was established to obtain a reference standard for cervical spine development staging.

[0112] Based on the cervical spine development stage reference standard and cervical spine curvature-positional holographic data, an ideal curvature model was constructed to obtain an age-stage ideal curvature model.

[0113] Based on the ideal curvature model for age stages and the pressure distribution index map, the actual support effect was measured to obtain the dynamic curvature change trajectory.

[0114] A curvature deviation quantitative analysis was performed on the dynamic curvature change trajectory and the ideal curvature model for age staging to obtain a curvature deviation index set.

[0115] In this embodiment of the invention, age staging standards are established based on pressure distribution index maps and cervical curvature-postural holographic data to obtain a reference standard for cervical spine development staging. Children are grouped by age into four age groups: 0-3 years, 3-6 years, 6-10 years, and 10-16 years. Based on a large amount of cervical curvature-postural holographic data of children, the physiological curvature characteristics of the cervical spine in each age group are statistically analyzed. Parameters such as cervical curvature and vertebral angle are analyzed, and standard values ​​and acceptable ranges are set. The head-neck ratio of different age groups is analyzed to establish corresponding reference standards. The pressure distribution index map is analyzed to extract the pressure distribution characteristics of different age groups. The cervical spine development staging reference standard includes: age group, standard values ​​of cervical curvature parameters, head-neck ratio reference values, and pressure distribution characteristics.

[0116] An ideal cervical curvature model was constructed based on the cervical spine developmental staging reference standard and cervical curvature-postural holographic data to obtain an age-staging ideal curvature model. For each age group, an ideal cervical curvature model was constructed. The ideal curvature model is based on the cervical spine developmental staging reference standard and a large amount of cervical spine data from children. A spline curve fitting method was used to fit the cervical spine centerline to obtain the morphological parameters of the ideal cervical curve. Morphological parameters include curvature, arc length, and key point angles. The ideal curvature model is represented by a parametric equation, C(t) = (x(t), y(t), z(t)), where t is a parameter with a value range of [0, 1]. The age-staging ideal curvature model includes: age group, ideal cervical curve parametric equation, and coordinates of key cervical points.

[0117] An ideal cervical curvature model was constructed based on the cervical spine developmental staging reference standard and cervical curvature-postural holographic data to obtain an age-staging ideal curvature model. For each age group, an ideal cervical curvature model was constructed. The ideal curvature model is based on the cervical spine developmental staging reference standard and a large amount of cervical spine data from children. A spline curve fitting method was used to fit the cervical spine centerline to obtain the morphological parameters of the ideal cervical curve. Morphological parameters include curvature, arc length, and key point angles. The ideal curvature model is represented by a parametric equation, C(t) = (x(t), y(t), z(t)), where t is a parameter with a value range of [0, 1]. The age-staging ideal curvature model includes: age group, ideal cervical curve parametric equation, and coordinates of key cervical points.

[0118] A quantitative analysis of curvature deviation was performed on the dynamic curvature change trajectory and the ideal curvature model for age stages to obtain a curvature deviation index set. The actual cervical curvature was compared with the ideal curvature model. The deviation value between the actual cervical curvature and the ideal curvature model was calculated. The distance from a point on the actual cervical curve to the ideal cervical curve was calculated using the point-to-curve distance calculation method. The curve integral difference value, i.e., the area difference between the actual curve and the ideal curve, was calculated. The degree and distribution of curvature deviation were quantitatively assessed. A comprehensive deviation index was calculated. The curvature deviation index set is represented as D={(deviation value, distribution, index)|(C i -C i )|i=1,2,…,N}, where C i This represents the actual cervical curvature parameter, C. i This represents the parameters of the ideal cervical curvature.

[0119] Preferably, the pressure-curvature response analysis in step S3 includes:

[0120] High-frequency synchronous data acquisition was performed on the pressure distribution index spectrum to obtain pressure-curvature synchronous time series data; the pressure-curvature synchronous time series data was then processed by time window segmentation to obtain a windowed rate of change dataset;

[0121] Based on the windowed rate of change dataset and the pressure distribution index map, key pressure regions are divided to obtain a functional region pressure characteristic table.

[0122] Based on the functional area pressure characteristic table, the area sensitivity measurement is carried out to obtain the area curvature sensitivity coefficient table;

[0123] Critical pressure points are identified based on the regional curvature sensitivity coefficient table and the functional region pressure characteristic table, resulting in a critical pressure point location map.

[0124] Based on the critical pressure point location map, a pressure-curvature mapping function is constructed to obtain a set of point-curve mapping functions;

[0125] Based on the point-curve mapping function set, time delay characteristics are analyzed to obtain the regional response time delay table;

[0126] Generate the pressure-curvature response matrix based on the regional response delay table;

[0127] The curvature restoring score is calculated based on the pressure-curvature response matrix and the curvature deviation index set to obtain the curvature restoring score table.

[0128] The curvature restoration fitting factor is obtained by comprehensively generating fitting factors based on the curvature restoration rating table and the pressure-curvature response matrix.

[0129] In this embodiment of the invention, high-frequency synchronous data acquisition is performed on the pressure distribution index spectrum to obtain pressure-curvature synchronous time-series data. A high-sampling-rate pressure sensor array and a cervical curvature measurement device are used to synchronously acquire the pressure distribution index spectrum and cervical curvature data. The sampling frequency of the pressure sensor array is greater than 20Hz. The cervical curvature measurement device uses an optical or inertial measurement unit (IMU) with a sampling frequency greater than 20Hz. The synchronously acquired data includes: the pressure value at each moment and the cervical curvature parameters at each moment. The pressure distribution index spectrum is represented as G={(x i y i index i The cervical curvature data is represented as C(t) = (x(t), y(t), z(t)) | i = 1, 2, ..., N). The pressure-curvature synchronous time series data is represented as S = {(t) | i = 1, 2, ..., N}. j G j C j )|j=1,2,…,T}, where t j G represents time. j Indicates at time t j Pressure distribution index map, C j Indicates at time t j The cervical curvature data.

[0130] The pressure-curvature synchronous time-series data is segmented into time windows to obtain a windowed rate of change dataset. The pressure-curvature synchronous time-series data S is divided into multiple time windows, each with a length of 1 second. For each time window, the rate of change of the pressure distribution index and the rate of change of the cervical curvature parameter are calculated. The rate of change of the pressure distribution index is obtained by calculating the difference in pressure indices between adjacent time points. The rate of change of the cervical curvature parameter is obtained by calculating the difference in cervical curvature parameters between adjacent time points. The windowed rate of change dataset is represented as W={(t k ΔG k ΔC k )|k=1,2,…,K}, where t k ΔG represents the center moment of the time window.k ΔC represents the rate of change of the pressure distribution index within a time window. k This represents the rate of change of cervical curvature parameters within a time window, where K represents the total number of time windows.

[0131] Based on the windowed rate of change dataset and the pressure distribution index map, key pressure regions are divided to obtain a functional area pressure feature table. Key pressure regions are defined according to the pressure distribution index map. These key pressure regions include the headrest area, neck support area, and shoulder transition area. For each key pressure region, the mean, maximum, minimum, and rate of change of the pressure distribution index are calculated. The functional area pressure feature table is represented as F={(zone i p i p_max i p_min i , Δp i )|i=1,2,…,M}, where zone i Indicates the region type, p i p_max represents the average pressure distribution index. i p_min represents the maximum pressure distribution index. i Δp represents the minimum pressure distribution index. i This represents the rate of change of the pressure distribution index, and M represents the total number of critical pressure zones.

[0132] Based on the functional area pressure characteristic table, regional sensitivity measurements were performed to obtain a regional curvature sensitivity coefficient table. The influence of each key pressure area on cervical curvature was calculated. The calculation method involved calculating the correlation coefficient between the pressure change rate and the cervical curvature change rate for each key pressure area. The formula for calculating the correlation coefficient is r = ∑ i [(x i x )(y i )] / √(∑ i (x i x )²∑ i (y i )²), where x i y represents the rate of change of pressure. i The x represents the rate of change in cervical curvature. and These represent their average values. The zone curvature sensitivity coefficient table is represented as R={(zone i coefficienti )|i=1,2,…,M}, where zone i Indicates the region type, coefficient i This represents the correlation coefficient.

[0133] Critical pressure points are identified using the zone curvature sensitivity coefficient table and the functional zone pressure characteristic table, resulting in a critical pressure point location map. Based on the zone curvature sensitivity coefficient, the pressure points with the greatest impact on cervical curvature are identified. For each critical pressure zone, the point with the largest rate of pressure change is found. The critical pressure point location map is represented as L={(zone...} i , (x i y i ))|i=1,2,…,M}, where zone i Indicates the region type, (x i y i () indicates the location of the critical pressure point.

[0134] Based on the critical pressure point location map, a pressure-curvature mapping function is constructed to obtain a set of point-curve mapping functions. A mapping function between pressure and cervical curvature is then established. For each critical pressure point, a correspondence between pressure changes and cervical curvature changes is established. Linear functions, polynomial functions, or neural networks can be used for mapping. The set of point-curve mapping functions is represented as M={(point...} i f i )|i=1,2,…,M}, where point i f represents the critical pressure point. i This represents the pressure-curvature mapping function.

[0135] Time delay characteristics are analyzed based on the point-curve mapping function set to obtain a regional response time delay table. The effect of pressure changes on cervical curvature changes is analyzed. The time delay between pressure changes and cervical curvature changes is calculated. The time delay can be calculated using cross-correlation analysis or time series analysis. The regional response time delay table is represented as D={(zone i delay i )|i=1,2,…,M}, where zone i Indicates the region type, delay i Indicates a time delay.

[0136] Generate a pressure-curvature response matrix based on the regional response delay table. Construct the pressure-curvature response matrix. The rows of the matrix represent pressure regions, the columns represent cervical curvature parameters, and the matrix elements represent the effect of pressure changes on cervical curvature. The pressure-curvature response matrix is ​​represented as R=[r 11 r 12 …r 1k ;r21 r 22 …r 2k ;…;r m1 r m2 …r mk ], where r ij This represents the influence of the i-th pressure region on the j-th cervical curvature parameter.

[0137] The recovery score is calculated based on the pressure-curvature response matrix and the curvature deviation index set, resulting in a curvature recovery score table. The cervical curvature recovery score is calculated using the pressure-curvature response matrix and the curvature deviation index set. The curvature deviation is weighted according to the degree of influence of different pressure zones on the cervical curvature. The recovery score range is set to 0-100 points. The curvature recovery score table is represented as S={(score... i weight i )|i=1,2,…,N}, where score i Indicates recovery score, weight i Indicates the weight.

[0138] The curvature recovery fitting factor is generated by comprehensively considering the curvature recovery score and the stress-curvature response matrix. The fitting factor includes the recovery coefficient, the adaptability index, and the developmental promotion value. The curvature recovery fitting factor is expressed as A = (recovery coefficient, adaptability index, developmental promotion value).

[0139] Preferably, the calculation of the biomechanical support index table in step S4 includes:

[0140] A material performance parameter library was constructed based on pillow material performance data; material rebound response analysis was performed based on the material performance parameter library and curvature recovery adaptation factor to obtain a material rebound characteristic evaluation table;

[0141] Collect a set of head and neck biomechanical parameters based on curvature restoration adaptation factors; calculate the ideal support force table for the region based on the set of head and neck biomechanical parameters.

[0142] Based on the set of material support force curves measured using the regional ideal support force table;

[0143] Calculate the regional support matching index based on the material support force curve set;

[0144] Postural difference analysis was performed based on the regional support matching index to obtain the posture support correction coefficient;

[0145] Based on the posture support correction coefficient, a sleeping posture ratio monitoring and analysis was conducted to obtain a sleeping posture time ratio table.

[0146] The support stability coefficient is assessed based on the sleeping posture time percentage table;

[0147] The biomechanical support index table is obtained by calculating the comprehensive support index based on the regional support matching index, posture support correction coefficient, sleeping posture time ratio table, and support stability coefficient.

[0148] In this embodiment of the invention, a material performance parameter library is constructed based on pillow material performance data. Performance data for various pillow materials are collected, including memory foam, latex, fiber, hydrogel, etc. The material performance data includes: hardness, rebound time, density, air permeability, thermal conductivity, durability, and compressive strength. Hardness is measured using a Shore hardness tester. Rebound time is measured using a pressure sensor and timer, defined as the time required for the material to recover to its initial state after being compressed. Density is calculated using mass and volume. Air permeability is measured using an air permeability tester. Thermal conductivity is measured using a thermal conductivity meter. Durability is tested using a fatigue tester. Compressive strength is tested using a universal testing machine. The material performance parameter library is represented as P={(material i hardness i ,rebound_time i density i air_permeability i thermal_conductivity i Durability i compressive_strength i )|i=1,2,…,N}, where material i Indicates material type, hardness i Represents hardness, rebound_time i Indicates rebound time, density i Represents density, air_permeability i Thermal_conductivity indicates breathability. i Indicates thermal conductivity, durability i Indicates durability, compressive_strength i This indicates the compressive strength, and N represents the total amount of material.

[0149] Material springback response analysis was performed based on a material performance parameter library and curvature recovery adaptation factor to obtain a material springback characteristic evaluation table. Key material performance indicators were determined based on the curvature recovery adaptation factor. These key material performance indicators include springback time, hardness, and support force. Pressure and displacement sensors were used to measure the material's springback response characteristics. The springback time and deformation of the material under different pressures were measured. The material springback characteristic evaluation table is expressed as T={(material...} i pressure i ,rebound_time i deformation i )|i=1,2,…,N}, where material i Indicates material type, pressure i Represents pressure, rebound_time i Indicates rebound time, deformation i This represents deformation, and N represents the total amount of material.

[0150] A set of head and neck biomechanical parameters was collected based on the curvature recovery fitting factor. The biomechanical parameters of the child's head and neck were determined based on the curvature recovery fitting factor. These biomechanical parameters included: head weight, neck length, cervical curvature, and muscle strength. Head weight was measured using an electronic scale. Neck length was measured using a measuring tape. Cervical curvature was measured using a 3D scanner. Muscle strength was measured using a muscle strength tester. The set of head and neck biomechanical parameters is represented as B = {(weight, length, curvature, muscle strength)}.

[0151] The ideal support force table for each zone is calculated based on the head and neck biomechanical parameter set. The ideal support force is related to head weight, neck length, and cervical curvature. The calculation formula can employ a mechanical model or empirical formula. The ideal support force table is expressed as I = {(zone ...} i ideal_force i )|i=1,2,…,M}, where zone i Indicates the region type, ideal_force i M represents the ideal support force, and M represents the total number of regions.

[0152] The material support force curve set is measured based on the ideal support force table for the region. Using a universal testing machine, the support force of different materials under different pressures is measured. The support force of different materials under different deformations is also measured. The material support force curve set is represented as C = {(material...} i pressure i , forcei )|i=1,2,…,N}, where material i Indicates material type, pressure i To indicate pressure, force i The symbol represents the supporting force, and N represents the total amount of material.

[0153] The regional support matching index is calculated based on the material support force curve set. The degree of matching between the material support force and the ideal support force is calculated. The calculation method involves calculating the difference between the material support force and the ideal support force. The matching index is then calculated; for example, relative error or correlation coefficient can be used. The regional support matching index is expressed as M = {(zone...} i material i matching_index i )|i=1,2,…,M}, where zone i Indicates the region type, material i Indicates the material type, matching_index i This represents the support matching index, and M represents the total number of regions.

[0154] Postural difference analysis was performed based on the regional support matching index to obtain the postural support correction coefficient. The differences in support matching under different sleeping positions were analyzed. The support matching index for different sleeping positions was calculated. The postural support correction coefficient is expressed as S={(pose i zone j correction_factor ij )|i=1,2,…,P;j=1,2,…,M}, where pose i Indicates the type of posture, zone j Indicates the region type, correction_factor ij The value represents the posture support correction factor, P represents the total number of postures, and M represents the total number of regions.

[0155] Sleep position proportion monitoring and analysis were conducted based on the postural support correction coefficient to obtain a sleep position time proportion table. Children's sleep time in different sleeping positions was monitored. Sleep time for each sleeping position was recorded. The percentage of sleep time for each sleeping position was calculated. The sleep position time proportion table is represented as T={(pose i , percentage i )|i=1,2,…,P}, where pose i Indicates the gesture type, percentage i The value represents the percentage of sleep time, and P represents the total number of postures.

[0156] Assess the support stability coefficient based on the sleeping position time percentage table. Evaluate the support stability of the pillow / bedding. Support stability is related to the material's rebound time, firmness, and shape. Calculate the support stability coefficient. The support stability coefficient is expressed as Y = {stability_coefficient}.

[0157] A comprehensive support index is calculated based on the zone support matching index, posture support correction coefficient, sleep position time ratio, and support stability coefficient, resulting in a biomechanical support index table. The biomechanical support index is calculated by comprehensively considering the zone support matching index, posture support correction coefficient, sleep position time ratio, and support stability. The calculation formula can use a weighted average or other suitable calculation methods. The biomechanical support index table is represented as B={(zone...} i index i )|i=1,2,…,M}, where zone i Indicates the region type, index i denoted as the biomechanical support index, and M represents the total number of regions.

[0158] Preferably, the personalized pillow support recommendation in step S4 includes:

[0159] Pillow morphological parameters were optimized based on the biomechanical support index table and curvature recovery adaptation factor to obtain a combination of morphological parameters.

[0160] Pillow materials are combined based on morphological parameter combinations and biomechanical support index tables to obtain material combination schemes;

[0161] A personalized parameter adjustment table is calculated based on the material combination scheme and morphological parameter combination.

[0162] Based on the combination of morphological parameters, material combination schemes, and personalized adjustment parameter tables, a comprehensive set of recommended supporting parameters is generated.

[0163] In this embodiment of the invention, the pillow's morphological parameters are optimized based on the biomechanical support index table and curvature recovery adaptation factor to obtain a combination of morphological parameters. According to the biomechanical support index table B={(zone... i index iThe pillow's morphological parameters are determined using the formulas |i=1, 2, ..., M} and the curvature recovery adaptation factor. These parameters include height, curvature, edge transition angle, and support area width. Height optimization: The optimal height range is determined based on the biomechanical support index. The optimal height is related to cervical curvature, head-neck ratio, and sleeping posture. The height range is set as: minimum, maximum, and step value. Curvature optimization: The optimal curvature is determined based on cervical curvature and pressure distribution. Curvature can be represented using a curve equation, such as a Bézier curve. Edge transition angle optimization: The optimal edge transition angle is determined based on shoulder structure and sleeping posture. Support area width optimization: The optimal support area width is determined based on cervical spine length and sleeping posture. Optimization algorithms can use genetic algorithms, particle swarm optimization, or gradient descent algorithms. The combination of morphological parameters is represented as O={(height, curvature, edge_angle, width)}.

[0164] Pillow materials are combined based on morphological parameter combinations and a biomechanical support index table to obtain a material combination scheme. The morphological parameter combination O = {(height, curvature, edge_angle, width)} and the biomechanical support index table B = {(zone...}...} are used. i index i Let |i=1,2,…,M}, determine the pillow material combination. Divide the pillow into different zones, such as a head support zone, a neck support zone, and a transition buffer zone. For each zone, select an appropriate material.

[0165] Material selection is based on a material performance parameter library P={(material i hardness i ,rebound_time i density i air_permeability i thermal_conductivity i Durability i compressive_strength i The springback evaluation table T = {(material) | i = 1, 2, ..., N} and the springback characteristic evaluation table T = {(material) | i = 1, 2, ..., N} i pressure i ,rebound_time i deformation i The material combination scheme includes the material type and the combination ratio. The material combination scheme is represented as C = {(zone ...} | i = 1, 2, ..., N}. i material i ratioi )|i=1,2,…,M}, where zone i Indicates the region type, material i Indicates material type, ratio i Indicates the proportion of materials.

[0166] A personalized parameter adjustment table is calculated based on the material combination scheme and morphological parameter combination. According to the material combination scheme C={(zone i material i ratio i The personalized adjustment parameters are calculated using the combination of morphological parameters O = {(height, curvature, edge_angle, width)} and |i=1,2,…,M}. These parameters consider individual differences, such as head shape, sleep habits, and specific physical conditions. Head shape: Adjust pillow height and curvature according to head shape. Sleep habits: Adjust pillow support and material according to sleeping posture. Specific physical conditions: Adjust pillow material based on allergy history. Personalized adjustment parameters can be represented using coefficients or offsets. The personalized adjustment parameter table is represented as A = {(parameters)}. i adjustment i )|i=1,2,…,K}, where parameter i Indicates the parameter type, adjustment i This represents the adjustment value, and K represents the total number of parameters.

[0167] A comprehensive set of recommended support parameters is generated based on the combination of morphological parameters, material combination schemes, and personalized adjustment parameter tables. The morphological parameter combination O, material combination scheme C, and personalized adjustment parameter table A are integrated to generate comprehensive recommended parameters. These comprehensive recommended parameters include: recommended pillow height range, material type and combination ratio, firmness zone design, shape design parameters, and usage suggestions. Recommended pillow height range: The recommended height range is determined based on the morphological parameter combination and personalized adjustment parameters. Material type and combination ratio: The recommended material type and combination ratio are determined based on the material combination scheme. Firmness zone design: Firmness zones are designed based on the biomechanical support index and personalized adjustment parameters. Shape design parameters: The pillow's shape design parameters are determined based on the morphological parameter combination and personalized adjustment parameters. Usage suggestions: Usage suggestions are provided based on material characteristics and individual differences, such as replacement cycle and cleaning methods.

[0168] The recommended set of support parameters is represented as R={(height_range, material_composition, hardness_zone, shape_parameters, usage_advice)}.

[0169] Most importantly, the optimization of pillow shape parameters specifically includes:

[0170] Functional regions are defined based on the biomechanical support index table, resulting in a functional region size table.

[0171] Calculate the set of area height parameters based on the functional area size table;

[0172] Construct a set of contour curve equations based on the region height parameter set;

[0173] The edge transition angles of the functional area size table are optimized based on the contour curve equations to obtain the edge transition angle table.

[0174] The posture adaptability assessment was conducted based on the edge transition angle table to obtain a posture adaptability scoring table;

[0175] Based on the posture adaptability rating scale, the age segment parameters are adjusted to obtain the age segment parameter table;

[0176] Calculate the individual difference compensation value based on the age segmentation parameter table;

[0177] By integrating the edge transition angle table, the posture adaptability scoring table, and the individual difference compensation value, a combination of morphological parameters is obtained;

[0178] In this embodiment of the invention, functional regions are divided and set according to the biomechanical support index table to obtain a functional region size table. According to the biomechanical support index table B={(zone ... i index i The pillow is divided into functional zones based on the following formula: |i=1,2,…,M}. These zones include a head support zone, a neck support zone, and a shoulder transition zone. The dimensions of each zone are determined according to the support index. Head support zone: Width and length are determined based on head weight and pressure distribution. Neck support zone: Width and height are determined based on cervical spine length and curvature. Shoulder transition zone: Width and angle are determined based on shoulder width and sleeping posture. The functional zone dimensions are represented as S={(zone ...}}. i width i , length i height i )|i=1,2,…,M}, where zone i Indicates the region type, width i Indicates width, length i Indicates length, height i Indicates altitude.

[0179] Calculate the set of zone height parameters based on the functional zone dimension table. Based on the functional zone dimension table, S = {(zone...}i width i , length i height i )|i=1,2,…,M}, calculate the set of region height parameters. The height of the head support zone is determined based on head weight and pressure distribution. The height of the neck support zone is determined based on cervical curvature and support requirements. The height of the shoulder transition zone is determined based on shoulder structure and sleeping posture. Calculate the height of each zone and set the height range. The region height parameter set is represented as H={(zone ...}}. i height_min i height_max i height_step i )|i=1,2,…,M}, where zone i Indicates the region type, height_min i The maximum height is represented by `height_max`. i The height_step represents the maximum height. i This represents the height step value.

[0180] Construct a set of contour curve equations based on the region height parameter set H={(zone i height_min i height_max i height_step i Construct the contour curve equations for each i = 1, 2, ..., M. The contour curve equations describe the shape of the pillow's side surface. Construct the contour curve equations using Bézier curves or spline curves. The control points of the Bézier curves are determined based on the region height parameter. Construct multiple curve equations, each corresponding to a different side surface shape. The contour curve equation system is represented as C = {C1(x), C2(x), ..., C}. n (x)}, where C i (x) represents the equation of the i-th curve.

[0181] The edge transition angles of the functional area size table are optimized based on the contour curve equations to obtain an edge transition angle table. This is based on the contour curve equations C={C1(x), C2(x), …C n (x)} and functional area size table S={(zone)} i width i , length i height iThe optimization involves finding the edge transition angles (i = 1, 2, ..., M) and optimizing the transition angles between different areas of the pillow. The edge transition angles are determined by adjusting the control points of the curve. The optimization goal is to match the edge transition angles to the shoulder structure and sleeping posture. Optimization algorithms, such as genetic algorithms or particle swarm optimization, are used. The edge transition angle table is represented as A = {(zone ...} | i = 1, 2, ..., M}. i , angle i )|i=1,2,…,M}, where zone i Indicates the region type, angle i Indicates the edge transition angle.

[0182] Postural adaptability is assessed based on the edge transition angle table, resulting in a postural adaptability scoring table. According to the edge transition angle table A={(zone... i , angle i The postural adaptability of a pillow is evaluated using the formula |i=1,2,…,M}. Postural adaptability refers to the pillow's support effect on different sleeping positions. Evaluation methods include simulating pressure distribution and cervical curvature under different sleeping positions. Finite element analysis (FEA) or experimental measurement methods are used. FEA simulation: A three-dimensional model of the pillow is built, and pressure and boundary conditions are applied. Experimental measurement: Children use the pillow, and pressure distribution and cervical curvature are measured. Scoring criteria are set for different sleeping positions. The postural adaptability rating scale is represented as P={(pose…M}|i=1,2,…,M}. i score i )|i=1,2,…,N}, where pose i Indicates the pose type, score i Indicates the rating.

[0183] Based on the postural adaptability rating scale, age-segment parameters were adjusted to obtain the age-segment parameter table. According to the postural adaptability rating scale, P={(pose...} i score i For each age group (i=1, 2, ..., N), adjust the parameters for each age group. Adjust the pillow's shape parameters, such as height, curvature, and firmness, according to the child's age group. Adjust the weighting of the postural adaptability score according to the age group. The age-segmented parameter table is represented as T={(age ...}}. i parameter i value i )|i=1, 2,…,A}, where age i Indicates age range, parameter i Indicates the parameter type, value i This represents the parameter value, where A represents the total number of age groups.

[0184] Individual difference compensation values ​​are calculated based on the age segmentation parameter table. Individual difference factors are considered when calculating the compensation values. These factors include head shape characteristics, sleep habits, and specific physical conditions. Head shape characteristics: Adjust pillow height and curvature according to head shape. Sleep habits: Adjust pillow support and material according to sleeping posture. Specific physical conditions: Adjust pillow material based on allergy history. Compensation values ​​can be expressed using coefficients or offsets. Calculation method: Adjust the age segmentation parameters based on individual difference factors.

[0185] The edge transition angle table, posture adaptability rating table, and individual difference compensation values ​​are integrated to obtain the morphological parameter combination. The edge transition angle table A, posture adaptability rating table P, and individual difference compensation values ​​are integrated. The morphological parameter combination includes height, curvature, edge transition angle, and support area width. The morphological parameter combination is represented as O = {(height_range, curvature, edge_angle, width)}.

[0186] Preferably, the present invention also provides a home textile recommendation system based on children's health data monitoring and analysis, used to execute the home textile recommendation method based on children's health data monitoring and analysis as described above, the home textile recommendation system based on children's health data monitoring and analysis comprising:

[0187] The three-dimensional modeling module for vital signs is used to collect the original point cloud coordinate set of children's sleeping postures; the cervical curvature parameter set is extracted based on the cervical curvature parameter set extracted from the spatial distribution map of key skeletal points; the cervical spine and body position are analyzed based on the cervical curvature parameter set to obtain cervical curvature-body position holographic data.

[0188] The partitioned pressure mapping module is used to collect static pressure baseline datasets based on cervical curvature-postural holographic data; perform postural-pressure correlation analysis based on the static pressure baseline datasets to obtain a postural-pressure mapping relationship table; and generate a pressure distribution index map based on the postural-pressure mapping relationship table.

[0189] The curvature restoration modeling module is used to quantify the curvature-support effect based on the pressure distribution index map to obtain the curvature deviation index set; and to analyze the pressure-curvature response relationship between the curvature deviation index set and the pressure distribution index map to obtain the curvature restoration adaptation factor.

[0190] The support matching reasoning module is used to acquire pillow material performance data; calculate the biomechanical support index table based on the pillow material performance data and curvature recovery adaptation factor; and make personalized pillow support recommendations based on the biomechanical support index table to obtain a set of recommended support parameters.

[0191] Therefore, the embodiments should be considered as exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of the equivalents of the application are intended to be included within the invention.

[0192] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

Claims

1. A home textile recommendation method based on child health data monitoring analysis, characterized in that, The method comprises the following steps: Step S1: collecting a raw point cloud coordinate set of a child's sleeping posture; extracting a cervical curvature parameter set according to the cervical curvature parameter set of the extracted skeleton key point spatial distribution diagram; and performing cervical vertebra and body position analysis according to the cervical curvature parameter set to obtain cervical curvature-body position holographic data; Step S2: collecting a static pressure baseline data set according to the cervical curvature-body position holographic data; performing body position-pressure correlation analysis according to the static pressure baseline data set to obtain a body position-pressure mapping relationship table; and generating a pressure distribution index atlas according to the body position-pressure mapping relationship table; wherein step S2 comprises the following steps: Step S21: performing accurate measurement of a contact area according to the cervical curvature-body position holographic data to obtain a contact area division diagram; Step S22: collecting a static pressure baseline data set according to the contact area division diagram; wherein collecting the static pressure baseline data set in step S22 specifically comprises: performing posture stability guidance collection according to the contact area division diagram to obtain a standard posture record table; collecting an original pressure data matrix according to the standard posture record table; extracting a regional pressure feature table of the original pressure data matrix; calculating a pressure uniformity distribution diagram according to the regional pressure feature table; performing pressure gradient analysis on the pressure uniformity distribution diagram to obtain a pressure gradient distribution diagram; performing anatomical structure pressure mapping according to the pressure gradient distribution diagram to obtain an anatomical pressure corresponding table; performing pressure data standardization processing according to the anatomical pressure corresponding table to obtain the static pressure baseline data set; Step S23: monitoring a dynamic pressure change sequence according to the static pressure baseline data set and the contact area division diagram; Step S24: calculating pressure uniformity according to the dynamic pressure change sequence and the static pressure baseline data set to obtain a pressure uniformity distribution matrix; Step S25: performing body position-pressure correlation analysis on the dynamic pressure change sequence and the cervical curvature-body position holographic data to obtain a body position-pressure mapping relationship table; Step S26: performing pressure peak value distribution analysis according to the body position-pressure mapping relationship table and the pressure uniformity distribution matrix to obtain a pressure peak value distribution feature diagram; Step S27: calculating a pressure distribution index atlas according to the pressure uniformity distribution matrix, the body position-pressure mapping relationship table and the pressure peak value distribution feature diagram; Step S3: performing curvature-support effect quantification according to the pressure distribution index atlas to obtain a curvature deviation index set; performing pressure-curvature response relationship analysis on the curvature deviation index set and the pressure distribution index atlas to obtain a curvature recovery adaptation factor; Step S4: obtaining pillow material performance data; calculating a biomechanical support index table according to the pillow material performance data and the curvature recovery adaptation factor; performing pillow support individualization recommendation according to the biomechanical support index table to obtain a recommended support parameter set; wherein the pillow support individualization recommendation in step S4 comprises: performing pillow form parameter optimization according to the biomechanical support index table and the curvature recovery adaptation factor to obtain a form parameter combination; wherein the pillow form parameter optimization specifically comprises: performing functional region division setting according to the biomechanical support index table to obtain a functional region size table; calculating a regional height parameter set according to the functional region size table; Constructing a contour curve equation set according to the regional height parameter set; Optimizing the edge transition angle table according to the contour curve equation set; Performing posture adaptability evaluation according to the edge transition angle table to obtain a posture adaptability score table; Adjusting the age segmentation parameters according to the posture adaptability score table to obtain an age segmentation parameter table; Calculating individual difference compensation values according to the age segmentation parameter table; Integrating the edge transition angle table, the posture adaptability score table, and the individual difference compensation values to obtain a shape parameter combination; Performing pillow material combination according to the shape parameter combination and the biomechanical support index table to obtain a material combination scheme; Calculating a personalized adjustment parameter table according to the material combination scheme and the shape parameter combination; Generating comprehensive recommended parameters according to the shape parameter combination, the material combination scheme, and the personalized adjustment parameter table to obtain a recommended support parameter set.

2. The home textile recommendation method based on child health data monitoring analysis according to claim 1, characterized in that, Step S1 includes the following steps: Step S11: obtaining a natural sleeping posture state of a child through a high-speed camera and performing multi-angle optical scanning on the natural sleeping posture state of the child to obtain an original point cloud coordinate set; Step S12: positioning key points of a skeleton on the original point cloud coordinate set and drawing a skeleton key point spatial distribution map; Step S13: extracting a cervical curvature parameter set of the skeleton key point spatial distribution map; Step S14: performing head-neck ratio measurement analysis according to the skeleton key point spatial distribution map and the cervical curvature parameter set to obtain head-neck mechanical ratio data; Step S15: measuring multi-dimensional angle parameters of a head-bed included angle, a cervical vertebra-shoulder line angle, and a cervical vertebra axis-horizon included angle according to the cervical curvature parameter set and the head-neck mechanical ratio data, and constructing a multi-dimensional posture angle matrix; Step S16: performing holographic data integration standardization on the cervical curvature parameter set and the multi-dimensional posture angle matrix to obtain cervical curvature-posture holographic data. 3.The home textile recommendation method based on child health data monitoring analysis according to claim 2, characterized in that, The step S13 of extracting the cervical curvature parameter set of the skeleton key point spatial distribution map includes: extracting a cervical center line track according to the skeleton key point spatial distribution map; performing multi-plane curvature calculation on the cervical center line track to obtain a three-plane curvature distribution map; measuring key segment angle values of the three-plane curvature distribution map; performing curve length and shape measurement according to the cervical center line track and the key segment angle values to obtain a curve shape feature set; performing standard curve deviation analysis on the curve shape feature set to obtain a curvature standard deviation value; performing stress distribution estimation according to the curvature standard deviation value to obtain a cervical stress distribution map; performing dynamic change characteristic measurement according to the cervical center line track and the curve shape feature set to obtain a curvature dynamic change characteristic; constructing the cervical curvature parameter set according to the three-plane curvature distribution map, the key segment angle values, the curve shape feature set, the curvature standard deviation value, the cervical stress distribution map, and the curvature dynamic change characteristic.

4. The home textile recommendation method based on child health data monitoring analysis according to claim 3, characterized in that, The step S25 of posture-pressure correlation analysis includes: performing time sequence synchronization processing on the dynamic pressure change sequence and the cervical curvature-posture holographic data to obtain a time synchronization data pair; performing spatial coordinate mapping conversion on the time synchronization data pair to obtain a spatial corresponding mapping matrix; The standard body position state is extracted according to the space corresponding mapping matrix and the time synchronization data pair, and a standard body position pressure feature is obtained; The pressure transfer trajectory set is calculated according to the standard body position pressure feature, and a regional pressure response time delay table is obtained; The pressure response time delay of the pressure transfer trajectory set is measured, and a regional pressure response time delay table is obtained; The body position change influence coefficient table is calculated according to the regional pressure response time delay table and the pressure transfer trajectory set; The body position-pressure mapping relationship table is constructed according to the body position change influence coefficient table.

5. The home textile recommendation method based on child health data monitoring analysis according to claim 1, characterized in that, The curvature-support effect quantification in step S3 includes: The age staging reference standard of cervical spine development is obtained by establishing an age staging standard according to the pressure distribution index atlas and the cervical spine curvature-body position holographic data; The ideal curvature model is constructed according to the cervical spine development staging reference standard and the cervical spine curvature-body position holographic data, and an age staging ideal curvature model is obtained; The actual support effect is measured according to the age staging ideal curvature model and the pressure distribution index atlas, and a dynamic curvature change trajectory is obtained; The curvature deviation index set is obtained by quantitatively analyzing the curvature deviation of the dynamic curvature change trajectory and the age staging ideal curvature model.

6. The home textile recommendation method based on child health data monitoring analysis according to claim 1, characterized in that, The pressure-curvature response relationship analysis in step S3 includes: The pressure-curvature synchronous time series data is obtained by collecting high-frequency synchronous data from the pressure distribution index atlas; the windowed change rate data set is obtained by performing time window segmentation processing on the pressure-curvature synchronous time series data; The key pressure region is divided according to the windowed change rate data set and the pressure distribution index atlas, and a functional region pressure feature table is obtained; The regional sensitivity is measured according to the functional region pressure feature table, and a regional curvature sensitivity coefficient table is obtained; The critical pressure point position map is obtained by identifying the critical pressure point according to the regional curvature sensitivity coefficient table and the functional region pressure feature table; The point-curve mapping function set is obtained by constructing the pressure-curvature mapping function according to the critical pressure point position map; The regional response time delay table is obtained by analyzing the time delay characteristics according to the point-curve mapping function set; The pressure-curvature response matrix is generated according to the regional response time delay table; The curvature recovery degree score table is obtained by calculating the recovery degree score according to the pressure-curvature response matrix and the curvature deviation index set; The curvature recovery adaptation factor is obtained by generating the adaptation factor according to the curvature recovery degree score table and the pressure-curvature response matrix.

7. The home textile recommendation method based on child health data monitoring analysis according to claim 1, characterized in that, The calculation of the biomechanical support index table in step S4 includes: The material performance parameter library is constructed according to the pillow material performance data; the material resilience response analysis is performed according to the material performance parameter library and the curvature recovery adaptation factor, and a material resilience characteristic evaluation table is obtained; The head and neck biomechanical parameter set is collected according to the curvature recovery adaptation factor; the regional ideal support force table is calculated according to the head and neck biomechanical parameter set; The material support force curve set is measured according to the regional ideal support force table; The regional support matching degree index is calculated according to the material support force curve set; The posture difference analysis is performed according to the regional support matching degree index, and a posture support correction coefficient is obtained; The sleep posture proportion table is obtained by monitoring and analyzing the sleep posture proportion according to the posture support correction coefficient; The support stability coefficient is evaluated according to the sleep posture proportion table; According to the regional support matching degree index, the posture support correction coefficient, the sleep posture time proportion table and the support stability coefficient, a comprehensive support index is calculated to obtain a biomechanical support index table.

8. A home textile recommendation system based on child health data monitoring analysis, characterized in that, The home textile recommendation method based on child health data monitoring analysis is used to execute the method according to claim 1, and the home textile recommendation system based on child health data monitoring analysis comprises: The sign three-dimensional modeling module is used to collect the original point cloud coordinate set of the child sleep posture; the cervical curvature parameter group is extracted according to the cervical curvature parameter group of the extracted skeleton key point space distribution diagram; the cervical vertebra and the body position are analyzed according to the cervical curvature parameter group to obtain the cervical curvature-body position holographic data; The partition pressure mapping module is used to collect the static pressure baseline data set according to the cervical curvature-body position holographic data; the body position-pressure correlation analysis is performed according to the static pressure baseline data set to obtain the body position-pressure mapping relationship table; and the pressure distribution index atlas is generated according to the body position-pressure mapping relationship table; The curvature recovery modeling module is used to perform curvature-support effect quantification according to the pressure distribution index atlas to obtain the curvature deviation index set; the pressure-curvature response relationship analysis is performed on the curvature deviation index set and the pressure distribution index atlas to obtain the curvature recovery adaptation factor; The support matching reasoning module is used to obtain the pillow material performance data; the biomechanical support index table is calculated according to the pillow material performance data and the curvature recovery adaptation factor; the pillow support individualization recommendation is performed according to the biomechanical support index table to obtain the recommended support parameter set.

Images